2023-11-16 16:49:47,541 - mmdet - INFO - Environment info: ------------------------------------------------------------ sys.platform: linux Python: 3.8.17 (default, Jul 5 2023, 21:04:15) [GCC 11.2.0] CUDA available: True GPU 0,1,2,3,4,5,6,7: NVIDIA A100-SXM4-80GB CUDA_HOME: /mnt/petrelfs/share/cuda-11.3 NVCC: Cuda compilation tools, release 11.3, V11.3.109 GCC: gcc (GCC) 7.5.0 PyTorch: 1.12.0 PyTorch compiling details: PyTorch built with: - GCC 9.3 - C++ Version: 201402 - Intel(R) oneAPI Math Kernel Library Version 2023.1-Product Build 20230303 for Intel(R) 64 architecture applications - Intel(R) MKL-DNN v2.6.0 (Git Hash 52b5f107dd9cf10910aaa19cb47f3abf9b349815) - OpenMP 201511 (a.k.a. OpenMP 4.5) - LAPACK is enabled (usually provided by MKL) - NNPACK is enabled - CPU capability usage: AVX2 - CUDA Runtime 11.3 - NVCC architecture flags: -gencode;arch=compute_37,code=sm_37;-gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_61,code=sm_61;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-gencode;arch=compute_80,code=sm_80;-gencode;arch=compute_86,code=sm_86;-gencode;arch=compute_37,code=compute_37 - CuDNN 8.3.2 (built against CUDA 11.5) - Magma 2.5.2 - Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.3, CUDNN_VERSION=8.3.2, CXX_COMPILER=/opt/rh/devtoolset-9/root/usr/bin/c++, CXX_FLAGS= -Wno-deprecated -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -fopenmp -DNDEBUG -DUSE_KINETO -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DSYMBOLICATE_MOBILE_DEBUG_HANDLE -DEDGE_PROFILER_USE_KINETO -O2 -fPIC -Wno-narrowing -Wall -Wextra -Werror=return-type -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wno-unused-parameter -Wno-unused-function -Wno-unused-result -Wno-unused-local-typedefs -Wno-strict-overflow -Wno-strict-aliasing -Wno-error=deprecated-declarations -Wno-stringop-overflow -Wno-psabi -Wno-error=pedantic -Wno-error=redundant-decls -Wno-error=old-style-cast -fdiagnostics-color=always -faligned-new -Wno-unused-but-set-variable -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Werror=format -Werror=cast-function-type -Wno-stringop-overflow, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, TORCH_VERSION=1.12.0, USE_CUDA=ON, USE_CUDNN=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=OFF, USE_MPI=OFF, USE_NCCL=ON, USE_NNPACK=ON, USE_OPENMP=ON, USE_ROCM=OFF, TorchVision: 0.13.0 OpenCV: 4.8.0 MMCV: 1.5.0 MMCV Compiler: GCC 7.5 MMCV CUDA Compiler: 11.3 MMDetection: 2.28.1+13b586e ------------------------------------------------------------ 2023-11-16 16:49:50,216 - mmdet - INFO - Distributed training: True 2023-11-16 16:49:53,003 - mmdet - INFO - Config: model = dict( type='MaskRCNN', backbone=dict( type='Flash_InternImage_nsmx', core_op='FlashDCNv3', channels=112, depths=[4, 4, 21, 4], groups=[7, 14, 28, 56], mlp_ratio=4.0, drop_path_rate=0.4, norm_layer='LN', layer_scale=1.0, offset_scale=0.5, post_norm=True, with_cp=True, op_bias=True, out_indices=(0, 1, 2, 3), init_cfg=dict( type='Pretrained', checkpoint= '/mnt/petrelfs/share_data/xiongyuwen/checkpoint/flash_internimage_b_1k_224_nosmx_dw/ckpt_epoch_ema_best.pth' )), neck=dict( type='FPN_vitdet', in_channels=[112, 224, 448, 896], out_channels=256, num_outs=5, norm_cfg=dict(type='LN', requires_grad=True), use_residual=True), rpn_head=dict( type='RPNHead', in_channels=256, feat_channels=256, anchor_generator=dict( type='AnchorGenerator', scales=[8], ratios=[0.5, 1.0, 2.0], strides=[4, 8, 16, 32, 64]), bbox_coder=dict( type='DeltaXYWHBBoxCoder', target_means=[0.0, 0.0, 0.0, 0.0], target_stds=[1.0, 1.0, 1.0, 1.0]), loss_cls=dict( type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0), loss_bbox=dict(type='L1Loss', loss_weight=1.0)), roi_head=dict( type='StandardRoIHead', bbox_roi_extractor=dict( type='SingleRoIExtractor', roi_layer=dict(type='RoIAlign', output_size=7, sampling_ratio=0), out_channels=256, featmap_strides=[4, 8, 16, 32]), bbox_head=dict( type='Shared2FCBBoxHead', in_channels=256, fc_out_channels=1024, roi_feat_size=7, num_classes=80, bbox_coder=dict( type='DeltaXYWHBBoxCoder', target_means=[0.0, 0.0, 0.0, 0.0], target_stds=[0.1, 0.1, 0.2, 0.2]), reg_class_agnostic=False, loss_cls=dict( type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0), loss_bbox=dict(type='L1Loss', loss_weight=1.0)), mask_roi_extractor=dict( type='SingleRoIExtractor', roi_layer=dict(type='RoIAlign', output_size=14, sampling_ratio=0), out_channels=256, featmap_strides=[4, 8, 16, 32]), mask_head=dict( type='FCNMaskHead', num_convs=4, in_channels=256, conv_out_channels=256, num_classes=80, loss_mask=dict( type='CrossEntropyLoss', use_mask=True, loss_weight=1.0))), train_cfg=dict( rpn=dict( assigner=dict( type='MaxIoUAssigner', pos_iou_thr=0.7, neg_iou_thr=0.3, min_pos_iou=0.3, match_low_quality=True, ignore_iof_thr=-1), sampler=dict( type='RandomSampler', num=256, pos_fraction=0.5, neg_pos_ub=-1, add_gt_as_proposals=False), allowed_border=-1, pos_weight=-1, debug=False), rpn_proposal=dict( nms_pre=2000, max_per_img=1000, nms=dict(type='nms', iou_threshold=0.7), min_bbox_size=0), rcnn=dict( assigner=dict( type='MaxIoUAssigner', pos_iou_thr=0.5, neg_iou_thr=0.5, min_pos_iou=0.5, match_low_quality=True, ignore_iof_thr=-1), sampler=dict( type='RandomSampler', num=512, pos_fraction=0.25, neg_pos_ub=-1, add_gt_as_proposals=True), mask_size=28, pos_weight=-1, debug=False)), test_cfg=dict( rpn=dict( nms_pre=1000, max_per_img=1000, nms=dict(type='nms', iou_threshold=0.7), min_bbox_size=0), rcnn=dict( score_thr=0.05, nms=dict(type='nms', iou_threshold=0.5), max_per_img=100, mask_thr_binary=0.5))) dataset_type = 'CocoDataset' data_root = 'data/coco/' img_norm_cfg = dict( mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True) train_pipeline = [ dict(type='LoadImageFromFile'), dict(type='LoadAnnotations', with_bbox=True, with_mask=True), dict(type='RandomFlip', flip_ratio=0.5), dict( type='AutoAugment', policies=[[{ 'type': 'Resize', 'img_scale': [(480, 1333), (512, 1333), (544, 1333), (576, 1333), (608, 1333), (640, 1333), (672, 1333), (704, 1333), (736, 1333), (768, 1333), (800, 1333)], 'multiscale_mode': 'value', 'keep_ratio': True }], [{ 'type': 'Resize', 'img_scale': [(400, 1333), (500, 1333), (600, 1333)], 'multiscale_mode': 'value', 'keep_ratio': True }, { 'type': 'RandomCrop', 'crop_type': 'absolute_range', 'crop_size': (384, 600), 'allow_negative_crop': True }, { 'type': 'Resize', 'img_scale': [(480, 1333), (512, 1333), (544, 1333), (576, 1333), (608, 1333), (640, 1333), (672, 1333), (704, 1333), (736, 1333), (768, 1333), (800, 1333)], 'multiscale_mode': 'value', 'override': True, 'keep_ratio': True }]]), dict( type='Normalize', mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True), dict(type='Pad', size_divisor=32), dict(type='DefaultFormatBundle'), dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']) ] test_pipeline = [ dict(type='LoadImageFromFile'), dict( type='MultiScaleFlipAug', img_scale=(1333, 800), flip=False, transforms=[ dict(type='Resize', keep_ratio=True), dict(type='RandomFlip'), dict( type='Normalize', mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True), dict(type='Pad', size_divisor=32), dict(type='ImageToTensor', keys=['img']), dict(type='Collect', keys=['img']) ]) ] data = dict( samples_per_gpu=4, workers_per_gpu=2, train=dict( type='CocoDataset', ann_file='data/coco/annotations/instances_train2017.json', img_prefix='data/coco/train2017/', pipeline=[ dict(type='LoadImageFromFile'), dict(type='LoadAnnotations', with_bbox=True, with_mask=True), dict(type='RandomFlip', flip_ratio=0.5), dict( type='AutoAugment', policies=[[{ 'type': 'Resize', 'img_scale': [(480, 1333), (512, 1333), (544, 1333), (576, 1333), (608, 1333), (640, 1333), (672, 1333), (704, 1333), (736, 1333), (768, 1333), (800, 1333)], 'multiscale_mode': 'value', 'keep_ratio': True }], [{ 'type': 'Resize', 'img_scale': [(400, 1333), (500, 1333), (600, 1333)], 'multiscale_mode': 'value', 'keep_ratio': True }, { 'type': 'RandomCrop', 'crop_type': 'absolute_range', 'crop_size': (384, 600), 'allow_negative_crop': True }, { 'type': 'Resize', 'img_scale': [(480, 1333), (512, 1333), (544, 1333), (576, 1333), (608, 1333), (640, 1333), (672, 1333), (704, 1333), (736, 1333), (768, 1333), (800, 1333)], 'multiscale_mode': 'value', 'override': True, 'keep_ratio': True }]]), dict( type='Normalize', mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True), dict(type='Pad', size_divisor=32), dict(type='DefaultFormatBundle'), dict( type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']) ]), val=dict( type='CocoDataset', ann_file='data/coco/annotations/instances_val2017.json', img_prefix='data/coco/val2017/', pipeline=[ dict(type='LoadImageFromFile'), dict( type='MultiScaleFlipAug', img_scale=(1333, 800), flip=False, transforms=[ dict(type='Resize', keep_ratio=True), dict(type='RandomFlip'), dict( type='Normalize', mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True), dict(type='Pad', size_divisor=32), dict(type='ImageToTensor', keys=['img']), dict(type='Collect', keys=['img']) ]) ]), test=dict( type='CocoDataset', ann_file='data/coco/annotations/instances_val2017.json', img_prefix='data/coco/val2017/', pipeline=[ dict(type='LoadImageFromFile'), dict( type='MultiScaleFlipAug', img_scale=(1333, 800), flip=False, transforms=[ dict(type='Resize', keep_ratio=True), dict(type='RandomFlip'), dict( type='Normalize', mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True), dict(type='Pad', size_divisor=32), dict(type='ImageToTensor', keys=['img']), dict(type='Collect', keys=['img']) ]) ])) evaluation = dict(metric=['bbox', 'segm'], classwise=True, save_best='auto') optimizer = dict( type='AdamW', lr=0.0002, weight_decay=0.05, constructor='CustomLayerDecayOptimizerConstructor', paramwise_cfg=dict( num_layers=33, layer_decay_rate=0.9, depths=[4, 4, 21, 4], offset_lr_scale=0.01)) optimizer_config = dict(grad_clip=None) lr_config = dict( policy='step', warmup='linear', warmup_iters=500, warmup_ratio=0.001, step=[27, 33]) runner = dict(type='EpochBasedRunner', max_epochs=36) checkpoint_config = dict(interval=1, max_keep_ckpts=1, save_last=True) log_config = dict(interval=50, hooks=[dict(type='TextLoggerHook')]) custom_hooks = [dict(type='NumClassCheckHook')] dist_params = dict(backend='nccl') log_level = 'INFO' load_from = None resume_from = None workflow = [('train', 1)] pretrained = '/mnt/petrelfs/share_data/xiongyuwen/checkpoint/flash_internimage_b_1k_224_nosmx_dw/ckpt_epoch_ema_best.pth' norm_cfg = dict(type='LN', requires_grad=True) work_dir = 'work_dirs/mask_rcnn_flash_internimage_b_fpn_3x_cocoo_0.4_0.9_4x16/' auto_resume = False gpu_ids = range(0, 16) 2023-11-16 16:49:56,964 - mmdet - INFO - Set random seed to 1869077043, deterministic: False 2023-11-16 16:49:56,965 - mmdet - INFO - using core type: FlashDCNv3 2023-11-16 16:49:56,965 - mmdet - INFO - using activation layer: GELU 2023-11-16 16:49:56,965 - mmdet - INFO - using main norm layer: LN 2023-11-16 16:49:56,965 - mmdet - INFO - using dpr: linear, 0.4 2023-11-16 16:49:56,965 - mmdet - INFO - level2_post_norm: False 2023-11-16 16:49:56,965 - mmdet - INFO - level2_post_norm_block_ids: None 2023-11-16 16:49:56,965 - mmdet - INFO - res_post_norm: False 2023-11-16 16:50:27,567 - mmdet - INFO - load checkpoint from local path: /mnt/petrelfs/share_data/xiongyuwen/checkpoint/flash_internimage_b_1k_224_nosmx_dw/ckpt_epoch_ema_best.pth 2023-11-16 16:50:31,783 - mmdet - INFO - _IncompatibleKeys(missing_keys=[], unexpected_keys=['conv_head.0.weight', 'conv_head.1.0.weight', 'conv_head.1.0.bias', 'conv_head.1.0.running_mean', 'conv_head.1.0.running_var', 'conv_head.1.0.num_batches_tracked', 'head.weight', 'head.bias']) 2023-11-16 16:50:35,570 - mmdet - INFO - initialize FPN_vitdet with init_cfg {'type': 'Xavier', 'layer': 'Conv2d', 'distribution': 'uniform'} 2023-11-16 16:50:35,925 - mmdet - INFO - initialize RPNHead with init_cfg {'type': 'Normal', 'layer': 'Conv2d', 'std': 0.01} 2023-11-16 16:50:35,971 - mmdet - INFO - initialize Shared2FCBBoxHead with init_cfg [{'type': 'Normal', 'std': 0.01, 'override': {'name': 'fc_cls'}}, {'type': 'Normal', 'std': 0.001, 'override': {'name': 'fc_reg'}}, {'type': 'Xavier', 'distribution': 'uniform', 'override': [{'name': 'shared_fcs'}, {'name': 'cls_fcs'}, {'name': 'reg_fcs'}]}] Name of parameter - Initialization information backbone.patch_embed.conv1.weight - torch.Size([56, 3, 3, 3]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.patch_embed.conv1.bias - torch.Size([56]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.patch_embed.norm1.1.weight - torch.Size([56]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.patch_embed.norm1.1.bias - torch.Size([56]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.patch_embed.conv2.weight - torch.Size([112, 56, 3, 3]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.patch_embed.conv2.bias - torch.Size([112]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.patch_embed.norm2.1.weight - torch.Size([112]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.patch_embed.norm2.1.bias - torch.Size([112]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.0.gamma1 - torch.Size([112]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.0.gamma2 - torch.Size([112]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.0.norm1.0.weight - torch.Size([112]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.0.norm1.0.bias - torch.Size([112]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.0.dcn.offset_mask_dw.weight - torch.Size([112, 1, 3, 3]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.0.dcn.offset_mask_dw.bias - torch.Size([112]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.0.dcn.offset_mask.weight - torch.Size([189, 112]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.0.dcn.offset_mask.bias - torch.Size([189]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.0.dcn.value_proj.weight - torch.Size([112, 112]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.0.dcn.value_proj.bias - torch.Size([112]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.0.dcn.output_proj.weight - torch.Size([112, 112]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.0.norm2.0.weight - torch.Size([112]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.0.norm2.0.bias - torch.Size([112]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.0.mlp.fc1.weight - torch.Size([448, 112]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.0.mlp.fc1.bias - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.0.mlp.fc2.weight - torch.Size([112, 448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.1.gamma1 - torch.Size([112]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.1.gamma2 - torch.Size([112]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.1.norm1.0.weight - torch.Size([112]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.1.norm1.0.bias - torch.Size([112]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.1.dcn.offset_mask_dw.weight - torch.Size([112, 1, 3, 3]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.1.dcn.offset_mask_dw.bias - torch.Size([112]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.1.dcn.offset_mask.weight - torch.Size([189, 112]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.1.dcn.offset_mask.bias - torch.Size([189]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.1.dcn.value_proj.weight - torch.Size([112, 112]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.1.dcn.value_proj.bias - torch.Size([112]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.1.dcn.output_proj.weight - torch.Size([112, 112]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.1.norm2.0.weight - torch.Size([112]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.1.norm2.0.bias - torch.Size([112]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.1.mlp.fc1.weight - torch.Size([448, 112]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.1.mlp.fc1.bias - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.1.mlp.fc2.weight - torch.Size([112, 448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.2.gamma1 - torch.Size([112]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.2.gamma2 - torch.Size([112]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.2.norm1.0.weight - torch.Size([112]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.2.norm1.0.bias - torch.Size([112]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.2.dcn.offset_mask_dw.weight - torch.Size([112, 1, 3, 3]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.2.dcn.offset_mask_dw.bias - torch.Size([112]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.2.dcn.offset_mask.weight - torch.Size([189, 112]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.2.dcn.offset_mask.bias - torch.Size([189]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.2.dcn.value_proj.weight - torch.Size([112, 112]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.2.dcn.value_proj.bias - torch.Size([112]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.2.dcn.output_proj.weight - torch.Size([112, 112]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.2.norm2.0.weight - torch.Size([112]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.2.norm2.0.bias - torch.Size([112]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.2.mlp.fc1.weight - torch.Size([448, 112]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.2.mlp.fc1.bias - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.2.mlp.fc2.weight - torch.Size([112, 448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.3.gamma1 - torch.Size([112]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.3.gamma2 - torch.Size([112]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.3.norm1.0.weight - torch.Size([112]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.3.norm1.0.bias - torch.Size([112]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.3.dcn.offset_mask_dw.weight - torch.Size([112, 1, 3, 3]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.3.dcn.offset_mask_dw.bias - torch.Size([112]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.3.dcn.offset_mask.weight - torch.Size([189, 112]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.3.dcn.offset_mask.bias - torch.Size([189]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.3.dcn.value_proj.weight - torch.Size([112, 112]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.3.dcn.value_proj.bias - torch.Size([112]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.3.dcn.output_proj.weight - torch.Size([112, 112]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.3.norm2.0.weight - torch.Size([112]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.3.norm2.0.bias - torch.Size([112]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.3.mlp.fc1.weight - torch.Size([448, 112]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.3.mlp.fc1.bias - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.3.mlp.fc2.weight - torch.Size([112, 448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.downsample.conv.weight - torch.Size([224, 112, 3, 3]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.downsample.norm.1.weight - torch.Size([224]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.downsample.norm.1.bias - torch.Size([224]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.0.gamma1 - torch.Size([224]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.0.gamma2 - torch.Size([224]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.0.norm1.0.weight - torch.Size([224]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.0.norm1.0.bias - torch.Size([224]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.0.dcn.offset_mask_dw.weight - torch.Size([224, 1, 3, 3]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.0.dcn.offset_mask_dw.bias - torch.Size([224]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.0.dcn.offset_mask.weight - torch.Size([378, 224]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.0.dcn.offset_mask.bias - torch.Size([378]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.0.dcn.value_proj.weight - torch.Size([224, 224]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.0.dcn.value_proj.bias - torch.Size([224]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.0.dcn.output_proj.weight - torch.Size([224, 224]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.0.norm2.0.weight - torch.Size([224]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.0.norm2.0.bias - torch.Size([224]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.0.mlp.fc1.weight - torch.Size([896, 224]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.0.mlp.fc1.bias - torch.Size([896]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.0.mlp.fc2.weight - torch.Size([224, 896]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.1.gamma1 - torch.Size([224]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.1.gamma2 - torch.Size([224]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.1.norm1.0.weight - torch.Size([224]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.1.norm1.0.bias - torch.Size([224]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.1.dcn.offset_mask_dw.weight - torch.Size([224, 1, 3, 3]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.1.dcn.offset_mask_dw.bias - torch.Size([224]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.1.dcn.offset_mask.weight - torch.Size([378, 224]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.1.dcn.offset_mask.bias - torch.Size([378]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.1.dcn.value_proj.weight - torch.Size([224, 224]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.1.dcn.value_proj.bias - torch.Size([224]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.1.dcn.output_proj.weight - torch.Size([224, 224]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.1.norm2.0.weight - torch.Size([224]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.1.norm2.0.bias - torch.Size([224]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.1.mlp.fc1.weight - torch.Size([896, 224]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.1.mlp.fc1.bias - torch.Size([896]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.1.mlp.fc2.weight - torch.Size([224, 896]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.2.gamma1 - torch.Size([224]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.2.gamma2 - torch.Size([224]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.2.norm1.0.weight - torch.Size([224]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.2.norm1.0.bias - torch.Size([224]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.2.dcn.offset_mask_dw.weight - torch.Size([224, 1, 3, 3]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.2.dcn.offset_mask_dw.bias - torch.Size([224]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.2.dcn.offset_mask.weight - torch.Size([378, 224]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.2.dcn.offset_mask.bias - torch.Size([378]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.2.dcn.value_proj.weight - torch.Size([224, 224]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.2.dcn.value_proj.bias - torch.Size([224]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.2.dcn.output_proj.weight - torch.Size([224, 224]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.2.norm2.0.weight - torch.Size([224]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.2.norm2.0.bias - torch.Size([224]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.2.mlp.fc1.weight - torch.Size([896, 224]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.2.mlp.fc1.bias - torch.Size([896]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.2.mlp.fc2.weight - torch.Size([224, 896]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.3.gamma1 - torch.Size([224]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.3.gamma2 - torch.Size([224]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.3.norm1.0.weight - torch.Size([224]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.3.norm1.0.bias - torch.Size([224]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.3.dcn.offset_mask_dw.weight - torch.Size([224, 1, 3, 3]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.3.dcn.offset_mask_dw.bias - torch.Size([224]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.3.dcn.offset_mask.weight - torch.Size([378, 224]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.3.dcn.offset_mask.bias - torch.Size([378]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.3.dcn.value_proj.weight - torch.Size([224, 224]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.3.dcn.value_proj.bias - torch.Size([224]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.3.dcn.output_proj.weight - torch.Size([224, 224]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.3.norm2.0.weight - torch.Size([224]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.3.norm2.0.bias - torch.Size([224]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.3.mlp.fc1.weight - torch.Size([896, 224]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.3.mlp.fc1.bias - torch.Size([896]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.3.mlp.fc2.weight - torch.Size([224, 896]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.downsample.conv.weight - torch.Size([448, 224, 3, 3]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.downsample.norm.1.weight - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.downsample.norm.1.bias - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.0.gamma1 - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.0.gamma2 - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.0.norm1.0.weight - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.0.norm1.0.bias - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.0.dcn.offset_mask_dw.weight - torch.Size([448, 1, 3, 3]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.0.dcn.offset_mask_dw.bias - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.0.dcn.offset_mask.weight - torch.Size([756, 448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.0.dcn.offset_mask.bias - torch.Size([756]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.0.dcn.value_proj.weight - torch.Size([448, 448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.0.dcn.value_proj.bias - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.0.dcn.output_proj.weight - torch.Size([448, 448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.0.norm2.0.weight - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.0.norm2.0.bias - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.0.mlp.fc1.weight - torch.Size([1792, 448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.0.mlp.fc1.bias - torch.Size([1792]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.0.mlp.fc2.weight - torch.Size([448, 1792]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.1.gamma1 - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.1.gamma2 - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.1.norm1.0.weight - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.1.norm1.0.bias - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.1.dcn.offset_mask_dw.weight - torch.Size([448, 1, 3, 3]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.1.dcn.offset_mask_dw.bias - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.1.dcn.offset_mask.weight - torch.Size([756, 448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.1.dcn.offset_mask.bias - torch.Size([756]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.1.dcn.value_proj.weight - torch.Size([448, 448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.1.dcn.value_proj.bias - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.1.dcn.output_proj.weight - torch.Size([448, 448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.1.norm2.0.weight - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.1.norm2.0.bias - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.1.mlp.fc1.weight - torch.Size([1792, 448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.1.mlp.fc1.bias - torch.Size([1792]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.1.mlp.fc2.weight - torch.Size([448, 1792]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.2.gamma1 - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.2.gamma2 - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.2.norm1.0.weight - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.2.norm1.0.bias - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.2.dcn.offset_mask_dw.weight - torch.Size([448, 1, 3, 3]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.2.dcn.offset_mask_dw.bias - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.2.dcn.offset_mask.weight - torch.Size([756, 448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.2.dcn.offset_mask.bias - torch.Size([756]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.2.dcn.value_proj.weight - torch.Size([448, 448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.2.dcn.value_proj.bias - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.2.dcn.output_proj.weight - torch.Size([448, 448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.2.norm2.0.weight - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.2.norm2.0.bias - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.2.mlp.fc1.weight - torch.Size([1792, 448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.2.mlp.fc1.bias - torch.Size([1792]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.2.mlp.fc2.weight - torch.Size([448, 1792]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.3.gamma1 - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.3.gamma2 - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.3.norm1.0.weight - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.3.norm1.0.bias - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.3.dcn.offset_mask_dw.weight - torch.Size([448, 1, 3, 3]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.3.dcn.offset_mask_dw.bias - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.3.dcn.offset_mask.weight - torch.Size([756, 448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.3.dcn.offset_mask.bias - torch.Size([756]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.3.dcn.value_proj.weight - torch.Size([448, 448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.3.dcn.value_proj.bias - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.3.dcn.output_proj.weight - torch.Size([448, 448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.3.norm2.0.weight - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.3.norm2.0.bias - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.3.mlp.fc1.weight - torch.Size([1792, 448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.3.mlp.fc1.bias - torch.Size([1792]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.3.mlp.fc2.weight - torch.Size([448, 1792]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.4.gamma1 - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.4.gamma2 - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.4.norm1.0.weight - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.4.norm1.0.bias - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.4.dcn.offset_mask_dw.weight - torch.Size([448, 1, 3, 3]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.4.dcn.offset_mask_dw.bias - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.4.dcn.offset_mask.weight - torch.Size([756, 448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.4.dcn.offset_mask.bias - torch.Size([756]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.4.dcn.value_proj.weight - torch.Size([448, 448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.4.dcn.value_proj.bias - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.4.dcn.output_proj.weight - torch.Size([448, 448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.4.norm2.0.weight - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.4.norm2.0.bias - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.4.mlp.fc1.weight - torch.Size([1792, 448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.4.mlp.fc1.bias - torch.Size([1792]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.4.mlp.fc2.weight - torch.Size([448, 1792]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.5.gamma1 - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.5.gamma2 - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.5.norm1.0.weight - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.5.norm1.0.bias - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.5.dcn.offset_mask_dw.weight - torch.Size([448, 1, 3, 3]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.5.dcn.offset_mask_dw.bias - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.5.dcn.offset_mask.weight - torch.Size([756, 448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.5.dcn.offset_mask.bias - torch.Size([756]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.5.dcn.value_proj.weight - torch.Size([448, 448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.5.dcn.value_proj.bias - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.5.dcn.output_proj.weight - torch.Size([448, 448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.5.norm2.0.weight - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.5.norm2.0.bias - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.5.mlp.fc1.weight - torch.Size([1792, 448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.5.mlp.fc1.bias - torch.Size([1792]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.5.mlp.fc2.weight - torch.Size([448, 1792]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.6.gamma1 - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.6.gamma2 - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.6.norm1.0.weight - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.6.norm1.0.bias - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.6.dcn.offset_mask_dw.weight - torch.Size([448, 1, 3, 3]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.6.dcn.offset_mask_dw.bias - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.6.dcn.offset_mask.weight - torch.Size([756, 448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.6.dcn.offset_mask.bias - torch.Size([756]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.6.dcn.value_proj.weight - torch.Size([448, 448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.6.dcn.value_proj.bias - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.6.dcn.output_proj.weight - torch.Size([448, 448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.6.norm2.0.weight - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.6.norm2.0.bias - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.6.mlp.fc1.weight - torch.Size([1792, 448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.6.mlp.fc1.bias - torch.Size([1792]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.6.mlp.fc2.weight - torch.Size([448, 1792]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.7.gamma1 - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.7.gamma2 - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.7.norm1.0.weight - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.7.norm1.0.bias - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.7.dcn.offset_mask_dw.weight - torch.Size([448, 1, 3, 3]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.7.dcn.offset_mask_dw.bias - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.7.dcn.offset_mask.weight - torch.Size([756, 448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.7.dcn.offset_mask.bias - torch.Size([756]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.7.dcn.value_proj.weight - torch.Size([448, 448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.7.dcn.value_proj.bias - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.7.dcn.output_proj.weight - torch.Size([448, 448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.7.norm2.0.weight - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.7.norm2.0.bias - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.7.mlp.fc1.weight - torch.Size([1792, 448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.7.mlp.fc1.bias - torch.Size([1792]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.7.mlp.fc2.weight - torch.Size([448, 1792]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.8.gamma1 - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.8.gamma2 - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.8.norm1.0.weight - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.8.norm1.0.bias - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.8.dcn.offset_mask_dw.weight - torch.Size([448, 1, 3, 3]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.8.dcn.offset_mask_dw.bias - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.8.dcn.offset_mask.weight - torch.Size([756, 448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.8.dcn.offset_mask.bias - torch.Size([756]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.8.dcn.value_proj.weight - torch.Size([448, 448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.8.dcn.value_proj.bias - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.8.dcn.output_proj.weight - torch.Size([448, 448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.8.norm2.0.weight - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.8.norm2.0.bias - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.8.mlp.fc1.weight - torch.Size([1792, 448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.8.mlp.fc1.bias - torch.Size([1792]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.8.mlp.fc2.weight - torch.Size([448, 1792]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.9.gamma1 - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.9.gamma2 - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.9.norm1.0.weight - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.9.norm1.0.bias - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.9.dcn.offset_mask_dw.weight - torch.Size([448, 1, 3, 3]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.9.dcn.offset_mask_dw.bias - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.9.dcn.offset_mask.weight - torch.Size([756, 448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.9.dcn.offset_mask.bias - torch.Size([756]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.9.dcn.value_proj.weight - torch.Size([448, 448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.9.dcn.value_proj.bias - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.9.dcn.output_proj.weight - torch.Size([448, 448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.9.norm2.0.weight - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.9.norm2.0.bias - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.9.mlp.fc1.weight - torch.Size([1792, 448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.9.mlp.fc1.bias - torch.Size([1792]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.9.mlp.fc2.weight - torch.Size([448, 1792]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.10.gamma1 - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.10.gamma2 - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.10.norm1.0.weight - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.10.norm1.0.bias - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.10.dcn.offset_mask_dw.weight - torch.Size([448, 1, 3, 3]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.10.dcn.offset_mask_dw.bias - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.10.dcn.offset_mask.weight - torch.Size([756, 448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.10.dcn.offset_mask.bias - torch.Size([756]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.10.dcn.value_proj.weight - torch.Size([448, 448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.10.dcn.value_proj.bias - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.10.dcn.output_proj.weight - torch.Size([448, 448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.10.norm2.0.weight - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.10.norm2.0.bias - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.10.mlp.fc1.weight - torch.Size([1792, 448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.10.mlp.fc1.bias - torch.Size([1792]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.10.mlp.fc2.weight - torch.Size([448, 1792]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.11.gamma1 - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.11.gamma2 - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.11.norm1.0.weight - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.11.norm1.0.bias - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.11.dcn.offset_mask_dw.weight - torch.Size([448, 1, 3, 3]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.11.dcn.offset_mask_dw.bias - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.11.dcn.offset_mask.weight - torch.Size([756, 448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.11.dcn.offset_mask.bias - torch.Size([756]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.11.dcn.value_proj.weight - torch.Size([448, 448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.11.dcn.value_proj.bias - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.11.dcn.output_proj.weight - torch.Size([448, 448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.11.norm2.0.weight - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.11.norm2.0.bias - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.11.mlp.fc1.weight - torch.Size([1792, 448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.11.mlp.fc1.bias - torch.Size([1792]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.11.mlp.fc2.weight - torch.Size([448, 1792]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.12.gamma1 - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.12.gamma2 - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.12.norm1.0.weight - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.12.norm1.0.bias - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.12.dcn.offset_mask_dw.weight - torch.Size([448, 1, 3, 3]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.12.dcn.offset_mask_dw.bias - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.12.dcn.offset_mask.weight - torch.Size([756, 448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.12.dcn.offset_mask.bias - torch.Size([756]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.12.dcn.value_proj.weight - torch.Size([448, 448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.12.dcn.value_proj.bias - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.12.dcn.output_proj.weight - torch.Size([448, 448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.12.norm2.0.weight - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.12.norm2.0.bias - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.12.mlp.fc1.weight - torch.Size([1792, 448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.12.mlp.fc1.bias - torch.Size([1792]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.12.mlp.fc2.weight - torch.Size([448, 1792]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.13.gamma1 - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.13.gamma2 - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.13.norm1.0.weight - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.13.norm1.0.bias - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.13.dcn.offset_mask_dw.weight - torch.Size([448, 1, 3, 3]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.13.dcn.offset_mask_dw.bias - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.13.dcn.offset_mask.weight - torch.Size([756, 448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.13.dcn.offset_mask.bias - torch.Size([756]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.13.dcn.value_proj.weight - torch.Size([448, 448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.13.dcn.value_proj.bias - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.13.dcn.output_proj.weight - torch.Size([448, 448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.13.norm2.0.weight - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.13.norm2.0.bias - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.13.mlp.fc1.weight - torch.Size([1792, 448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.13.mlp.fc1.bias - torch.Size([1792]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.13.mlp.fc2.weight - torch.Size([448, 1792]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.14.gamma1 - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.14.gamma2 - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.14.norm1.0.weight - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.14.norm1.0.bias - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.14.dcn.offset_mask_dw.weight - torch.Size([448, 1, 3, 3]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.14.dcn.offset_mask_dw.bias - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.14.dcn.offset_mask.weight - torch.Size([756, 448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.14.dcn.offset_mask.bias - torch.Size([756]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.14.dcn.value_proj.weight - torch.Size([448, 448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.14.dcn.value_proj.bias - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.14.dcn.output_proj.weight - torch.Size([448, 448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.14.norm2.0.weight - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.14.norm2.0.bias - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.14.mlp.fc1.weight - torch.Size([1792, 448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.14.mlp.fc1.bias - torch.Size([1792]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.14.mlp.fc2.weight - torch.Size([448, 1792]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.15.gamma1 - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.15.gamma2 - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.15.norm1.0.weight - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.15.norm1.0.bias - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.15.dcn.offset_mask_dw.weight - torch.Size([448, 1, 3, 3]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.15.dcn.offset_mask_dw.bias - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.15.dcn.offset_mask.weight - torch.Size([756, 448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.15.dcn.offset_mask.bias - torch.Size([756]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.15.dcn.value_proj.weight - torch.Size([448, 448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.15.dcn.value_proj.bias - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.15.dcn.output_proj.weight - torch.Size([448, 448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.15.norm2.0.weight - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.15.norm2.0.bias - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.15.mlp.fc1.weight - torch.Size([1792, 448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.15.mlp.fc1.bias - torch.Size([1792]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.15.mlp.fc2.weight - torch.Size([448, 1792]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.16.gamma1 - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.16.gamma2 - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.16.norm1.0.weight - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.16.norm1.0.bias - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.16.dcn.offset_mask_dw.weight - torch.Size([448, 1, 3, 3]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.16.dcn.offset_mask_dw.bias - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.16.dcn.offset_mask.weight - torch.Size([756, 448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.16.dcn.offset_mask.bias - torch.Size([756]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.16.dcn.value_proj.weight - torch.Size([448, 448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.16.dcn.value_proj.bias - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.16.dcn.output_proj.weight - torch.Size([448, 448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.16.norm2.0.weight - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.16.norm2.0.bias - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.16.mlp.fc1.weight - torch.Size([1792, 448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.16.mlp.fc1.bias - torch.Size([1792]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.16.mlp.fc2.weight - torch.Size([448, 1792]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.17.gamma1 - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.17.gamma2 - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.17.norm1.0.weight - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.17.norm1.0.bias - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.17.dcn.offset_mask_dw.weight - torch.Size([448, 1, 3, 3]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.17.dcn.offset_mask_dw.bias - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.17.dcn.offset_mask.weight - torch.Size([756, 448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.17.dcn.offset_mask.bias - torch.Size([756]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.17.dcn.value_proj.weight - torch.Size([448, 448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.17.dcn.value_proj.bias - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.17.dcn.output_proj.weight - torch.Size([448, 448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.17.norm2.0.weight - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.17.norm2.0.bias - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.17.mlp.fc1.weight - torch.Size([1792, 448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.17.mlp.fc1.bias - torch.Size([1792]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.17.mlp.fc2.weight - torch.Size([448, 1792]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.18.gamma1 - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.18.gamma2 - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.18.norm1.0.weight - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.18.norm1.0.bias - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.18.dcn.offset_mask_dw.weight - torch.Size([448, 1, 3, 3]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.18.dcn.offset_mask_dw.bias - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.18.dcn.offset_mask.weight - torch.Size([756, 448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.18.dcn.offset_mask.bias - torch.Size([756]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.18.dcn.value_proj.weight - torch.Size([448, 448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.18.dcn.value_proj.bias - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.18.dcn.output_proj.weight - torch.Size([448, 448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.18.norm2.0.weight - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.18.norm2.0.bias - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.18.mlp.fc1.weight - torch.Size([1792, 448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.18.mlp.fc1.bias - torch.Size([1792]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.18.mlp.fc2.weight - torch.Size([448, 1792]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.19.gamma1 - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.19.gamma2 - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.19.norm1.0.weight - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.19.norm1.0.bias - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.19.dcn.offset_mask_dw.weight - torch.Size([448, 1, 3, 3]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.19.dcn.offset_mask_dw.bias - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.19.dcn.offset_mask.weight - torch.Size([756, 448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.19.dcn.offset_mask.bias - torch.Size([756]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.19.dcn.value_proj.weight - torch.Size([448, 448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.19.dcn.value_proj.bias - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.19.dcn.output_proj.weight - torch.Size([448, 448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.19.norm2.0.weight - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.19.norm2.0.bias - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.19.mlp.fc1.weight - torch.Size([1792, 448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.19.mlp.fc1.bias - torch.Size([1792]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.19.mlp.fc2.weight - torch.Size([448, 1792]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.20.gamma1 - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.20.gamma2 - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.20.norm1.0.weight - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.20.norm1.0.bias - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.20.dcn.offset_mask_dw.weight - torch.Size([448, 1, 3, 3]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.20.dcn.offset_mask_dw.bias - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.20.dcn.offset_mask.weight - torch.Size([756, 448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.20.dcn.offset_mask.bias - torch.Size([756]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.20.dcn.value_proj.weight - torch.Size([448, 448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.20.dcn.value_proj.bias - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.20.dcn.output_proj.weight - torch.Size([448, 448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.20.norm2.0.weight - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.20.norm2.0.bias - torch.Size([448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.20.mlp.fc1.weight - torch.Size([1792, 448]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.20.mlp.fc1.bias - torch.Size([1792]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.20.mlp.fc2.weight - torch.Size([448, 1792]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.downsample.conv.weight - torch.Size([896, 448, 3, 3]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.downsample.norm.1.weight - torch.Size([896]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.downsample.norm.1.bias - torch.Size([896]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.0.gamma1 - torch.Size([896]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.0.gamma2 - torch.Size([896]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.0.norm1.0.weight - torch.Size([896]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.0.norm1.0.bias - torch.Size([896]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.0.dcn.offset_mask_dw.weight - torch.Size([896, 1, 3, 3]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.0.dcn.offset_mask_dw.bias - torch.Size([896]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.0.dcn.offset_mask.weight - torch.Size([1512, 896]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.0.dcn.offset_mask.bias - torch.Size([1512]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.0.dcn.value_proj.weight - torch.Size([896, 896]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.0.dcn.value_proj.bias - torch.Size([896]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.0.dcn.output_proj.weight - torch.Size([896, 896]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.0.norm2.0.weight - torch.Size([896]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.0.norm2.0.bias - torch.Size([896]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.0.mlp.fc1.weight - torch.Size([3584, 896]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.0.mlp.fc1.bias - torch.Size([3584]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.0.mlp.fc2.weight - torch.Size([896, 3584]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.1.gamma1 - torch.Size([896]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.1.gamma2 - torch.Size([896]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.1.norm1.0.weight - torch.Size([896]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.1.norm1.0.bias - torch.Size([896]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.1.dcn.offset_mask_dw.weight - torch.Size([896, 1, 3, 3]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.1.dcn.offset_mask_dw.bias - torch.Size([896]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.1.dcn.offset_mask.weight - torch.Size([1512, 896]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.1.dcn.offset_mask.bias - torch.Size([1512]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.1.dcn.value_proj.weight - torch.Size([896, 896]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.1.dcn.value_proj.bias - torch.Size([896]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.1.dcn.output_proj.weight - torch.Size([896, 896]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.1.norm2.0.weight - torch.Size([896]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.1.norm2.0.bias - torch.Size([896]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.1.mlp.fc1.weight - torch.Size([3584, 896]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.1.mlp.fc1.bias - torch.Size([3584]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.1.mlp.fc2.weight - torch.Size([896, 3584]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.2.gamma1 - torch.Size([896]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.2.gamma2 - torch.Size([896]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.2.norm1.0.weight - torch.Size([896]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.2.norm1.0.bias - torch.Size([896]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.2.dcn.offset_mask_dw.weight - torch.Size([896, 1, 3, 3]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.2.dcn.offset_mask_dw.bias - torch.Size([896]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.2.dcn.offset_mask.weight - torch.Size([1512, 896]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.2.dcn.offset_mask.bias - torch.Size([1512]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.2.dcn.value_proj.weight - torch.Size([896, 896]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.2.dcn.value_proj.bias - torch.Size([896]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.2.dcn.output_proj.weight - torch.Size([896, 896]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.2.norm2.0.weight - torch.Size([896]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.2.norm2.0.bias - torch.Size([896]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.2.mlp.fc1.weight - torch.Size([3584, 896]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.2.mlp.fc1.bias - torch.Size([3584]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.2.mlp.fc2.weight - torch.Size([896, 3584]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.3.gamma1 - torch.Size([896]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.3.gamma2 - torch.Size([896]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.3.norm1.0.weight - torch.Size([896]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.3.norm1.0.bias - torch.Size([896]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.3.dcn.offset_mask_dw.weight - torch.Size([896, 1, 3, 3]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.3.dcn.offset_mask_dw.bias - torch.Size([896]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.3.dcn.offset_mask.weight - torch.Size([1512, 896]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.3.dcn.offset_mask.bias - torch.Size([1512]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.3.dcn.value_proj.weight - torch.Size([896, 896]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.3.dcn.value_proj.bias - torch.Size([896]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.3.dcn.output_proj.weight - torch.Size([896, 896]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.3.norm2.0.weight - torch.Size([896]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.3.norm2.0.bias - torch.Size([896]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.3.mlp.fc1.weight - torch.Size([3584, 896]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.3.mlp.fc1.bias - torch.Size([3584]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.3.mlp.fc2.weight - torch.Size([896, 3584]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx neck.lateral_convs.0.conv.weight - torch.Size([256, 112, 1, 1]): XavierInit: gain=1, distribution=uniform, bias=0 neck.lateral_convs.0.ln.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of MaskRCNN neck.lateral_convs.0.ln.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of MaskRCNN neck.lateral_convs.1.conv.weight - torch.Size([256, 224, 1, 1]): XavierInit: gain=1, distribution=uniform, bias=0 neck.lateral_convs.1.ln.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of MaskRCNN neck.lateral_convs.1.ln.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of MaskRCNN neck.lateral_convs.2.conv.weight - torch.Size([256, 448, 1, 1]): XavierInit: gain=1, distribution=uniform, bias=0 neck.lateral_convs.2.ln.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of MaskRCNN neck.lateral_convs.2.ln.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of MaskRCNN neck.lateral_convs.3.conv.weight - torch.Size([256, 896, 1, 1]): XavierInit: gain=1, distribution=uniform, bias=0 neck.lateral_convs.3.ln.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of MaskRCNN neck.lateral_convs.3.ln.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of MaskRCNN neck.fpn_convs.0.conv.weight - torch.Size([256, 256, 3, 3]): XavierInit: gain=1, distribution=uniform, bias=0 neck.fpn_convs.0.ln.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of MaskRCNN neck.fpn_convs.0.ln.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of MaskRCNN neck.fpn_convs.1.conv.weight - torch.Size([256, 256, 3, 3]): XavierInit: gain=1, distribution=uniform, bias=0 neck.fpn_convs.1.ln.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of MaskRCNN neck.fpn_convs.1.ln.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of MaskRCNN neck.fpn_convs.2.conv.weight - torch.Size([256, 256, 3, 3]): XavierInit: gain=1, distribution=uniform, bias=0 neck.fpn_convs.2.ln.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of MaskRCNN neck.fpn_convs.2.ln.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of MaskRCNN neck.fpn_convs.3.conv.weight - torch.Size([256, 256, 3, 3]): XavierInit: gain=1, distribution=uniform, bias=0 neck.fpn_convs.3.ln.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of MaskRCNN neck.fpn_convs.3.ln.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of MaskRCNN rpn_head.rpn_conv.weight - torch.Size([256, 256, 3, 3]): NormalInit: mean=0, std=0.01, bias=0 rpn_head.rpn_conv.bias - torch.Size([256]): NormalInit: mean=0, std=0.01, bias=0 rpn_head.rpn_cls.weight - torch.Size([3, 256, 1, 1]): NormalInit: mean=0, std=0.01, bias=0 rpn_head.rpn_cls.bias - torch.Size([3]): NormalInit: mean=0, std=0.01, bias=0 rpn_head.rpn_reg.weight - torch.Size([12, 256, 1, 1]): NormalInit: mean=0, std=0.01, bias=0 rpn_head.rpn_reg.bias - torch.Size([12]): NormalInit: mean=0, std=0.01, bias=0 roi_head.bbox_head.fc_cls.weight - torch.Size([81, 1024]): NormalInit: mean=0, std=0.01, bias=0 roi_head.bbox_head.fc_cls.bias - torch.Size([81]): NormalInit: mean=0, std=0.01, bias=0 roi_head.bbox_head.fc_reg.weight - torch.Size([320, 1024]): NormalInit: mean=0, std=0.001, bias=0 roi_head.bbox_head.fc_reg.bias - torch.Size([320]): NormalInit: mean=0, std=0.001, bias=0 roi_head.bbox_head.shared_fcs.0.weight - torch.Size([1024, 12544]): XavierInit: gain=1, distribution=uniform, bias=0 roi_head.bbox_head.shared_fcs.0.bias - torch.Size([1024]): XavierInit: gain=1, distribution=uniform, bias=0 roi_head.bbox_head.shared_fcs.1.weight - torch.Size([1024, 1024]): XavierInit: gain=1, distribution=uniform, bias=0 roi_head.bbox_head.shared_fcs.1.bias - torch.Size([1024]): XavierInit: gain=1, distribution=uniform, bias=0 roi_head.mask_head.convs.0.conv.weight - torch.Size([256, 256, 3, 3]): Initialized by user-defined `init_weights` in ConvModule roi_head.mask_head.convs.0.conv.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of MaskRCNN roi_head.mask_head.convs.1.conv.weight - torch.Size([256, 256, 3, 3]): Initialized by user-defined `init_weights` in ConvModule roi_head.mask_head.convs.1.conv.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of MaskRCNN roi_head.mask_head.convs.2.conv.weight - torch.Size([256, 256, 3, 3]): Initialized by user-defined `init_weights` in ConvModule roi_head.mask_head.convs.2.conv.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of MaskRCNN roi_head.mask_head.convs.3.conv.weight - torch.Size([256, 256, 3, 3]): Initialized by user-defined `init_weights` in ConvModule roi_head.mask_head.convs.3.conv.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of MaskRCNN roi_head.mask_head.upsample.weight - torch.Size([256, 256, 2, 2]): Initialized by user-defined `init_weights` in FCNMaskHead roi_head.mask_head.upsample.bias - torch.Size([256]): Initialized by user-defined `init_weights` in FCNMaskHead roi_head.mask_head.conv_logits.weight - torch.Size([80, 256, 1, 1]): Initialized by user-defined `init_weights` in FCNMaskHead roi_head.mask_head.conv_logits.bias - torch.Size([80]): Initialized by user-defined `init_weights` in FCNMaskHead 2023-11-16 16:50:37,093 - mmdet - INFO - MaskRCNN( (backbone): Flash_InternImage_nsmx( (patch_embed): StemLayer( (conv1): Conv2d(3, 56, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1)) (norm1): Sequential( (0): to_channels_last() (1): LayerNorm((56,), eps=1e-06, elementwise_affine=True) (2): to_channels_first() ) (act): GELU(approximate=none) (conv2): Conv2d(56, 112, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1)) (norm2): Sequential( (0): to_channels_last() (1): LayerNorm((112,), eps=1e-06, elementwise_affine=True) ) ) (pos_drop): Dropout(p=0.0, inplace=False) (levels): ModuleList( (0): InternImageBlock( (blocks): ModuleList( (0): InternImageLayer( (norm1): Sequential( (0): LayerNorm((112,), eps=1e-06, elementwise_affine=True) ) (dcn): FlashDCNv3( (offset_mask_dw): Conv2d(112, 112, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=112) (offset_mask): Linear(in_features=112, out_features=189, bias=True) (value_proj): Linear(in_features=112, out_features=112, bias=True) (output_proj): Linear(in_features=112, out_features=112, bias=False) ) (drop_path): Identity() (norm2): Sequential( (0): LayerNorm((112,), eps=1e-06, elementwise_affine=True) ) (mlp): MLPLayer( (fc1): Linear(in_features=112, out_features=448, bias=True) (act): GELU(approximate=none) (fc2): Linear(in_features=448, out_features=112, bias=False) (drop): Dropout(p=0.0, inplace=False) ) ) (1): InternImageLayer( (norm1): Sequential( (0): LayerNorm((112,), eps=1e-06, elementwise_affine=True) ) (dcn): FlashDCNv3( (offset_mask_dw): Conv2d(112, 112, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=112) (offset_mask): Linear(in_features=112, out_features=189, bias=True) (value_proj): Linear(in_features=112, out_features=112, bias=True) (output_proj): Linear(in_features=112, out_features=112, bias=False) ) (drop_path): DropPath(drop_prob=0.013) (norm2): Sequential( (0): LayerNorm((112,), eps=1e-06, elementwise_affine=True) ) (mlp): MLPLayer( (fc1): Linear(in_features=112, out_features=448, bias=True) (act): GELU(approximate=none) (fc2): Linear(in_features=448, out_features=112, bias=False) (drop): Dropout(p=0.0, inplace=False) ) ) (2): InternImageLayer( (norm1): Sequential( (0): LayerNorm((112,), eps=1e-06, elementwise_affine=True) ) (dcn): FlashDCNv3( (offset_mask_dw): Conv2d(112, 112, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=112) (offset_mask): Linear(in_features=112, out_features=189, bias=True) (value_proj): Linear(in_features=112, out_features=112, bias=True) (output_proj): Linear(in_features=112, out_features=112, bias=False) ) (drop_path): DropPath(drop_prob=0.025) (norm2): Sequential( (0): LayerNorm((112,), eps=1e-06, elementwise_affine=True) ) (mlp): MLPLayer( (fc1): Linear(in_features=112, out_features=448, bias=True) (act): GELU(approximate=none) (fc2): Linear(in_features=448, out_features=112, bias=False) (drop): Dropout(p=0.0, inplace=False) ) ) (3): InternImageLayer( (norm1): Sequential( (0): LayerNorm((112,), eps=1e-06, elementwise_affine=True) ) (dcn): FlashDCNv3( (offset_mask_dw): Conv2d(112, 112, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=112) (offset_mask): Linear(in_features=112, out_features=189, bias=True) (value_proj): Linear(in_features=112, out_features=112, bias=True) (output_proj): Linear(in_features=112, out_features=112, bias=False) ) (drop_path): DropPath(drop_prob=0.038) (norm2): Sequential( (0): LayerNorm((112,), eps=1e-06, elementwise_affine=True) ) (mlp): MLPLayer( (fc1): Linear(in_features=112, out_features=448, bias=True) (act): GELU(approximate=none) (fc2): Linear(in_features=448, out_features=112, bias=False) (drop): Dropout(p=0.0, inplace=False) ) ) ) (downsample): DownsampleLayer( (conv): Conv2d(112, 224, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) (norm): Sequential( (0): to_channels_last() (1): LayerNorm((224,), eps=1e-06, elementwise_affine=True) (2): to_channels_first() ) ) ) (1): InternImageBlock( (blocks): ModuleList( (0): InternImageLayer( (norm1): Sequential( (0): LayerNorm((224,), eps=1e-06, elementwise_affine=True) ) (dcn): FlashDCNv3( (offset_mask_dw): Conv2d(224, 224, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=224) (offset_mask): Linear(in_features=224, out_features=378, bias=True) (value_proj): Linear(in_features=224, out_features=224, bias=True) (output_proj): Linear(in_features=224, out_features=224, bias=False) ) (drop_path): DropPath(drop_prob=0.050) (norm2): Sequential( (0): LayerNorm((224,), eps=1e-06, elementwise_affine=True) ) (mlp): MLPLayer( (fc1): Linear(in_features=224, out_features=896, bias=True) (act): GELU(approximate=none) (fc2): Linear(in_features=896, out_features=224, bias=False) (drop): Dropout(p=0.0, inplace=False) ) ) (1): InternImageLayer( (norm1): Sequential( (0): LayerNorm((224,), eps=1e-06, elementwise_affine=True) ) (dcn): FlashDCNv3( (offset_mask_dw): Conv2d(224, 224, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=224) (offset_mask): Linear(in_features=224, out_features=378, bias=True) (value_proj): Linear(in_features=224, out_features=224, bias=True) (output_proj): Linear(in_features=224, out_features=224, bias=False) ) (drop_path): DropPath(drop_prob=0.062) (norm2): Sequential( (0): LayerNorm((224,), eps=1e-06, elementwise_affine=True) ) (mlp): MLPLayer( (fc1): Linear(in_features=224, out_features=896, bias=True) (act): GELU(approximate=none) (fc2): Linear(in_features=896, out_features=224, bias=False) (drop): Dropout(p=0.0, inplace=False) ) ) (2): InternImageLayer( (norm1): Sequential( (0): LayerNorm((224,), eps=1e-06, elementwise_affine=True) ) (dcn): FlashDCNv3( (offset_mask_dw): Conv2d(224, 224, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=224) (offset_mask): Linear(in_features=224, out_features=378, bias=True) (value_proj): Linear(in_features=224, out_features=224, bias=True) (output_proj): Linear(in_features=224, out_features=224, bias=False) ) (drop_path): DropPath(drop_prob=0.075) (norm2): Sequential( (0): LayerNorm((224,), eps=1e-06, elementwise_affine=True) ) (mlp): MLPLayer( (fc1): Linear(in_features=224, out_features=896, bias=True) (act): GELU(approximate=none) (fc2): Linear(in_features=896, out_features=224, bias=False) (drop): Dropout(p=0.0, inplace=False) ) ) (3): InternImageLayer( (norm1): Sequential( (0): LayerNorm((224,), eps=1e-06, elementwise_affine=True) ) (dcn): FlashDCNv3( (offset_mask_dw): Conv2d(224, 224, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=224) (offset_mask): Linear(in_features=224, out_features=378, bias=True) (value_proj): Linear(in_features=224, out_features=224, bias=True) (output_proj): Linear(in_features=224, out_features=224, bias=False) ) (drop_path): DropPath(drop_prob=0.087) (norm2): Sequential( (0): LayerNorm((224,), eps=1e-06, elementwise_affine=True) ) (mlp): MLPLayer( (fc1): Linear(in_features=224, out_features=896, bias=True) (act): GELU(approximate=none) (fc2): Linear(in_features=896, out_features=224, bias=False) (drop): Dropout(p=0.0, inplace=False) ) ) ) (downsample): DownsampleLayer( (conv): Conv2d(224, 448, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) (norm): Sequential( (0): to_channels_last() (1): LayerNorm((448,), eps=1e-06, elementwise_affine=True) (2): to_channels_first() ) ) ) (2): InternImageBlock( (blocks): ModuleList( (0): InternImageLayer( (norm1): Sequential( (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True) ) (dcn): FlashDCNv3( (offset_mask_dw): Conv2d(448, 448, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=448) (offset_mask): Linear(in_features=448, out_features=756, bias=True) (value_proj): Linear(in_features=448, out_features=448, bias=True) (output_proj): Linear(in_features=448, out_features=448, bias=False) ) (drop_path): DropPath(drop_prob=0.100) (norm2): Sequential( (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True) ) (mlp): MLPLayer( (fc1): Linear(in_features=448, out_features=1792, bias=True) (act): GELU(approximate=none) (fc2): Linear(in_features=1792, out_features=448, bias=False) (drop): Dropout(p=0.0, inplace=False) ) ) (1): InternImageLayer( (norm1): Sequential( (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True) ) (dcn): FlashDCNv3( (offset_mask_dw): Conv2d(448, 448, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=448) (offset_mask): Linear(in_features=448, out_features=756, bias=True) (value_proj): Linear(in_features=448, out_features=448, bias=True) (output_proj): Linear(in_features=448, out_features=448, bias=False) ) (drop_path): DropPath(drop_prob=0.113) (norm2): Sequential( (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True) ) (mlp): MLPLayer( (fc1): Linear(in_features=448, out_features=1792, bias=True) (act): GELU(approximate=none) (fc2): Linear(in_features=1792, out_features=448, bias=False) (drop): Dropout(p=0.0, inplace=False) ) ) (2): InternImageLayer( (norm1): Sequential( (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True) ) (dcn): FlashDCNv3( (offset_mask_dw): Conv2d(448, 448, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=448) (offset_mask): Linear(in_features=448, out_features=756, bias=True) (value_proj): Linear(in_features=448, out_features=448, bias=True) (output_proj): Linear(in_features=448, out_features=448, bias=False) ) (drop_path): DropPath(drop_prob=0.125) (norm2): Sequential( (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True) ) (mlp): MLPLayer( (fc1): Linear(in_features=448, out_features=1792, bias=True) (act): GELU(approximate=none) (fc2): Linear(in_features=1792, out_features=448, bias=False) (drop): Dropout(p=0.0, inplace=False) ) ) (3): InternImageLayer( (norm1): Sequential( (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True) ) (dcn): FlashDCNv3( (offset_mask_dw): Conv2d(448, 448, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=448) (offset_mask): Linear(in_features=448, out_features=756, bias=True) (value_proj): Linear(in_features=448, out_features=448, bias=True) (output_proj): Linear(in_features=448, out_features=448, bias=False) ) (drop_path): DropPath(drop_prob=0.138) (norm2): Sequential( (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True) ) (mlp): MLPLayer( (fc1): Linear(in_features=448, out_features=1792, bias=True) (act): GELU(approximate=none) (fc2): Linear(in_features=1792, out_features=448, bias=False) (drop): Dropout(p=0.0, inplace=False) ) ) (4): InternImageLayer( (norm1): Sequential( (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True) ) (dcn): FlashDCNv3( (offset_mask_dw): Conv2d(448, 448, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=448) (offset_mask): Linear(in_features=448, out_features=756, bias=True) (value_proj): Linear(in_features=448, out_features=448, bias=True) (output_proj): Linear(in_features=448, out_features=448, bias=False) ) (drop_path): DropPath(drop_prob=0.150) (norm2): Sequential( (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True) ) (mlp): MLPLayer( (fc1): Linear(in_features=448, out_features=1792, bias=True) (act): GELU(approximate=none) (fc2): Linear(in_features=1792, out_features=448, bias=False) (drop): Dropout(p=0.0, inplace=False) ) ) (5): InternImageLayer( (norm1): Sequential( (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True) ) (dcn): FlashDCNv3( (offset_mask_dw): Conv2d(448, 448, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=448) (offset_mask): Linear(in_features=448, out_features=756, bias=True) (value_proj): Linear(in_features=448, out_features=448, bias=True) (output_proj): Linear(in_features=448, out_features=448, bias=False) ) (drop_path): DropPath(drop_prob=0.162) (norm2): Sequential( (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True) ) (mlp): MLPLayer( (fc1): Linear(in_features=448, out_features=1792, bias=True) (act): GELU(approximate=none) (fc2): Linear(in_features=1792, out_features=448, bias=False) (drop): Dropout(p=0.0, inplace=False) ) ) (6): InternImageLayer( (norm1): Sequential( (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True) ) (dcn): FlashDCNv3( (offset_mask_dw): Conv2d(448, 448, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=448) (offset_mask): Linear(in_features=448, out_features=756, bias=True) (value_proj): Linear(in_features=448, out_features=448, bias=True) (output_proj): Linear(in_features=448, out_features=448, bias=False) ) (drop_path): DropPath(drop_prob=0.175) (norm2): Sequential( (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True) ) (mlp): MLPLayer( (fc1): Linear(in_features=448, out_features=1792, bias=True) (act): GELU(approximate=none) (fc2): Linear(in_features=1792, out_features=448, bias=False) (drop): Dropout(p=0.0, inplace=False) ) ) (7): InternImageLayer( (norm1): Sequential( (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True) ) (dcn): FlashDCNv3( (offset_mask_dw): Conv2d(448, 448, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=448) (offset_mask): Linear(in_features=448, out_features=756, bias=True) (value_proj): Linear(in_features=448, out_features=448, bias=True) (output_proj): Linear(in_features=448, out_features=448, bias=False) ) (drop_path): DropPath(drop_prob=0.188) (norm2): Sequential( (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True) ) (mlp): MLPLayer( (fc1): Linear(in_features=448, out_features=1792, bias=True) (act): GELU(approximate=none) (fc2): Linear(in_features=1792, out_features=448, bias=False) (drop): Dropout(p=0.0, inplace=False) ) ) (8): InternImageLayer( (norm1): Sequential( (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True) ) (dcn): FlashDCNv3( (offset_mask_dw): Conv2d(448, 448, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=448) (offset_mask): Linear(in_features=448, out_features=756, bias=True) (value_proj): Linear(in_features=448, out_features=448, bias=True) (output_proj): Linear(in_features=448, out_features=448, bias=False) ) (drop_path): DropPath(drop_prob=0.200) (norm2): Sequential( (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True) ) (mlp): MLPLayer( (fc1): Linear(in_features=448, out_features=1792, bias=True) (act): GELU(approximate=none) (fc2): Linear(in_features=1792, out_features=448, bias=False) (drop): Dropout(p=0.0, inplace=False) ) ) (9): InternImageLayer( (norm1): Sequential( (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True) ) (dcn): FlashDCNv3( (offset_mask_dw): Conv2d(448, 448, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=448) (offset_mask): Linear(in_features=448, out_features=756, bias=True) (value_proj): Linear(in_features=448, out_features=448, bias=True) (output_proj): Linear(in_features=448, out_features=448, bias=False) ) (drop_path): DropPath(drop_prob=0.213) (norm2): Sequential( (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True) ) (mlp): MLPLayer( (fc1): Linear(in_features=448, out_features=1792, bias=True) (act): GELU(approximate=none) (fc2): Linear(in_features=1792, out_features=448, bias=False) (drop): Dropout(p=0.0, inplace=False) ) ) (10): InternImageLayer( (norm1): Sequential( (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True) ) (dcn): FlashDCNv3( (offset_mask_dw): Conv2d(448, 448, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=448) (offset_mask): Linear(in_features=448, out_features=756, bias=True) (value_proj): Linear(in_features=448, out_features=448, bias=True) (output_proj): Linear(in_features=448, out_features=448, bias=False) ) (drop_path): DropPath(drop_prob=0.225) (norm2): Sequential( (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True) ) (mlp): MLPLayer( (fc1): Linear(in_features=448, out_features=1792, bias=True) (act): GELU(approximate=none) (fc2): Linear(in_features=1792, out_features=448, bias=False) (drop): Dropout(p=0.0, inplace=False) ) ) (11): InternImageLayer( (norm1): Sequential( (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True) ) (dcn): FlashDCNv3( (offset_mask_dw): Conv2d(448, 448, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=448) (offset_mask): Linear(in_features=448, out_features=756, bias=True) (value_proj): Linear(in_features=448, out_features=448, bias=True) (output_proj): Linear(in_features=448, out_features=448, bias=False) ) (drop_path): DropPath(drop_prob=0.238) (norm2): Sequential( (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True) ) (mlp): MLPLayer( (fc1): Linear(in_features=448, out_features=1792, bias=True) (act): GELU(approximate=none) (fc2): Linear(in_features=1792, out_features=448, bias=False) (drop): Dropout(p=0.0, inplace=False) ) ) (12): InternImageLayer( (norm1): Sequential( (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True) ) (dcn): FlashDCNv3( (offset_mask_dw): Conv2d(448, 448, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=448) (offset_mask): Linear(in_features=448, out_features=756, bias=True) (value_proj): Linear(in_features=448, out_features=448, bias=True) (output_proj): Linear(in_features=448, out_features=448, bias=False) ) (drop_path): DropPath(drop_prob=0.250) (norm2): Sequential( (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True) ) (mlp): MLPLayer( (fc1): Linear(in_features=448, out_features=1792, bias=True) (act): GELU(approximate=none) (fc2): Linear(in_features=1792, out_features=448, bias=False) (drop): Dropout(p=0.0, inplace=False) ) ) (13): InternImageLayer( (norm1): Sequential( (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True) ) (dcn): FlashDCNv3( (offset_mask_dw): Conv2d(448, 448, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=448) (offset_mask): Linear(in_features=448, out_features=756, bias=True) (value_proj): Linear(in_features=448, out_features=448, bias=True) (output_proj): Linear(in_features=448, out_features=448, bias=False) ) (drop_path): DropPath(drop_prob=0.262) (norm2): Sequential( (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True) ) (mlp): MLPLayer( (fc1): Linear(in_features=448, out_features=1792, bias=True) (act): GELU(approximate=none) (fc2): Linear(in_features=1792, out_features=448, bias=False) (drop): Dropout(p=0.0, inplace=False) ) ) (14): InternImageLayer( (norm1): Sequential( (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True) ) (dcn): FlashDCNv3( (offset_mask_dw): Conv2d(448, 448, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=448) (offset_mask): Linear(in_features=448, out_features=756, bias=True) (value_proj): Linear(in_features=448, out_features=448, bias=True) (output_proj): Linear(in_features=448, out_features=448, bias=False) ) (drop_path): DropPath(drop_prob=0.275) (norm2): Sequential( (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True) ) (mlp): MLPLayer( (fc1): Linear(in_features=448, out_features=1792, bias=True) (act): GELU(approximate=none) (fc2): Linear(in_features=1792, out_features=448, bias=False) (drop): Dropout(p=0.0, inplace=False) ) ) (15): InternImageLayer( (norm1): Sequential( (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True) ) (dcn): FlashDCNv3( (offset_mask_dw): Conv2d(448, 448, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=448) (offset_mask): Linear(in_features=448, out_features=756, bias=True) (value_proj): Linear(in_features=448, out_features=448, bias=True) (output_proj): Linear(in_features=448, out_features=448, bias=False) ) (drop_path): DropPath(drop_prob=0.287) (norm2): Sequential( (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True) ) (mlp): MLPLayer( (fc1): Linear(in_features=448, out_features=1792, bias=True) (act): GELU(approximate=none) (fc2): Linear(in_features=1792, out_features=448, bias=False) (drop): Dropout(p=0.0, inplace=False) ) ) (16): InternImageLayer( (norm1): Sequential( (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True) ) (dcn): FlashDCNv3( (offset_mask_dw): Conv2d(448, 448, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=448) (offset_mask): Linear(in_features=448, out_features=756, bias=True) (value_proj): Linear(in_features=448, out_features=448, bias=True) (output_proj): Linear(in_features=448, out_features=448, bias=False) ) (drop_path): DropPath(drop_prob=0.300) (norm2): Sequential( (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True) ) (mlp): MLPLayer( (fc1): Linear(in_features=448, out_features=1792, bias=True) (act): GELU(approximate=none) (fc2): Linear(in_features=1792, out_features=448, bias=False) (drop): Dropout(p=0.0, inplace=False) ) ) (17): InternImageLayer( (norm1): Sequential( (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True) ) (dcn): FlashDCNv3( (offset_mask_dw): Conv2d(448, 448, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=448) (offset_mask): Linear(in_features=448, out_features=756, bias=True) (value_proj): Linear(in_features=448, out_features=448, bias=True) (output_proj): Linear(in_features=448, out_features=448, bias=False) ) (drop_path): DropPath(drop_prob=0.312) (norm2): Sequential( (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True) ) (mlp): MLPLayer( (fc1): Linear(in_features=448, out_features=1792, bias=True) (act): GELU(approximate=none) (fc2): Linear(in_features=1792, out_features=448, bias=False) (drop): Dropout(p=0.0, inplace=False) ) ) (18): InternImageLayer( (norm1): Sequential( (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True) ) (dcn): FlashDCNv3( (offset_mask_dw): Conv2d(448, 448, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=448) (offset_mask): Linear(in_features=448, out_features=756, bias=True) (value_proj): Linear(in_features=448, out_features=448, bias=True) (output_proj): Linear(in_features=448, out_features=448, bias=False) ) (drop_path): DropPath(drop_prob=0.325) (norm2): Sequential( (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True) ) (mlp): MLPLayer( (fc1): Linear(in_features=448, out_features=1792, bias=True) (act): GELU(approximate=none) (fc2): Linear(in_features=1792, out_features=448, bias=False) (drop): Dropout(p=0.0, inplace=False) ) ) (19): InternImageLayer( (norm1): Sequential( (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True) ) (dcn): FlashDCNv3( (offset_mask_dw): Conv2d(448, 448, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=448) (offset_mask): Linear(in_features=448, out_features=756, bias=True) (value_proj): Linear(in_features=448, out_features=448, bias=True) (output_proj): Linear(in_features=448, out_features=448, bias=False) ) (drop_path): DropPath(drop_prob=0.338) (norm2): Sequential( (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True) ) (mlp): MLPLayer( (fc1): Linear(in_features=448, out_features=1792, bias=True) (act): GELU(approximate=none) (fc2): Linear(in_features=1792, out_features=448, bias=False) (drop): Dropout(p=0.0, inplace=False) ) ) (20): InternImageLayer( (norm1): Sequential( (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True) ) (dcn): FlashDCNv3( (offset_mask_dw): Conv2d(448, 448, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=448) (offset_mask): Linear(in_features=448, out_features=756, bias=True) (value_proj): Linear(in_features=448, out_features=448, bias=True) (output_proj): Linear(in_features=448, out_features=448, bias=False) ) (drop_path): DropPath(drop_prob=0.350) (norm2): Sequential( (0): LayerNorm((448,), eps=1e-06, elementwise_affine=True) ) (mlp): MLPLayer( (fc1): Linear(in_features=448, out_features=1792, bias=True) (act): GELU(approximate=none) (fc2): Linear(in_features=1792, out_features=448, bias=False) (drop): Dropout(p=0.0, inplace=False) ) ) ) (downsample): DownsampleLayer( (conv): Conv2d(448, 896, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) (norm): Sequential( (0): to_channels_last() (1): LayerNorm((896,), eps=1e-06, elementwise_affine=True) (2): to_channels_first() ) ) ) (3): InternImageBlock( (blocks): ModuleList( (0): InternImageLayer( (norm1): Sequential( (0): LayerNorm((896,), eps=1e-06, elementwise_affine=True) ) (dcn): FlashDCNv3( (offset_mask_dw): Conv2d(896, 896, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=896) (offset_mask): Linear(in_features=896, out_features=1512, bias=True) (value_proj): Linear(in_features=896, out_features=896, bias=True) (output_proj): Linear(in_features=896, out_features=896, bias=False) ) (drop_path): DropPath(drop_prob=0.363) (norm2): Sequential( (0): LayerNorm((896,), eps=1e-06, elementwise_affine=True) ) (mlp): MLPLayer( (fc1): Linear(in_features=896, out_features=3584, bias=True) (act): GELU(approximate=none) (fc2): Linear(in_features=3584, out_features=896, bias=False) (drop): Dropout(p=0.0, inplace=False) ) ) (1): InternImageLayer( (norm1): Sequential( (0): LayerNorm((896,), eps=1e-06, elementwise_affine=True) ) (dcn): FlashDCNv3( (offset_mask_dw): Conv2d(896, 896, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=896) (offset_mask): Linear(in_features=896, out_features=1512, bias=True) (value_proj): Linear(in_features=896, out_features=896, bias=True) (output_proj): Linear(in_features=896, out_features=896, bias=False) ) (drop_path): DropPath(drop_prob=0.375) (norm2): Sequential( (0): LayerNorm((896,), eps=1e-06, elementwise_affine=True) ) (mlp): MLPLayer( (fc1): Linear(in_features=896, out_features=3584, bias=True) (act): GELU(approximate=none) (fc2): Linear(in_features=3584, out_features=896, bias=False) (drop): Dropout(p=0.0, inplace=False) ) ) (2): InternImageLayer( (norm1): Sequential( (0): LayerNorm((896,), eps=1e-06, elementwise_affine=True) ) (dcn): FlashDCNv3( (offset_mask_dw): Conv2d(896, 896, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=896) (offset_mask): Linear(in_features=896, out_features=1512, bias=True) (value_proj): Linear(in_features=896, out_features=896, bias=True) (output_proj): Linear(in_features=896, out_features=896, bias=False) ) (drop_path): DropPath(drop_prob=0.388) (norm2): Sequential( (0): LayerNorm((896,), eps=1e-06, elementwise_affine=True) ) (mlp): MLPLayer( (fc1): Linear(in_features=896, out_features=3584, bias=True) (act): GELU(approximate=none) (fc2): Linear(in_features=3584, out_features=896, bias=False) (drop): Dropout(p=0.0, inplace=False) ) ) (3): InternImageLayer( (norm1): Sequential( (0): LayerNorm((896,), eps=1e-06, elementwise_affine=True) ) (dcn): FlashDCNv3( (offset_mask_dw): Conv2d(896, 896, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=896) (offset_mask): Linear(in_features=896, out_features=1512, bias=True) (value_proj): Linear(in_features=896, out_features=896, bias=True) (output_proj): Linear(in_features=896, out_features=896, bias=False) ) (drop_path): DropPath(drop_prob=0.400) (norm2): Sequential( (0): LayerNorm((896,), eps=1e-06, elementwise_affine=True) ) (mlp): MLPLayer( (fc1): Linear(in_features=896, out_features=3584, bias=True) (act): GELU(approximate=none) (fc2): Linear(in_features=3584, out_features=896, bias=False) (drop): Dropout(p=0.0, inplace=False) ) ) ) ) ) ) (neck): FPN_vitdet( (lateral_convs): ModuleList( (0): ConvModule_Norm( (conv): Conv2d(112, 256, kernel_size=(1, 1), stride=(1, 1), bias=False) (ln): LayerNorm((256,), eps=1e-05, elementwise_affine=True) ) (1): ConvModule_Norm( (conv): Conv2d(224, 256, kernel_size=(1, 1), stride=(1, 1), bias=False) (ln): LayerNorm((256,), eps=1e-05, elementwise_affine=True) ) (2): ConvModule_Norm( (conv): Conv2d(448, 256, kernel_size=(1, 1), stride=(1, 1), bias=False) (ln): LayerNorm((256,), eps=1e-05, elementwise_affine=True) ) (3): ConvModule_Norm( (conv): Conv2d(896, 256, kernel_size=(1, 1), stride=(1, 1), bias=False) (ln): LayerNorm((256,), eps=1e-05, elementwise_affine=True) ) ) (fpn_convs): ModuleList( (0): ConvModule_Norm( (conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (ln): LayerNorm((256,), eps=1e-05, elementwise_affine=True) ) (1): ConvModule_Norm( (conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (ln): LayerNorm((256,), eps=1e-05, elementwise_affine=True) ) (2): ConvModule_Norm( (conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (ln): LayerNorm((256,), eps=1e-05, elementwise_affine=True) ) (3): ConvModule_Norm( (conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (ln): LayerNorm((256,), eps=1e-05, elementwise_affine=True) ) ) ) init_cfg={'type': 'Xavier', 'layer': 'Conv2d', 'distribution': 'uniform'} (rpn_head): RPNHead( (loss_cls): CrossEntropyLoss(avg_non_ignore=False) (loss_bbox): L1Loss() (rpn_conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (rpn_cls): Conv2d(256, 3, kernel_size=(1, 1), stride=(1, 1)) (rpn_reg): Conv2d(256, 12, kernel_size=(1, 1), stride=(1, 1)) ) init_cfg={'type': 'Normal', 'layer': 'Conv2d', 'std': 0.01} (roi_head): StandardRoIHead( (bbox_roi_extractor): SingleRoIExtractor( (roi_layers): ModuleList( (0): RoIAlign(output_size=(7, 7), spatial_scale=0.25, sampling_ratio=0, pool_mode=avg, aligned=True, use_torchvision=False) (1): RoIAlign(output_size=(7, 7), spatial_scale=0.125, sampling_ratio=0, pool_mode=avg, aligned=True, use_torchvision=False) (2): RoIAlign(output_size=(7, 7), spatial_scale=0.0625, sampling_ratio=0, pool_mode=avg, aligned=True, use_torchvision=False) (3): RoIAlign(output_size=(7, 7), spatial_scale=0.03125, sampling_ratio=0, pool_mode=avg, aligned=True, use_torchvision=False) ) ) (bbox_head): Shared2FCBBoxHead( (loss_cls): CrossEntropyLoss(avg_non_ignore=False) (loss_bbox): L1Loss() (fc_cls): Linear(in_features=1024, out_features=81, bias=True) (fc_reg): Linear(in_features=1024, out_features=320, bias=True) (shared_convs): ModuleList() (shared_fcs): ModuleList( (0): Linear(in_features=12544, out_features=1024, bias=True) (1): Linear(in_features=1024, out_features=1024, bias=True) ) (cls_convs): ModuleList() (cls_fcs): ModuleList() (reg_convs): ModuleList() (reg_fcs): ModuleList() (relu): ReLU(inplace=True) ) init_cfg=[{'type': 'Normal', 'std': 0.01, 'override': {'name': 'fc_cls'}}, {'type': 'Normal', 'std': 0.001, 'override': {'name': 'fc_reg'}}, {'type': 'Xavier', 'distribution': 'uniform', 'override': [{'name': 'shared_fcs'}, {'name': 'cls_fcs'}, {'name': 'reg_fcs'}]}] (mask_roi_extractor): SingleRoIExtractor( (roi_layers): ModuleList( (0): RoIAlign(output_size=(14, 14), spatial_scale=0.25, sampling_ratio=0, pool_mode=avg, aligned=True, use_torchvision=False) (1): RoIAlign(output_size=(14, 14), spatial_scale=0.125, sampling_ratio=0, pool_mode=avg, aligned=True, use_torchvision=False) (2): RoIAlign(output_size=(14, 14), spatial_scale=0.0625, sampling_ratio=0, pool_mode=avg, aligned=True, use_torchvision=False) (3): RoIAlign(output_size=(14, 14), spatial_scale=0.03125, sampling_ratio=0, pool_mode=avg, aligned=True, use_torchvision=False) ) ) (mask_head): FCNMaskHead( (loss_mask): CrossEntropyLoss(avg_non_ignore=False) (convs): ModuleList( (0): ConvModule( (conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (activate): ReLU(inplace=True) ) (1): ConvModule( (conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (activate): ReLU(inplace=True) ) (2): ConvModule( (conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (activate): ReLU(inplace=True) ) (3): ConvModule( (conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (activate): ReLU(inplace=True) ) ) (upsample): ConvTranspose2d(256, 256, kernel_size=(2, 2), stride=(2, 2)) (conv_logits): Conv2d(256, 80, kernel_size=(1, 1), stride=(1, 1)) (relu): ReLU(inplace=True) ) ) ) 2023-11-16 16:50:57,846 - mmdet - INFO - Automatic scaling of learning rate (LR) has been disabled. 2023-11-16 16:50:57,846 - mmdet - INFO - {'num_layers': 33, 'layer_decay_rate': 0.9, 'depths': [4, 4, 21, 4], 'offset_lr_scale': 0.01} 2023-11-16 16:50:57,846 - mmdet - INFO - Build CustomLayerDecayOptimizerConstructor 0.900000 - 35 2023-11-16 16:50:57,851 - mmdet - INFO - Param groups = { "layer_0_decay": { "param_names": [ "backbone.patch_embed.conv1.weight", "backbone.patch_embed.conv2.weight" ], "lr_scale": 0.027812838944369374, "lr": 5.562567788873875e-06, "weight_decay": 0.05 }, "layer_0_no_decay": { "param_names": [ "backbone.patch_embed.conv1.bias", "backbone.patch_embed.norm1.1.weight", "backbone.patch_embed.norm1.1.bias", "backbone.patch_embed.conv2.bias", "backbone.patch_embed.norm2.1.weight", "backbone.patch_embed.norm2.1.bias" ], "lr_scale": 0.027812838944369374, "lr": 5.562567788873875e-06, "weight_decay": 0.0 }, "layer_1_no_decay": { "param_names": [ "backbone.levels.0.blocks.0.gamma1", "backbone.levels.0.blocks.0.gamma2", "backbone.levels.0.blocks.0.norm1.0.weight", "backbone.levels.0.blocks.0.norm1.0.bias", "backbone.levels.0.blocks.0.dcn.offset_mask_dw.bias", "backbone.levels.0.blocks.0.dcn.value_proj.bias", "backbone.levels.0.blocks.0.norm2.0.weight", "backbone.levels.0.blocks.0.norm2.0.bias", "backbone.levels.0.blocks.0.mlp.fc1.bias" ], "lr_scale": 0.030903154382632636, "lr": 6.180630876526528e-06, "weight_decay": 0.0 }, "layer_1_decay": { "param_names": [ "backbone.levels.0.blocks.0.dcn.offset_mask_dw.weight", "backbone.levels.0.blocks.0.dcn.value_proj.weight", "backbone.levels.0.blocks.0.dcn.output_proj.weight", "backbone.levels.0.blocks.0.mlp.fc1.weight", "backbone.levels.0.blocks.0.mlp.fc2.weight" ], "lr_scale": 0.030903154382632636, "lr": 6.180630876526528e-06, "weight_decay": 0.05 }, "layer_1_decay_offset_lr_scale": { "param_names": [ "backbone.levels.0.blocks.0.dcn.offset_mask.weight" ], "lr_scale": 0.00030903154382632634, "lr": 6.180630876526527e-08, "weight_decay": 0.05 }, "layer_1_no_decay_offset_lr_scale": { "param_names": [ "backbone.levels.0.blocks.0.dcn.offset_mask.bias" ], "lr_scale": 0.00030903154382632634, "lr": 6.180630876526527e-08, "weight_decay": 0.0 }, "layer_2_no_decay": { "param_names": [ "backbone.levels.0.blocks.1.gamma1", "backbone.levels.0.blocks.1.gamma2", "backbone.levels.0.blocks.1.norm1.0.weight", "backbone.levels.0.blocks.1.norm1.0.bias", "backbone.levels.0.blocks.1.dcn.offset_mask_dw.bias", "backbone.levels.0.blocks.1.dcn.value_proj.bias", "backbone.levels.0.blocks.1.norm2.0.weight", "backbone.levels.0.blocks.1.norm2.0.bias", "backbone.levels.0.blocks.1.mlp.fc1.bias" ], "lr_scale": 0.03433683820292515, "lr": 6.8673676405850304e-06, "weight_decay": 0.0 }, "layer_2_decay": { "param_names": [ "backbone.levels.0.blocks.1.dcn.offset_mask_dw.weight", "backbone.levels.0.blocks.1.dcn.value_proj.weight", "backbone.levels.0.blocks.1.dcn.output_proj.weight", "backbone.levels.0.blocks.1.mlp.fc1.weight", "backbone.levels.0.blocks.1.mlp.fc2.weight" ], "lr_scale": 0.03433683820292515, "lr": 6.8673676405850304e-06, "weight_decay": 0.05 }, "layer_2_decay_offset_lr_scale": { "param_names": [ "backbone.levels.0.blocks.1.dcn.offset_mask.weight" ], "lr_scale": 0.00034336838202925153, "lr": 6.86736764058503e-08, "weight_decay": 0.05 }, "layer_2_no_decay_offset_lr_scale": { "param_names": [ "backbone.levels.0.blocks.1.dcn.offset_mask.bias" ], "lr_scale": 0.00034336838202925153, "lr": 6.86736764058503e-08, "weight_decay": 0.0 }, "layer_3_no_decay": { "param_names": [ "backbone.levels.0.blocks.2.gamma1", "backbone.levels.0.blocks.2.gamma2", "backbone.levels.0.blocks.2.norm1.0.weight", "backbone.levels.0.blocks.2.norm1.0.bias", "backbone.levels.0.blocks.2.dcn.offset_mask_dw.bias", "backbone.levels.0.blocks.2.dcn.value_proj.bias", "backbone.levels.0.blocks.2.norm2.0.weight", "backbone.levels.0.blocks.2.norm2.0.bias", "backbone.levels.0.blocks.2.mlp.fc1.bias" ], "lr_scale": 0.038152042447694615, "lr": 7.630408489538923e-06, "weight_decay": 0.0 }, "layer_3_decay": { "param_names": [ "backbone.levels.0.blocks.2.dcn.offset_mask_dw.weight", "backbone.levels.0.blocks.2.dcn.value_proj.weight", "backbone.levels.0.blocks.2.dcn.output_proj.weight", "backbone.levels.0.blocks.2.mlp.fc1.weight", "backbone.levels.0.blocks.2.mlp.fc2.weight" ], "lr_scale": 0.038152042447694615, "lr": 7.630408489538923e-06, "weight_decay": 0.05 }, "layer_3_decay_offset_lr_scale": { "param_names": [ "backbone.levels.0.blocks.2.dcn.offset_mask.weight" ], "lr_scale": 0.00038152042447694615, "lr": 7.630408489538923e-08, "weight_decay": 0.05 }, "layer_3_no_decay_offset_lr_scale": { "param_names": [ "backbone.levels.0.blocks.2.dcn.offset_mask.bias" ], "lr_scale": 0.00038152042447694615, "lr": 7.630408489538923e-08, "weight_decay": 0.0 }, "layer_4_no_decay": { "param_names": [ "backbone.levels.0.blocks.3.gamma1", "backbone.levels.0.blocks.3.gamma2", "backbone.levels.0.blocks.3.norm1.0.weight", "backbone.levels.0.blocks.3.norm1.0.bias", "backbone.levels.0.blocks.3.dcn.offset_mask_dw.bias", "backbone.levels.0.blocks.3.dcn.value_proj.bias", "backbone.levels.0.blocks.3.norm2.0.weight", "backbone.levels.0.blocks.3.norm2.0.bias", "backbone.levels.0.blocks.3.mlp.fc1.bias" ], "lr_scale": 0.04239115827521624, "lr": 8.478231655043248e-06, "weight_decay": 0.0 }, "layer_4_decay": { "param_names": [ "backbone.levels.0.blocks.3.dcn.offset_mask_dw.weight", "backbone.levels.0.blocks.3.dcn.value_proj.weight", "backbone.levels.0.blocks.3.dcn.output_proj.weight", "backbone.levels.0.blocks.3.mlp.fc1.weight", "backbone.levels.0.blocks.3.mlp.fc2.weight" ], "lr_scale": 0.04239115827521624, "lr": 8.478231655043248e-06, "weight_decay": 0.05 }, "layer_4_decay_offset_lr_scale": { "param_names": [ "backbone.levels.0.blocks.3.dcn.offset_mask.weight" ], "lr_scale": 0.0004239115827521624, "lr": 8.478231655043248e-08, "weight_decay": 0.05 }, "layer_4_no_decay_offset_lr_scale": { "param_names": [ "backbone.levels.0.blocks.3.dcn.offset_mask.bias" ], "lr_scale": 0.0004239115827521624, "lr": 8.478231655043248e-08, "weight_decay": 0.0 }, "layer_5_decay": { "param_names": [ "backbone.levels.0.downsample.conv.weight", "backbone.levels.1.blocks.0.dcn.offset_mask_dw.weight", "backbone.levels.1.blocks.0.dcn.value_proj.weight", "backbone.levels.1.blocks.0.dcn.output_proj.weight", "backbone.levels.1.blocks.0.mlp.fc1.weight", "backbone.levels.1.blocks.0.mlp.fc2.weight" ], "lr_scale": 0.047101286972462485, "lr": 9.420257394492498e-06, "weight_decay": 0.05 }, "layer_5_no_decay": { "param_names": [ "backbone.levels.0.downsample.norm.1.weight", "backbone.levels.0.downsample.norm.1.bias", "backbone.levels.1.blocks.0.gamma1", "backbone.levels.1.blocks.0.gamma2", "backbone.levels.1.blocks.0.norm1.0.weight", "backbone.levels.1.blocks.0.norm1.0.bias", "backbone.levels.1.blocks.0.dcn.offset_mask_dw.bias", "backbone.levels.1.blocks.0.dcn.value_proj.bias", "backbone.levels.1.blocks.0.norm2.0.weight", "backbone.levels.1.blocks.0.norm2.0.bias", "backbone.levels.1.blocks.0.mlp.fc1.bias" ], "lr_scale": 0.047101286972462485, "lr": 9.420257394492498e-06, "weight_decay": 0.0 }, "layer_5_decay_offset_lr_scale": { "param_names": [ "backbone.levels.1.blocks.0.dcn.offset_mask.weight" ], "lr_scale": 0.0004710128697246249, "lr": 9.420257394492498e-08, "weight_decay": 0.05 }, "layer_5_no_decay_offset_lr_scale": { "param_names": [ "backbone.levels.1.blocks.0.dcn.offset_mask.bias" ], "lr_scale": 0.0004710128697246249, "lr": 9.420257394492498e-08, "weight_decay": 0.0 }, "layer_6_no_decay": { "param_names": [ "backbone.levels.1.blocks.1.gamma1", "backbone.levels.1.blocks.1.gamma2", "backbone.levels.1.blocks.1.norm1.0.weight", "backbone.levels.1.blocks.1.norm1.0.bias", "backbone.levels.1.blocks.1.dcn.offset_mask_dw.bias", "backbone.levels.1.blocks.1.dcn.value_proj.bias", "backbone.levels.1.blocks.1.norm2.0.weight", "backbone.levels.1.blocks.1.norm2.0.bias", "backbone.levels.1.blocks.1.mlp.fc1.bias" ], "lr_scale": 0.05233476330273609, "lr": 1.046695266054722e-05, "weight_decay": 0.0 }, "layer_6_decay": { "param_names": [ "backbone.levels.1.blocks.1.dcn.offset_mask_dw.weight", "backbone.levels.1.blocks.1.dcn.value_proj.weight", "backbone.levels.1.blocks.1.dcn.output_proj.weight", "backbone.levels.1.blocks.1.mlp.fc1.weight", "backbone.levels.1.blocks.1.mlp.fc2.weight" ], "lr_scale": 0.05233476330273609, "lr": 1.046695266054722e-05, "weight_decay": 0.05 }, "layer_6_decay_offset_lr_scale": { "param_names": [ "backbone.levels.1.blocks.1.dcn.offset_mask.weight" ], "lr_scale": 0.000523347633027361, "lr": 1.046695266054722e-07, "weight_decay": 0.05 }, "layer_6_no_decay_offset_lr_scale": { "param_names": [ "backbone.levels.1.blocks.1.dcn.offset_mask.bias" ], "lr_scale": 0.000523347633027361, "lr": 1.046695266054722e-07, "weight_decay": 0.0 }, "layer_7_no_decay": { "param_names": [ "backbone.levels.1.blocks.2.gamma1", "backbone.levels.1.blocks.2.gamma2", "backbone.levels.1.blocks.2.norm1.0.weight", "backbone.levels.1.blocks.2.norm1.0.bias", "backbone.levels.1.blocks.2.dcn.offset_mask_dw.bias", "backbone.levels.1.blocks.2.dcn.value_proj.bias", "backbone.levels.1.blocks.2.norm2.0.weight", "backbone.levels.1.blocks.2.norm2.0.bias", "backbone.levels.1.blocks.2.mlp.fc1.bias" ], "lr_scale": 0.058149737003040096, "lr": 1.1629947400608019e-05, "weight_decay": 0.0 }, "layer_7_decay": { "param_names": [ "backbone.levels.1.blocks.2.dcn.offset_mask_dw.weight", "backbone.levels.1.blocks.2.dcn.value_proj.weight", "backbone.levels.1.blocks.2.dcn.output_proj.weight", "backbone.levels.1.blocks.2.mlp.fc1.weight", "backbone.levels.1.blocks.2.mlp.fc2.weight" ], "lr_scale": 0.058149737003040096, "lr": 1.1629947400608019e-05, "weight_decay": 0.05 }, "layer_7_decay_offset_lr_scale": { "param_names": [ "backbone.levels.1.blocks.2.dcn.offset_mask.weight" ], "lr_scale": 0.000581497370030401, "lr": 1.162994740060802e-07, "weight_decay": 0.05 }, "layer_7_no_decay_offset_lr_scale": { "param_names": [ "backbone.levels.1.blocks.2.dcn.offset_mask.bias" ], "lr_scale": 0.000581497370030401, "lr": 1.162994740060802e-07, "weight_decay": 0.0 }, "layer_8_no_decay": { "param_names": [ "backbone.levels.1.blocks.3.gamma1", "backbone.levels.1.blocks.3.gamma2", "backbone.levels.1.blocks.3.norm1.0.weight", "backbone.levels.1.blocks.3.norm1.0.bias", "backbone.levels.1.blocks.3.dcn.offset_mask_dw.bias", "backbone.levels.1.blocks.3.dcn.value_proj.bias", "backbone.levels.1.blocks.3.norm2.0.weight", "backbone.levels.1.blocks.3.norm2.0.bias", "backbone.levels.1.blocks.3.mlp.fc1.bias" ], "lr_scale": 0.06461081889226677, "lr": 1.2922163778453355e-05, "weight_decay": 0.0 }, "layer_8_decay": { "param_names": [ "backbone.levels.1.blocks.3.dcn.offset_mask_dw.weight", "backbone.levels.1.blocks.3.dcn.value_proj.weight", "backbone.levels.1.blocks.3.dcn.output_proj.weight", "backbone.levels.1.blocks.3.mlp.fc1.weight", "backbone.levels.1.blocks.3.mlp.fc2.weight" ], "lr_scale": 0.06461081889226677, "lr": 1.2922163778453355e-05, "weight_decay": 0.05 }, "layer_8_decay_offset_lr_scale": { "param_names": [ "backbone.levels.1.blocks.3.dcn.offset_mask.weight" ], "lr_scale": 0.0006461081889226677, "lr": 1.2922163778453356e-07, "weight_decay": 0.05 }, "layer_8_no_decay_offset_lr_scale": { "param_names": [ "backbone.levels.1.blocks.3.dcn.offset_mask.bias" ], "lr_scale": 0.0006461081889226677, "lr": 1.2922163778453356e-07, "weight_decay": 0.0 }, "layer_9_decay": { "param_names": [ "backbone.levels.1.downsample.conv.weight", "backbone.levels.2.blocks.0.dcn.offset_mask_dw.weight", "backbone.levels.2.blocks.0.dcn.value_proj.weight", "backbone.levels.2.blocks.0.dcn.output_proj.weight", "backbone.levels.2.blocks.0.mlp.fc1.weight", "backbone.levels.2.blocks.0.mlp.fc2.weight" ], "lr_scale": 0.0717897987691853, "lr": 1.4357959753837061e-05, "weight_decay": 0.05 }, "layer_9_no_decay": { "param_names": [ "backbone.levels.1.downsample.norm.1.weight", "backbone.levels.1.downsample.norm.1.bias", "backbone.levels.2.blocks.0.gamma1", "backbone.levels.2.blocks.0.gamma2", "backbone.levels.2.blocks.0.norm1.0.weight", "backbone.levels.2.blocks.0.norm1.0.bias", "backbone.levels.2.blocks.0.dcn.offset_mask_dw.bias", "backbone.levels.2.blocks.0.dcn.value_proj.bias", "backbone.levels.2.blocks.0.norm2.0.weight", "backbone.levels.2.blocks.0.norm2.0.bias", "backbone.levels.2.blocks.0.mlp.fc1.bias" ], "lr_scale": 0.0717897987691853, "lr": 1.4357959753837061e-05, "weight_decay": 0.0 }, "layer_9_decay_offset_lr_scale": { "param_names": [ "backbone.levels.2.blocks.0.dcn.offset_mask.weight" ], "lr_scale": 0.000717897987691853, "lr": 1.435795975383706e-07, "weight_decay": 0.05 }, "layer_9_no_decay_offset_lr_scale": { "param_names": [ "backbone.levels.2.blocks.0.dcn.offset_mask.bias" ], "lr_scale": 0.000717897987691853, "lr": 1.435795975383706e-07, "weight_decay": 0.0 }, "layer_10_no_decay": { "param_names": [ "backbone.levels.2.blocks.1.gamma1", "backbone.levels.2.blocks.1.gamma2", "backbone.levels.2.blocks.1.norm1.0.weight", "backbone.levels.2.blocks.1.norm1.0.bias", "backbone.levels.2.blocks.1.dcn.offset_mask_dw.bias", "backbone.levels.2.blocks.1.dcn.value_proj.bias", "backbone.levels.2.blocks.1.norm2.0.weight", "backbone.levels.2.blocks.1.norm2.0.bias", "backbone.levels.2.blocks.1.mlp.fc1.bias" ], "lr_scale": 0.07976644307687256, "lr": 1.595328861537451e-05, "weight_decay": 0.0 }, "layer_10_decay": { "param_names": [ "backbone.levels.2.blocks.1.dcn.offset_mask_dw.weight", "backbone.levels.2.blocks.1.dcn.value_proj.weight", "backbone.levels.2.blocks.1.dcn.output_proj.weight", "backbone.levels.2.blocks.1.mlp.fc1.weight", "backbone.levels.2.blocks.1.mlp.fc2.weight" ], "lr_scale": 0.07976644307687256, "lr": 1.595328861537451e-05, "weight_decay": 0.05 }, "layer_10_decay_offset_lr_scale": { "param_names": [ "backbone.levels.2.blocks.1.dcn.offset_mask.weight" ], "lr_scale": 0.0007976644307687256, "lr": 1.5953288615374512e-07, "weight_decay": 0.05 }, "layer_10_no_decay_offset_lr_scale": { "param_names": [ "backbone.levels.2.blocks.1.dcn.offset_mask.bias" ], "lr_scale": 0.0007976644307687256, "lr": 1.5953288615374512e-07, "weight_decay": 0.0 }, "layer_11_no_decay": { "param_names": [ "backbone.levels.2.blocks.2.gamma1", "backbone.levels.2.blocks.2.gamma2", "backbone.levels.2.blocks.2.norm1.0.weight", "backbone.levels.2.blocks.2.norm1.0.bias", "backbone.levels.2.blocks.2.dcn.offset_mask_dw.bias", "backbone.levels.2.blocks.2.dcn.value_proj.bias", "backbone.levels.2.blocks.2.norm2.0.weight", "backbone.levels.2.blocks.2.norm2.0.bias", "backbone.levels.2.blocks.2.mlp.fc1.bias" ], "lr_scale": 0.08862938119652507, "lr": 1.7725876239305016e-05, "weight_decay": 0.0 }, "layer_11_decay": { "param_names": [ "backbone.levels.2.blocks.2.dcn.offset_mask_dw.weight", "backbone.levels.2.blocks.2.dcn.value_proj.weight", "backbone.levels.2.blocks.2.dcn.output_proj.weight", "backbone.levels.2.blocks.2.mlp.fc1.weight", "backbone.levels.2.blocks.2.mlp.fc2.weight" ], "lr_scale": 0.08862938119652507, "lr": 1.7725876239305016e-05, "weight_decay": 0.05 }, "layer_11_decay_offset_lr_scale": { "param_names": [ "backbone.levels.2.blocks.2.dcn.offset_mask.weight" ], "lr_scale": 0.0008862938119652507, "lr": 1.7725876239305015e-07, "weight_decay": 0.05 }, "layer_11_no_decay_offset_lr_scale": { "param_names": [ "backbone.levels.2.blocks.2.dcn.offset_mask.bias" ], "lr_scale": 0.0008862938119652507, "lr": 1.7725876239305015e-07, "weight_decay": 0.0 }, "layer_12_no_decay": { "param_names": [ "backbone.levels.2.blocks.3.gamma1", "backbone.levels.2.blocks.3.gamma2", "backbone.levels.2.blocks.3.norm1.0.weight", "backbone.levels.2.blocks.3.norm1.0.bias", "backbone.levels.2.blocks.3.dcn.offset_mask_dw.bias", "backbone.levels.2.blocks.3.dcn.value_proj.bias", "backbone.levels.2.blocks.3.norm2.0.weight", "backbone.levels.2.blocks.3.norm2.0.bias", "backbone.levels.2.blocks.3.mlp.fc1.bias" ], "lr_scale": 0.09847709021836118, "lr": 1.9695418043672237e-05, "weight_decay": 0.0 }, "layer_12_decay": { "param_names": [ "backbone.levels.2.blocks.3.dcn.offset_mask_dw.weight", "backbone.levels.2.blocks.3.dcn.value_proj.weight", "backbone.levels.2.blocks.3.dcn.output_proj.weight", "backbone.levels.2.blocks.3.mlp.fc1.weight", "backbone.levels.2.blocks.3.mlp.fc2.weight" ], "lr_scale": 0.09847709021836118, "lr": 1.9695418043672237e-05, "weight_decay": 0.05 }, "layer_12_decay_offset_lr_scale": { "param_names": [ "backbone.levels.2.blocks.3.dcn.offset_mask.weight" ], "lr_scale": 0.0009847709021836117, "lr": 1.9695418043672235e-07, "weight_decay": 0.05 }, "layer_12_no_decay_offset_lr_scale": { "param_names": [ "backbone.levels.2.blocks.3.dcn.offset_mask.bias" ], "lr_scale": 0.0009847709021836117, "lr": 1.9695418043672235e-07, "weight_decay": 0.0 }, "layer_13_no_decay": { "param_names": [ "backbone.levels.2.blocks.4.gamma1", "backbone.levels.2.blocks.4.gamma2", "backbone.levels.2.blocks.4.norm1.0.weight", "backbone.levels.2.blocks.4.norm1.0.bias", "backbone.levels.2.blocks.4.dcn.offset_mask_dw.bias", "backbone.levels.2.blocks.4.dcn.value_proj.bias", "backbone.levels.2.blocks.4.norm2.0.weight", "backbone.levels.2.blocks.4.norm2.0.bias", "backbone.levels.2.blocks.4.mlp.fc1.bias" ], "lr_scale": 0.10941898913151242, "lr": 2.1883797826302484e-05, "weight_decay": 0.0 }, "layer_13_decay": { "param_names": [ "backbone.levels.2.blocks.4.dcn.offset_mask_dw.weight", "backbone.levels.2.blocks.4.dcn.value_proj.weight", "backbone.levels.2.blocks.4.dcn.output_proj.weight", "backbone.levels.2.blocks.4.mlp.fc1.weight", "backbone.levels.2.blocks.4.mlp.fc2.weight" ], "lr_scale": 0.10941898913151242, "lr": 2.1883797826302484e-05, "weight_decay": 0.05 }, "layer_13_decay_offset_lr_scale": { "param_names": [ "backbone.levels.2.blocks.4.dcn.offset_mask.weight" ], "lr_scale": 0.0010941898913151243, "lr": 2.1883797826302487e-07, "weight_decay": 0.05 }, "layer_13_no_decay_offset_lr_scale": { "param_names": [ "backbone.levels.2.blocks.4.dcn.offset_mask.bias" ], "lr_scale": 0.0010941898913151243, "lr": 2.1883797826302487e-07, "weight_decay": 0.0 }, "layer_14_no_decay": { "param_names": [ "backbone.levels.2.blocks.5.gamma1", "backbone.levels.2.blocks.5.gamma2", "backbone.levels.2.blocks.5.norm1.0.weight", "backbone.levels.2.blocks.5.norm1.0.bias", "backbone.levels.2.blocks.5.dcn.offset_mask_dw.bias", "backbone.levels.2.blocks.5.dcn.value_proj.bias", "backbone.levels.2.blocks.5.norm2.0.weight", "backbone.levels.2.blocks.5.norm2.0.bias", "backbone.levels.2.blocks.5.mlp.fc1.bias" ], "lr_scale": 0.12157665459056935, "lr": 2.431533091811387e-05, "weight_decay": 0.0 }, "layer_14_decay": { "param_names": [ "backbone.levels.2.blocks.5.dcn.offset_mask_dw.weight", "backbone.levels.2.blocks.5.dcn.value_proj.weight", "backbone.levels.2.blocks.5.dcn.output_proj.weight", "backbone.levels.2.blocks.5.mlp.fc1.weight", "backbone.levels.2.blocks.5.mlp.fc2.weight" ], "lr_scale": 0.12157665459056935, "lr": 2.431533091811387e-05, "weight_decay": 0.05 }, "layer_14_decay_offset_lr_scale": { "param_names": [ "backbone.levels.2.blocks.5.dcn.offset_mask.weight" ], "lr_scale": 0.0012157665459056935, "lr": 2.4315330918113873e-07, "weight_decay": 0.05 }, "layer_14_no_decay_offset_lr_scale": { "param_names": [ "backbone.levels.2.blocks.5.dcn.offset_mask.bias" ], "lr_scale": 0.0012157665459056935, "lr": 2.4315330918113873e-07, "weight_decay": 0.0 }, "layer_15_no_decay": { "param_names": [ "backbone.levels.2.blocks.6.gamma1", "backbone.levels.2.blocks.6.gamma2", "backbone.levels.2.blocks.6.norm1.0.weight", "backbone.levels.2.blocks.6.norm1.0.bias", "backbone.levels.2.blocks.6.dcn.offset_mask_dw.bias", "backbone.levels.2.blocks.6.dcn.value_proj.bias", "backbone.levels.2.blocks.6.norm2.0.weight", "backbone.levels.2.blocks.6.norm2.0.bias", "backbone.levels.2.blocks.6.mlp.fc1.bias" ], "lr_scale": 0.13508517176729928, "lr": 2.7017034353459858e-05, "weight_decay": 0.0 }, "layer_15_decay": { "param_names": [ "backbone.levels.2.blocks.6.dcn.offset_mask_dw.weight", "backbone.levels.2.blocks.6.dcn.value_proj.weight", "backbone.levels.2.blocks.6.dcn.output_proj.weight", "backbone.levels.2.blocks.6.mlp.fc1.weight", "backbone.levels.2.blocks.6.mlp.fc2.weight" ], "lr_scale": 0.13508517176729928, "lr": 2.7017034353459858e-05, "weight_decay": 0.05 }, "layer_15_decay_offset_lr_scale": { "param_names": [ "backbone.levels.2.blocks.6.dcn.offset_mask.weight" ], "lr_scale": 0.0013508517176729928, "lr": 2.7017034353459856e-07, "weight_decay": 0.05 }, "layer_15_no_decay_offset_lr_scale": { "param_names": [ "backbone.levels.2.blocks.6.dcn.offset_mask.bias" ], "lr_scale": 0.0013508517176729928, "lr": 2.7017034353459856e-07, "weight_decay": 0.0 }, "layer_16_no_decay": { "param_names": [ "backbone.levels.2.blocks.7.gamma1", "backbone.levels.2.blocks.7.gamma2", "backbone.levels.2.blocks.7.norm1.0.weight", "backbone.levels.2.blocks.7.norm1.0.bias", "backbone.levels.2.blocks.7.dcn.offset_mask_dw.bias", "backbone.levels.2.blocks.7.dcn.value_proj.bias", "backbone.levels.2.blocks.7.norm2.0.weight", "backbone.levels.2.blocks.7.norm2.0.bias", "backbone.levels.2.blocks.7.mlp.fc1.bias" ], "lr_scale": 0.15009463529699918, "lr": 3.0018927059399838e-05, "weight_decay": 0.0 }, "layer_16_decay": { "param_names": [ "backbone.levels.2.blocks.7.dcn.offset_mask_dw.weight", "backbone.levels.2.blocks.7.dcn.value_proj.weight", "backbone.levels.2.blocks.7.dcn.output_proj.weight", "backbone.levels.2.blocks.7.mlp.fc1.weight", "backbone.levels.2.blocks.7.mlp.fc2.weight" ], "lr_scale": 0.15009463529699918, "lr": 3.0018927059399838e-05, "weight_decay": 0.05 }, "layer_16_decay_offset_lr_scale": { "param_names": [ "backbone.levels.2.blocks.7.dcn.offset_mask.weight" ], "lr_scale": 0.0015009463529699917, "lr": 3.0018927059399836e-07, "weight_decay": 0.05 }, "layer_16_no_decay_offset_lr_scale": { "param_names": [ "backbone.levels.2.blocks.7.dcn.offset_mask.bias" ], "lr_scale": 0.0015009463529699917, "lr": 3.0018927059399836e-07, "weight_decay": 0.0 }, "layer_17_no_decay": { "param_names": [ "backbone.levels.2.blocks.8.gamma1", "backbone.levels.2.blocks.8.gamma2", "backbone.levels.2.blocks.8.norm1.0.weight", "backbone.levels.2.blocks.8.norm1.0.bias", "backbone.levels.2.blocks.8.dcn.offset_mask_dw.bias", "backbone.levels.2.blocks.8.dcn.value_proj.bias", "backbone.levels.2.blocks.8.norm2.0.weight", "backbone.levels.2.blocks.8.norm2.0.bias", "backbone.levels.2.blocks.8.mlp.fc1.bias" ], "lr_scale": 0.16677181699666577, "lr": 3.3354363399333154e-05, "weight_decay": 0.0 }, "layer_17_decay": { "param_names": [ "backbone.levels.2.blocks.8.dcn.offset_mask_dw.weight", "backbone.levels.2.blocks.8.dcn.value_proj.weight", "backbone.levels.2.blocks.8.dcn.output_proj.weight", "backbone.levels.2.blocks.8.mlp.fc1.weight", "backbone.levels.2.blocks.8.mlp.fc2.weight" ], "lr_scale": 0.16677181699666577, "lr": 3.3354363399333154e-05, "weight_decay": 0.05 }, "layer_17_decay_offset_lr_scale": { "param_names": [ "backbone.levels.2.blocks.8.dcn.offset_mask.weight" ], "lr_scale": 0.0016677181699666576, "lr": 3.3354363399333153e-07, "weight_decay": 0.05 }, "layer_17_no_decay_offset_lr_scale": { "param_names": [ "backbone.levels.2.blocks.8.dcn.offset_mask.bias" ], "lr_scale": 0.0016677181699666576, "lr": 3.3354363399333153e-07, "weight_decay": 0.0 }, "layer_18_no_decay": { "param_names": [ "backbone.levels.2.blocks.9.gamma1", "backbone.levels.2.blocks.9.gamma2", "backbone.levels.2.blocks.9.norm1.0.weight", "backbone.levels.2.blocks.9.norm1.0.bias", "backbone.levels.2.blocks.9.dcn.offset_mask_dw.bias", "backbone.levels.2.blocks.9.dcn.value_proj.bias", "backbone.levels.2.blocks.9.norm2.0.weight", "backbone.levels.2.blocks.9.norm2.0.bias", "backbone.levels.2.blocks.9.mlp.fc1.bias" ], "lr_scale": 0.18530201888518416, "lr": 3.706040377703683e-05, "weight_decay": 0.0 }, "layer_18_decay": { "param_names": [ "backbone.levels.2.blocks.9.dcn.offset_mask_dw.weight", "backbone.levels.2.blocks.9.dcn.value_proj.weight", "backbone.levels.2.blocks.9.dcn.output_proj.weight", "backbone.levels.2.blocks.9.mlp.fc1.weight", "backbone.levels.2.blocks.9.mlp.fc2.weight" ], "lr_scale": 0.18530201888518416, "lr": 3.706040377703683e-05, "weight_decay": 0.05 }, "layer_18_decay_offset_lr_scale": { "param_names": [ "backbone.levels.2.blocks.9.dcn.offset_mask.weight" ], "lr_scale": 0.0018530201888518416, "lr": 3.7060403777036834e-07, "weight_decay": 0.05 }, "layer_18_no_decay_offset_lr_scale": { "param_names": [ "backbone.levels.2.blocks.9.dcn.offset_mask.bias" ], "lr_scale": 0.0018530201888518416, "lr": 3.7060403777036834e-07, "weight_decay": 0.0 }, "layer_19_no_decay": { "param_names": [ "backbone.levels.2.blocks.10.gamma1", "backbone.levels.2.blocks.10.gamma2", "backbone.levels.2.blocks.10.norm1.0.weight", "backbone.levels.2.blocks.10.norm1.0.bias", "backbone.levels.2.blocks.10.dcn.offset_mask_dw.bias", "backbone.levels.2.blocks.10.dcn.value_proj.bias", "backbone.levels.2.blocks.10.norm2.0.weight", "backbone.levels.2.blocks.10.norm2.0.bias", "backbone.levels.2.blocks.10.mlp.fc1.bias" ], "lr_scale": 0.20589113209464907, "lr": 4.117822641892981e-05, "weight_decay": 0.0 }, "layer_19_decay": { "param_names": [ "backbone.levels.2.blocks.10.dcn.offset_mask_dw.weight", "backbone.levels.2.blocks.10.dcn.value_proj.weight", "backbone.levels.2.blocks.10.dcn.output_proj.weight", "backbone.levels.2.blocks.10.mlp.fc1.weight", "backbone.levels.2.blocks.10.mlp.fc2.weight" ], "lr_scale": 0.20589113209464907, "lr": 4.117822641892981e-05, "weight_decay": 0.05 }, "layer_19_decay_offset_lr_scale": { "param_names": [ "backbone.levels.2.blocks.10.dcn.offset_mask.weight" ], "lr_scale": 0.002058911320946491, "lr": 4.1178226418929816e-07, "weight_decay": 0.05 }, "layer_19_no_decay_offset_lr_scale": { "param_names": [ "backbone.levels.2.blocks.10.dcn.offset_mask.bias" ], "lr_scale": 0.002058911320946491, "lr": 4.1178226418929816e-07, "weight_decay": 0.0 }, "layer_20_no_decay": { "param_names": [ "backbone.levels.2.blocks.11.gamma1", "backbone.levels.2.blocks.11.gamma2", "backbone.levels.2.blocks.11.norm1.0.weight", "backbone.levels.2.blocks.11.norm1.0.bias", "backbone.levels.2.blocks.11.dcn.offset_mask_dw.bias", "backbone.levels.2.blocks.11.dcn.value_proj.bias", "backbone.levels.2.blocks.11.norm2.0.weight", "backbone.levels.2.blocks.11.norm2.0.bias", "backbone.levels.2.blocks.11.mlp.fc1.bias" ], "lr_scale": 0.2287679245496101, "lr": 4.575358490992202e-05, "weight_decay": 0.0 }, "layer_20_decay": { "param_names": [ "backbone.levels.2.blocks.11.dcn.offset_mask_dw.weight", "backbone.levels.2.blocks.11.dcn.value_proj.weight", "backbone.levels.2.blocks.11.dcn.output_proj.weight", "backbone.levels.2.blocks.11.mlp.fc1.weight", "backbone.levels.2.blocks.11.mlp.fc2.weight" ], "lr_scale": 0.2287679245496101, "lr": 4.575358490992202e-05, "weight_decay": 0.05 }, "layer_20_decay_offset_lr_scale": { "param_names": [ "backbone.levels.2.blocks.11.dcn.offset_mask.weight" ], "lr_scale": 0.002287679245496101, "lr": 4.575358490992202e-07, "weight_decay": 0.05 }, "layer_20_no_decay_offset_lr_scale": { "param_names": [ "backbone.levels.2.blocks.11.dcn.offset_mask.bias" ], "lr_scale": 0.002287679245496101, "lr": 4.575358490992202e-07, "weight_decay": 0.0 }, "layer_21_no_decay": { "param_names": [ "backbone.levels.2.blocks.12.gamma1", "backbone.levels.2.blocks.12.gamma2", "backbone.levels.2.blocks.12.norm1.0.weight", "backbone.levels.2.blocks.12.norm1.0.bias", "backbone.levels.2.blocks.12.dcn.offset_mask_dw.bias", "backbone.levels.2.blocks.12.dcn.value_proj.bias", "backbone.levels.2.blocks.12.norm2.0.weight", "backbone.levels.2.blocks.12.norm2.0.bias", "backbone.levels.2.blocks.12.mlp.fc1.bias" ], "lr_scale": 0.2541865828329001, "lr": 5.083731656658002e-05, "weight_decay": 0.0 }, "layer_21_decay": { "param_names": [ "backbone.levels.2.blocks.12.dcn.offset_mask_dw.weight", "backbone.levels.2.blocks.12.dcn.value_proj.weight", "backbone.levels.2.blocks.12.dcn.output_proj.weight", "backbone.levels.2.blocks.12.mlp.fc1.weight", "backbone.levels.2.blocks.12.mlp.fc2.weight" ], "lr_scale": 0.2541865828329001, "lr": 5.083731656658002e-05, "weight_decay": 0.05 }, "layer_21_decay_offset_lr_scale": { "param_names": [ "backbone.levels.2.blocks.12.dcn.offset_mask.weight" ], "lr_scale": 0.002541865828329001, "lr": 5.083731656658002e-07, "weight_decay": 0.05 }, "layer_21_no_decay_offset_lr_scale": { "param_names": [ "backbone.levels.2.blocks.12.dcn.offset_mask.bias" ], "lr_scale": 0.002541865828329001, "lr": 5.083731656658002e-07, "weight_decay": 0.0 }, "layer_22_no_decay": { "param_names": [ "backbone.levels.2.blocks.13.gamma1", "backbone.levels.2.blocks.13.gamma2", "backbone.levels.2.blocks.13.norm1.0.weight", "backbone.levels.2.blocks.13.norm1.0.bias", "backbone.levels.2.blocks.13.dcn.offset_mask_dw.bias", "backbone.levels.2.blocks.13.dcn.value_proj.bias", "backbone.levels.2.blocks.13.norm2.0.weight", "backbone.levels.2.blocks.13.norm2.0.bias", "backbone.levels.2.blocks.13.mlp.fc1.bias" ], "lr_scale": 0.2824295364810001, "lr": 5.648590729620002e-05, "weight_decay": 0.0 }, "layer_22_decay": { "param_names": [ "backbone.levels.2.blocks.13.dcn.offset_mask_dw.weight", "backbone.levels.2.blocks.13.dcn.value_proj.weight", "backbone.levels.2.blocks.13.dcn.output_proj.weight", "backbone.levels.2.blocks.13.mlp.fc1.weight", "backbone.levels.2.blocks.13.mlp.fc2.weight" ], "lr_scale": 0.2824295364810001, "lr": 5.648590729620002e-05, "weight_decay": 0.05 }, "layer_22_decay_offset_lr_scale": { "param_names": [ "backbone.levels.2.blocks.13.dcn.offset_mask.weight" ], "lr_scale": 0.0028242953648100013, "lr": 5.648590729620003e-07, "weight_decay": 0.05 }, "layer_22_no_decay_offset_lr_scale": { "param_names": [ "backbone.levels.2.blocks.13.dcn.offset_mask.bias" ], "lr_scale": 0.0028242953648100013, "lr": 5.648590729620003e-07, "weight_decay": 0.0 }, "layer_23_no_decay": { "param_names": [ "backbone.levels.2.blocks.14.gamma1", "backbone.levels.2.blocks.14.gamma2", "backbone.levels.2.blocks.14.norm1.0.weight", "backbone.levels.2.blocks.14.norm1.0.bias", "backbone.levels.2.blocks.14.dcn.offset_mask_dw.bias", "backbone.levels.2.blocks.14.dcn.value_proj.bias", "backbone.levels.2.blocks.14.norm2.0.weight", "backbone.levels.2.blocks.14.norm2.0.bias", "backbone.levels.2.blocks.14.mlp.fc1.bias" ], "lr_scale": 0.31381059609000006, "lr": 6.276211921800002e-05, "weight_decay": 0.0 }, "layer_23_decay": { "param_names": [ "backbone.levels.2.blocks.14.dcn.offset_mask_dw.weight", "backbone.levels.2.blocks.14.dcn.value_proj.weight", "backbone.levels.2.blocks.14.dcn.output_proj.weight", "backbone.levels.2.blocks.14.mlp.fc1.weight", "backbone.levels.2.blocks.14.mlp.fc2.weight" ], "lr_scale": 0.31381059609000006, "lr": 6.276211921800002e-05, "weight_decay": 0.05 }, "layer_23_decay_offset_lr_scale": { "param_names": [ "backbone.levels.2.blocks.14.dcn.offset_mask.weight" ], "lr_scale": 0.0031381059609000006, "lr": 6.276211921800002e-07, "weight_decay": 0.05 }, "layer_23_no_decay_offset_lr_scale": { "param_names": [ "backbone.levels.2.blocks.14.dcn.offset_mask.bias" ], "lr_scale": 0.0031381059609000006, "lr": 6.276211921800002e-07, "weight_decay": 0.0 }, "layer_24_no_decay": { "param_names": [ "backbone.levels.2.blocks.15.gamma1", "backbone.levels.2.blocks.15.gamma2", "backbone.levels.2.blocks.15.norm1.0.weight", "backbone.levels.2.blocks.15.norm1.0.bias", "backbone.levels.2.blocks.15.dcn.offset_mask_dw.bias", "backbone.levels.2.blocks.15.dcn.value_proj.bias", "backbone.levels.2.blocks.15.norm2.0.weight", "backbone.levels.2.blocks.15.norm2.0.bias", "backbone.levels.2.blocks.15.mlp.fc1.bias" ], "lr_scale": 0.3486784401000001, "lr": 6.973568802000002e-05, "weight_decay": 0.0 }, "layer_24_decay": { "param_names": [ "backbone.levels.2.blocks.15.dcn.offset_mask_dw.weight", "backbone.levels.2.blocks.15.dcn.value_proj.weight", "backbone.levels.2.blocks.15.dcn.output_proj.weight", "backbone.levels.2.blocks.15.mlp.fc1.weight", "backbone.levels.2.blocks.15.mlp.fc2.weight" ], "lr_scale": 0.3486784401000001, "lr": 6.973568802000002e-05, "weight_decay": 0.05 }, "layer_24_decay_offset_lr_scale": { "param_names": [ "backbone.levels.2.blocks.15.dcn.offset_mask.weight" ], "lr_scale": 0.003486784401000001, "lr": 6.973568802000003e-07, "weight_decay": 0.05 }, "layer_24_no_decay_offset_lr_scale": { "param_names": [ "backbone.levels.2.blocks.15.dcn.offset_mask.bias" ], "lr_scale": 0.003486784401000001, "lr": 6.973568802000003e-07, "weight_decay": 0.0 }, "layer_25_no_decay": { "param_names": [ "backbone.levels.2.blocks.16.gamma1", "backbone.levels.2.blocks.16.gamma2", "backbone.levels.2.blocks.16.norm1.0.weight", "backbone.levels.2.blocks.16.norm1.0.bias", "backbone.levels.2.blocks.16.dcn.offset_mask_dw.bias", "backbone.levels.2.blocks.16.dcn.value_proj.bias", "backbone.levels.2.blocks.16.norm2.0.weight", "backbone.levels.2.blocks.16.norm2.0.bias", "backbone.levels.2.blocks.16.mlp.fc1.bias" ], "lr_scale": 0.3874204890000001, "lr": 7.748409780000002e-05, "weight_decay": 0.0 }, "layer_25_decay": { "param_names": [ "backbone.levels.2.blocks.16.dcn.offset_mask_dw.weight", "backbone.levels.2.blocks.16.dcn.value_proj.weight", "backbone.levels.2.blocks.16.dcn.output_proj.weight", "backbone.levels.2.blocks.16.mlp.fc1.weight", "backbone.levels.2.blocks.16.mlp.fc2.weight" ], "lr_scale": 0.3874204890000001, "lr": 7.748409780000002e-05, "weight_decay": 0.05 }, "layer_25_decay_offset_lr_scale": { "param_names": [ "backbone.levels.2.blocks.16.dcn.offset_mask.weight" ], "lr_scale": 0.003874204890000001, "lr": 7.748409780000002e-07, "weight_decay": 0.05 }, "layer_25_no_decay_offset_lr_scale": { "param_names": [ "backbone.levels.2.blocks.16.dcn.offset_mask.bias" ], "lr_scale": 0.003874204890000001, "lr": 7.748409780000002e-07, "weight_decay": 0.0 }, "layer_26_no_decay": { "param_names": [ "backbone.levels.2.blocks.17.gamma1", "backbone.levels.2.blocks.17.gamma2", "backbone.levels.2.blocks.17.norm1.0.weight", "backbone.levels.2.blocks.17.norm1.0.bias", "backbone.levels.2.blocks.17.dcn.offset_mask_dw.bias", "backbone.levels.2.blocks.17.dcn.value_proj.bias", "backbone.levels.2.blocks.17.norm2.0.weight", "backbone.levels.2.blocks.17.norm2.0.bias", "backbone.levels.2.blocks.17.mlp.fc1.bias" ], "lr_scale": 0.4304672100000001, "lr": 8.609344200000003e-05, "weight_decay": 0.0 }, "layer_26_decay": { "param_names": [ "backbone.levels.2.blocks.17.dcn.offset_mask_dw.weight", "backbone.levels.2.blocks.17.dcn.value_proj.weight", "backbone.levels.2.blocks.17.dcn.output_proj.weight", "backbone.levels.2.blocks.17.mlp.fc1.weight", "backbone.levels.2.blocks.17.mlp.fc2.weight" ], "lr_scale": 0.4304672100000001, "lr": 8.609344200000003e-05, "weight_decay": 0.05 }, "layer_26_decay_offset_lr_scale": { "param_names": [ "backbone.levels.2.blocks.17.dcn.offset_mask.weight" ], "lr_scale": 0.004304672100000001, "lr": 8.609344200000002e-07, "weight_decay": 0.05 }, "layer_26_no_decay_offset_lr_scale": { "param_names": [ "backbone.levels.2.blocks.17.dcn.offset_mask.bias" ], "lr_scale": 0.004304672100000001, "lr": 8.609344200000002e-07, "weight_decay": 0.0 }, "layer_27_no_decay": { "param_names": [ "backbone.levels.2.blocks.18.gamma1", "backbone.levels.2.blocks.18.gamma2", "backbone.levels.2.blocks.18.norm1.0.weight", "backbone.levels.2.blocks.18.norm1.0.bias", "backbone.levels.2.blocks.18.dcn.offset_mask_dw.bias", "backbone.levels.2.blocks.18.dcn.value_proj.bias", "backbone.levels.2.blocks.18.norm2.0.weight", "backbone.levels.2.blocks.18.norm2.0.bias", "backbone.levels.2.blocks.18.mlp.fc1.bias" ], "lr_scale": 0.4782969000000001, "lr": 9.565938000000003e-05, "weight_decay": 0.0 }, "layer_27_decay": { "param_names": [ "backbone.levels.2.blocks.18.dcn.offset_mask_dw.weight", "backbone.levels.2.blocks.18.dcn.value_proj.weight", "backbone.levels.2.blocks.18.dcn.output_proj.weight", "backbone.levels.2.blocks.18.mlp.fc1.weight", "backbone.levels.2.blocks.18.mlp.fc2.weight" ], "lr_scale": 0.4782969000000001, "lr": 9.565938000000003e-05, "weight_decay": 0.05 }, "layer_27_decay_offset_lr_scale": { "param_names": [ "backbone.levels.2.blocks.18.dcn.offset_mask.weight" ], "lr_scale": 0.004782969000000001, "lr": 9.565938000000002e-07, "weight_decay": 0.05 }, "layer_27_no_decay_offset_lr_scale": { "param_names": [ "backbone.levels.2.blocks.18.dcn.offset_mask.bias" ], "lr_scale": 0.004782969000000001, "lr": 9.565938000000002e-07, "weight_decay": 0.0 }, "layer_28_no_decay": { "param_names": [ "backbone.levels.2.blocks.19.gamma1", "backbone.levels.2.blocks.19.gamma2", "backbone.levels.2.blocks.19.norm1.0.weight", "backbone.levels.2.blocks.19.norm1.0.bias", "backbone.levels.2.blocks.19.dcn.offset_mask_dw.bias", "backbone.levels.2.blocks.19.dcn.value_proj.bias", "backbone.levels.2.blocks.19.norm2.0.weight", "backbone.levels.2.blocks.19.norm2.0.bias", "backbone.levels.2.blocks.19.mlp.fc1.bias" ], "lr_scale": 0.531441, "lr": 0.00010628820000000001, "weight_decay": 0.0 }, "layer_28_decay": { "param_names": [ "backbone.levels.2.blocks.19.dcn.offset_mask_dw.weight", "backbone.levels.2.blocks.19.dcn.value_proj.weight", "backbone.levels.2.blocks.19.dcn.output_proj.weight", "backbone.levels.2.blocks.19.mlp.fc1.weight", "backbone.levels.2.blocks.19.mlp.fc2.weight" ], "lr_scale": 0.531441, "lr": 0.00010628820000000001, "weight_decay": 0.05 }, "layer_28_decay_offset_lr_scale": { "param_names": [ "backbone.levels.2.blocks.19.dcn.offset_mask.weight" ], "lr_scale": 0.00531441, "lr": 1.0628820000000002e-06, "weight_decay": 0.05 }, "layer_28_no_decay_offset_lr_scale": { "param_names": [ "backbone.levels.2.blocks.19.dcn.offset_mask.bias" ], "lr_scale": 0.00531441, "lr": 1.0628820000000002e-06, "weight_decay": 0.0 }, "layer_29_no_decay": { "param_names": [ "backbone.levels.2.blocks.20.gamma1", "backbone.levels.2.blocks.20.gamma2", "backbone.levels.2.blocks.20.norm1.0.weight", "backbone.levels.2.blocks.20.norm1.0.bias", "backbone.levels.2.blocks.20.dcn.offset_mask_dw.bias", "backbone.levels.2.blocks.20.dcn.value_proj.bias", "backbone.levels.2.blocks.20.norm2.0.weight", "backbone.levels.2.blocks.20.norm2.0.bias", "backbone.levels.2.blocks.20.mlp.fc1.bias" ], "lr_scale": 0.5904900000000001, "lr": 0.00011809800000000002, "weight_decay": 0.0 }, "layer_29_decay": { "param_names": [ "backbone.levels.2.blocks.20.dcn.offset_mask_dw.weight", "backbone.levels.2.blocks.20.dcn.value_proj.weight", "backbone.levels.2.blocks.20.dcn.output_proj.weight", "backbone.levels.2.blocks.20.mlp.fc1.weight", "backbone.levels.2.blocks.20.mlp.fc2.weight" ], "lr_scale": 0.5904900000000001, "lr": 0.00011809800000000002, "weight_decay": 0.05 }, "layer_29_decay_offset_lr_scale": { "param_names": [ "backbone.levels.2.blocks.20.dcn.offset_mask.weight" ], "lr_scale": 0.005904900000000001, "lr": 1.1809800000000003e-06, "weight_decay": 0.05 }, "layer_29_no_decay_offset_lr_scale": { "param_names": [ "backbone.levels.2.blocks.20.dcn.offset_mask.bias" ], "lr_scale": 0.005904900000000001, "lr": 1.1809800000000003e-06, "weight_decay": 0.0 }, "layer_30_decay": { "param_names": [ "backbone.levels.2.downsample.conv.weight", "backbone.levels.3.blocks.0.dcn.offset_mask_dw.weight", "backbone.levels.3.blocks.0.dcn.value_proj.weight", "backbone.levels.3.blocks.0.dcn.output_proj.weight", "backbone.levels.3.blocks.0.mlp.fc1.weight", "backbone.levels.3.blocks.0.mlp.fc2.weight" ], "lr_scale": 0.6561, "lr": 0.00013122, "weight_decay": 0.05 }, "layer_30_no_decay": { "param_names": [ "backbone.levels.2.downsample.norm.1.weight", "backbone.levels.2.downsample.norm.1.bias", "backbone.levels.3.blocks.0.gamma1", "backbone.levels.3.blocks.0.gamma2", "backbone.levels.3.blocks.0.norm1.0.weight", "backbone.levels.3.blocks.0.norm1.0.bias", "backbone.levels.3.blocks.0.dcn.offset_mask_dw.bias", "backbone.levels.3.blocks.0.dcn.value_proj.bias", "backbone.levels.3.blocks.0.norm2.0.weight", "backbone.levels.3.blocks.0.norm2.0.bias", "backbone.levels.3.blocks.0.mlp.fc1.bias" ], "lr_scale": 0.6561, "lr": 0.00013122, "weight_decay": 0.0 }, "layer_30_decay_offset_lr_scale": { "param_names": [ "backbone.levels.3.blocks.0.dcn.offset_mask.weight" ], "lr_scale": 0.006561, "lr": 1.3122000000000001e-06, "weight_decay": 0.05 }, "layer_30_no_decay_offset_lr_scale": { "param_names": [ "backbone.levels.3.blocks.0.dcn.offset_mask.bias" ], "lr_scale": 0.006561, "lr": 1.3122000000000001e-06, "weight_decay": 0.0 }, "layer_31_no_decay": { "param_names": [ "backbone.levels.3.blocks.1.gamma1", "backbone.levels.3.blocks.1.gamma2", "backbone.levels.3.blocks.1.norm1.0.weight", "backbone.levels.3.blocks.1.norm1.0.bias", "backbone.levels.3.blocks.1.dcn.offset_mask_dw.bias", "backbone.levels.3.blocks.1.dcn.value_proj.bias", "backbone.levels.3.blocks.1.norm2.0.weight", "backbone.levels.3.blocks.1.norm2.0.bias", "backbone.levels.3.blocks.1.mlp.fc1.bias" ], "lr_scale": 0.7290000000000001, "lr": 0.00014580000000000002, "weight_decay": 0.0 }, "layer_31_decay": { "param_names": [ "backbone.levels.3.blocks.1.dcn.offset_mask_dw.weight", "backbone.levels.3.blocks.1.dcn.value_proj.weight", "backbone.levels.3.blocks.1.dcn.output_proj.weight", "backbone.levels.3.blocks.1.mlp.fc1.weight", "backbone.levels.3.blocks.1.mlp.fc2.weight" ], "lr_scale": 0.7290000000000001, "lr": 0.00014580000000000002, "weight_decay": 0.05 }, "layer_31_decay_offset_lr_scale": { "param_names": [ "backbone.levels.3.blocks.1.dcn.offset_mask.weight" ], "lr_scale": 0.007290000000000001, "lr": 1.4580000000000003e-06, "weight_decay": 0.05 }, "layer_31_no_decay_offset_lr_scale": { "param_names": [ "backbone.levels.3.blocks.1.dcn.offset_mask.bias" ], "lr_scale": 0.007290000000000001, "lr": 1.4580000000000003e-06, "weight_decay": 0.0 }, "layer_32_no_decay": { "param_names": [ "backbone.levels.3.blocks.2.gamma1", "backbone.levels.3.blocks.2.gamma2", "backbone.levels.3.blocks.2.norm1.0.weight", "backbone.levels.3.blocks.2.norm1.0.bias", "backbone.levels.3.blocks.2.dcn.offset_mask_dw.bias", "backbone.levels.3.blocks.2.dcn.value_proj.bias", "backbone.levels.3.blocks.2.norm2.0.weight", "backbone.levels.3.blocks.2.norm2.0.bias", "backbone.levels.3.blocks.2.mlp.fc1.bias" ], "lr_scale": 0.81, "lr": 0.000162, "weight_decay": 0.0 }, "layer_32_decay": { "param_names": [ "backbone.levels.3.blocks.2.dcn.offset_mask_dw.weight", "backbone.levels.3.blocks.2.dcn.value_proj.weight", "backbone.levels.3.blocks.2.dcn.output_proj.weight", "backbone.levels.3.blocks.2.mlp.fc1.weight", "backbone.levels.3.blocks.2.mlp.fc2.weight" ], "lr_scale": 0.81, "lr": 0.000162, "weight_decay": 0.05 }, "layer_32_decay_offset_lr_scale": { "param_names": [ "backbone.levels.3.blocks.2.dcn.offset_mask.weight" ], "lr_scale": 0.008100000000000001, "lr": 1.6200000000000004e-06, "weight_decay": 0.05 }, "layer_32_no_decay_offset_lr_scale": { "param_names": [ "backbone.levels.3.blocks.2.dcn.offset_mask.bias" ], "lr_scale": 0.008100000000000001, "lr": 1.6200000000000004e-06, "weight_decay": 0.0 }, "layer_33_no_decay": { "param_names": [ "backbone.levels.3.blocks.3.gamma1", "backbone.levels.3.blocks.3.gamma2", "backbone.levels.3.blocks.3.norm1.0.weight", "backbone.levels.3.blocks.3.norm1.0.bias", "backbone.levels.3.blocks.3.dcn.offset_mask_dw.bias", "backbone.levels.3.blocks.3.dcn.value_proj.bias", "backbone.levels.3.blocks.3.norm2.0.weight", "backbone.levels.3.blocks.3.norm2.0.bias", "backbone.levels.3.blocks.3.mlp.fc1.bias" ], "lr_scale": 0.9, "lr": 0.00018, "weight_decay": 0.0 }, "layer_33_decay": { "param_names": [ "backbone.levels.3.blocks.3.dcn.offset_mask_dw.weight", "backbone.levels.3.blocks.3.dcn.value_proj.weight", "backbone.levels.3.blocks.3.dcn.output_proj.weight", "backbone.levels.3.blocks.3.mlp.fc1.weight", "backbone.levels.3.blocks.3.mlp.fc2.weight" ], "lr_scale": 0.9, "lr": 0.00018, "weight_decay": 0.05 }, "layer_33_decay_offset_lr_scale": { "param_names": [ "backbone.levels.3.blocks.3.dcn.offset_mask.weight" ], "lr_scale": 0.009000000000000001, "lr": 1.8000000000000003e-06, "weight_decay": 0.05 }, "layer_33_no_decay_offset_lr_scale": { "param_names": [ "backbone.levels.3.blocks.3.dcn.offset_mask.bias" ], "lr_scale": 0.009000000000000001, "lr": 1.8000000000000003e-06, "weight_decay": 0.0 }, "layer_34_decay": { "param_names": [ "neck.lateral_convs.0.conv.weight", "neck.lateral_convs.1.conv.weight", "neck.lateral_convs.2.conv.weight", "neck.lateral_convs.3.conv.weight", "neck.fpn_convs.0.conv.weight", "neck.fpn_convs.1.conv.weight", "neck.fpn_convs.2.conv.weight", "neck.fpn_convs.3.conv.weight", "rpn_head.rpn_conv.weight", "rpn_head.rpn_cls.weight", "rpn_head.rpn_reg.weight", "roi_head.bbox_head.fc_cls.weight", "roi_head.bbox_head.fc_reg.weight", "roi_head.bbox_head.shared_fcs.0.weight", "roi_head.bbox_head.shared_fcs.1.weight", "roi_head.mask_head.convs.0.conv.weight", "roi_head.mask_head.convs.1.conv.weight", "roi_head.mask_head.convs.2.conv.weight", "roi_head.mask_head.convs.3.conv.weight", "roi_head.mask_head.upsample.weight", "roi_head.mask_head.conv_logits.weight" ], "lr_scale": 1.0, "lr": 0.0002, "weight_decay": 0.05 }, "layer_34_no_decay": { "param_names": [ "neck.lateral_convs.0.ln.weight", "neck.lateral_convs.0.ln.bias", "neck.lateral_convs.1.ln.weight", "neck.lateral_convs.1.ln.bias", "neck.lateral_convs.2.ln.weight", "neck.lateral_convs.2.ln.bias", "neck.lateral_convs.3.ln.weight", "neck.lateral_convs.3.ln.bias", "neck.fpn_convs.0.ln.weight", "neck.fpn_convs.0.ln.bias", "neck.fpn_convs.1.ln.weight", "neck.fpn_convs.1.ln.bias", "neck.fpn_convs.2.ln.weight", "neck.fpn_convs.2.ln.bias", "neck.fpn_convs.3.ln.weight", "neck.fpn_convs.3.ln.bias", "rpn_head.rpn_conv.bias", "rpn_head.rpn_cls.bias", "rpn_head.rpn_reg.bias", "roi_head.bbox_head.fc_cls.bias", "roi_head.bbox_head.fc_reg.bias", "roi_head.bbox_head.shared_fcs.0.bias", "roi_head.bbox_head.shared_fcs.1.bias", "roi_head.mask_head.convs.0.conv.bias", "roi_head.mask_head.convs.1.conv.bias", "roi_head.mask_head.convs.2.conv.bias", "roi_head.mask_head.convs.3.conv.bias", "roi_head.mask_head.upsample.bias", "roi_head.mask_head.conv_logits.bias" ], "lr_scale": 1.0, "lr": 0.0002, "weight_decay": 0.0 } } 2023-11-16 16:50:58,587 - mmdet - INFO - Start running, host: lizhiqi@SH-IDC1-10-140-37-157, work_dir: /mnt/petrelfs/lizhiqi/DINO/detection/work_dirs/mask_rcnn_flash_internimage_b_fpn_3x_cocoo_0.4_0.9_4x16 2023-11-16 16:50:58,588 - mmdet - INFO - Hooks will be executed in the following order: before_run: (VERY_HIGH ) StepLrUpdaterHook (NORMAL ) CheckpointHook (LOW ) DistEvalHook (VERY_LOW ) TextLoggerHook -------------------- before_train_epoch: (VERY_HIGH ) StepLrUpdaterHook (NORMAL ) NumClassCheckHook (NORMAL ) DistSamplerSeedHook (LOW ) IterTimerHook (LOW ) DistEvalHook (VERY_LOW ) TextLoggerHook -------------------- before_train_iter: (VERY_HIGH ) StepLrUpdaterHook (LOW ) IterTimerHook (LOW ) DistEvalHook -------------------- after_train_iter: (ABOVE_NORMAL) OptimizerHook (NORMAL ) CheckpointHook (LOW ) IterTimerHook (LOW ) DistEvalHook (VERY_LOW ) TextLoggerHook -------------------- after_train_epoch: (NORMAL ) CheckpointHook (LOW ) DistEvalHook (VERY_LOW ) TextLoggerHook -------------------- before_val_epoch: (NORMAL ) NumClassCheckHook (NORMAL ) DistSamplerSeedHook (LOW ) IterTimerHook (VERY_LOW ) TextLoggerHook -------------------- before_val_iter: (LOW ) IterTimerHook -------------------- after_val_iter: (LOW ) IterTimerHook -------------------- after_val_epoch: (VERY_LOW ) TextLoggerHook -------------------- after_run: (VERY_LOW ) TextLoggerHook -------------------- 2023-11-16 16:50:58,588 - mmdet - INFO - workflow: [('train', 1)], max: 36 epochs 2023-11-16 16:50:58,588 - mmdet - INFO - Checkpoints will be saved to /mnt/petrelfs/lizhiqi/DINO/detection/work_dirs/mask_rcnn_flash_internimage_b_fpn_3x_cocoo_0.4_0.9_4x16 by HardDiskBackend. 2023-11-16 16:51:45,306 - mmdet - INFO - Epoch [1][50/1833] lr: 5.501e-07, eta: 17:06:34, time: 0.934, data_time: 0.103, memory: 9197, loss_rpn_cls: 0.6509, loss_rpn_bbox: 0.0861, loss_cls: 2.8017, acc: 67.0706, loss_bbox: 0.0557, loss_mask: 0.7522, loss: 4.3467 2023-11-16 16:52:26,303 - mmdet - INFO - Epoch [1][100/1833] lr: 1.106e-06, eta: 16:03:07, time: 0.820, data_time: 0.036, memory: 9474, loss_rpn_cls: 0.3525, loss_rpn_bbox: 0.0784, loss_cls: 0.4824, acc: 94.3393, loss_bbox: 0.1985, loss_mask: 0.6886, loss: 1.8004 2023-11-16 16:53:07,597 - mmdet - INFO - Epoch [1][150/1833] lr: 1.662e-06, eta: 15:43:25, time: 0.825, data_time: 0.031, memory: 9474, loss_rpn_cls: 0.1970, loss_rpn_bbox: 0.0781, loss_cls: 0.4717, acc: 92.7944, loss_bbox: 0.2652, loss_mask: 0.6443, loss: 1.6563 2023-11-16 16:53:49,129 - mmdet - INFO - Epoch [1][200/1833] lr: 2.217e-06, eta: 15:34:53, time: 0.831, data_time: 0.031, memory: 9474, loss_rpn_cls: 0.1403, loss_rpn_bbox: 0.0746, loss_cls: 0.4749, acc: 92.0356, loss_bbox: 0.2995, loss_mask: 0.5808, loss: 1.5702 2023-11-16 16:54:31,252 - mmdet - INFO - Epoch [1][250/1833] lr: 2.773e-06, eta: 15:31:56, time: 0.842, data_time: 0.033, memory: 9909, loss_rpn_cls: 0.1060, loss_rpn_bbox: 0.0745, loss_cls: 0.4722, acc: 91.2870, loss_bbox: 0.3322, loss_mask: 0.5185, loss: 1.5034 2023-11-16 16:55:13,276 - mmdet - INFO - Epoch [1][300/1833] lr: 3.329e-06, eta: 15:29:23, time: 0.840, data_time: 0.029, memory: 9909, loss_rpn_cls: 0.0899, loss_rpn_bbox: 0.0661, loss_cls: 0.4369, acc: 90.9247, loss_bbox: 0.3421, loss_mask: 0.4723, loss: 1.4074 2023-11-16 16:55:56,131 - mmdet - INFO - Epoch [1][350/1833] lr: 3.884e-06, eta: 15:29:57, time: 0.857, data_time: 0.032, memory: 9909, loss_rpn_cls: 0.0831, loss_rpn_bbox: 0.0665, loss_cls: 0.4060, acc: 90.2369, loss_bbox: 0.3584, loss_mask: 0.4398, loss: 1.3539 2023-11-16 16:56:38,979 - mmdet - INFO - Epoch [1][400/1833] lr: 4.440e-06, eta: 15:30:11, time: 0.857, data_time: 0.034, memory: 9961, loss_rpn_cls: 0.0787, loss_rpn_bbox: 0.0660, loss_cls: 0.3689, acc: 90.0511, loss_bbox: 0.3641, loss_mask: 0.4140, loss: 1.2917 2023-11-16 16:57:22,025 - mmdet - INFO - Epoch [1][450/1833] lr: 4.996e-06, eta: 15:30:41, time: 0.861, data_time: 0.039, memory: 10122, loss_rpn_cls: 0.0726, loss_rpn_bbox: 0.0630, loss_cls: 0.3472, acc: 90.1732, loss_bbox: 0.3609, loss_mask: 0.3963, loss: 1.2401 2023-11-16 16:58:04,570 - mmdet - INFO - Epoch [1][500/1833] lr: 5.551e-06, eta: 15:29:51, time: 0.851, data_time: 0.033, memory: 10122, loss_rpn_cls: 0.0731, loss_rpn_bbox: 0.0617, loss_cls: 0.3270, acc: 90.2224, loss_bbox: 0.3597, loss_mask: 0.3838, loss: 1.2052 2023-11-16 16:58:48,231 - mmdet - INFO - Epoch [1][550/1833] lr: 5.563e-06, eta: 15:31:14, time: 0.873, data_time: 0.034, memory: 10122, loss_rpn_cls: 0.0721, loss_rpn_bbox: 0.0634, loss_cls: 0.3239, acc: 90.0828, loss_bbox: 0.3612, loss_mask: 0.3678, loss: 1.1884 2023-11-16 16:59:31,138 - mmdet - INFO - Epoch [1][600/1833] lr: 5.563e-06, eta: 15:30:54, time: 0.858, data_time: 0.028, memory: 10339, loss_rpn_cls: 0.0635, loss_rpn_bbox: 0.0596, loss_cls: 0.3003, acc: 90.6673, loss_bbox: 0.3394, loss_mask: 0.3496, loss: 1.1124 2023-11-16 17:00:14,727 - mmdet - INFO - Epoch [1][650/1833] lr: 5.563e-06, eta: 15:31:41, time: 0.872, data_time: 0.034, memory: 10339, loss_rpn_cls: 0.0653, loss_rpn_bbox: 0.0595, loss_cls: 0.3001, acc: 90.5177, loss_bbox: 0.3428, loss_mask: 0.3442, loss: 1.1119 2023-11-16 17:00:57,791 - mmdet - INFO - Epoch [1][700/1833] lr: 5.563e-06, eta: 15:31:24, time: 0.861, data_time: 0.031, memory: 10339, loss_rpn_cls: 0.0617, loss_rpn_bbox: 0.0594, loss_cls: 0.2910, acc: 90.7190, loss_bbox: 0.3341, loss_mask: 0.3407, loss: 1.0869 2023-11-16 17:01:40,577 - mmdet - INFO - Epoch [1][750/1833] lr: 5.563e-06, eta: 15:30:41, time: 0.856, data_time: 0.031, memory: 10339, loss_rpn_cls: 0.0590, loss_rpn_bbox: 0.0565, loss_cls: 0.2847, acc: 90.8121, loss_bbox: 0.3254, loss_mask: 0.3330, loss: 1.0587 2023-11-16 17:02:23,997 - mmdet - INFO - Epoch [1][800/1833] lr: 5.563e-06, eta: 15:30:48, time: 0.868, data_time: 0.038, memory: 10339, loss_rpn_cls: 0.0616, loss_rpn_bbox: 0.0574, loss_cls: 0.2876, acc: 90.8237, loss_bbox: 0.3269, loss_mask: 0.3286, loss: 1.0620 2023-11-16 17:03:06,882 - mmdet - INFO - Epoch [1][850/1833] lr: 5.563e-06, eta: 15:30:09, time: 0.858, data_time: 0.037, memory: 10339, loss_rpn_cls: 0.0583, loss_rpn_bbox: 0.0557, loss_cls: 0.2830, acc: 90.8003, loss_bbox: 0.3264, loss_mask: 0.3277, loss: 1.0511 2023-11-16 17:03:49,709 - mmdet - INFO - Epoch [1][900/1833] lr: 5.563e-06, eta: 15:29:23, time: 0.856, data_time: 0.032, memory: 10339, loss_rpn_cls: 0.0563, loss_rpn_bbox: 0.0544, loss_cls: 0.2726, acc: 91.0968, loss_bbox: 0.3166, loss_mask: 0.3157, loss: 1.0155 2023-11-16 17:04:32,851 - mmdet - INFO - Epoch [1][950/1833] lr: 5.563e-06, eta: 15:29:03, time: 0.863, data_time: 0.036, memory: 10339, loss_rpn_cls: 0.0549, loss_rpn_bbox: 0.0543, loss_cls: 0.2758, acc: 91.0068, loss_bbox: 0.3211, loss_mask: 0.3160, loss: 1.0221 2023-11-16 17:05:15,981 - mmdet - INFO - Exp name: mask_rcnn_flash_internimage_b_fpn_3x_coco_0.4_0.9-4x16.py 2023-11-16 17:05:15,981 - mmdet - INFO - Epoch [1][1000/1833] lr: 5.563e-06, eta: 15:28:38, time: 0.863, data_time: 0.034, memory: 10339, loss_rpn_cls: 0.0569, loss_rpn_bbox: 0.0547, loss_cls: 0.2761, acc: 90.9459, loss_bbox: 0.3211, loss_mask: 0.3137, loss: 1.0225 2023-11-16 17:05:59,370 - mmdet - INFO - Epoch [1][1050/1833] lr: 5.563e-06, eta: 15:28:26, time: 0.867, data_time: 0.035, memory: 10339, loss_rpn_cls: 0.0545, loss_rpn_bbox: 0.0526, loss_cls: 0.2695, acc: 91.1138, loss_bbox: 0.3135, loss_mask: 0.3125, loss: 1.0026 2023-11-16 17:06:43,329 - mmdet - INFO - Epoch [1][1100/1833] lr: 5.563e-06, eta: 15:28:47, time: 0.880, data_time: 0.035, memory: 10339, loss_rpn_cls: 0.0545, loss_rpn_bbox: 0.0535, loss_cls: 0.2663, acc: 91.0992, loss_bbox: 0.3120, loss_mask: 0.3079, loss: 0.9942 2023-11-16 17:07:26,484 - mmdet - INFO - Epoch [1][1150/1833] lr: 5.563e-06, eta: 15:28:17, time: 0.863, data_time: 0.035, memory: 10339, loss_rpn_cls: 0.0542, loss_rpn_bbox: 0.0539, loss_cls: 0.2694, acc: 91.1170, loss_bbox: 0.3143, loss_mask: 0.3074, loss: 0.9992 2023-11-16 17:08:09,862 - mmdet - INFO - Epoch [1][1200/1833] lr: 5.563e-06, eta: 15:27:57, time: 0.867, data_time: 0.036, memory: 10339, loss_rpn_cls: 0.0530, loss_rpn_bbox: 0.0554, loss_cls: 0.2660, acc: 91.1068, loss_bbox: 0.3123, loss_mask: 0.3057, loss: 0.9923 2023-11-16 17:08:52,904 - mmdet - INFO - Epoch [1][1250/1833] lr: 5.563e-06, eta: 15:27:18, time: 0.861, data_time: 0.030, memory: 10339, loss_rpn_cls: 0.0519, loss_rpn_bbox: 0.0516, loss_cls: 0.2599, acc: 91.3202, loss_bbox: 0.3052, loss_mask: 0.3021, loss: 0.9708 2023-11-16 17:09:36,367 - mmdet - INFO - Epoch [1][1300/1833] lr: 5.563e-06, eta: 15:26:58, time: 0.869, data_time: 0.033, memory: 10339, loss_rpn_cls: 0.0534, loss_rpn_bbox: 0.0522, loss_cls: 0.2617, acc: 91.3453, loss_bbox: 0.3053, loss_mask: 0.3025, loss: 0.9751 2023-11-16 17:10:20,322 - mmdet - INFO - Epoch [1][1350/1833] lr: 5.563e-06, eta: 15:27:02, time: 0.880, data_time: 0.034, memory: 10339, loss_rpn_cls: 0.0527, loss_rpn_bbox: 0.0534, loss_cls: 0.2633, acc: 91.1588, loss_bbox: 0.3134, loss_mask: 0.2998, loss: 0.9826 2023-11-16 17:11:03,494 - mmdet - INFO - Epoch [1][1400/1833] lr: 5.563e-06, eta: 15:26:26, time: 0.863, data_time: 0.034, memory: 10339, loss_rpn_cls: 0.0498, loss_rpn_bbox: 0.0504, loss_cls: 0.2566, acc: 91.3616, loss_bbox: 0.2990, loss_mask: 0.2925, loss: 0.9483 2023-11-16 17:11:46,864 - mmdet - INFO - Epoch [1][1450/1833] lr: 5.563e-06, eta: 15:25:58, time: 0.867, data_time: 0.033, memory: 10339, loss_rpn_cls: 0.0517, loss_rpn_bbox: 0.0513, loss_cls: 0.2619, acc: 91.2465, loss_bbox: 0.3016, loss_mask: 0.2975, loss: 0.9639 2023-11-16 17:12:30,025 - mmdet - INFO - Epoch [1][1500/1833] lr: 5.563e-06, eta: 15:25:20, time: 0.863, data_time: 0.035, memory: 10339, loss_rpn_cls: 0.0513, loss_rpn_bbox: 0.0517, loss_cls: 0.2580, acc: 91.4037, loss_bbox: 0.2990, loss_mask: 0.2942, loss: 0.9543 2023-11-16 17:13:13,312 - mmdet - INFO - Epoch [1][1550/1833] lr: 5.563e-06, eta: 15:24:47, time: 0.866, data_time: 0.032, memory: 10339, loss_rpn_cls: 0.0494, loss_rpn_bbox: 0.0506, loss_cls: 0.2535, acc: 91.4539, loss_bbox: 0.3012, loss_mask: 0.2892, loss: 0.9440 2023-11-16 17:13:56,726 - mmdet - INFO - Epoch [1][1600/1833] lr: 5.563e-06, eta: 15:24:18, time: 0.868, data_time: 0.031, memory: 10339, loss_rpn_cls: 0.0512, loss_rpn_bbox: 0.0505, loss_cls: 0.2593, acc: 91.2485, loss_bbox: 0.3029, loss_mask: 0.2926, loss: 0.9565 2023-11-16 17:14:40,328 - mmdet - INFO - Epoch [1][1650/1833] lr: 5.563e-06, eta: 15:23:56, time: 0.872, data_time: 0.033, memory: 10339, loss_rpn_cls: 0.0485, loss_rpn_bbox: 0.0506, loss_cls: 0.2565, acc: 91.3521, loss_bbox: 0.3005, loss_mask: 0.2933, loss: 0.9493 2023-11-16 17:15:23,175 - mmdet - INFO - Epoch [1][1700/1833] lr: 5.563e-06, eta: 15:23:04, time: 0.857, data_time: 0.032, memory: 10339, loss_rpn_cls: 0.0487, loss_rpn_bbox: 0.0500, loss_cls: 0.2545, acc: 91.4869, loss_bbox: 0.2964, loss_mask: 0.2896, loss: 0.9392 2023-11-16 17:16:06,610 - mmdet - INFO - Epoch [1][1750/1833] lr: 5.563e-06, eta: 15:22:34, time: 0.869, data_time: 0.039, memory: 10339, loss_rpn_cls: 0.0490, loss_rpn_bbox: 0.0506, loss_cls: 0.2513, acc: 91.5022, loss_bbox: 0.2983, loss_mask: 0.2903, loss: 0.9394 2023-11-16 17:16:49,895 - mmdet - INFO - Epoch [1][1800/1833] lr: 5.563e-06, eta: 15:21:58, time: 0.866, data_time: 0.038, memory: 10339, loss_rpn_cls: 0.0493, loss_rpn_bbox: 0.0496, loss_cls: 0.2501, acc: 91.4893, loss_bbox: 0.2986, loss_mask: 0.2888, loss: 0.9364 2023-11-16 17:17:19,589 - mmdet - INFO - Saving checkpoint at 1 epochs 2023-11-16 17:18:01,269 - mmdet - INFO - Evaluating bbox... 2023-11-16 17:18:38,994 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.325 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.584 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.332 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.214 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.361 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.413 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.473 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.473 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.473 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.322 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.516 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.582 2023-11-16 17:18:38,998 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.457 | bicycle | 0.244 | car | 0.349 | | motorcycle | 0.344 | airplane | 0.468 | bus | 0.529 | | train | 0.489 | truck | 0.286 | boat | 0.210 | | traffic light | 0.219 | fire hydrant | 0.553 | stop sign | 0.508 | | parking meter | 0.380 | bench | 0.190 | bird | 0.306 | | cat | 0.593 | dog | 0.496 | horse | 0.466 | | sheep | 0.394 | cow | 0.490 | elephant | 0.510 | | bear | 0.599 | zebra | 0.538 | giraffe | 0.540 | | backpack | 0.123 | umbrella | 0.262 | handbag | 0.119 | | tie | 0.208 | suitcase | 0.278 | frisbee | 0.533 | | skis | 0.122 | snowboard | 0.209 | sports ball | 0.403 | | kite | 0.326 | baseball bat | 0.218 | baseball glove | 0.328 | | skateboard | 0.362 | surfboard | 0.256 | tennis racket | 0.351 | | bottle | 0.332 | wine glass | 0.249 | cup | 0.383 | | fork | 0.146 | knife | 0.079 | spoon | 0.118 | | bowl | 0.360 | banana | 0.169 | apple | 0.177 | | sandwich | 0.321 | orange | 0.242 | broccoli | 0.192 | | carrot | 0.162 | hot dog | 0.252 | pizza | 0.403 | | donut | 0.379 | cake | 0.298 | chair | 0.218 | | couch | 0.333 | potted plant | 0.197 | bed | 0.351 | | dining table | 0.177 | toilet | 0.482 | tv | 0.510 | | laptop | 0.457 | mouse | 0.557 | remote | 0.231 | | keyboard | 0.380 | cell phone | 0.308 | microwave | 0.547 | | oven | 0.231 | toaster | 0.343 | sink | 0.320 | | refrigerator | 0.404 | book | 0.099 | clock | 0.472 | | vase | 0.314 | scissors | 0.090 | teddy bear | 0.353 | | hair drier | 0.055 | toothbrush | 0.050 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-16 17:18:38,998 - mmdet - INFO - Evaluating segm... 2023-11-16 17:19:25,005 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.320 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.551 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.331 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.166 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.353 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.466 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.457 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.457 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.457 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.287 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.498 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.597 2023-11-16 17:19:25,008 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.393 | bicycle | 0.150 | car | 0.327 | | motorcycle | 0.272 | airplane | 0.406 | bus | 0.570 | | train | 0.574 | truck | 0.318 | boat | 0.204 | | traffic light | 0.218 | fire hydrant | 0.605 | stop sign | 0.555 | | parking meter | 0.440 | bench | 0.137 | bird | 0.270 | | cat | 0.618 | dog | 0.543 | horse | 0.349 | | sheep | 0.385 | cow | 0.430 | elephant | 0.497 | | bear | 0.670 | zebra | 0.451 | giraffe | 0.381 | | backpack | 0.136 | umbrella | 0.397 | handbag | 0.144 | | tie | 0.215 | suitcase | 0.314 | frisbee | 0.581 | | skis | 0.006 | snowboard | 0.145 | sports ball | 0.402 | | kite | 0.241 | baseball bat | 0.164 | baseball glove | 0.374 | | skateboard | 0.215 | surfboard | 0.237 | tennis racket | 0.479 | | bottle | 0.334 | wine glass | 0.247 | cup | 0.405 | | fork | 0.071 | knife | 0.053 | spoon | 0.068 | | bowl | 0.371 | banana | 0.146 | apple | 0.183 | | sandwich | 0.363 | orange | 0.237 | broccoli | 0.192 | | carrot | 0.157 | hot dog | 0.215 | pizza | 0.425 | | donut | 0.415 | cake | 0.327 | chair | 0.153 | | couch | 0.291 | potted plant | 0.167 | bed | 0.281 | | dining table | 0.096 | toilet | 0.532 | tv | 0.551 | | laptop | 0.545 | mouse | 0.566 | remote | 0.240 | | keyboard | 0.426 | cell phone | 0.315 | microwave | 0.598 | | oven | 0.256 | toaster | 0.401 | sink | 0.325 | | refrigerator | 0.454 | book | 0.069 | clock | 0.503 | | vase | 0.322 | scissors | 0.086 | teddy bear | 0.357 | | hair drier | 0.048 | toothbrush | 0.019 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-16 17:19:29,188 - mmdet - INFO - Now best checkpoint is saved as best_bbox_mAP_epoch_1.pth. 2023-11-16 17:19:29,188 - mmdet - INFO - Best bbox_mAP is 0.3250 at 1 epoch. 2023-11-16 17:19:29,189 - mmdet - INFO - Exp name: mask_rcnn_flash_internimage_b_fpn_3x_coco_0.4_0.9-4x16.py 2023-11-16 17:19:29,189 - mmdet - INFO - Epoch(val) [1][313] bbox_mAP: 0.3250, bbox_mAP_50: 0.5836, bbox_mAP_75: 0.3317, bbox_mAP_s: 0.2136, bbox_mAP_m: 0.3610, bbox_mAP_l: 0.4130, bbox_mAP_copypaste: 0.3250 0.5836 0.3317 0.2136 0.3610 0.4130, segm_mAP: 0.3202, segm_mAP_50: 0.5513, segm_mAP_75: 0.3315, segm_mAP_s: 0.1663, segm_mAP_m: 0.3533, segm_mAP_l: 0.4662, segm_mAP_copypaste: 0.3202 0.5513 0.3315 0.1663 0.3533 0.4662 2023-11-16 17:20:16,214 - mmdet - INFO - Epoch [2][50/1833] lr: 5.563e-06, eta: 15:06:52, time: 0.940, data_time: 0.097, memory: 10339, loss_rpn_cls: 0.0471, loss_rpn_bbox: 0.0498, loss_cls: 0.2483, acc: 91.5378, loss_bbox: 0.2971, loss_mask: 0.2865, loss: 0.9288 2023-11-16 17:20:59,999 - mmdet - INFO - Epoch [2][100/1833] lr: 5.563e-06, eta: 15:06:54, time: 0.876, data_time: 0.035, memory: 10339, loss_rpn_cls: 0.0483, loss_rpn_bbox: 0.0506, loss_cls: 0.2490, acc: 91.5363, loss_bbox: 0.2957, loss_mask: 0.2858, loss: 0.9294 2023-11-16 17:21:43,448 - mmdet - INFO - Epoch [2][150/1833] lr: 5.563e-06, eta: 15:06:43, time: 0.869, data_time: 0.033, memory: 10339, loss_rpn_cls: 0.0457, loss_rpn_bbox: 0.0496, loss_cls: 0.2459, acc: 91.5480, loss_bbox: 0.2937, loss_mask: 0.2850, loss: 0.9199 2023-11-16 17:22:27,237 - mmdet - INFO - Epoch [2][200/1833] lr: 5.563e-06, eta: 15:06:41, time: 0.876, data_time: 0.037, memory: 10339, loss_rpn_cls: 0.0482, loss_rpn_bbox: 0.0490, loss_cls: 0.2424, acc: 91.7098, loss_bbox: 0.2927, loss_mask: 0.2836, loss: 0.9160 2023-11-16 17:23:10,759 - mmdet - INFO - Epoch [2][250/1833] lr: 5.563e-06, eta: 15:06:29, time: 0.870, data_time: 0.034, memory: 10339, loss_rpn_cls: 0.0455, loss_rpn_bbox: 0.0468, loss_cls: 0.2366, acc: 91.9437, loss_bbox: 0.2807, loss_mask: 0.2817, loss: 0.8914 2023-11-16 17:23:53,975 - mmdet - INFO - Epoch [2][300/1833] lr: 5.563e-06, eta: 15:06:06, time: 0.864, data_time: 0.035, memory: 10339, loss_rpn_cls: 0.0462, loss_rpn_bbox: 0.0467, loss_cls: 0.2346, acc: 91.9591, loss_bbox: 0.2821, loss_mask: 0.2801, loss: 0.8897 2023-11-16 17:24:37,606 - mmdet - INFO - Epoch [2][350/1833] lr: 5.563e-06, eta: 15:05:54, time: 0.873, data_time: 0.040, memory: 10339, loss_rpn_cls: 0.0476, loss_rpn_bbox: 0.0491, loss_cls: 0.2412, acc: 91.7412, loss_bbox: 0.2893, loss_mask: 0.2847, loss: 0.9119 2023-11-16 17:25:21,332 - mmdet - INFO - Epoch [2][400/1833] lr: 5.563e-06, eta: 15:05:44, time: 0.874, data_time: 0.033, memory: 10339, loss_rpn_cls: 0.0453, loss_rpn_bbox: 0.0485, loss_cls: 0.2424, acc: 91.6810, loss_bbox: 0.2906, loss_mask: 0.2778, loss: 0.9045 2023-11-16 17:26:05,006 - mmdet - INFO - Epoch [2][450/1833] lr: 5.563e-06, eta: 15:05:31, time: 0.873, data_time: 0.037, memory: 10339, loss_rpn_cls: 0.0455, loss_rpn_bbox: 0.0481, loss_cls: 0.2379, acc: 91.8697, loss_bbox: 0.2871, loss_mask: 0.2782, loss: 0.8969 2023-11-16 17:26:48,101 - mmdet - INFO - Epoch [2][500/1833] lr: 5.563e-06, eta: 15:05:00, time: 0.862, data_time: 0.038, memory: 10339, loss_rpn_cls: 0.0461, loss_rpn_bbox: 0.0498, loss_cls: 0.2432, acc: 91.6623, loss_bbox: 0.2898, loss_mask: 0.2792, loss: 0.9080 2023-11-16 17:27:31,768 - mmdet - INFO - Epoch [2][550/1833] lr: 5.563e-06, eta: 15:04:45, time: 0.873, data_time: 0.035, memory: 10339, loss_rpn_cls: 0.0455, loss_rpn_bbox: 0.0469, loss_cls: 0.2349, acc: 91.9806, loss_bbox: 0.2800, loss_mask: 0.2737, loss: 0.8812 2023-11-16 17:28:15,112 - mmdet - INFO - Epoch [2][600/1833] lr: 5.563e-06, eta: 15:04:20, time: 0.867, data_time: 0.034, memory: 10339, loss_rpn_cls: 0.0433, loss_rpn_bbox: 0.0462, loss_cls: 0.2354, acc: 92.0300, loss_bbox: 0.2773, loss_mask: 0.2731, loss: 0.8754 2023-11-16 17:28:58,889 - mmdet - INFO - Epoch [2][650/1833] lr: 5.563e-06, eta: 15:04:05, time: 0.876, data_time: 0.036, memory: 10339, loss_rpn_cls: 0.0433, loss_rpn_bbox: 0.0462, loss_cls: 0.2311, acc: 92.0242, loss_bbox: 0.2782, loss_mask: 0.2766, loss: 0.8754 2023-11-16 17:29:43,030 - mmdet - INFO - Epoch [2][700/1833] lr: 5.563e-06, eta: 15:03:58, time: 0.883, data_time: 0.035, memory: 10339, loss_rpn_cls: 0.0437, loss_rpn_bbox: 0.0471, loss_cls: 0.2402, acc: 91.7232, loss_bbox: 0.2859, loss_mask: 0.2748, loss: 0.8917 2023-11-16 17:30:26,108 - mmdet - INFO - Epoch [2][750/1833] lr: 5.563e-06, eta: 15:03:23, time: 0.861, data_time: 0.033, memory: 10339, loss_rpn_cls: 0.0455, loss_rpn_bbox: 0.0474, loss_cls: 0.2375, acc: 91.8621, loss_bbox: 0.2820, loss_mask: 0.2762, loss: 0.8885 2023-11-16 17:31:09,634 - mmdet - INFO - Epoch [2][800/1833] lr: 5.563e-06, eta: 15:03:00, time: 0.871, data_time: 0.040, memory: 10339, loss_rpn_cls: 0.0444, loss_rpn_bbox: 0.0472, loss_cls: 0.2340, acc: 91.8989, loss_bbox: 0.2803, loss_mask: 0.2742, loss: 0.8801 2023-11-16 17:31:52,954 - mmdet - INFO - Epoch [2][850/1833] lr: 5.563e-06, eta: 15:02:30, time: 0.866, data_time: 0.036, memory: 10339, loss_rpn_cls: 0.0442, loss_rpn_bbox: 0.0473, loss_cls: 0.2327, acc: 91.9499, loss_bbox: 0.2800, loss_mask: 0.2757, loss: 0.8798 2023-11-16 17:32:36,563 - mmdet - INFO - Epoch [2][900/1833] lr: 5.563e-06, eta: 15:02:07, time: 0.872, data_time: 0.036, memory: 10339, loss_rpn_cls: 0.0455, loss_rpn_bbox: 0.0477, loss_cls: 0.2331, acc: 92.0273, loss_bbox: 0.2818, loss_mask: 0.2726, loss: 0.8807 2023-11-16 17:33:20,196 - mmdet - INFO - Epoch [2][950/1833] lr: 5.563e-06, eta: 15:01:43, time: 0.873, data_time: 0.040, memory: 10339, loss_rpn_cls: 0.0439, loss_rpn_bbox: 0.0479, loss_cls: 0.2349, acc: 91.9512, loss_bbox: 0.2805, loss_mask: 0.2734, loss: 0.8805 2023-11-16 17:34:04,165 - mmdet - INFO - Epoch [2][1000/1833] lr: 5.563e-06, eta: 15:01:26, time: 0.879, data_time: 0.035, memory: 10339, loss_rpn_cls: 0.0430, loss_rpn_bbox: 0.0466, loss_cls: 0.2350, acc: 91.8628, loss_bbox: 0.2809, loss_mask: 0.2749, loss: 0.8805 2023-11-16 17:34:47,851 - mmdet - INFO - Epoch [2][1050/1833] lr: 5.563e-06, eta: 15:01:02, time: 0.874, data_time: 0.043, memory: 10339, loss_rpn_cls: 0.0431, loss_rpn_bbox: 0.0468, loss_cls: 0.2366, acc: 91.8136, loss_bbox: 0.2811, loss_mask: 0.2720, loss: 0.8796 2023-11-16 17:35:31,758 - mmdet - INFO - Epoch [2][1100/1833] lr: 5.563e-06, eta: 15:00:42, time: 0.878, data_time: 0.041, memory: 10339, loss_rpn_cls: 0.0429, loss_rpn_bbox: 0.0460, loss_cls: 0.2330, acc: 91.9651, loss_bbox: 0.2789, loss_mask: 0.2688, loss: 0.8697 2023-11-16 17:36:15,818 - mmdet - INFO - Epoch [2][1150/1833] lr: 5.563e-06, eta: 15:00:25, time: 0.882, data_time: 0.037, memory: 10339, loss_rpn_cls: 0.0440, loss_rpn_bbox: 0.0475, loss_cls: 0.2350, acc: 91.9448, loss_bbox: 0.2795, loss_mask: 0.2739, loss: 0.8799 2023-11-16 17:36:59,726 - mmdet - INFO - Epoch [2][1200/1833] lr: 5.563e-06, eta: 15:00:04, time: 0.878, data_time: 0.037, memory: 10339, loss_rpn_cls: 0.0430, loss_rpn_bbox: 0.0460, loss_cls: 0.2317, acc: 92.0286, loss_bbox: 0.2747, loss_mask: 0.2723, loss: 0.8677 2023-11-16 17:37:43,416 - mmdet - INFO - Epoch [2][1250/1833] lr: 5.563e-06, eta: 14:59:37, time: 0.874, data_time: 0.038, memory: 10339, loss_rpn_cls: 0.0430, loss_rpn_bbox: 0.0463, loss_cls: 0.2322, acc: 91.9443, loss_bbox: 0.2820, loss_mask: 0.2712, loss: 0.8747 2023-11-16 17:38:26,988 - mmdet - INFO - Epoch [2][1300/1833] lr: 5.563e-06, eta: 14:59:08, time: 0.871, data_time: 0.037, memory: 10339, loss_rpn_cls: 0.0435, loss_rpn_bbox: 0.0463, loss_cls: 0.2341, acc: 91.9813, loss_bbox: 0.2792, loss_mask: 0.2727, loss: 0.8758 2023-11-16 17:39:10,862 - mmdet - INFO - Epoch [2][1350/1833] lr: 5.563e-06, eta: 14:58:44, time: 0.877, data_time: 0.043, memory: 10339, loss_rpn_cls: 0.0441, loss_rpn_bbox: 0.0470, loss_cls: 0.2335, acc: 91.9386, loss_bbox: 0.2793, loss_mask: 0.2715, loss: 0.8753 2023-11-16 17:39:54,722 - mmdet - INFO - Epoch [2][1400/1833] lr: 5.563e-06, eta: 14:58:19, time: 0.877, data_time: 0.039, memory: 10339, loss_rpn_cls: 0.0426, loss_rpn_bbox: 0.0474, loss_cls: 0.2349, acc: 91.8963, loss_bbox: 0.2807, loss_mask: 0.2699, loss: 0.8754 2023-11-16 17:40:37,967 - mmdet - INFO - Epoch [2][1450/1833] lr: 5.563e-06, eta: 14:57:41, time: 0.864, data_time: 0.036, memory: 10339, loss_rpn_cls: 0.0413, loss_rpn_bbox: 0.0443, loss_cls: 0.2265, acc: 92.1400, loss_bbox: 0.2722, loss_mask: 0.2671, loss: 0.8513 2023-11-16 17:41:21,597 - mmdet - INFO - Epoch [2][1500/1833] lr: 5.563e-06, eta: 14:57:11, time: 0.873, data_time: 0.042, memory: 10339, loss_rpn_cls: 0.0410, loss_rpn_bbox: 0.0449, loss_cls: 0.2276, acc: 92.1807, loss_bbox: 0.2716, loss_mask: 0.2675, loss: 0.8527 2023-11-16 17:42:05,730 - mmdet - INFO - Epoch [2][1550/1833] lr: 5.563e-06, eta: 14:56:50, time: 0.883, data_time: 0.038, memory: 10339, loss_rpn_cls: 0.0408, loss_rpn_bbox: 0.0439, loss_cls: 0.2249, acc: 92.2203, loss_bbox: 0.2728, loss_mask: 0.2691, loss: 0.8515 2023-11-16 17:42:49,751 - mmdet - INFO - Epoch [2][1600/1833] lr: 5.563e-06, eta: 14:56:26, time: 0.880, data_time: 0.039, memory: 10339, loss_rpn_cls: 0.0416, loss_rpn_bbox: 0.0458, loss_cls: 0.2237, acc: 92.1987, loss_bbox: 0.2729, loss_mask: 0.2707, loss: 0.8547 2023-11-16 17:43:32,863 - mmdet - INFO - Epoch [2][1650/1833] lr: 5.563e-06, eta: 14:55:45, time: 0.862, data_time: 0.041, memory: 10339, loss_rpn_cls: 0.0406, loss_rpn_bbox: 0.0441, loss_cls: 0.2286, acc: 92.1378, loss_bbox: 0.2732, loss_mask: 0.2674, loss: 0.8539 2023-11-16 17:45:14,789 - mmdet - INFO - Epoch [2][1700/1833] lr: 5.563e-06, eta: 15:12:24, time: 2.039, data_time: 1.199, memory: 10339, loss_rpn_cls: 0.0412, loss_rpn_bbox: 0.0445, loss_cls: 0.2249, acc: 92.1813, loss_bbox: 0.2744, loss_mask: 0.2687, loss: 0.8537 2023-11-16 17:45:58,335 - mmdet - INFO - Epoch [2][1750/1833] lr: 5.563e-06, eta: 15:11:35, time: 0.871, data_time: 0.039, memory: 10339, loss_rpn_cls: 0.0412, loss_rpn_bbox: 0.0460, loss_cls: 0.2263, acc: 92.1751, loss_bbox: 0.2732, loss_mask: 0.2690, loss: 0.8558 2023-11-16 17:46:42,121 - mmdet - INFO - Epoch [2][1800/1833] lr: 5.563e-06, eta: 15:10:51, time: 0.876, data_time: 0.039, memory: 10339, loss_rpn_cls: 0.0404, loss_rpn_bbox: 0.0452, loss_cls: 0.2261, acc: 92.2033, loss_bbox: 0.2723, loss_mask: 0.2662, loss: 0.8501 2023-11-16 17:47:11,070 - mmdet - INFO - Saving checkpoint at 2 epochs 2023-11-16 17:47:50,008 - mmdet - INFO - Evaluating bbox... 2023-11-16 17:48:26,311 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.382 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.633 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.413 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.256 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.419 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.491 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.529 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.529 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.529 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.375 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.571 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.653 2023-11-16 17:48:26,314 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.510 | bicycle | 0.284 | car | 0.397 | | motorcycle | 0.374 | airplane | 0.564 | bus | 0.618 | | train | 0.585 | truck | 0.318 | boat | 0.235 | | traffic light | 0.268 | fire hydrant | 0.631 | stop sign | 0.591 | | parking meter | 0.469 | bench | 0.228 | bird | 0.341 | | cat | 0.649 | dog | 0.584 | horse | 0.548 | | sheep | 0.495 | cow | 0.535 | elephant | 0.605 | | bear | 0.707 | zebra | 0.588 | giraffe | 0.595 | | backpack | 0.148 | umbrella | 0.364 | handbag | 0.151 | | tie | 0.253 | suitcase | 0.325 | frisbee | 0.642 | | skis | 0.146 | snowboard | 0.313 | sports ball | 0.435 | | kite | 0.377 | baseball bat | 0.291 | baseball glove | 0.376 | | skateboard | 0.449 | surfboard | 0.329 | tennis racket | 0.411 | | bottle | 0.386 | wine glass | 0.300 | cup | 0.452 | | fork | 0.252 | knife | 0.163 | spoon | 0.141 | | bowl | 0.400 | banana | 0.214 | apple | 0.189 | | sandwich | 0.337 | orange | 0.297 | broccoli | 0.211 | | carrot | 0.185 | hot dog | 0.327 | pizza | 0.449 | | donut | 0.464 | cake | 0.372 | chair | 0.258 | | couch | 0.388 | potted plant | 0.244 | bed | 0.410 | | dining table | 0.229 | toilet | 0.529 | tv | 0.525 | | laptop | 0.548 | mouse | 0.583 | remote | 0.288 | | keyboard | 0.446 | cell phone | 0.373 | microwave | 0.603 | | oven | 0.326 | toaster | 0.286 | sink | 0.361 | | refrigerator | 0.494 | book | 0.112 | clock | 0.486 | | vase | 0.338 | scissors | 0.243 | teddy bear | 0.406 | | hair drier | 0.112 | toothbrush | 0.143 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-16 17:48:26,314 - mmdet - INFO - Evaluating segm... 2023-11-16 17:49:09,288 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.362 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.599 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.382 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.191 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.401 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.527 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.500 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.500 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.500 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.329 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.547 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.652 2023-11-16 17:49:09,290 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.446 | bicycle | 0.170 | car | 0.364 | | motorcycle | 0.312 | airplane | 0.468 | bus | 0.618 | | train | 0.598 | truck | 0.349 | boat | 0.222 | | traffic light | 0.258 | fire hydrant | 0.647 | stop sign | 0.603 | | parking meter | 0.504 | bench | 0.162 | bird | 0.297 | | cat | 0.684 | dog | 0.609 | horse | 0.392 | | sheep | 0.446 | cow | 0.467 | elephant | 0.549 | | bear | 0.726 | zebra | 0.489 | giraffe | 0.446 | | backpack | 0.163 | umbrella | 0.464 | handbag | 0.164 | | tie | 0.267 | suitcase | 0.367 | frisbee | 0.622 | | skis | 0.015 | snowboard | 0.218 | sports ball | 0.415 | | kite | 0.270 | baseball bat | 0.221 | baseball glove | 0.406 | | skateboard | 0.244 | surfboard | 0.291 | tennis racket | 0.524 | | bottle | 0.370 | wine glass | 0.283 | cup | 0.454 | | fork | 0.137 | knife | 0.115 | spoon | 0.116 | | bowl | 0.384 | banana | 0.176 | apple | 0.200 | | sandwich | 0.389 | orange | 0.302 | broccoli | 0.210 | | carrot | 0.168 | hot dog | 0.273 | pizza | 0.460 | | donut | 0.487 | cake | 0.395 | chair | 0.191 | | couch | 0.340 | potted plant | 0.216 | bed | 0.325 | | dining table | 0.134 | toilet | 0.567 | tv | 0.574 | | laptop | 0.609 | mouse | 0.595 | remote | 0.279 | | keyboard | 0.498 | cell phone | 0.370 | microwave | 0.628 | | oven | 0.304 | toaster | 0.358 | sink | 0.363 | | refrigerator | 0.511 | book | 0.078 | clock | 0.501 | | vase | 0.344 | scissors | 0.208 | teddy bear | 0.413 | | hair drier | 0.049 | toothbrush | 0.096 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-16 17:49:09,909 - mmdet - INFO - The previous best checkpoint /mnt/petrelfs/lizhiqi/DINO/detection/work_dirs/mask_rcnn_flash_internimage_b_fpn_3x_cocoo_0.4_0.9_4x16/best_bbox_mAP_epoch_1.pth was removed 2023-11-16 17:49:13,549 - mmdet - INFO - Now best checkpoint is saved as best_bbox_mAP_epoch_2.pth. 2023-11-16 17:49:13,550 - mmdet - INFO - Best bbox_mAP is 0.3825 at 2 epoch. 2023-11-16 17:49:13,550 - mmdet - INFO - Exp name: mask_rcnn_flash_internimage_b_fpn_3x_coco_0.4_0.9-4x16.py 2023-11-16 17:49:13,550 - mmdet - INFO - Epoch(val) [2][313] bbox_mAP: 0.3825, bbox_mAP_50: 0.6327, bbox_mAP_75: 0.4131, bbox_mAP_s: 0.2558, bbox_mAP_m: 0.4187, bbox_mAP_l: 0.4908, bbox_mAP_copypaste: 0.3825 0.6327 0.4131 0.2558 0.4187 0.4908, segm_mAP: 0.3618, segm_mAP_50: 0.5994, segm_mAP_75: 0.3817, segm_mAP_s: 0.1907, segm_mAP_m: 0.4006, segm_mAP_l: 0.5268, segm_mAP_copypaste: 0.3618 0.5994 0.3817 0.1907 0.4006 0.5268 2023-11-16 17:50:00,052 - mmdet - INFO - Epoch [3][50/1833] lr: 5.563e-06, eta: 15:02:17, time: 0.928, data_time: 0.102, memory: 10339, loss_rpn_cls: 0.0376, loss_rpn_bbox: 0.0438, loss_cls: 0.2228, acc: 92.2006, loss_bbox: 0.2700, loss_mask: 0.2644, loss: 0.8386 2023-11-16 17:50:43,487 - mmdet - INFO - Epoch [3][100/1833] lr: 5.563e-06, eta: 15:01:33, time: 0.869, data_time: 0.035, memory: 10339, loss_rpn_cls: 0.0410, loss_rpn_bbox: 0.0441, loss_cls: 0.2187, acc: 92.4407, loss_bbox: 0.2670, loss_mask: 0.2633, loss: 0.8340 2023-11-16 17:51:27,651 - mmdet - INFO - Epoch [3][150/1833] lr: 5.563e-06, eta: 15:01:01, time: 0.883, data_time: 0.035, memory: 10339, loss_rpn_cls: 0.0397, loss_rpn_bbox: 0.0447, loss_cls: 0.2216, acc: 92.2138, loss_bbox: 0.2689, loss_mask: 0.2667, loss: 0.8417 2023-11-16 17:52:11,960 - mmdet - INFO - Epoch [3][200/1833] lr: 5.563e-06, eta: 15:00:30, time: 0.886, data_time: 0.043, memory: 10339, loss_rpn_cls: 0.0412, loss_rpn_bbox: 0.0453, loss_cls: 0.2213, acc: 92.2399, loss_bbox: 0.2726, loss_mask: 0.2657, loss: 0.8462 2023-11-16 17:52:56,231 - mmdet - INFO - Epoch [3][250/1833] lr: 5.563e-06, eta: 14:59:59, time: 0.885, data_time: 0.035, memory: 10339, loss_rpn_cls: 0.0403, loss_rpn_bbox: 0.0455, loss_cls: 0.2203, acc: 92.3479, loss_bbox: 0.2682, loss_mask: 0.2635, loss: 0.8377 2023-11-16 17:53:39,861 - mmdet - INFO - Epoch [3][300/1833] lr: 5.563e-06, eta: 14:59:18, time: 0.873, data_time: 0.038, memory: 10339, loss_rpn_cls: 0.0421, loss_rpn_bbox: 0.0453, loss_cls: 0.2182, acc: 92.3205, loss_bbox: 0.2658, loss_mask: 0.2614, loss: 0.8327 2023-11-16 17:54:23,515 - mmdet - INFO - Epoch [3][350/1833] lr: 5.563e-06, eta: 14:58:37, time: 0.873, data_time: 0.038, memory: 10339, loss_rpn_cls: 0.0384, loss_rpn_bbox: 0.0441, loss_cls: 0.2155, acc: 92.4405, loss_bbox: 0.2634, loss_mask: 0.2620, loss: 0.8234 2023-11-16 17:55:06,827 - mmdet - INFO - Epoch [3][400/1833] lr: 5.563e-06, eta: 14:57:50, time: 0.866, data_time: 0.036, memory: 10339, loss_rpn_cls: 0.0405, loss_rpn_bbox: 0.0451, loss_cls: 0.2197, acc: 92.2855, loss_bbox: 0.2691, loss_mask: 0.2681, loss: 0.8425 2023-11-16 17:55:50,901 - mmdet - INFO - Epoch [3][450/1833] lr: 5.563e-06, eta: 14:57:15, time: 0.882, data_time: 0.038, memory: 10339, loss_rpn_cls: 0.0401, loss_rpn_bbox: 0.0441, loss_cls: 0.2228, acc: 92.2120, loss_bbox: 0.2696, loss_mask: 0.2626, loss: 0.8391 2023-11-16 17:56:34,850 - mmdet - INFO - Epoch [3][500/1833] lr: 5.563e-06, eta: 14:56:39, time: 0.880, data_time: 0.033, memory: 10339, loss_rpn_cls: 0.0376, loss_rpn_bbox: 0.0439, loss_cls: 0.2211, acc: 92.2068, loss_bbox: 0.2708, loss_mask: 0.2627, loss: 0.8361 2023-11-16 17:57:18,862 - mmdet - INFO - Epoch [3][550/1833] lr: 5.563e-06, eta: 14:56:02, time: 0.880, data_time: 0.034, memory: 10339, loss_rpn_cls: 0.0398, loss_rpn_bbox: 0.0447, loss_cls: 0.2205, acc: 92.3137, loss_bbox: 0.2689, loss_mask: 0.2651, loss: 0.8389 2023-11-16 17:58:02,978 - mmdet - INFO - Epoch [3][600/1833] lr: 5.563e-06, eta: 14:55:27, time: 0.882, data_time: 0.035, memory: 10339, loss_rpn_cls: 0.0396, loss_rpn_bbox: 0.0440, loss_cls: 0.2209, acc: 92.2515, loss_bbox: 0.2699, loss_mask: 0.2614, loss: 0.8358 2023-11-16 17:58:46,985 - mmdet - INFO - Epoch [3][650/1833] lr: 5.563e-06, eta: 14:54:51, time: 0.880, data_time: 0.042, memory: 10339, loss_rpn_cls: 0.0393, loss_rpn_bbox: 0.0446, loss_cls: 0.2227, acc: 92.2180, loss_bbox: 0.2714, loss_mask: 0.2613, loss: 0.8393 2023-11-16 17:59:30,940 - mmdet - INFO - Epoch [3][700/1833] lr: 5.563e-06, eta: 14:54:13, time: 0.879, data_time: 0.034, memory: 10345, loss_rpn_cls: 0.0386, loss_rpn_bbox: 0.0439, loss_cls: 0.2225, acc: 92.2383, loss_bbox: 0.2691, loss_mask: 0.2614, loss: 0.8355 2023-11-16 18:00:14,079 - mmdet - INFO - Epoch [3][750/1833] lr: 5.563e-06, eta: 14:53:24, time: 0.863, data_time: 0.037, memory: 10345, loss_rpn_cls: 0.0405, loss_rpn_bbox: 0.0445, loss_cls: 0.2241, acc: 92.2167, loss_bbox: 0.2678, loss_mask: 0.2607, loss: 0.8375 2023-11-16 18:00:59,038 - mmdet - INFO - Epoch [3][800/1833] lr: 5.563e-06, eta: 14:53:00, time: 0.899, data_time: 0.043, memory: 10345, loss_rpn_cls: 0.0393, loss_rpn_bbox: 0.0440, loss_cls: 0.2245, acc: 92.2221, loss_bbox: 0.2708, loss_mask: 0.2638, loss: 0.8424 2023-11-16 18:01:43,047 - mmdet - INFO - Epoch [3][850/1833] lr: 5.563e-06, eta: 14:52:23, time: 0.880, data_time: 0.036, memory: 10345, loss_rpn_cls: 0.0391, loss_rpn_bbox: 0.0434, loss_cls: 0.2209, acc: 92.3479, loss_bbox: 0.2645, loss_mask: 0.2604, loss: 0.8283 2023-11-16 18:02:26,691 - mmdet - INFO - Epoch [3][900/1833] lr: 5.563e-06, eta: 14:51:41, time: 0.873, data_time: 0.038, memory: 10345, loss_rpn_cls: 0.0382, loss_rpn_bbox: 0.0429, loss_cls: 0.2186, acc: 92.4191, loss_bbox: 0.2613, loss_mask: 0.2596, loss: 0.8205 2023-11-16 18:03:10,581 - mmdet - INFO - Epoch [3][950/1833] lr: 5.563e-06, eta: 14:51:02, time: 0.878, data_time: 0.033, memory: 10345, loss_rpn_cls: 0.0390, loss_rpn_bbox: 0.0432, loss_cls: 0.2208, acc: 92.2464, loss_bbox: 0.2701, loss_mask: 0.2607, loss: 0.8339 2023-11-16 18:03:54,644 - mmdet - INFO - Epoch [3][1000/1833] lr: 5.563e-06, eta: 14:50:25, time: 0.881, data_time: 0.040, memory: 10345, loss_rpn_cls: 0.0378, loss_rpn_bbox: 0.0428, loss_cls: 0.2194, acc: 92.3611, loss_bbox: 0.2653, loss_mask: 0.2587, loss: 0.8240 2023-11-16 18:04:38,534 - mmdet - INFO - Epoch [3][1050/1833] lr: 5.563e-06, eta: 14:49:46, time: 0.878, data_time: 0.032, memory: 10345, loss_rpn_cls: 0.0382, loss_rpn_bbox: 0.0427, loss_cls: 0.2138, acc: 92.4910, loss_bbox: 0.2616, loss_mask: 0.2613, loss: 0.8176 2023-11-16 18:05:22,452 - mmdet - INFO - Epoch [3][1100/1833] lr: 5.563e-06, eta: 14:49:07, time: 0.878, data_time: 0.035, memory: 10345, loss_rpn_cls: 0.0381, loss_rpn_bbox: 0.0435, loss_cls: 0.2154, acc: 92.4881, loss_bbox: 0.2619, loss_mask: 0.2598, loss: 0.8187 2023-11-16 18:06:06,353 - mmdet - INFO - Epoch [3][1150/1833] lr: 5.563e-06, eta: 14:48:27, time: 0.877, data_time: 0.037, memory: 10345, loss_rpn_cls: 0.0393, loss_rpn_bbox: 0.0439, loss_cls: 0.2179, acc: 92.3290, loss_bbox: 0.2687, loss_mask: 0.2599, loss: 0.8297 2023-11-16 18:06:49,724 - mmdet - INFO - Epoch [3][1200/1833] lr: 5.563e-06, eta: 14:47:41, time: 0.868, data_time: 0.037, memory: 10345, loss_rpn_cls: 0.0377, loss_rpn_bbox: 0.0441, loss_cls: 0.2188, acc: 92.2734, loss_bbox: 0.2671, loss_mask: 0.2621, loss: 0.8297 2023-11-16 18:07:33,855 - mmdet - INFO - Epoch [3][1250/1833] lr: 5.563e-06, eta: 14:47:05, time: 0.883, data_time: 0.034, memory: 10345, loss_rpn_cls: 0.0406, loss_rpn_bbox: 0.0443, loss_cls: 0.2157, acc: 92.4799, loss_bbox: 0.2619, loss_mask: 0.2588, loss: 0.8212 2023-11-16 18:08:17,172 - mmdet - INFO - Epoch [3][1300/1833] lr: 5.563e-06, eta: 14:46:18, time: 0.866, data_time: 0.033, memory: 10345, loss_rpn_cls: 0.0376, loss_rpn_bbox: 0.0425, loss_cls: 0.2158, acc: 92.4486, loss_bbox: 0.2635, loss_mask: 0.2581, loss: 0.8175 2023-11-16 18:09:00,809 - mmdet - INFO - Epoch [3][1350/1833] lr: 5.563e-06, eta: 14:45:35, time: 0.872, data_time: 0.044, memory: 10345, loss_rpn_cls: 0.0374, loss_rpn_bbox: 0.0432, loss_cls: 0.2150, acc: 92.4818, loss_bbox: 0.2616, loss_mask: 0.2578, loss: 0.8149 2023-11-16 18:09:44,961 - mmdet - INFO - Epoch [3][1400/1833] lr: 5.563e-06, eta: 14:44:58, time: 0.884, data_time: 0.037, memory: 10345, loss_rpn_cls: 0.0384, loss_rpn_bbox: 0.0442, loss_cls: 0.2107, acc: 92.5997, loss_bbox: 0.2589, loss_mask: 0.2576, loss: 0.8099 2023-11-16 18:10:28,611 - mmdet - INFO - Epoch [3][1450/1833] lr: 5.563e-06, eta: 14:44:16, time: 0.873, data_time: 0.030, memory: 10345, loss_rpn_cls: 0.0376, loss_rpn_bbox: 0.0429, loss_cls: 0.2163, acc: 92.4606, loss_bbox: 0.2600, loss_mask: 0.2566, loss: 0.8135 2023-11-16 18:11:12,689 - mmdet - INFO - Epoch [3][1500/1833] lr: 5.563e-06, eta: 14:43:38, time: 0.882, data_time: 0.035, memory: 10345, loss_rpn_cls: 0.0393, loss_rpn_bbox: 0.0437, loss_cls: 0.2189, acc: 92.3497, loss_bbox: 0.2640, loss_mask: 0.2631, loss: 0.8289 2023-11-16 18:11:56,199 - mmdet - INFO - Epoch [3][1550/1833] lr: 5.563e-06, eta: 14:42:53, time: 0.870, data_time: 0.036, memory: 10345, loss_rpn_cls: 0.0374, loss_rpn_bbox: 0.0440, loss_cls: 0.2184, acc: 92.3489, loss_bbox: 0.2665, loss_mask: 0.2584, loss: 0.8246 2023-11-16 18:12:39,874 - mmdet - INFO - Epoch [3][1600/1833] lr: 5.563e-06, eta: 14:42:11, time: 0.873, data_time: 0.036, memory: 10345, loss_rpn_cls: 0.0376, loss_rpn_bbox: 0.0440, loss_cls: 0.2161, acc: 92.4791, loss_bbox: 0.2619, loss_mask: 0.2566, loss: 0.8161 2023-11-16 18:13:23,630 - mmdet - INFO - Epoch [3][1650/1833] lr: 5.563e-06, eta: 14:41:29, time: 0.875, data_time: 0.033, memory: 10345, loss_rpn_cls: 0.0367, loss_rpn_bbox: 0.0416, loss_cls: 0.2114, acc: 92.5965, loss_bbox: 0.2591, loss_mask: 0.2561, loss: 0.8049 2023-11-16 18:14:07,179 - mmdet - INFO - Epoch [3][1700/1833] lr: 5.563e-06, eta: 14:40:45, time: 0.870, data_time: 0.036, memory: 10345, loss_rpn_cls: 0.0381, loss_rpn_bbox: 0.0433, loss_cls: 0.2183, acc: 92.3672, loss_bbox: 0.2617, loss_mask: 0.2550, loss: 0.8163 2023-11-16 18:14:51,000 - mmdet - INFO - Epoch [3][1750/1833] lr: 5.563e-06, eta: 14:40:04, time: 0.877, data_time: 0.036, memory: 10345, loss_rpn_cls: 0.0351, loss_rpn_bbox: 0.0405, loss_cls: 0.2103, acc: 92.6975, loss_bbox: 0.2551, loss_mask: 0.2522, loss: 0.7932 2023-11-16 18:15:34,359 - mmdet - INFO - Epoch [3][1800/1833] lr: 5.563e-06, eta: 14:39:18, time: 0.867, data_time: 0.033, memory: 10345, loss_rpn_cls: 0.0368, loss_rpn_bbox: 0.0426, loss_cls: 0.2110, acc: 92.5884, loss_bbox: 0.2581, loss_mask: 0.2554, loss: 0.8039 2023-11-16 18:16:03,703 - mmdet - INFO - Saving checkpoint at 3 epochs 2023-11-16 18:16:40,660 - mmdet - INFO - Evaluating bbox... 2023-11-16 18:17:18,349 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.408 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.652 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.444 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.281 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.452 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.521 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.547 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.547 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.547 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.396 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.591 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.674 2023-11-16 18:17:18,352 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.534 | bicycle | 0.322 | car | 0.428 | | motorcycle | 0.416 | airplane | 0.618 | bus | 0.639 | | train | 0.592 | truck | 0.347 | boat | 0.269 | | traffic light | 0.253 | fire hydrant | 0.668 | stop sign | 0.626 | | parking meter | 0.449 | bench | 0.243 | bird | 0.372 | | cat | 0.645 | dog | 0.625 | horse | 0.573 | | sheep | 0.523 | cow | 0.563 | elephant | 0.624 | | bear | 0.678 | zebra | 0.630 | giraffe | 0.603 | | backpack | 0.172 | umbrella | 0.386 | handbag | 0.158 | | tie | 0.292 | suitcase | 0.384 | frisbee | 0.668 | | skis | 0.170 | snowboard | 0.273 | sports ball | 0.460 | | kite | 0.410 | baseball bat | 0.290 | baseball glove | 0.367 | | skateboard | 0.486 | surfboard | 0.361 | tennis racket | 0.447 | | bottle | 0.410 | wine glass | 0.350 | cup | 0.447 | | fork | 0.291 | knife | 0.192 | spoon | 0.192 | | bowl | 0.424 | banana | 0.230 | apple | 0.228 | | sandwich | 0.393 | orange | 0.306 | broccoli | 0.236 | | carrot | 0.221 | hot dog | 0.314 | pizza | 0.486 | | donut | 0.476 | cake | 0.398 | chair | 0.288 | | couch | 0.423 | potted plant | 0.230 | bed | 0.429 | | dining table | 0.251 | toilet | 0.549 | tv | 0.573 | | laptop | 0.583 | mouse | 0.617 | remote | 0.331 | | keyboard | 0.465 | cell phone | 0.378 | microwave | 0.611 | | oven | 0.344 | toaster | 0.390 | sink | 0.392 | | refrigerator | 0.554 | book | 0.138 | clock | 0.510 | | vase | 0.368 | scissors | 0.286 | teddy bear | 0.454 | | hair drier | 0.111 | toothbrush | 0.208 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-16 18:17:18,352 - mmdet - INFO - Evaluating segm... 2023-11-16 18:17:57,169 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.380 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.621 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.405 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.212 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.420 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.553 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.510 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.510 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.510 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.344 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.560 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.662 2023-11-16 18:17:57,172 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.459 | bicycle | 0.193 | car | 0.397 | | motorcycle | 0.336 | airplane | 0.495 | bus | 0.645 | | train | 0.607 | truck | 0.354 | boat | 0.245 | | traffic light | 0.243 | fire hydrant | 0.654 | stop sign | 0.621 | | parking meter | 0.482 | bench | 0.175 | bird | 0.310 | | cat | 0.692 | dog | 0.623 | horse | 0.436 | | sheep | 0.473 | cow | 0.486 | elephant | 0.572 | | bear | 0.725 | zebra | 0.525 | giraffe | 0.483 | | backpack | 0.182 | umbrella | 0.473 | handbag | 0.168 | | tie | 0.296 | suitcase | 0.434 | frisbee | 0.630 | | skis | 0.023 | snowboard | 0.196 | sports ball | 0.431 | | kite | 0.297 | baseball bat | 0.244 | baseball glove | 0.422 | | skateboard | 0.305 | surfboard | 0.321 | tennis racket | 0.548 | | bottle | 0.389 | wine glass | 0.317 | cup | 0.458 | | fork | 0.162 | knife | 0.134 | spoon | 0.140 | | bowl | 0.399 | banana | 0.188 | apple | 0.233 | | sandwich | 0.425 | orange | 0.305 | broccoli | 0.228 | | carrot | 0.192 | hot dog | 0.240 | pizza | 0.481 | | donut | 0.498 | cake | 0.418 | chair | 0.207 | | couch | 0.370 | potted plant | 0.206 | bed | 0.342 | | dining table | 0.128 | toilet | 0.591 | tv | 0.602 | | laptop | 0.620 | mouse | 0.604 | remote | 0.303 | | keyboard | 0.492 | cell phone | 0.380 | microwave | 0.625 | | oven | 0.322 | toaster | 0.402 | sink | 0.379 | | refrigerator | 0.589 | book | 0.099 | clock | 0.516 | | vase | 0.363 | scissors | 0.238 | teddy bear | 0.443 | | hair drier | 0.094 | toothbrush | 0.114 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-16 18:17:57,801 - mmdet - INFO - The previous best checkpoint /mnt/petrelfs/lizhiqi/DINO/detection/work_dirs/mask_rcnn_flash_internimage_b_fpn_3x_cocoo_0.4_0.9_4x16/best_bbox_mAP_epoch_2.pth was removed 2023-11-16 18:18:01,403 - mmdet - INFO - Now best checkpoint is saved as best_bbox_mAP_epoch_3.pth. 2023-11-16 18:18:01,403 - mmdet - INFO - Best bbox_mAP is 0.4080 at 3 epoch. 2023-11-16 18:18:01,403 - mmdet - INFO - Exp name: mask_rcnn_flash_internimage_b_fpn_3x_coco_0.4_0.9-4x16.py 2023-11-16 18:18:01,403 - mmdet - INFO - Epoch(val) [3][313] bbox_mAP: 0.4080, bbox_mAP_50: 0.6521, bbox_mAP_75: 0.4443, bbox_mAP_s: 0.2807, bbox_mAP_m: 0.4519, bbox_mAP_l: 0.5206, bbox_mAP_copypaste: 0.4080 0.6521 0.4443 0.2807 0.4519 0.5206, segm_mAP: 0.3804, segm_mAP_50: 0.6213, segm_mAP_75: 0.4054, segm_mAP_s: 0.2120, segm_mAP_m: 0.4204, segm_mAP_l: 0.5526, segm_mAP_copypaste: 0.3804 0.6213 0.4054 0.2120 0.4204 0.5526 2023-11-16 18:18:47,784 - mmdet - INFO - Epoch [4][50/1833] lr: 5.563e-06, eta: 14:33:23, time: 0.927, data_time: 0.095, memory: 10345, loss_rpn_cls: 0.0371, loss_rpn_bbox: 0.0431, loss_cls: 0.2141, acc: 92.3794, loss_bbox: 0.2654, loss_mask: 0.2555, loss: 0.8152 2023-11-16 18:19:31,075 - mmdet - INFO - Epoch [4][100/1833] lr: 5.563e-06, eta: 14:32:39, time: 0.866, data_time: 0.034, memory: 10345, loss_rpn_cls: 0.0363, loss_rpn_bbox: 0.0419, loss_cls: 0.2105, acc: 92.5770, loss_bbox: 0.2598, loss_mask: 0.2540, loss: 0.8025 2023-11-16 18:20:14,905 - mmdet - INFO - Epoch [4][150/1833] lr: 5.563e-06, eta: 14:32:00, time: 0.876, data_time: 0.034, memory: 10345, loss_rpn_cls: 0.0368, loss_rpn_bbox: 0.0416, loss_cls: 0.2082, acc: 92.6225, loss_bbox: 0.2571, loss_mask: 0.2522, loss: 0.7959 2023-11-16 18:20:58,876 - mmdet - INFO - Epoch [4][200/1833] lr: 5.563e-06, eta: 14:31:24, time: 0.879, data_time: 0.033, memory: 10345, loss_rpn_cls: 0.0365, loss_rpn_bbox: 0.0428, loss_cls: 0.2096, acc: 92.5535, loss_bbox: 0.2605, loss_mask: 0.2553, loss: 0.8047 2023-11-16 18:21:42,502 - mmdet - INFO - Epoch [4][250/1833] lr: 5.563e-06, eta: 14:30:43, time: 0.872, data_time: 0.032, memory: 10345, loss_rpn_cls: 0.0362, loss_rpn_bbox: 0.0418, loss_cls: 0.2099, acc: 92.6100, loss_bbox: 0.2569, loss_mask: 0.2536, loss: 0.7984 2023-11-16 18:22:26,038 - mmdet - INFO - Epoch [4][300/1833] lr: 5.563e-06, eta: 14:30:01, time: 0.871, data_time: 0.044, memory: 10345, loss_rpn_cls: 0.0346, loss_rpn_bbox: 0.0423, loss_cls: 0.2100, acc: 92.6204, loss_bbox: 0.2571, loss_mask: 0.2539, loss: 0.7979 2023-11-16 18:23:09,731 - mmdet - INFO - Epoch [4][350/1833] lr: 5.563e-06, eta: 14:29:21, time: 0.874, data_time: 0.040, memory: 10345, loss_rpn_cls: 0.0369, loss_rpn_bbox: 0.0426, loss_cls: 0.2097, acc: 92.6273, loss_bbox: 0.2580, loss_mask: 0.2586, loss: 0.8059 2023-11-16 18:23:53,626 - mmdet - INFO - Epoch [4][400/1833] lr: 5.563e-06, eta: 14:28:43, time: 0.878, data_time: 0.041, memory: 10345, loss_rpn_cls: 0.0370, loss_rpn_bbox: 0.0432, loss_cls: 0.2108, acc: 92.5337, loss_bbox: 0.2589, loss_mask: 0.2527, loss: 0.8027 2023-11-16 18:24:37,866 - mmdet - INFO - Epoch [4][450/1833] lr: 5.563e-06, eta: 14:28:09, time: 0.885, data_time: 0.039, memory: 10345, loss_rpn_cls: 0.0378, loss_rpn_bbox: 0.0443, loss_cls: 0.2109, acc: 92.5241, loss_bbox: 0.2611, loss_mask: 0.2544, loss: 0.8085 2023-11-16 18:25:21,634 - mmdet - INFO - Epoch [4][500/1833] lr: 5.563e-06, eta: 14:27:29, time: 0.875, data_time: 0.034, memory: 10345, loss_rpn_cls: 0.0347, loss_rpn_bbox: 0.0415, loss_cls: 0.2077, acc: 92.6542, loss_bbox: 0.2601, loss_mask: 0.2538, loss: 0.7978 2023-11-16 18:26:04,995 - mmdet - INFO - Epoch [4][550/1833] lr: 5.563e-06, eta: 14:26:46, time: 0.867, data_time: 0.038, memory: 10345, loss_rpn_cls: 0.0360, loss_rpn_bbox: 0.0414, loss_cls: 0.2019, acc: 92.8717, loss_bbox: 0.2530, loss_mask: 0.2516, loss: 0.7838 2023-11-16 18:26:48,914 - mmdet - INFO - Epoch [4][600/1833] lr: 5.563e-06, eta: 14:26:07, time: 0.878, data_time: 0.038, memory: 10345, loss_rpn_cls: 0.0360, loss_rpn_bbox: 0.0431, loss_cls: 0.2082, acc: 92.6572, loss_bbox: 0.2563, loss_mask: 0.2501, loss: 0.7938 2023-11-16 18:27:32,744 - mmdet - INFO - Epoch [4][650/1833] lr: 5.563e-06, eta: 14:25:28, time: 0.877, data_time: 0.034, memory: 10345, loss_rpn_cls: 0.0355, loss_rpn_bbox: 0.0400, loss_cls: 0.2078, acc: 92.6592, loss_bbox: 0.2565, loss_mask: 0.2518, loss: 0.7916 2023-11-16 18:28:16,815 - mmdet - INFO - Epoch [4][700/1833] lr: 5.563e-06, eta: 14:24:52, time: 0.881, data_time: 0.036, memory: 10345, loss_rpn_cls: 0.0354, loss_rpn_bbox: 0.0419, loss_cls: 0.2087, acc: 92.6190, loss_bbox: 0.2570, loss_mask: 0.2530, loss: 0.7960 2023-11-16 18:29:00,246 - mmdet - INFO - Epoch [4][750/1833] lr: 5.563e-06, eta: 14:24:08, time: 0.869, data_time: 0.033, memory: 10345, loss_rpn_cls: 0.0367, loss_rpn_bbox: 0.0409, loss_cls: 0.2083, acc: 92.6525, loss_bbox: 0.2540, loss_mask: 0.2518, loss: 0.7917 2023-11-16 18:29:44,226 - mmdet - INFO - Epoch [4][800/1833] lr: 5.563e-06, eta: 14:23:31, time: 0.880, data_time: 0.035, memory: 10345, loss_rpn_cls: 0.0370, loss_rpn_bbox: 0.0436, loss_cls: 0.2138, acc: 92.4139, loss_bbox: 0.2611, loss_mask: 0.2563, loss: 0.8118 2023-11-16 18:30:27,920 - mmdet - INFO - Epoch [4][850/1833] lr: 5.563e-06, eta: 14:22:50, time: 0.874, data_time: 0.034, memory: 10345, loss_rpn_cls: 0.0356, loss_rpn_bbox: 0.0416, loss_cls: 0.2068, acc: 92.6506, loss_bbox: 0.2561, loss_mask: 0.2507, loss: 0.7909 2023-11-16 18:31:11,381 - mmdet - INFO - Epoch [4][900/1833] lr: 5.563e-06, eta: 14:22:07, time: 0.869, data_time: 0.036, memory: 10345, loss_rpn_cls: 0.0346, loss_rpn_bbox: 0.0410, loss_cls: 0.2107, acc: 92.5812, loss_bbox: 0.2558, loss_mask: 0.2489, loss: 0.7909 2023-11-16 18:31:55,026 - mmdet - INFO - Epoch [4][950/1833] lr: 5.563e-06, eta: 14:21:26, time: 0.873, data_time: 0.033, memory: 10345, loss_rpn_cls: 0.0359, loss_rpn_bbox: 0.0420, loss_cls: 0.2038, acc: 92.8287, loss_bbox: 0.2516, loss_mask: 0.2521, loss: 0.7855 2023-11-16 18:32:38,480 - mmdet - INFO - Epoch [4][1000/1833] lr: 5.563e-06, eta: 14:20:43, time: 0.869, data_time: 0.036, memory: 10345, loss_rpn_cls: 0.0368, loss_rpn_bbox: 0.0426, loss_cls: 0.2099, acc: 92.5973, loss_bbox: 0.2581, loss_mask: 0.2518, loss: 0.7992 2023-11-16 18:33:21,809 - mmdet - INFO - Epoch [4][1050/1833] lr: 5.563e-06, eta: 14:19:59, time: 0.867, data_time: 0.029, memory: 10345, loss_rpn_cls: 0.0337, loss_rpn_bbox: 0.0409, loss_cls: 0.2041, acc: 92.8007, loss_bbox: 0.2512, loss_mask: 0.2477, loss: 0.7777 2023-11-16 18:34:05,849 - mmdet - INFO - Epoch [4][1100/1833] lr: 5.563e-06, eta: 14:19:21, time: 0.881, data_time: 0.040, memory: 10345, loss_rpn_cls: 0.0366, loss_rpn_bbox: 0.0419, loss_cls: 0.2104, acc: 92.6127, loss_bbox: 0.2559, loss_mask: 0.2537, loss: 0.7984 2023-11-16 18:34:49,811 - mmdet - INFO - Epoch [4][1150/1833] lr: 5.563e-06, eta: 14:18:43, time: 0.879, data_time: 0.041, memory: 10345, loss_rpn_cls: 0.0349, loss_rpn_bbox: 0.0421, loss_cls: 0.2112, acc: 92.6014, loss_bbox: 0.2580, loss_mask: 0.2509, loss: 0.7971 2023-11-16 18:35:33,820 - mmdet - INFO - Epoch [4][1200/1833] lr: 5.563e-06, eta: 14:18:04, time: 0.880, data_time: 0.038, memory: 10345, loss_rpn_cls: 0.0341, loss_rpn_bbox: 0.0403, loss_cls: 0.2083, acc: 92.6785, loss_bbox: 0.2553, loss_mask: 0.2507, loss: 0.7888 2023-11-16 18:36:17,657 - mmdet - INFO - Epoch [4][1250/1833] lr: 5.563e-06, eta: 14:17:24, time: 0.876, data_time: 0.032, memory: 10345, loss_rpn_cls: 0.0346, loss_rpn_bbox: 0.0406, loss_cls: 0.2048, acc: 92.8190, loss_bbox: 0.2522, loss_mask: 0.2541, loss: 0.7862 2023-11-16 18:37:01,526 - mmdet - INFO - Epoch [4][1300/1833] lr: 5.563e-06, eta: 14:16:45, time: 0.878, data_time: 0.036, memory: 10345, loss_rpn_cls: 0.0361, loss_rpn_bbox: 0.0417, loss_cls: 0.2094, acc: 92.5950, loss_bbox: 0.2548, loss_mask: 0.2488, loss: 0.7908 2023-11-16 18:37:45,256 - mmdet - INFO - Epoch [4][1350/1833] lr: 5.563e-06, eta: 14:16:04, time: 0.875, data_time: 0.036, memory: 10345, loss_rpn_cls: 0.0355, loss_rpn_bbox: 0.0406, loss_cls: 0.2085, acc: 92.6967, loss_bbox: 0.2526, loss_mask: 0.2518, loss: 0.7889 2023-11-16 18:38:29,001 - mmdet - INFO - Epoch [4][1400/1833] lr: 5.563e-06, eta: 14:15:24, time: 0.875, data_time: 0.034, memory: 10345, loss_rpn_cls: 0.0336, loss_rpn_bbox: 0.0398, loss_cls: 0.2035, acc: 92.7815, loss_bbox: 0.2508, loss_mask: 0.2478, loss: 0.7753 2023-11-16 18:39:12,972 - mmdet - INFO - Epoch [4][1450/1833] lr: 5.563e-06, eta: 14:14:45, time: 0.879, data_time: 0.036, memory: 10345, loss_rpn_cls: 0.0348, loss_rpn_bbox: 0.0407, loss_cls: 0.2028, acc: 92.7571, loss_bbox: 0.2506, loss_mask: 0.2472, loss: 0.7760 2023-11-16 18:39:56,831 - mmdet - INFO - Epoch [4][1500/1833] lr: 5.563e-06, eta: 14:14:05, time: 0.877, data_time: 0.037, memory: 10345, loss_rpn_cls: 0.0346, loss_rpn_bbox: 0.0416, loss_cls: 0.2094, acc: 92.5825, loss_bbox: 0.2577, loss_mask: 0.2537, loss: 0.7970 2023-11-16 18:40:40,573 - mmdet - INFO - Epoch [4][1550/1833] lr: 5.563e-06, eta: 14:13:24, time: 0.875, data_time: 0.032, memory: 10345, loss_rpn_cls: 0.0351, loss_rpn_bbox: 0.0415, loss_cls: 0.2081, acc: 92.7031, loss_bbox: 0.2534, loss_mask: 0.2535, loss: 0.7916 2023-11-16 18:41:24,273 - mmdet - INFO - Epoch [4][1600/1833] lr: 5.563e-06, eta: 14:12:43, time: 0.874, data_time: 0.035, memory: 10345, loss_rpn_cls: 0.0345, loss_rpn_bbox: 0.0409, loss_cls: 0.2019, acc: 92.8053, loss_bbox: 0.2504, loss_mask: 0.2528, loss: 0.7804 2023-11-16 18:42:08,231 - mmdet - INFO - Epoch [4][1650/1833] lr: 5.563e-06, eta: 14:12:03, time: 0.879, data_time: 0.035, memory: 10345, loss_rpn_cls: 0.0345, loss_rpn_bbox: 0.0406, loss_cls: 0.2033, acc: 92.7551, loss_bbox: 0.2531, loss_mask: 0.2496, loss: 0.7812 2023-11-16 18:42:51,900 - mmdet - INFO - Epoch [4][1700/1833] lr: 5.563e-06, eta: 14:11:22, time: 0.874, data_time: 0.032, memory: 10345, loss_rpn_cls: 0.0339, loss_rpn_bbox: 0.0408, loss_cls: 0.2055, acc: 92.6844, loss_bbox: 0.2536, loss_mask: 0.2509, loss: 0.7847 2023-11-16 18:43:36,070 - mmdet - INFO - Epoch [4][1750/1833] lr: 5.563e-06, eta: 14:10:44, time: 0.883, data_time: 0.032, memory: 10345, loss_rpn_cls: 0.0356, loss_rpn_bbox: 0.0420, loss_cls: 0.2076, acc: 92.7144, loss_bbox: 0.2552, loss_mask: 0.2489, loss: 0.7892 2023-11-16 18:44:19,533 - mmdet - INFO - Epoch [4][1800/1833] lr: 5.563e-06, eta: 14:10:01, time: 0.869, data_time: 0.036, memory: 10345, loss_rpn_cls: 0.0349, loss_rpn_bbox: 0.0409, loss_cls: 0.2075, acc: 92.6777, loss_bbox: 0.2521, loss_mask: 0.2494, loss: 0.7848 2023-11-16 18:44:50,939 - mmdet - INFO - Saving checkpoint at 4 epochs 2023-11-16 18:45:27,682 - mmdet - INFO - Evaluating bbox... 2023-11-16 18:46:03,244 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.424 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.670 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.467 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.284 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.466 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.548 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.561 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.561 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.561 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.393 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.602 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.698 2023-11-16 18:46:03,247 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.539 | bicycle | 0.335 | car | 0.433 | | motorcycle | 0.427 | airplane | 0.642 | bus | 0.643 | | train | 0.606 | truck | 0.404 | boat | 0.291 | | traffic light | 0.286 | fire hydrant | 0.671 | stop sign | 0.587 | | parking meter | 0.456 | bench | 0.244 | bird | 0.366 | | cat | 0.663 | dog | 0.635 | horse | 0.588 | | sheep | 0.560 | cow | 0.575 | elephant | 0.654 | | bear | 0.674 | zebra | 0.642 | giraffe | 0.654 | | backpack | 0.182 | umbrella | 0.402 | handbag | 0.173 | | tie | 0.305 | suitcase | 0.425 | frisbee | 0.679 | | skis | 0.207 | snowboard | 0.356 | sports ball | 0.443 | | kite | 0.428 | baseball bat | 0.330 | baseball glove | 0.377 | | skateboard | 0.525 | surfboard | 0.370 | tennis racket | 0.467 | | bottle | 0.420 | wine glass | 0.360 | cup | 0.481 | | fork | 0.317 | knife | 0.222 | spoon | 0.211 | | bowl | 0.441 | banana | 0.251 | apple | 0.228 | | sandwich | 0.401 | orange | 0.317 | broccoli | 0.243 | | carrot | 0.232 | hot dog | 0.326 | pizza | 0.478 | | donut | 0.493 | cake | 0.417 | chair | 0.302 | | couch | 0.443 | potted plant | 0.289 | bed | 0.440 | | dining table | 0.266 | toilet | 0.563 | tv | 0.579 | | laptop | 0.604 | mouse | 0.622 | remote | 0.346 | | keyboard | 0.485 | cell phone | 0.394 | microwave | 0.592 | | oven | 0.348 | toaster | 0.350 | sink | 0.406 | | refrigerator | 0.571 | book | 0.145 | clock | 0.544 | | vase | 0.396 | scissors | 0.339 | teddy bear | 0.463 | | hair drier | 0.133 | toothbrush | 0.215 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-16 18:46:03,247 - mmdet - INFO - Evaluating segm... 2023-11-16 18:46:40,201 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.392 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.632 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.420 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.203 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.432 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.574 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.523 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.523 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.523 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.334 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.569 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.683 2023-11-16 18:46:40,203 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.472 | bicycle | 0.198 | car | 0.404 | | motorcycle | 0.348 | airplane | 0.502 | bus | 0.656 | | train | 0.635 | truck | 0.406 | boat | 0.265 | | traffic light | 0.279 | fire hydrant | 0.657 | stop sign | 0.606 | | parking meter | 0.481 | bench | 0.186 | bird | 0.317 | | cat | 0.686 | dog | 0.636 | horse | 0.440 | | sheep | 0.490 | cow | 0.490 | elephant | 0.585 | | bear | 0.718 | zebra | 0.562 | giraffe | 0.499 | | backpack | 0.192 | umbrella | 0.487 | handbag | 0.176 | | tie | 0.306 | suitcase | 0.458 | frisbee | 0.643 | | skis | 0.030 | snowboard | 0.247 | sports ball | 0.427 | | kite | 0.300 | baseball bat | 0.236 | baseball glove | 0.415 | | skateboard | 0.332 | surfboard | 0.321 | tennis racket | 0.552 | | bottle | 0.406 | wine glass | 0.305 | cup | 0.483 | | fork | 0.180 | knife | 0.150 | spoon | 0.158 | | bowl | 0.420 | banana | 0.201 | apple | 0.221 | | sandwich | 0.445 | orange | 0.317 | broccoli | 0.243 | | carrot | 0.202 | hot dog | 0.253 | pizza | 0.495 | | donut | 0.513 | cake | 0.430 | chair | 0.212 | | couch | 0.385 | potted plant | 0.251 | bed | 0.336 | | dining table | 0.154 | toilet | 0.597 | tv | 0.627 | | laptop | 0.636 | mouse | 0.611 | remote | 0.323 | | keyboard | 0.509 | cell phone | 0.379 | microwave | 0.658 | | oven | 0.351 | toaster | 0.388 | sink | 0.381 | | refrigerator | 0.596 | book | 0.112 | clock | 0.533 | | vase | 0.385 | scissors | 0.275 | teddy bear | 0.453 | | hair drier | 0.041 | toothbrush | 0.133 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-16 18:46:40,772 - mmdet - INFO - The previous best checkpoint /mnt/petrelfs/lizhiqi/DINO/detection/work_dirs/mask_rcnn_flash_internimage_b_fpn_3x_cocoo_0.4_0.9_4x16/best_bbox_mAP_epoch_3.pth was removed 2023-11-16 18:46:44,700 - mmdet - INFO - Now best checkpoint is saved as best_bbox_mAP_epoch_4.pth. 2023-11-16 18:46:44,700 - mmdet - INFO - Best bbox_mAP is 0.4240 at 4 epoch. 2023-11-16 18:46:44,701 - mmdet - INFO - Exp name: mask_rcnn_flash_internimage_b_fpn_3x_coco_0.4_0.9-4x16.py 2023-11-16 18:46:44,701 - mmdet - INFO - Epoch(val) [4][313] bbox_mAP: 0.4240, bbox_mAP_50: 0.6697, bbox_mAP_75: 0.4674, bbox_mAP_s: 0.2837, bbox_mAP_m: 0.4658, bbox_mAP_l: 0.5475, bbox_mAP_copypaste: 0.4240 0.6697 0.4674 0.2837 0.4658 0.5475, segm_mAP: 0.3924, segm_mAP_50: 0.6321, segm_mAP_75: 0.4204, segm_mAP_s: 0.2027, segm_mAP_m: 0.4315, segm_mAP_l: 0.5743, segm_mAP_copypaste: 0.3924 0.6321 0.4204 0.2027 0.4315 0.5743 2023-11-16 18:47:31,745 - mmdet - INFO - Epoch [5][50/1833] lr: 5.563e-06, eta: 14:05:30, time: 0.940, data_time: 0.092, memory: 10345, loss_rpn_cls: 0.0339, loss_rpn_bbox: 0.0412, loss_cls: 0.2027, acc: 92.7702, loss_bbox: 0.2529, loss_mask: 0.2494, loss: 0.7801 2023-11-16 18:48:15,825 - mmdet - INFO - Epoch [5][100/1833] lr: 5.563e-06, eta: 14:04:53, time: 0.882, data_time: 0.038, memory: 10345, loss_rpn_cls: 0.0340, loss_rpn_bbox: 0.0415, loss_cls: 0.2037, acc: 92.7366, loss_bbox: 0.2528, loss_mask: 0.2463, loss: 0.7783 2023-11-16 18:48:59,968 - mmdet - INFO - Epoch [5][150/1833] lr: 5.563e-06, eta: 14:04:16, time: 0.883, data_time: 0.037, memory: 10345, loss_rpn_cls: 0.0323, loss_rpn_bbox: 0.0399, loss_cls: 0.2003, acc: 92.8206, loss_bbox: 0.2496, loss_mask: 0.2463, loss: 0.7684 2023-11-16 18:49:43,397 - mmdet - INFO - Epoch [5][200/1833] lr: 5.563e-06, eta: 14:03:34, time: 0.869, data_time: 0.035, memory: 10345, loss_rpn_cls: 0.0339, loss_rpn_bbox: 0.0417, loss_cls: 0.2045, acc: 92.6900, loss_bbox: 0.2530, loss_mask: 0.2506, loss: 0.7838 2023-11-16 18:50:29,849 - mmdet - INFO - Epoch [5][250/1833] lr: 5.563e-06, eta: 14:03:15, time: 0.929, data_time: 0.040, memory: 10345, loss_rpn_cls: 0.0337, loss_rpn_bbox: 0.0414, loss_cls: 0.2043, acc: 92.7480, loss_bbox: 0.2537, loss_mask: 0.2489, loss: 0.7820 2023-11-16 18:51:13,632 - mmdet - INFO - Epoch [5][300/1833] lr: 5.563e-06, eta: 14:02:35, time: 0.876, data_time: 0.040, memory: 10345, loss_rpn_cls: 0.0340, loss_rpn_bbox: 0.0407, loss_cls: 0.2003, acc: 92.8350, loss_bbox: 0.2522, loss_mask: 0.2452, loss: 0.7724 2023-11-16 18:51:57,320 - mmdet - INFO - Epoch [5][350/1833] lr: 5.563e-06, eta: 14:01:55, time: 0.874, data_time: 0.038, memory: 10345, loss_rpn_cls: 0.0334, loss_rpn_bbox: 0.0406, loss_cls: 0.2013, acc: 92.8572, loss_bbox: 0.2470, loss_mask: 0.2437, loss: 0.7661 2023-11-16 18:52:42,693 - mmdet - INFO - Epoch [5][400/1833] lr: 5.563e-06, eta: 14:01:27, time: 0.907, data_time: 0.034, memory: 10345, loss_rpn_cls: 0.0346, loss_rpn_bbox: 0.0419, loss_cls: 0.2045, acc: 92.7009, loss_bbox: 0.2562, loss_mask: 0.2487, loss: 0.7859 2023-11-16 18:53:28,895 - mmdet - INFO - Epoch [5][450/1833] lr: 5.563e-06, eta: 14:01:05, time: 0.924, data_time: 0.034, memory: 10345, loss_rpn_cls: 0.0335, loss_rpn_bbox: 0.0406, loss_cls: 0.2016, acc: 92.8157, loss_bbox: 0.2483, loss_mask: 0.2471, loss: 0.7712 2023-11-16 18:54:13,219 - mmdet - INFO - Epoch [5][500/1833] lr: 5.563e-06, eta: 14:00:29, time: 0.887, data_time: 0.035, memory: 10345, loss_rpn_cls: 0.0327, loss_rpn_bbox: 0.0403, loss_cls: 0.2002, acc: 92.9033, loss_bbox: 0.2485, loss_mask: 0.2438, loss: 0.7655 2023-11-16 18:55:00,207 - mmdet - INFO - Epoch [5][550/1833] lr: 5.563e-06, eta: 14:00:12, time: 0.940, data_time: 0.041, memory: 10345, loss_rpn_cls: 0.0331, loss_rpn_bbox: 0.0404, loss_cls: 0.2021, acc: 92.8126, loss_bbox: 0.2503, loss_mask: 0.2462, loss: 0.7720 2023-11-16 18:55:43,995 - mmdet - INFO - Epoch [5][600/1833] lr: 5.563e-06, eta: 13:59:32, time: 0.876, data_time: 0.034, memory: 10345, loss_rpn_cls: 0.0334, loss_rpn_bbox: 0.0401, loss_cls: 0.1964, acc: 93.0326, loss_bbox: 0.2429, loss_mask: 0.2447, loss: 0.7575 2023-11-16 18:56:28,372 - mmdet - INFO - Epoch [5][650/1833] lr: 5.563e-06, eta: 13:58:56, time: 0.887, data_time: 0.034, memory: 10345, loss_rpn_cls: 0.0340, loss_rpn_bbox: 0.0413, loss_cls: 0.2028, acc: 92.7831, loss_bbox: 0.2523, loss_mask: 0.2450, loss: 0.7754 2023-11-16 18:57:14,366 - mmdet - INFO - Epoch [5][700/1833] lr: 5.563e-06, eta: 13:58:31, time: 0.920, data_time: 0.033, memory: 10345, loss_rpn_cls: 0.0331, loss_rpn_bbox: 0.0401, loss_cls: 0.1980, acc: 92.9404, loss_bbox: 0.2464, loss_mask: 0.2464, loss: 0.7640 2023-11-16 18:57:57,847 - mmdet - INFO - Epoch [5][750/1833] lr: 5.563e-06, eta: 13:57:48, time: 0.870, data_time: 0.039, memory: 10345, loss_rpn_cls: 0.0351, loss_rpn_bbox: 0.0410, loss_cls: 0.1980, acc: 92.9592, loss_bbox: 0.2488, loss_mask: 0.2427, loss: 0.7656 2023-11-16 18:58:42,005 - mmdet - INFO - Epoch [5][800/1833] lr: 5.563e-06, eta: 13:57:10, time: 0.883, data_time: 0.033, memory: 10345, loss_rpn_cls: 0.0324, loss_rpn_bbox: 0.0394, loss_cls: 0.1968, acc: 92.9286, loss_bbox: 0.2452, loss_mask: 0.2414, loss: 0.7552 2023-11-16 18:59:25,269 - mmdet - INFO - Epoch [5][850/1833] lr: 5.563e-06, eta: 13:56:26, time: 0.865, data_time: 0.036, memory: 10345, loss_rpn_cls: 0.0322, loss_rpn_bbox: 0.0387, loss_cls: 0.1978, acc: 92.9459, loss_bbox: 0.2480, loss_mask: 0.2448, loss: 0.7615 2023-11-16 19:00:09,154 - mmdet - INFO - Epoch [5][900/1833] lr: 5.563e-06, eta: 13:55:46, time: 0.878, data_time: 0.038, memory: 10345, loss_rpn_cls: 0.0321, loss_rpn_bbox: 0.0405, loss_cls: 0.2014, acc: 92.7950, loss_bbox: 0.2529, loss_mask: 0.2490, loss: 0.7759 2023-11-16 19:00:52,651 - mmdet - INFO - Epoch [5][950/1833] lr: 5.563e-06, eta: 13:55:03, time: 0.870, data_time: 0.036, memory: 10345, loss_rpn_cls: 0.0350, loss_rpn_bbox: 0.0409, loss_cls: 0.2007, acc: 92.8626, loss_bbox: 0.2490, loss_mask: 0.2446, loss: 0.7700 2023-11-16 19:01:39,053 - mmdet - INFO - Epoch [5][1000/1833] lr: 5.563e-06, eta: 13:54:40, time: 0.927, data_time: 0.033, memory: 10345, loss_rpn_cls: 0.0333, loss_rpn_bbox: 0.0406, loss_cls: 0.1999, acc: 92.8832, loss_bbox: 0.2473, loss_mask: 0.2456, loss: 0.7668 2023-11-16 19:02:23,231 - mmdet - INFO - Epoch [5][1050/1833] lr: 5.563e-06, eta: 13:54:02, time: 0.884, data_time: 0.040, memory: 10345, loss_rpn_cls: 0.0326, loss_rpn_bbox: 0.0419, loss_cls: 0.2027, acc: 92.7572, loss_bbox: 0.2505, loss_mask: 0.2486, loss: 0.7763 2023-11-16 19:03:07,190 - mmdet - INFO - Epoch [5][1100/1833] lr: 5.563e-06, eta: 13:53:22, time: 0.879, data_time: 0.036, memory: 10345, loss_rpn_cls: 0.0326, loss_rpn_bbox: 0.0395, loss_cls: 0.1976, acc: 92.9280, loss_bbox: 0.2473, loss_mask: 0.2442, loss: 0.7612 2023-11-16 19:03:51,378 - mmdet - INFO - Epoch [5][1150/1833] lr: 5.563e-06, eta: 13:52:44, time: 0.884, data_time: 0.037, memory: 10345, loss_rpn_cls: 0.0330, loss_rpn_bbox: 0.0404, loss_cls: 0.1989, acc: 92.9212, loss_bbox: 0.2449, loss_mask: 0.2437, loss: 0.7609 2023-11-16 19:04:36,102 - mmdet - INFO - Epoch [5][1200/1833] lr: 5.563e-06, eta: 13:52:09, time: 0.894, data_time: 0.033, memory: 10345, loss_rpn_cls: 0.0324, loss_rpn_bbox: 0.0393, loss_cls: 0.1985, acc: 92.9305, loss_bbox: 0.2473, loss_mask: 0.2431, loss: 0.7606 2023-11-16 19:05:19,910 - mmdet - INFO - Epoch [5][1250/1833] lr: 5.563e-06, eta: 13:51:28, time: 0.876, data_time: 0.034, memory: 10345, loss_rpn_cls: 0.0323, loss_rpn_bbox: 0.0397, loss_cls: 0.2007, acc: 92.8139, loss_bbox: 0.2484, loss_mask: 0.2438, loss: 0.7649 2023-11-16 19:06:03,720 - mmdet - INFO - Epoch [5][1300/1833] lr: 5.563e-06, eta: 13:50:47, time: 0.876, data_time: 0.037, memory: 10345, loss_rpn_cls: 0.0334, loss_rpn_bbox: 0.0400, loss_cls: 0.2007, acc: 92.8658, loss_bbox: 0.2479, loss_mask: 0.2442, loss: 0.7662 2023-11-16 19:06:47,451 - mmdet - INFO - Epoch [5][1350/1833] lr: 5.563e-06, eta: 13:50:05, time: 0.875, data_time: 0.034, memory: 10345, loss_rpn_cls: 0.0341, loss_rpn_bbox: 0.0427, loss_cls: 0.2064, acc: 92.6546, loss_bbox: 0.2541, loss_mask: 0.2469, loss: 0.7843 2023-11-16 19:07:33,831 - mmdet - INFO - Epoch [5][1400/1833] lr: 5.563e-06, eta: 13:49:41, time: 0.928, data_time: 0.038, memory: 10345, loss_rpn_cls: 0.0334, loss_rpn_bbox: 0.0403, loss_cls: 0.1980, acc: 92.9814, loss_bbox: 0.2451, loss_mask: 0.2441, loss: 0.7610 2023-11-16 19:08:17,532 - mmdet - INFO - Epoch [5][1450/1833] lr: 5.563e-06, eta: 13:48:59, time: 0.874, data_time: 0.034, memory: 10345, loss_rpn_cls: 0.0328, loss_rpn_bbox: 0.0407, loss_cls: 0.2065, acc: 92.6962, loss_bbox: 0.2525, loss_mask: 0.2499, loss: 0.7824 2023-11-16 19:09:01,433 - mmdet - INFO - Epoch [5][1500/1833] lr: 5.563e-06, eta: 13:48:18, time: 0.878, data_time: 0.031, memory: 10345, loss_rpn_cls: 0.0318, loss_rpn_bbox: 0.0393, loss_cls: 0.2005, acc: 92.8643, loss_bbox: 0.2503, loss_mask: 0.2471, loss: 0.7690 2023-11-16 19:09:45,283 - mmdet - INFO - Epoch [5][1550/1833] lr: 5.563e-06, eta: 13:47:37, time: 0.877, data_time: 0.030, memory: 10345, loss_rpn_cls: 0.0348, loss_rpn_bbox: 0.0405, loss_cls: 0.1977, acc: 93.0021, loss_bbox: 0.2458, loss_mask: 0.2415, loss: 0.7603 2023-11-16 19:10:29,163 - mmdet - INFO - Epoch [5][1600/1833] lr: 5.563e-06, eta: 13:46:56, time: 0.878, data_time: 0.034, memory: 10345, loss_rpn_cls: 0.0318, loss_rpn_bbox: 0.0392, loss_cls: 0.1997, acc: 92.8577, loss_bbox: 0.2501, loss_mask: 0.2458, loss: 0.7666 2023-11-16 19:11:13,351 - mmdet - INFO - Epoch [5][1650/1833] lr: 5.563e-06, eta: 13:46:17, time: 0.884, data_time: 0.036, memory: 10345, loss_rpn_cls: 0.0357, loss_rpn_bbox: 0.0423, loss_cls: 0.2030, acc: 92.7571, loss_bbox: 0.2527, loss_mask: 0.2473, loss: 0.7810 2023-11-16 19:11:56,917 - mmdet - INFO - Epoch [5][1700/1833] lr: 5.563e-06, eta: 13:45:34, time: 0.871, data_time: 0.032, memory: 10345, loss_rpn_cls: 0.0327, loss_rpn_bbox: 0.0386, loss_cls: 0.1981, acc: 93.0380, loss_bbox: 0.2415, loss_mask: 0.2444, loss: 0.7553 2023-11-16 19:12:40,520 - mmdet - INFO - Epoch [5][1750/1833] lr: 5.563e-06, eta: 13:44:51, time: 0.872, data_time: 0.032, memory: 10345, loss_rpn_cls: 0.0335, loss_rpn_bbox: 0.0406, loss_cls: 0.2005, acc: 92.8401, loss_bbox: 0.2482, loss_mask: 0.2446, loss: 0.7674 2023-11-16 19:13:24,745 - mmdet - INFO - Epoch [5][1800/1833] lr: 5.563e-06, eta: 13:44:12, time: 0.884, data_time: 0.032, memory: 10345, loss_rpn_cls: 0.0317, loss_rpn_bbox: 0.0406, loss_cls: 0.2019, acc: 92.8700, loss_bbox: 0.2488, loss_mask: 0.2443, loss: 0.7673 2023-11-16 19:13:54,100 - mmdet - INFO - Saving checkpoint at 5 epochs 2023-11-16 19:14:33,175 - mmdet - INFO - Evaluating bbox... 2023-11-16 19:15:07,283 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.439 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.682 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.487 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.304 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.478 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.563 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.572 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.572 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.572 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.422 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.615 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.707 2023-11-16 19:15:07,286 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.551 | bicycle | 0.341 | car | 0.458 | | motorcycle | 0.446 | airplane | 0.630 | bus | 0.671 | | train | 0.644 | truck | 0.381 | boat | 0.309 | | traffic light | 0.296 | fire hydrant | 0.640 | stop sign | 0.631 | | parking meter | 0.499 | bench | 0.258 | bird | 0.395 | | cat | 0.672 | dog | 0.658 | horse | 0.594 | | sheep | 0.550 | cow | 0.609 | elephant | 0.663 | | bear | 0.728 | zebra | 0.646 | giraffe | 0.663 | | backpack | 0.187 | umbrella | 0.424 | handbag | 0.193 | | tie | 0.325 | suitcase | 0.423 | frisbee | 0.674 | | skis | 0.237 | snowboard | 0.374 | sports ball | 0.455 | | kite | 0.445 | baseball bat | 0.354 | baseball glove | 0.398 | | skateboard | 0.529 | surfboard | 0.405 | tennis racket | 0.481 | | bottle | 0.430 | wine glass | 0.360 | cup | 0.478 | | fork | 0.354 | knife | 0.245 | spoon | 0.230 | | bowl | 0.444 | banana | 0.275 | apple | 0.259 | | sandwich | 0.417 | orange | 0.340 | broccoli | 0.255 | | carrot | 0.236 | hot dog | 0.378 | pizza | 0.477 | | donut | 0.502 | cake | 0.401 | chair | 0.313 | | couch | 0.438 | potted plant | 0.288 | bed | 0.424 | | dining table | 0.283 | toilet | 0.611 | tv | 0.577 | | laptop | 0.628 | mouse | 0.626 | remote | 0.364 | | keyboard | 0.496 | cell phone | 0.408 | microwave | 0.617 | | oven | 0.367 | toaster | 0.440 | sink | 0.418 | | refrigerator | 0.613 | book | 0.157 | clock | 0.539 | | vase | 0.392 | scissors | 0.320 | teddy bear | 0.490 | | hair drier | 0.113 | toothbrush | 0.251 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-16 19:15:07,286 - mmdet - INFO - Evaluating segm... 2023-11-16 19:15:48,022 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.403 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.646 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.435 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.223 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.442 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.590 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.528 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.528 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.528 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.353 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.576 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.692 2023-11-16 19:15:48,024 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.477 | bicycle | 0.204 | car | 0.421 | | motorcycle | 0.363 | airplane | 0.511 | bus | 0.671 | | train | 0.645 | truck | 0.381 | boat | 0.276 | | traffic light | 0.277 | fire hydrant | 0.676 | stop sign | 0.633 | | parking meter | 0.514 | bench | 0.196 | bird | 0.324 | | cat | 0.705 | dog | 0.645 | horse | 0.447 | | sheep | 0.488 | cow | 0.518 | elephant | 0.596 | | bear | 0.732 | zebra | 0.563 | giraffe | 0.508 | | backpack | 0.199 | umbrella | 0.488 | handbag | 0.189 | | tie | 0.314 | suitcase | 0.465 | frisbee | 0.627 | | skis | 0.033 | snowboard | 0.255 | sports ball | 0.439 | | kite | 0.292 | baseball bat | 0.261 | baseball glove | 0.429 | | skateboard | 0.317 | surfboard | 0.349 | tennis racket | 0.558 | | bottle | 0.412 | wine glass | 0.309 | cup | 0.486 | | fork | 0.192 | knife | 0.157 | spoon | 0.167 | | bowl | 0.424 | banana | 0.217 | apple | 0.250 | | sandwich | 0.455 | orange | 0.346 | broccoli | 0.239 | | carrot | 0.209 | hot dog | 0.290 | pizza | 0.480 | | donut | 0.524 | cake | 0.423 | chair | 0.225 | | couch | 0.373 | potted plant | 0.243 | bed | 0.360 | | dining table | 0.166 | toilet | 0.612 | tv | 0.623 | | laptop | 0.647 | mouse | 0.619 | remote | 0.327 | | keyboard | 0.521 | cell phone | 0.404 | microwave | 0.646 | | oven | 0.348 | toaster | 0.492 | sink | 0.396 | | refrigerator | 0.641 | book | 0.120 | clock | 0.528 | | vase | 0.399 | scissors | 0.265 | teddy bear | 0.466 | | hair drier | 0.095 | toothbrush | 0.187 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-16 19:15:48,587 - mmdet - INFO - The previous best checkpoint /mnt/petrelfs/lizhiqi/DINO/detection/work_dirs/mask_rcnn_flash_internimage_b_fpn_3x_cocoo_0.4_0.9_4x16/best_bbox_mAP_epoch_4.pth was removed 2023-11-16 19:15:52,501 - mmdet - INFO - Now best checkpoint is saved as best_bbox_mAP_epoch_5.pth. 2023-11-16 19:15:52,502 - mmdet - INFO - Best bbox_mAP is 0.4386 at 5 epoch. 2023-11-16 19:15:52,502 - mmdet - INFO - Exp name: mask_rcnn_flash_internimage_b_fpn_3x_coco_0.4_0.9-4x16.py 2023-11-16 19:15:52,502 - mmdet - INFO - Epoch(val) [5][313] bbox_mAP: 0.4386, bbox_mAP_50: 0.6820, bbox_mAP_75: 0.4868, bbox_mAP_s: 0.3043, bbox_mAP_m: 0.4785, bbox_mAP_l: 0.5627, bbox_mAP_copypaste: 0.4386 0.6820 0.4868 0.3043 0.4785 0.5627, segm_mAP: 0.4034, segm_mAP_50: 0.6463, segm_mAP_75: 0.4347, segm_mAP_s: 0.2227, segm_mAP_m: 0.4419, segm_mAP_l: 0.5902, segm_mAP_copypaste: 0.4034 0.6463 0.4347 0.2227 0.4419 0.5902 2023-11-16 19:16:39,280 - mmdet - INFO - Epoch [6][50/1833] lr: 5.563e-06, eta: 13:40:23, time: 0.935, data_time: 0.093, memory: 10345, loss_rpn_cls: 0.0321, loss_rpn_bbox: 0.0402, loss_cls: 0.1962, acc: 92.9900, loss_bbox: 0.2447, loss_mask: 0.2397, loss: 0.7529 2023-11-16 19:17:23,361 - mmdet - INFO - Epoch [6][100/1833] lr: 5.563e-06, eta: 13:39:45, time: 0.881, data_time: 0.034, memory: 10345, loss_rpn_cls: 0.0322, loss_rpn_bbox: 0.0394, loss_cls: 0.1939, acc: 93.0280, loss_bbox: 0.2474, loss_mask: 0.2442, loss: 0.7572 2023-11-16 19:18:07,387 - mmdet - INFO - Epoch [6][150/1833] lr: 5.563e-06, eta: 13:39:05, time: 0.881, data_time: 0.039, memory: 10345, loss_rpn_cls: 0.0325, loss_rpn_bbox: 0.0405, loss_cls: 0.1987, acc: 92.8484, loss_bbox: 0.2483, loss_mask: 0.2452, loss: 0.7653 2023-11-16 19:18:51,121 - mmdet - INFO - Epoch [6][200/1833] lr: 5.563e-06, eta: 13:38:24, time: 0.875, data_time: 0.035, memory: 10345, loss_rpn_cls: 0.0319, loss_rpn_bbox: 0.0402, loss_cls: 0.1940, acc: 93.0868, loss_bbox: 0.2407, loss_mask: 0.2409, loss: 0.7479 2023-11-16 19:19:35,375 - mmdet - INFO - Epoch [6][250/1833] lr: 5.563e-06, eta: 13:37:46, time: 0.885, data_time: 0.034, memory: 10345, loss_rpn_cls: 0.0321, loss_rpn_bbox: 0.0403, loss_cls: 0.1974, acc: 92.9438, loss_bbox: 0.2469, loss_mask: 0.2446, loss: 0.7613 2023-11-16 19:20:19,621 - mmdet - INFO - Epoch [6][300/1833] lr: 5.563e-06, eta: 13:37:08, time: 0.885, data_time: 0.036, memory: 10345, loss_rpn_cls: 0.0344, loss_rpn_bbox: 0.0415, loss_cls: 0.1994, acc: 92.8499, loss_bbox: 0.2490, loss_mask: 0.2410, loss: 0.7653 2023-11-16 19:21:03,273 - mmdet - INFO - Epoch [6][350/1833] lr: 5.563e-06, eta: 13:36:26, time: 0.873, data_time: 0.036, memory: 10345, loss_rpn_cls: 0.0323, loss_rpn_bbox: 0.0401, loss_cls: 0.1950, acc: 92.9828, loss_bbox: 0.2457, loss_mask: 0.2420, loss: 0.7551 2023-11-16 19:21:47,529 - mmdet - INFO - Epoch [6][400/1833] lr: 5.563e-06, eta: 13:35:48, time: 0.885, data_time: 0.033, memory: 10345, loss_rpn_cls: 0.0334, loss_rpn_bbox: 0.0402, loss_cls: 0.1967, acc: 92.9229, loss_bbox: 0.2478, loss_mask: 0.2450, loss: 0.7631 2023-11-16 19:22:31,788 - mmdet - INFO - Epoch [6][450/1833] lr: 5.563e-06, eta: 13:35:10, time: 0.885, data_time: 0.032, memory: 10345, loss_rpn_cls: 0.0335, loss_rpn_bbox: 0.0397, loss_cls: 0.1937, acc: 93.0762, loss_bbox: 0.2439, loss_mask: 0.2435, loss: 0.7542 2023-11-16 19:23:19,304 - mmdet - INFO - Epoch [6][500/1833] lr: 5.563e-06, eta: 13:34:51, time: 0.950, data_time: 0.048, memory: 10345, loss_rpn_cls: 0.0303, loss_rpn_bbox: 0.0385, loss_cls: 0.1947, acc: 93.0240, loss_bbox: 0.2426, loss_mask: 0.2395, loss: 0.7457 2023-11-16 19:24:03,559 - mmdet - INFO - Epoch [6][550/1833] lr: 5.563e-06, eta: 13:34:12, time: 0.885, data_time: 0.036, memory: 10345, loss_rpn_cls: 0.0334, loss_rpn_bbox: 0.0398, loss_cls: 0.1975, acc: 92.9661, loss_bbox: 0.2438, loss_mask: 0.2396, loss: 0.7540 2023-11-16 19:24:48,117 - mmdet - INFO - Epoch [6][600/1833] lr: 5.563e-06, eta: 13:33:35, time: 0.891, data_time: 0.034, memory: 10345, loss_rpn_cls: 0.0307, loss_rpn_bbox: 0.0389, loss_cls: 0.1946, acc: 93.0005, loss_bbox: 0.2436, loss_mask: 0.2413, loss: 0.7490 2023-11-16 19:25:31,894 - mmdet - INFO - Epoch [6][650/1833] lr: 5.563e-06, eta: 13:32:54, time: 0.876, data_time: 0.035, memory: 10345, loss_rpn_cls: 0.0327, loss_rpn_bbox: 0.0399, loss_cls: 0.1948, acc: 93.0153, loss_bbox: 0.2424, loss_mask: 0.2426, loss: 0.7524 2023-11-16 19:26:16,339 - mmdet - INFO - Epoch [6][700/1833] lr: 5.563e-06, eta: 13:32:16, time: 0.888, data_time: 0.037, memory: 10345, loss_rpn_cls: 0.0322, loss_rpn_bbox: 0.0401, loss_cls: 0.1968, acc: 92.9189, loss_bbox: 0.2470, loss_mask: 0.2416, loss: 0.7577 2023-11-16 19:27:00,545 - mmdet - INFO - Epoch [6][750/1833] lr: 5.563e-06, eta: 13:31:38, time: 0.884, data_time: 0.030, memory: 10345, loss_rpn_cls: 0.0321, loss_rpn_bbox: 0.0391, loss_cls: 0.1941, acc: 93.0743, loss_bbox: 0.2421, loss_mask: 0.2411, loss: 0.7485 2023-11-16 19:27:44,757 - mmdet - INFO - Epoch [6][800/1833] lr: 5.563e-06, eta: 13:30:59, time: 0.885, data_time: 0.037, memory: 10345, loss_rpn_cls: 0.0320, loss_rpn_bbox: 0.0398, loss_cls: 0.1968, acc: 92.9650, loss_bbox: 0.2437, loss_mask: 0.2413, loss: 0.7535 2023-11-16 19:28:28,825 - mmdet - INFO - Epoch [6][850/1833] lr: 5.563e-06, eta: 13:30:19, time: 0.881, data_time: 0.036, memory: 10345, loss_rpn_cls: 0.0316, loss_rpn_bbox: 0.0389, loss_cls: 0.1956, acc: 92.9979, loss_bbox: 0.2434, loss_mask: 0.2393, loss: 0.7487 2023-11-16 19:29:13,064 - mmdet - INFO - Epoch [6][900/1833] lr: 5.563e-06, eta: 13:29:40, time: 0.885, data_time: 0.035, memory: 10345, loss_rpn_cls: 0.0314, loss_rpn_bbox: 0.0392, loss_cls: 0.1929, acc: 93.0567, loss_bbox: 0.2427, loss_mask: 0.2403, loss: 0.7465 2023-11-16 19:29:57,284 - mmdet - INFO - Epoch [6][950/1833] lr: 5.563e-06, eta: 13:29:01, time: 0.884, data_time: 0.040, memory: 10345, loss_rpn_cls: 0.0297, loss_rpn_bbox: 0.0378, loss_cls: 0.1909, acc: 93.1471, loss_bbox: 0.2397, loss_mask: 0.2401, loss: 0.7383 2023-11-16 19:30:43,528 - mmdet - INFO - Epoch [6][1000/1833] lr: 5.563e-06, eta: 13:28:33, time: 0.925, data_time: 0.056, memory: 10345, loss_rpn_cls: 0.0326, loss_rpn_bbox: 0.0397, loss_cls: 0.1951, acc: 92.9801, loss_bbox: 0.2425, loss_mask: 0.2402, loss: 0.7501 2023-11-16 19:31:27,825 - mmdet - INFO - Epoch [6][1050/1833] lr: 5.563e-06, eta: 13:27:54, time: 0.886, data_time: 0.034, memory: 10345, loss_rpn_cls: 0.0308, loss_rpn_bbox: 0.0392, loss_cls: 0.1907, acc: 93.1102, loss_bbox: 0.2394, loss_mask: 0.2403, loss: 0.7404 2023-11-16 19:32:12,203 - mmdet - INFO - Epoch [6][1100/1833] lr: 5.563e-06, eta: 13:27:15, time: 0.888, data_time: 0.038, memory: 10345, loss_rpn_cls: 0.0317, loss_rpn_bbox: 0.0398, loss_cls: 0.1972, acc: 92.8944, loss_bbox: 0.2476, loss_mask: 0.2398, loss: 0.7561 2023-11-16 19:32:57,302 - mmdet - INFO - Epoch [6][1150/1833] lr: 5.563e-06, eta: 13:26:41, time: 0.902, data_time: 0.032, memory: 10345, loss_rpn_cls: 0.0313, loss_rpn_bbox: 0.0393, loss_cls: 0.1942, acc: 93.0232, loss_bbox: 0.2437, loss_mask: 0.2416, loss: 0.7500 2023-11-16 19:33:41,402 - mmdet - INFO - Epoch [6][1200/1833] lr: 5.563e-06, eta: 13:26:00, time: 0.881, data_time: 0.034, memory: 10345, loss_rpn_cls: 0.0323, loss_rpn_bbox: 0.0400, loss_cls: 0.1989, acc: 92.8963, loss_bbox: 0.2483, loss_mask: 0.2427, loss: 0.7623 2023-11-16 19:34:25,208 - mmdet - INFO - Epoch [6][1250/1833] lr: 5.563e-06, eta: 13:25:19, time: 0.877, data_time: 0.035, memory: 10345, loss_rpn_cls: 0.0298, loss_rpn_bbox: 0.0382, loss_cls: 0.1927, acc: 93.0699, loss_bbox: 0.2416, loss_mask: 0.2405, loss: 0.7429 2023-11-16 19:35:09,461 - mmdet - INFO - Epoch [6][1300/1833] lr: 5.563e-06, eta: 13:24:40, time: 0.885, data_time: 0.036, memory: 10345, loss_rpn_cls: 0.0313, loss_rpn_bbox: 0.0387, loss_cls: 0.1965, acc: 93.0037, loss_bbox: 0.2449, loss_mask: 0.2418, loss: 0.7532 2023-11-16 19:35:53,254 - mmdet - INFO - Epoch [6][1350/1833] lr: 5.563e-06, eta: 13:23:58, time: 0.876, data_time: 0.039, memory: 10345, loss_rpn_cls: 0.0322, loss_rpn_bbox: 0.0396, loss_cls: 0.1893, acc: 93.1542, loss_bbox: 0.2388, loss_mask: 0.2425, loss: 0.7424 2023-11-16 19:36:38,164 - mmdet - INFO - Epoch [6][1400/1833] lr: 5.563e-06, eta: 13:23:22, time: 0.898, data_time: 0.056, memory: 10345, loss_rpn_cls: 0.0308, loss_rpn_bbox: 0.0393, loss_cls: 0.1937, acc: 93.1091, loss_bbox: 0.2403, loss_mask: 0.2421, loss: 0.7462 2023-11-16 19:37:22,243 - mmdet - INFO - Epoch [6][1450/1833] lr: 5.563e-06, eta: 13:22:41, time: 0.882, data_time: 0.032, memory: 10345, loss_rpn_cls: 0.0313, loss_rpn_bbox: 0.0387, loss_cls: 0.1947, acc: 93.0996, loss_bbox: 0.2396, loss_mask: 0.2427, loss: 0.7470 2023-11-16 19:38:06,322 - mmdet - INFO - Epoch [6][1500/1833] lr: 5.563e-06, eta: 13:22:01, time: 0.881, data_time: 0.037, memory: 10345, loss_rpn_cls: 0.0324, loss_rpn_bbox: 0.0407, loss_cls: 0.1989, acc: 92.8606, loss_bbox: 0.2466, loss_mask: 0.2421, loss: 0.7606 2023-11-16 19:38:52,085 - mmdet - INFO - Epoch [6][1550/1833] lr: 5.563e-06, eta: 13:21:29, time: 0.916, data_time: 0.031, memory: 10345, loss_rpn_cls: 0.0314, loss_rpn_bbox: 0.0389, loss_cls: 0.1952, acc: 92.9884, loss_bbox: 0.2462, loss_mask: 0.2415, loss: 0.7532 2023-11-16 19:39:35,736 - mmdet - INFO - Epoch [6][1600/1833] lr: 5.563e-06, eta: 13:20:46, time: 0.873, data_time: 0.033, memory: 10345, loss_rpn_cls: 0.0310, loss_rpn_bbox: 0.0388, loss_cls: 0.1929, acc: 93.1203, loss_bbox: 0.2406, loss_mask: 0.2421, loss: 0.7454 2023-11-16 19:40:19,752 - mmdet - INFO - Epoch [6][1650/1833] lr: 5.563e-06, eta: 13:20:06, time: 0.880, data_time: 0.034, memory: 10345, loss_rpn_cls: 0.0317, loss_rpn_bbox: 0.0391, loss_cls: 0.1950, acc: 93.0630, loss_bbox: 0.2391, loss_mask: 0.2404, loss: 0.7452 2023-11-16 19:41:03,481 - mmdet - INFO - Epoch [6][1700/1833] lr: 5.563e-06, eta: 13:19:23, time: 0.875, data_time: 0.043, memory: 10345, loss_rpn_cls: 0.0314, loss_rpn_bbox: 0.0384, loss_cls: 0.1907, acc: 93.1629, loss_bbox: 0.2384, loss_mask: 0.2416, loss: 0.7405 2023-11-16 19:41:48,685 - mmdet - INFO - Epoch [6][1750/1833] lr: 5.563e-06, eta: 13:18:48, time: 0.904, data_time: 0.028, memory: 10345, loss_rpn_cls: 0.0322, loss_rpn_bbox: 0.0392, loss_cls: 0.1946, acc: 92.9813, loss_bbox: 0.2443, loss_mask: 0.2412, loss: 0.7514 2023-11-16 19:42:39,182 - mmdet - INFO - Epoch [6][1800/1833] lr: 5.563e-06, eta: 13:18:40, time: 1.010, data_time: 0.028, memory: 10345, loss_rpn_cls: 0.0302, loss_rpn_bbox: 0.0382, loss_cls: 0.1920, acc: 93.1519, loss_bbox: 0.2375, loss_mask: 0.2368, loss: 0.7347 2023-11-16 19:43:08,866 - mmdet - INFO - Saving checkpoint at 6 epochs 2023-11-16 19:43:50,538 - mmdet - INFO - Evaluating bbox... 2023-11-16 19:44:24,974 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.446 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.687 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.496 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.316 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.489 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.574 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.580 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.580 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.580 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.424 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.624 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.718 2023-11-16 19:44:24,976 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.554 | bicycle | 0.333 | car | 0.457 | | motorcycle | 0.453 | airplane | 0.662 | bus | 0.663 | | train | 0.644 | truck | 0.413 | boat | 0.308 | | traffic light | 0.293 | fire hydrant | 0.690 | stop sign | 0.640 | | parking meter | 0.484 | bench | 0.269 | bird | 0.400 | | cat | 0.687 | dog | 0.672 | horse | 0.592 | | sheep | 0.554 | cow | 0.600 | elephant | 0.675 | | bear | 0.681 | zebra | 0.671 | giraffe | 0.665 | | backpack | 0.201 | umbrella | 0.429 | handbag | 0.206 | | tie | 0.328 | suitcase | 0.454 | frisbee | 0.693 | | skis | 0.238 | snowboard | 0.418 | sports ball | 0.468 | | kite | 0.450 | baseball bat | 0.373 | baseball glove | 0.415 | | skateboard | 0.516 | surfboard | 0.422 | tennis racket | 0.485 | | bottle | 0.428 | wine glass | 0.389 | cup | 0.487 | | fork | 0.384 | knife | 0.260 | spoon | 0.228 | | bowl | 0.453 | banana | 0.268 | apple | 0.246 | | sandwich | 0.431 | orange | 0.357 | broccoli | 0.272 | | carrot | 0.261 | hot dog | 0.405 | pizza | 0.523 | | donut | 0.511 | cake | 0.419 | chair | 0.328 | | couch | 0.408 | potted plant | 0.302 | bed | 0.431 | | dining table | 0.270 | toilet | 0.614 | tv | 0.598 | | laptop | 0.626 | mouse | 0.644 | remote | 0.378 | | keyboard | 0.504 | cell phone | 0.417 | microwave | 0.623 | | oven | 0.373 | toaster | 0.347 | sink | 0.404 | | refrigerator | 0.580 | book | 0.171 | clock | 0.541 | | vase | 0.415 | scissors | 0.346 | teddy bear | 0.491 | | hair drier | 0.149 | toothbrush | 0.259 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-16 19:44:24,976 - mmdet - INFO - Evaluating segm... 2023-11-16 19:45:06,002 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.409 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.653 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.439 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.230 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.450 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.598 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.534 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.534 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.534 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.360 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.580 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.694 2023-11-16 19:45:06,005 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.484 | bicycle | 0.204 | car | 0.428 | | motorcycle | 0.362 | airplane | 0.514 | bus | 0.663 | | train | 0.645 | truck | 0.408 | boat | 0.288 | | traffic light | 0.290 | fire hydrant | 0.681 | stop sign | 0.621 | | parking meter | 0.498 | bench | 0.213 | bird | 0.325 | | cat | 0.719 | dog | 0.647 | horse | 0.437 | | sheep | 0.499 | cow | 0.514 | elephant | 0.609 | | bear | 0.708 | zebra | 0.592 | giraffe | 0.510 | | backpack | 0.195 | umbrella | 0.495 | handbag | 0.206 | | tie | 0.332 | suitcase | 0.469 | frisbee | 0.639 | | skis | 0.037 | snowboard | 0.246 | sports ball | 0.431 | | kite | 0.316 | baseball bat | 0.268 | baseball glove | 0.440 | | skateboard | 0.317 | surfboard | 0.358 | tennis racket | 0.567 | | bottle | 0.420 | wine glass | 0.345 | cup | 0.485 | | fork | 0.206 | knife | 0.179 | spoon | 0.187 | | bowl | 0.428 | banana | 0.219 | apple | 0.247 | | sandwich | 0.474 | orange | 0.356 | broccoli | 0.255 | | carrot | 0.230 | hot dog | 0.341 | pizza | 0.523 | | donut | 0.535 | cake | 0.443 | chair | 0.239 | | couch | 0.354 | potted plant | 0.261 | bed | 0.339 | | dining table | 0.160 | toilet | 0.610 | tv | 0.632 | | laptop | 0.644 | mouse | 0.627 | remote | 0.346 | | keyboard | 0.505 | cell phone | 0.408 | microwave | 0.651 | | oven | 0.355 | toaster | 0.384 | sink | 0.392 | | refrigerator | 0.610 | book | 0.118 | clock | 0.541 | | vase | 0.413 | scissors | 0.283 | teddy bear | 0.477 | | hair drier | 0.134 | toothbrush | 0.170 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-16 19:45:06,582 - mmdet - INFO - The previous best checkpoint /mnt/petrelfs/lizhiqi/DINO/detection/work_dirs/mask_rcnn_flash_internimage_b_fpn_3x_cocoo_0.4_0.9_4x16/best_bbox_mAP_epoch_5.pth was removed 2023-11-16 19:45:10,469 - mmdet - INFO - Now best checkpoint is saved as best_bbox_mAP_epoch_6.pth. 2023-11-16 19:45:10,469 - mmdet - INFO - Best bbox_mAP is 0.4463 at 6 epoch. 2023-11-16 19:45:10,469 - mmdet - INFO - Exp name: mask_rcnn_flash_internimage_b_fpn_3x_coco_0.4_0.9-4x16.py 2023-11-16 19:45:10,469 - mmdet - INFO - Epoch(val) [6][313] bbox_mAP: 0.4463, bbox_mAP_50: 0.6866, bbox_mAP_75: 0.4962, bbox_mAP_s: 0.3163, bbox_mAP_m: 0.4886, bbox_mAP_l: 0.5739, bbox_mAP_copypaste: 0.4463 0.6866 0.4962 0.3163 0.4886 0.5739, segm_mAP: 0.4087, segm_mAP_50: 0.6527, segm_mAP_75: 0.4390, segm_mAP_s: 0.2305, segm_mAP_m: 0.4502, segm_mAP_l: 0.5977, segm_mAP_copypaste: 0.4087 0.6527 0.4390 0.2305 0.4502 0.5977 2023-11-16 19:45:56,896 - mmdet - INFO - Epoch [7][50/1833] lr: 5.563e-06, eta: 13:15:19, time: 0.928, data_time: 0.099, memory: 10345, loss_rpn_cls: 0.0310, loss_rpn_bbox: 0.0404, loss_cls: 0.1929, acc: 93.0273, loss_bbox: 0.2446, loss_mask: 0.2417, loss: 0.7507 2023-11-16 19:46:40,348 - mmdet - INFO - Epoch [7][100/1833] lr: 5.563e-06, eta: 13:14:36, time: 0.869, data_time: 0.033, memory: 10345, loss_rpn_cls: 0.0308, loss_rpn_bbox: 0.0382, loss_cls: 0.1862, acc: 93.2617, loss_bbox: 0.2358, loss_mask: 0.2385, loss: 0.7295 2023-11-16 19:47:24,120 - mmdet - INFO - Epoch [7][150/1833] lr: 5.563e-06, eta: 13:13:54, time: 0.875, data_time: 0.034, memory: 10345, loss_rpn_cls: 0.0295, loss_rpn_bbox: 0.0371, loss_cls: 0.1868, acc: 93.2476, loss_bbox: 0.2372, loss_mask: 0.2395, loss: 0.7301 2023-11-16 19:48:07,822 - mmdet - INFO - Epoch [7][200/1833] lr: 5.563e-06, eta: 13:13:12, time: 0.874, data_time: 0.030, memory: 10345, loss_rpn_cls: 0.0289, loss_rpn_bbox: 0.0373, loss_cls: 0.1890, acc: 93.2013, loss_bbox: 0.2377, loss_mask: 0.2358, loss: 0.7287 2023-11-16 19:48:51,512 - mmdet - INFO - Epoch [7][250/1833] lr: 5.563e-06, eta: 13:12:29, time: 0.873, data_time: 0.036, memory: 10345, loss_rpn_cls: 0.0297, loss_rpn_bbox: 0.0378, loss_cls: 0.1850, acc: 93.3127, loss_bbox: 0.2335, loss_mask: 0.2362, loss: 0.7223 2023-11-16 19:49:35,697 - mmdet - INFO - Epoch [7][300/1833] lr: 5.563e-06, eta: 13:11:50, time: 0.884, data_time: 0.042, memory: 10345, loss_rpn_cls: 0.0311, loss_rpn_bbox: 0.0402, loss_cls: 0.1921, acc: 93.0852, loss_bbox: 0.2408, loss_mask: 0.2400, loss: 0.7442 2023-11-16 19:50:19,386 - mmdet - INFO - Epoch [7][350/1833] lr: 5.563e-06, eta: 13:11:07, time: 0.874, data_time: 0.041, memory: 10345, loss_rpn_cls: 0.0305, loss_rpn_bbox: 0.0382, loss_cls: 0.1886, acc: 93.2184, loss_bbox: 0.2377, loss_mask: 0.2381, loss: 0.7331 2023-11-16 19:51:03,539 - mmdet - INFO - Epoch [7][400/1833] lr: 5.563e-06, eta: 13:10:27, time: 0.883, data_time: 0.033, memory: 10345, loss_rpn_cls: 0.0314, loss_rpn_bbox: 0.0397, loss_cls: 0.1921, acc: 93.1145, loss_bbox: 0.2417, loss_mask: 0.2375, loss: 0.7424 2023-11-16 19:51:47,388 - mmdet - INFO - Epoch [7][450/1833] lr: 5.563e-06, eta: 13:09:46, time: 0.877, data_time: 0.044, memory: 10345, loss_rpn_cls: 0.0299, loss_rpn_bbox: 0.0376, loss_cls: 0.1885, acc: 93.2182, loss_bbox: 0.2368, loss_mask: 0.2357, loss: 0.7285 2023-11-16 19:52:31,260 - mmdet - INFO - Epoch [7][500/1833] lr: 5.563e-06, eta: 13:09:05, time: 0.877, data_time: 0.033, memory: 10345, loss_rpn_cls: 0.0319, loss_rpn_bbox: 0.0394, loss_cls: 0.1888, acc: 93.1713, loss_bbox: 0.2385, loss_mask: 0.2398, loss: 0.7384 2023-11-16 19:53:14,750 - mmdet - INFO - Epoch [7][550/1833] lr: 5.563e-06, eta: 13:08:21, time: 0.870, data_time: 0.034, memory: 10345, loss_rpn_cls: 0.0309, loss_rpn_bbox: 0.0382, loss_cls: 0.1883, acc: 93.2099, loss_bbox: 0.2369, loss_mask: 0.2345, loss: 0.7288 2023-11-16 19:53:58,724 - mmdet - INFO - Epoch [7][600/1833] lr: 5.563e-06, eta: 13:07:40, time: 0.880, data_time: 0.033, memory: 10345, loss_rpn_cls: 0.0313, loss_rpn_bbox: 0.0393, loss_cls: 0.1940, acc: 92.9905, loss_bbox: 0.2447, loss_mask: 0.2396, loss: 0.7489 2023-11-16 19:54:43,072 - mmdet - INFO - Epoch [7][650/1833] lr: 5.563e-06, eta: 13:07:01, time: 0.887, data_time: 0.035, memory: 10345, loss_rpn_cls: 0.0301, loss_rpn_bbox: 0.0387, loss_cls: 0.1958, acc: 92.9981, loss_bbox: 0.2445, loss_mask: 0.2411, loss: 0.7502 2023-11-16 19:55:27,085 - mmdet - INFO - Epoch [7][700/1833] lr: 5.563e-06, eta: 13:06:20, time: 0.880, data_time: 0.035, memory: 10345, loss_rpn_cls: 0.0287, loss_rpn_bbox: 0.0380, loss_cls: 0.1913, acc: 93.1359, loss_bbox: 0.2385, loss_mask: 0.2378, loss: 0.7343 2023-11-16 19:56:10,639 - mmdet - INFO - Epoch [7][750/1833] lr: 5.563e-06, eta: 13:05:37, time: 0.871, data_time: 0.036, memory: 10345, loss_rpn_cls: 0.0310, loss_rpn_bbox: 0.0389, loss_cls: 0.1945, acc: 93.0596, loss_bbox: 0.2411, loss_mask: 0.2396, loss: 0.7451 2023-11-16 19:56:54,652 - mmdet - INFO - Epoch [7][800/1833] lr: 5.563e-06, eta: 13:04:56, time: 0.880, data_time: 0.038, memory: 10345, loss_rpn_cls: 0.0300, loss_rpn_bbox: 0.0394, loss_cls: 0.1916, acc: 93.1195, loss_bbox: 0.2408, loss_mask: 0.2378, loss: 0.7396 2023-11-16 19:57:38,663 - mmdet - INFO - Epoch [7][850/1833] lr: 5.563e-06, eta: 13:04:15, time: 0.880, data_time: 0.043, memory: 10345, loss_rpn_cls: 0.0313, loss_rpn_bbox: 0.0381, loss_cls: 0.1872, acc: 93.2350, loss_bbox: 0.2364, loss_mask: 0.2385, loss: 0.7315 2023-11-16 19:58:22,455 - mmdet - INFO - Epoch [7][900/1833] lr: 5.563e-06, eta: 13:03:34, time: 0.876, data_time: 0.037, memory: 10345, loss_rpn_cls: 0.0312, loss_rpn_bbox: 0.0400, loss_cls: 0.1897, acc: 93.2225, loss_bbox: 0.2380, loss_mask: 0.2367, loss: 0.7356 2023-11-16 19:59:06,161 - mmdet - INFO - Epoch [7][950/1833] lr: 5.563e-06, eta: 13:02:51, time: 0.874, data_time: 0.034, memory: 10345, loss_rpn_cls: 0.0303, loss_rpn_bbox: 0.0373, loss_cls: 0.1845, acc: 93.3024, loss_bbox: 0.2349, loss_mask: 0.2366, loss: 0.7236 2023-11-16 19:59:49,568 - mmdet - INFO - Epoch [7][1000/1833] lr: 5.563e-06, eta: 13:02:07, time: 0.868, data_time: 0.036, memory: 10345, loss_rpn_cls: 0.0311, loss_rpn_bbox: 0.0391, loss_cls: 0.1871, acc: 93.2206, loss_bbox: 0.2383, loss_mask: 0.2387, loss: 0.7343 2023-11-16 20:00:33,684 - mmdet - INFO - Epoch [7][1050/1833] lr: 5.563e-06, eta: 13:01:27, time: 0.883, data_time: 0.036, memory: 10345, loss_rpn_cls: 0.0299, loss_rpn_bbox: 0.0375, loss_cls: 0.1891, acc: 93.1539, loss_bbox: 0.2379, loss_mask: 0.2344, loss: 0.7289 2023-11-16 20:01:17,852 - mmdet - INFO - Epoch [7][1100/1833] lr: 5.563e-06, eta: 13:00:47, time: 0.883, data_time: 0.037, memory: 10345, loss_rpn_cls: 0.0306, loss_rpn_bbox: 0.0394, loss_cls: 0.1940, acc: 93.0264, loss_bbox: 0.2430, loss_mask: 0.2397, loss: 0.7467 2023-11-16 20:02:02,478 - mmdet - INFO - Epoch [7][1150/1833] lr: 5.563e-06, eta: 13:00:08, time: 0.892, data_time: 0.035, memory: 10345, loss_rpn_cls: 0.0313, loss_rpn_bbox: 0.0399, loss_cls: 0.1945, acc: 93.0370, loss_bbox: 0.2432, loss_mask: 0.2425, loss: 0.7514 2023-11-16 20:02:46,730 - mmdet - INFO - Epoch [7][1200/1833] lr: 5.563e-06, eta: 12:59:28, time: 0.885, data_time: 0.042, memory: 10345, loss_rpn_cls: 0.0309, loss_rpn_bbox: 0.0387, loss_cls: 0.1897, acc: 93.1567, loss_bbox: 0.2391, loss_mask: 0.2361, loss: 0.7345 2023-11-16 20:03:30,503 - mmdet - INFO - Epoch [7][1250/1833] lr: 5.563e-06, eta: 12:58:46, time: 0.876, data_time: 0.035, memory: 10345, loss_rpn_cls: 0.0303, loss_rpn_bbox: 0.0373, loss_cls: 0.1894, acc: 93.1992, loss_bbox: 0.2374, loss_mask: 0.2386, loss: 0.7330 2023-11-16 20:04:14,321 - mmdet - INFO - Epoch [7][1300/1833] lr: 5.563e-06, eta: 12:58:04, time: 0.876, data_time: 0.035, memory: 10345, loss_rpn_cls: 0.0309, loss_rpn_bbox: 0.0396, loss_cls: 0.1916, acc: 93.0974, loss_bbox: 0.2405, loss_mask: 0.2392, loss: 0.7418 2023-11-16 20:04:58,347 - mmdet - INFO - Epoch [7][1350/1833] lr: 5.563e-06, eta: 12:57:23, time: 0.881, data_time: 0.036, memory: 10345, loss_rpn_cls: 0.0309, loss_rpn_bbox: 0.0384, loss_cls: 0.1893, acc: 93.1989, loss_bbox: 0.2355, loss_mask: 0.2383, loss: 0.7324 2023-11-16 20:05:41,570 - mmdet - INFO - Epoch [7][1400/1833] lr: 5.563e-06, eta: 12:56:38, time: 0.864, data_time: 0.036, memory: 10345, loss_rpn_cls: 0.0298, loss_rpn_bbox: 0.0380, loss_cls: 0.1909, acc: 93.1656, loss_bbox: 0.2364, loss_mask: 0.2363, loss: 0.7314 2023-11-16 20:06:25,320 - mmdet - INFO - Epoch [7][1450/1833] lr: 5.563e-06, eta: 12:55:56, time: 0.875, data_time: 0.034, memory: 10345, loss_rpn_cls: 0.0310, loss_rpn_bbox: 0.0388, loss_cls: 0.1902, acc: 93.1144, loss_bbox: 0.2394, loss_mask: 0.2405, loss: 0.7399 2023-11-16 20:07:09,127 - mmdet - INFO - Epoch [7][1500/1833] lr: 5.563e-06, eta: 12:55:14, time: 0.876, data_time: 0.035, memory: 10345, loss_rpn_cls: 0.0302, loss_rpn_bbox: 0.0380, loss_cls: 0.1895, acc: 93.1725, loss_bbox: 0.2401, loss_mask: 0.2394, loss: 0.7372 2023-11-16 20:07:53,065 - mmdet - INFO - Epoch [7][1550/1833] lr: 5.563e-06, eta: 12:54:33, time: 0.879, data_time: 0.037, memory: 10345, loss_rpn_cls: 0.0302, loss_rpn_bbox: 0.0387, loss_cls: 0.1909, acc: 93.1068, loss_bbox: 0.2392, loss_mask: 0.2375, loss: 0.7365 2023-11-16 20:08:37,521 - mmdet - INFO - Epoch [7][1600/1833] lr: 5.563e-06, eta: 12:53:53, time: 0.889, data_time: 0.033, memory: 10345, loss_rpn_cls: 0.0291, loss_rpn_bbox: 0.0375, loss_cls: 0.1880, acc: 93.1796, loss_bbox: 0.2380, loss_mask: 0.2375, loss: 0.7301 2023-11-16 20:09:21,408 - mmdet - INFO - Epoch [7][1650/1833] lr: 5.563e-06, eta: 12:53:11, time: 0.878, data_time: 0.034, memory: 10345, loss_rpn_cls: 0.0312, loss_rpn_bbox: 0.0394, loss_cls: 0.1905, acc: 93.1113, loss_bbox: 0.2430, loss_mask: 0.2391, loss: 0.7431 2023-11-16 20:10:04,902 - mmdet - INFO - Epoch [7][1700/1833] lr: 5.563e-06, eta: 12:52:28, time: 0.870, data_time: 0.034, memory: 10345, loss_rpn_cls: 0.0302, loss_rpn_bbox: 0.0379, loss_cls: 0.1868, acc: 93.2294, loss_bbox: 0.2375, loss_mask: 0.2358, loss: 0.7283 2023-11-16 20:10:48,745 - mmdet - INFO - Epoch [7][1750/1833] lr: 5.563e-06, eta: 12:51:46, time: 0.877, data_time: 0.037, memory: 10345, loss_rpn_cls: 0.0297, loss_rpn_bbox: 0.0383, loss_cls: 0.1909, acc: 93.0600, loss_bbox: 0.2401, loss_mask: 0.2380, loss: 0.7370 2023-11-16 20:11:32,815 - mmdet - INFO - Epoch [7][1800/1833] lr: 5.563e-06, eta: 12:51:05, time: 0.881, data_time: 0.034, memory: 10345, loss_rpn_cls: 0.0297, loss_rpn_bbox: 0.0387, loss_cls: 0.1950, acc: 92.9784, loss_bbox: 0.2425, loss_mask: 0.2378, loss: 0.7438 2023-11-16 20:12:02,237 - mmdet - INFO - Saving checkpoint at 7 epochs 2023-11-16 20:12:36,177 - mmdet - INFO - Evaluating bbox... 2023-11-16 20:13:10,927 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.456 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.694 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.503 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.323 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.495 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.597 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.585 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.585 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.585 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.431 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.630 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.727 2023-11-16 20:13:10,930 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.559 | bicycle | 0.364 | car | 0.466 | | motorcycle | 0.461 | airplane | 0.656 | bus | 0.659 | | train | 0.677 | truck | 0.411 | boat | 0.318 | | traffic light | 0.295 | fire hydrant | 0.706 | stop sign | 0.654 | | parking meter | 0.493 | bench | 0.276 | bird | 0.388 | | cat | 0.701 | dog | 0.676 | horse | 0.622 | | sheep | 0.572 | cow | 0.613 | elephant | 0.665 | | bear | 0.746 | zebra | 0.660 | giraffe | 0.657 | | backpack | 0.200 | umbrella | 0.435 | handbag | 0.213 | | tie | 0.355 | suitcase | 0.450 | frisbee | 0.691 | | skis | 0.265 | snowboard | 0.373 | sports ball | 0.468 | | kite | 0.448 | baseball bat | 0.373 | baseball glove | 0.400 | | skateboard | 0.559 | surfboard | 0.439 | tennis racket | 0.491 | | bottle | 0.448 | wine glass | 0.393 | cup | 0.491 | | fork | 0.398 | knife | 0.251 | spoon | 0.244 | | bowl | 0.464 | banana | 0.265 | apple | 0.257 | | sandwich | 0.426 | orange | 0.334 | broccoli | 0.274 | | carrot | 0.250 | hot dog | 0.392 | pizza | 0.508 | | donut | 0.517 | cake | 0.420 | chair | 0.338 | | couch | 0.426 | potted plant | 0.311 | bed | 0.463 | | dining table | 0.285 | toilet | 0.642 | tv | 0.595 | | laptop | 0.640 | mouse | 0.629 | remote | 0.386 | | keyboard | 0.505 | cell phone | 0.416 | microwave | 0.654 | | oven | 0.372 | toaster | 0.458 | sink | 0.438 | | refrigerator | 0.628 | book | 0.182 | clock | 0.544 | | vase | 0.426 | scissors | 0.360 | teddy bear | 0.501 | | hair drier | 0.184 | toothbrush | 0.303 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-16 20:13:10,930 - mmdet - INFO - Evaluating segm... 2023-11-16 20:13:49,055 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.418 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.662 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.449 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.236 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.456 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.609 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.541 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.541 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.541 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.366 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.590 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.700 2023-11-16 20:13:49,058 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.487 | bicycle | 0.228 | car | 0.429 | | motorcycle | 0.383 | airplane | 0.511 | bus | 0.660 | | train | 0.672 | truck | 0.419 | boat | 0.300 | | traffic light | 0.287 | fire hydrant | 0.683 | stop sign | 0.653 | | parking meter | 0.509 | bench | 0.220 | bird | 0.332 | | cat | 0.720 | dog | 0.649 | horse | 0.466 | | sheep | 0.511 | cow | 0.527 | elephant | 0.615 | | bear | 0.743 | zebra | 0.590 | giraffe | 0.525 | | backpack | 0.209 | umbrella | 0.506 | handbag | 0.210 | | tie | 0.328 | suitcase | 0.482 | frisbee | 0.657 | | skis | 0.041 | snowboard | 0.248 | sports ball | 0.455 | | kite | 0.320 | baseball bat | 0.279 | baseball glove | 0.434 | | skateboard | 0.341 | surfboard | 0.368 | tennis racket | 0.575 | | bottle | 0.431 | wine glass | 0.339 | cup | 0.498 | | fork | 0.222 | knife | 0.175 | spoon | 0.187 | | bowl | 0.447 | banana | 0.219 | apple | 0.253 | | sandwich | 0.458 | orange | 0.343 | broccoli | 0.252 | | carrot | 0.221 | hot dog | 0.325 | pizza | 0.514 | | donut | 0.545 | cake | 0.448 | chair | 0.248 | | couch | 0.365 | potted plant | 0.260 | bed | 0.366 | | dining table | 0.157 | toilet | 0.627 | tv | 0.638 | | laptop | 0.660 | mouse | 0.616 | remote | 0.353 | | keyboard | 0.523 | cell phone | 0.394 | microwave | 0.681 | | oven | 0.364 | toaster | 0.453 | sink | 0.414 | | refrigerator | 0.642 | book | 0.136 | clock | 0.551 | | vase | 0.426 | scissors | 0.291 | teddy bear | 0.483 | | hair drier | 0.137 | toothbrush | 0.205 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-16 20:13:49,573 - mmdet - INFO - The previous best checkpoint /mnt/petrelfs/lizhiqi/DINO/detection/work_dirs/mask_rcnn_flash_internimage_b_fpn_3x_cocoo_0.4_0.9_4x16/best_bbox_mAP_epoch_6.pth was removed 2023-11-16 20:13:53,246 - mmdet - INFO - Now best checkpoint is saved as best_bbox_mAP_epoch_7.pth. 2023-11-16 20:13:53,246 - mmdet - INFO - Best bbox_mAP is 0.4559 at 7 epoch. 2023-11-16 20:13:53,247 - mmdet - INFO - Exp name: mask_rcnn_flash_internimage_b_fpn_3x_coco_0.4_0.9-4x16.py 2023-11-16 20:13:53,247 - mmdet - INFO - Epoch(val) [7][313] bbox_mAP: 0.4559, bbox_mAP_50: 0.6943, bbox_mAP_75: 0.5032, bbox_mAP_s: 0.3233, bbox_mAP_m: 0.4955, bbox_mAP_l: 0.5972, bbox_mAP_copypaste: 0.4559 0.6943 0.5032 0.3233 0.4955 0.5972, segm_mAP: 0.4180, segm_mAP_50: 0.6624, segm_mAP_75: 0.4487, segm_mAP_s: 0.2360, segm_mAP_m: 0.4561, segm_mAP_l: 0.6091, segm_mAP_copypaste: 0.4180 0.6624 0.4487 0.2360 0.4561 0.6091 2023-11-16 20:14:40,518 - mmdet - INFO - Epoch [8][50/1833] lr: 5.563e-06, eta: 12:48:10, time: 0.945, data_time: 0.098, memory: 10345, loss_rpn_cls: 0.0296, loss_rpn_bbox: 0.0387, loss_cls: 0.1861, acc: 93.1967, loss_bbox: 0.2385, loss_mask: 0.2372, loss: 0.7301 2023-11-16 20:15:23,951 - mmdet - INFO - Epoch [8][100/1833] lr: 5.563e-06, eta: 12:47:26, time: 0.869, data_time: 0.036, memory: 10345, loss_rpn_cls: 0.0307, loss_rpn_bbox: 0.0400, loss_cls: 0.1907, acc: 93.0554, loss_bbox: 0.2428, loss_mask: 0.2357, loss: 0.7400 2023-11-16 20:16:07,925 - mmdet - INFO - Epoch [8][150/1833] lr: 5.563e-06, eta: 12:46:45, time: 0.879, data_time: 0.034, memory: 10345, loss_rpn_cls: 0.0301, loss_rpn_bbox: 0.0385, loss_cls: 0.1888, acc: 93.1351, loss_bbox: 0.2398, loss_mask: 0.2350, loss: 0.7322 2023-11-16 20:16:51,867 - mmdet - INFO - Epoch [8][200/1833] lr: 5.563e-06, eta: 12:46:04, time: 0.879, data_time: 0.036, memory: 10345, loss_rpn_cls: 0.0280, loss_rpn_bbox: 0.0370, loss_cls: 0.1851, acc: 93.2865, loss_bbox: 0.2325, loss_mask: 0.2334, loss: 0.7161 2023-11-16 20:17:35,710 - mmdet - INFO - Epoch [8][250/1833] lr: 5.563e-06, eta: 12:45:23, time: 0.877, data_time: 0.033, memory: 10345, loss_rpn_cls: 0.0285, loss_rpn_bbox: 0.0370, loss_cls: 0.1848, acc: 93.3337, loss_bbox: 0.2325, loss_mask: 0.2369, loss: 0.7198 2023-11-16 20:18:19,570 - mmdet - INFO - Epoch [8][300/1833] lr: 5.563e-06, eta: 12:44:41, time: 0.877, data_time: 0.031, memory: 10345, loss_rpn_cls: 0.0291, loss_rpn_bbox: 0.0368, loss_cls: 0.1893, acc: 93.2125, loss_bbox: 0.2374, loss_mask: 0.2373, loss: 0.7298 2023-11-16 20:19:03,751 - mmdet - INFO - Epoch [8][350/1833] lr: 5.563e-06, eta: 12:44:01, time: 0.884, data_time: 0.035, memory: 10345, loss_rpn_cls: 0.0297, loss_rpn_bbox: 0.0393, loss_cls: 0.1865, acc: 93.2129, loss_bbox: 0.2384, loss_mask: 0.2389, loss: 0.7328 2023-11-16 20:19:47,343 - mmdet - INFO - Epoch [8][400/1833] lr: 5.563e-06, eta: 12:43:18, time: 0.872, data_time: 0.040, memory: 10345, loss_rpn_cls: 0.0288, loss_rpn_bbox: 0.0387, loss_cls: 0.1894, acc: 93.0787, loss_bbox: 0.2407, loss_mask: 0.2348, loss: 0.7324 2023-11-16 20:20:31,435 - mmdet - INFO - Epoch [8][450/1833] lr: 5.563e-06, eta: 12:42:37, time: 0.882, data_time: 0.034, memory: 10345, loss_rpn_cls: 0.0293, loss_rpn_bbox: 0.0372, loss_cls: 0.1828, acc: 93.3436, loss_bbox: 0.2319, loss_mask: 0.2334, loss: 0.7146 2023-11-16 20:21:15,295 - mmdet - INFO - Epoch [8][500/1833] lr: 5.563e-06, eta: 12:41:56, time: 0.877, data_time: 0.036, memory: 10345, loss_rpn_cls: 0.0290, loss_rpn_bbox: 0.0382, loss_cls: 0.1879, acc: 93.1911, loss_bbox: 0.2373, loss_mask: 0.2353, loss: 0.7277 2023-11-16 20:21:59,095 - mmdet - INFO - Epoch [8][550/1833] lr: 5.563e-06, eta: 12:41:14, time: 0.876, data_time: 0.035, memory: 10345, loss_rpn_cls: 0.0301, loss_rpn_bbox: 0.0381, loss_cls: 0.1862, acc: 93.2860, loss_bbox: 0.2356, loss_mask: 0.2355, loss: 0.7255 2023-11-16 20:22:43,359 - mmdet - INFO - Epoch [8][600/1833] lr: 5.563e-06, eta: 12:40:34, time: 0.885, data_time: 0.036, memory: 10345, loss_rpn_cls: 0.0286, loss_rpn_bbox: 0.0370, loss_cls: 0.1847, acc: 93.3029, loss_bbox: 0.2340, loss_mask: 0.2349, loss: 0.7193 2023-11-16 20:23:27,417 - mmdet - INFO - Epoch [8][650/1833] lr: 5.563e-06, eta: 12:39:53, time: 0.881, data_time: 0.039, memory: 10345, loss_rpn_cls: 0.0295, loss_rpn_bbox: 0.0364, loss_cls: 0.1840, acc: 93.3633, loss_bbox: 0.2313, loss_mask: 0.2333, loss: 0.7146 2023-11-16 20:24:11,093 - mmdet - INFO - Epoch [8][700/1833] lr: 5.563e-06, eta: 12:39:11, time: 0.873, data_time: 0.034, memory: 10345, loss_rpn_cls: 0.0303, loss_rpn_bbox: 0.0390, loss_cls: 0.1869, acc: 93.2350, loss_bbox: 0.2362, loss_mask: 0.2398, loss: 0.7322 2023-11-16 20:24:54,786 - mmdet - INFO - Epoch [8][750/1833] lr: 5.563e-06, eta: 12:38:28, time: 0.874, data_time: 0.032, memory: 10345, loss_rpn_cls: 0.0291, loss_rpn_bbox: 0.0381, loss_cls: 0.1859, acc: 93.2708, loss_bbox: 0.2362, loss_mask: 0.2384, loss: 0.7278 2023-11-16 20:25:38,087 - mmdet - INFO - Epoch [8][800/1833] lr: 5.563e-06, eta: 12:37:44, time: 0.866, data_time: 0.034, memory: 10345, loss_rpn_cls: 0.0301, loss_rpn_bbox: 0.0379, loss_cls: 0.1849, acc: 93.3208, loss_bbox: 0.2325, loss_mask: 0.2351, loss: 0.7205 2023-11-16 20:26:21,882 - mmdet - INFO - Epoch [8][850/1833] lr: 5.563e-06, eta: 12:37:02, time: 0.876, data_time: 0.036, memory: 10345, loss_rpn_cls: 0.0298, loss_rpn_bbox: 0.0378, loss_cls: 0.1832, acc: 93.3809, loss_bbox: 0.2341, loss_mask: 0.2347, loss: 0.7196 2023-11-16 20:27:05,291 - mmdet - INFO - Epoch [8][900/1833] lr: 5.563e-06, eta: 12:36:19, time: 0.868, data_time: 0.042, memory: 10345, loss_rpn_cls: 0.0313, loss_rpn_bbox: 0.0389, loss_cls: 0.1949, acc: 92.9846, loss_bbox: 0.2441, loss_mask: 0.2376, loss: 0.7468 2023-11-16 20:27:49,181 - mmdet - INFO - Epoch [8][950/1833] lr: 5.563e-06, eta: 12:35:37, time: 0.878, data_time: 0.034, memory: 10345, loss_rpn_cls: 0.0296, loss_rpn_bbox: 0.0372, loss_cls: 0.1876, acc: 93.2046, loss_bbox: 0.2384, loss_mask: 0.2363, loss: 0.7290 2023-11-16 20:28:32,647 - mmdet - INFO - Epoch [8][1000/1833] lr: 5.563e-06, eta: 12:34:54, time: 0.870, data_time: 0.034, memory: 10345, loss_rpn_cls: 0.0293, loss_rpn_bbox: 0.0372, loss_cls: 0.1848, acc: 93.2906, loss_bbox: 0.2352, loss_mask: 0.2370, loss: 0.7236 2023-11-16 20:29:16,197 - mmdet - INFO - Epoch [8][1050/1833] lr: 5.563e-06, eta: 12:34:11, time: 0.871, data_time: 0.038, memory: 10345, loss_rpn_cls: 0.0289, loss_rpn_bbox: 0.0388, loss_cls: 0.1869, acc: 93.2307, loss_bbox: 0.2369, loss_mask: 0.2369, loss: 0.7283 2023-11-16 20:30:00,128 - mmdet - INFO - Epoch [8][1100/1833] lr: 5.563e-06, eta: 12:33:30, time: 0.879, data_time: 0.037, memory: 10345, loss_rpn_cls: 0.0295, loss_rpn_bbox: 0.0379, loss_cls: 0.1842, acc: 93.3932, loss_bbox: 0.2342, loss_mask: 0.2333, loss: 0.7191 2023-11-16 20:30:44,272 - mmdet - INFO - Epoch [8][1150/1833] lr: 5.563e-06, eta: 12:32:49, time: 0.883, data_time: 0.033, memory: 10345, loss_rpn_cls: 0.0299, loss_rpn_bbox: 0.0376, loss_cls: 0.1846, acc: 93.3275, loss_bbox: 0.2346, loss_mask: 0.2326, loss: 0.7192 2023-11-16 20:31:28,388 - mmdet - INFO - Epoch [8][1200/1833] lr: 5.563e-06, eta: 12:32:08, time: 0.882, data_time: 0.035, memory: 10345, loss_rpn_cls: 0.0292, loss_rpn_bbox: 0.0367, loss_cls: 0.1832, acc: 93.4005, loss_bbox: 0.2305, loss_mask: 0.2305, loss: 0.7101 2023-11-16 20:32:12,197 - mmdet - INFO - Epoch [8][1250/1833] lr: 5.563e-06, eta: 12:31:26, time: 0.876, data_time: 0.031, memory: 10345, loss_rpn_cls: 0.0301, loss_rpn_bbox: 0.0389, loss_cls: 0.1864, acc: 93.2628, loss_bbox: 0.2355, loss_mask: 0.2408, loss: 0.7317 2023-11-16 20:32:55,910 - mmdet - INFO - Epoch [8][1300/1833] lr: 5.563e-06, eta: 12:30:43, time: 0.875, data_time: 0.038, memory: 10345, loss_rpn_cls: 0.0289, loss_rpn_bbox: 0.0382, loss_cls: 0.1858, acc: 93.2551, loss_bbox: 0.2364, loss_mask: 0.2346, loss: 0.7239 2023-11-16 20:33:39,797 - mmdet - INFO - Epoch [8][1350/1833] lr: 5.563e-06, eta: 12:30:02, time: 0.878, data_time: 0.039, memory: 10345, loss_rpn_cls: 0.0292, loss_rpn_bbox: 0.0375, loss_cls: 0.1881, acc: 93.1418, loss_bbox: 0.2379, loss_mask: 0.2351, loss: 0.7279 2023-11-16 20:34:23,459 - mmdet - INFO - Epoch [8][1400/1833] lr: 5.563e-06, eta: 12:29:19, time: 0.873, data_time: 0.039, memory: 10345, loss_rpn_cls: 0.0292, loss_rpn_bbox: 0.0386, loss_cls: 0.1895, acc: 93.1463, loss_bbox: 0.2362, loss_mask: 0.2373, loss: 0.7308 2023-11-16 20:35:07,813 - mmdet - INFO - Epoch [8][1450/1833] lr: 5.563e-06, eta: 12:28:39, time: 0.886, data_time: 0.032, memory: 10345, loss_rpn_cls: 0.0282, loss_rpn_bbox: 0.0364, loss_cls: 0.1817, acc: 93.4496, loss_bbox: 0.2312, loss_mask: 0.2340, loss: 0.7114 2023-11-16 20:35:51,263 - mmdet - INFO - Epoch [8][1500/1833] lr: 5.563e-06, eta: 12:27:56, time: 0.870, data_time: 0.036, memory: 10345, loss_rpn_cls: 0.0291, loss_rpn_bbox: 0.0372, loss_cls: 0.1819, acc: 93.4061, loss_bbox: 0.2307, loss_mask: 0.2372, loss: 0.7162 2023-11-16 20:36:35,352 - mmdet - INFO - Epoch [8][1550/1833] lr: 5.563e-06, eta: 12:27:15, time: 0.882, data_time: 0.035, memory: 10345, loss_rpn_cls: 0.0291, loss_rpn_bbox: 0.0380, loss_cls: 0.1822, acc: 93.3569, loss_bbox: 0.2320, loss_mask: 0.2328, loss: 0.7142 2023-11-16 20:37:19,283 - mmdet - INFO - Epoch [8][1600/1833] lr: 5.563e-06, eta: 12:26:33, time: 0.878, data_time: 0.034, memory: 10345, loss_rpn_cls: 0.0299, loss_rpn_bbox: 0.0381, loss_cls: 0.1913, acc: 93.1199, loss_bbox: 0.2406, loss_mask: 0.2373, loss: 0.7373 2023-11-16 20:38:02,814 - mmdet - INFO - Epoch [8][1650/1833] lr: 5.563e-06, eta: 12:25:50, time: 0.871, data_time: 0.038, memory: 10345, loss_rpn_cls: 0.0302, loss_rpn_bbox: 0.0376, loss_cls: 0.1865, acc: 93.2404, loss_bbox: 0.2330, loss_mask: 0.2328, loss: 0.7200 2023-11-16 20:38:46,408 - mmdet - INFO - Epoch [8][1700/1833] lr: 5.563e-06, eta: 12:25:07, time: 0.872, data_time: 0.034, memory: 10345, loss_rpn_cls: 0.0298, loss_rpn_bbox: 0.0377, loss_cls: 0.1822, acc: 93.3396, loss_bbox: 0.2335, loss_mask: 0.2343, loss: 0.7175 2023-11-16 20:39:30,158 - mmdet - INFO - Epoch [8][1750/1833] lr: 5.563e-06, eta: 12:24:24, time: 0.875, data_time: 0.036, memory: 10345, loss_rpn_cls: 0.0299, loss_rpn_bbox: 0.0379, loss_cls: 0.1897, acc: 93.2096, loss_bbox: 0.2353, loss_mask: 0.2352, loss: 0.7279 2023-11-16 20:40:14,815 - mmdet - INFO - Epoch [8][1800/1833] lr: 5.563e-06, eta: 12:23:45, time: 0.893, data_time: 0.033, memory: 10345, loss_rpn_cls: 0.0293, loss_rpn_bbox: 0.0383, loss_cls: 0.1886, acc: 93.1235, loss_bbox: 0.2388, loss_mask: 0.2346, loss: 0.7296 2023-11-16 20:40:44,167 - mmdet - INFO - Saving checkpoint at 8 epochs 2023-11-16 20:41:17,106 - mmdet - INFO - Evaluating bbox... 2023-11-16 20:41:52,035 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.464 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.700 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.509 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.327 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.505 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.601 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.594 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.594 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.594 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.448 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.634 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.733 2023-11-16 20:41:52,038 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.557 | bicycle | 0.359 | car | 0.465 | | motorcycle | 0.468 | airplane | 0.670 | bus | 0.666 | | train | 0.661 | truck | 0.407 | boat | 0.322 | | traffic light | 0.295 | fire hydrant | 0.681 | stop sign | 0.625 | | parking meter | 0.503 | bench | 0.281 | bird | 0.406 | | cat | 0.727 | dog | 0.686 | horse | 0.619 | | sheep | 0.572 | cow | 0.618 | elephant | 0.681 | | bear | 0.749 | zebra | 0.671 | giraffe | 0.661 | | backpack | 0.214 | umbrella | 0.448 | handbag | 0.230 | | tie | 0.356 | suitcase | 0.479 | frisbee | 0.703 | | skis | 0.284 | snowboard | 0.441 | sports ball | 0.469 | | kite | 0.467 | baseball bat | 0.412 | baseball glove | 0.426 | | skateboard | 0.561 | surfboard | 0.449 | tennis racket | 0.511 | | bottle | 0.446 | wine glass | 0.399 | cup | 0.498 | | fork | 0.414 | knife | 0.276 | spoon | 0.255 | | bowl | 0.474 | banana | 0.280 | apple | 0.256 | | sandwich | 0.450 | orange | 0.336 | broccoli | 0.263 | | carrot | 0.254 | hot dog | 0.394 | pizza | 0.550 | | donut | 0.530 | cake | 0.435 | chair | 0.341 | | couch | 0.452 | potted plant | 0.314 | bed | 0.450 | | dining table | 0.307 | toilet | 0.633 | tv | 0.621 | | laptop | 0.651 | mouse | 0.626 | remote | 0.386 | | keyboard | 0.500 | cell phone | 0.428 | microwave | 0.656 | | oven | 0.384 | toaster | 0.457 | sink | 0.437 | | refrigerator | 0.633 | book | 0.186 | clock | 0.546 | | vase | 0.400 | scissors | 0.385 | teddy bear | 0.515 | | hair drier | 0.163 | toothbrush | 0.296 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-16 20:41:52,038 - mmdet - INFO - Evaluating segm... 2023-11-16 20:42:28,283 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.421 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.667 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.452 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.242 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.457 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.611 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.544 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.544 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.544 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.380 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.588 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.705 2023-11-16 20:42:28,286 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.487 | bicycle | 0.225 | car | 0.429 | | motorcycle | 0.377 | airplane | 0.508 | bus | 0.665 | | train | 0.669 | truck | 0.420 | boat | 0.286 | | traffic light | 0.288 | fire hydrant | 0.681 | stop sign | 0.630 | | parking meter | 0.514 | bench | 0.215 | bird | 0.333 | | cat | 0.723 | dog | 0.650 | horse | 0.461 | | sheep | 0.508 | cow | 0.539 | elephant | 0.617 | | bear | 0.745 | zebra | 0.580 | giraffe | 0.517 | | backpack | 0.212 | umbrella | 0.501 | handbag | 0.219 | | tie | 0.328 | suitcase | 0.497 | frisbee | 0.642 | | skis | 0.038 | snowboard | 0.271 | sports ball | 0.452 | | kite | 0.317 | baseball bat | 0.285 | baseball glove | 0.461 | | skateboard | 0.337 | surfboard | 0.369 | tennis racket | 0.572 | | bottle | 0.433 | wine glass | 0.345 | cup | 0.498 | | fork | 0.204 | knife | 0.183 | spoon | 0.180 | | bowl | 0.450 | banana | 0.224 | apple | 0.255 | | sandwich | 0.480 | orange | 0.345 | broccoli | 0.254 | | carrot | 0.218 | hot dog | 0.305 | pizza | 0.526 | | donut | 0.549 | cake | 0.459 | chair | 0.245 | | couch | 0.388 | potted plant | 0.273 | bed | 0.375 | | dining table | 0.186 | toilet | 0.628 | tv | 0.657 | | laptop | 0.663 | mouse | 0.623 | remote | 0.348 | | keyboard | 0.514 | cell phone | 0.421 | microwave | 0.669 | | oven | 0.372 | toaster | 0.478 | sink | 0.424 | | refrigerator | 0.653 | book | 0.140 | clock | 0.554 | | vase | 0.412 | scissors | 0.286 | teddy bear | 0.485 | | hair drier | 0.162 | toothbrush | 0.214 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-16 20:42:28,837 - mmdet - INFO - The previous best checkpoint /mnt/petrelfs/lizhiqi/DINO/detection/work_dirs/mask_rcnn_flash_internimage_b_fpn_3x_cocoo_0.4_0.9_4x16/best_bbox_mAP_epoch_7.pth was removed 2023-11-16 20:42:32,591 - mmdet - INFO - Now best checkpoint is saved as best_bbox_mAP_epoch_8.pth. 2023-11-16 20:42:32,591 - mmdet - INFO - Best bbox_mAP is 0.4635 at 8 epoch. 2023-11-16 20:42:32,592 - mmdet - INFO - Exp name: mask_rcnn_flash_internimage_b_fpn_3x_coco_0.4_0.9-4x16.py 2023-11-16 20:42:32,592 - mmdet - INFO - Epoch(val) [8][313] bbox_mAP: 0.4635, bbox_mAP_50: 0.7002, bbox_mAP_75: 0.5091, bbox_mAP_s: 0.3267, bbox_mAP_m: 0.5053, bbox_mAP_l: 0.6006, bbox_mAP_copypaste: 0.4635 0.7002 0.5091 0.3267 0.5053 0.6006, segm_mAP: 0.4206, segm_mAP_50: 0.6665, segm_mAP_75: 0.4516, segm_mAP_s: 0.2425, segm_mAP_m: 0.4569, segm_mAP_l: 0.6106, segm_mAP_copypaste: 0.4206 0.6665 0.4516 0.2425 0.4569 0.6106 2023-11-16 20:43:19,200 - mmdet - INFO - Epoch [9][50/1833] lr: 5.563e-06, eta: 12:21:04, time: 0.932, data_time: 0.094, memory: 10345, loss_rpn_cls: 0.0281, loss_rpn_bbox: 0.0371, loss_cls: 0.1817, acc: 93.4299, loss_bbox: 0.2306, loss_mask: 0.2302, loss: 0.7078 2023-11-16 20:44:02,879 - mmdet - INFO - Epoch [9][100/1833] lr: 5.563e-06, eta: 12:20:22, time: 0.874, data_time: 0.034, memory: 10345, loss_rpn_cls: 0.0288, loss_rpn_bbox: 0.0374, loss_cls: 0.1801, acc: 93.4396, loss_bbox: 0.2303, loss_mask: 0.2331, loss: 0.7098 2023-11-16 20:44:46,377 - mmdet - INFO - Epoch [9][150/1833] lr: 5.563e-06, eta: 12:19:39, time: 0.870, data_time: 0.037, memory: 10345, loss_rpn_cls: 0.0281, loss_rpn_bbox: 0.0371, loss_cls: 0.1796, acc: 93.4366, loss_bbox: 0.2304, loss_mask: 0.2310, loss: 0.7062 2023-11-16 20:45:32,616 - mmdet - INFO - Epoch [9][200/1833] lr: 5.563e-06, eta: 12:19:06, time: 0.925, data_time: 0.034, memory: 10345, loss_rpn_cls: 0.0295, loss_rpn_bbox: 0.0381, loss_cls: 0.1882, acc: 93.2255, loss_bbox: 0.2375, loss_mask: 0.2350, loss: 0.7284 2023-11-16 20:46:16,717 - mmdet - INFO - Epoch [9][250/1833] lr: 5.563e-06, eta: 12:18:25, time: 0.882, data_time: 0.034, memory: 10345, loss_rpn_cls: 0.0283, loss_rpn_bbox: 0.0377, loss_cls: 0.1837, acc: 93.2745, loss_bbox: 0.2358, loss_mask: 0.2323, loss: 0.7178 2023-11-16 20:47:00,850 - mmdet - INFO - Epoch [9][300/1833] lr: 5.563e-06, eta: 12:17:44, time: 0.882, data_time: 0.034, memory: 10345, loss_rpn_cls: 0.0286, loss_rpn_bbox: 0.0371, loss_cls: 0.1834, acc: 93.2842, loss_bbox: 0.2353, loss_mask: 0.2349, loss: 0.7194 2023-11-16 20:47:44,266 - mmdet - INFO - Epoch [9][350/1833] lr: 5.563e-06, eta: 12:17:01, time: 0.869, data_time: 0.038, memory: 10345, loss_rpn_cls: 0.0302, loss_rpn_bbox: 0.0375, loss_cls: 0.1804, acc: 93.4468, loss_bbox: 0.2278, loss_mask: 0.2335, loss: 0.7094 2023-11-16 20:48:28,481 - mmdet - INFO - Epoch [9][400/1833] lr: 5.563e-06, eta: 12:16:20, time: 0.884, data_time: 0.030, memory: 10345, loss_rpn_cls: 0.0281, loss_rpn_bbox: 0.0380, loss_cls: 0.1810, acc: 93.3878, loss_bbox: 0.2320, loss_mask: 0.2332, loss: 0.7122 2023-11-16 20:49:12,269 - mmdet - INFO - Epoch [9][450/1833] lr: 5.563e-06, eta: 12:15:38, time: 0.876, data_time: 0.037, memory: 10345, loss_rpn_cls: 0.0285, loss_rpn_bbox: 0.0381, loss_cls: 0.1791, acc: 93.4704, loss_bbox: 0.2321, loss_mask: 0.2326, loss: 0.7104 2023-11-16 20:49:55,696 - mmdet - INFO - Epoch [9][500/1833] lr: 5.563e-06, eta: 12:14:55, time: 0.869, data_time: 0.032, memory: 10345, loss_rpn_cls: 0.0283, loss_rpn_bbox: 0.0363, loss_cls: 0.1773, acc: 93.5590, loss_bbox: 0.2266, loss_mask: 0.2336, loss: 0.7021 2023-11-16 20:50:39,707 - mmdet - INFO - Epoch [9][550/1833] lr: 5.563e-06, eta: 12:14:14, time: 0.880, data_time: 0.032, memory: 10345, loss_rpn_cls: 0.0269, loss_rpn_bbox: 0.0366, loss_cls: 0.1800, acc: 93.4352, loss_bbox: 0.2303, loss_mask: 0.2303, loss: 0.7040 2023-11-16 20:51:24,003 - mmdet - INFO - Epoch [9][600/1833] lr: 5.563e-06, eta: 12:13:33, time: 0.886, data_time: 0.038, memory: 10345, loss_rpn_cls: 0.0299, loss_rpn_bbox: 0.0393, loss_cls: 0.1885, acc: 93.1505, loss_bbox: 0.2410, loss_mask: 0.2351, loss: 0.7336 2023-11-16 20:52:07,693 - mmdet - INFO - Epoch [9][650/1833] lr: 5.563e-06, eta: 12:12:51, time: 0.874, data_time: 0.032, memory: 10345, loss_rpn_cls: 0.0275, loss_rpn_bbox: 0.0366, loss_cls: 0.1777, acc: 93.5789, loss_bbox: 0.2288, loss_mask: 0.2328, loss: 0.7034 2023-11-16 20:52:51,920 - mmdet - INFO - Epoch [9][700/1833] lr: 5.563e-06, eta: 12:12:10, time: 0.885, data_time: 0.030, memory: 10345, loss_rpn_cls: 0.0305, loss_rpn_bbox: 0.0389, loss_cls: 0.1884, acc: 93.1790, loss_bbox: 0.2379, loss_mask: 0.2351, loss: 0.7307 2023-11-16 20:53:35,214 - mmdet - INFO - Epoch [9][750/1833] lr: 5.563e-06, eta: 12:11:27, time: 0.866, data_time: 0.030, memory: 10345, loss_rpn_cls: 0.0282, loss_rpn_bbox: 0.0366, loss_cls: 0.1794, acc: 93.5137, loss_bbox: 0.2286, loss_mask: 0.2292, loss: 0.7019 2023-11-16 20:54:19,085 - mmdet - INFO - Epoch [9][800/1833] lr: 5.563e-06, eta: 12:10:45, time: 0.877, data_time: 0.035, memory: 10345, loss_rpn_cls: 0.0292, loss_rpn_bbox: 0.0390, loss_cls: 0.1806, acc: 93.3707, loss_bbox: 0.2324, loss_mask: 0.2360, loss: 0.7172 2023-11-16 20:55:02,951 - mmdet - INFO - Epoch [9][850/1833] lr: 5.563e-06, eta: 12:10:03, time: 0.877, data_time: 0.037, memory: 10345, loss_rpn_cls: 0.0288, loss_rpn_bbox: 0.0378, loss_cls: 0.1808, acc: 93.4161, loss_bbox: 0.2329, loss_mask: 0.2330, loss: 0.7133 2023-11-16 20:55:46,690 - mmdet - INFO - Epoch [9][900/1833] lr: 5.563e-06, eta: 12:09:21, time: 0.875, data_time: 0.033, memory: 10345, loss_rpn_cls: 0.0283, loss_rpn_bbox: 0.0372, loss_cls: 0.1821, acc: 93.3934, loss_bbox: 0.2313, loss_mask: 0.2319, loss: 0.7107 2023-11-16 20:56:29,946 - mmdet - INFO - Epoch [9][950/1833] lr: 5.563e-06, eta: 12:08:37, time: 0.865, data_time: 0.030, memory: 10345, loss_rpn_cls: 0.0273, loss_rpn_bbox: 0.0363, loss_cls: 0.1795, acc: 93.4407, loss_bbox: 0.2269, loss_mask: 0.2297, loss: 0.6997 2023-11-16 20:57:13,726 - mmdet - INFO - Epoch [9][1000/1833] lr: 5.563e-06, eta: 12:07:55, time: 0.876, data_time: 0.034, memory: 10345, loss_rpn_cls: 0.0283, loss_rpn_bbox: 0.0365, loss_cls: 0.1780, acc: 93.5211, loss_bbox: 0.2270, loss_mask: 0.2321, loss: 0.7020 2023-11-16 20:57:57,429 - mmdet - INFO - Epoch [9][1050/1833] lr: 5.563e-06, eta: 12:07:12, time: 0.873, data_time: 0.033, memory: 10345, loss_rpn_cls: 0.0288, loss_rpn_bbox: 0.0372, loss_cls: 0.1828, acc: 93.3334, loss_bbox: 0.2332, loss_mask: 0.2341, loss: 0.7162 2023-11-16 20:58:41,560 - mmdet - INFO - Epoch [9][1100/1833] lr: 5.563e-06, eta: 12:06:31, time: 0.883, data_time: 0.035, memory: 10345, loss_rpn_cls: 0.0274, loss_rpn_bbox: 0.0365, loss_cls: 0.1793, acc: 93.5075, loss_bbox: 0.2306, loss_mask: 0.2309, loss: 0.7048 2023-11-16 20:59:26,069 - mmdet - INFO - Epoch [9][1150/1833] lr: 5.563e-06, eta: 12:05:51, time: 0.890, data_time: 0.030, memory: 10345, loss_rpn_cls: 0.0298, loss_rpn_bbox: 0.0387, loss_cls: 0.1848, acc: 93.3029, loss_bbox: 0.2334, loss_mask: 0.2306, loss: 0.7173 2023-11-16 21:00:09,784 - mmdet - INFO - Epoch [9][1200/1833] lr: 5.563e-06, eta: 12:05:09, time: 0.874, data_time: 0.032, memory: 10345, loss_rpn_cls: 0.0295, loss_rpn_bbox: 0.0387, loss_cls: 0.1840, acc: 93.2629, loss_bbox: 0.2360, loss_mask: 0.2330, loss: 0.7211 2023-11-16 21:00:53,491 - mmdet - INFO - Epoch [9][1250/1833] lr: 5.563e-06, eta: 12:04:26, time: 0.874, data_time: 0.031, memory: 10345, loss_rpn_cls: 0.0276, loss_rpn_bbox: 0.0373, loss_cls: 0.1823, acc: 93.4482, loss_bbox: 0.2293, loss_mask: 0.2326, loss: 0.7091 2023-11-16 21:01:37,538 - mmdet - INFO - Epoch [9][1300/1833] lr: 5.563e-06, eta: 12:03:45, time: 0.881, data_time: 0.036, memory: 10345, loss_rpn_cls: 0.0285, loss_rpn_bbox: 0.0369, loss_cls: 0.1844, acc: 93.3475, loss_bbox: 0.2328, loss_mask: 0.2330, loss: 0.7156 2023-11-16 21:02:21,447 - mmdet - INFO - Epoch [9][1350/1833] lr: 5.563e-06, eta: 12:03:03, time: 0.878, data_time: 0.032, memory: 10345, loss_rpn_cls: 0.0281, loss_rpn_bbox: 0.0369, loss_cls: 0.1844, acc: 93.3289, loss_bbox: 0.2353, loss_mask: 0.2316, loss: 0.7163 2023-11-16 21:03:04,651 - mmdet - INFO - Epoch [9][1400/1833] lr: 5.563e-06, eta: 12:02:19, time: 0.864, data_time: 0.032, memory: 10345, loss_rpn_cls: 0.0285, loss_rpn_bbox: 0.0374, loss_cls: 0.1795, acc: 93.5259, loss_bbox: 0.2284, loss_mask: 0.2333, loss: 0.7071 2023-11-16 21:03:48,423 - mmdet - INFO - Epoch [9][1450/1833] lr: 5.563e-06, eta: 12:01:37, time: 0.875, data_time: 0.033, memory: 10346, loss_rpn_cls: 0.0285, loss_rpn_bbox: 0.0385, loss_cls: 0.1890, acc: 93.0926, loss_bbox: 0.2403, loss_mask: 0.2387, loss: 0.7350 2023-11-16 21:04:32,371 - mmdet - INFO - Epoch [9][1500/1833] lr: 5.563e-06, eta: 12:00:55, time: 0.879, data_time: 0.034, memory: 10346, loss_rpn_cls: 0.0299, loss_rpn_bbox: 0.0388, loss_cls: 0.1889, acc: 93.1125, loss_bbox: 0.2377, loss_mask: 0.2363, loss: 0.7316 2023-11-16 21:05:16,419 - mmdet - INFO - Epoch [9][1550/1833] lr: 5.563e-06, eta: 12:00:14, time: 0.881, data_time: 0.034, memory: 10346, loss_rpn_cls: 0.0281, loss_rpn_bbox: 0.0364, loss_cls: 0.1784, acc: 93.4946, loss_bbox: 0.2295, loss_mask: 0.2300, loss: 0.7025 2023-11-16 21:05:59,753 - mmdet - INFO - Epoch [9][1600/1833] lr: 5.563e-06, eta: 11:59:30, time: 0.866, data_time: 0.037, memory: 10346, loss_rpn_cls: 0.0287, loss_rpn_bbox: 0.0363, loss_cls: 0.1821, acc: 93.4401, loss_bbox: 0.2296, loss_mask: 0.2331, loss: 0.7098 2023-11-16 21:06:43,568 - mmdet - INFO - Epoch [9][1650/1833] lr: 5.563e-06, eta: 11:58:48, time: 0.876, data_time: 0.037, memory: 10346, loss_rpn_cls: 0.0291, loss_rpn_bbox: 0.0375, loss_cls: 0.1824, acc: 93.3367, loss_bbox: 0.2339, loss_mask: 0.2351, loss: 0.7179 2023-11-16 21:07:27,483 - mmdet - INFO - Epoch [9][1700/1833] lr: 5.563e-06, eta: 11:58:06, time: 0.879, data_time: 0.035, memory: 10346, loss_rpn_cls: 0.0285, loss_rpn_bbox: 0.0367, loss_cls: 0.1809, acc: 93.4485, loss_bbox: 0.2281, loss_mask: 0.2313, loss: 0.7056 2023-11-16 21:08:11,554 - mmdet - INFO - Epoch [9][1750/1833] lr: 5.563e-06, eta: 11:57:25, time: 0.881, data_time: 0.035, memory: 10346, loss_rpn_cls: 0.0267, loss_rpn_bbox: 0.0364, loss_cls: 0.1806, acc: 93.4142, loss_bbox: 0.2284, loss_mask: 0.2298, loss: 0.7020 2023-11-16 21:08:54,965 - mmdet - INFO - Epoch [9][1800/1833] lr: 5.563e-06, eta: 11:56:41, time: 0.868, data_time: 0.036, memory: 10346, loss_rpn_cls: 0.0280, loss_rpn_bbox: 0.0376, loss_cls: 0.1848, acc: 93.3102, loss_bbox: 0.2338, loss_mask: 0.2340, loss: 0.7182 2023-11-16 21:09:24,233 - mmdet - INFO - Saving checkpoint at 9 epochs 2023-11-16 21:09:59,686 - mmdet - INFO - Evaluating bbox... 2023-11-16 21:10:32,788 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.466 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.702 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.518 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.331 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.507 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.597 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.600 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.600 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.600 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.457 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.640 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.734 2023-11-16 21:10:32,790 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.566 | bicycle | 0.364 | car | 0.475 | | motorcycle | 0.445 | airplane | 0.676 | bus | 0.676 | | train | 0.687 | truck | 0.436 | boat | 0.323 | | traffic light | 0.299 | fire hydrant | 0.695 | stop sign | 0.658 | | parking meter | 0.496 | bench | 0.281 | bird | 0.408 | | cat | 0.713 | dog | 0.676 | horse | 0.601 | | sheep | 0.572 | cow | 0.628 | elephant | 0.691 | | bear | 0.712 | zebra | 0.674 | giraffe | 0.674 | | backpack | 0.221 | umbrella | 0.452 | handbag | 0.226 | | tie | 0.361 | suitcase | 0.484 | frisbee | 0.692 | | skis | 0.273 | snowboard | 0.425 | sports ball | 0.488 | | kite | 0.458 | baseball bat | 0.401 | baseball glove | 0.437 | | skateboard | 0.534 | surfboard | 0.455 | tennis racket | 0.537 | | bottle | 0.451 | wine glass | 0.406 | cup | 0.497 | | fork | 0.410 | knife | 0.283 | spoon | 0.244 | | bowl | 0.468 | banana | 0.289 | apple | 0.267 | | sandwich | 0.394 | orange | 0.356 | broccoli | 0.271 | | carrot | 0.266 | hot dog | 0.450 | pizza | 0.543 | | donut | 0.537 | cake | 0.438 | chair | 0.341 | | couch | 0.460 | potted plant | 0.331 | bed | 0.475 | | dining table | 0.302 | toilet | 0.635 | tv | 0.615 | | laptop | 0.646 | mouse | 0.614 | remote | 0.395 | | keyboard | 0.532 | cell phone | 0.446 | microwave | 0.652 | | oven | 0.388 | toaster | 0.400 | sink | 0.426 | | refrigerator | 0.634 | book | 0.182 | clock | 0.556 | | vase | 0.417 | scissors | 0.397 | teddy bear | 0.508 | | hair drier | 0.188 | toothbrush | 0.269 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-16 21:10:32,791 - mmdet - INFO - Evaluating segm... 2023-11-16 21:11:11,780 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.426 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.670 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.459 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.246 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.466 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.609 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.552 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.552 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.552 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.386 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.598 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.706 2023-11-16 21:11:11,782 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.493 | bicycle | 0.218 | car | 0.431 | | motorcycle | 0.391 | airplane | 0.541 | bus | 0.671 | | train | 0.678 | truck | 0.437 | boat | 0.308 | | traffic light | 0.286 | fire hydrant | 0.696 | stop sign | 0.658 | | parking meter | 0.506 | bench | 0.223 | bird | 0.341 | | cat | 0.732 | dog | 0.654 | horse | 0.449 | | sheep | 0.514 | cow | 0.540 | elephant | 0.617 | | bear | 0.703 | zebra | 0.591 | giraffe | 0.534 | | backpack | 0.211 | umbrella | 0.515 | handbag | 0.223 | | tie | 0.338 | suitcase | 0.493 | frisbee | 0.646 | | skis | 0.042 | snowboard | 0.265 | sports ball | 0.461 | | kite | 0.319 | baseball bat | 0.306 | baseball glove | 0.468 | | skateboard | 0.341 | surfboard | 0.377 | tennis racket | 0.577 | | bottle | 0.431 | wine glass | 0.350 | cup | 0.500 | | fork | 0.227 | knife | 0.199 | spoon | 0.189 | | bowl | 0.443 | banana | 0.238 | apple | 0.269 | | sandwich | 0.433 | orange | 0.357 | broccoli | 0.254 | | carrot | 0.228 | hot dog | 0.382 | pizza | 0.532 | | donut | 0.561 | cake | 0.448 | chair | 0.243 | | couch | 0.395 | potted plant | 0.282 | bed | 0.373 | | dining table | 0.179 | toilet | 0.634 | tv | 0.649 | | laptop | 0.662 | mouse | 0.611 | remote | 0.360 | | keyboard | 0.532 | cell phone | 0.426 | microwave | 0.681 | | oven | 0.373 | toaster | 0.445 | sink | 0.409 | | refrigerator | 0.666 | book | 0.137 | clock | 0.550 | | vase | 0.423 | scissors | 0.310 | teddy bear | 0.491 | | hair drier | 0.166 | toothbrush | 0.209 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-16 21:11:12,319 - mmdet - INFO - The previous best checkpoint /mnt/petrelfs/lizhiqi/DINO/detection/work_dirs/mask_rcnn_flash_internimage_b_fpn_3x_cocoo_0.4_0.9_4x16/best_bbox_mAP_epoch_8.pth was removed 2023-11-16 21:11:16,067 - mmdet - INFO - Now best checkpoint is saved as best_bbox_mAP_epoch_9.pth. 2023-11-16 21:11:16,067 - mmdet - INFO - Best bbox_mAP is 0.4656 at 9 epoch. 2023-11-16 21:11:16,068 - mmdet - INFO - Exp name: mask_rcnn_flash_internimage_b_fpn_3x_coco_0.4_0.9-4x16.py 2023-11-16 21:11:16,068 - mmdet - INFO - Epoch(val) [9][313] bbox_mAP: 0.4656, bbox_mAP_50: 0.7024, bbox_mAP_75: 0.5182, bbox_mAP_s: 0.3314, bbox_mAP_m: 0.5075, bbox_mAP_l: 0.5967, bbox_mAP_copypaste: 0.4656 0.7024 0.5182 0.3314 0.5075 0.5967, segm_mAP: 0.4255, segm_mAP_50: 0.6705, segm_mAP_75: 0.4588, segm_mAP_s: 0.2460, segm_mAP_m: 0.4664, segm_mAP_l: 0.6095, segm_mAP_copypaste: 0.4255 0.6705 0.4588 0.2460 0.4664 0.6095 2023-11-16 21:12:03,094 - mmdet - INFO - Epoch [10][50/1833] lr: 5.563e-06, eta: 11:54:14, time: 0.940, data_time: 0.100, memory: 10346, loss_rpn_cls: 0.0282, loss_rpn_bbox: 0.0375, loss_cls: 0.1819, acc: 93.3597, loss_bbox: 0.2312, loss_mask: 0.2295, loss: 0.7082 2023-11-16 21:12:46,862 - mmdet - INFO - Epoch [10][100/1833] lr: 5.563e-06, eta: 11:53:32, time: 0.875, data_time: 0.039, memory: 10346, loss_rpn_cls: 0.0284, loss_rpn_bbox: 0.0383, loss_cls: 0.1806, acc: 93.3645, loss_bbox: 0.2314, loss_mask: 0.2314, loss: 0.7100 2023-11-16 21:13:31,342 - mmdet - INFO - Epoch [10][150/1833] lr: 5.563e-06, eta: 11:52:52, time: 0.890, data_time: 0.034, memory: 10346, loss_rpn_cls: 0.0255, loss_rpn_bbox: 0.0358, loss_cls: 0.1739, acc: 93.6459, loss_bbox: 0.2236, loss_mask: 0.2286, loss: 0.6874 2023-11-16 21:14:15,771 - mmdet - INFO - Epoch [10][200/1833] lr: 5.563e-06, eta: 11:52:12, time: 0.888, data_time: 0.041, memory: 10346, loss_rpn_cls: 0.0272, loss_rpn_bbox: 0.0363, loss_cls: 0.1780, acc: 93.5480, loss_bbox: 0.2266, loss_mask: 0.2321, loss: 0.7003 2023-11-16 21:15:00,048 - mmdet - INFO - Epoch [10][250/1833] lr: 5.563e-06, eta: 11:51:31, time: 0.886, data_time: 0.041, memory: 10346, loss_rpn_cls: 0.0269, loss_rpn_bbox: 0.0366, loss_cls: 0.1767, acc: 93.5807, loss_bbox: 0.2258, loss_mask: 0.2283, loss: 0.6944 2023-11-16 21:15:44,355 - mmdet - INFO - Epoch [10][300/1833] lr: 5.563e-06, eta: 11:50:51, time: 0.886, data_time: 0.036, memory: 10346, loss_rpn_cls: 0.0288, loss_rpn_bbox: 0.0364, loss_cls: 0.1775, acc: 93.5180, loss_bbox: 0.2292, loss_mask: 0.2317, loss: 0.7035 2023-11-16 21:16:28,458 - mmdet - INFO - Epoch [10][350/1833] lr: 5.563e-06, eta: 11:50:10, time: 0.882, data_time: 0.035, memory: 10346, loss_rpn_cls: 0.0272, loss_rpn_bbox: 0.0360, loss_cls: 0.1749, acc: 93.6175, loss_bbox: 0.2263, loss_mask: 0.2287, loss: 0.6930 2023-11-16 21:17:12,858 - mmdet - INFO - Epoch [10][400/1833] lr: 5.563e-06, eta: 11:49:29, time: 0.887, data_time: 0.040, memory: 10346, loss_rpn_cls: 0.0276, loss_rpn_bbox: 0.0366, loss_cls: 0.1811, acc: 93.3782, loss_bbox: 0.2335, loss_mask: 0.2341, loss: 0.7128 2023-11-16 21:17:56,684 - mmdet - INFO - Epoch [10][450/1833] lr: 5.563e-06, eta: 11:48:47, time: 0.877, data_time: 0.037, memory: 10346, loss_rpn_cls: 0.0291, loss_rpn_bbox: 0.0375, loss_cls: 0.1788, acc: 93.4625, loss_bbox: 0.2287, loss_mask: 0.2298, loss: 0.7040 2023-11-16 21:18:40,428 - mmdet - INFO - Epoch [10][500/1833] lr: 5.563e-06, eta: 11:48:05, time: 0.875, data_time: 0.042, memory: 10346, loss_rpn_cls: 0.0268, loss_rpn_bbox: 0.0379, loss_cls: 0.1795, acc: 93.4014, loss_bbox: 0.2311, loss_mask: 0.2335, loss: 0.7087 2023-11-16 21:19:25,015 - mmdet - INFO - Epoch [10][550/1833] lr: 5.563e-06, eta: 11:47:25, time: 0.892, data_time: 0.037, memory: 10346, loss_rpn_cls: 0.0305, loss_rpn_bbox: 0.0372, loss_cls: 0.1812, acc: 93.4397, loss_bbox: 0.2307, loss_mask: 0.2334, loss: 0.7131 2023-11-16 21:20:09,001 - mmdet - INFO - Epoch [10][600/1833] lr: 5.563e-06, eta: 11:46:44, time: 0.880, data_time: 0.039, memory: 10346, loss_rpn_cls: 0.0273, loss_rpn_bbox: 0.0366, loss_cls: 0.1770, acc: 93.5497, loss_bbox: 0.2256, loss_mask: 0.2298, loss: 0.6963 2023-11-16 21:20:53,139 - mmdet - INFO - Epoch [10][650/1833] lr: 5.563e-06, eta: 11:46:03, time: 0.883, data_time: 0.036, memory: 10346, loss_rpn_cls: 0.0276, loss_rpn_bbox: 0.0376, loss_cls: 0.1772, acc: 93.5491, loss_bbox: 0.2274, loss_mask: 0.2287, loss: 0.6986 2023-11-16 21:21:37,484 - mmdet - INFO - Epoch [10][700/1833] lr: 5.563e-06, eta: 11:45:22, time: 0.886, data_time: 0.036, memory: 10346, loss_rpn_cls: 0.0266, loss_rpn_bbox: 0.0366, loss_cls: 0.1791, acc: 93.4620, loss_bbox: 0.2283, loss_mask: 0.2301, loss: 0.7005 2023-11-16 21:22:21,752 - mmdet - INFO - Epoch [10][750/1833] lr: 5.563e-06, eta: 11:44:41, time: 0.886, data_time: 0.036, memory: 10346, loss_rpn_cls: 0.0270, loss_rpn_bbox: 0.0358, loss_cls: 0.1773, acc: 93.5229, loss_bbox: 0.2267, loss_mask: 0.2311, loss: 0.6979 2023-11-16 21:23:05,891 - mmdet - INFO - Epoch [10][800/1833] lr: 5.563e-06, eta: 11:44:00, time: 0.883, data_time: 0.035, memory: 10346, loss_rpn_cls: 0.0283, loss_rpn_bbox: 0.0372, loss_cls: 0.1779, acc: 93.4904, loss_bbox: 0.2302, loss_mask: 0.2345, loss: 0.7081 2023-11-16 21:23:49,971 - mmdet - INFO - Epoch [10][850/1833] lr: 5.563e-06, eta: 11:43:18, time: 0.882, data_time: 0.034, memory: 10346, loss_rpn_cls: 0.0281, loss_rpn_bbox: 0.0372, loss_cls: 0.1799, acc: 93.4359, loss_bbox: 0.2312, loss_mask: 0.2315, loss: 0.7081 2023-11-16 21:24:33,870 - mmdet - INFO - Epoch [10][900/1833] lr: 5.563e-06, eta: 11:42:37, time: 0.878, data_time: 0.037, memory: 10346, loss_rpn_cls: 0.0282, loss_rpn_bbox: 0.0364, loss_cls: 0.1793, acc: 93.4194, loss_bbox: 0.2307, loss_mask: 0.2302, loss: 0.7049 2023-11-16 21:25:18,254 - mmdet - INFO - Epoch [10][950/1833] lr: 5.563e-06, eta: 11:41:56, time: 0.888, data_time: 0.041, memory: 10346, loss_rpn_cls: 0.0288, loss_rpn_bbox: 0.0382, loss_cls: 0.1805, acc: 93.4360, loss_bbox: 0.2341, loss_mask: 0.2347, loss: 0.7163 2023-11-16 21:26:02,194 - mmdet - INFO - Epoch [10][1000/1833] lr: 5.563e-06, eta: 11:41:14, time: 0.879, data_time: 0.034, memory: 10346, loss_rpn_cls: 0.0285, loss_rpn_bbox: 0.0366, loss_cls: 0.1790, acc: 93.5203, loss_bbox: 0.2290, loss_mask: 0.2302, loss: 0.7032 2023-11-16 21:26:46,312 - mmdet - INFO - Epoch [10][1050/1833] lr: 5.563e-06, eta: 11:40:33, time: 0.882, data_time: 0.037, memory: 10346, loss_rpn_cls: 0.0270, loss_rpn_bbox: 0.0356, loss_cls: 0.1767, acc: 93.5801, loss_bbox: 0.2267, loss_mask: 0.2297, loss: 0.6956 2023-11-16 21:27:30,730 - mmdet - INFO - Epoch [10][1100/1833] lr: 5.563e-06, eta: 11:39:52, time: 0.888, data_time: 0.042, memory: 10346, loss_rpn_cls: 0.0291, loss_rpn_bbox: 0.0384, loss_cls: 0.1880, acc: 93.0837, loss_bbox: 0.2380, loss_mask: 0.2345, loss: 0.7280 2023-11-16 21:28:15,174 - mmdet - INFO - Epoch [10][1150/1833] lr: 5.563e-06, eta: 11:39:12, time: 0.889, data_time: 0.034, memory: 10346, loss_rpn_cls: 0.0281, loss_rpn_bbox: 0.0376, loss_cls: 0.1824, acc: 93.3065, loss_bbox: 0.2353, loss_mask: 0.2326, loss: 0.7159 2023-11-16 21:28:59,391 - mmdet - INFO - Epoch [10][1200/1833] lr: 5.563e-06, eta: 11:38:31, time: 0.884, data_time: 0.035, memory: 10346, loss_rpn_cls: 0.0275, loss_rpn_bbox: 0.0366, loss_cls: 0.1763, acc: 93.5944, loss_bbox: 0.2264, loss_mask: 0.2281, loss: 0.6949 2023-11-16 21:29:43,111 - mmdet - INFO - Epoch [10][1250/1833] lr: 5.563e-06, eta: 11:37:48, time: 0.874, data_time: 0.034, memory: 10346, loss_rpn_cls: 0.0284, loss_rpn_bbox: 0.0370, loss_cls: 0.1776, acc: 93.5098, loss_bbox: 0.2291, loss_mask: 0.2321, loss: 0.7042 2023-11-16 21:30:27,695 - mmdet - INFO - Epoch [10][1300/1833] lr: 5.563e-06, eta: 11:37:08, time: 0.892, data_time: 0.036, memory: 10346, loss_rpn_cls: 0.0268, loss_rpn_bbox: 0.0366, loss_cls: 0.1812, acc: 93.4129, loss_bbox: 0.2294, loss_mask: 0.2330, loss: 0.7069 2023-11-16 21:31:12,050 - mmdet - INFO - Epoch [10][1350/1833] lr: 5.563e-06, eta: 11:36:27, time: 0.887, data_time: 0.037, memory: 10346, loss_rpn_cls: 0.0277, loss_rpn_bbox: 0.0359, loss_cls: 0.1768, acc: 93.6138, loss_bbox: 0.2253, loss_mask: 0.2317, loss: 0.6973 2023-11-16 21:31:56,002 - mmdet - INFO - Epoch [10][1400/1833] lr: 5.563e-06, eta: 11:35:45, time: 0.879, data_time: 0.034, memory: 10346, loss_rpn_cls: 0.0285, loss_rpn_bbox: 0.0369, loss_cls: 0.1746, acc: 93.6908, loss_bbox: 0.2224, loss_mask: 0.2280, loss: 0.6904 2023-11-16 21:32:40,184 - mmdet - INFO - Epoch [10][1450/1833] lr: 5.563e-06, eta: 11:35:04, time: 0.883, data_time: 0.037, memory: 10346, loss_rpn_cls: 0.0294, loss_rpn_bbox: 0.0370, loss_cls: 0.1807, acc: 93.4198, loss_bbox: 0.2311, loss_mask: 0.2314, loss: 0.7095 2023-11-16 21:33:24,550 - mmdet - INFO - Epoch [10][1500/1833] lr: 5.563e-06, eta: 11:34:23, time: 0.888, data_time: 0.033, memory: 10346, loss_rpn_cls: 0.0287, loss_rpn_bbox: 0.0368, loss_cls: 0.1815, acc: 93.3733, loss_bbox: 0.2326, loss_mask: 0.2308, loss: 0.7104 2023-11-16 21:34:08,633 - mmdet - INFO - Epoch [10][1550/1833] lr: 5.563e-06, eta: 11:33:41, time: 0.881, data_time: 0.035, memory: 10346, loss_rpn_cls: 0.0273, loss_rpn_bbox: 0.0369, loss_cls: 0.1771, acc: 93.5810, loss_bbox: 0.2280, loss_mask: 0.2306, loss: 0.6999 2023-11-16 21:34:52,635 - mmdet - INFO - Epoch [10][1600/1833] lr: 5.563e-06, eta: 11:33:00, time: 0.880, data_time: 0.033, memory: 10346, loss_rpn_cls: 0.0275, loss_rpn_bbox: 0.0368, loss_cls: 0.1797, acc: 93.4603, loss_bbox: 0.2289, loss_mask: 0.2328, loss: 0.7056 2023-11-16 21:35:36,667 - mmdet - INFO - Epoch [10][1650/1833] lr: 5.563e-06, eta: 11:32:18, time: 0.881, data_time: 0.034, memory: 10346, loss_rpn_cls: 0.0282, loss_rpn_bbox: 0.0366, loss_cls: 0.1834, acc: 93.3665, loss_bbox: 0.2289, loss_mask: 0.2312, loss: 0.7083 2023-11-16 21:36:20,894 - mmdet - INFO - Epoch [10][1700/1833] lr: 5.563e-06, eta: 11:31:36, time: 0.885, data_time: 0.035, memory: 10346, loss_rpn_cls: 0.0280, loss_rpn_bbox: 0.0371, loss_cls: 0.1833, acc: 93.2938, loss_bbox: 0.2345, loss_mask: 0.2313, loss: 0.7142 2023-11-16 21:37:04,992 - mmdet - INFO - Epoch [10][1750/1833] lr: 5.563e-06, eta: 11:30:55, time: 0.882, data_time: 0.035, memory: 10346, loss_rpn_cls: 0.0255, loss_rpn_bbox: 0.0343, loss_cls: 0.1738, acc: 93.6236, loss_bbox: 0.2229, loss_mask: 0.2260, loss: 0.6825 2023-11-16 21:37:48,780 - mmdet - INFO - Epoch [10][1800/1833] lr: 5.563e-06, eta: 11:30:12, time: 0.875, data_time: 0.038, memory: 10346, loss_rpn_cls: 0.0287, loss_rpn_bbox: 0.0364, loss_cls: 0.1775, acc: 93.5595, loss_bbox: 0.2270, loss_mask: 0.2295, loss: 0.6992 2023-11-16 21:38:18,311 - mmdet - INFO - Saving checkpoint at 10 epochs 2023-11-16 21:38:54,212 - mmdet - INFO - Evaluating bbox... 2023-11-16 21:39:27,232 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.469 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.703 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.519 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.336 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.509 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.601 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.600 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.600 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.600 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.454 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.641 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.734 2023-11-16 21:39:27,234 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.568 | bicycle | 0.377 | car | 0.475 | | motorcycle | 0.490 | airplane | 0.678 | bus | 0.673 | | train | 0.678 | truck | 0.433 | boat | 0.327 | | traffic light | 0.310 | fire hydrant | 0.698 | stop sign | 0.656 | | parking meter | 0.497 | bench | 0.289 | bird | 0.417 | | cat | 0.727 | dog | 0.694 | horse | 0.608 | | sheep | 0.575 | cow | 0.628 | elephant | 0.684 | | bear | 0.703 | zebra | 0.686 | giraffe | 0.673 | | backpack | 0.218 | umbrella | 0.452 | handbag | 0.222 | | tie | 0.372 | suitcase | 0.476 | frisbee | 0.720 | | skis | 0.275 | snowboard | 0.427 | sports ball | 0.473 | | kite | 0.461 | baseball bat | 0.391 | baseball glove | 0.438 | | skateboard | 0.577 | surfboard | 0.441 | tennis racket | 0.527 | | bottle | 0.454 | wine glass | 0.407 | cup | 0.501 | | fork | 0.429 | knife | 0.288 | spoon | 0.266 | | bowl | 0.470 | banana | 0.288 | apple | 0.261 | | sandwich | 0.423 | orange | 0.360 | broccoli | 0.273 | | carrot | 0.269 | hot dog | 0.461 | pizza | 0.543 | | donut | 0.547 | cake | 0.433 | chair | 0.351 | | couch | 0.477 | potted plant | 0.322 | bed | 0.476 | | dining table | 0.315 | toilet | 0.651 | tv | 0.623 | | laptop | 0.655 | mouse | 0.617 | remote | 0.401 | | keyboard | 0.517 | cell phone | 0.430 | microwave | 0.634 | | oven | 0.398 | toaster | 0.415 | sink | 0.428 | | refrigerator | 0.626 | book | 0.169 | clock | 0.545 | | vase | 0.422 | scissors | 0.410 | teddy bear | 0.525 | | hair drier | 0.178 | toothbrush | 0.277 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-16 21:39:27,234 - mmdet - INFO - Evaluating segm... 2023-11-16 21:40:03,607 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.428 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.675 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.459 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.247 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.468 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.615 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.552 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.552 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.552 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.384 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.598 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.706 2023-11-16 21:40:03,610 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.496 | bicycle | 0.225 | car | 0.434 | | motorcycle | 0.394 | airplane | 0.529 | bus | 0.677 | | train | 0.677 | truck | 0.432 | boat | 0.309 | | traffic light | 0.298 | fire hydrant | 0.690 | stop sign | 0.654 | | parking meter | 0.515 | bench | 0.221 | bird | 0.339 | | cat | 0.730 | dog | 0.656 | horse | 0.460 | | sheep | 0.520 | cow | 0.532 | elephant | 0.630 | | bear | 0.701 | zebra | 0.594 | giraffe | 0.538 | | backpack | 0.221 | umbrella | 0.512 | handbag | 0.209 | | tie | 0.346 | suitcase | 0.490 | frisbee | 0.653 | | skis | 0.037 | snowboard | 0.265 | sports ball | 0.463 | | kite | 0.319 | baseball bat | 0.294 | baseball glove | 0.460 | | skateboard | 0.376 | surfboard | 0.370 | tennis racket | 0.575 | | bottle | 0.440 | wine glass | 0.336 | cup | 0.504 | | fork | 0.217 | knife | 0.198 | spoon | 0.206 | | bowl | 0.443 | banana | 0.243 | apple | 0.257 | | sandwich | 0.461 | orange | 0.354 | broccoli | 0.259 | | carrot | 0.237 | hot dog | 0.396 | pizza | 0.530 | | donut | 0.564 | cake | 0.454 | chair | 0.253 | | couch | 0.405 | potted plant | 0.283 | bed | 0.397 | | dining table | 0.188 | toilet | 0.636 | tv | 0.658 | | laptop | 0.670 | mouse | 0.612 | remote | 0.363 | | keyboard | 0.515 | cell phone | 0.418 | microwave | 0.675 | | oven | 0.373 | toaster | 0.428 | sink | 0.405 | | refrigerator | 0.658 | book | 0.124 | clock | 0.544 | | vase | 0.425 | scissors | 0.312 | teddy bear | 0.501 | | hair drier | 0.237 | toothbrush | 0.209 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-16 21:40:04,189 - mmdet - INFO - The previous best checkpoint /mnt/petrelfs/lizhiqi/DINO/detection/work_dirs/mask_rcnn_flash_internimage_b_fpn_3x_cocoo_0.4_0.9_4x16/best_bbox_mAP_epoch_9.pth was removed 2023-11-16 21:40:08,022 - mmdet - INFO - Now best checkpoint is saved as best_bbox_mAP_epoch_10.pth. 2023-11-16 21:40:08,022 - mmdet - INFO - Best bbox_mAP is 0.4694 at 10 epoch. 2023-11-16 21:40:08,023 - mmdet - INFO - Exp name: mask_rcnn_flash_internimage_b_fpn_3x_coco_0.4_0.9-4x16.py 2023-11-16 21:40:08,023 - mmdet - INFO - Epoch(val) [10][313] bbox_mAP: 0.4694, bbox_mAP_50: 0.7031, bbox_mAP_75: 0.5185, bbox_mAP_s: 0.3363, bbox_mAP_m: 0.5093, bbox_mAP_l: 0.6013, bbox_mAP_copypaste: 0.4694 0.7031 0.5185 0.3363 0.5093 0.6013, segm_mAP: 0.4278, segm_mAP_50: 0.6746, segm_mAP_75: 0.4593, segm_mAP_s: 0.2466, segm_mAP_m: 0.4680, segm_mAP_l: 0.6149, segm_mAP_copypaste: 0.4278 0.6746 0.4593 0.2466 0.4680 0.6149 2023-11-16 21:40:54,763 - mmdet - INFO - Epoch [11][50/1833] lr: 5.563e-06, eta: 11:27:54, time: 0.933, data_time: 0.092, memory: 10346, loss_rpn_cls: 0.0264, loss_rpn_bbox: 0.0356, loss_cls: 0.1729, acc: 93.6157, loss_bbox: 0.2241, loss_mask: 0.2255, loss: 0.6845 2023-11-16 21:41:38,661 - mmdet - INFO - Epoch [11][100/1833] lr: 5.563e-06, eta: 11:27:12, time: 0.878, data_time: 0.035, memory: 10346, loss_rpn_cls: 0.0260, loss_rpn_bbox: 0.0357, loss_cls: 0.1759, acc: 93.5043, loss_bbox: 0.2242, loss_mask: 0.2252, loss: 0.6871 2023-11-16 21:42:22,743 - mmdet - INFO - Epoch [11][150/1833] lr: 5.563e-06, eta: 11:26:31, time: 0.882, data_time: 0.037, memory: 10346, loss_rpn_cls: 0.0281, loss_rpn_bbox: 0.0372, loss_cls: 0.1773, acc: 93.4647, loss_bbox: 0.2309, loss_mask: 0.2293, loss: 0.7027 2023-11-16 21:43:06,353 - mmdet - INFO - Epoch [11][200/1833] lr: 5.563e-06, eta: 11:25:48, time: 0.872, data_time: 0.035, memory: 10346, loss_rpn_cls: 0.0285, loss_rpn_bbox: 0.0370, loss_cls: 0.1771, acc: 93.4680, loss_bbox: 0.2294, loss_mask: 0.2319, loss: 0.7039 2023-11-16 21:43:49,791 - mmdet - INFO - Epoch [11][250/1833] lr: 5.563e-06, eta: 11:25:05, time: 0.869, data_time: 0.039, memory: 10346, loss_rpn_cls: 0.0274, loss_rpn_bbox: 0.0369, loss_cls: 0.1795, acc: 93.4550, loss_bbox: 0.2294, loss_mask: 0.2280, loss: 0.7012 2023-11-16 21:44:34,257 - mmdet - INFO - Epoch [11][300/1833] lr: 5.563e-06, eta: 11:24:25, time: 0.889, data_time: 0.036, memory: 10346, loss_rpn_cls: 0.0263, loss_rpn_bbox: 0.0354, loss_cls: 0.1726, acc: 93.6857, loss_bbox: 0.2244, loss_mask: 0.2266, loss: 0.6853 2023-11-16 21:45:18,113 - mmdet - INFO - Epoch [11][350/1833] lr: 5.563e-06, eta: 11:23:43, time: 0.877, data_time: 0.041, memory: 10346, loss_rpn_cls: 0.0275, loss_rpn_bbox: 0.0363, loss_cls: 0.1761, acc: 93.5755, loss_bbox: 0.2255, loss_mask: 0.2291, loss: 0.6945 2023-11-16 21:46:02,468 - mmdet - INFO - Epoch [11][400/1833] lr: 5.563e-06, eta: 11:23:02, time: 0.887, data_time: 0.036, memory: 10346, loss_rpn_cls: 0.0275, loss_rpn_bbox: 0.0355, loss_cls: 0.1730, acc: 93.6577, loss_bbox: 0.2247, loss_mask: 0.2298, loss: 0.6905 2023-11-16 21:46:46,919 - mmdet - INFO - Epoch [11][450/1833] lr: 5.563e-06, eta: 11:22:21, time: 0.889, data_time: 0.037, memory: 10346, loss_rpn_cls: 0.0266, loss_rpn_bbox: 0.0368, loss_cls: 0.1770, acc: 93.4818, loss_bbox: 0.2291, loss_mask: 0.2299, loss: 0.6993 2023-11-16 21:47:30,316 - mmdet - INFO - Epoch [11][500/1833] lr: 5.563e-06, eta: 11:21:38, time: 0.868, data_time: 0.035, memory: 10346, loss_rpn_cls: 0.0271, loss_rpn_bbox: 0.0357, loss_cls: 0.1746, acc: 93.5839, loss_bbox: 0.2236, loss_mask: 0.2291, loss: 0.6901 2023-11-16 21:48:14,196 - mmdet - INFO - Epoch [11][550/1833] lr: 5.563e-06, eta: 11:20:56, time: 0.878, data_time: 0.033, memory: 10346, loss_rpn_cls: 0.0261, loss_rpn_bbox: 0.0361, loss_cls: 0.1763, acc: 93.5582, loss_bbox: 0.2264, loss_mask: 0.2277, loss: 0.6926 2023-11-16 21:48:58,124 - mmdet - INFO - Epoch [11][600/1833] lr: 5.563e-06, eta: 11:20:14, time: 0.878, data_time: 0.032, memory: 10346, loss_rpn_cls: 0.0278, loss_rpn_bbox: 0.0352, loss_cls: 0.1744, acc: 93.6528, loss_bbox: 0.2235, loss_mask: 0.2278, loss: 0.6886 2023-11-16 21:49:42,085 - mmdet - INFO - Epoch [11][650/1833] lr: 5.563e-06, eta: 11:19:32, time: 0.880, data_time: 0.032, memory: 10346, loss_rpn_cls: 0.0283, loss_rpn_bbox: 0.0366, loss_cls: 0.1793, acc: 93.4774, loss_bbox: 0.2287, loss_mask: 0.2259, loss: 0.6987 2023-11-16 21:50:25,889 - mmdet - INFO - Epoch [11][700/1833] lr: 5.563e-06, eta: 11:18:50, time: 0.876, data_time: 0.034, memory: 10346, loss_rpn_cls: 0.0265, loss_rpn_bbox: 0.0366, loss_cls: 0.1790, acc: 93.4515, loss_bbox: 0.2287, loss_mask: 0.2276, loss: 0.6984 2023-11-16 21:51:09,583 - mmdet - INFO - Epoch [11][750/1833] lr: 5.563e-06, eta: 11:18:07, time: 0.874, data_time: 0.036, memory: 10346, loss_rpn_cls: 0.0270, loss_rpn_bbox: 0.0358, loss_cls: 0.1769, acc: 93.5124, loss_bbox: 0.2255, loss_mask: 0.2281, loss: 0.6933 2023-11-16 21:51:53,084 - mmdet - INFO - Epoch [11][800/1833] lr: 5.563e-06, eta: 11:17:24, time: 0.869, data_time: 0.038, memory: 10346, loss_rpn_cls: 0.0261, loss_rpn_bbox: 0.0366, loss_cls: 0.1741, acc: 93.5894, loss_bbox: 0.2259, loss_mask: 0.2283, loss: 0.6909 2023-11-16 21:52:36,835 - mmdet - INFO - Epoch [11][850/1833] lr: 5.563e-06, eta: 11:16:42, time: 0.876, data_time: 0.035, memory: 10346, loss_rpn_cls: 0.0269, loss_rpn_bbox: 0.0356, loss_cls: 0.1728, acc: 93.6915, loss_bbox: 0.2238, loss_mask: 0.2287, loss: 0.6878 2023-11-16 21:53:22,978 - mmdet - INFO - Epoch [11][900/1833] lr: 5.563e-06, eta: 11:16:05, time: 0.923, data_time: 0.032, memory: 10346, loss_rpn_cls: 0.0269, loss_rpn_bbox: 0.0368, loss_cls: 0.1784, acc: 93.4019, loss_bbox: 0.2311, loss_mask: 0.2292, loss: 0.7025 2023-11-16 21:54:06,551 - mmdet - INFO - Epoch [11][950/1833] lr: 5.563e-06, eta: 11:15:22, time: 0.872, data_time: 0.035, memory: 10346, loss_rpn_cls: 0.0253, loss_rpn_bbox: 0.0356, loss_cls: 0.1701, acc: 93.7292, loss_bbox: 0.2232, loss_mask: 0.2272, loss: 0.6815 2023-11-16 21:54:50,504 - mmdet - INFO - Epoch [11][1000/1833] lr: 5.563e-06, eta: 11:14:40, time: 0.879, data_time: 0.032, memory: 10346, loss_rpn_cls: 0.0275, loss_rpn_bbox: 0.0370, loss_cls: 0.1781, acc: 93.4948, loss_bbox: 0.2274, loss_mask: 0.2297, loss: 0.6997 2023-11-16 21:55:34,361 - mmdet - INFO - Epoch [11][1050/1833] lr: 5.563e-06, eta: 11:13:58, time: 0.877, data_time: 0.034, memory: 10346, loss_rpn_cls: 0.0272, loss_rpn_bbox: 0.0362, loss_cls: 0.1750, acc: 93.6398, loss_bbox: 0.2235, loss_mask: 0.2278, loss: 0.6896 2023-11-16 21:56:18,077 - mmdet - INFO - Epoch [11][1100/1833] lr: 5.563e-06, eta: 11:13:15, time: 0.874, data_time: 0.037, memory: 10346, loss_rpn_cls: 0.0286, loss_rpn_bbox: 0.0365, loss_cls: 0.1769, acc: 93.5739, loss_bbox: 0.2269, loss_mask: 0.2290, loss: 0.6980 2023-11-16 21:57:02,644 - mmdet - INFO - Epoch [11][1150/1833] lr: 5.563e-06, eta: 11:12:35, time: 0.891, data_time: 0.039, memory: 10346, loss_rpn_cls: 0.0269, loss_rpn_bbox: 0.0370, loss_cls: 0.1759, acc: 93.5768, loss_bbox: 0.2249, loss_mask: 0.2272, loss: 0.6918 2023-11-16 21:57:46,954 - mmdet - INFO - Epoch [11][1200/1833] lr: 5.563e-06, eta: 11:11:53, time: 0.886, data_time: 0.034, memory: 10346, loss_rpn_cls: 0.0262, loss_rpn_bbox: 0.0362, loss_cls: 0.1760, acc: 93.5714, loss_bbox: 0.2264, loss_mask: 0.2263, loss: 0.6911 2023-11-16 21:58:40,968 - mmdet - INFO - Epoch [11][1250/1833] lr: 5.563e-06, eta: 11:11:35, time: 1.080, data_time: 0.033, memory: 10346, loss_rpn_cls: 0.0259, loss_rpn_bbox: 0.0358, loss_cls: 0.1791, acc: 93.4003, loss_bbox: 0.2279, loss_mask: 0.2301, loss: 0.6988 2023-11-16 21:59:24,786 - mmdet - INFO - Epoch [11][1300/1833] lr: 5.563e-06, eta: 11:10:53, time: 0.876, data_time: 0.034, memory: 10346, loss_rpn_cls: 0.0275, loss_rpn_bbox: 0.0365, loss_cls: 0.1766, acc: 93.5464, loss_bbox: 0.2264, loss_mask: 0.2258, loss: 0.6928 2023-11-16 22:00:08,474 - mmdet - INFO - Epoch [11][1350/1833] lr: 5.563e-06, eta: 11:10:10, time: 0.874, data_time: 0.036, memory: 10346, loss_rpn_cls: 0.0292, loss_rpn_bbox: 0.0381, loss_cls: 0.1772, acc: 93.5233, loss_bbox: 0.2276, loss_mask: 0.2297, loss: 0.7017 2023-11-16 22:00:52,412 - mmdet - INFO - Epoch [11][1400/1833] lr: 5.563e-06, eta: 11:09:28, time: 0.879, data_time: 0.035, memory: 10346, loss_rpn_cls: 0.0276, loss_rpn_bbox: 0.0359, loss_cls: 0.1768, acc: 93.5277, loss_bbox: 0.2260, loss_mask: 0.2291, loss: 0.6953 2023-11-16 22:01:36,831 - mmdet - INFO - Epoch [11][1450/1833] lr: 5.563e-06, eta: 11:08:47, time: 0.888, data_time: 0.031, memory: 10346, loss_rpn_cls: 0.0275, loss_rpn_bbox: 0.0363, loss_cls: 0.1774, acc: 93.5526, loss_bbox: 0.2294, loss_mask: 0.2310, loss: 0.7015 2023-11-16 22:02:20,902 - mmdet - INFO - Epoch [11][1500/1833] lr: 5.563e-06, eta: 11:08:05, time: 0.881, data_time: 0.032, memory: 10346, loss_rpn_cls: 0.0267, loss_rpn_bbox: 0.0351, loss_cls: 0.1756, acc: 93.5569, loss_bbox: 0.2264, loss_mask: 0.2294, loss: 0.6931 2023-11-16 22:03:05,332 - mmdet - INFO - Epoch [11][1550/1833] lr: 5.563e-06, eta: 11:07:24, time: 0.889, data_time: 0.035, memory: 10346, loss_rpn_cls: 0.0263, loss_rpn_bbox: 0.0362, loss_cls: 0.1766, acc: 93.5381, loss_bbox: 0.2279, loss_mask: 0.2271, loss: 0.6940 2023-11-16 22:03:48,998 - mmdet - INFO - Epoch [11][1600/1833] lr: 5.563e-06, eta: 11:06:41, time: 0.873, data_time: 0.038, memory: 10346, loss_rpn_cls: 0.0279, loss_rpn_bbox: 0.0377, loss_cls: 0.1767, acc: 93.5484, loss_bbox: 0.2264, loss_mask: 0.2314, loss: 0.7001 2023-11-16 22:04:33,347 - mmdet - INFO - Epoch [11][1650/1833] lr: 5.563e-06, eta: 11:06:00, time: 0.887, data_time: 0.035, memory: 10346, loss_rpn_cls: 0.0275, loss_rpn_bbox: 0.0363, loss_cls: 0.1773, acc: 93.5600, loss_bbox: 0.2232, loss_mask: 0.2307, loss: 0.6950 2023-11-16 22:05:17,251 - mmdet - INFO - Epoch [11][1700/1833] lr: 5.563e-06, eta: 11:05:17, time: 0.878, data_time: 0.031, memory: 10346, loss_rpn_cls: 0.0274, loss_rpn_bbox: 0.0356, loss_cls: 0.1741, acc: 93.6496, loss_bbox: 0.2212, loss_mask: 0.2266, loss: 0.6848 2023-11-16 22:06:01,294 - mmdet - INFO - Epoch [11][1750/1833] lr: 5.563e-06, eta: 11:04:35, time: 0.880, data_time: 0.034, memory: 10346, loss_rpn_cls: 0.0267, loss_rpn_bbox: 0.0370, loss_cls: 0.1793, acc: 93.4258, loss_bbox: 0.2289, loss_mask: 0.2305, loss: 0.7024 2023-11-16 22:06:45,150 - mmdet - INFO - Epoch [11][1800/1833] lr: 5.563e-06, eta: 11:03:53, time: 0.877, data_time: 0.034, memory: 10346, loss_rpn_cls: 0.0272, loss_rpn_bbox: 0.0371, loss_cls: 0.1777, acc: 93.4889, loss_bbox: 0.2298, loss_mask: 0.2304, loss: 0.7022 2023-11-16 22:07:14,788 - mmdet - INFO - Saving checkpoint at 11 epochs 2023-11-16 22:07:49,268 - mmdet - INFO - Evaluating bbox... 2023-11-16 22:08:20,667 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.477 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.708 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.527 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.338 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.518 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.614 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.604 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.604 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.604 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.454 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.649 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.749 2023-11-16 22:08:20,669 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.573 | bicycle | 0.385 | car | 0.474 | | motorcycle | 0.486 | airplane | 0.683 | bus | 0.684 | | train | 0.671 | truck | 0.443 | boat | 0.317 | | traffic light | 0.315 | fire hydrant | 0.720 | stop sign | 0.679 | | parking meter | 0.527 | bench | 0.294 | bird | 0.420 | | cat | 0.733 | dog | 0.696 | horse | 0.628 | | sheep | 0.587 | cow | 0.625 | elephant | 0.687 | | bear | 0.734 | zebra | 0.690 | giraffe | 0.688 | | backpack | 0.216 | umbrella | 0.450 | handbag | 0.227 | | tie | 0.374 | suitcase | 0.502 | frisbee | 0.700 | | skis | 0.279 | snowboard | 0.428 | sports ball | 0.478 | | kite | 0.465 | baseball bat | 0.430 | baseball glove | 0.436 | | skateboard | 0.570 | surfboard | 0.472 | tennis racket | 0.536 | | bottle | 0.457 | wine glass | 0.403 | cup | 0.492 | | fork | 0.446 | knife | 0.294 | spoon | 0.280 | | bowl | 0.471 | banana | 0.287 | apple | 0.263 | | sandwich | 0.452 | orange | 0.368 | broccoli | 0.275 | | carrot | 0.259 | hot dog | 0.449 | pizza | 0.540 | | donut | 0.560 | cake | 0.436 | chair | 0.349 | | couch | 0.483 | potted plant | 0.326 | bed | 0.487 | | dining table | 0.300 | toilet | 0.657 | tv | 0.615 | | laptop | 0.662 | mouse | 0.623 | remote | 0.408 | | keyboard | 0.513 | cell phone | 0.435 | microwave | 0.653 | | oven | 0.380 | toaster | 0.506 | sink | 0.433 | | refrigerator | 0.646 | book | 0.181 | clock | 0.545 | | vase | 0.435 | scissors | 0.402 | teddy bear | 0.526 | | hair drier | 0.213 | toothbrush | 0.329 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-16 22:08:20,669 - mmdet - INFO - Evaluating segm... 2023-11-16 22:08:55,112 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.433 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.675 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.465 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.250 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.472 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.623 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.556 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.556 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.556 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.392 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.602 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.715 2023-11-16 22:08:55,115 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.498 | bicycle | 0.235 | car | 0.439 | | motorcycle | 0.387 | airplane | 0.531 | bus | 0.675 | | train | 0.677 | truck | 0.440 | boat | 0.299 | | traffic light | 0.305 | fire hydrant | 0.702 | stop sign | 0.666 | | parking meter | 0.526 | bench | 0.223 | bird | 0.346 | | cat | 0.739 | dog | 0.650 | horse | 0.466 | | sheep | 0.526 | cow | 0.539 | elephant | 0.624 | | bear | 0.736 | zebra | 0.601 | giraffe | 0.537 | | backpack | 0.224 | umbrella | 0.520 | handbag | 0.229 | | tie | 0.358 | suitcase | 0.527 | frisbee | 0.646 | | skis | 0.043 | snowboard | 0.282 | sports ball | 0.470 | | kite | 0.324 | baseball bat | 0.309 | baseball glove | 0.473 | | skateboard | 0.367 | surfboard | 0.394 | tennis racket | 0.595 | | bottle | 0.446 | wine glass | 0.370 | cup | 0.499 | | fork | 0.231 | knife | 0.198 | spoon | 0.216 | | bowl | 0.447 | banana | 0.236 | apple | 0.261 | | sandwich | 0.486 | orange | 0.365 | broccoli | 0.252 | | carrot | 0.229 | hot dog | 0.355 | pizza | 0.536 | | donut | 0.569 | cake | 0.450 | chair | 0.250 | | couch | 0.397 | potted plant | 0.281 | bed | 0.392 | | dining table | 0.181 | toilet | 0.636 | tv | 0.657 | | laptop | 0.674 | mouse | 0.613 | remote | 0.368 | | keyboard | 0.520 | cell phone | 0.420 | microwave | 0.682 | | oven | 0.362 | toaster | 0.513 | sink | 0.418 | | refrigerator | 0.659 | book | 0.140 | clock | 0.541 | | vase | 0.433 | scissors | 0.312 | teddy bear | 0.501 | | hair drier | 0.207 | toothbrush | 0.220 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-16 22:08:55,680 - mmdet - INFO - The previous best checkpoint /mnt/petrelfs/lizhiqi/DINO/detection/work_dirs/mask_rcnn_flash_internimage_b_fpn_3x_cocoo_0.4_0.9_4x16/best_bbox_mAP_epoch_10.pth was removed 2023-11-16 22:08:59,273 - mmdet - INFO - Now best checkpoint is saved as best_bbox_mAP_epoch_11.pth. 2023-11-16 22:08:59,273 - mmdet - INFO - Best bbox_mAP is 0.4767 at 11 epoch. 2023-11-16 22:08:59,274 - mmdet - INFO - Exp name: mask_rcnn_flash_internimage_b_fpn_3x_coco_0.4_0.9-4x16.py 2023-11-16 22:08:59,274 - mmdet - INFO - Epoch(val) [11][313] bbox_mAP: 0.4767, bbox_mAP_50: 0.7077, bbox_mAP_75: 0.5266, bbox_mAP_s: 0.3375, bbox_mAP_m: 0.5179, bbox_mAP_l: 0.6141, bbox_mAP_copypaste: 0.4767 0.7077 0.5266 0.3375 0.5179 0.6141, segm_mAP: 0.4332, segm_mAP_50: 0.6750, segm_mAP_75: 0.4653, segm_mAP_s: 0.2505, segm_mAP_m: 0.4724, segm_mAP_l: 0.6228, segm_mAP_copypaste: 0.4332 0.6750 0.4653 0.2505 0.4724 0.6228 2023-11-16 22:09:46,584 - mmdet - INFO - Epoch [12][50/1833] lr: 5.563e-06, eta: 11:01:44, time: 0.946, data_time: 0.094, memory: 10346, loss_rpn_cls: 0.0263, loss_rpn_bbox: 0.0350, loss_cls: 0.1699, acc: 93.7579, loss_bbox: 0.2208, loss_mask: 0.2250, loss: 0.6769 2023-11-16 22:10:30,383 - mmdet - INFO - Epoch [12][100/1833] lr: 5.563e-06, eta: 11:01:02, time: 0.876, data_time: 0.040, memory: 10346, loss_rpn_cls: 0.0265, loss_rpn_bbox: 0.0366, loss_cls: 0.1770, acc: 93.5068, loss_bbox: 0.2270, loss_mask: 0.2272, loss: 0.6942 2023-11-16 22:11:14,642 - mmdet - INFO - Epoch [12][150/1833] lr: 5.563e-06, eta: 11:00:21, time: 0.885, data_time: 0.036, memory: 10346, loss_rpn_cls: 0.0251, loss_rpn_bbox: 0.0353, loss_cls: 0.1723, acc: 93.6766, loss_bbox: 0.2249, loss_mask: 0.2221, loss: 0.6796 2023-11-16 22:11:59,816 - mmdet - INFO - Epoch [12][200/1833] lr: 5.563e-06, eta: 10:59:41, time: 0.903, data_time: 0.038, memory: 10346, loss_rpn_cls: 0.0254, loss_rpn_bbox: 0.0352, loss_cls: 0.1738, acc: 93.6878, loss_bbox: 0.2217, loss_mask: 0.2266, loss: 0.6827 2023-11-16 22:12:44,448 - mmdet - INFO - Epoch [12][250/1833] lr: 5.563e-06, eta: 10:59:01, time: 0.893, data_time: 0.041, memory: 10346, loss_rpn_cls: 0.0256, loss_rpn_bbox: 0.0359, loss_cls: 0.1718, acc: 93.6773, loss_bbox: 0.2249, loss_mask: 0.2258, loss: 0.6840 2023-11-16 22:13:28,352 - mmdet - INFO - Epoch [12][300/1833] lr: 5.563e-06, eta: 10:58:19, time: 0.878, data_time: 0.038, memory: 10346, loss_rpn_cls: 0.0270, loss_rpn_bbox: 0.0362, loss_cls: 0.1770, acc: 93.5120, loss_bbox: 0.2297, loss_mask: 0.2279, loss: 0.6977 2023-11-16 22:14:12,422 - mmdet - INFO - Epoch [12][350/1833] lr: 5.563e-06, eta: 10:57:37, time: 0.882, data_time: 0.034, memory: 10346, loss_rpn_cls: 0.0267, loss_rpn_bbox: 0.0366, loss_cls: 0.1752, acc: 93.5674, loss_bbox: 0.2252, loss_mask: 0.2274, loss: 0.6910 2023-11-16 22:14:55,860 - mmdet - INFO - Epoch [12][400/1833] lr: 5.563e-06, eta: 10:56:53, time: 0.869, data_time: 0.037, memory: 10346, loss_rpn_cls: 0.0253, loss_rpn_bbox: 0.0346, loss_cls: 0.1711, acc: 93.6743, loss_bbox: 0.2224, loss_mask: 0.2242, loss: 0.6776 2023-11-16 22:15:39,711 - mmdet - INFO - Epoch [12][450/1833] lr: 5.563e-06, eta: 10:56:11, time: 0.877, data_time: 0.038, memory: 10346, loss_rpn_cls: 0.0261, loss_rpn_bbox: 0.0356, loss_cls: 0.1690, acc: 93.7618, loss_bbox: 0.2239, loss_mask: 0.2262, loss: 0.6808 2023-11-16 22:16:27,499 - mmdet - INFO - Epoch [12][500/1833] lr: 5.563e-06, eta: 10:55:37, time: 0.956, data_time: 0.032, memory: 10346, loss_rpn_cls: 0.0266, loss_rpn_bbox: 0.0363, loss_cls: 0.1768, acc: 93.5148, loss_bbox: 0.2268, loss_mask: 0.2243, loss: 0.6909 2023-11-16 22:17:14,004 - mmdet - INFO - Epoch [12][550/1833] lr: 5.563e-06, eta: 10:55:01, time: 0.930, data_time: 0.038, memory: 10346, loss_rpn_cls: 0.0276, loss_rpn_bbox: 0.0368, loss_cls: 0.1758, acc: 93.5174, loss_bbox: 0.2266, loss_mask: 0.2285, loss: 0.6952 2023-11-16 22:17:57,846 - mmdet - INFO - Epoch [12][600/1833] lr: 5.563e-06, eta: 10:54:18, time: 0.877, data_time: 0.034, memory: 10346, loss_rpn_cls: 0.0265, loss_rpn_bbox: 0.0359, loss_cls: 0.1714, acc: 93.6884, loss_bbox: 0.2237, loss_mask: 0.2271, loss: 0.6844 2023-11-16 22:18:42,162 - mmdet - INFO - Epoch [12][650/1833] lr: 5.563e-06, eta: 10:53:37, time: 0.886, data_time: 0.038, memory: 10346, loss_rpn_cls: 0.0267, loss_rpn_bbox: 0.0370, loss_cls: 0.1752, acc: 93.5587, loss_bbox: 0.2282, loss_mask: 0.2289, loss: 0.6960 2023-11-16 22:19:29,435 - mmdet - INFO - Epoch [12][700/1833] lr: 5.563e-06, eta: 10:53:02, time: 0.945, data_time: 0.034, memory: 10346, loss_rpn_cls: 0.0258, loss_rpn_bbox: 0.0358, loss_cls: 0.1747, acc: 93.5642, loss_bbox: 0.2269, loss_mask: 0.2279, loss: 0.6911 2023-11-16 22:20:12,791 - mmdet - INFO - Epoch [12][750/1833] lr: 5.563e-06, eta: 10:52:18, time: 0.867, data_time: 0.032, memory: 10346, loss_rpn_cls: 0.0262, loss_rpn_bbox: 0.0346, loss_cls: 0.1711, acc: 93.7260, loss_bbox: 0.2216, loss_mask: 0.2267, loss: 0.6803 2023-11-16 22:20:56,558 - mmdet - INFO - Epoch [12][800/1833] lr: 5.563e-06, eta: 10:51:36, time: 0.875, data_time: 0.034, memory: 10346, loss_rpn_cls: 0.0268, loss_rpn_bbox: 0.0369, loss_cls: 0.1752, acc: 93.5272, loss_bbox: 0.2258, loss_mask: 0.2253, loss: 0.6900 2023-11-16 22:21:39,933 - mmdet - INFO - Epoch [12][850/1833] lr: 5.563e-06, eta: 10:50:52, time: 0.868, data_time: 0.034, memory: 10346, loss_rpn_cls: 0.0246, loss_rpn_bbox: 0.0344, loss_cls: 0.1688, acc: 93.8478, loss_bbox: 0.2185, loss_mask: 0.2254, loss: 0.6718 2023-11-16 22:22:26,532 - mmdet - INFO - Epoch [12][900/1833] lr: 5.563e-06, eta: 10:50:15, time: 0.932, data_time: 0.037, memory: 10346, loss_rpn_cls: 0.0271, loss_rpn_bbox: 0.0362, loss_cls: 0.1747, acc: 93.5715, loss_bbox: 0.2258, loss_mask: 0.2274, loss: 0.6913 2023-11-16 22:23:09,825 - mmdet - INFO - Epoch [12][950/1833] lr: 5.563e-06, eta: 10:49:32, time: 0.866, data_time: 0.034, memory: 10346, loss_rpn_cls: 0.0259, loss_rpn_bbox: 0.0353, loss_cls: 0.1721, acc: 93.6746, loss_bbox: 0.2218, loss_mask: 0.2299, loss: 0.6851 2023-11-16 22:23:54,021 - mmdet - INFO - Epoch [12][1000/1833] lr: 5.563e-06, eta: 10:48:50, time: 0.884, data_time: 0.035, memory: 10346, loss_rpn_cls: 0.0266, loss_rpn_bbox: 0.0357, loss_cls: 0.1753, acc: 93.5880, loss_bbox: 0.2244, loss_mask: 0.2266, loss: 0.6887 2023-11-16 22:24:37,966 - mmdet - INFO - Epoch [12][1050/1833] lr: 5.563e-06, eta: 10:48:08, time: 0.879, data_time: 0.037, memory: 10346, loss_rpn_cls: 0.0266, loss_rpn_bbox: 0.0374, loss_cls: 0.1762, acc: 93.5137, loss_bbox: 0.2287, loss_mask: 0.2296, loss: 0.6986 2023-11-16 22:25:21,500 - mmdet - INFO - Epoch [12][1100/1833] lr: 5.563e-06, eta: 10:47:24, time: 0.871, data_time: 0.035, memory: 10346, loss_rpn_cls: 0.0254, loss_rpn_bbox: 0.0347, loss_cls: 0.1715, acc: 93.7352, loss_bbox: 0.2218, loss_mask: 0.2263, loss: 0.6797 2023-11-16 22:26:05,529 - mmdet - INFO - Epoch [12][1150/1833] lr: 5.563e-06, eta: 10:46:42, time: 0.881, data_time: 0.037, memory: 10346, loss_rpn_cls: 0.0253, loss_rpn_bbox: 0.0354, loss_cls: 0.1728, acc: 93.6936, loss_bbox: 0.2232, loss_mask: 0.2275, loss: 0.6842 2023-11-16 22:26:49,249 - mmdet - INFO - Epoch [12][1200/1833] lr: 5.563e-06, eta: 10:45:59, time: 0.874, data_time: 0.033, memory: 10346, loss_rpn_cls: 0.0284, loss_rpn_bbox: 0.0372, loss_cls: 0.1753, acc: 93.6137, loss_bbox: 0.2246, loss_mask: 0.2284, loss: 0.6940 2023-11-16 22:27:33,241 - mmdet - INFO - Epoch [12][1250/1833] lr: 5.563e-06, eta: 10:45:17, time: 0.880, data_time: 0.036, memory: 10346, loss_rpn_cls: 0.0264, loss_rpn_bbox: 0.0358, loss_cls: 0.1736, acc: 93.6476, loss_bbox: 0.2253, loss_mask: 0.2300, loss: 0.6911 2023-11-16 22:28:17,156 - mmdet - INFO - Epoch [12][1300/1833] lr: 5.563e-06, eta: 10:44:35, time: 0.879, data_time: 0.035, memory: 10346, loss_rpn_cls: 0.0264, loss_rpn_bbox: 0.0360, loss_cls: 0.1774, acc: 93.5242, loss_bbox: 0.2269, loss_mask: 0.2284, loss: 0.6951 2023-11-16 22:29:00,916 - mmdet - INFO - Epoch [12][1350/1833] lr: 5.563e-06, eta: 10:43:52, time: 0.875, data_time: 0.035, memory: 10346, loss_rpn_cls: 0.0264, loss_rpn_bbox: 0.0364, loss_cls: 0.1752, acc: 93.5992, loss_bbox: 0.2246, loss_mask: 0.2291, loss: 0.6917 2023-11-16 22:29:44,076 - mmdet - INFO - Epoch [12][1400/1833] lr: 5.563e-06, eta: 10:43:08, time: 0.863, data_time: 0.037, memory: 10346, loss_rpn_cls: 0.0260, loss_rpn_bbox: 0.0357, loss_cls: 0.1764, acc: 93.5038, loss_bbox: 0.2272, loss_mask: 0.2296, loss: 0.6949 2023-11-16 22:30:30,200 - mmdet - INFO - Epoch [12][1450/1833] lr: 5.563e-06, eta: 10:42:30, time: 0.922, data_time: 0.039, memory: 10346, loss_rpn_cls: 0.0251, loss_rpn_bbox: 0.0349, loss_cls: 0.1697, acc: 93.8414, loss_bbox: 0.2175, loss_mask: 0.2242, loss: 0.6714 2023-11-16 22:31:14,095 - mmdet - INFO - Epoch [12][1500/1833] lr: 5.563e-06, eta: 10:41:48, time: 0.878, data_time: 0.038, memory: 10346, loss_rpn_cls: 0.0277, loss_rpn_bbox: 0.0373, loss_cls: 0.1750, acc: 93.5875, loss_bbox: 0.2260, loss_mask: 0.2271, loss: 0.6932 2023-11-16 22:31:57,625 - mmdet - INFO - Epoch [12][1550/1833] lr: 5.563e-06, eta: 10:41:04, time: 0.871, data_time: 0.040, memory: 10346, loss_rpn_cls: 0.0276, loss_rpn_bbox: 0.0363, loss_cls: 0.1731, acc: 93.6157, loss_bbox: 0.2219, loss_mask: 0.2272, loss: 0.6859 2023-11-16 22:32:41,364 - mmdet - INFO - Epoch [12][1600/1833] lr: 5.563e-06, eta: 10:40:22, time: 0.875, data_time: 0.035, memory: 10346, loss_rpn_cls: 0.0269, loss_rpn_bbox: 0.0363, loss_cls: 0.1725, acc: 93.6798, loss_bbox: 0.2235, loss_mask: 0.2297, loss: 0.6889 2023-11-16 22:33:25,288 - mmdet - INFO - Epoch [12][1650/1833] lr: 5.563e-06, eta: 10:39:39, time: 0.878, data_time: 0.036, memory: 10346, loss_rpn_cls: 0.0258, loss_rpn_bbox: 0.0352, loss_cls: 0.1718, acc: 93.7134, loss_bbox: 0.2214, loss_mask: 0.2260, loss: 0.6802 2023-11-16 22:34:08,638 - mmdet - INFO - Epoch [12][1700/1833] lr: 5.563e-06, eta: 10:38:55, time: 0.867, data_time: 0.038, memory: 10346, loss_rpn_cls: 0.0268, loss_rpn_bbox: 0.0365, loss_cls: 0.1731, acc: 93.6369, loss_bbox: 0.2242, loss_mask: 0.2266, loss: 0.6872 2023-11-16 22:34:52,447 - mmdet - INFO - Epoch [12][1750/1833] lr: 5.563e-06, eta: 10:38:13, time: 0.876, data_time: 0.036, memory: 10346, loss_rpn_cls: 0.0263, loss_rpn_bbox: 0.0366, loss_cls: 0.1758, acc: 93.4960, loss_bbox: 0.2259, loss_mask: 0.2279, loss: 0.6926 2023-11-16 22:35:36,125 - mmdet - INFO - Epoch [12][1800/1833] lr: 5.563e-06, eta: 10:37:30, time: 0.874, data_time: 0.035, memory: 10346, loss_rpn_cls: 0.0267, loss_rpn_bbox: 0.0363, loss_cls: 0.1774, acc: 93.4706, loss_bbox: 0.2265, loss_mask: 0.2276, loss: 0.6945 2023-11-16 22:36:05,855 - mmdet - INFO - Saving checkpoint at 12 epochs 2023-11-16 22:36:40,833 - mmdet - INFO - Evaluating bbox... 2023-11-16 22:37:11,791 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.478 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.709 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.526 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.341 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.519 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.615 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.604 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.604 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.604 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.459 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.646 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.744 2023-11-16 22:37:11,793 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.576 | bicycle | 0.381 | car | 0.484 | | motorcycle | 0.491 | airplane | 0.685 | bus | 0.689 | | train | 0.691 | truck | 0.430 | boat | 0.339 | | traffic light | 0.301 | fire hydrant | 0.716 | stop sign | 0.659 | | parking meter | 0.484 | bench | 0.292 | bird | 0.420 | | cat | 0.744 | dog | 0.692 | horse | 0.624 | | sheep | 0.593 | cow | 0.625 | elephant | 0.669 | | bear | 0.744 | zebra | 0.680 | giraffe | 0.689 | | backpack | 0.225 | umbrella | 0.452 | handbag | 0.236 | | tie | 0.379 | suitcase | 0.487 | frisbee | 0.698 | | skis | 0.285 | snowboard | 0.424 | sports ball | 0.482 | | kite | 0.470 | baseball bat | 0.430 | baseball glove | 0.444 | | skateboard | 0.570 | surfboard | 0.470 | tennis racket | 0.541 | | bottle | 0.465 | wine glass | 0.418 | cup | 0.505 | | fork | 0.464 | knife | 0.305 | spoon | 0.269 | | bowl | 0.488 | banana | 0.296 | apple | 0.270 | | sandwich | 0.420 | orange | 0.360 | broccoli | 0.265 | | carrot | 0.273 | hot dog | 0.463 | pizza | 0.556 | | donut | 0.559 | cake | 0.469 | chair | 0.351 | | couch | 0.486 | potted plant | 0.342 | bed | 0.498 | | dining table | 0.307 | toilet | 0.664 | tv | 0.617 | | laptop | 0.664 | mouse | 0.649 | remote | 0.428 | | keyboard | 0.532 | cell phone | 0.446 | microwave | 0.628 | | oven | 0.407 | toaster | 0.455 | sink | 0.416 | | refrigerator | 0.657 | book | 0.189 | clock | 0.540 | | vase | 0.425 | scissors | 0.396 | teddy bear | 0.519 | | hair drier | 0.178 | toothbrush | 0.303 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-16 22:37:11,793 - mmdet - INFO - Evaluating segm... 2023-11-16 22:37:45,548 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.432 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.675 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.465 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.252 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.469 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.619 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.550 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.550 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.550 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.385 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.595 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.708 2023-11-16 22:37:45,551 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.500 | bicycle | 0.226 | car | 0.445 | | motorcycle | 0.380 | airplane | 0.534 | bus | 0.679 | | train | 0.675 | truck | 0.432 | boat | 0.318 | | traffic light | 0.286 | fire hydrant | 0.699 | stop sign | 0.640 | | parking meter | 0.501 | bench | 0.225 | bird | 0.343 | | cat | 0.741 | dog | 0.657 | horse | 0.467 | | sheep | 0.528 | cow | 0.536 | elephant | 0.621 | | bear | 0.741 | zebra | 0.577 | giraffe | 0.542 | | backpack | 0.224 | umbrella | 0.512 | handbag | 0.226 | | tie | 0.359 | suitcase | 0.510 | frisbee | 0.660 | | skis | 0.037 | snowboard | 0.277 | sports ball | 0.459 | | kite | 0.320 | baseball bat | 0.303 | baseball glove | 0.467 | | skateboard | 0.369 | surfboard | 0.380 | tennis racket | 0.585 | | bottle | 0.446 | wine glass | 0.376 | cup | 0.507 | | fork | 0.233 | knife | 0.198 | spoon | 0.195 | | bowl | 0.458 | banana | 0.251 | apple | 0.266 | | sandwich | 0.454 | orange | 0.353 | broccoli | 0.247 | | carrot | 0.245 | hot dog | 0.371 | pizza | 0.533 | | donut | 0.561 | cake | 0.483 | chair | 0.252 | | couch | 0.407 | potted plant | 0.292 | bed | 0.379 | | dining table | 0.185 | toilet | 0.642 | tv | 0.650 | | laptop | 0.672 | mouse | 0.627 | remote | 0.382 | | keyboard | 0.537 | cell phone | 0.420 | microwave | 0.654 | | oven | 0.393 | toaster | 0.487 | sink | 0.403 | | refrigerator | 0.681 | book | 0.137 | clock | 0.540 | | vase | 0.418 | scissors | 0.314 | teddy bear | 0.516 | | hair drier | 0.195 | toothbrush | 0.199 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-16 22:37:46,131 - mmdet - INFO - The previous best checkpoint /mnt/petrelfs/lizhiqi/DINO/detection/work_dirs/mask_rcnn_flash_internimage_b_fpn_3x_cocoo_0.4_0.9_4x16/best_bbox_mAP_epoch_11.pth was removed 2023-11-16 22:37:50,090 - mmdet - INFO - Now best checkpoint is saved as best_bbox_mAP_epoch_12.pth. 2023-11-16 22:37:50,091 - mmdet - INFO - Best bbox_mAP is 0.4779 at 12 epoch. 2023-11-16 22:37:50,091 - mmdet - INFO - Exp name: mask_rcnn_flash_internimage_b_fpn_3x_coco_0.4_0.9-4x16.py 2023-11-16 22:37:50,091 - mmdet - INFO - Epoch(val) [12][313] bbox_mAP: 0.4779, bbox_mAP_50: 0.7091, bbox_mAP_75: 0.5261, bbox_mAP_s: 0.3412, bbox_mAP_m: 0.5193, bbox_mAP_l: 0.6155, bbox_mAP_copypaste: 0.4779 0.7091 0.5261 0.3412 0.5193 0.6155, segm_mAP: 0.4317, segm_mAP_50: 0.6752, segm_mAP_75: 0.4651, segm_mAP_s: 0.2519, segm_mAP_m: 0.4693, segm_mAP_l: 0.6192, segm_mAP_copypaste: 0.4317 0.6752 0.4651 0.2519 0.4693 0.6192 2023-11-16 22:38:37,356 - mmdet - INFO - Epoch [13][50/1833] lr: 5.563e-06, eta: 10:35:28, time: 0.945, data_time: 0.094, memory: 10346, loss_rpn_cls: 0.0252, loss_rpn_bbox: 0.0349, loss_cls: 0.1692, acc: 93.8160, loss_bbox: 0.2192, loss_mask: 0.2200, loss: 0.6684 2023-11-16 22:39:21,439 - mmdet - INFO - Epoch [13][100/1833] lr: 5.563e-06, eta: 10:34:46, time: 0.882, data_time: 0.043, memory: 10346, loss_rpn_cls: 0.0257, loss_rpn_bbox: 0.0348, loss_cls: 0.1717, acc: 93.6428, loss_bbox: 0.2236, loss_mask: 0.2262, loss: 0.6820 2023-11-16 22:40:05,179 - mmdet - INFO - Epoch [13][150/1833] lr: 5.563e-06, eta: 10:34:03, time: 0.875, data_time: 0.032, memory: 10346, loss_rpn_cls: 0.0242, loss_rpn_bbox: 0.0341, loss_cls: 0.1700, acc: 93.6858, loss_bbox: 0.2233, loss_mask: 0.2243, loss: 0.6758 2023-11-16 22:40:49,280 - mmdet - INFO - Epoch [13][200/1833] lr: 5.563e-06, eta: 10:33:21, time: 0.882, data_time: 0.032, memory: 10346, loss_rpn_cls: 0.0254, loss_rpn_bbox: 0.0352, loss_cls: 0.1681, acc: 93.7686, loss_bbox: 0.2186, loss_mask: 0.2242, loss: 0.6716 2023-11-16 22:41:33,238 - mmdet - INFO - Epoch [13][250/1833] lr: 5.563e-06, eta: 10:32:39, time: 0.879, data_time: 0.036, memory: 10346, loss_rpn_cls: 0.0251, loss_rpn_bbox: 0.0351, loss_cls: 0.1676, acc: 93.8025, loss_bbox: 0.2178, loss_mask: 0.2242, loss: 0.6698 2023-11-16 22:42:17,072 - mmdet - INFO - Epoch [13][300/1833] lr: 5.563e-06, eta: 10:31:57, time: 0.877, data_time: 0.043, memory: 10346, loss_rpn_cls: 0.0264, loss_rpn_bbox: 0.0371, loss_cls: 0.1729, acc: 93.6137, loss_bbox: 0.2263, loss_mask: 0.2231, loss: 0.6858 2023-11-16 22:43:03,946 - mmdet - INFO - Epoch [13][350/1833] lr: 5.563e-06, eta: 10:31:20, time: 0.937, data_time: 0.040, memory: 10346, loss_rpn_cls: 0.0250, loss_rpn_bbox: 0.0353, loss_cls: 0.1706, acc: 93.7292, loss_bbox: 0.2206, loss_mask: 0.2233, loss: 0.6749 2023-11-16 22:43:48,230 - mmdet - INFO - Epoch [13][400/1833] lr: 5.563e-06, eta: 10:30:38, time: 0.886, data_time: 0.036, memory: 10346, loss_rpn_cls: 0.0254, loss_rpn_bbox: 0.0370, loss_cls: 0.1731, acc: 93.5824, loss_bbox: 0.2271, loss_mask: 0.2280, loss: 0.6907 2023-11-16 22:44:32,131 - mmdet - INFO - Epoch [13][450/1833] lr: 5.563e-06, eta: 10:29:56, time: 0.878, data_time: 0.041, memory: 10346, loss_rpn_cls: 0.0274, loss_rpn_bbox: 0.0364, loss_cls: 0.1710, acc: 93.6871, loss_bbox: 0.2212, loss_mask: 0.2276, loss: 0.6836 2023-11-16 22:45:16,285 - mmdet - INFO - Epoch [13][500/1833] lr: 5.563e-06, eta: 10:29:14, time: 0.883, data_time: 0.035, memory: 10346, loss_rpn_cls: 0.0262, loss_rpn_bbox: 0.0353, loss_cls: 0.1714, acc: 93.6995, loss_bbox: 0.2218, loss_mask: 0.2270, loss: 0.6817 2023-11-16 22:46:00,589 - mmdet - INFO - Epoch [13][550/1833] lr: 5.563e-06, eta: 10:28:32, time: 0.886, data_time: 0.034, memory: 10346, loss_rpn_cls: 0.0255, loss_rpn_bbox: 0.0355, loss_cls: 0.1732, acc: 93.6717, loss_bbox: 0.2241, loss_mask: 0.2274, loss: 0.6857 2023-11-16 22:46:44,935 - mmdet - INFO - Epoch [13][600/1833] lr: 5.563e-06, eta: 10:27:51, time: 0.887, data_time: 0.041, memory: 10346, loss_rpn_cls: 0.0254, loss_rpn_bbox: 0.0358, loss_cls: 0.1710, acc: 93.7301, loss_bbox: 0.2207, loss_mask: 0.2275, loss: 0.6804 2023-11-16 22:47:29,342 - mmdet - INFO - Epoch [13][650/1833] lr: 5.563e-06, eta: 10:27:09, time: 0.888, data_time: 0.036, memory: 10346, loss_rpn_cls: 0.0264, loss_rpn_bbox: 0.0354, loss_cls: 0.1695, acc: 93.7882, loss_bbox: 0.2188, loss_mask: 0.2238, loss: 0.6738 2023-11-16 22:48:13,616 - mmdet - INFO - Epoch [13][700/1833] lr: 5.563e-06, eta: 10:26:27, time: 0.886, data_time: 0.042, memory: 10346, loss_rpn_cls: 0.0257, loss_rpn_bbox: 0.0359, loss_cls: 0.1732, acc: 93.5982, loss_bbox: 0.2240, loss_mask: 0.2234, loss: 0.6822 2023-11-16 22:48:57,683 - mmdet - INFO - Epoch [13][750/1833] lr: 5.563e-06, eta: 10:25:45, time: 0.881, data_time: 0.036, memory: 10346, loss_rpn_cls: 0.0269, loss_rpn_bbox: 0.0367, loss_cls: 0.1730, acc: 93.6699, loss_bbox: 0.2237, loss_mask: 0.2262, loss: 0.6864 2023-11-16 22:49:41,298 - mmdet - INFO - Epoch [13][800/1833] lr: 5.563e-06, eta: 10:25:02, time: 0.872, data_time: 0.033, memory: 10346, loss_rpn_cls: 0.0260, loss_rpn_bbox: 0.0359, loss_cls: 0.1726, acc: 93.6450, loss_bbox: 0.2242, loss_mask: 0.2291, loss: 0.6879 2023-11-16 22:50:25,384 - mmdet - INFO - Epoch [13][850/1833] lr: 5.563e-06, eta: 10:24:20, time: 0.882, data_time: 0.034, memory: 10346, loss_rpn_cls: 0.0259, loss_rpn_bbox: 0.0351, loss_cls: 0.1707, acc: 93.6664, loss_bbox: 0.2214, loss_mask: 0.2235, loss: 0.6765 2023-11-16 22:51:09,390 - mmdet - INFO - Epoch [13][900/1833] lr: 5.563e-06, eta: 10:23:38, time: 0.880, data_time: 0.035, memory: 10346, loss_rpn_cls: 0.0254, loss_rpn_bbox: 0.0350, loss_cls: 0.1711, acc: 93.7103, loss_bbox: 0.2229, loss_mask: 0.2262, loss: 0.6807 2023-11-16 22:51:53,196 - mmdet - INFO - Epoch [13][950/1833] lr: 5.563e-06, eta: 10:22:55, time: 0.876, data_time: 0.032, memory: 10346, loss_rpn_cls: 0.0277, loss_rpn_bbox: 0.0363, loss_cls: 0.1743, acc: 93.5999, loss_bbox: 0.2247, loss_mask: 0.2269, loss: 0.6900 2023-11-16 22:52:37,914 - mmdet - INFO - Epoch [13][1000/1833] lr: 5.563e-06, eta: 10:22:14, time: 0.894, data_time: 0.033, memory: 10346, loss_rpn_cls: 0.0248, loss_rpn_bbox: 0.0358, loss_cls: 0.1710, acc: 93.6832, loss_bbox: 0.2239, loss_mask: 0.2251, loss: 0.6807 2023-11-16 22:53:21,804 - mmdet - INFO - Epoch [13][1050/1833] lr: 5.563e-06, eta: 10:21:32, time: 0.878, data_time: 0.035, memory: 10346, loss_rpn_cls: 0.0255, loss_rpn_bbox: 0.0362, loss_cls: 0.1725, acc: 93.6147, loss_bbox: 0.2245, loss_mask: 0.2263, loss: 0.6850 2023-11-16 22:54:05,322 - mmdet - INFO - Epoch [13][1100/1833] lr: 5.563e-06, eta: 10:20:48, time: 0.870, data_time: 0.034, memory: 10346, loss_rpn_cls: 0.0253, loss_rpn_bbox: 0.0344, loss_cls: 0.1729, acc: 93.6433, loss_bbox: 0.2251, loss_mask: 0.2243, loss: 0.6821 2023-11-16 22:54:49,763 - mmdet - INFO - Epoch [13][1150/1833] lr: 5.563e-06, eta: 10:20:07, time: 0.889, data_time: 0.035, memory: 10346, loss_rpn_cls: 0.0255, loss_rpn_bbox: 0.0371, loss_cls: 0.1725, acc: 93.6440, loss_bbox: 0.2255, loss_mask: 0.2245, loss: 0.6852 2023-11-16 22:55:34,014 - mmdet - INFO - Epoch [13][1200/1833] lr: 5.563e-06, eta: 10:19:25, time: 0.885, data_time: 0.037, memory: 10346, loss_rpn_cls: 0.0269, loss_rpn_bbox: 0.0360, loss_cls: 0.1754, acc: 93.5546, loss_bbox: 0.2268, loss_mask: 0.2270, loss: 0.6922 2023-11-16 22:56:17,746 - mmdet - INFO - Epoch [13][1250/1833] lr: 5.563e-06, eta: 10:18:42, time: 0.875, data_time: 0.033, memory: 10346, loss_rpn_cls: 0.0260, loss_rpn_bbox: 0.0356, loss_cls: 0.1719, acc: 93.6887, loss_bbox: 0.2204, loss_mask: 0.2275, loss: 0.6814 2023-11-16 22:57:02,203 - mmdet - INFO - Epoch [13][1300/1833] lr: 5.563e-06, eta: 10:18:00, time: 0.888, data_time: 0.036, memory: 10346, loss_rpn_cls: 0.0263, loss_rpn_bbox: 0.0358, loss_cls: 0.1741, acc: 93.5728, loss_bbox: 0.2255, loss_mask: 0.2255, loss: 0.6872 2023-11-16 22:57:46,430 - mmdet - INFO - Epoch [13][1350/1833] lr: 5.563e-06, eta: 10:17:19, time: 0.885, data_time: 0.037, memory: 10346, loss_rpn_cls: 0.0258, loss_rpn_bbox: 0.0357, loss_cls: 0.1746, acc: 93.5082, loss_bbox: 0.2240, loss_mask: 0.2252, loss: 0.6853 2023-11-16 22:58:30,230 - mmdet - INFO - Epoch [13][1400/1833] lr: 5.563e-06, eta: 10:16:36, time: 0.876, data_time: 0.032, memory: 10346, loss_rpn_cls: 0.0259, loss_rpn_bbox: 0.0347, loss_cls: 0.1683, acc: 93.8516, loss_bbox: 0.2183, loss_mask: 0.2253, loss: 0.6725 2023-11-16 22:59:14,797 - mmdet - INFO - Epoch [13][1450/1833] lr: 5.563e-06, eta: 10:15:54, time: 0.891, data_time: 0.034, memory: 10346, loss_rpn_cls: 0.0265, loss_rpn_bbox: 0.0369, loss_cls: 0.1773, acc: 93.4642, loss_bbox: 0.2294, loss_mask: 0.2287, loss: 0.6988 2023-11-16 22:59:58,417 - mmdet - INFO - Epoch [13][1500/1833] lr: 5.563e-06, eta: 10:15:11, time: 0.872, data_time: 0.032, memory: 10346, loss_rpn_cls: 0.0249, loss_rpn_bbox: 0.0340, loss_cls: 0.1716, acc: 93.6845, loss_bbox: 0.2194, loss_mask: 0.2256, loss: 0.6754 2023-11-16 23:00:42,512 - mmdet - INFO - Epoch [13][1550/1833] lr: 5.563e-06, eta: 10:14:29, time: 0.881, data_time: 0.033, memory: 10346, loss_rpn_cls: 0.0254, loss_rpn_bbox: 0.0345, loss_cls: 0.1677, acc: 93.8181, loss_bbox: 0.2158, loss_mask: 0.2224, loss: 0.6657 2023-11-16 23:01:26,555 - mmdet - INFO - Epoch [13][1600/1833] lr: 5.563e-06, eta: 10:13:47, time: 0.881, data_time: 0.032, memory: 10346, loss_rpn_cls: 0.0260, loss_rpn_bbox: 0.0348, loss_cls: 0.1721, acc: 93.6782, loss_bbox: 0.2210, loss_mask: 0.2231, loss: 0.6771 2023-11-16 23:02:10,799 - mmdet - INFO - Epoch [13][1650/1833] lr: 5.563e-06, eta: 10:13:05, time: 0.885, data_time: 0.036, memory: 10346, loss_rpn_cls: 0.0260, loss_rpn_bbox: 0.0353, loss_cls: 0.1713, acc: 93.6967, loss_bbox: 0.2195, loss_mask: 0.2247, loss: 0.6769 2023-11-16 23:02:54,601 - mmdet - INFO - Epoch [13][1700/1833] lr: 5.563e-06, eta: 10:12:22, time: 0.876, data_time: 0.032, memory: 10346, loss_rpn_cls: 0.0257, loss_rpn_bbox: 0.0352, loss_cls: 0.1699, acc: 93.7639, loss_bbox: 0.2183, loss_mask: 0.2243, loss: 0.6734 2023-11-16 23:03:38,217 - mmdet - INFO - Epoch [13][1750/1833] lr: 5.563e-06, eta: 10:11:39, time: 0.872, data_time: 0.034, memory: 10346, loss_rpn_cls: 0.0256, loss_rpn_bbox: 0.0358, loss_cls: 0.1733, acc: 93.6607, loss_bbox: 0.2245, loss_mask: 0.2253, loss: 0.6845 2023-11-16 23:04:22,594 - mmdet - INFO - Epoch [13][1800/1833] lr: 5.563e-06, eta: 10:10:57, time: 0.888, data_time: 0.033, memory: 10346, loss_rpn_cls: 0.0256, loss_rpn_bbox: 0.0358, loss_cls: 0.1730, acc: 93.6460, loss_bbox: 0.2250, loss_mask: 0.2271, loss: 0.6864 2023-11-16 23:04:52,044 - mmdet - INFO - Saving checkpoint at 13 epochs 2023-11-16 23:05:30,764 - mmdet - INFO - Evaluating bbox... 2023-11-16 23:06:02,229 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.481 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.713 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.532 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.342 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.522 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.621 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.609 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.609 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.609 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.463 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.651 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.748 2023-11-16 23:06:02,232 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.577 | bicycle | 0.388 | car | 0.487 | | motorcycle | 0.484 | airplane | 0.673 | bus | 0.684 | | train | 0.695 | truck | 0.448 | boat | 0.332 | | traffic light | 0.309 | fire hydrant | 0.720 | stop sign | 0.665 | | parking meter | 0.490 | bench | 0.300 | bird | 0.418 | | cat | 0.726 | dog | 0.702 | horse | 0.639 | | sheep | 0.591 | cow | 0.627 | elephant | 0.702 | | bear | 0.750 | zebra | 0.684 | giraffe | 0.685 | | backpack | 0.218 | umbrella | 0.442 | handbag | 0.238 | | tie | 0.366 | suitcase | 0.497 | frisbee | 0.722 | | skis | 0.281 | snowboard | 0.432 | sports ball | 0.480 | | kite | 0.469 | baseball bat | 0.418 | baseball glove | 0.430 | | skateboard | 0.577 | surfboard | 0.471 | tennis racket | 0.535 | | bottle | 0.468 | wine glass | 0.417 | cup | 0.508 | | fork | 0.463 | knife | 0.300 | spoon | 0.274 | | bowl | 0.487 | banana | 0.289 | apple | 0.264 | | sandwich | 0.481 | orange | 0.353 | broccoli | 0.264 | | carrot | 0.266 | hot dog | 0.486 | pizza | 0.558 | | donut | 0.560 | cake | 0.461 | chair | 0.352 | | couch | 0.496 | potted plant | 0.327 | bed | 0.494 | | dining table | 0.312 | toilet | 0.639 | tv | 0.621 | | laptop | 0.663 | mouse | 0.654 | remote | 0.439 | | keyboard | 0.534 | cell phone | 0.444 | microwave | 0.646 | | oven | 0.397 | toaster | 0.446 | sink | 0.426 | | refrigerator | 0.656 | book | 0.189 | clock | 0.552 | | vase | 0.430 | scissors | 0.419 | teddy bear | 0.552 | | hair drier | 0.191 | toothbrush | 0.321 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-16 23:06:02,232 - mmdet - INFO - Evaluating segm... 2023-11-16 23:06:37,054 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.434 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.678 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.471 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.252 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.475 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.625 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.555 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.555 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.555 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.387 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.601 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.712 2023-11-16 23:06:37,057 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.500 | bicycle | 0.226 | car | 0.442 | | motorcycle | 0.397 | airplane | 0.541 | bus | 0.675 | | train | 0.684 | truck | 0.447 | boat | 0.311 | | traffic light | 0.293 | fire hydrant | 0.699 | stop sign | 0.653 | | parking meter | 0.498 | bench | 0.228 | bird | 0.343 | | cat | 0.738 | dog | 0.659 | horse | 0.468 | | sheep | 0.526 | cow | 0.537 | elephant | 0.635 | | bear | 0.747 | zebra | 0.580 | giraffe | 0.546 | | backpack | 0.221 | umbrella | 0.502 | handbag | 0.225 | | tie | 0.342 | suitcase | 0.507 | frisbee | 0.667 | | skis | 0.042 | snowboard | 0.274 | sports ball | 0.457 | | kite | 0.330 | baseball bat | 0.317 | baseball glove | 0.470 | | skateboard | 0.365 | surfboard | 0.381 | tennis racket | 0.581 | | bottle | 0.448 | wine glass | 0.359 | cup | 0.503 | | fork | 0.241 | knife | 0.194 | spoon | 0.196 | | bowl | 0.453 | banana | 0.253 | apple | 0.269 | | sandwich | 0.501 | orange | 0.357 | broccoli | 0.246 | | carrot | 0.227 | hot dog | 0.383 | pizza | 0.535 | | donut | 0.563 | cake | 0.465 | chair | 0.252 | | couch | 0.421 | potted plant | 0.281 | bed | 0.402 | | dining table | 0.189 | toilet | 0.625 | tv | 0.654 | | laptop | 0.673 | mouse | 0.622 | remote | 0.391 | | keyboard | 0.544 | cell phone | 0.420 | microwave | 0.685 | | oven | 0.379 | toaster | 0.485 | sink | 0.419 | | refrigerator | 0.667 | book | 0.143 | clock | 0.550 | | vase | 0.425 | scissors | 0.318 | teddy bear | 0.525 | | hair drier | 0.199 | toothbrush | 0.198 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-16 23:06:37,590 - mmdet - INFO - The previous best checkpoint /mnt/petrelfs/lizhiqi/DINO/detection/work_dirs/mask_rcnn_flash_internimage_b_fpn_3x_cocoo_0.4_0.9_4x16/best_bbox_mAP_epoch_12.pth was removed 2023-11-16 23:06:41,418 - mmdet - INFO - Now best checkpoint is saved as best_bbox_mAP_epoch_13.pth. 2023-11-16 23:06:41,419 - mmdet - INFO - Best bbox_mAP is 0.4806 at 13 epoch. 2023-11-16 23:06:41,419 - mmdet - INFO - Exp name: mask_rcnn_flash_internimage_b_fpn_3x_coco_0.4_0.9-4x16.py 2023-11-16 23:06:41,419 - mmdet - INFO - Epoch(val) [13][313] bbox_mAP: 0.4806, bbox_mAP_50: 0.7125, bbox_mAP_75: 0.5323, bbox_mAP_s: 0.3417, bbox_mAP_m: 0.5222, bbox_mAP_l: 0.6209, bbox_mAP_copypaste: 0.4806 0.7125 0.5323 0.3417 0.5222 0.6209, segm_mAP: 0.4340, segm_mAP_50: 0.6776, segm_mAP_75: 0.4707, segm_mAP_s: 0.2519, segm_mAP_m: 0.4747, segm_mAP_l: 0.6247, segm_mAP_copypaste: 0.4340 0.6776 0.4707 0.2519 0.4747 0.6247 2023-11-16 23:07:28,156 - mmdet - INFO - Epoch [14][50/1833] lr: 5.563e-06, eta: 10:09:00, time: 0.934, data_time: 0.097, memory: 10346, loss_rpn_cls: 0.0239, loss_rpn_bbox: 0.0350, loss_cls: 0.1648, acc: 93.9005, loss_bbox: 0.2161, loss_mask: 0.2219, loss: 0.6617 2023-11-16 23:08:11,732 - mmdet - INFO - Epoch [14][100/1833] lr: 5.563e-06, eta: 10:08:17, time: 0.872, data_time: 0.035, memory: 10346, loss_rpn_cls: 0.0245, loss_rpn_bbox: 0.0354, loss_cls: 0.1709, acc: 93.6422, loss_bbox: 0.2237, loss_mask: 0.2248, loss: 0.6792 2023-11-16 23:08:56,175 - mmdet - INFO - Epoch [14][150/1833] lr: 5.563e-06, eta: 10:07:36, time: 0.889, data_time: 0.030, memory: 10346, loss_rpn_cls: 0.0247, loss_rpn_bbox: 0.0348, loss_cls: 0.1673, acc: 93.8138, loss_bbox: 0.2214, loss_mask: 0.2251, loss: 0.6732 2023-11-16 23:09:40,095 - mmdet - INFO - Epoch [14][200/1833] lr: 5.563e-06, eta: 10:06:53, time: 0.878, data_time: 0.038, memory: 10346, loss_rpn_cls: 0.0261, loss_rpn_bbox: 0.0353, loss_cls: 0.1671, acc: 93.8389, loss_bbox: 0.2169, loss_mask: 0.2215, loss: 0.6669 2023-11-16 23:10:24,340 - mmdet - INFO - Epoch [14][250/1833] lr: 5.563e-06, eta: 10:06:11, time: 0.885, data_time: 0.035, memory: 10346, loss_rpn_cls: 0.0263, loss_rpn_bbox: 0.0361, loss_cls: 0.1713, acc: 93.6967, loss_bbox: 0.2230, loss_mask: 0.2252, loss: 0.6818 2023-11-16 23:11:07,665 - mmdet - INFO - Epoch [14][300/1833] lr: 5.563e-06, eta: 10:05:28, time: 0.866, data_time: 0.034, memory: 10346, loss_rpn_cls: 0.0251, loss_rpn_bbox: 0.0345, loss_cls: 0.1697, acc: 93.7605, loss_bbox: 0.2213, loss_mask: 0.2203, loss: 0.6708 2023-11-16 23:11:51,291 - mmdet - INFO - Epoch [14][350/1833] lr: 5.563e-06, eta: 10:04:45, time: 0.873, data_time: 0.034, memory: 10346, loss_rpn_cls: 0.0264, loss_rpn_bbox: 0.0363, loss_cls: 0.1676, acc: 93.8102, loss_bbox: 0.2205, loss_mask: 0.2261, loss: 0.6769 2023-11-16 23:12:35,489 - mmdet - INFO - Epoch [14][400/1833] lr: 5.563e-06, eta: 10:04:03, time: 0.884, data_time: 0.034, memory: 10346, loss_rpn_cls: 0.0255, loss_rpn_bbox: 0.0356, loss_cls: 0.1735, acc: 93.5823, loss_bbox: 0.2242, loss_mask: 0.2262, loss: 0.6850 2023-11-16 23:13:19,193 - mmdet - INFO - Epoch [14][450/1833] lr: 5.563e-06, eta: 10:03:20, time: 0.873, data_time: 0.030, memory: 10346, loss_rpn_cls: 0.0247, loss_rpn_bbox: 0.0353, loss_cls: 0.1680, acc: 93.7597, loss_bbox: 0.2205, loss_mask: 0.2251, loss: 0.6737 2023-11-16 23:14:02,842 - mmdet - INFO - Epoch [14][500/1833] lr: 5.563e-06, eta: 10:02:37, time: 0.873, data_time: 0.039, memory: 10346, loss_rpn_cls: 0.0246, loss_rpn_bbox: 0.0339, loss_cls: 0.1660, acc: 93.8902, loss_bbox: 0.2157, loss_mask: 0.2231, loss: 0.6633 2023-11-16 23:14:46,236 - mmdet - INFO - Epoch [14][550/1833] lr: 5.563e-06, eta: 10:01:53, time: 0.868, data_time: 0.033, memory: 10346, loss_rpn_cls: 0.0247, loss_rpn_bbox: 0.0350, loss_cls: 0.1692, acc: 93.7245, loss_bbox: 0.2200, loss_mask: 0.2242, loss: 0.6732 2023-11-16 23:15:30,257 - mmdet - INFO - Epoch [14][600/1833] lr: 5.563e-06, eta: 10:01:11, time: 0.880, data_time: 0.031, memory: 10346, loss_rpn_cls: 0.0258, loss_rpn_bbox: 0.0360, loss_cls: 0.1685, acc: 93.7701, loss_bbox: 0.2195, loss_mask: 0.2231, loss: 0.6728 2023-11-16 23:16:14,690 - mmdet - INFO - Epoch [14][650/1833] lr: 5.563e-06, eta: 10:00:29, time: 0.889, data_time: 0.035, memory: 10346, loss_rpn_cls: 0.0273, loss_rpn_bbox: 0.0356, loss_cls: 0.1725, acc: 93.6351, loss_bbox: 0.2232, loss_mask: 0.2258, loss: 0.6844 2023-11-16 23:16:59,462 - mmdet - INFO - Epoch [14][700/1833] lr: 5.563e-06, eta: 9:59:48, time: 0.895, data_time: 0.035, memory: 10346, loss_rpn_cls: 0.0266, loss_rpn_bbox: 0.0376, loss_cls: 0.1743, acc: 93.5247, loss_bbox: 0.2266, loss_mask: 0.2235, loss: 0.6887 2023-11-16 23:17:43,075 - mmdet - INFO - Epoch [14][750/1833] lr: 5.563e-06, eta: 9:59:05, time: 0.872, data_time: 0.034, memory: 10346, loss_rpn_cls: 0.0253, loss_rpn_bbox: 0.0350, loss_cls: 0.1698, acc: 93.7068, loss_bbox: 0.2238, loss_mask: 0.2240, loss: 0.6780 2023-11-16 23:18:26,638 - mmdet - INFO - Epoch [14][800/1833] lr: 5.563e-06, eta: 9:58:22, time: 0.871, data_time: 0.041, memory: 10346, loss_rpn_cls: 0.0262, loss_rpn_bbox: 0.0357, loss_cls: 0.1702, acc: 93.7592, loss_bbox: 0.2193, loss_mask: 0.2243, loss: 0.6758 2023-11-16 23:19:10,430 - mmdet - INFO - Epoch [14][850/1833] lr: 5.563e-06, eta: 9:57:39, time: 0.876, data_time: 0.038, memory: 10346, loss_rpn_cls: 0.0266, loss_rpn_bbox: 0.0362, loss_cls: 0.1700, acc: 93.7516, loss_bbox: 0.2205, loss_mask: 0.2248, loss: 0.6781 2023-11-16 23:19:53,938 - mmdet - INFO - Epoch [14][900/1833] lr: 5.563e-06, eta: 9:56:56, time: 0.870, data_time: 0.038, memory: 10346, loss_rpn_cls: 0.0248, loss_rpn_bbox: 0.0342, loss_cls: 0.1624, acc: 94.0255, loss_bbox: 0.2140, loss_mask: 0.2231, loss: 0.6584 2023-11-16 23:20:37,612 - mmdet - INFO - Epoch [14][950/1833] lr: 5.563e-06, eta: 9:56:13, time: 0.874, data_time: 0.033, memory: 10346, loss_rpn_cls: 0.0244, loss_rpn_bbox: 0.0345, loss_cls: 0.1687, acc: 93.7560, loss_bbox: 0.2206, loss_mask: 0.2242, loss: 0.6724 2023-11-16 23:21:21,809 - mmdet - INFO - Epoch [14][1000/1833] lr: 5.563e-06, eta: 9:55:31, time: 0.884, data_time: 0.034, memory: 10346, loss_rpn_cls: 0.0252, loss_rpn_bbox: 0.0356, loss_cls: 0.1718, acc: 93.6716, loss_bbox: 0.2234, loss_mask: 0.2239, loss: 0.6800 2023-11-16 23:22:05,631 - mmdet - INFO - Epoch [14][1050/1833] lr: 5.563e-06, eta: 9:54:48, time: 0.876, data_time: 0.036, memory: 10346, loss_rpn_cls: 0.0257, loss_rpn_bbox: 0.0352, loss_cls: 0.1705, acc: 93.7062, loss_bbox: 0.2197, loss_mask: 0.2246, loss: 0.6757 2023-11-16 23:22:50,970 - mmdet - INFO - Epoch [14][1100/1833] lr: 5.563e-06, eta: 9:54:08, time: 0.907, data_time: 0.034, memory: 10346, loss_rpn_cls: 0.0252, loss_rpn_bbox: 0.0353, loss_cls: 0.1715, acc: 93.6982, loss_bbox: 0.2222, loss_mask: 0.2241, loss: 0.6784 2023-11-16 23:23:35,009 - mmdet - INFO - Epoch [14][1150/1833] lr: 5.563e-06, eta: 9:53:26, time: 0.881, data_time: 0.036, memory: 10346, loss_rpn_cls: 0.0245, loss_rpn_bbox: 0.0340, loss_cls: 0.1715, acc: 93.7002, loss_bbox: 0.2229, loss_mask: 0.2276, loss: 0.6805 2023-11-16 23:24:21,812 - mmdet - INFO - Epoch [14][1200/1833] lr: 5.563e-06, eta: 9:52:48, time: 0.936, data_time: 0.080, memory: 10346, loss_rpn_cls: 0.0265, loss_rpn_bbox: 0.0353, loss_cls: 0.1711, acc: 93.6608, loss_bbox: 0.2236, loss_mask: 0.2245, loss: 0.6809 2023-11-16 23:25:06,615 - mmdet - INFO - Epoch [14][1250/1833] lr: 5.563e-06, eta: 9:52:07, time: 0.896, data_time: 0.034, memory: 10346, loss_rpn_cls: 0.0250, loss_rpn_bbox: 0.0355, loss_cls: 0.1729, acc: 93.6302, loss_bbox: 0.2240, loss_mask: 0.2222, loss: 0.6796 2023-11-16 23:25:50,446 - mmdet - INFO - Epoch [14][1300/1833] lr: 5.563e-06, eta: 9:51:24, time: 0.877, data_time: 0.034, memory: 10346, loss_rpn_cls: 0.0268, loss_rpn_bbox: 0.0363, loss_cls: 0.1734, acc: 93.6186, loss_bbox: 0.2243, loss_mask: 0.2265, loss: 0.6873 2023-11-16 23:26:34,451 - mmdet - INFO - Epoch [14][1350/1833] lr: 5.563e-06, eta: 9:50:42, time: 0.880, data_time: 0.034, memory: 10346, loss_rpn_cls: 0.0257, loss_rpn_bbox: 0.0359, loss_cls: 0.1717, acc: 93.6509, loss_bbox: 0.2220, loss_mask: 0.2256, loss: 0.6809 2023-11-16 23:27:21,998 - mmdet - INFO - Epoch [14][1400/1833] lr: 5.563e-06, eta: 9:50:05, time: 0.951, data_time: 0.042, memory: 10346, loss_rpn_cls: 0.0257, loss_rpn_bbox: 0.0356, loss_cls: 0.1688, acc: 93.8004, loss_bbox: 0.2179, loss_mask: 0.2217, loss: 0.6698 2023-11-16 23:28:06,287 - mmdet - INFO - Epoch [14][1450/1833] lr: 5.563e-06, eta: 9:49:23, time: 0.886, data_time: 0.035, memory: 10346, loss_rpn_cls: 0.0250, loss_rpn_bbox: 0.0347, loss_cls: 0.1657, acc: 93.9467, loss_bbox: 0.2161, loss_mask: 0.2206, loss: 0.6621 2023-11-16 23:28:49,846 - mmdet - INFO - Epoch [14][1500/1833] lr: 5.563e-06, eta: 9:48:39, time: 0.871, data_time: 0.033, memory: 10346, loss_rpn_cls: 0.0242, loss_rpn_bbox: 0.0342, loss_cls: 0.1636, acc: 93.9584, loss_bbox: 0.2144, loss_mask: 0.2229, loss: 0.6593 2023-11-16 23:29:34,041 - mmdet - INFO - Epoch [14][1550/1833] lr: 5.563e-06, eta: 9:47:57, time: 0.883, data_time: 0.034, memory: 10346, loss_rpn_cls: 0.0249, loss_rpn_bbox: 0.0352, loss_cls: 0.1679, acc: 93.8334, loss_bbox: 0.2175, loss_mask: 0.2240, loss: 0.6695 2023-11-16 23:30:17,781 - mmdet - INFO - Epoch [14][1600/1833] lr: 5.563e-06, eta: 9:47:14, time: 0.875, data_time: 0.033, memory: 10346, loss_rpn_cls: 0.0253, loss_rpn_bbox: 0.0344, loss_cls: 0.1657, acc: 93.9340, loss_bbox: 0.2169, loss_mask: 0.2211, loss: 0.6633 2023-11-16 23:31:02,438 - mmdet - INFO - Epoch [14][1650/1833] lr: 5.563e-06, eta: 9:46:33, time: 0.893, data_time: 0.042, memory: 10346, loss_rpn_cls: 0.0246, loss_rpn_bbox: 0.0350, loss_cls: 0.1696, acc: 93.6893, loss_bbox: 0.2225, loss_mask: 0.2257, loss: 0.6774 2023-11-16 23:31:46,533 - mmdet - INFO - Epoch [14][1700/1833] lr: 5.563e-06, eta: 9:45:50, time: 0.882, data_time: 0.033, memory: 10346, loss_rpn_cls: 0.0253, loss_rpn_bbox: 0.0348, loss_cls: 0.1711, acc: 93.7355, loss_bbox: 0.2215, loss_mask: 0.2232, loss: 0.6759 2023-11-16 23:32:34,463 - mmdet - INFO - Epoch [14][1750/1833] lr: 5.563e-06, eta: 9:45:14, time: 0.959, data_time: 0.069, memory: 10346, loss_rpn_cls: 0.0254, loss_rpn_bbox: 0.0356, loss_cls: 0.1696, acc: 93.7892, loss_bbox: 0.2196, loss_mask: 0.2232, loss: 0.6734 2023-11-16 23:33:18,532 - mmdet - INFO - Epoch [14][1800/1833] lr: 5.563e-06, eta: 9:44:32, time: 0.881, data_time: 0.030, memory: 10346, loss_rpn_cls: 0.0240, loss_rpn_bbox: 0.0345, loss_cls: 0.1684, acc: 93.7739, loss_bbox: 0.2186, loss_mask: 0.2238, loss: 0.6693 2023-11-16 23:33:48,383 - mmdet - INFO - Saving checkpoint at 14 epochs 2023-11-16 23:34:27,715 - mmdet - INFO - Evaluating bbox... 2023-11-16 23:34:59,214 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.481 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.709 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.528 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.340 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.525 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.618 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.606 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.606 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.606 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.452 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.647 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.748 2023-11-16 23:34:59,217 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.577 | bicycle | 0.396 | car | 0.490 | | motorcycle | 0.483 | airplane | 0.691 | bus | 0.678 | | train | 0.695 | truck | 0.420 | boat | 0.332 | | traffic light | 0.296 | fire hydrant | 0.715 | stop sign | 0.684 | | parking meter | 0.542 | bench | 0.302 | bird | 0.415 | | cat | 0.739 | dog | 0.699 | horse | 0.640 | | sheep | 0.584 | cow | 0.629 | elephant | 0.706 | | bear | 0.725 | zebra | 0.691 | giraffe | 0.659 | | backpack | 0.222 | umbrella | 0.456 | handbag | 0.235 | | tie | 0.391 | suitcase | 0.485 | frisbee | 0.716 | | skis | 0.293 | snowboard | 0.434 | sports ball | 0.461 | | kite | 0.463 | baseball bat | 0.420 | baseball glove | 0.450 | | skateboard | 0.584 | surfboard | 0.473 | tennis racket | 0.557 | | bottle | 0.463 | wine glass | 0.407 | cup | 0.516 | | fork | 0.472 | knife | 0.305 | spoon | 0.261 | | bowl | 0.477 | banana | 0.294 | apple | 0.267 | | sandwich | 0.464 | orange | 0.360 | broccoli | 0.283 | | carrot | 0.265 | hot dog | 0.457 | pizza | 0.547 | | donut | 0.538 | cake | 0.457 | chair | 0.358 | | couch | 0.481 | potted plant | 0.339 | bed | 0.502 | | dining table | 0.319 | toilet | 0.656 | tv | 0.630 | | laptop | 0.679 | mouse | 0.636 | remote | 0.425 | | keyboard | 0.535 | cell phone | 0.450 | microwave | 0.653 | | oven | 0.414 | toaster | 0.420 | sink | 0.435 | | refrigerator | 0.663 | book | 0.184 | clock | 0.547 | | vase | 0.425 | scissors | 0.386 | teddy bear | 0.556 | | hair drier | 0.207 | toothbrush | 0.294 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-16 23:34:59,217 - mmdet - INFO - Evaluating segm... 2023-11-16 23:35:34,262 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.437 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.677 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.474 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.254 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.479 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.626 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.557 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.557 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.557 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.387 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.603 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.717 2023-11-16 23:35:34,265 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.504 | bicycle | 0.233 | car | 0.455 | | motorcycle | 0.398 | airplane | 0.557 | bus | 0.672 | | train | 0.681 | truck | 0.424 | boat | 0.315 | | traffic light | 0.292 | fire hydrant | 0.698 | stop sign | 0.662 | | parking meter | 0.528 | bench | 0.233 | bird | 0.348 | | cat | 0.737 | dog | 0.653 | horse | 0.468 | | sheep | 0.525 | cow | 0.545 | elephant | 0.643 | | bear | 0.720 | zebra | 0.600 | giraffe | 0.534 | | backpack | 0.221 | umbrella | 0.522 | handbag | 0.214 | | tie | 0.358 | suitcase | 0.512 | frisbee | 0.668 | | skis | 0.055 | snowboard | 0.296 | sports ball | 0.460 | | kite | 0.331 | baseball bat | 0.318 | baseball glove | 0.467 | | skateboard | 0.392 | surfboard | 0.395 | tennis racket | 0.596 | | bottle | 0.448 | wine glass | 0.367 | cup | 0.513 | | fork | 0.248 | knife | 0.207 | spoon | 0.212 | | bowl | 0.450 | banana | 0.260 | apple | 0.261 | | sandwich | 0.488 | orange | 0.363 | broccoli | 0.268 | | carrot | 0.233 | hot dog | 0.373 | pizza | 0.533 | | donut | 0.550 | cake | 0.469 | chair | 0.264 | | couch | 0.404 | potted plant | 0.293 | bed | 0.404 | | dining table | 0.173 | toilet | 0.647 | tv | 0.662 | | laptop | 0.683 | mouse | 0.627 | remote | 0.383 | | keyboard | 0.544 | cell phone | 0.432 | microwave | 0.684 | | oven | 0.385 | toaster | 0.461 | sink | 0.426 | | refrigerator | 0.682 | book | 0.138 | clock | 0.548 | | vase | 0.426 | scissors | 0.308 | teddy bear | 0.516 | | hair drier | 0.215 | toothbrush | 0.202 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-16 23:35:34,814 - mmdet - INFO - The previous best checkpoint /mnt/petrelfs/lizhiqi/DINO/detection/work_dirs/mask_rcnn_flash_internimage_b_fpn_3x_cocoo_0.4_0.9_4x16/best_bbox_mAP_epoch_13.pth was removed 2023-11-16 23:35:38,524 - mmdet - INFO - Now best checkpoint is saved as best_bbox_mAP_epoch_14.pth. 2023-11-16 23:35:38,525 - mmdet - INFO - Best bbox_mAP is 0.4807 at 14 epoch. 2023-11-16 23:35:38,525 - mmdet - INFO - Exp name: mask_rcnn_flash_internimage_b_fpn_3x_coco_0.4_0.9-4x16.py 2023-11-16 23:35:38,525 - mmdet - INFO - Epoch(val) [14][313] bbox_mAP: 0.4807, bbox_mAP_50: 0.7091, bbox_mAP_75: 0.5283, bbox_mAP_s: 0.3395, bbox_mAP_m: 0.5248, bbox_mAP_l: 0.6177, bbox_mAP_copypaste: 0.4807 0.7091 0.5283 0.3395 0.5248 0.6177, segm_mAP: 0.4373, segm_mAP_50: 0.6775, segm_mAP_75: 0.4743, segm_mAP_s: 0.2538, segm_mAP_m: 0.4788, segm_mAP_l: 0.6260, segm_mAP_copypaste: 0.4373 0.6775 0.4743 0.2538 0.4788 0.6260 2023-11-16 23:36:26,608 - mmdet - INFO - Epoch [15][50/1833] lr: 5.563e-06, eta: 9:42:42, time: 0.959, data_time: 0.094, memory: 10346, loss_rpn_cls: 0.0242, loss_rpn_bbox: 0.0356, loss_cls: 0.1664, acc: 93.8046, loss_bbox: 0.2198, loss_mask: 0.2212, loss: 0.6672 2023-11-16 23:37:10,318 - mmdet - INFO - Epoch [15][100/1833] lr: 5.563e-06, eta: 9:41:59, time: 0.874, data_time: 0.036, memory: 10346, loss_rpn_cls: 0.0247, loss_rpn_bbox: 0.0351, loss_cls: 0.1682, acc: 93.7491, loss_bbox: 0.2215, loss_mask: 0.2231, loss: 0.6725 2023-11-16 23:37:54,415 - mmdet - INFO - Epoch [15][150/1833] lr: 5.563e-06, eta: 9:41:16, time: 0.882, data_time: 0.032, memory: 10346, loss_rpn_cls: 0.0250, loss_rpn_bbox: 0.0356, loss_cls: 0.1684, acc: 93.7888, loss_bbox: 0.2215, loss_mask: 0.2214, loss: 0.6719 2023-11-16 23:38:38,601 - mmdet - INFO - Epoch [15][200/1833] lr: 5.563e-06, eta: 9:40:34, time: 0.884, data_time: 0.034, memory: 10346, loss_rpn_cls: 0.0245, loss_rpn_bbox: 0.0354, loss_cls: 0.1668, acc: 93.8371, loss_bbox: 0.2180, loss_mask: 0.2209, loss: 0.6656 2023-11-16 23:39:22,818 - mmdet - INFO - Epoch [15][250/1833] lr: 5.563e-06, eta: 9:39:52, time: 0.884, data_time: 0.033, memory: 10346, loss_rpn_cls: 0.0236, loss_rpn_bbox: 0.0341, loss_cls: 0.1671, acc: 93.7892, loss_bbox: 0.2174, loss_mask: 0.2214, loss: 0.6635 2023-11-16 23:40:06,754 - mmdet - INFO - Epoch [15][300/1833] lr: 5.563e-06, eta: 9:39:09, time: 0.878, data_time: 0.040, memory: 10346, loss_rpn_cls: 0.0240, loss_rpn_bbox: 0.0350, loss_cls: 0.1676, acc: 93.7842, loss_bbox: 0.2181, loss_mask: 0.2204, loss: 0.6651 2023-11-16 23:40:50,748 - mmdet - INFO - Epoch [15][350/1833] lr: 5.563e-06, eta: 9:38:27, time: 0.881, data_time: 0.037, memory: 10346, loss_rpn_cls: 0.0260, loss_rpn_bbox: 0.0363, loss_cls: 0.1686, acc: 93.7272, loss_bbox: 0.2226, loss_mask: 0.2237, loss: 0.6772 2023-11-16 23:41:34,518 - mmdet - INFO - Epoch [15][400/1833] lr: 5.563e-06, eta: 9:37:44, time: 0.875, data_time: 0.036, memory: 10346, loss_rpn_cls: 0.0240, loss_rpn_bbox: 0.0337, loss_cls: 0.1609, acc: 94.0555, loss_bbox: 0.2109, loss_mask: 0.2186, loss: 0.6482 2023-11-16 23:42:19,023 - mmdet - INFO - Epoch [15][450/1833] lr: 5.563e-06, eta: 9:37:02, time: 0.890, data_time: 0.040, memory: 10346, loss_rpn_cls: 0.0261, loss_rpn_bbox: 0.0358, loss_cls: 0.1697, acc: 93.7164, loss_bbox: 0.2221, loss_mask: 0.2254, loss: 0.6793 2023-11-16 23:43:02,920 - mmdet - INFO - Epoch [15][500/1833] lr: 5.563e-06, eta: 9:36:20, time: 0.878, data_time: 0.032, memory: 10346, loss_rpn_cls: 0.0241, loss_rpn_bbox: 0.0337, loss_cls: 0.1653, acc: 93.8797, loss_bbox: 0.2171, loss_mask: 0.2221, loss: 0.6623 2023-11-16 23:43:46,785 - mmdet - INFO - Epoch [15][550/1833] lr: 5.563e-06, eta: 9:35:37, time: 0.877, data_time: 0.036, memory: 10346, loss_rpn_cls: 0.0244, loss_rpn_bbox: 0.0344, loss_cls: 0.1705, acc: 93.6926, loss_bbox: 0.2199, loss_mask: 0.2225, loss: 0.6716 2023-11-16 23:44:30,800 - mmdet - INFO - Epoch [15][600/1833] lr: 5.563e-06, eta: 9:34:54, time: 0.880, data_time: 0.035, memory: 10346, loss_rpn_cls: 0.0248, loss_rpn_bbox: 0.0349, loss_cls: 0.1663, acc: 93.8246, loss_bbox: 0.2172, loss_mask: 0.2224, loss: 0.6656 2023-11-16 23:45:15,159 - mmdet - INFO - Epoch [15][650/1833] lr: 5.563e-06, eta: 9:34:12, time: 0.887, data_time: 0.037, memory: 10346, loss_rpn_cls: 0.0245, loss_rpn_bbox: 0.0349, loss_cls: 0.1635, acc: 93.9139, loss_bbox: 0.2151, loss_mask: 0.2202, loss: 0.6582 2023-11-16 23:45:59,176 - mmdet - INFO - Epoch [15][700/1833] lr: 5.563e-06, eta: 9:33:30, time: 0.880, data_time: 0.038, memory: 10346, loss_rpn_cls: 0.0251, loss_rpn_bbox: 0.0357, loss_cls: 0.1682, acc: 93.7746, loss_bbox: 0.2204, loss_mask: 0.2239, loss: 0.6733 2023-11-16 23:46:43,052 - mmdet - INFO - Epoch [15][750/1833] lr: 5.563e-06, eta: 9:32:47, time: 0.878, data_time: 0.038, memory: 10346, loss_rpn_cls: 0.0260, loss_rpn_bbox: 0.0363, loss_cls: 0.1721, acc: 93.6548, loss_bbox: 0.2227, loss_mask: 0.2231, loss: 0.6802 2023-11-16 23:47:26,984 - mmdet - INFO - Epoch [15][800/1833] lr: 5.563e-06, eta: 9:32:04, time: 0.879, data_time: 0.037, memory: 10346, loss_rpn_cls: 0.0251, loss_rpn_bbox: 0.0338, loss_cls: 0.1650, acc: 93.9119, loss_bbox: 0.2158, loss_mask: 0.2213, loss: 0.6610 2023-11-16 23:48:10,817 - mmdet - INFO - Epoch [15][850/1833] lr: 5.563e-06, eta: 9:31:22, time: 0.877, data_time: 0.036, memory: 10346, loss_rpn_cls: 0.0250, loss_rpn_bbox: 0.0354, loss_cls: 0.1685, acc: 93.8005, loss_bbox: 0.2186, loss_mask: 0.2246, loss: 0.6720 2023-11-16 23:48:54,544 - mmdet - INFO - Epoch [15][900/1833] lr: 5.563e-06, eta: 9:30:39, time: 0.874, data_time: 0.036, memory: 10346, loss_rpn_cls: 0.0244, loss_rpn_bbox: 0.0347, loss_cls: 0.1666, acc: 93.8491, loss_bbox: 0.2185, loss_mask: 0.2203, loss: 0.6645 2023-11-16 23:49:38,312 - mmdet - INFO - Epoch [15][950/1833] lr: 5.563e-06, eta: 9:29:56, time: 0.875, data_time: 0.035, memory: 10346, loss_rpn_cls: 0.0251, loss_rpn_bbox: 0.0357, loss_cls: 0.1672, acc: 93.8166, loss_bbox: 0.2200, loss_mask: 0.2214, loss: 0.6695 2023-11-16 23:50:22,219 - mmdet - INFO - Epoch [15][1000/1833] lr: 5.563e-06, eta: 9:29:13, time: 0.879, data_time: 0.033, memory: 10346, loss_rpn_cls: 0.0245, loss_rpn_bbox: 0.0344, loss_cls: 0.1640, acc: 93.9225, loss_bbox: 0.2157, loss_mask: 0.2207, loss: 0.6593 2023-11-16 23:51:06,535 - mmdet - INFO - Epoch [15][1050/1833] lr: 5.563e-06, eta: 9:28:31, time: 0.886, data_time: 0.037, memory: 10346, loss_rpn_cls: 0.0254, loss_rpn_bbox: 0.0349, loss_cls: 0.1675, acc: 93.8516, loss_bbox: 0.2169, loss_mask: 0.2227, loss: 0.6674 2023-11-16 23:51:50,611 - mmdet - INFO - Epoch [15][1100/1833] lr: 5.563e-06, eta: 9:27:48, time: 0.882, data_time: 0.035, memory: 10346, loss_rpn_cls: 0.0258, loss_rpn_bbox: 0.0347, loss_cls: 0.1695, acc: 93.7091, loss_bbox: 0.2194, loss_mask: 0.2227, loss: 0.6720 2023-11-16 23:52:34,830 - mmdet - INFO - Epoch [15][1150/1833] lr: 5.563e-06, eta: 9:27:06, time: 0.884, data_time: 0.033, memory: 10346, loss_rpn_cls: 0.0258, loss_rpn_bbox: 0.0352, loss_cls: 0.1669, acc: 93.8721, loss_bbox: 0.2168, loss_mask: 0.2222, loss: 0.6668 2023-11-16 23:53:18,999 - mmdet - INFO - Epoch [15][1200/1833] lr: 5.563e-06, eta: 9:26:24, time: 0.883, data_time: 0.033, memory: 10346, loss_rpn_cls: 0.0243, loss_rpn_bbox: 0.0353, loss_cls: 0.1661, acc: 93.8276, loss_bbox: 0.2182, loss_mask: 0.2235, loss: 0.6674 2023-11-16 23:54:02,959 - mmdet - INFO - Epoch [15][1250/1833] lr: 5.563e-06, eta: 9:25:41, time: 0.879, data_time: 0.033, memory: 10346, loss_rpn_cls: 0.0252, loss_rpn_bbox: 0.0357, loss_cls: 0.1684, acc: 93.7610, loss_bbox: 0.2207, loss_mask: 0.2261, loss: 0.6760 2023-11-16 23:54:46,577 - mmdet - INFO - Epoch [15][1300/1833] lr: 5.563e-06, eta: 9:24:58, time: 0.872, data_time: 0.030, memory: 10346, loss_rpn_cls: 0.0243, loss_rpn_bbox: 0.0350, loss_cls: 0.1651, acc: 93.9420, loss_bbox: 0.2153, loss_mask: 0.2205, loss: 0.6602 2023-11-16 23:55:30,847 - mmdet - INFO - Epoch [15][1350/1833] lr: 5.563e-06, eta: 9:24:16, time: 0.885, data_time: 0.031, memory: 10367, loss_rpn_cls: 0.0234, loss_rpn_bbox: 0.0336, loss_cls: 0.1625, acc: 93.9911, loss_bbox: 0.2147, loss_mask: 0.2212, loss: 0.6555 2023-11-16 23:56:14,647 - mmdet - INFO - Epoch [15][1400/1833] lr: 5.563e-06, eta: 9:23:33, time: 0.876, data_time: 0.032, memory: 10367, loss_rpn_cls: 0.0236, loss_rpn_bbox: 0.0337, loss_cls: 0.1655, acc: 93.8767, loss_bbox: 0.2170, loss_mask: 0.2214, loss: 0.6613 2023-11-16 23:56:58,492 - mmdet - INFO - Epoch [15][1450/1833] lr: 5.563e-06, eta: 9:22:50, time: 0.877, data_time: 0.033, memory: 10367, loss_rpn_cls: 0.0259, loss_rpn_bbox: 0.0358, loss_cls: 0.1688, acc: 93.7427, loss_bbox: 0.2211, loss_mask: 0.2244, loss: 0.6759 2023-11-16 23:57:42,633 - mmdet - INFO - Epoch [15][1500/1833] lr: 5.563e-06, eta: 9:22:08, time: 0.882, data_time: 0.040, memory: 10367, loss_rpn_cls: 0.0271, loss_rpn_bbox: 0.0357, loss_cls: 0.1699, acc: 93.6906, loss_bbox: 0.2232, loss_mask: 0.2231, loss: 0.6791 2023-11-16 23:58:26,716 - mmdet - INFO - Epoch [15][1550/1833] lr: 5.563e-06, eta: 9:21:25, time: 0.882, data_time: 0.034, memory: 10367, loss_rpn_cls: 0.0249, loss_rpn_bbox: 0.0351, loss_cls: 0.1685, acc: 93.8192, loss_bbox: 0.2213, loss_mask: 0.2241, loss: 0.6739 2023-11-16 23:59:10,327 - mmdet - INFO - Epoch [15][1600/1833] lr: 5.563e-06, eta: 9:20:42, time: 0.872, data_time: 0.038, memory: 10367, loss_rpn_cls: 0.0253, loss_rpn_bbox: 0.0351, loss_cls: 0.1678, acc: 93.8037, loss_bbox: 0.2178, loss_mask: 0.2226, loss: 0.6686 2023-11-16 23:59:53,819 - mmdet - INFO - Epoch [15][1650/1833] lr: 5.563e-06, eta: 9:19:59, time: 0.870, data_time: 0.035, memory: 10367, loss_rpn_cls: 0.0259, loss_rpn_bbox: 0.0361, loss_cls: 0.1695, acc: 93.7199, loss_bbox: 0.2198, loss_mask: 0.2225, loss: 0.6738 2023-11-17 00:00:37,656 - mmdet - INFO - Epoch [15][1700/1833] lr: 5.563e-06, eta: 9:19:16, time: 0.877, data_time: 0.033, memory: 10367, loss_rpn_cls: 0.0247, loss_rpn_bbox: 0.0346, loss_cls: 0.1661, acc: 93.8720, loss_bbox: 0.2155, loss_mask: 0.2195, loss: 0.6603 2023-11-17 00:01:22,331 - mmdet - INFO - Epoch [15][1750/1833] lr: 5.563e-06, eta: 9:18:34, time: 0.893, data_time: 0.034, memory: 10367, loss_rpn_cls: 0.0251, loss_rpn_bbox: 0.0348, loss_cls: 0.1676, acc: 93.7795, loss_bbox: 0.2193, loss_mask: 0.2219, loss: 0.6687 2023-11-17 00:02:06,210 - mmdet - INFO - Epoch [15][1800/1833] lr: 5.563e-06, eta: 9:17:51, time: 0.878, data_time: 0.036, memory: 10367, loss_rpn_cls: 0.0244, loss_rpn_bbox: 0.0355, loss_cls: 0.1696, acc: 93.7317, loss_bbox: 0.2212, loss_mask: 0.2256, loss: 0.6764 2023-11-17 00:02:35,841 - mmdet - INFO - Saving checkpoint at 15 epochs 2023-11-17 00:03:09,090 - mmdet - INFO - Evaluating bbox... 2023-11-17 00:03:42,377 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.484 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.714 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.537 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.341 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.526 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.620 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.614 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.614 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.614 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.467 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.656 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.752 2023-11-17 00:03:42,379 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.576 | bicycle | 0.389 | car | 0.494 | | motorcycle | 0.484 | airplane | 0.692 | bus | 0.693 | | train | 0.710 | truck | 0.445 | boat | 0.338 | | traffic light | 0.304 | fire hydrant | 0.722 | stop sign | 0.674 | | parking meter | 0.480 | bench | 0.296 | bird | 0.407 | | cat | 0.732 | dog | 0.689 | horse | 0.640 | | sheep | 0.594 | cow | 0.636 | elephant | 0.716 | | bear | 0.766 | zebra | 0.691 | giraffe | 0.695 | | backpack | 0.218 | umbrella | 0.462 | handbag | 0.244 | | tie | 0.388 | suitcase | 0.483 | frisbee | 0.709 | | skis | 0.292 | snowboard | 0.467 | sports ball | 0.482 | | kite | 0.469 | baseball bat | 0.433 | baseball glove | 0.443 | | skateboard | 0.582 | surfboard | 0.460 | tennis racket | 0.562 | | bottle | 0.459 | wine glass | 0.423 | cup | 0.518 | | fork | 0.456 | knife | 0.318 | spoon | 0.284 | | bowl | 0.469 | banana | 0.295 | apple | 0.274 | | sandwich | 0.437 | orange | 0.352 | broccoli | 0.283 | | carrot | 0.261 | hot dog | 0.471 | pizza | 0.549 | | donut | 0.535 | cake | 0.456 | chair | 0.361 | | couch | 0.472 | potted plant | 0.350 | bed | 0.503 | | dining table | 0.325 | toilet | 0.670 | tv | 0.635 | | laptop | 0.682 | mouse | 0.643 | remote | 0.422 | | keyboard | 0.542 | cell phone | 0.451 | microwave | 0.668 | | oven | 0.406 | toaster | 0.408 | sink | 0.460 | | refrigerator | 0.662 | book | 0.199 | clock | 0.546 | | vase | 0.426 | scissors | 0.456 | teddy bear | 0.544 | | hair drier | 0.198 | toothbrush | 0.306 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-17 00:03:42,379 - mmdet - INFO - Evaluating segm... 2023-11-17 00:04:16,863 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.434 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.679 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.466 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.246 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.478 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.624 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.557 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.557 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.557 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.389 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.603 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.713 2023-11-17 00:04:16,866 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.503 | bicycle | 0.226 | car | 0.448 | | motorcycle | 0.391 | airplane | 0.537 | bus | 0.680 | | train | 0.681 | truck | 0.436 | boat | 0.307 | | traffic light | 0.285 | fire hydrant | 0.701 | stop sign | 0.662 | | parking meter | 0.502 | bench | 0.229 | bird | 0.338 | | cat | 0.735 | dog | 0.655 | horse | 0.468 | | sheep | 0.532 | cow | 0.546 | elephant | 0.642 | | bear | 0.750 | zebra | 0.598 | giraffe | 0.539 | | backpack | 0.219 | umbrella | 0.518 | handbag | 0.227 | | tie | 0.361 | suitcase | 0.507 | frisbee | 0.663 | | skis | 0.033 | snowboard | 0.258 | sports ball | 0.456 | | kite | 0.336 | baseball bat | 0.290 | baseball glove | 0.459 | | skateboard | 0.374 | surfboard | 0.372 | tennis racket | 0.574 | | bottle | 0.433 | wine glass | 0.376 | cup | 0.515 | | fork | 0.241 | knife | 0.202 | spoon | 0.207 | | bowl | 0.442 | banana | 0.254 | apple | 0.270 | | sandwich | 0.459 | orange | 0.354 | broccoli | 0.260 | | carrot | 0.224 | hot dog | 0.374 | pizza | 0.526 | | donut | 0.558 | cake | 0.474 | chair | 0.256 | | couch | 0.412 | potted plant | 0.299 | bed | 0.386 | | dining table | 0.183 | toilet | 0.647 | tv | 0.661 | | laptop | 0.678 | mouse | 0.629 | remote | 0.379 | | keyboard | 0.547 | cell phone | 0.426 | microwave | 0.688 | | oven | 0.387 | toaster | 0.440 | sink | 0.436 | | refrigerator | 0.691 | book | 0.148 | clock | 0.543 | | vase | 0.420 | scissors | 0.317 | teddy bear | 0.517 | | hair drier | 0.223 | toothbrush | 0.226 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-17 00:04:17,467 - mmdet - INFO - The previous best checkpoint /mnt/petrelfs/lizhiqi/DINO/detection/work_dirs/mask_rcnn_flash_internimage_b_fpn_3x_cocoo_0.4_0.9_4x16/best_bbox_mAP_epoch_14.pth was removed 2023-11-17 00:04:23,118 - mmdet - INFO - Now best checkpoint is saved as best_bbox_mAP_epoch_15.pth. 2023-11-17 00:04:23,118 - mmdet - INFO - Best bbox_mAP is 0.4841 at 15 epoch. 2023-11-17 00:04:23,118 - mmdet - INFO - Exp name: mask_rcnn_flash_internimage_b_fpn_3x_coco_0.4_0.9-4x16.py 2023-11-17 00:04:23,118 - mmdet - INFO - Epoch(val) [15][313] bbox_mAP: 0.4841, bbox_mAP_50: 0.7139, bbox_mAP_75: 0.5371, bbox_mAP_s: 0.3414, bbox_mAP_m: 0.5262, bbox_mAP_l: 0.6200, bbox_mAP_copypaste: 0.4841 0.7139 0.5371 0.3414 0.5262 0.6200, segm_mAP: 0.4343, segm_mAP_50: 0.6788, segm_mAP_75: 0.4659, segm_mAP_s: 0.2456, segm_mAP_m: 0.4779, segm_mAP_l: 0.6244, segm_mAP_copypaste: 0.4343 0.6788 0.4659 0.2456 0.4779 0.6244 2023-11-17 00:05:09,709 - mmdet - INFO - Epoch [16][50/1833] lr: 5.563e-06, eta: 9:16:03, time: 0.931, data_time: 0.098, memory: 10367, loss_rpn_cls: 0.0250, loss_rpn_bbox: 0.0344, loss_cls: 0.1626, acc: 93.9581, loss_bbox: 0.2148, loss_mask: 0.2202, loss: 0.6571 2023-11-17 00:05:53,728 - mmdet - INFO - Epoch [16][100/1833] lr: 5.563e-06, eta: 9:15:21, time: 0.880, data_time: 0.035, memory: 10367, loss_rpn_cls: 0.0255, loss_rpn_bbox: 0.0352, loss_cls: 0.1634, acc: 93.9355, loss_bbox: 0.2165, loss_mask: 0.2204, loss: 0.6611 2023-11-17 00:06:38,373 - mmdet - INFO - Epoch [16][150/1833] lr: 5.563e-06, eta: 9:14:39, time: 0.893, data_time: 0.033, memory: 10367, loss_rpn_cls: 0.0243, loss_rpn_bbox: 0.0346, loss_cls: 0.1626, acc: 93.9753, loss_bbox: 0.2132, loss_mask: 0.2207, loss: 0.6554 2023-11-17 00:07:22,276 - mmdet - INFO - Epoch [16][200/1833] lr: 5.563e-06, eta: 9:13:57, time: 0.878, data_time: 0.032, memory: 10367, loss_rpn_cls: 0.0241, loss_rpn_bbox: 0.0343, loss_cls: 0.1639, acc: 93.9043, loss_bbox: 0.2181, loss_mask: 0.2177, loss: 0.6581 2023-11-17 00:08:06,770 - mmdet - INFO - Epoch [16][250/1833] lr: 5.563e-06, eta: 9:13:15, time: 0.889, data_time: 0.038, memory: 10367, loss_rpn_cls: 0.0238, loss_rpn_bbox: 0.0337, loss_cls: 0.1622, acc: 94.0197, loss_bbox: 0.2148, loss_mask: 0.2174, loss: 0.6520 2023-11-17 00:08:50,818 - mmdet - INFO - Epoch [16][300/1833] lr: 5.563e-06, eta: 9:12:32, time: 0.882, data_time: 0.034, memory: 10367, loss_rpn_cls: 0.0256, loss_rpn_bbox: 0.0355, loss_cls: 0.1696, acc: 93.6864, loss_bbox: 0.2241, loss_mask: 0.2234, loss: 0.6782 2023-11-17 00:09:34,646 - mmdet - INFO - Epoch [16][350/1833] lr: 5.563e-06, eta: 9:11:49, time: 0.876, data_time: 0.036, memory: 10367, loss_rpn_cls: 0.0242, loss_rpn_bbox: 0.0348, loss_cls: 0.1661, acc: 93.8286, loss_bbox: 0.2175, loss_mask: 0.2203, loss: 0.6630 2023-11-17 00:10:18,893 - mmdet - INFO - Epoch [16][400/1833] lr: 5.563e-06, eta: 9:11:07, time: 0.885, data_time: 0.035, memory: 10367, loss_rpn_cls: 0.0240, loss_rpn_bbox: 0.0347, loss_cls: 0.1632, acc: 93.9494, loss_bbox: 0.2162, loss_mask: 0.2225, loss: 0.6606 2023-11-17 00:11:03,157 - mmdet - INFO - Epoch [16][450/1833] lr: 5.563e-06, eta: 9:10:25, time: 0.885, data_time: 0.034, memory: 10367, loss_rpn_cls: 0.0253, loss_rpn_bbox: 0.0354, loss_cls: 0.1689, acc: 93.7435, loss_bbox: 0.2205, loss_mask: 0.2230, loss: 0.6730 2023-11-17 00:11:47,428 - mmdet - INFO - Epoch [16][500/1833] lr: 5.563e-06, eta: 9:09:43, time: 0.885, data_time: 0.034, memory: 10367, loss_rpn_cls: 0.0240, loss_rpn_bbox: 0.0349, loss_cls: 0.1645, acc: 93.9035, loss_bbox: 0.2173, loss_mask: 0.2204, loss: 0.6611 2023-11-17 00:12:31,667 - mmdet - INFO - Epoch [16][550/1833] lr: 5.563e-06, eta: 9:09:00, time: 0.885, data_time: 0.028, memory: 10367, loss_rpn_cls: 0.0238, loss_rpn_bbox: 0.0351, loss_cls: 0.1703, acc: 93.7298, loss_bbox: 0.2225, loss_mask: 0.2230, loss: 0.6749 2023-11-17 00:13:15,971 - mmdet - INFO - Epoch [16][600/1833] lr: 5.563e-06, eta: 9:08:18, time: 0.886, data_time: 0.030, memory: 10367, loss_rpn_cls: 0.0238, loss_rpn_bbox: 0.0345, loss_cls: 0.1654, acc: 93.8426, loss_bbox: 0.2184, loss_mask: 0.2207, loss: 0.6627 2023-11-17 00:14:00,113 - mmdet - INFO - Epoch [16][650/1833] lr: 5.563e-06, eta: 9:07:36, time: 0.883, data_time: 0.038, memory: 10367, loss_rpn_cls: 0.0249, loss_rpn_bbox: 0.0358, loss_cls: 0.1678, acc: 93.7783, loss_bbox: 0.2198, loss_mask: 0.2186, loss: 0.6669 2023-11-17 00:14:43,763 - mmdet - INFO - Epoch [16][700/1833] lr: 5.563e-06, eta: 9:06:53, time: 0.873, data_time: 0.035, memory: 10367, loss_rpn_cls: 0.0248, loss_rpn_bbox: 0.0356, loss_cls: 0.1631, acc: 93.9146, loss_bbox: 0.2146, loss_mask: 0.2218, loss: 0.6600 2023-11-17 00:15:27,823 - mmdet - INFO - Epoch [16][750/1833] lr: 5.563e-06, eta: 9:06:10, time: 0.881, data_time: 0.033, memory: 10367, loss_rpn_cls: 0.0246, loss_rpn_bbox: 0.0344, loss_cls: 0.1677, acc: 93.7782, loss_bbox: 0.2197, loss_mask: 0.2221, loss: 0.6685 2023-11-17 00:16:11,049 - mmdet - INFO - Epoch [16][800/1833] lr: 5.563e-06, eta: 9:05:26, time: 0.864, data_time: 0.036, memory: 10367, loss_rpn_cls: 0.0250, loss_rpn_bbox: 0.0349, loss_cls: 0.1699, acc: 93.7181, loss_bbox: 0.2229, loss_mask: 0.2217, loss: 0.6743 2023-11-17 00:16:55,025 - mmdet - INFO - Epoch [16][850/1833] lr: 5.563e-06, eta: 9:04:44, time: 0.880, data_time: 0.037, memory: 10367, loss_rpn_cls: 0.0237, loss_rpn_bbox: 0.0348, loss_cls: 0.1662, acc: 93.8195, loss_bbox: 0.2199, loss_mask: 0.2223, loss: 0.6669 2023-11-17 00:17:38,719 - mmdet - INFO - Epoch [16][900/1833] lr: 5.563e-06, eta: 9:04:01, time: 0.873, data_time: 0.032, memory: 10367, loss_rpn_cls: 0.0261, loss_rpn_bbox: 0.0356, loss_cls: 0.1655, acc: 93.9207, loss_bbox: 0.2153, loss_mask: 0.2217, loss: 0.6643 2023-11-17 00:18:22,605 - mmdet - INFO - Epoch [16][950/1833] lr: 5.563e-06, eta: 9:03:18, time: 0.878, data_time: 0.035, memory: 10367, loss_rpn_cls: 0.0241, loss_rpn_bbox: 0.0348, loss_cls: 0.1619, acc: 93.9910, loss_bbox: 0.2129, loss_mask: 0.2182, loss: 0.6518 2023-11-17 00:19:06,866 - mmdet - INFO - Epoch [16][1000/1833] lr: 5.563e-06, eta: 9:02:36, time: 0.885, data_time: 0.034, memory: 10367, loss_rpn_cls: 0.0261, loss_rpn_bbox: 0.0363, loss_cls: 0.1685, acc: 93.7816, loss_bbox: 0.2209, loss_mask: 0.2234, loss: 0.6752 2023-11-17 00:19:50,769 - mmdet - INFO - Epoch [16][1050/1833] lr: 5.563e-06, eta: 9:01:53, time: 0.877, data_time: 0.039, memory: 10367, loss_rpn_cls: 0.0247, loss_rpn_bbox: 0.0348, loss_cls: 0.1623, acc: 93.9677, loss_bbox: 0.2139, loss_mask: 0.2192, loss: 0.6550 2023-11-17 00:20:35,143 - mmdet - INFO - Epoch [16][1100/1833] lr: 5.563e-06, eta: 9:01:11, time: 0.888, data_time: 0.037, memory: 10367, loss_rpn_cls: 0.0237, loss_rpn_bbox: 0.0336, loss_cls: 0.1620, acc: 94.0184, loss_bbox: 0.2139, loss_mask: 0.2186, loss: 0.6518 2023-11-17 00:21:19,229 - mmdet - INFO - Epoch [16][1150/1833] lr: 5.563e-06, eta: 9:00:28, time: 0.882, data_time: 0.032, memory: 10367, loss_rpn_cls: 0.0238, loss_rpn_bbox: 0.0336, loss_cls: 0.1601, acc: 94.0718, loss_bbox: 0.2110, loss_mask: 0.2181, loss: 0.6467 2023-11-17 00:22:03,668 - mmdet - INFO - Epoch [16][1200/1833] lr: 5.563e-06, eta: 8:59:46, time: 0.889, data_time: 0.035, memory: 10367, loss_rpn_cls: 0.0246, loss_rpn_bbox: 0.0350, loss_cls: 0.1649, acc: 93.8444, loss_bbox: 0.2165, loss_mask: 0.2208, loss: 0.6618 2023-11-17 00:22:47,476 - mmdet - INFO - Epoch [16][1250/1833] lr: 5.563e-06, eta: 8:59:03, time: 0.876, data_time: 0.035, memory: 10367, loss_rpn_cls: 0.0251, loss_rpn_bbox: 0.0349, loss_cls: 0.1642, acc: 93.9564, loss_bbox: 0.2168, loss_mask: 0.2214, loss: 0.6624 2023-11-17 00:23:30,752 - mmdet - INFO - Epoch [16][1300/1833] lr: 5.563e-06, eta: 8:58:19, time: 0.866, data_time: 0.032, memory: 10367, loss_rpn_cls: 0.0255, loss_rpn_bbox: 0.0357, loss_cls: 0.1665, acc: 93.8298, loss_bbox: 0.2197, loss_mask: 0.2232, loss: 0.6705 2023-11-17 00:24:14,319 - mmdet - INFO - Epoch [16][1350/1833] lr: 5.563e-06, eta: 8:57:36, time: 0.871, data_time: 0.031, memory: 10367, loss_rpn_cls: 0.0238, loss_rpn_bbox: 0.0344, loss_cls: 0.1629, acc: 94.0031, loss_bbox: 0.2126, loss_mask: 0.2203, loss: 0.6540 2023-11-17 00:25:00,454 - mmdet - INFO - Epoch [16][1400/1833] lr: 5.563e-06, eta: 8:56:56, time: 0.923, data_time: 0.038, memory: 10367, loss_rpn_cls: 0.0251, loss_rpn_bbox: 0.0345, loss_cls: 0.1691, acc: 93.7769, loss_bbox: 0.2193, loss_mask: 0.2260, loss: 0.6740 2023-11-17 00:25:44,280 - mmdet - INFO - Epoch [16][1450/1833] lr: 5.563e-06, eta: 8:56:13, time: 0.877, data_time: 0.034, memory: 10707, loss_rpn_cls: 0.0239, loss_rpn_bbox: 0.0346, loss_cls: 0.1667, acc: 93.8373, loss_bbox: 0.2164, loss_mask: 0.2195, loss: 0.6611 2023-11-17 00:26:28,140 - mmdet - INFO - Epoch [16][1500/1833] lr: 5.563e-06, eta: 8:55:31, time: 0.877, data_time: 0.034, memory: 10707, loss_rpn_cls: 0.0242, loss_rpn_bbox: 0.0345, loss_cls: 0.1658, acc: 93.8329, loss_bbox: 0.2184, loss_mask: 0.2237, loss: 0.6667 2023-11-17 00:27:12,928 - mmdet - INFO - Epoch [16][1550/1833] lr: 5.563e-06, eta: 8:54:49, time: 0.895, data_time: 0.034, memory: 10707, loss_rpn_cls: 0.0240, loss_rpn_bbox: 0.0356, loss_cls: 0.1716, acc: 93.5668, loss_bbox: 0.2209, loss_mask: 0.2232, loss: 0.6752 2023-11-17 00:27:56,860 - mmdet - INFO - Epoch [16][1600/1833] lr: 5.563e-06, eta: 8:54:06, time: 0.879, data_time: 0.043, memory: 10707, loss_rpn_cls: 0.0243, loss_rpn_bbox: 0.0352, loss_cls: 0.1678, acc: 93.7835, loss_bbox: 0.2196, loss_mask: 0.2206, loss: 0.6675 2023-11-17 00:28:40,671 - mmdet - INFO - Epoch [16][1650/1833] lr: 5.563e-06, eta: 8:53:23, time: 0.876, data_time: 0.035, memory: 10707, loss_rpn_cls: 0.0245, loss_rpn_bbox: 0.0349, loss_cls: 0.1698, acc: 93.7390, loss_bbox: 0.2209, loss_mask: 0.2207, loss: 0.6708 2023-11-17 00:29:24,381 - mmdet - INFO - Epoch [16][1700/1833] lr: 5.563e-06, eta: 8:52:40, time: 0.874, data_time: 0.033, memory: 10707, loss_rpn_cls: 0.0250, loss_rpn_bbox: 0.0344, loss_cls: 0.1683, acc: 93.7932, loss_bbox: 0.2201, loss_mask: 0.2210, loss: 0.6688 2023-11-17 00:30:08,115 - mmdet - INFO - Epoch [16][1750/1833] lr: 5.563e-06, eta: 8:51:57, time: 0.874, data_time: 0.030, memory: 10707, loss_rpn_cls: 0.0249, loss_rpn_bbox: 0.0343, loss_cls: 0.1660, acc: 93.8671, loss_bbox: 0.2156, loss_mask: 0.2218, loss: 0.6626 2023-11-17 00:30:51,770 - mmdet - INFO - Epoch [16][1800/1833] lr: 5.563e-06, eta: 8:51:14, time: 0.873, data_time: 0.031, memory: 10707, loss_rpn_cls: 0.0239, loss_rpn_bbox: 0.0346, loss_cls: 0.1641, acc: 93.9769, loss_bbox: 0.2150, loss_mask: 0.2192, loss: 0.6567 2023-11-17 00:31:21,686 - mmdet - INFO - Saving checkpoint at 16 epochs 2023-11-17 00:31:56,138 - mmdet - INFO - Evaluating bbox... 2023-11-17 00:32:26,825 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.488 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.717 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.539 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.351 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.532 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.628 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.610 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.610 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.610 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.460 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.655 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.747 2023-11-17 00:32:26,827 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.577 | bicycle | 0.392 | car | 0.493 | | motorcycle | 0.493 | airplane | 0.673 | bus | 0.684 | | train | 0.694 | truck | 0.448 | boat | 0.341 | | traffic light | 0.317 | fire hydrant | 0.723 | stop sign | 0.666 | | parking meter | 0.523 | bench | 0.309 | bird | 0.415 | | cat | 0.726 | dog | 0.696 | horse | 0.638 | | sheep | 0.587 | cow | 0.646 | elephant | 0.700 | | bear | 0.779 | zebra | 0.693 | giraffe | 0.681 | | backpack | 0.217 | umbrella | 0.450 | handbag | 0.244 | | tie | 0.385 | suitcase | 0.495 | frisbee | 0.717 | | skis | 0.298 | snowboard | 0.442 | sports ball | 0.488 | | kite | 0.484 | baseball bat | 0.431 | baseball glove | 0.441 | | skateboard | 0.593 | surfboard | 0.487 | tennis racket | 0.544 | | bottle | 0.471 | wine glass | 0.419 | cup | 0.524 | | fork | 0.468 | knife | 0.322 | spoon | 0.284 | | bowl | 0.468 | banana | 0.301 | apple | 0.262 | | sandwich | 0.471 | orange | 0.361 | broccoli | 0.276 | | carrot | 0.274 | hot dog | 0.482 | pizza | 0.568 | | donut | 0.572 | cake | 0.471 | chair | 0.368 | | couch | 0.461 | potted plant | 0.341 | bed | 0.488 | | dining table | 0.321 | toilet | 0.653 | tv | 0.640 | | laptop | 0.673 | mouse | 0.651 | remote | 0.434 | | keyboard | 0.534 | cell phone | 0.463 | microwave | 0.655 | | oven | 0.423 | toaster | 0.497 | sink | 0.445 | | refrigerator | 0.665 | book | 0.189 | clock | 0.550 | | vase | 0.426 | scissors | 0.433 | teddy bear | 0.555 | | hair drier | 0.226 | toothbrush | 0.308 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-17 00:32:26,828 - mmdet - INFO - Evaluating segm... 2023-11-17 00:33:01,105 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.439 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.685 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.473 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.259 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.480 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.631 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.557 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.557 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.557 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.388 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.605 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.715 2023-11-17 00:33:01,108 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.502 | bicycle | 0.233 | car | 0.449 | | motorcycle | 0.400 | airplane | 0.531 | bus | 0.673 | | train | 0.680 | truck | 0.441 | boat | 0.311 | | traffic light | 0.300 | fire hydrant | 0.699 | stop sign | 0.654 | | parking meter | 0.529 | bench | 0.231 | bird | 0.339 | | cat | 0.734 | dog | 0.663 | horse | 0.467 | | sheep | 0.525 | cow | 0.541 | elephant | 0.635 | | bear | 0.765 | zebra | 0.581 | giraffe | 0.529 | | backpack | 0.208 | umbrella | 0.520 | handbag | 0.240 | | tie | 0.356 | suitcase | 0.508 | frisbee | 0.658 | | skis | 0.057 | snowboard | 0.293 | sports ball | 0.464 | | kite | 0.327 | baseball bat | 0.293 | baseball glove | 0.462 | | skateboard | 0.376 | surfboard | 0.398 | tennis racket | 0.583 | | bottle | 0.443 | wine glass | 0.375 | cup | 0.516 | | fork | 0.253 | knife | 0.212 | spoon | 0.207 | | bowl | 0.436 | banana | 0.257 | apple | 0.265 | | sandwich | 0.497 | orange | 0.358 | broccoli | 0.263 | | carrot | 0.231 | hot dog | 0.372 | pizza | 0.544 | | donut | 0.574 | cake | 0.479 | chair | 0.264 | | couch | 0.404 | potted plant | 0.291 | bed | 0.404 | | dining table | 0.194 | toilet | 0.638 | tv | 0.674 | | laptop | 0.688 | mouse | 0.614 | remote | 0.386 | | keyboard | 0.515 | cell phone | 0.443 | microwave | 0.689 | | oven | 0.390 | toaster | 0.537 | sink | 0.435 | | refrigerator | 0.687 | book | 0.139 | clock | 0.539 | | vase | 0.432 | scissors | 0.311 | teddy bear | 0.535 | | hair drier | 0.258 | toothbrush | 0.221 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-17 00:33:01,643 - mmdet - INFO - The previous best checkpoint /mnt/petrelfs/lizhiqi/DINO/detection/work_dirs/mask_rcnn_flash_internimage_b_fpn_3x_cocoo_0.4_0.9_4x16/best_bbox_mAP_epoch_15.pth was removed 2023-11-17 00:33:05,452 - mmdet - INFO - Now best checkpoint is saved as best_bbox_mAP_epoch_16.pth. 2023-11-17 00:33:05,452 - mmdet - INFO - Best bbox_mAP is 0.4876 at 16 epoch. 2023-11-17 00:33:05,452 - mmdet - INFO - Exp name: mask_rcnn_flash_internimage_b_fpn_3x_coco_0.4_0.9-4x16.py 2023-11-17 00:33:05,452 - mmdet - INFO - Epoch(val) [16][313] bbox_mAP: 0.4876, bbox_mAP_50: 0.7170, bbox_mAP_75: 0.5389, bbox_mAP_s: 0.3508, bbox_mAP_m: 0.5325, bbox_mAP_l: 0.6282, bbox_mAP_copypaste: 0.4876 0.7170 0.5389 0.3508 0.5325 0.6282, segm_mAP: 0.4391, segm_mAP_50: 0.6848, segm_mAP_75: 0.4727, segm_mAP_s: 0.2592, segm_mAP_m: 0.4804, segm_mAP_l: 0.6308, segm_mAP_copypaste: 0.4391 0.6848 0.4727 0.2592 0.4804 0.6308 2023-11-17 00:33:51,930 - mmdet - INFO - Epoch [17][50/1833] lr: 5.563e-06, eta: 8:49:30, time: 0.929, data_time: 0.093, memory: 10707, loss_rpn_cls: 0.0225, loss_rpn_bbox: 0.0325, loss_cls: 0.1579, acc: 94.0919, loss_bbox: 0.2098, loss_mask: 0.2173, loss: 0.6401 2023-11-17 00:34:36,048 - mmdet - INFO - Epoch [17][100/1833] lr: 5.563e-06, eta: 8:48:47, time: 0.882, data_time: 0.034, memory: 10707, loss_rpn_cls: 0.0251, loss_rpn_bbox: 0.0350, loss_cls: 0.1679, acc: 93.7750, loss_bbox: 0.2200, loss_mask: 0.2207, loss: 0.6687 2023-11-17 00:35:19,727 - mmdet - INFO - Epoch [17][150/1833] lr: 5.563e-06, eta: 8:48:04, time: 0.873, data_time: 0.039, memory: 10707, loss_rpn_cls: 0.0231, loss_rpn_bbox: 0.0345, loss_cls: 0.1610, acc: 94.0114, loss_bbox: 0.2138, loss_mask: 0.2172, loss: 0.6496 2023-11-17 00:36:03,667 - mmdet - INFO - Epoch [17][200/1833] lr: 5.563e-06, eta: 8:47:21, time: 0.879, data_time: 0.035, memory: 10707, loss_rpn_cls: 0.0236, loss_rpn_bbox: 0.0346, loss_cls: 0.1654, acc: 93.8312, loss_bbox: 0.2177, loss_mask: 0.2213, loss: 0.6626 2023-11-17 00:36:47,770 - mmdet - INFO - Epoch [17][250/1833] lr: 5.563e-06, eta: 8:46:39, time: 0.882, data_time: 0.031, memory: 10707, loss_rpn_cls: 0.0250, loss_rpn_bbox: 0.0342, loss_cls: 0.1655, acc: 93.8318, loss_bbox: 0.2188, loss_mask: 0.2210, loss: 0.6645 2023-11-17 00:37:31,869 - mmdet - INFO - Epoch [17][300/1833] lr: 5.563e-06, eta: 8:45:56, time: 0.882, data_time: 0.037, memory: 10707, loss_rpn_cls: 0.0259, loss_rpn_bbox: 0.0357, loss_cls: 0.1673, acc: 93.7631, loss_bbox: 0.2190, loss_mask: 0.2211, loss: 0.6690 2023-11-17 00:38:15,667 - mmdet - INFO - Epoch [17][350/1833] lr: 5.563e-06, eta: 8:45:14, time: 0.876, data_time: 0.031, memory: 10707, loss_rpn_cls: 0.0244, loss_rpn_bbox: 0.0349, loss_cls: 0.1628, acc: 93.9520, loss_bbox: 0.2150, loss_mask: 0.2193, loss: 0.6564 2023-11-17 00:38:59,716 - mmdet - INFO - Epoch [17][400/1833] lr: 5.563e-06, eta: 8:44:31, time: 0.881, data_time: 0.033, memory: 10707, loss_rpn_cls: 0.0235, loss_rpn_bbox: 0.0336, loss_cls: 0.1616, acc: 93.9586, loss_bbox: 0.2135, loss_mask: 0.2170, loss: 0.6493 2023-11-17 00:39:43,933 - mmdet - INFO - Epoch [17][450/1833] lr: 5.563e-06, eta: 8:43:49, time: 0.884, data_time: 0.034, memory: 10707, loss_rpn_cls: 0.0243, loss_rpn_bbox: 0.0344, loss_cls: 0.1628, acc: 93.9309, loss_bbox: 0.2143, loss_mask: 0.2180, loss: 0.6538 2023-11-17 00:40:27,834 - mmdet - INFO - Epoch [17][500/1833] lr: 5.563e-06, eta: 8:43:06, time: 0.878, data_time: 0.030, memory: 10707, loss_rpn_cls: 0.0237, loss_rpn_bbox: 0.0344, loss_cls: 0.1622, acc: 93.9651, loss_bbox: 0.2139, loss_mask: 0.2170, loss: 0.6512 2023-11-17 00:41:11,684 - mmdet - INFO - Epoch [17][550/1833] lr: 5.563e-06, eta: 8:42:23, time: 0.877, data_time: 0.035, memory: 10707, loss_rpn_cls: 0.0238, loss_rpn_bbox: 0.0344, loss_cls: 0.1630, acc: 93.9958, loss_bbox: 0.2132, loss_mask: 0.2193, loss: 0.6537 2023-11-17 00:41:55,747 - mmdet - INFO - Epoch [17][600/1833] lr: 5.563e-06, eta: 8:41:40, time: 0.881, data_time: 0.034, memory: 10707, loss_rpn_cls: 0.0239, loss_rpn_bbox: 0.0342, loss_cls: 0.1650, acc: 93.8856, loss_bbox: 0.2174, loss_mask: 0.2185, loss: 0.6591 2023-11-17 00:42:40,036 - mmdet - INFO - Epoch [17][650/1833] lr: 5.563e-06, eta: 8:40:58, time: 0.886, data_time: 0.034, memory: 10707, loss_rpn_cls: 0.0234, loss_rpn_bbox: 0.0337, loss_cls: 0.1641, acc: 93.8726, loss_bbox: 0.2163, loss_mask: 0.2191, loss: 0.6566 2023-11-17 00:43:24,151 - mmdet - INFO - Epoch [17][700/1833] lr: 5.563e-06, eta: 8:40:15, time: 0.882, data_time: 0.033, memory: 10707, loss_rpn_cls: 0.0238, loss_rpn_bbox: 0.0355, loss_cls: 0.1644, acc: 93.9044, loss_bbox: 0.2154, loss_mask: 0.2179, loss: 0.6571 2023-11-17 00:44:07,619 - mmdet - INFO - Epoch [17][750/1833] lr: 5.563e-06, eta: 8:39:32, time: 0.869, data_time: 0.036, memory: 10707, loss_rpn_cls: 0.0236, loss_rpn_bbox: 0.0336, loss_cls: 0.1625, acc: 93.9604, loss_bbox: 0.2155, loss_mask: 0.2183, loss: 0.6535 2023-11-17 00:44:51,807 - mmdet - INFO - Epoch [17][800/1833] lr: 5.563e-06, eta: 8:38:50, time: 0.884, data_time: 0.036, memory: 10707, loss_rpn_cls: 0.0235, loss_rpn_bbox: 0.0344, loss_cls: 0.1647, acc: 93.8813, loss_bbox: 0.2181, loss_mask: 0.2190, loss: 0.6598 2023-11-17 00:45:36,139 - mmdet - INFO - Epoch [17][850/1833] lr: 5.563e-06, eta: 8:38:07, time: 0.887, data_time: 0.043, memory: 10707, loss_rpn_cls: 0.0237, loss_rpn_bbox: 0.0341, loss_cls: 0.1650, acc: 93.9031, loss_bbox: 0.2155, loss_mask: 0.2180, loss: 0.6563 2023-11-17 00:46:19,851 - mmdet - INFO - Epoch [17][900/1833] lr: 5.563e-06, eta: 8:37:24, time: 0.874, data_time: 0.036, memory: 10707, loss_rpn_cls: 0.0234, loss_rpn_bbox: 0.0342, loss_cls: 0.1632, acc: 93.9338, loss_bbox: 0.2177, loss_mask: 0.2170, loss: 0.6556 2023-11-17 00:47:03,947 - mmdet - INFO - Epoch [17][950/1833] lr: 5.563e-06, eta: 8:36:42, time: 0.882, data_time: 0.040, memory: 10707, loss_rpn_cls: 0.0258, loss_rpn_bbox: 0.0353, loss_cls: 0.1645, acc: 93.8831, loss_bbox: 0.2176, loss_mask: 0.2213, loss: 0.6645 2023-11-17 00:47:47,953 - mmdet - INFO - Epoch [17][1000/1833] lr: 5.563e-06, eta: 8:35:59, time: 0.880, data_time: 0.032, memory: 10707, loss_rpn_cls: 0.0242, loss_rpn_bbox: 0.0345, loss_cls: 0.1649, acc: 93.8672, loss_bbox: 0.2164, loss_mask: 0.2219, loss: 0.6619 2023-11-17 00:48:31,932 - mmdet - INFO - Epoch [17][1050/1833] lr: 5.563e-06, eta: 8:35:16, time: 0.880, data_time: 0.032, memory: 10707, loss_rpn_cls: 0.0233, loss_rpn_bbox: 0.0335, loss_cls: 0.1626, acc: 93.9736, loss_bbox: 0.2147, loss_mask: 0.2220, loss: 0.6561 2023-11-17 00:49:15,990 - mmdet - INFO - Epoch [17][1100/1833] lr: 5.563e-06, eta: 8:34:34, time: 0.881, data_time: 0.034, memory: 10707, loss_rpn_cls: 0.0237, loss_rpn_bbox: 0.0340, loss_cls: 0.1611, acc: 94.0300, loss_bbox: 0.2131, loss_mask: 0.2204, loss: 0.6523 2023-11-17 00:50:00,166 - mmdet - INFO - Epoch [17][1150/1833] lr: 5.563e-06, eta: 8:33:51, time: 0.883, data_time: 0.030, memory: 10707, loss_rpn_cls: 0.0245, loss_rpn_bbox: 0.0339, loss_cls: 0.1640, acc: 93.8890, loss_bbox: 0.2163, loss_mask: 0.2202, loss: 0.6590 2023-11-17 00:50:44,788 - mmdet - INFO - Epoch [17][1200/1833] lr: 5.563e-06, eta: 8:33:09, time: 0.892, data_time: 0.036, memory: 10707, loss_rpn_cls: 0.0244, loss_rpn_bbox: 0.0351, loss_cls: 0.1657, acc: 93.8226, loss_bbox: 0.2198, loss_mask: 0.2237, loss: 0.6687 2023-11-17 00:51:28,900 - mmdet - INFO - Epoch [17][1250/1833] lr: 5.563e-06, eta: 8:32:26, time: 0.882, data_time: 0.037, memory: 10707, loss_rpn_cls: 0.0224, loss_rpn_bbox: 0.0332, loss_cls: 0.1593, acc: 94.0688, loss_bbox: 0.2095, loss_mask: 0.2168, loss: 0.6413 2023-11-17 00:52:12,531 - mmdet - INFO - Epoch [17][1300/1833] lr: 5.563e-06, eta: 8:31:43, time: 0.873, data_time: 0.034, memory: 10707, loss_rpn_cls: 0.0234, loss_rpn_bbox: 0.0337, loss_cls: 0.1603, acc: 94.0479, loss_bbox: 0.2120, loss_mask: 0.2172, loss: 0.6467 2023-11-17 00:52:56,373 - mmdet - INFO - Epoch [17][1350/1833] lr: 5.563e-06, eta: 8:31:00, time: 0.877, data_time: 0.032, memory: 10707, loss_rpn_cls: 0.0248, loss_rpn_bbox: 0.0347, loss_cls: 0.1656, acc: 93.8084, loss_bbox: 0.2194, loss_mask: 0.2229, loss: 0.6674 2023-11-17 00:53:40,275 - mmdet - INFO - Epoch [17][1400/1833] lr: 5.563e-06, eta: 8:30:17, time: 0.878, data_time: 0.038, memory: 10707, loss_rpn_cls: 0.0236, loss_rpn_bbox: 0.0346, loss_cls: 0.1636, acc: 93.9402, loss_bbox: 0.2174, loss_mask: 0.2210, loss: 0.6601 2023-11-17 00:54:24,085 - mmdet - INFO - Epoch [17][1450/1833] lr: 5.563e-06, eta: 8:29:34, time: 0.876, data_time: 0.035, memory: 10707, loss_rpn_cls: 0.0234, loss_rpn_bbox: 0.0336, loss_cls: 0.1591, acc: 94.1257, loss_bbox: 0.2089, loss_mask: 0.2180, loss: 0.6429 2023-11-17 00:55:08,016 - mmdet - INFO - Epoch [17][1500/1833] lr: 5.563e-06, eta: 8:28:52, time: 0.879, data_time: 0.032, memory: 10707, loss_rpn_cls: 0.0241, loss_rpn_bbox: 0.0349, loss_cls: 0.1677, acc: 93.7737, loss_bbox: 0.2177, loss_mask: 0.2186, loss: 0.6629 2023-11-17 00:55:56,135 - mmdet - INFO - Epoch [17][1550/1833] lr: 5.563e-06, eta: 8:28:14, time: 0.962, data_time: 0.045, memory: 10707, loss_rpn_cls: 0.0239, loss_rpn_bbox: 0.0344, loss_cls: 0.1662, acc: 93.8042, loss_bbox: 0.2180, loss_mask: 0.2219, loss: 0.6644 2023-11-17 00:56:42,159 - mmdet - INFO - Epoch [17][1600/1833] lr: 5.563e-06, eta: 8:27:33, time: 0.920, data_time: 0.035, memory: 10707, loss_rpn_cls: 0.0231, loss_rpn_bbox: 0.0344, loss_cls: 0.1654, acc: 93.9054, loss_bbox: 0.2150, loss_mask: 0.2203, loss: 0.6581 2023-11-17 00:57:26,187 - mmdet - INFO - Epoch [17][1650/1833] lr: 5.563e-06, eta: 8:26:50, time: 0.881, data_time: 0.031, memory: 10707, loss_rpn_cls: 0.0237, loss_rpn_bbox: 0.0337, loss_cls: 0.1623, acc: 93.9929, loss_bbox: 0.2138, loss_mask: 0.2186, loss: 0.6521 2023-11-17 00:58:10,098 - mmdet - INFO - Epoch [17][1700/1833] lr: 5.563e-06, eta: 8:26:07, time: 0.878, data_time: 0.034, memory: 10707, loss_rpn_cls: 0.0242, loss_rpn_bbox: 0.0357, loss_cls: 0.1643, acc: 93.9056, loss_bbox: 0.2163, loss_mask: 0.2210, loss: 0.6614 2023-11-17 00:58:54,515 - mmdet - INFO - Epoch [17][1750/1833] lr: 5.563e-06, eta: 8:25:25, time: 0.888, data_time: 0.031, memory: 10707, loss_rpn_cls: 0.0244, loss_rpn_bbox: 0.0351, loss_cls: 0.1656, acc: 93.8341, loss_bbox: 0.2189, loss_mask: 0.2195, loss: 0.6635 2023-11-17 00:59:38,582 - mmdet - INFO - Epoch [17][1800/1833] lr: 5.563e-06, eta: 8:24:42, time: 0.881, data_time: 0.037, memory: 10707, loss_rpn_cls: 0.0243, loss_rpn_bbox: 0.0341, loss_cls: 0.1649, acc: 93.8626, loss_bbox: 0.2172, loss_mask: 0.2180, loss: 0.6584 2023-11-17 01:00:08,170 - mmdet - INFO - Saving checkpoint at 17 epochs 2023-11-17 01:00:42,509 - mmdet - INFO - Evaluating bbox... 2023-11-17 01:01:14,540 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.487 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.719 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.539 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.353 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.531 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.623 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.614 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.614 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.614 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.474 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.657 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.748 2023-11-17 01:01:14,542 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.582 | bicycle | 0.409 | car | 0.476 | | motorcycle | 0.496 | airplane | 0.688 | bus | 0.667 | | train | 0.699 | truck | 0.449 | boat | 0.350 | | traffic light | 0.313 | fire hydrant | 0.741 | stop sign | 0.676 | | parking meter | 0.546 | bench | 0.308 | bird | 0.431 | | cat | 0.738 | dog | 0.672 | horse | 0.622 | | sheep | 0.599 | cow | 0.636 | elephant | 0.689 | | bear | 0.747 | zebra | 0.694 | giraffe | 0.689 | | backpack | 0.217 | umbrella | 0.468 | handbag | 0.254 | | tie | 0.404 | suitcase | 0.497 | frisbee | 0.735 | | skis | 0.307 | snowboard | 0.469 | sports ball | 0.477 | | kite | 0.488 | baseball bat | 0.426 | baseball glove | 0.456 | | skateboard | 0.589 | surfboard | 0.475 | tennis racket | 0.549 | | bottle | 0.468 | wine glass | 0.421 | cup | 0.517 | | fork | 0.468 | knife | 0.313 | spoon | 0.302 | | bowl | 0.478 | banana | 0.303 | apple | 0.253 | | sandwich | 0.473 | orange | 0.340 | broccoli | 0.279 | | carrot | 0.274 | hot dog | 0.436 | pizza | 0.543 | | donut | 0.568 | cake | 0.473 | chair | 0.362 | | couch | 0.477 | potted plant | 0.349 | bed | 0.480 | | dining table | 0.319 | toilet | 0.669 | tv | 0.635 | | laptop | 0.672 | mouse | 0.631 | remote | 0.433 | | keyboard | 0.525 | cell phone | 0.447 | microwave | 0.638 | | oven | 0.413 | toaster | 0.455 | sink | 0.452 | | refrigerator | 0.675 | book | 0.196 | clock | 0.544 | | vase | 0.424 | scissors | 0.433 | teddy bear | 0.550 | | hair drier | 0.225 | toothbrush | 0.339 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-17 01:01:14,543 - mmdet - INFO - Evaluating segm... 2023-11-17 01:01:48,553 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.442 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.690 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.476 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.263 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.482 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.628 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.562 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.562 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.562 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.402 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.610 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.714 2023-11-17 01:01:48,555 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.511 | bicycle | 0.250 | car | 0.436 | | motorcycle | 0.407 | airplane | 0.549 | bus | 0.659 | | train | 0.683 | truck | 0.451 | boat | 0.324 | | traffic light | 0.306 | fire hydrant | 0.714 | stop sign | 0.658 | | parking meter | 0.541 | bench | 0.239 | bird | 0.352 | | cat | 0.739 | dog | 0.654 | horse | 0.470 | | sheep | 0.544 | cow | 0.539 | elephant | 0.625 | | bear | 0.738 | zebra | 0.608 | giraffe | 0.554 | | backpack | 0.218 | umbrella | 0.525 | handbag | 0.238 | | tie | 0.360 | suitcase | 0.510 | frisbee | 0.667 | | skis | 0.056 | snowboard | 0.293 | sports ball | 0.466 | | kite | 0.348 | baseball bat | 0.314 | baseball glove | 0.471 | | skateboard | 0.390 | surfboard | 0.393 | tennis racket | 0.589 | | bottle | 0.450 | wine glass | 0.370 | cup | 0.516 | | fork | 0.254 | knife | 0.209 | spoon | 0.213 | | bowl | 0.450 | banana | 0.258 | apple | 0.253 | | sandwich | 0.497 | orange | 0.343 | broccoli | 0.265 | | carrot | 0.239 | hot dog | 0.350 | pizza | 0.524 | | donut | 0.575 | cake | 0.486 | chair | 0.261 | | couch | 0.409 | potted plant | 0.302 | bed | 0.380 | | dining table | 0.193 | toilet | 0.645 | tv | 0.669 | | laptop | 0.682 | mouse | 0.621 | remote | 0.398 | | keyboard | 0.543 | cell phone | 0.437 | microwave | 0.676 | | oven | 0.389 | toaster | 0.504 | sink | 0.431 | | refrigerator | 0.707 | book | 0.152 | clock | 0.542 | | vase | 0.415 | scissors | 0.327 | teddy bear | 0.536 | | hair drier | 0.288 | toothbrush | 0.233 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-17 01:01:49,044 - mmdet - INFO - Exp name: mask_rcnn_flash_internimage_b_fpn_3x_coco_0.4_0.9-4x16.py 2023-11-17 01:01:49,044 - mmdet - INFO - Epoch(val) [17][313] bbox_mAP: 0.4872, bbox_mAP_50: 0.7193, bbox_mAP_75: 0.5386, bbox_mAP_s: 0.3527, bbox_mAP_m: 0.5312, bbox_mAP_l: 0.6225, bbox_mAP_copypaste: 0.4872 0.7193 0.5386 0.3527 0.5312 0.6225, segm_mAP: 0.4423, segm_mAP_50: 0.6904, segm_mAP_75: 0.4764, segm_mAP_s: 0.2632, segm_mAP_m: 0.4823, segm_mAP_l: 0.6278, segm_mAP_copypaste: 0.4423 0.6904 0.4764 0.2632 0.4823 0.6278 2023-11-17 01:02:36,476 - mmdet - INFO - Epoch [18][50/1833] lr: 5.563e-06, eta: 8:23:03, time: 0.947, data_time: 0.089, memory: 10707, loss_rpn_cls: 0.0230, loss_rpn_bbox: 0.0339, loss_cls: 0.1613, acc: 93.9805, loss_bbox: 0.2137, loss_mask: 0.2184, loss: 0.6503 2023-11-17 01:03:20,864 - mmdet - INFO - Epoch [18][100/1833] lr: 5.563e-06, eta: 8:22:20, time: 0.888, data_time: 0.040, memory: 10707, loss_rpn_cls: 0.0237, loss_rpn_bbox: 0.0332, loss_cls: 0.1613, acc: 93.9974, loss_bbox: 0.2145, loss_mask: 0.2174, loss: 0.6501 2023-11-17 01:04:05,336 - mmdet - INFO - Epoch [18][150/1833] lr: 5.563e-06, eta: 8:21:38, time: 0.889, data_time: 0.038, memory: 10707, loss_rpn_cls: 0.0236, loss_rpn_bbox: 0.0340, loss_cls: 0.1596, acc: 94.0241, loss_bbox: 0.2144, loss_mask: 0.2158, loss: 0.6473 2023-11-17 01:04:49,218 - mmdet - INFO - Epoch [18][200/1833] lr: 5.563e-06, eta: 8:20:55, time: 0.877, data_time: 0.031, memory: 10707, loss_rpn_cls: 0.0237, loss_rpn_bbox: 0.0343, loss_cls: 0.1608, acc: 94.0280, loss_bbox: 0.2152, loss_mask: 0.2209, loss: 0.6550 2023-11-17 01:05:33,233 - mmdet - INFO - Epoch [18][250/1833] lr: 5.563e-06, eta: 8:20:13, time: 0.881, data_time: 0.034, memory: 10707, loss_rpn_cls: 0.0235, loss_rpn_bbox: 0.0348, loss_cls: 0.1605, acc: 94.0687, loss_bbox: 0.2112, loss_mask: 0.2185, loss: 0.6486 2023-11-17 01:06:17,470 - mmdet - INFO - Epoch [18][300/1833] lr: 5.563e-06, eta: 8:19:30, time: 0.885, data_time: 0.036, memory: 10707, loss_rpn_cls: 0.0229, loss_rpn_bbox: 0.0336, loss_cls: 0.1603, acc: 94.0403, loss_bbox: 0.2135, loss_mask: 0.2185, loss: 0.6487 2023-11-17 01:07:01,836 - mmdet - INFO - Epoch [18][350/1833] lr: 5.563e-06, eta: 8:18:48, time: 0.887, data_time: 0.034, memory: 10707, loss_rpn_cls: 0.0244, loss_rpn_bbox: 0.0351, loss_cls: 0.1632, acc: 93.9586, loss_bbox: 0.2154, loss_mask: 0.2185, loss: 0.6567 2023-11-17 01:07:47,032 - mmdet - INFO - Epoch [18][400/1833] lr: 5.563e-06, eta: 8:18:06, time: 0.904, data_time: 0.042, memory: 10707, loss_rpn_cls: 0.0236, loss_rpn_bbox: 0.0341, loss_cls: 0.1639, acc: 93.8806, loss_bbox: 0.2165, loss_mask: 0.2184, loss: 0.6566 2023-11-17 01:08:31,073 - mmdet - INFO - Epoch [18][450/1833] lr: 5.563e-06, eta: 8:17:24, time: 0.881, data_time: 0.034, memory: 10707, loss_rpn_cls: 0.0234, loss_rpn_bbox: 0.0339, loss_cls: 0.1609, acc: 93.9912, loss_bbox: 0.2133, loss_mask: 0.2188, loss: 0.6503 2023-11-17 01:09:15,711 - mmdet - INFO - Epoch [18][500/1833] lr: 5.563e-06, eta: 8:16:42, time: 0.893, data_time: 0.030, memory: 10707, loss_rpn_cls: 0.0234, loss_rpn_bbox: 0.0331, loss_cls: 0.1622, acc: 93.9407, loss_bbox: 0.2171, loss_mask: 0.2183, loss: 0.6541 2023-11-17 01:10:00,973 - mmdet - INFO - Epoch [18][550/1833] lr: 5.563e-06, eta: 8:16:00, time: 0.905, data_time: 0.028, memory: 10707, loss_rpn_cls: 0.0234, loss_rpn_bbox: 0.0350, loss_cls: 0.1639, acc: 93.9020, loss_bbox: 0.2162, loss_mask: 0.2170, loss: 0.6554 2023-11-17 01:10:45,220 - mmdet - INFO - Epoch [18][600/1833] lr: 5.563e-06, eta: 8:15:18, time: 0.885, data_time: 0.036, memory: 10707, loss_rpn_cls: 0.0244, loss_rpn_bbox: 0.0349, loss_cls: 0.1614, acc: 94.0109, loss_bbox: 0.2167, loss_mask: 0.2237, loss: 0.6612 2023-11-17 01:11:29,603 - mmdet - INFO - Epoch [18][650/1833] lr: 5.563e-06, eta: 8:14:35, time: 0.888, data_time: 0.032, memory: 10707, loss_rpn_cls: 0.0241, loss_rpn_bbox: 0.0344, loss_cls: 0.1628, acc: 93.9155, loss_bbox: 0.2151, loss_mask: 0.2213, loss: 0.6577 2023-11-17 01:12:13,832 - mmdet - INFO - Epoch [18][700/1833] lr: 5.563e-06, eta: 8:13:53, time: 0.885, data_time: 0.033, memory: 10707, loss_rpn_cls: 0.0233, loss_rpn_bbox: 0.0350, loss_cls: 0.1638, acc: 93.9083, loss_bbox: 0.2150, loss_mask: 0.2205, loss: 0.6576 2023-11-17 01:12:57,823 - mmdet - INFO - Epoch [18][750/1833] lr: 5.563e-06, eta: 8:13:10, time: 0.880, data_time: 0.032, memory: 10707, loss_rpn_cls: 0.0232, loss_rpn_bbox: 0.0337, loss_cls: 0.1593, acc: 94.0457, loss_bbox: 0.2140, loss_mask: 0.2190, loss: 0.6492 2023-11-17 01:13:42,220 - mmdet - INFO - Epoch [18][800/1833] lr: 5.563e-06, eta: 8:12:28, time: 0.888, data_time: 0.029, memory: 10707, loss_rpn_cls: 0.0229, loss_rpn_bbox: 0.0330, loss_cls: 0.1587, acc: 94.0689, loss_bbox: 0.2112, loss_mask: 0.2164, loss: 0.6422 2023-11-17 01:14:26,382 - mmdet - INFO - Epoch [18][850/1833] lr: 5.563e-06, eta: 8:11:45, time: 0.883, data_time: 0.032, memory: 10707, loss_rpn_cls: 0.0232, loss_rpn_bbox: 0.0343, loss_cls: 0.1602, acc: 94.0124, loss_bbox: 0.2148, loss_mask: 0.2194, loss: 0.6519 2023-11-17 01:15:10,706 - mmdet - INFO - Epoch [18][900/1833] lr: 5.563e-06, eta: 8:11:02, time: 0.886, data_time: 0.035, memory: 10707, loss_rpn_cls: 0.0230, loss_rpn_bbox: 0.0337, loss_cls: 0.1625, acc: 93.9028, loss_bbox: 0.2164, loss_mask: 0.2177, loss: 0.6534 2023-11-17 01:15:55,080 - mmdet - INFO - Epoch [18][950/1833] lr: 5.563e-06, eta: 8:10:20, time: 0.888, data_time: 0.030, memory: 10707, loss_rpn_cls: 0.0241, loss_rpn_bbox: 0.0356, loss_cls: 0.1667, acc: 93.8370, loss_bbox: 0.2174, loss_mask: 0.2199, loss: 0.6637 2023-11-17 01:16:39,514 - mmdet - INFO - Epoch [18][1000/1833] lr: 5.563e-06, eta: 8:09:38, time: 0.889, data_time: 0.040, memory: 10707, loss_rpn_cls: 0.0246, loss_rpn_bbox: 0.0355, loss_cls: 0.1681, acc: 93.6846, loss_bbox: 0.2212, loss_mask: 0.2226, loss: 0.6720 2023-11-17 01:17:24,150 - mmdet - INFO - Epoch [18][1050/1833] lr: 5.563e-06, eta: 8:08:56, time: 0.893, data_time: 0.033, memory: 10707, loss_rpn_cls: 0.0229, loss_rpn_bbox: 0.0341, loss_cls: 0.1643, acc: 93.9169, loss_bbox: 0.2165, loss_mask: 0.2221, loss: 0.6599 2023-11-17 01:18:08,264 - mmdet - INFO - Epoch [18][1100/1833] lr: 5.563e-06, eta: 8:08:13, time: 0.882, data_time: 0.031, memory: 10707, loss_rpn_cls: 0.0235, loss_rpn_bbox: 0.0355, loss_cls: 0.1672, acc: 93.7845, loss_bbox: 0.2217, loss_mask: 0.2198, loss: 0.6678 2023-11-17 01:18:52,513 - mmdet - INFO - Epoch [18][1150/1833] lr: 5.563e-06, eta: 8:07:30, time: 0.885, data_time: 0.031, memory: 10707, loss_rpn_cls: 0.0230, loss_rpn_bbox: 0.0335, loss_cls: 0.1620, acc: 93.9834, loss_bbox: 0.2174, loss_mask: 0.2159, loss: 0.6518 2023-11-17 01:19:36,495 - mmdet - INFO - Epoch [18][1200/1833] lr: 5.563e-06, eta: 8:06:47, time: 0.880, data_time: 0.030, memory: 10707, loss_rpn_cls: 0.0232, loss_rpn_bbox: 0.0339, loss_cls: 0.1625, acc: 93.9913, loss_bbox: 0.2132, loss_mask: 0.2175, loss: 0.6503 2023-11-17 01:20:20,667 - mmdet - INFO - Epoch [18][1250/1833] lr: 5.563e-06, eta: 8:06:05, time: 0.883, data_time: 0.030, memory: 10707, loss_rpn_cls: 0.0229, loss_rpn_bbox: 0.0335, loss_cls: 0.1598, acc: 94.0356, loss_bbox: 0.2101, loss_mask: 0.2160, loss: 0.6423 2023-11-17 01:21:05,224 - mmdet - INFO - Epoch [18][1300/1833] lr: 5.563e-06, eta: 8:05:22, time: 0.891, data_time: 0.030, memory: 10707, loss_rpn_cls: 0.0241, loss_rpn_bbox: 0.0351, loss_cls: 0.1633, acc: 93.9518, loss_bbox: 0.2138, loss_mask: 0.2177, loss: 0.6539 2023-11-17 01:21:49,378 - mmdet - INFO - Epoch [18][1350/1833] lr: 5.563e-06, eta: 8:04:40, time: 0.884, data_time: 0.036, memory: 10707, loss_rpn_cls: 0.0227, loss_rpn_bbox: 0.0331, loss_cls: 0.1590, acc: 94.0978, loss_bbox: 0.2113, loss_mask: 0.2167, loss: 0.6427 2023-11-17 01:22:33,551 - mmdet - INFO - Epoch [18][1400/1833] lr: 5.563e-06, eta: 8:03:57, time: 0.883, data_time: 0.033, memory: 10707, loss_rpn_cls: 0.0260, loss_rpn_bbox: 0.0357, loss_cls: 0.1663, acc: 93.8339, loss_bbox: 0.2182, loss_mask: 0.2198, loss: 0.6659 2023-11-17 01:23:18,285 - mmdet - INFO - Epoch [18][1450/1833] lr: 5.563e-06, eta: 8:03:15, time: 0.895, data_time: 0.031, memory: 10707, loss_rpn_cls: 0.0233, loss_rpn_bbox: 0.0339, loss_cls: 0.1599, acc: 94.0826, loss_bbox: 0.2099, loss_mask: 0.2147, loss: 0.6416 2023-11-17 01:24:02,114 - mmdet - INFO - Epoch [18][1500/1833] lr: 5.563e-06, eta: 8:02:32, time: 0.877, data_time: 0.029, memory: 10707, loss_rpn_cls: 0.0233, loss_rpn_bbox: 0.0334, loss_cls: 0.1627, acc: 93.9537, loss_bbox: 0.2121, loss_mask: 0.2184, loss: 0.6499 2023-11-17 01:24:46,288 - mmdet - INFO - Epoch [18][1550/1833] lr: 5.563e-06, eta: 8:01:49, time: 0.883, data_time: 0.033, memory: 10707, loss_rpn_cls: 0.0240, loss_rpn_bbox: 0.0345, loss_cls: 0.1622, acc: 93.9708, loss_bbox: 0.2153, loss_mask: 0.2200, loss: 0.6559 2023-11-17 01:25:30,669 - mmdet - INFO - Epoch [18][1600/1833] lr: 5.563e-06, eta: 8:01:07, time: 0.888, data_time: 0.030, memory: 10707, loss_rpn_cls: 0.0239, loss_rpn_bbox: 0.0332, loss_cls: 0.1587, acc: 94.1155, loss_bbox: 0.2081, loss_mask: 0.2168, loss: 0.6406 2023-11-17 01:26:15,038 - mmdet - INFO - Epoch [18][1650/1833] lr: 5.563e-06, eta: 8:00:24, time: 0.887, data_time: 0.031, memory: 10707, loss_rpn_cls: 0.0231, loss_rpn_bbox: 0.0338, loss_cls: 0.1603, acc: 94.0653, loss_bbox: 0.2118, loss_mask: 0.2197, loss: 0.6487 2023-11-17 01:26:59,317 - mmdet - INFO - Epoch [18][1700/1833] lr: 5.563e-06, eta: 7:59:42, time: 0.886, data_time: 0.033, memory: 10707, loss_rpn_cls: 0.0233, loss_rpn_bbox: 0.0332, loss_cls: 0.1649, acc: 93.8715, loss_bbox: 0.2182, loss_mask: 0.2188, loss: 0.6584 2023-11-17 01:27:43,028 - mmdet - INFO - Epoch [18][1750/1833] lr: 5.563e-06, eta: 7:58:59, time: 0.874, data_time: 0.030, memory: 10707, loss_rpn_cls: 0.0234, loss_rpn_bbox: 0.0340, loss_cls: 0.1655, acc: 93.8455, loss_bbox: 0.2159, loss_mask: 0.2189, loss: 0.6578 2023-11-17 01:28:27,154 - mmdet - INFO - Epoch [18][1800/1833] lr: 5.563e-06, eta: 7:58:16, time: 0.882, data_time: 0.037, memory: 10707, loss_rpn_cls: 0.0245, loss_rpn_bbox: 0.0344, loss_cls: 0.1635, acc: 93.9596, loss_bbox: 0.2116, loss_mask: 0.2203, loss: 0.6543 2023-11-17 01:28:56,870 - mmdet - INFO - Saving checkpoint at 18 epochs 2023-11-17 01:29:33,542 - mmdet - INFO - Evaluating bbox... 2023-11-17 01:30:04,126 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.491 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.722 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.542 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.347 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.532 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.628 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.617 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.617 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.617 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.474 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.658 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.760 2023-11-17 01:30:04,129 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.585 | bicycle | 0.392 | car | 0.490 | | motorcycle | 0.500 | airplane | 0.688 | bus | 0.675 | | train | 0.689 | truck | 0.451 | boat | 0.346 | | traffic light | 0.320 | fire hydrant | 0.731 | stop sign | 0.672 | | parking meter | 0.535 | bench | 0.302 | bird | 0.427 | | cat | 0.719 | dog | 0.702 | horse | 0.641 | | sheep | 0.613 | cow | 0.640 | elephant | 0.698 | | bear | 0.774 | zebra | 0.674 | giraffe | 0.696 | | backpack | 0.227 | umbrella | 0.467 | handbag | 0.251 | | tie | 0.402 | suitcase | 0.497 | frisbee | 0.717 | | skis | 0.310 | snowboard | 0.447 | sports ball | 0.484 | | kite | 0.476 | baseball bat | 0.433 | baseball glove | 0.449 | | skateboard | 0.588 | surfboard | 0.480 | tennis racket | 0.563 | | bottle | 0.479 | wine glass | 0.420 | cup | 0.517 | | fork | 0.475 | knife | 0.312 | spoon | 0.296 | | bowl | 0.493 | banana | 0.306 | apple | 0.247 | | sandwich | 0.466 | orange | 0.362 | broccoli | 0.283 | | carrot | 0.269 | hot dog | 0.457 | pizza | 0.545 | | donut | 0.557 | cake | 0.482 | chair | 0.368 | | couch | 0.484 | potted plant | 0.349 | bed | 0.491 | | dining table | 0.318 | toilet | 0.672 | tv | 0.636 | | laptop | 0.687 | mouse | 0.663 | remote | 0.430 | | keyboard | 0.561 | cell phone | 0.467 | microwave | 0.689 | | oven | 0.415 | toaster | 0.490 | sink | 0.453 | | refrigerator | 0.691 | book | 0.197 | clock | 0.547 | | vase | 0.401 | scissors | 0.459 | teddy bear | 0.566 | | hair drier | 0.210 | toothbrush | 0.345 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-17 01:30:04,129 - mmdet - INFO - Evaluating segm... 2023-11-17 01:30:39,653 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.444 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.691 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.479 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.265 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.482 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.627 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.563 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.563 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.563 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.403 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.609 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.718 2023-11-17 01:30:39,655 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.507 | bicycle | 0.237 | car | 0.452 | | motorcycle | 0.413 | airplane | 0.559 | bus | 0.665 | | train | 0.673 | truck | 0.440 | boat | 0.330 | | traffic light | 0.311 | fire hydrant | 0.696 | stop sign | 0.668 | | parking meter | 0.539 | bench | 0.233 | bird | 0.351 | | cat | 0.730 | dog | 0.668 | horse | 0.478 | | sheep | 0.538 | cow | 0.544 | elephant | 0.637 | | bear | 0.741 | zebra | 0.585 | giraffe | 0.552 | | backpack | 0.228 | umbrella | 0.512 | handbag | 0.230 | | tie | 0.379 | suitcase | 0.506 | frisbee | 0.667 | | skis | 0.052 | snowboard | 0.293 | sports ball | 0.465 | | kite | 0.352 | baseball bat | 0.320 | baseball glove | 0.477 | | skateboard | 0.394 | surfboard | 0.401 | tennis racket | 0.593 | | bottle | 0.454 | wine glass | 0.378 | cup | 0.514 | | fork | 0.249 | knife | 0.224 | spoon | 0.221 | | bowl | 0.465 | banana | 0.262 | apple | 0.253 | | sandwich | 0.498 | orange | 0.360 | broccoli | 0.272 | | carrot | 0.233 | hot dog | 0.372 | pizza | 0.536 | | donut | 0.563 | cake | 0.493 | chair | 0.266 | | couch | 0.406 | potted plant | 0.296 | bed | 0.389 | | dining table | 0.195 | toilet | 0.653 | tv | 0.663 | | laptop | 0.683 | mouse | 0.638 | remote | 0.393 | | keyboard | 0.556 | cell phone | 0.446 | microwave | 0.698 | | oven | 0.398 | toaster | 0.561 | sink | 0.431 | | refrigerator | 0.711 | book | 0.150 | clock | 0.544 | | vase | 0.400 | scissors | 0.335 | teddy bear | 0.523 | | hair drier | 0.214 | toothbrush | 0.231 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-17 01:30:40,175 - mmdet - INFO - The previous best checkpoint /mnt/petrelfs/lizhiqi/DINO/detection/work_dirs/mask_rcnn_flash_internimage_b_fpn_3x_cocoo_0.4_0.9_4x16/best_bbox_mAP_epoch_16.pth was removed 2023-11-17 01:30:43,833 - mmdet - INFO - Now best checkpoint is saved as best_bbox_mAP_epoch_18.pth. 2023-11-17 01:30:43,834 - mmdet - INFO - Best bbox_mAP is 0.4913 at 18 epoch. 2023-11-17 01:30:43,834 - mmdet - INFO - Exp name: mask_rcnn_flash_internimage_b_fpn_3x_coco_0.4_0.9-4x16.py 2023-11-17 01:30:43,834 - mmdet - INFO - Epoch(val) [18][313] bbox_mAP: 0.4913, bbox_mAP_50: 0.7225, bbox_mAP_75: 0.5418, bbox_mAP_s: 0.3470, bbox_mAP_m: 0.5315, bbox_mAP_l: 0.6278, bbox_mAP_copypaste: 0.4913 0.7225 0.5418 0.3470 0.5315 0.6278, segm_mAP: 0.4443, segm_mAP_50: 0.6909, segm_mAP_75: 0.4793, segm_mAP_s: 0.2648, segm_mAP_m: 0.4822, segm_mAP_l: 0.6269, segm_mAP_copypaste: 0.4443 0.6909 0.4793 0.2648 0.4822 0.6269 2023-11-17 01:31:30,685 - mmdet - INFO - Epoch [19][50/1833] lr: 5.563e-06, eta: 7:56:38, time: 0.937, data_time: 0.096, memory: 10707, loss_rpn_cls: 0.0235, loss_rpn_bbox: 0.0351, loss_cls: 0.1597, acc: 93.9888, loss_bbox: 0.2121, loss_mask: 0.2201, loss: 0.6505 2023-11-17 01:32:14,291 - mmdet - INFO - Epoch [19][100/1833] lr: 5.563e-06, eta: 7:55:55, time: 0.872, data_time: 0.038, memory: 10707, loss_rpn_cls: 0.0235, loss_rpn_bbox: 0.0346, loss_cls: 0.1581, acc: 94.0969, loss_bbox: 0.2112, loss_mask: 0.2173, loss: 0.6447 2023-11-17 01:32:58,488 - mmdet - INFO - Epoch [19][150/1833] lr: 5.563e-06, eta: 7:55:13, time: 0.884, data_time: 0.033, memory: 10707, loss_rpn_cls: 0.0221, loss_rpn_bbox: 0.0330, loss_cls: 0.1568, acc: 94.1504, loss_bbox: 0.2105, loss_mask: 0.2178, loss: 0.6402 2023-11-17 01:33:42,199 - mmdet - INFO - Epoch [19][200/1833] lr: 5.563e-06, eta: 7:54:29, time: 0.874, data_time: 0.031, memory: 10707, loss_rpn_cls: 0.0236, loss_rpn_bbox: 0.0339, loss_cls: 0.1601, acc: 94.0038, loss_bbox: 0.2154, loss_mask: 0.2167, loss: 0.6497 2023-11-17 01:34:26,097 - mmdet - INFO - Epoch [19][250/1833] lr: 5.563e-06, eta: 7:53:47, time: 0.878, data_time: 0.042, memory: 10707, loss_rpn_cls: 0.0231, loss_rpn_bbox: 0.0338, loss_cls: 0.1598, acc: 94.0491, loss_bbox: 0.2123, loss_mask: 0.2161, loss: 0.6451 2023-11-17 01:35:10,045 - mmdet - INFO - Epoch [19][300/1833] lr: 5.563e-06, eta: 7:53:04, time: 0.879, data_time: 0.037, memory: 10707, loss_rpn_cls: 0.0229, loss_rpn_bbox: 0.0338, loss_cls: 0.1607, acc: 93.9644, loss_bbox: 0.2151, loss_mask: 0.2173, loss: 0.6499 2023-11-17 01:35:53,869 - mmdet - INFO - Epoch [19][350/1833] lr: 5.563e-06, eta: 7:52:21, time: 0.876, data_time: 0.034, memory: 10707, loss_rpn_cls: 0.0229, loss_rpn_bbox: 0.0329, loss_cls: 0.1578, acc: 94.1757, loss_bbox: 0.2095, loss_mask: 0.2166, loss: 0.6396 2023-11-17 01:36:38,207 - mmdet - INFO - Epoch [19][400/1833] lr: 5.563e-06, eta: 7:51:38, time: 0.887, data_time: 0.037, memory: 10707, loss_rpn_cls: 0.0220, loss_rpn_bbox: 0.0339, loss_cls: 0.1621, acc: 93.9141, loss_bbox: 0.2158, loss_mask: 0.2229, loss: 0.6567 2023-11-17 01:37:22,133 - mmdet - INFO - Epoch [19][450/1833] lr: 5.563e-06, eta: 7:50:55, time: 0.878, data_time: 0.034, memory: 10707, loss_rpn_cls: 0.0220, loss_rpn_bbox: 0.0331, loss_cls: 0.1572, acc: 94.1470, loss_bbox: 0.2109, loss_mask: 0.2169, loss: 0.6401 2023-11-17 01:38:06,008 - mmdet - INFO - Epoch [19][500/1833] lr: 5.563e-06, eta: 7:50:12, time: 0.877, data_time: 0.038, memory: 10707, loss_rpn_cls: 0.0237, loss_rpn_bbox: 0.0346, loss_cls: 0.1616, acc: 93.9703, loss_bbox: 0.2174, loss_mask: 0.2192, loss: 0.6565 2023-11-17 01:38:49,994 - mmdet - INFO - Epoch [19][550/1833] lr: 5.563e-06, eta: 7:49:29, time: 0.880, data_time: 0.039, memory: 10707, loss_rpn_cls: 0.0247, loss_rpn_bbox: 0.0341, loss_cls: 0.1634, acc: 93.9337, loss_bbox: 0.2140, loss_mask: 0.2175, loss: 0.6537 2023-11-17 01:39:34,093 - mmdet - INFO - Epoch [19][600/1833] lr: 5.563e-06, eta: 7:48:47, time: 0.882, data_time: 0.034, memory: 10707, loss_rpn_cls: 0.0224, loss_rpn_bbox: 0.0332, loss_cls: 0.1612, acc: 94.0280, loss_bbox: 0.2151, loss_mask: 0.2192, loss: 0.6510 2023-11-17 01:40:18,316 - mmdet - INFO - Epoch [19][650/1833] lr: 5.563e-06, eta: 7:48:04, time: 0.885, data_time: 0.039, memory: 10707, loss_rpn_cls: 0.0232, loss_rpn_bbox: 0.0339, loss_cls: 0.1604, acc: 94.0084, loss_bbox: 0.2152, loss_mask: 0.2174, loss: 0.6502 2023-11-17 01:41:02,116 - mmdet - INFO - Epoch [19][700/1833] lr: 5.563e-06, eta: 7:47:21, time: 0.876, data_time: 0.038, memory: 10707, loss_rpn_cls: 0.0227, loss_rpn_bbox: 0.0340, loss_cls: 0.1616, acc: 93.9886, loss_bbox: 0.2133, loss_mask: 0.2199, loss: 0.6515 2023-11-17 01:41:45,772 - mmdet - INFO - Epoch [19][750/1833] lr: 5.563e-06, eta: 7:46:38, time: 0.873, data_time: 0.036, memory: 10707, loss_rpn_cls: 0.0242, loss_rpn_bbox: 0.0348, loss_cls: 0.1584, acc: 94.0491, loss_bbox: 0.2117, loss_mask: 0.2180, loss: 0.6471 2023-11-17 01:42:29,351 - mmdet - INFO - Epoch [19][800/1833] lr: 5.563e-06, eta: 7:45:55, time: 0.872, data_time: 0.040, memory: 10707, loss_rpn_cls: 0.0224, loss_rpn_bbox: 0.0337, loss_cls: 0.1566, acc: 94.2092, loss_bbox: 0.2080, loss_mask: 0.2167, loss: 0.6375 2023-11-17 01:43:13,356 - mmdet - INFO - Epoch [19][850/1833] lr: 5.563e-06, eta: 7:45:12, time: 0.880, data_time: 0.038, memory: 10707, loss_rpn_cls: 0.0225, loss_rpn_bbox: 0.0319, loss_cls: 0.1553, acc: 94.2248, loss_bbox: 0.2033, loss_mask: 0.2129, loss: 0.6257 2023-11-17 01:43:57,072 - mmdet - INFO - Epoch [19][900/1833] lr: 5.563e-06, eta: 7:44:29, time: 0.874, data_time: 0.035, memory: 10707, loss_rpn_cls: 0.0234, loss_rpn_bbox: 0.0341, loss_cls: 0.1595, acc: 94.1131, loss_bbox: 0.2087, loss_mask: 0.2153, loss: 0.6409 2023-11-17 01:44:41,801 - mmdet - INFO - Epoch [19][950/1833] lr: 5.563e-06, eta: 7:43:46, time: 0.894, data_time: 0.034, memory: 10707, loss_rpn_cls: 0.0226, loss_rpn_bbox: 0.0333, loss_cls: 0.1569, acc: 94.1152, loss_bbox: 0.2097, loss_mask: 0.2169, loss: 0.6395 2023-11-17 01:45:25,890 - mmdet - INFO - Epoch [19][1000/1833] lr: 5.563e-06, eta: 7:43:04, time: 0.882, data_time: 0.038, memory: 10707, loss_rpn_cls: 0.0230, loss_rpn_bbox: 0.0337, loss_cls: 0.1590, acc: 94.0971, loss_bbox: 0.2111, loss_mask: 0.2164, loss: 0.6431 2023-11-17 01:46:09,473 - mmdet - INFO - Epoch [19][1050/1833] lr: 5.563e-06, eta: 7:42:20, time: 0.872, data_time: 0.034, memory: 10707, loss_rpn_cls: 0.0231, loss_rpn_bbox: 0.0340, loss_cls: 0.1601, acc: 94.0433, loss_bbox: 0.2097, loss_mask: 0.2187, loss: 0.6455 2023-11-17 01:46:53,026 - mmdet - INFO - Epoch [19][1100/1833] lr: 5.563e-06, eta: 7:41:37, time: 0.871, data_time: 0.033, memory: 10707, loss_rpn_cls: 0.0225, loss_rpn_bbox: 0.0333, loss_cls: 0.1576, acc: 94.1552, loss_bbox: 0.2082, loss_mask: 0.2137, loss: 0.6354 2023-11-17 01:47:37,565 - mmdet - INFO - Epoch [19][1150/1833] lr: 5.563e-06, eta: 7:40:55, time: 0.891, data_time: 0.039, memory: 10707, loss_rpn_cls: 0.0248, loss_rpn_bbox: 0.0346, loss_cls: 0.1599, acc: 94.0223, loss_bbox: 0.2137, loss_mask: 0.2167, loss: 0.6497 2023-11-17 01:48:23,545 - mmdet - INFO - Epoch [19][1200/1833] lr: 5.563e-06, eta: 7:40:14, time: 0.920, data_time: 0.037, memory: 10707, loss_rpn_cls: 0.0246, loss_rpn_bbox: 0.0349, loss_cls: 0.1631, acc: 93.9613, loss_bbox: 0.2161, loss_mask: 0.2224, loss: 0.6612 2023-11-17 01:49:07,022 - mmdet - INFO - Epoch [19][1250/1833] lr: 5.563e-06, eta: 7:39:30, time: 0.869, data_time: 0.035, memory: 10707, loss_rpn_cls: 0.0229, loss_rpn_bbox: 0.0342, loss_cls: 0.1617, acc: 93.9690, loss_bbox: 0.2137, loss_mask: 0.2173, loss: 0.6498 2023-11-17 01:49:50,977 - mmdet - INFO - Epoch [19][1300/1833] lr: 5.563e-06, eta: 7:38:47, time: 0.879, data_time: 0.032, memory: 10707, loss_rpn_cls: 0.0228, loss_rpn_bbox: 0.0338, loss_cls: 0.1619, acc: 93.9567, loss_bbox: 0.2155, loss_mask: 0.2174, loss: 0.6514 2023-11-17 01:50:34,893 - mmdet - INFO - Epoch [19][1350/1833] lr: 5.563e-06, eta: 7:38:04, time: 0.878, data_time: 0.032, memory: 10707, loss_rpn_cls: 0.0240, loss_rpn_bbox: 0.0338, loss_cls: 0.1613, acc: 93.9916, loss_bbox: 0.2123, loss_mask: 0.2174, loss: 0.6488 2023-11-17 01:51:18,535 - mmdet - INFO - Epoch [19][1400/1833] lr: 5.563e-06, eta: 7:37:21, time: 0.873, data_time: 0.032, memory: 10707, loss_rpn_cls: 0.0230, loss_rpn_bbox: 0.0345, loss_cls: 0.1624, acc: 93.9313, loss_bbox: 0.2146, loss_mask: 0.2190, loss: 0.6535 2023-11-17 01:52:02,795 - mmdet - INFO - Epoch [19][1450/1833] lr: 5.563e-06, eta: 7:36:38, time: 0.885, data_time: 0.036, memory: 10707, loss_rpn_cls: 0.0231, loss_rpn_bbox: 0.0335, loss_cls: 0.1594, acc: 94.0903, loss_bbox: 0.2097, loss_mask: 0.2183, loss: 0.6441 2023-11-17 01:52:46,786 - mmdet - INFO - Epoch [19][1500/1833] lr: 5.563e-06, eta: 7:35:55, time: 0.880, data_time: 0.031, memory: 10707, loss_rpn_cls: 0.0222, loss_rpn_bbox: 0.0337, loss_cls: 0.1581, acc: 94.1449, loss_bbox: 0.2103, loss_mask: 0.2201, loss: 0.6445 2023-11-17 01:53:31,248 - mmdet - INFO - Epoch [19][1550/1833] lr: 5.563e-06, eta: 7:35:13, time: 0.889, data_time: 0.034, memory: 10707, loss_rpn_cls: 0.0235, loss_rpn_bbox: 0.0350, loss_cls: 0.1654, acc: 93.8432, loss_bbox: 0.2196, loss_mask: 0.2194, loss: 0.6630 2023-11-17 01:54:15,316 - mmdet - INFO - Epoch [19][1600/1833] lr: 5.563e-06, eta: 7:34:30, time: 0.881, data_time: 0.034, memory: 10707, loss_rpn_cls: 0.0233, loss_rpn_bbox: 0.0336, loss_cls: 0.1596, acc: 94.1001, loss_bbox: 0.2104, loss_mask: 0.2177, loss: 0.6447 2023-11-17 01:55:01,633 - mmdet - INFO - Epoch [19][1650/1833] lr: 5.563e-06, eta: 7:33:49, time: 0.926, data_time: 0.033, memory: 10707, loss_rpn_cls: 0.0238, loss_rpn_bbox: 0.0339, loss_cls: 0.1623, acc: 93.9203, loss_bbox: 0.2140, loss_mask: 0.2167, loss: 0.6506 2023-11-17 01:55:45,439 - mmdet - INFO - Epoch [19][1700/1833] lr: 5.563e-06, eta: 7:33:06, time: 0.876, data_time: 0.038, memory: 10707, loss_rpn_cls: 0.0242, loss_rpn_bbox: 0.0345, loss_cls: 0.1644, acc: 93.9181, loss_bbox: 0.2161, loss_mask: 0.2188, loss: 0.6580 2023-11-17 01:56:29,778 - mmdet - INFO - Epoch [19][1750/1833] lr: 5.563e-06, eta: 7:32:24, time: 0.887, data_time: 0.036, memory: 10707, loss_rpn_cls: 0.0249, loss_rpn_bbox: 0.0355, loss_cls: 0.1668, acc: 93.7713, loss_bbox: 0.2187, loss_mask: 0.2211, loss: 0.6669 2023-11-17 01:57:13,671 - mmdet - INFO - Epoch [19][1800/1833] lr: 5.563e-06, eta: 7:31:41, time: 0.878, data_time: 0.032, memory: 10707, loss_rpn_cls: 0.0236, loss_rpn_bbox: 0.0340, loss_cls: 0.1618, acc: 94.0009, loss_bbox: 0.2124, loss_mask: 0.2160, loss: 0.6478 2023-11-17 01:57:43,145 - mmdet - INFO - Saving checkpoint at 19 epochs 2023-11-17 01:58:15,195 - mmdet - INFO - Evaluating bbox... 2023-11-17 01:58:47,347 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.489 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.718 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.540 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.346 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.536 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.627 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.613 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.613 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.613 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.463 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.657 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.752 2023-11-17 01:58:47,350 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.582 | bicycle | 0.395 | car | 0.499 | | motorcycle | 0.494 | airplane | 0.690 | bus | 0.687 | | train | 0.710 | truck | 0.452 | boat | 0.341 | | traffic light | 0.309 | fire hydrant | 0.738 | stop sign | 0.655 | | parking meter | 0.526 | bench | 0.299 | bird | 0.426 | | cat | 0.747 | dog | 0.700 | horse | 0.640 | | sheep | 0.598 | cow | 0.639 | elephant | 0.688 | | bear | 0.723 | zebra | 0.696 | giraffe | 0.688 | | backpack | 0.235 | umbrella | 0.468 | handbag | 0.244 | | tie | 0.402 | suitcase | 0.491 | frisbee | 0.729 | | skis | 0.304 | snowboard | 0.453 | sports ball | 0.481 | | kite | 0.474 | baseball bat | 0.404 | baseball glove | 0.455 | | skateboard | 0.600 | surfboard | 0.480 | tennis racket | 0.560 | | bottle | 0.483 | wine glass | 0.430 | cup | 0.517 | | fork | 0.466 | knife | 0.314 | spoon | 0.291 | | bowl | 0.480 | banana | 0.286 | apple | 0.281 | | sandwich | 0.484 | orange | 0.374 | broccoli | 0.268 | | carrot | 0.271 | hot dog | 0.476 | pizza | 0.558 | | donut | 0.550 | cake | 0.457 | chair | 0.373 | | couch | 0.480 | potted plant | 0.349 | bed | 0.482 | | dining table | 0.326 | toilet | 0.664 | tv | 0.626 | | laptop | 0.675 | mouse | 0.660 | remote | 0.435 | | keyboard | 0.551 | cell phone | 0.438 | microwave | 0.683 | | oven | 0.400 | toaster | 0.434 | sink | 0.455 | | refrigerator | 0.685 | book | 0.212 | clock | 0.562 | | vase | 0.431 | scissors | 0.436 | teddy bear | 0.563 | | hair drier | 0.193 | toothbrush | 0.332 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-17 01:58:47,350 - mmdet - INFO - Evaluating segm... 2023-11-17 01:59:22,239 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.441 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.686 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.476 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.257 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.483 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.622 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.559 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.559 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.559 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.392 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.608 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.714 2023-11-17 01:59:22,241 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.513 | bicycle | 0.234 | car | 0.453 | | motorcycle | 0.404 | airplane | 0.560 | bus | 0.672 | | train | 0.692 | truck | 0.446 | boat | 0.318 | | traffic light | 0.301 | fire hydrant | 0.699 | stop sign | 0.650 | | parking meter | 0.524 | bench | 0.233 | bird | 0.353 | | cat | 0.744 | dog | 0.654 | horse | 0.485 | | sheep | 0.538 | cow | 0.545 | elephant | 0.639 | | bear | 0.735 | zebra | 0.604 | giraffe | 0.553 | | backpack | 0.230 | umbrella | 0.521 | handbag | 0.239 | | tie | 0.372 | suitcase | 0.508 | frisbee | 0.673 | | skis | 0.058 | snowboard | 0.268 | sports ball | 0.463 | | kite | 0.327 | baseball bat | 0.307 | baseball glove | 0.470 | | skateboard | 0.391 | surfboard | 0.390 | tennis racket | 0.597 | | bottle | 0.460 | wine glass | 0.383 | cup | 0.513 | | fork | 0.249 | knife | 0.204 | spoon | 0.208 | | bowl | 0.448 | banana | 0.253 | apple | 0.277 | | sandwich | 0.500 | orange | 0.370 | broccoli | 0.253 | | carrot | 0.236 | hot dog | 0.392 | pizza | 0.539 | | donut | 0.552 | cake | 0.476 | chair | 0.274 | | couch | 0.403 | potted plant | 0.290 | bed | 0.387 | | dining table | 0.193 | toilet | 0.646 | tv | 0.656 | | laptop | 0.676 | mouse | 0.631 | remote | 0.393 | | keyboard | 0.545 | cell phone | 0.417 | microwave | 0.694 | | oven | 0.381 | toaster | 0.473 | sink | 0.424 | | refrigerator | 0.696 | book | 0.145 | clock | 0.557 | | vase | 0.425 | scissors | 0.318 | teddy bear | 0.534 | | hair drier | 0.200 | toothbrush | 0.230 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-17 01:59:22,631 - mmdet - INFO - Exp name: mask_rcnn_flash_internimage_b_fpn_3x_coco_0.4_0.9-4x16.py 2023-11-17 01:59:22,632 - mmdet - INFO - Epoch(val) [19][313] bbox_mAP: 0.4892, bbox_mAP_50: 0.7181, bbox_mAP_75: 0.5400, bbox_mAP_s: 0.3461, bbox_mAP_m: 0.5355, bbox_mAP_l: 0.6267, bbox_mAP_copypaste: 0.4892 0.7181 0.5400 0.3461 0.5355 0.6267, segm_mAP: 0.4408, segm_mAP_50: 0.6857, segm_mAP_75: 0.4756, segm_mAP_s: 0.2566, segm_mAP_m: 0.4834, segm_mAP_l: 0.6221, segm_mAP_copypaste: 0.4408 0.6857 0.4756 0.2566 0.4834 0.6221 2023-11-17 02:00:09,836 - mmdet - INFO - Epoch [20][50/1833] lr: 5.563e-06, eta: 7:30:06, time: 0.944, data_time: 0.092, memory: 10707, loss_rpn_cls: 0.0222, loss_rpn_bbox: 0.0336, loss_cls: 0.1573, acc: 94.0817, loss_bbox: 0.2119, loss_mask: 0.2156, loss: 0.6406 2023-11-17 02:00:53,893 - mmdet - INFO - Epoch [20][100/1833] lr: 5.563e-06, eta: 7:29:23, time: 0.881, data_time: 0.029, memory: 10707, loss_rpn_cls: 0.0221, loss_rpn_bbox: 0.0334, loss_cls: 0.1589, acc: 94.0309, loss_bbox: 0.2116, loss_mask: 0.2147, loss: 0.6407 2023-11-17 02:01:38,256 - mmdet - INFO - Epoch [20][150/1833] lr: 5.563e-06, eta: 7:28:41, time: 0.887, data_time: 0.035, memory: 10707, loss_rpn_cls: 0.0224, loss_rpn_bbox: 0.0327, loss_cls: 0.1580, acc: 94.0468, loss_bbox: 0.2093, loss_mask: 0.2135, loss: 0.6359 2023-11-17 02:02:21,970 - mmdet - INFO - Epoch [20][200/1833] lr: 5.563e-06, eta: 7:27:58, time: 0.874, data_time: 0.035, memory: 10707, loss_rpn_cls: 0.0222, loss_rpn_bbox: 0.0330, loss_cls: 0.1563, acc: 94.1537, loss_bbox: 0.2097, loss_mask: 0.2155, loss: 0.6367 2023-11-17 02:03:07,745 - mmdet - INFO - Epoch [20][250/1833] lr: 5.563e-06, eta: 7:27:16, time: 0.915, data_time: 0.034, memory: 10707, loss_rpn_cls: 0.0218, loss_rpn_bbox: 0.0329, loss_cls: 0.1549, acc: 94.1896, loss_bbox: 0.2081, loss_mask: 0.2163, loss: 0.6339 2023-11-17 02:03:51,702 - mmdet - INFO - Epoch [20][300/1833] lr: 5.563e-06, eta: 7:26:33, time: 0.879, data_time: 0.034, memory: 10707, loss_rpn_cls: 0.0227, loss_rpn_bbox: 0.0338, loss_cls: 0.1567, acc: 94.1548, loss_bbox: 0.2115, loss_mask: 0.2161, loss: 0.6408 2023-11-17 02:04:35,940 - mmdet - INFO - Epoch [20][350/1833] lr: 5.563e-06, eta: 7:25:51, time: 0.885, data_time: 0.033, memory: 10707, loss_rpn_cls: 0.0239, loss_rpn_bbox: 0.0340, loss_cls: 0.1603, acc: 94.0496, loss_bbox: 0.2129, loss_mask: 0.2154, loss: 0.6465 2023-11-17 02:05:20,233 - mmdet - INFO - Epoch [20][400/1833] lr: 5.563e-06, eta: 7:25:08, time: 0.886, data_time: 0.034, memory: 10707, loss_rpn_cls: 0.0236, loss_rpn_bbox: 0.0337, loss_cls: 0.1581, acc: 94.0913, loss_bbox: 0.2105, loss_mask: 0.2161, loss: 0.6420 2023-11-17 02:06:04,103 - mmdet - INFO - Epoch [20][450/1833] lr: 5.563e-06, eta: 7:24:25, time: 0.877, data_time: 0.035, memory: 10707, loss_rpn_cls: 0.0230, loss_rpn_bbox: 0.0335, loss_cls: 0.1576, acc: 94.0938, loss_bbox: 0.2109, loss_mask: 0.2176, loss: 0.6426 2023-11-17 02:06:48,416 - mmdet - INFO - Epoch [20][500/1833] lr: 5.563e-06, eta: 7:23:42, time: 0.886, data_time: 0.031, memory: 10707, loss_rpn_cls: 0.0234, loss_rpn_bbox: 0.0349, loss_cls: 0.1614, acc: 93.9611, loss_bbox: 0.2156, loss_mask: 0.2205, loss: 0.6558 2023-11-17 02:07:33,061 - mmdet - INFO - Epoch [20][550/1833] lr: 5.563e-06, eta: 7:23:00, time: 0.893, data_time: 0.040, memory: 10707, loss_rpn_cls: 0.0225, loss_rpn_bbox: 0.0343, loss_cls: 0.1613, acc: 93.9880, loss_bbox: 0.2129, loss_mask: 0.2186, loss: 0.6496 2023-11-17 02:08:17,003 - mmdet - INFO - Epoch [20][600/1833] lr: 5.563e-06, eta: 7:22:17, time: 0.879, data_time: 0.036, memory: 10707, loss_rpn_cls: 0.0237, loss_rpn_bbox: 0.0341, loss_cls: 0.1588, acc: 94.0473, loss_bbox: 0.2119, loss_mask: 0.2177, loss: 0.6462 2023-11-17 02:09:01,088 - mmdet - INFO - Epoch [20][650/1833] lr: 5.563e-06, eta: 7:21:34, time: 0.882, data_time: 0.030, memory: 10707, loss_rpn_cls: 0.0227, loss_rpn_bbox: 0.0336, loss_cls: 0.1547, acc: 94.2206, loss_bbox: 0.2060, loss_mask: 0.2171, loss: 0.6341 2023-11-17 02:09:44,677 - mmdet - INFO - Epoch [20][700/1833] lr: 5.563e-06, eta: 7:20:51, time: 0.872, data_time: 0.035, memory: 10707, loss_rpn_cls: 0.0233, loss_rpn_bbox: 0.0338, loss_cls: 0.1622, acc: 93.9716, loss_bbox: 0.2126, loss_mask: 0.2187, loss: 0.6505 2023-11-17 02:10:28,701 - mmdet - INFO - Epoch [20][750/1833] lr: 5.563e-06, eta: 7:20:08, time: 0.880, data_time: 0.035, memory: 10707, loss_rpn_cls: 0.0218, loss_rpn_bbox: 0.0333, loss_cls: 0.1565, acc: 94.1016, loss_bbox: 0.2101, loss_mask: 0.2182, loss: 0.6399 2023-11-17 02:11:12,580 - mmdet - INFO - Epoch [20][800/1833] lr: 5.563e-06, eta: 7:19:25, time: 0.878, data_time: 0.036, memory: 10707, loss_rpn_cls: 0.0226, loss_rpn_bbox: 0.0338, loss_cls: 0.1583, acc: 94.0827, loss_bbox: 0.2105, loss_mask: 0.2161, loss: 0.6413 2023-11-17 02:11:56,200 - mmdet - INFO - Epoch [20][850/1833] lr: 5.563e-06, eta: 7:18:42, time: 0.872, data_time: 0.036, memory: 10707, loss_rpn_cls: 0.0233, loss_rpn_bbox: 0.0338, loss_cls: 0.1592, acc: 94.0745, loss_bbox: 0.2124, loss_mask: 0.2182, loss: 0.6469 2023-11-17 02:12:40,674 - mmdet - INFO - Epoch [20][900/1833] lr: 5.563e-06, eta: 7:17:59, time: 0.889, data_time: 0.033, memory: 10707, loss_rpn_cls: 0.0231, loss_rpn_bbox: 0.0344, loss_cls: 0.1593, acc: 94.0832, loss_bbox: 0.2106, loss_mask: 0.2160, loss: 0.6433 2023-11-17 02:13:24,753 - mmdet - INFO - Epoch [20][950/1833] lr: 5.563e-06, eta: 7:17:16, time: 0.882, data_time: 0.035, memory: 10707, loss_rpn_cls: 0.0224, loss_rpn_bbox: 0.0333, loss_cls: 0.1569, acc: 94.1577, loss_bbox: 0.2100, loss_mask: 0.2167, loss: 0.6392 2023-11-17 02:14:08,463 - mmdet - INFO - Epoch [20][1000/1833] lr: 5.563e-06, eta: 7:16:33, time: 0.874, data_time: 0.033, memory: 10707, loss_rpn_cls: 0.0235, loss_rpn_bbox: 0.0338, loss_cls: 0.1610, acc: 94.0287, loss_bbox: 0.2104, loss_mask: 0.2166, loss: 0.6453 2023-11-17 02:14:52,630 - mmdet - INFO - Epoch [20][1050/1833] lr: 5.563e-06, eta: 7:15:50, time: 0.883, data_time: 0.034, memory: 10707, loss_rpn_cls: 0.0234, loss_rpn_bbox: 0.0355, loss_cls: 0.1616, acc: 93.9554, loss_bbox: 0.2155, loss_mask: 0.2179, loss: 0.6538 2023-11-17 02:15:36,516 - mmdet - INFO - Epoch [20][1100/1833] lr: 5.563e-06, eta: 7:15:07, time: 0.878, data_time: 0.035, memory: 10707, loss_rpn_cls: 0.0230, loss_rpn_bbox: 0.0340, loss_cls: 0.1595, acc: 94.0517, loss_bbox: 0.2119, loss_mask: 0.2171, loss: 0.6455 2023-11-17 02:16:20,641 - mmdet - INFO - Epoch [20][1150/1833] lr: 5.563e-06, eta: 7:14:25, time: 0.882, data_time: 0.030, memory: 10707, loss_rpn_cls: 0.0236, loss_rpn_bbox: 0.0338, loss_cls: 0.1618, acc: 93.9769, loss_bbox: 0.2128, loss_mask: 0.2163, loss: 0.6483 2023-11-17 02:17:05,161 - mmdet - INFO - Epoch [20][1200/1833] lr: 5.563e-06, eta: 7:13:42, time: 0.890, data_time: 0.034, memory: 10707, loss_rpn_cls: 0.0221, loss_rpn_bbox: 0.0340, loss_cls: 0.1595, acc: 94.0861, loss_bbox: 0.2094, loss_mask: 0.2141, loss: 0.6391 2023-11-17 02:17:49,106 - mmdet - INFO - Epoch [20][1250/1833] lr: 5.563e-06, eta: 7:12:59, time: 0.879, data_time: 0.033, memory: 10707, loss_rpn_cls: 0.0217, loss_rpn_bbox: 0.0326, loss_cls: 0.1587, acc: 94.0660, loss_bbox: 0.2111, loss_mask: 0.2131, loss: 0.6372 2023-11-17 02:18:33,134 - mmdet - INFO - Epoch [20][1300/1833] lr: 5.563e-06, eta: 7:12:16, time: 0.880, data_time: 0.032, memory: 10707, loss_rpn_cls: 0.0234, loss_rpn_bbox: 0.0341, loss_cls: 0.1610, acc: 93.9941, loss_bbox: 0.2153, loss_mask: 0.2178, loss: 0.6516 2023-11-17 02:19:17,239 - mmdet - INFO - Epoch [20][1350/1833] lr: 5.563e-06, eta: 7:11:33, time: 0.882, data_time: 0.034, memory: 10707, loss_rpn_cls: 0.0250, loss_rpn_bbox: 0.0355, loss_cls: 0.1662, acc: 93.8203, loss_bbox: 0.2184, loss_mask: 0.2175, loss: 0.6626 2023-11-17 02:20:01,116 - mmdet - INFO - Epoch [20][1400/1833] lr: 5.563e-06, eta: 7:10:50, time: 0.878, data_time: 0.032, memory: 10707, loss_rpn_cls: 0.0240, loss_rpn_bbox: 0.0347, loss_cls: 0.1595, acc: 94.1152, loss_bbox: 0.2105, loss_mask: 0.2185, loss: 0.6472 2023-11-17 02:20:45,255 - mmdet - INFO - Epoch [20][1450/1833] lr: 5.563e-06, eta: 7:10:07, time: 0.883, data_time: 0.041, memory: 10707, loss_rpn_cls: 0.0232, loss_rpn_bbox: 0.0347, loss_cls: 0.1582, acc: 94.1580, loss_bbox: 0.2130, loss_mask: 0.2189, loss: 0.6480 2023-11-17 02:21:31,023 - mmdet - INFO - Epoch [20][1500/1833] lr: 5.563e-06, eta: 7:09:26, time: 0.915, data_time: 0.038, memory: 10707, loss_rpn_cls: 0.0223, loss_rpn_bbox: 0.0331, loss_cls: 0.1584, acc: 94.0950, loss_bbox: 0.2100, loss_mask: 0.2146, loss: 0.6384 2023-11-17 02:22:15,174 - mmdet - INFO - Epoch [20][1550/1833] lr: 5.563e-06, eta: 7:08:43, time: 0.883, data_time: 0.034, memory: 10707, loss_rpn_cls: 0.0226, loss_rpn_bbox: 0.0342, loss_cls: 0.1617, acc: 93.9805, loss_bbox: 0.2133, loss_mask: 0.2183, loss: 0.6501 2023-11-17 02:22:59,206 - mmdet - INFO - Epoch [20][1600/1833] lr: 5.563e-06, eta: 7:08:00, time: 0.881, data_time: 0.036, memory: 10707, loss_rpn_cls: 0.0241, loss_rpn_bbox: 0.0350, loss_cls: 0.1638, acc: 93.9217, loss_bbox: 0.2163, loss_mask: 0.2191, loss: 0.6584 2023-11-17 02:23:42,871 - mmdet - INFO - Epoch [20][1650/1833] lr: 5.563e-06, eta: 7:07:17, time: 0.873, data_time: 0.034, memory: 10707, loss_rpn_cls: 0.0231, loss_rpn_bbox: 0.0340, loss_cls: 0.1619, acc: 93.9680, loss_bbox: 0.2139, loss_mask: 0.2177, loss: 0.6506 2023-11-17 02:24:27,117 - mmdet - INFO - Epoch [20][1700/1833] lr: 5.563e-06, eta: 7:06:34, time: 0.885, data_time: 0.037, memory: 10707, loss_rpn_cls: 0.0226, loss_rpn_bbox: 0.0324, loss_cls: 0.1588, acc: 94.0960, loss_bbox: 0.2109, loss_mask: 0.2133, loss: 0.6380 2023-11-17 02:25:11,040 - mmdet - INFO - Epoch [20][1750/1833] lr: 5.563e-06, eta: 7:05:51, time: 0.878, data_time: 0.033, memory: 10707, loss_rpn_cls: 0.0215, loss_rpn_bbox: 0.0327, loss_cls: 0.1583, acc: 94.0780, loss_bbox: 0.2093, loss_mask: 0.2140, loss: 0.6359 2023-11-17 02:25:55,810 - mmdet - INFO - Epoch [20][1800/1833] lr: 5.563e-06, eta: 7:05:09, time: 0.895, data_time: 0.033, memory: 10707, loss_rpn_cls: 0.0230, loss_rpn_bbox: 0.0329, loss_cls: 0.1571, acc: 94.1938, loss_bbox: 0.2074, loss_mask: 0.2132, loss: 0.6336 2023-11-17 02:26:24,976 - mmdet - INFO - Saving checkpoint at 20 epochs 2023-11-17 02:26:56,865 - mmdet - INFO - Evaluating bbox... 2023-11-17 02:27:28,792 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.493 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.721 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.546 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.355 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.536 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.638 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.621 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.621 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.621 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.480 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.660 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.763 2023-11-17 02:27:28,794 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.583 | bicycle | 0.397 | car | 0.495 | | motorcycle | 0.498 | airplane | 0.704 | bus | 0.687 | | train | 0.705 | truck | 0.461 | boat | 0.348 | | traffic light | 0.314 | fire hydrant | 0.733 | stop sign | 0.668 | | parking meter | 0.496 | bench | 0.312 | bird | 0.430 | | cat | 0.747 | dog | 0.692 | horse | 0.647 | | sheep | 0.603 | cow | 0.644 | elephant | 0.690 | | bear | 0.778 | zebra | 0.685 | giraffe | 0.697 | | backpack | 0.238 | umbrella | 0.473 | handbag | 0.250 | | tie | 0.400 | suitcase | 0.499 | frisbee | 0.723 | | skis | 0.316 | snowboard | 0.462 | sports ball | 0.474 | | kite | 0.482 | baseball bat | 0.422 | baseball glove | 0.443 | | skateboard | 0.595 | surfboard | 0.488 | tennis racket | 0.560 | | bottle | 0.473 | wine glass | 0.432 | cup | 0.520 | | fork | 0.489 | knife | 0.321 | spoon | 0.282 | | bowl | 0.487 | banana | 0.311 | apple | 0.274 | | sandwich | 0.487 | orange | 0.369 | broccoli | 0.285 | | carrot | 0.274 | hot dog | 0.461 | pizza | 0.561 | | donut | 0.556 | cake | 0.463 | chair | 0.367 | | couch | 0.492 | potted plant | 0.341 | bed | 0.483 | | dining table | 0.330 | toilet | 0.677 | tv | 0.640 | | laptop | 0.692 | mouse | 0.648 | remote | 0.451 | | keyboard | 0.557 | cell phone | 0.475 | microwave | 0.667 | | oven | 0.412 | toaster | 0.478 | sink | 0.457 | | refrigerator | 0.674 | book | 0.196 | clock | 0.536 | | vase | 0.420 | scissors | 0.450 | teddy bear | 0.579 | | hair drier | 0.188 | toothbrush | 0.352 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-17 02:27:28,794 - mmdet - INFO - Evaluating segm... 2023-11-17 02:28:01,884 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.446 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.690 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.482 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.266 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.485 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.638 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.567 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.567 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.567 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.407 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.610 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.723 2023-11-17 02:28:01,887 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.508 | bicycle | 0.247 | car | 0.459 | | motorcycle | 0.415 | airplane | 0.562 | bus | 0.679 | | train | 0.692 | truck | 0.459 | boat | 0.325 | | traffic light | 0.303 | fire hydrant | 0.698 | stop sign | 0.658 | | parking meter | 0.521 | bench | 0.240 | bird | 0.347 | | cat | 0.742 | dog | 0.649 | horse | 0.487 | | sheep | 0.540 | cow | 0.557 | elephant | 0.640 | | bear | 0.775 | zebra | 0.598 | giraffe | 0.566 | | backpack | 0.241 | umbrella | 0.526 | handbag | 0.241 | | tie | 0.366 | suitcase | 0.518 | frisbee | 0.665 | | skis | 0.061 | snowboard | 0.292 | sports ball | 0.462 | | kite | 0.336 | baseball bat | 0.311 | baseball glove | 0.464 | | skateboard | 0.397 | surfboard | 0.415 | tennis racket | 0.596 | | bottle | 0.457 | wine glass | 0.385 | cup | 0.521 | | fork | 0.257 | knife | 0.220 | spoon | 0.212 | | bowl | 0.456 | banana | 0.265 | apple | 0.272 | | sandwich | 0.505 | orange | 0.370 | broccoli | 0.263 | | carrot | 0.245 | hot dog | 0.377 | pizza | 0.545 | | donut | 0.560 | cake | 0.468 | chair | 0.272 | | couch | 0.415 | potted plant | 0.294 | bed | 0.392 | | dining table | 0.194 | toilet | 0.664 | tv | 0.668 | | laptop | 0.692 | mouse | 0.629 | remote | 0.414 | | keyboard | 0.544 | cell phone | 0.447 | microwave | 0.683 | | oven | 0.396 | toaster | 0.536 | sink | 0.439 | | refrigerator | 0.700 | book | 0.148 | clock | 0.532 | | vase | 0.412 | scissors | 0.334 | teddy bear | 0.543 | | hair drier | 0.177 | toothbrush | 0.238 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-17 02:28:02,398 - mmdet - INFO - The previous best checkpoint /mnt/petrelfs/lizhiqi/DINO/detection/work_dirs/mask_rcnn_flash_internimage_b_fpn_3x_cocoo_0.4_0.9_4x16/best_bbox_mAP_epoch_18.pth was removed 2023-11-17 02:28:06,310 - mmdet - INFO - Now best checkpoint is saved as best_bbox_mAP_epoch_20.pth. 2023-11-17 02:28:06,310 - mmdet - INFO - Best bbox_mAP is 0.4930 at 20 epoch. 2023-11-17 02:28:06,310 - mmdet - INFO - Exp name: mask_rcnn_flash_internimage_b_fpn_3x_coco_0.4_0.9-4x16.py 2023-11-17 02:28:06,310 - mmdet - INFO - Epoch(val) [20][313] bbox_mAP: 0.4930, bbox_mAP_50: 0.7206, bbox_mAP_75: 0.5458, bbox_mAP_s: 0.3546, bbox_mAP_m: 0.5361, bbox_mAP_l: 0.6381, bbox_mAP_copypaste: 0.4930 0.7206 0.5458 0.3546 0.5361 0.6381, segm_mAP: 0.4462, segm_mAP_50: 0.6898, segm_mAP_75: 0.4820, segm_mAP_s: 0.2660, segm_mAP_m: 0.4845, segm_mAP_l: 0.6377, segm_mAP_copypaste: 0.4462 0.6898 0.4820 0.2660 0.4845 0.6377 2023-11-17 02:28:53,035 - mmdet - INFO - Epoch [21][50/1833] lr: 5.563e-06, eta: 7:03:36, time: 0.934, data_time: 0.090, memory: 10707, loss_rpn_cls: 0.0216, loss_rpn_bbox: 0.0329, loss_cls: 0.1548, acc: 94.2504, loss_bbox: 0.2087, loss_mask: 0.2132, loss: 0.6311 2023-11-17 02:29:36,499 - mmdet - INFO - Epoch [21][100/1833] lr: 5.563e-06, eta: 7:02:53, time: 0.869, data_time: 0.031, memory: 10707, loss_rpn_cls: 0.0232, loss_rpn_bbox: 0.0329, loss_cls: 0.1567, acc: 94.1564, loss_bbox: 0.2075, loss_mask: 0.2141, loss: 0.6344 2023-11-17 02:30:20,385 - mmdet - INFO - Epoch [21][150/1833] lr: 5.563e-06, eta: 7:02:10, time: 0.877, data_time: 0.033, memory: 10707, loss_rpn_cls: 0.0229, loss_rpn_bbox: 0.0333, loss_cls: 0.1571, acc: 94.0905, loss_bbox: 0.2118, loss_mask: 0.2164, loss: 0.6415 2023-11-17 02:31:04,797 - mmdet - INFO - Epoch [21][200/1833] lr: 5.563e-06, eta: 7:01:27, time: 0.889, data_time: 0.038, memory: 10707, loss_rpn_cls: 0.0232, loss_rpn_bbox: 0.0334, loss_cls: 0.1557, acc: 94.1842, loss_bbox: 0.2073, loss_mask: 0.2158, loss: 0.6355 2023-11-17 02:31:54,279 - mmdet - INFO - Epoch [21][250/1833] lr: 5.563e-06, eta: 7:00:49, time: 0.990, data_time: 0.102, memory: 10707, loss_rpn_cls: 0.0237, loss_rpn_bbox: 0.0343, loss_cls: 0.1587, acc: 94.0863, loss_bbox: 0.2122, loss_mask: 0.2165, loss: 0.6454 2023-11-17 02:32:50,298 - mmdet - INFO - Epoch [21][300/1833] lr: 5.563e-06, eta: 7:00:15, time: 1.120, data_time: 0.315, memory: 10707, loss_rpn_cls: 0.0226, loss_rpn_bbox: 0.0334, loss_cls: 0.1550, acc: 94.1811, loss_bbox: 0.2072, loss_mask: 0.2184, loss: 0.6367 2023-11-17 02:33:34,119 - mmdet - INFO - Epoch [21][350/1833] lr: 5.563e-06, eta: 6:59:32, time: 0.876, data_time: 0.034, memory: 10707, loss_rpn_cls: 0.0229, loss_rpn_bbox: 0.0330, loss_cls: 0.1545, acc: 94.1896, loss_bbox: 0.2066, loss_mask: 0.2156, loss: 0.6326 2023-11-17 02:34:20,584 - mmdet - INFO - Epoch [21][400/1833] lr: 5.563e-06, eta: 6:58:51, time: 0.929, data_time: 0.032, memory: 10707, loss_rpn_cls: 0.0230, loss_rpn_bbox: 0.0333, loss_cls: 0.1541, acc: 94.2156, loss_bbox: 0.2060, loss_mask: 0.2142, loss: 0.6306 2023-11-17 02:35:04,924 - mmdet - INFO - Epoch [21][450/1833] lr: 5.563e-06, eta: 6:58:08, time: 0.887, data_time: 0.034, memory: 10707, loss_rpn_cls: 0.0223, loss_rpn_bbox: 0.0326, loss_cls: 0.1560, acc: 94.1481, loss_bbox: 0.2086, loss_mask: 0.2158, loss: 0.6352 2023-11-17 02:35:49,306 - mmdet - INFO - Epoch [21][500/1833] lr: 5.563e-06, eta: 6:57:25, time: 0.888, data_time: 0.034, memory: 10707, loss_rpn_cls: 0.0238, loss_rpn_bbox: 0.0332, loss_cls: 0.1572, acc: 94.1367, loss_bbox: 0.2093, loss_mask: 0.2152, loss: 0.6387 2023-11-17 02:36:33,452 - mmdet - INFO - Epoch [21][550/1833] lr: 5.563e-06, eta: 6:56:43, time: 0.883, data_time: 0.035, memory: 10707, loss_rpn_cls: 0.0217, loss_rpn_bbox: 0.0326, loss_cls: 0.1565, acc: 94.1249, loss_bbox: 0.2094, loss_mask: 0.2129, loss: 0.6331 2023-11-17 02:37:17,647 - mmdet - INFO - Epoch [21][600/1833] lr: 5.563e-06, eta: 6:56:00, time: 0.884, data_time: 0.032, memory: 10707, loss_rpn_cls: 0.0225, loss_rpn_bbox: 0.0341, loss_cls: 0.1611, acc: 93.9504, loss_bbox: 0.2163, loss_mask: 0.2149, loss: 0.6489 2023-11-17 02:38:02,287 - mmdet - INFO - Epoch [21][650/1833] lr: 5.563e-06, eta: 6:55:17, time: 0.893, data_time: 0.033, memory: 10707, loss_rpn_cls: 0.0212, loss_rpn_bbox: 0.0335, loss_cls: 0.1545, acc: 94.2038, loss_bbox: 0.2086, loss_mask: 0.2126, loss: 0.6304 2023-11-17 02:38:46,803 - mmdet - INFO - Epoch [21][700/1833] lr: 5.563e-06, eta: 6:54:34, time: 0.890, data_time: 0.034, memory: 10707, loss_rpn_cls: 0.0217, loss_rpn_bbox: 0.0330, loss_cls: 0.1545, acc: 94.2086, loss_bbox: 0.2087, loss_mask: 0.2129, loss: 0.6308 2023-11-17 02:39:30,929 - mmdet - INFO - Epoch [21][750/1833] lr: 5.563e-06, eta: 6:53:52, time: 0.883, data_time: 0.033, memory: 10707, loss_rpn_cls: 0.0222, loss_rpn_bbox: 0.0332, loss_cls: 0.1550, acc: 94.1860, loss_bbox: 0.2122, loss_mask: 0.2171, loss: 0.6398 2023-11-17 02:40:18,662 - mmdet - INFO - Epoch [21][800/1833] lr: 5.563e-06, eta: 6:53:11, time: 0.954, data_time: 0.035, memory: 10707, loss_rpn_cls: 0.0223, loss_rpn_bbox: 0.0338, loss_cls: 0.1567, acc: 94.1310, loss_bbox: 0.2109, loss_mask: 0.2153, loss: 0.6391 2023-11-17 02:41:02,700 - mmdet - INFO - Epoch [21][850/1833] lr: 5.563e-06, eta: 6:52:28, time: 0.881, data_time: 0.032, memory: 10707, loss_rpn_cls: 0.0222, loss_rpn_bbox: 0.0328, loss_cls: 0.1541, acc: 94.2898, loss_bbox: 0.2051, loss_mask: 0.2164, loss: 0.6305 2023-11-17 02:41:48,432 - mmdet - INFO - Epoch [21][900/1833] lr: 5.563e-06, eta: 6:51:47, time: 0.915, data_time: 0.037, memory: 10707, loss_rpn_cls: 0.0224, loss_rpn_bbox: 0.0330, loss_cls: 0.1578, acc: 94.0962, loss_bbox: 0.2128, loss_mask: 0.2180, loss: 0.6440 2023-11-17 02:42:32,452 - mmdet - INFO - Epoch [21][950/1833] lr: 5.563e-06, eta: 6:51:04, time: 0.880, data_time: 0.034, memory: 10707, loss_rpn_cls: 0.0235, loss_rpn_bbox: 0.0342, loss_cls: 0.1583, acc: 94.0937, loss_bbox: 0.2103, loss_mask: 0.2159, loss: 0.6422 2023-11-17 02:43:16,869 - mmdet - INFO - Epoch [21][1000/1833] lr: 5.563e-06, eta: 6:50:21, time: 0.888, data_time: 0.030, memory: 10707, loss_rpn_cls: 0.0217, loss_rpn_bbox: 0.0332, loss_cls: 0.1553, acc: 94.1772, loss_bbox: 0.2083, loss_mask: 0.2149, loss: 0.6334 2023-11-17 02:44:01,311 - mmdet - INFO - Epoch [21][1050/1833] lr: 5.563e-06, eta: 6:49:38, time: 0.889, data_time: 0.031, memory: 10707, loss_rpn_cls: 0.0228, loss_rpn_bbox: 0.0339, loss_cls: 0.1606, acc: 94.0500, loss_bbox: 0.2130, loss_mask: 0.2179, loss: 0.6482 2023-11-17 02:44:46,146 - mmdet - INFO - Epoch [21][1100/1833] lr: 5.563e-06, eta: 6:48:56, time: 0.897, data_time: 0.033, memory: 10707, loss_rpn_cls: 0.0228, loss_rpn_bbox: 0.0342, loss_cls: 0.1571, acc: 94.1259, loss_bbox: 0.2116, loss_mask: 0.2142, loss: 0.6399 2023-11-17 02:45:33,237 - mmdet - INFO - Epoch [21][1150/1833] lr: 5.563e-06, eta: 6:48:15, time: 0.942, data_time: 0.028, memory: 10707, loss_rpn_cls: 0.0230, loss_rpn_bbox: 0.0334, loss_cls: 0.1575, acc: 94.1311, loss_bbox: 0.2108, loss_mask: 0.2160, loss: 0.6407 2023-11-17 02:46:17,806 - mmdet - INFO - Epoch [21][1200/1833] lr: 5.563e-06, eta: 6:47:32, time: 0.891, data_time: 0.030, memory: 10707, loss_rpn_cls: 0.0241, loss_rpn_bbox: 0.0336, loss_cls: 0.1578, acc: 94.0729, loss_bbox: 0.2110, loss_mask: 0.2154, loss: 0.6421 2023-11-17 02:47:02,392 - mmdet - INFO - Epoch [21][1250/1833] lr: 5.563e-06, eta: 6:46:50, time: 0.892, data_time: 0.036, memory: 10707, loss_rpn_cls: 0.0222, loss_rpn_bbox: 0.0328, loss_cls: 0.1553, acc: 94.2178, loss_bbox: 0.2064, loss_mask: 0.2166, loss: 0.6333 2023-11-17 02:47:47,039 - mmdet - INFO - Epoch [21][1300/1833] lr: 5.563e-06, eta: 6:46:07, time: 0.893, data_time: 0.033, memory: 10707, loss_rpn_cls: 0.0234, loss_rpn_bbox: 0.0339, loss_cls: 0.1585, acc: 94.0854, loss_bbox: 0.2104, loss_mask: 0.2194, loss: 0.6455 2023-11-17 02:48:30,723 - mmdet - INFO - Epoch [21][1350/1833] lr: 5.563e-06, eta: 6:45:24, time: 0.874, data_time: 0.031, memory: 10707, loss_rpn_cls: 0.0218, loss_rpn_bbox: 0.0335, loss_cls: 0.1576, acc: 94.0942, loss_bbox: 0.2089, loss_mask: 0.2128, loss: 0.6346 2023-11-17 02:49:14,485 - mmdet - INFO - Epoch [21][1400/1833] lr: 5.563e-06, eta: 6:44:41, time: 0.875, data_time: 0.034, memory: 10707, loss_rpn_cls: 0.0230, loss_rpn_bbox: 0.0338, loss_cls: 0.1587, acc: 94.0921, loss_bbox: 0.2098, loss_mask: 0.2171, loss: 0.6424 2023-11-17 02:49:58,581 - mmdet - INFO - Epoch [21][1450/1833] lr: 5.563e-06, eta: 6:43:58, time: 0.882, data_time: 0.033, memory: 10707, loss_rpn_cls: 0.0225, loss_rpn_bbox: 0.0323, loss_cls: 0.1552, acc: 94.2036, loss_bbox: 0.2080, loss_mask: 0.2173, loss: 0.6353 2023-11-17 02:50:42,875 - mmdet - INFO - Epoch [21][1500/1833] lr: 5.563e-06, eta: 6:43:15, time: 0.886, data_time: 0.038, memory: 10707, loss_rpn_cls: 0.0228, loss_rpn_bbox: 0.0337, loss_cls: 0.1603, acc: 93.9972, loss_bbox: 0.2149, loss_mask: 0.2174, loss: 0.6491 2023-11-17 02:51:27,256 - mmdet - INFO - Epoch [21][1550/1833] lr: 5.563e-06, eta: 6:42:32, time: 0.888, data_time: 0.036, memory: 10707, loss_rpn_cls: 0.0230, loss_rpn_bbox: 0.0335, loss_cls: 0.1548, acc: 94.1943, loss_bbox: 0.2064, loss_mask: 0.2161, loss: 0.6338 2023-11-17 02:52:11,282 - mmdet - INFO - Epoch [21][1600/1833] lr: 5.563e-06, eta: 6:41:49, time: 0.880, data_time: 0.035, memory: 10707, loss_rpn_cls: 0.0219, loss_rpn_bbox: 0.0333, loss_cls: 0.1553, acc: 94.1387, loss_bbox: 0.2088, loss_mask: 0.2157, loss: 0.6350 2023-11-17 02:52:55,651 - mmdet - INFO - Epoch [21][1650/1833] lr: 5.563e-06, eta: 6:41:06, time: 0.887, data_time: 0.035, memory: 10707, loss_rpn_cls: 0.0225, loss_rpn_bbox: 0.0338, loss_cls: 0.1609, acc: 94.0194, loss_bbox: 0.2120, loss_mask: 0.2160, loss: 0.6452 2023-11-17 02:53:39,609 - mmdet - INFO - Epoch [21][1700/1833] lr: 5.563e-06, eta: 6:40:23, time: 0.879, data_time: 0.038, memory: 10707, loss_rpn_cls: 0.0232, loss_rpn_bbox: 0.0347, loss_cls: 0.1615, acc: 93.9633, loss_bbox: 0.2140, loss_mask: 0.2189, loss: 0.6523 2023-11-17 02:54:23,698 - mmdet - INFO - Epoch [21][1750/1833] lr: 5.563e-06, eta: 6:39:40, time: 0.882, data_time: 0.036, memory: 10707, loss_rpn_cls: 0.0212, loss_rpn_bbox: 0.0331, loss_cls: 0.1556, acc: 94.1757, loss_bbox: 0.2096, loss_mask: 0.2151, loss: 0.6345 2023-11-17 02:55:08,348 - mmdet - INFO - Epoch [21][1800/1833] lr: 5.563e-06, eta: 6:38:57, time: 0.893, data_time: 0.035, memory: 10707, loss_rpn_cls: 0.0232, loss_rpn_bbox: 0.0345, loss_cls: 0.1585, acc: 94.0579, loss_bbox: 0.2121, loss_mask: 0.2155, loss: 0.6438 2023-11-17 02:55:37,838 - mmdet - INFO - Saving checkpoint at 21 epochs 2023-11-17 02:56:11,423 - mmdet - INFO - Evaluating bbox... 2023-11-17 02:56:40,367 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.492 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.721 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.541 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.350 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.534 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.638 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.614 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.614 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.614 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.466 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.655 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.756 2023-11-17 02:56:40,370 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.583 | bicycle | 0.396 | car | 0.494 | | motorcycle | 0.498 | airplane | 0.695 | bus | 0.689 | | train | 0.710 | truck | 0.465 | boat | 0.341 | | traffic light | 0.313 | fire hydrant | 0.736 | stop sign | 0.653 | | parking meter | 0.510 | bench | 0.303 | bird | 0.424 | | cat | 0.750 | dog | 0.704 | horse | 0.644 | | sheep | 0.613 | cow | 0.648 | elephant | 0.701 | | bear | 0.734 | zebra | 0.686 | giraffe | 0.695 | | backpack | 0.237 | umbrella | 0.463 | handbag | 0.256 | | tie | 0.408 | suitcase | 0.487 | frisbee | 0.719 | | skis | 0.321 | snowboard | 0.487 | sports ball | 0.490 | | kite | 0.487 | baseball bat | 0.431 | baseball glove | 0.457 | | skateboard | 0.607 | surfboard | 0.495 | tennis racket | 0.562 | | bottle | 0.471 | wine glass | 0.420 | cup | 0.521 | | fork | 0.478 | knife | 0.316 | spoon | 0.290 | | bowl | 0.484 | banana | 0.299 | apple | 0.283 | | sandwich | 0.489 | orange | 0.373 | broccoli | 0.276 | | carrot | 0.258 | hot dog | 0.443 | pizza | 0.573 | | donut | 0.559 | cake | 0.468 | chair | 0.374 | | couch | 0.495 | potted plant | 0.360 | bed | 0.490 | | dining table | 0.313 | toilet | 0.674 | tv | 0.632 | | laptop | 0.678 | mouse | 0.641 | remote | 0.458 | | keyboard | 0.557 | cell phone | 0.471 | microwave | 0.653 | | oven | 0.400 | toaster | 0.461 | sink | 0.434 | | refrigerator | 0.670 | book | 0.194 | clock | 0.556 | | vase | 0.430 | scissors | 0.435 | teddy bear | 0.548 | | hair drier | 0.252 | toothbrush | 0.325 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-17 02:56:40,370 - mmdet - INFO - Evaluating segm... 2023-11-17 02:57:14,694 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.442 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.689 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.479 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.259 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.481 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.629 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.557 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.557 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.557 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.391 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.602 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.714 2023-11-17 02:57:14,697 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.508 | bicycle | 0.238 | car | 0.446 | | motorcycle | 0.395 | airplane | 0.550 | bus | 0.676 | | train | 0.692 | truck | 0.453 | boat | 0.315 | | traffic light | 0.296 | fire hydrant | 0.698 | stop sign | 0.644 | | parking meter | 0.528 | bench | 0.233 | bird | 0.347 | | cat | 0.739 | dog | 0.664 | horse | 0.478 | | sheep | 0.540 | cow | 0.547 | elephant | 0.635 | | bear | 0.718 | zebra | 0.585 | giraffe | 0.556 | | backpack | 0.233 | umbrella | 0.517 | handbag | 0.233 | | tie | 0.366 | suitcase | 0.499 | frisbee | 0.675 | | skis | 0.062 | snowboard | 0.306 | sports ball | 0.461 | | kite | 0.337 | baseball bat | 0.333 | baseball glove | 0.472 | | skateboard | 0.403 | surfboard | 0.403 | tennis racket | 0.587 | | bottle | 0.452 | wine glass | 0.382 | cup | 0.515 | | fork | 0.240 | knife | 0.202 | spoon | 0.205 | | bowl | 0.451 | banana | 0.247 | apple | 0.278 | | sandwich | 0.512 | orange | 0.365 | broccoli | 0.254 | | carrot | 0.229 | hot dog | 0.331 | pizza | 0.545 | | donut | 0.558 | cake | 0.479 | chair | 0.270 | | couch | 0.422 | potted plant | 0.303 | bed | 0.401 | | dining table | 0.188 | toilet | 0.651 | tv | 0.664 | | laptop | 0.677 | mouse | 0.622 | remote | 0.403 | | keyboard | 0.542 | cell phone | 0.440 | microwave | 0.674 | | oven | 0.387 | toaster | 0.546 | sink | 0.409 | | refrigerator | 0.685 | book | 0.145 | clock | 0.555 | | vase | 0.419 | scissors | 0.314 | teddy bear | 0.537 | | hair drier | 0.247 | toothbrush | 0.224 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-17 02:57:15,162 - mmdet - INFO - Exp name: mask_rcnn_flash_internimage_b_fpn_3x_coco_0.4_0.9-4x16.py 2023-11-17 02:57:15,162 - mmdet - INFO - Epoch(val) [21][313] bbox_mAP: 0.4924, bbox_mAP_50: 0.7212, bbox_mAP_75: 0.5411, bbox_mAP_s: 0.3503, bbox_mAP_m: 0.5338, bbox_mAP_l: 0.6381, bbox_mAP_copypaste: 0.4924 0.7212 0.5411 0.3503 0.5338 0.6381, segm_mAP: 0.4417, segm_mAP_50: 0.6895, segm_mAP_75: 0.4792, segm_mAP_s: 0.2588, segm_mAP_m: 0.4810, segm_mAP_l: 0.6286, segm_mAP_copypaste: 0.4417 0.6895 0.4792 0.2588 0.4810 0.6286 2023-11-17 02:58:01,946 - mmdet - INFO - Epoch [22][50/1833] lr: 5.563e-06, eta: 6:37:27, time: 0.935, data_time: 0.093, memory: 10707, loss_rpn_cls: 0.0225, loss_rpn_bbox: 0.0342, loss_cls: 0.1538, acc: 94.2289, loss_bbox: 0.2075, loss_mask: 0.2138, loss: 0.6318 2023-11-17 02:58:45,826 - mmdet - INFO - Epoch [22][100/1833] lr: 5.563e-06, eta: 6:36:44, time: 0.878, data_time: 0.042, memory: 10707, loss_rpn_cls: 0.0232, loss_rpn_bbox: 0.0341, loss_cls: 0.1560, acc: 94.1962, loss_bbox: 0.2096, loss_mask: 0.2129, loss: 0.6359 2023-11-17 02:59:29,875 - mmdet - INFO - Epoch [22][150/1833] lr: 5.563e-06, eta: 6:36:01, time: 0.881, data_time: 0.035, memory: 10707, loss_rpn_cls: 0.0209, loss_rpn_bbox: 0.0318, loss_cls: 0.1488, acc: 94.4114, loss_bbox: 0.2015, loss_mask: 0.2104, loss: 0.6134 2023-11-17 03:00:13,892 - mmdet - INFO - Epoch [22][200/1833] lr: 5.563e-06, eta: 6:35:18, time: 0.880, data_time: 0.034, memory: 10707, loss_rpn_cls: 0.0231, loss_rpn_bbox: 0.0345, loss_cls: 0.1583, acc: 94.0839, loss_bbox: 0.2102, loss_mask: 0.2184, loss: 0.6446 2023-11-17 03:00:58,265 - mmdet - INFO - Epoch [22][250/1833] lr: 5.563e-06, eta: 6:34:35, time: 0.887, data_time: 0.030, memory: 10707, loss_rpn_cls: 0.0230, loss_rpn_bbox: 0.0330, loss_cls: 0.1555, acc: 94.2174, loss_bbox: 0.2061, loss_mask: 0.2135, loss: 0.6311 2023-11-17 03:01:42,186 - mmdet - INFO - Epoch [22][300/1833] lr: 5.563e-06, eta: 6:33:52, time: 0.878, data_time: 0.032, memory: 10707, loss_rpn_cls: 0.0232, loss_rpn_bbox: 0.0345, loss_cls: 0.1553, acc: 94.1711, loss_bbox: 0.2089, loss_mask: 0.2142, loss: 0.6361 2023-11-17 03:02:26,202 - mmdet - INFO - Epoch [22][350/1833] lr: 5.563e-06, eta: 6:33:09, time: 0.880, data_time: 0.038, memory: 10707, loss_rpn_cls: 0.0220, loss_rpn_bbox: 0.0337, loss_cls: 0.1557, acc: 94.1982, loss_bbox: 0.2094, loss_mask: 0.2155, loss: 0.6363 2023-11-17 03:03:10,429 - mmdet - INFO - Epoch [22][400/1833] lr: 5.563e-06, eta: 6:32:26, time: 0.885, data_time: 0.028, memory: 10707, loss_rpn_cls: 0.0222, loss_rpn_bbox: 0.0327, loss_cls: 0.1557, acc: 94.1570, loss_bbox: 0.2079, loss_mask: 0.2172, loss: 0.6357 2023-11-17 03:03:54,685 - mmdet - INFO - Epoch [22][450/1833] lr: 5.563e-06, eta: 6:31:43, time: 0.885, data_time: 0.036, memory: 10707, loss_rpn_cls: 0.0224, loss_rpn_bbox: 0.0331, loss_cls: 0.1567, acc: 94.1174, loss_bbox: 0.2094, loss_mask: 0.2154, loss: 0.6371 2023-11-17 03:04:39,042 - mmdet - INFO - Epoch [22][500/1833] lr: 5.563e-06, eta: 6:31:00, time: 0.887, data_time: 0.034, memory: 10707, loss_rpn_cls: 0.0230, loss_rpn_bbox: 0.0338, loss_cls: 0.1587, acc: 94.0490, loss_bbox: 0.2136, loss_mask: 0.2162, loss: 0.6454 2023-11-17 03:05:23,315 - mmdet - INFO - Epoch [22][550/1833] lr: 5.563e-06, eta: 6:30:17, time: 0.885, data_time: 0.039, memory: 10707, loss_rpn_cls: 0.0233, loss_rpn_bbox: 0.0348, loss_cls: 0.1584, acc: 94.0833, loss_bbox: 0.2135, loss_mask: 0.2154, loss: 0.6454 2023-11-17 03:06:07,787 - mmdet - INFO - Epoch [22][600/1833] lr: 5.563e-06, eta: 6:29:34, time: 0.889, data_time: 0.035, memory: 10707, loss_rpn_cls: 0.0227, loss_rpn_bbox: 0.0331, loss_cls: 0.1567, acc: 94.1537, loss_bbox: 0.2100, loss_mask: 0.2149, loss: 0.6375 2023-11-17 03:06:51,788 - mmdet - INFO - Epoch [22][650/1833] lr: 5.563e-06, eta: 6:28:51, time: 0.880, data_time: 0.038, memory: 10707, loss_rpn_cls: 0.0222, loss_rpn_bbox: 0.0335, loss_cls: 0.1558, acc: 94.1727, loss_bbox: 0.2089, loss_mask: 0.2150, loss: 0.6355 2023-11-17 03:07:35,770 - mmdet - INFO - Epoch [22][700/1833] lr: 5.563e-06, eta: 6:28:08, time: 0.880, data_time: 0.047, memory: 10707, loss_rpn_cls: 0.0220, loss_rpn_bbox: 0.0329, loss_cls: 0.1507, acc: 94.3192, loss_bbox: 0.2028, loss_mask: 0.2113, loss: 0.6197 2023-11-17 03:08:20,127 - mmdet - INFO - Epoch [22][750/1833] lr: 5.563e-06, eta: 6:27:25, time: 0.887, data_time: 0.034, memory: 10707, loss_rpn_cls: 0.0225, loss_rpn_bbox: 0.0339, loss_cls: 0.1584, acc: 94.0912, loss_bbox: 0.2090, loss_mask: 0.2132, loss: 0.6370 2023-11-17 03:09:04,230 - mmdet - INFO - Epoch [22][800/1833] lr: 5.563e-06, eta: 6:26:42, time: 0.883, data_time: 0.038, memory: 10707, loss_rpn_cls: 0.0231, loss_rpn_bbox: 0.0343, loss_cls: 0.1583, acc: 94.0691, loss_bbox: 0.2119, loss_mask: 0.2143, loss: 0.6419 2023-11-17 03:09:48,426 - mmdet - INFO - Epoch [22][850/1833] lr: 5.563e-06, eta: 6:25:59, time: 0.884, data_time: 0.036, memory: 10707, loss_rpn_cls: 0.0226, loss_rpn_bbox: 0.0331, loss_cls: 0.1534, acc: 94.2380, loss_bbox: 0.2073, loss_mask: 0.2131, loss: 0.6295 2023-11-17 03:10:32,143 - mmdet - INFO - Epoch [22][900/1833] lr: 5.563e-06, eta: 6:25:16, time: 0.874, data_time: 0.034, memory: 10707, loss_rpn_cls: 0.0225, loss_rpn_bbox: 0.0323, loss_cls: 0.1529, acc: 94.3116, loss_bbox: 0.2062, loss_mask: 0.2162, loss: 0.6300 2023-11-17 03:11:15,926 - mmdet - INFO - Epoch [22][950/1833] lr: 5.563e-06, eta: 6:24:33, time: 0.876, data_time: 0.036, memory: 10707, loss_rpn_cls: 0.0210, loss_rpn_bbox: 0.0315, loss_cls: 0.1509, acc: 94.3953, loss_bbox: 0.2015, loss_mask: 0.2172, loss: 0.6221 2023-11-17 03:12:00,198 - mmdet - INFO - Epoch [22][1000/1833] lr: 5.563e-06, eta: 6:23:50, time: 0.885, data_time: 0.036, memory: 10707, loss_rpn_cls: 0.0216, loss_rpn_bbox: 0.0337, loss_cls: 0.1554, acc: 94.1628, loss_bbox: 0.2112, loss_mask: 0.2160, loss: 0.6379 2023-11-17 03:12:44,391 - mmdet - INFO - Epoch [22][1050/1833] lr: 5.563e-06, eta: 6:23:07, time: 0.884, data_time: 0.040, memory: 10707, loss_rpn_cls: 0.0222, loss_rpn_bbox: 0.0326, loss_cls: 0.1561, acc: 94.1784, loss_bbox: 0.2080, loss_mask: 0.2142, loss: 0.6331 2023-11-17 03:13:29,089 - mmdet - INFO - Epoch [22][1100/1833] lr: 5.563e-06, eta: 6:22:24, time: 0.894, data_time: 0.031, memory: 10707, loss_rpn_cls: 0.0212, loss_rpn_bbox: 0.0317, loss_cls: 0.1559, acc: 94.1454, loss_bbox: 0.2067, loss_mask: 0.2163, loss: 0.6317 2023-11-17 03:14:14,086 - mmdet - INFO - Epoch [22][1150/1833] lr: 5.563e-06, eta: 6:21:42, time: 0.900, data_time: 0.033, memory: 10707, loss_rpn_cls: 0.0227, loss_rpn_bbox: 0.0338, loss_cls: 0.1600, acc: 93.9879, loss_bbox: 0.2118, loss_mask: 0.2151, loss: 0.6433 2023-11-17 03:14:58,250 - mmdet - INFO - Epoch [22][1200/1833] lr: 5.563e-06, eta: 6:20:59, time: 0.883, data_time: 0.029, memory: 10707, loss_rpn_cls: 0.0216, loss_rpn_bbox: 0.0320, loss_cls: 0.1527, acc: 94.3584, loss_bbox: 0.2025, loss_mask: 0.2128, loss: 0.6217 2023-11-17 03:15:41,958 - mmdet - INFO - Epoch [22][1250/1833] lr: 5.563e-06, eta: 6:20:16, time: 0.874, data_time: 0.030, memory: 10707, loss_rpn_cls: 0.0217, loss_rpn_bbox: 0.0333, loss_cls: 0.1557, acc: 94.1436, loss_bbox: 0.2085, loss_mask: 0.2156, loss: 0.6347 2023-11-17 03:16:25,879 - mmdet - INFO - Epoch [22][1300/1833] lr: 5.563e-06, eta: 6:19:32, time: 0.878, data_time: 0.032, memory: 10707, loss_rpn_cls: 0.0232, loss_rpn_bbox: 0.0334, loss_cls: 0.1566, acc: 94.1780, loss_bbox: 0.2101, loss_mask: 0.2121, loss: 0.6355 2023-11-17 03:17:10,149 - mmdet - INFO - Epoch [22][1350/1833] lr: 5.563e-06, eta: 6:18:49, time: 0.885, data_time: 0.035, memory: 10707, loss_rpn_cls: 0.0230, loss_rpn_bbox: 0.0346, loss_cls: 0.1563, acc: 94.1326, loss_bbox: 0.2111, loss_mask: 0.2148, loss: 0.6398 2023-11-17 03:17:54,108 - mmdet - INFO - Epoch [22][1400/1833] lr: 5.563e-06, eta: 6:18:06, time: 0.879, data_time: 0.036, memory: 10707, loss_rpn_cls: 0.0220, loss_rpn_bbox: 0.0330, loss_cls: 0.1568, acc: 94.1486, loss_bbox: 0.2103, loss_mask: 0.2158, loss: 0.6379 2023-11-17 03:18:38,644 - mmdet - INFO - Epoch [22][1450/1833] lr: 5.563e-06, eta: 6:17:24, time: 0.891, data_time: 0.036, memory: 10707, loss_rpn_cls: 0.0231, loss_rpn_bbox: 0.0334, loss_cls: 0.1595, acc: 94.0609, loss_bbox: 0.2129, loss_mask: 0.2168, loss: 0.6456 2023-11-17 03:19:22,744 - mmdet - INFO - Epoch [22][1500/1833] lr: 5.563e-06, eta: 6:16:40, time: 0.882, data_time: 0.034, memory: 10707, loss_rpn_cls: 0.0211, loss_rpn_bbox: 0.0331, loss_cls: 0.1569, acc: 94.1197, loss_bbox: 0.2100, loss_mask: 0.2145, loss: 0.6356 2023-11-17 03:20:07,279 - mmdet - INFO - Epoch [22][1550/1833] lr: 5.563e-06, eta: 6:15:58, time: 0.891, data_time: 0.031, memory: 10707, loss_rpn_cls: 0.0211, loss_rpn_bbox: 0.0328, loss_cls: 0.1565, acc: 94.0910, loss_bbox: 0.2099, loss_mask: 0.2149, loss: 0.6353 2023-11-17 03:20:51,224 - mmdet - INFO - Epoch [22][1600/1833] lr: 5.563e-06, eta: 6:15:15, time: 0.879, data_time: 0.034, memory: 10707, loss_rpn_cls: 0.0226, loss_rpn_bbox: 0.0331, loss_cls: 0.1563, acc: 94.1287, loss_bbox: 0.2105, loss_mask: 0.2165, loss: 0.6389 2023-11-17 03:21:35,233 - mmdet - INFO - Epoch [22][1650/1833] lr: 5.563e-06, eta: 6:14:31, time: 0.880, data_time: 0.033, memory: 10707, loss_rpn_cls: 0.0217, loss_rpn_bbox: 0.0330, loss_cls: 0.1579, acc: 94.1473, loss_bbox: 0.2082, loss_mask: 0.2159, loss: 0.6367 2023-11-17 03:22:18,999 - mmdet - INFO - Epoch [22][1700/1833] lr: 5.563e-06, eta: 6:13:48, time: 0.875, data_time: 0.031, memory: 10707, loss_rpn_cls: 0.0224, loss_rpn_bbox: 0.0341, loss_cls: 0.1619, acc: 93.9397, loss_bbox: 0.2132, loss_mask: 0.2187, loss: 0.6502 2023-11-17 03:23:02,997 - mmdet - INFO - Epoch [22][1750/1833] lr: 5.563e-06, eta: 6:13:05, time: 0.880, data_time: 0.036, memory: 10707, loss_rpn_cls: 0.0232, loss_rpn_bbox: 0.0330, loss_cls: 0.1560, acc: 94.1616, loss_bbox: 0.2075, loss_mask: 0.2133, loss: 0.6330 2023-11-17 03:23:47,212 - mmdet - INFO - Epoch [22][1800/1833] lr: 5.563e-06, eta: 6:12:22, time: 0.884, data_time: 0.033, memory: 10707, loss_rpn_cls: 0.0205, loss_rpn_bbox: 0.0312, loss_cls: 0.1527, acc: 94.2385, loss_bbox: 0.2041, loss_mask: 0.2136, loss: 0.6221 2023-11-17 03:24:16,759 - mmdet - INFO - Saving checkpoint at 22 epochs 2023-11-17 03:24:48,160 - mmdet - INFO - Evaluating bbox... 2023-11-17 03:25:19,761 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.495 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.721 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.544 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.347 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.537 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.638 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.618 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.618 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.618 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.465 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.660 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.764 2023-11-17 03:25:19,764 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.583 | bicycle | 0.401 | car | 0.492 | | motorcycle | 0.510 | airplane | 0.715 | bus | 0.688 | | train | 0.703 | truck | 0.471 | boat | 0.345 | | traffic light | 0.312 | fire hydrant | 0.738 | stop sign | 0.671 | | parking meter | 0.507 | bench | 0.312 | bird | 0.422 | | cat | 0.740 | dog | 0.695 | horse | 0.633 | | sheep | 0.603 | cow | 0.641 | elephant | 0.708 | | bear | 0.798 | zebra | 0.701 | giraffe | 0.699 | | backpack | 0.228 | umbrella | 0.481 | handbag | 0.251 | | tie | 0.402 | suitcase | 0.501 | frisbee | 0.713 | | skis | 0.333 | snowboard | 0.470 | sports ball | 0.483 | | kite | 0.481 | baseball bat | 0.421 | baseball glove | 0.458 | | skateboard | 0.594 | surfboard | 0.486 | tennis racket | 0.557 | | bottle | 0.465 | wine glass | 0.432 | cup | 0.518 | | fork | 0.502 | knife | 0.322 | spoon | 0.284 | | bowl | 0.492 | banana | 0.301 | apple | 0.286 | | sandwich | 0.480 | orange | 0.384 | broccoli | 0.284 | | carrot | 0.275 | hot dog | 0.471 | pizza | 0.560 | | donut | 0.570 | cake | 0.468 | chair | 0.376 | | couch | 0.480 | potted plant | 0.352 | bed | 0.497 | | dining table | 0.317 | toilet | 0.667 | tv | 0.644 | | laptop | 0.682 | mouse | 0.657 | remote | 0.443 | | keyboard | 0.566 | cell phone | 0.476 | microwave | 0.677 | | oven | 0.419 | toaster | 0.495 | sink | 0.452 | | refrigerator | 0.677 | book | 0.201 | clock | 0.551 | | vase | 0.419 | scissors | 0.407 | teddy bear | 0.567 | | hair drier | 0.230 | toothbrush | 0.335 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-17 03:25:19,764 - mmdet - INFO - Evaluating segm... 2023-11-17 03:25:54,692 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.446 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.692 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.481 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.263 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.485 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.633 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.563 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.563 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.563 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.394 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.610 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.722 2023-11-17 03:25:54,694 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.511 | bicycle | 0.248 | car | 0.447 | | motorcycle | 0.404 | airplane | 0.570 | bus | 0.678 | | train | 0.687 | truck | 0.456 | boat | 0.320 | | traffic light | 0.307 | fire hydrant | 0.708 | stop sign | 0.669 | | parking meter | 0.512 | bench | 0.240 | bird | 0.344 | | cat | 0.742 | dog | 0.649 | horse | 0.477 | | sheep | 0.539 | cow | 0.553 | elephant | 0.641 | | bear | 0.752 | zebra | 0.591 | giraffe | 0.551 | | backpack | 0.215 | umbrella | 0.517 | handbag | 0.228 | | tie | 0.377 | suitcase | 0.517 | frisbee | 0.658 | | skis | 0.057 | snowboard | 0.294 | sports ball | 0.469 | | kite | 0.340 | baseball bat | 0.318 | baseball glove | 0.472 | | skateboard | 0.396 | surfboard | 0.405 | tennis racket | 0.586 | | bottle | 0.447 | wine glass | 0.393 | cup | 0.519 | | fork | 0.239 | knife | 0.221 | spoon | 0.213 | | bowl | 0.464 | banana | 0.257 | apple | 0.283 | | sandwich | 0.507 | orange | 0.380 | broccoli | 0.267 | | carrot | 0.240 | hot dog | 0.378 | pizza | 0.548 | | donut | 0.574 | cake | 0.482 | chair | 0.279 | | couch | 0.402 | potted plant | 0.297 | bed | 0.406 | | dining table | 0.192 | toilet | 0.639 | tv | 0.680 | | laptop | 0.686 | mouse | 0.639 | remote | 0.404 | | keyboard | 0.566 | cell phone | 0.454 | microwave | 0.687 | | oven | 0.384 | toaster | 0.573 | sink | 0.421 | | refrigerator | 0.690 | book | 0.153 | clock | 0.544 | | vase | 0.409 | scissors | 0.293 | teddy bear | 0.539 | | hair drier | 0.225 | toothbrush | 0.239 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-17 03:25:55,194 - mmdet - INFO - The previous best checkpoint /mnt/petrelfs/lizhiqi/DINO/detection/work_dirs/mask_rcnn_flash_internimage_b_fpn_3x_cocoo_0.4_0.9_4x16/best_bbox_mAP_epoch_20.pth was removed 2023-11-17 03:25:59,002 - mmdet - INFO - Now best checkpoint is saved as best_bbox_mAP_epoch_22.pth. 2023-11-17 03:25:59,003 - mmdet - INFO - Best bbox_mAP is 0.4954 at 22 epoch. 2023-11-17 03:25:59,003 - mmdet - INFO - Exp name: mask_rcnn_flash_internimage_b_fpn_3x_coco_0.4_0.9-4x16.py 2023-11-17 03:25:59,003 - mmdet - INFO - Epoch(val) [22][313] bbox_mAP: 0.4954, bbox_mAP_50: 0.7206, bbox_mAP_75: 0.5443, bbox_mAP_s: 0.3471, bbox_mAP_m: 0.5367, bbox_mAP_l: 0.6381, bbox_mAP_copypaste: 0.4954 0.7206 0.5443 0.3471 0.5367 0.6381, segm_mAP: 0.4457, segm_mAP_50: 0.6918, segm_mAP_75: 0.4811, segm_mAP_s: 0.2635, segm_mAP_m: 0.4852, segm_mAP_l: 0.6332, segm_mAP_copypaste: 0.4457 0.6918 0.4811 0.2635 0.4852 0.6332 2023-11-17 03:26:45,732 - mmdet - INFO - Epoch [23][50/1833] lr: 5.563e-06, eta: 6:10:54, time: 0.934, data_time: 0.099, memory: 10707, loss_rpn_cls: 0.0211, loss_rpn_bbox: 0.0331, loss_cls: 0.1525, acc: 94.2775, loss_bbox: 0.2065, loss_mask: 0.2106, loss: 0.6238 2023-11-17 03:27:29,947 - mmdet - INFO - Epoch [23][100/1833] lr: 5.563e-06, eta: 6:10:11, time: 0.884, data_time: 0.031, memory: 10707, loss_rpn_cls: 0.0205, loss_rpn_bbox: 0.0326, loss_cls: 0.1501, acc: 94.2993, loss_bbox: 0.2060, loss_mask: 0.2126, loss: 0.6218 2023-11-17 03:28:14,313 - mmdet - INFO - Epoch [23][150/1833] lr: 5.563e-06, eta: 6:09:28, time: 0.887, data_time: 0.035, memory: 10707, loss_rpn_cls: 0.0231, loss_rpn_bbox: 0.0346, loss_cls: 0.1593, acc: 93.9869, loss_bbox: 0.2136, loss_mask: 0.2149, loss: 0.6454 2023-11-17 03:28:58,413 - mmdet - INFO - Epoch [23][200/1833] lr: 5.563e-06, eta: 6:08:45, time: 0.882, data_time: 0.032, memory: 10707, loss_rpn_cls: 0.0217, loss_rpn_bbox: 0.0326, loss_cls: 0.1539, acc: 94.2187, loss_bbox: 0.2061, loss_mask: 0.2137, loss: 0.6280 2023-11-17 03:29:42,536 - mmdet - INFO - Epoch [23][250/1833] lr: 5.563e-06, eta: 6:08:02, time: 0.882, data_time: 0.035, memory: 10707, loss_rpn_cls: 0.0214, loss_rpn_bbox: 0.0325, loss_cls: 0.1512, acc: 94.3181, loss_bbox: 0.2053, loss_mask: 0.2092, loss: 0.6197 2023-11-17 03:30:27,027 - mmdet - INFO - Epoch [23][300/1833] lr: 5.563e-06, eta: 6:07:19, time: 0.889, data_time: 0.037, memory: 10707, loss_rpn_cls: 0.0215, loss_rpn_bbox: 0.0328, loss_cls: 0.1546, acc: 94.2234, loss_bbox: 0.2094, loss_mask: 0.2145, loss: 0.6327 2023-11-17 03:31:10,558 - mmdet - INFO - Epoch [23][350/1833] lr: 5.563e-06, eta: 6:06:36, time: 0.871, data_time: 0.035, memory: 10707, loss_rpn_cls: 0.0216, loss_rpn_bbox: 0.0332, loss_cls: 0.1552, acc: 94.1791, loss_bbox: 0.2070, loss_mask: 0.2147, loss: 0.6317 2023-11-17 03:31:54,872 - mmdet - INFO - Epoch [23][400/1833] lr: 5.563e-06, eta: 6:05:53, time: 0.886, data_time: 0.039, memory: 10707, loss_rpn_cls: 0.0221, loss_rpn_bbox: 0.0328, loss_cls: 0.1543, acc: 94.1625, loss_bbox: 0.2083, loss_mask: 0.2112, loss: 0.6287 2023-11-17 03:32:38,987 - mmdet - INFO - Epoch [23][450/1833] lr: 5.563e-06, eta: 6:05:10, time: 0.882, data_time: 0.044, memory: 10707, loss_rpn_cls: 0.0215, loss_rpn_bbox: 0.0336, loss_cls: 0.1546, acc: 94.1984, loss_bbox: 0.2077, loss_mask: 0.2142, loss: 0.6315 2023-11-17 03:33:23,466 - mmdet - INFO - Epoch [23][500/1833] lr: 5.563e-06, eta: 6:04:27, time: 0.890, data_time: 0.039, memory: 10707, loss_rpn_cls: 0.0227, loss_rpn_bbox: 0.0332, loss_cls: 0.1507, acc: 94.3638, loss_bbox: 0.2026, loss_mask: 0.2115, loss: 0.6206 2023-11-17 03:34:07,236 - mmdet - INFO - Epoch [23][550/1833] lr: 5.563e-06, eta: 6:03:44, time: 0.875, data_time: 0.036, memory: 10707, loss_rpn_cls: 0.0216, loss_rpn_bbox: 0.0333, loss_cls: 0.1556, acc: 94.1838, loss_bbox: 0.2085, loss_mask: 0.2133, loss: 0.6323 2023-11-17 03:34:51,819 - mmdet - INFO - Epoch [23][600/1833] lr: 5.563e-06, eta: 6:03:01, time: 0.892, data_time: 0.039, memory: 10707, loss_rpn_cls: 0.0226, loss_rpn_bbox: 0.0345, loss_cls: 0.1583, acc: 94.0625, loss_bbox: 0.2120, loss_mask: 0.2142, loss: 0.6416 2023-11-17 03:35:36,093 - mmdet - INFO - Epoch [23][650/1833] lr: 5.563e-06, eta: 6:02:18, time: 0.886, data_time: 0.035, memory: 10707, loss_rpn_cls: 0.0214, loss_rpn_bbox: 0.0334, loss_cls: 0.1547, acc: 94.1849, loss_bbox: 0.2090, loss_mask: 0.2144, loss: 0.6328 2023-11-17 03:36:19,709 - mmdet - INFO - Epoch [23][700/1833] lr: 5.563e-06, eta: 6:01:34, time: 0.872, data_time: 0.034, memory: 10707, loss_rpn_cls: 0.0220, loss_rpn_bbox: 0.0331, loss_cls: 0.1534, acc: 94.2170, loss_bbox: 0.2072, loss_mask: 0.2153, loss: 0.6309 2023-11-17 03:37:03,962 - mmdet - INFO - Epoch [23][750/1833] lr: 5.563e-06, eta: 6:00:51, time: 0.885, data_time: 0.034, memory: 10707, loss_rpn_cls: 0.0228, loss_rpn_bbox: 0.0332, loss_cls: 0.1566, acc: 94.1563, loss_bbox: 0.2108, loss_mask: 0.2162, loss: 0.6396 2023-11-17 03:37:48,471 - mmdet - INFO - Epoch [23][800/1833] lr: 5.563e-06, eta: 6:00:09, time: 0.890, data_time: 0.034, memory: 10707, loss_rpn_cls: 0.0223, loss_rpn_bbox: 0.0332, loss_cls: 0.1569, acc: 94.1526, loss_bbox: 0.2132, loss_mask: 0.2148, loss: 0.6404 2023-11-17 03:38:32,658 - mmdet - INFO - Epoch [23][850/1833] lr: 5.563e-06, eta: 5:59:26, time: 0.884, data_time: 0.039, memory: 10707, loss_rpn_cls: 0.0220, loss_rpn_bbox: 0.0331, loss_cls: 0.1573, acc: 94.0693, loss_bbox: 0.2121, loss_mask: 0.2161, loss: 0.6406 2023-11-17 03:39:16,158 - mmdet - INFO - Epoch [23][900/1833] lr: 5.563e-06, eta: 5:58:42, time: 0.870, data_time: 0.033, memory: 10707, loss_rpn_cls: 0.0225, loss_rpn_bbox: 0.0331, loss_cls: 0.1580, acc: 94.1262, loss_bbox: 0.2092, loss_mask: 0.2156, loss: 0.6385 2023-11-17 03:39:59,874 - mmdet - INFO - Epoch [23][950/1833] lr: 5.563e-06, eta: 5:57:59, time: 0.874, data_time: 0.034, memory: 10707, loss_rpn_cls: 0.0213, loss_rpn_bbox: 0.0313, loss_cls: 0.1497, acc: 94.3895, loss_bbox: 0.2002, loss_mask: 0.2147, loss: 0.6172 2023-11-17 03:40:43,758 - mmdet - INFO - Epoch [23][1000/1833] lr: 5.563e-06, eta: 5:57:16, time: 0.878, data_time: 0.031, memory: 10707, loss_rpn_cls: 0.0207, loss_rpn_bbox: 0.0327, loss_cls: 0.1531, acc: 94.2259, loss_bbox: 0.2082, loss_mask: 0.2137, loss: 0.6284 2023-11-17 03:41:28,023 - mmdet - INFO - Epoch [23][1050/1833] lr: 5.563e-06, eta: 5:56:33, time: 0.885, data_time: 0.034, memory: 10707, loss_rpn_cls: 0.0226, loss_rpn_bbox: 0.0337, loss_cls: 0.1534, acc: 94.2585, loss_bbox: 0.2060, loss_mask: 0.2137, loss: 0.6293 2023-11-17 03:42:11,686 - mmdet - INFO - Epoch [23][1100/1833] lr: 5.563e-06, eta: 5:55:49, time: 0.874, data_time: 0.033, memory: 10707, loss_rpn_cls: 0.0220, loss_rpn_bbox: 0.0325, loss_cls: 0.1517, acc: 94.3243, loss_bbox: 0.2057, loss_mask: 0.2132, loss: 0.6251 2023-11-17 03:42:56,190 - mmdet - INFO - Epoch [23][1150/1833] lr: 5.563e-06, eta: 5:55:07, time: 0.890, data_time: 0.035, memory: 10707, loss_rpn_cls: 0.0218, loss_rpn_bbox: 0.0338, loss_cls: 0.1536, acc: 94.2169, loss_bbox: 0.2075, loss_mask: 0.2132, loss: 0.6300 2023-11-17 03:43:40,057 - mmdet - INFO - Epoch [23][1200/1833] lr: 5.563e-06, eta: 5:54:23, time: 0.877, data_time: 0.034, memory: 10707, loss_rpn_cls: 0.0219, loss_rpn_bbox: 0.0327, loss_cls: 0.1562, acc: 94.1243, loss_bbox: 0.2117, loss_mask: 0.2144, loss: 0.6369 2023-11-17 03:44:24,204 - mmdet - INFO - Epoch [23][1250/1833] lr: 5.563e-06, eta: 5:53:40, time: 0.883, data_time: 0.035, memory: 10707, loss_rpn_cls: 0.0216, loss_rpn_bbox: 0.0325, loss_cls: 0.1531, acc: 94.2639, loss_bbox: 0.2045, loss_mask: 0.2119, loss: 0.6237 2023-11-17 03:45:08,336 - mmdet - INFO - Epoch [23][1300/1833] lr: 5.563e-06, eta: 5:52:57, time: 0.882, data_time: 0.032, memory: 10707, loss_rpn_cls: 0.0227, loss_rpn_bbox: 0.0330, loss_cls: 0.1590, acc: 94.0881, loss_bbox: 0.2104, loss_mask: 0.2145, loss: 0.6397 2023-11-17 03:45:52,712 - mmdet - INFO - Epoch [23][1350/1833] lr: 5.563e-06, eta: 5:52:14, time: 0.888, data_time: 0.032, memory: 10707, loss_rpn_cls: 0.0227, loss_rpn_bbox: 0.0334, loss_cls: 0.1539, acc: 94.2326, loss_bbox: 0.2065, loss_mask: 0.2121, loss: 0.6285 2023-11-17 03:46:36,454 - mmdet - INFO - Epoch [23][1400/1833] lr: 5.563e-06, eta: 5:51:31, time: 0.875, data_time: 0.035, memory: 10707, loss_rpn_cls: 0.0231, loss_rpn_bbox: 0.0330, loss_cls: 0.1537, acc: 94.2391, loss_bbox: 0.2055, loss_mask: 0.2172, loss: 0.6325 2023-11-17 03:47:20,363 - mmdet - INFO - Epoch [23][1450/1833] lr: 5.563e-06, eta: 5:50:48, time: 0.878, data_time: 0.037, memory: 10707, loss_rpn_cls: 0.0213, loss_rpn_bbox: 0.0324, loss_cls: 0.1530, acc: 94.2575, loss_bbox: 0.2071, loss_mask: 0.2146, loss: 0.6285 2023-11-17 03:48:04,143 - mmdet - INFO - Epoch [23][1500/1833] lr: 5.563e-06, eta: 5:50:04, time: 0.875, data_time: 0.034, memory: 10707, loss_rpn_cls: 0.0217, loss_rpn_bbox: 0.0329, loss_cls: 0.1519, acc: 94.3044, loss_bbox: 0.2050, loss_mask: 0.2155, loss: 0.6269 2023-11-17 03:48:48,034 - mmdet - INFO - Epoch [23][1550/1833] lr: 5.563e-06, eta: 5:49:21, time: 0.878, data_time: 0.033, memory: 10707, loss_rpn_cls: 0.0215, loss_rpn_bbox: 0.0328, loss_cls: 0.1544, acc: 94.1960, loss_bbox: 0.2072, loss_mask: 0.2147, loss: 0.6305 2023-11-17 03:49:32,168 - mmdet - INFO - Epoch [23][1600/1833] lr: 5.563e-06, eta: 5:48:38, time: 0.883, data_time: 0.031, memory: 10707, loss_rpn_cls: 0.0226, loss_rpn_bbox: 0.0335, loss_cls: 0.1601, acc: 94.0749, loss_bbox: 0.2108, loss_mask: 0.2130, loss: 0.6400 2023-11-17 03:50:15,962 - mmdet - INFO - Epoch [23][1650/1833] lr: 5.563e-06, eta: 5:47:55, time: 0.876, data_time: 0.031, memory: 10707, loss_rpn_cls: 0.0223, loss_rpn_bbox: 0.0337, loss_cls: 0.1591, acc: 94.0516, loss_bbox: 0.2139, loss_mask: 0.2175, loss: 0.6464 2023-11-17 03:50:59,646 - mmdet - INFO - Epoch [23][1700/1833] lr: 5.563e-06, eta: 5:47:11, time: 0.874, data_time: 0.036, memory: 10707, loss_rpn_cls: 0.0213, loss_rpn_bbox: 0.0323, loss_cls: 0.1512, acc: 94.3500, loss_bbox: 0.2022, loss_mask: 0.2090, loss: 0.6161 2023-11-17 03:51:43,944 - mmdet - INFO - Epoch [23][1750/1833] lr: 5.563e-06, eta: 5:46:28, time: 0.886, data_time: 0.035, memory: 10707, loss_rpn_cls: 0.0225, loss_rpn_bbox: 0.0328, loss_cls: 0.1521, acc: 94.3139, loss_bbox: 0.2034, loss_mask: 0.2143, loss: 0.6251 2023-11-17 03:52:28,631 - mmdet - INFO - Epoch [23][1800/1833] lr: 5.563e-06, eta: 5:45:46, time: 0.894, data_time: 0.035, memory: 10707, loss_rpn_cls: 0.0217, loss_rpn_bbox: 0.0337, loss_cls: 0.1582, acc: 94.1063, loss_bbox: 0.2116, loss_mask: 0.2167, loss: 0.6420 2023-11-17 03:52:58,032 - mmdet - INFO - Saving checkpoint at 23 epochs 2023-11-17 03:53:30,849 - mmdet - INFO - Evaluating bbox... 2023-11-17 03:54:02,521 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.493 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.721 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.548 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.355 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.537 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.636 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.617 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.617 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.617 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.467 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.660 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.759 2023-11-17 03:54:02,524 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.587 | bicycle | 0.399 | car | 0.502 | | motorcycle | 0.507 | airplane | 0.690 | bus | 0.677 | | train | 0.702 | truck | 0.460 | boat | 0.348 | | traffic light | 0.313 | fire hydrant | 0.738 | stop sign | 0.662 | | parking meter | 0.524 | bench | 0.312 | bird | 0.429 | | cat | 0.728 | dog | 0.704 | horse | 0.638 | | sheep | 0.597 | cow | 0.628 | elephant | 0.700 | | bear | 0.778 | zebra | 0.685 | giraffe | 0.693 | | backpack | 0.218 | umbrella | 0.475 | handbag | 0.254 | | tie | 0.401 | suitcase | 0.502 | frisbee | 0.712 | | skis | 0.327 | snowboard | 0.449 | sports ball | 0.472 | | kite | 0.476 | baseball bat | 0.419 | baseball glove | 0.444 | | skateboard | 0.602 | surfboard | 0.505 | tennis racket | 0.551 | | bottle | 0.472 | wine glass | 0.418 | cup | 0.507 | | fork | 0.491 | knife | 0.317 | spoon | 0.294 | | bowl | 0.491 | banana | 0.297 | apple | 0.268 | | sandwich | 0.484 | orange | 0.368 | broccoli | 0.285 | | carrot | 0.269 | hot dog | 0.483 | pizza | 0.553 | | donut | 0.551 | cake | 0.471 | chair | 0.376 | | couch | 0.498 | potted plant | 0.350 | bed | 0.499 | | dining table | 0.330 | toilet | 0.670 | tv | 0.639 | | laptop | 0.684 | mouse | 0.663 | remote | 0.439 | | keyboard | 0.566 | cell phone | 0.481 | microwave | 0.665 | | oven | 0.433 | toaster | 0.488 | sink | 0.447 | | refrigerator | 0.681 | book | 0.202 | clock | 0.520 | | vase | 0.427 | scissors | 0.443 | teddy bear | 0.563 | | hair drier | 0.200 | toothbrush | 0.338 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-17 03:54:02,524 - mmdet - INFO - Evaluating segm... 2023-11-17 03:54:34,552 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.443 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.690 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.478 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.261 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.481 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.636 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.560 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.560 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.560 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.393 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.606 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.721 2023-11-17 03:54:34,554 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.506 | bicycle | 0.236 | car | 0.457 | | motorcycle | 0.408 | airplane | 0.551 | bus | 0.659 | | train | 0.690 | truck | 0.446 | boat | 0.325 | | traffic light | 0.300 | fire hydrant | 0.708 | stop sign | 0.650 | | parking meter | 0.525 | bench | 0.238 | bird | 0.348 | | cat | 0.731 | dog | 0.664 | horse | 0.476 | | sheep | 0.532 | cow | 0.529 | elephant | 0.644 | | bear | 0.760 | zebra | 0.593 | giraffe | 0.542 | | backpack | 0.230 | umbrella | 0.523 | handbag | 0.237 | | tie | 0.366 | suitcase | 0.515 | frisbee | 0.658 | | skis | 0.060 | snowboard | 0.292 | sports ball | 0.465 | | kite | 0.319 | baseball bat | 0.310 | baseball glove | 0.465 | | skateboard | 0.402 | surfboard | 0.407 | tennis racket | 0.586 | | bottle | 0.450 | wine glass | 0.374 | cup | 0.507 | | fork | 0.260 | knife | 0.208 | spoon | 0.214 | | bowl | 0.459 | banana | 0.251 | apple | 0.269 | | sandwich | 0.499 | orange | 0.370 | broccoli | 0.264 | | carrot | 0.232 | hot dog | 0.379 | pizza | 0.538 | | donut | 0.554 | cake | 0.483 | chair | 0.269 | | couch | 0.422 | potted plant | 0.294 | bed | 0.383 | | dining table | 0.194 | toilet | 0.649 | tv | 0.672 | | laptop | 0.685 | mouse | 0.633 | remote | 0.388 | | keyboard | 0.564 | cell phone | 0.440 | microwave | 0.689 | | oven | 0.389 | toaster | 0.552 | sink | 0.422 | | refrigerator | 0.691 | book | 0.155 | clock | 0.531 | | vase | 0.419 | scissors | 0.328 | teddy bear | 0.548 | | hair drier | 0.195 | toothbrush | 0.226 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-17 03:54:34,952 - mmdet - INFO - Exp name: mask_rcnn_flash_internimage_b_fpn_3x_coco_0.4_0.9-4x16.py 2023-11-17 03:54:34,952 - mmdet - INFO - Epoch(val) [23][313] bbox_mAP: 0.4929, bbox_mAP_50: 0.7213, bbox_mAP_75: 0.5480, bbox_mAP_s: 0.3546, bbox_mAP_m: 0.5368, bbox_mAP_l: 0.6361, bbox_mAP_copypaste: 0.4929 0.7213 0.5480 0.3546 0.5368 0.6361, segm_mAP: 0.4425, segm_mAP_50: 0.6902, segm_mAP_75: 0.4778, segm_mAP_s: 0.2611, segm_mAP_m: 0.4808, segm_mAP_l: 0.6362, segm_mAP_copypaste: 0.4425 0.6902 0.4778 0.2611 0.4808 0.6362 2023-11-17 03:55:21,691 - mmdet - INFO - Epoch [24][50/1833] lr: 5.563e-06, eta: 5:44:19, time: 0.934, data_time: 0.096, memory: 10707, loss_rpn_cls: 0.0217, loss_rpn_bbox: 0.0332, loss_cls: 0.1519, acc: 94.2866, loss_bbox: 0.2061, loss_mask: 0.2113, loss: 0.6243 2023-11-17 03:56:05,803 - mmdet - INFO - Epoch [24][100/1833] lr: 5.563e-06, eta: 5:43:36, time: 0.882, data_time: 0.035, memory: 10707, loss_rpn_cls: 0.0206, loss_rpn_bbox: 0.0325, loss_cls: 0.1491, acc: 94.4434, loss_bbox: 0.2026, loss_mask: 0.2112, loss: 0.6160 2023-11-17 03:56:49,312 - mmdet - INFO - Epoch [24][150/1833] lr: 5.563e-06, eta: 5:42:53, time: 0.870, data_time: 0.029, memory: 10707, loss_rpn_cls: 0.0220, loss_rpn_bbox: 0.0325, loss_cls: 0.1514, acc: 94.3411, loss_bbox: 0.2035, loss_mask: 0.2126, loss: 0.6219 2023-11-17 03:57:33,196 - mmdet - INFO - Epoch [24][200/1833] lr: 5.563e-06, eta: 5:42:10, time: 0.878, data_time: 0.036, memory: 10707, loss_rpn_cls: 0.0223, loss_rpn_bbox: 0.0331, loss_cls: 0.1548, acc: 94.1841, loss_bbox: 0.2094, loss_mask: 0.2140, loss: 0.6337 2023-11-17 03:58:17,000 - mmdet - INFO - Epoch [24][250/1833] lr: 5.563e-06, eta: 5:41:26, time: 0.876, data_time: 0.034, memory: 10707, loss_rpn_cls: 0.0222, loss_rpn_bbox: 0.0342, loss_cls: 0.1543, acc: 94.1690, loss_bbox: 0.2103, loss_mask: 0.2162, loss: 0.6371 2023-11-17 03:59:01,168 - mmdet - INFO - Epoch [24][300/1833] lr: 5.563e-06, eta: 5:40:43, time: 0.883, data_time: 0.036, memory: 10707, loss_rpn_cls: 0.0214, loss_rpn_bbox: 0.0339, loss_cls: 0.1564, acc: 94.1161, loss_bbox: 0.2104, loss_mask: 0.2139, loss: 0.6361 2023-11-17 03:59:45,423 - mmdet - INFO - Epoch [24][350/1833] lr: 5.563e-06, eta: 5:40:00, time: 0.884, data_time: 0.038, memory: 10707, loss_rpn_cls: 0.0219, loss_rpn_bbox: 0.0328, loss_cls: 0.1520, acc: 94.3137, loss_bbox: 0.2078, loss_mask: 0.2113, loss: 0.6257 2023-11-17 04:00:29,342 - mmdet - INFO - Epoch [24][400/1833] lr: 5.563e-06, eta: 5:39:17, time: 0.879, data_time: 0.031, memory: 10707, loss_rpn_cls: 0.0210, loss_rpn_bbox: 0.0330, loss_cls: 0.1554, acc: 94.1754, loss_bbox: 0.2102, loss_mask: 0.2143, loss: 0.6339 2023-11-17 04:01:13,696 - mmdet - INFO - Epoch [24][450/1833] lr: 5.563e-06, eta: 5:38:34, time: 0.887, data_time: 0.034, memory: 10707, loss_rpn_cls: 0.0219, loss_rpn_bbox: 0.0328, loss_cls: 0.1503, acc: 94.3214, loss_bbox: 0.2031, loss_mask: 0.2110, loss: 0.6192 2023-11-17 04:01:57,663 - mmdet - INFO - Epoch [24][500/1833] lr: 5.563e-06, eta: 5:37:51, time: 0.879, data_time: 0.035, memory: 10707, loss_rpn_cls: 0.0210, loss_rpn_bbox: 0.0325, loss_cls: 0.1547, acc: 94.1617, loss_bbox: 0.2087, loss_mask: 0.2142, loss: 0.6311 2023-11-17 04:02:41,584 - mmdet - INFO - Epoch [24][550/1833] lr: 5.563e-06, eta: 5:37:08, time: 0.878, data_time: 0.035, memory: 10707, loss_rpn_cls: 0.0219, loss_rpn_bbox: 0.0335, loss_cls: 0.1553, acc: 94.1780, loss_bbox: 0.2103, loss_mask: 0.2136, loss: 0.6345 2023-11-17 04:03:25,744 - mmdet - INFO - Epoch [24][600/1833] lr: 5.563e-06, eta: 5:36:25, time: 0.883, data_time: 0.035, memory: 10707, loss_rpn_cls: 0.0221, loss_rpn_bbox: 0.0344, loss_cls: 0.1557, acc: 94.1703, loss_bbox: 0.2117, loss_mask: 0.2158, loss: 0.6396 2023-11-17 04:04:10,421 - mmdet - INFO - Epoch [24][650/1833] lr: 5.563e-06, eta: 5:35:42, time: 0.894, data_time: 0.029, memory: 10707, loss_rpn_cls: 0.0214, loss_rpn_bbox: 0.0334, loss_cls: 0.1522, acc: 94.2540, loss_bbox: 0.2049, loss_mask: 0.2118, loss: 0.6237 2023-11-17 04:04:54,207 - mmdet - INFO - Epoch [24][700/1833] lr: 5.563e-06, eta: 5:34:59, time: 0.876, data_time: 0.037, memory: 10707, loss_rpn_cls: 0.0205, loss_rpn_bbox: 0.0314, loss_cls: 0.1503, acc: 94.3754, loss_bbox: 0.2014, loss_mask: 0.2107, loss: 0.6143 2023-11-17 04:05:38,156 - mmdet - INFO - Epoch [24][750/1833] lr: 5.563e-06, eta: 5:34:15, time: 0.879, data_time: 0.033, memory: 10707, loss_rpn_cls: 0.0227, loss_rpn_bbox: 0.0329, loss_cls: 0.1536, acc: 94.1932, loss_bbox: 0.2087, loss_mask: 0.2125, loss: 0.6304 2023-11-17 04:06:22,527 - mmdet - INFO - Epoch [24][800/1833] lr: 5.563e-06, eta: 5:33:33, time: 0.887, data_time: 0.036, memory: 10707, loss_rpn_cls: 0.0213, loss_rpn_bbox: 0.0334, loss_cls: 0.1525, acc: 94.3045, loss_bbox: 0.2041, loss_mask: 0.2110, loss: 0.6223 2023-11-17 04:07:07,626 - mmdet - INFO - Epoch [24][850/1833] lr: 5.563e-06, eta: 5:32:50, time: 0.902, data_time: 0.039, memory: 10707, loss_rpn_cls: 0.0223, loss_rpn_bbox: 0.0333, loss_cls: 0.1549, acc: 94.2291, loss_bbox: 0.2088, loss_mask: 0.2121, loss: 0.6315 2023-11-17 04:07:51,752 - mmdet - INFO - Epoch [24][900/1833] lr: 5.563e-06, eta: 5:32:07, time: 0.883, data_time: 0.037, memory: 10707, loss_rpn_cls: 0.0216, loss_rpn_bbox: 0.0340, loss_cls: 0.1564, acc: 94.1099, loss_bbox: 0.2118, loss_mask: 0.2127, loss: 0.6365 2023-11-17 04:08:35,952 - mmdet - INFO - Epoch [24][950/1833] lr: 5.563e-06, eta: 5:31:24, time: 0.884, data_time: 0.035, memory: 10707, loss_rpn_cls: 0.0217, loss_rpn_bbox: 0.0335, loss_cls: 0.1550, acc: 94.2018, loss_bbox: 0.2098, loss_mask: 0.2131, loss: 0.6330 2023-11-17 04:09:20,237 - mmdet - INFO - Epoch [24][1000/1833] lr: 5.563e-06, eta: 5:30:41, time: 0.886, data_time: 0.034, memory: 10707, loss_rpn_cls: 0.0218, loss_rpn_bbox: 0.0328, loss_cls: 0.1518, acc: 94.3165, loss_bbox: 0.2058, loss_mask: 0.2127, loss: 0.6249 2023-11-17 04:10:05,070 - mmdet - INFO - Epoch [24][1050/1833] lr: 5.563e-06, eta: 5:29:58, time: 0.897, data_time: 0.038, memory: 10707, loss_rpn_cls: 0.0222, loss_rpn_bbox: 0.0328, loss_cls: 0.1537, acc: 94.2466, loss_bbox: 0.2071, loss_mask: 0.2143, loss: 0.6301 2023-11-17 04:10:49,427 - mmdet - INFO - Epoch [24][1100/1833] lr: 5.563e-06, eta: 5:29:15, time: 0.887, data_time: 0.034, memory: 10707, loss_rpn_cls: 0.0203, loss_rpn_bbox: 0.0321, loss_cls: 0.1497, acc: 94.3718, loss_bbox: 0.2035, loss_mask: 0.2110, loss: 0.6167 2023-11-17 04:11:33,876 - mmdet - INFO - Epoch [24][1150/1833] lr: 5.563e-06, eta: 5:28:32, time: 0.889, data_time: 0.033, memory: 10707, loss_rpn_cls: 0.0212, loss_rpn_bbox: 0.0327, loss_cls: 0.1544, acc: 94.2089, loss_bbox: 0.2065, loss_mask: 0.2115, loss: 0.6262 2023-11-17 04:12:25,240 - mmdet - INFO - Epoch [24][1200/1833] lr: 5.563e-06, eta: 5:27:53, time: 1.028, data_time: 0.069, memory: 10707, loss_rpn_cls: 0.0208, loss_rpn_bbox: 0.0325, loss_cls: 0.1495, acc: 94.3816, loss_bbox: 0.1991, loss_mask: 0.2095, loss: 0.6115 2023-11-17 04:13:09,333 - mmdet - INFO - Epoch [24][1250/1833] lr: 5.563e-06, eta: 5:27:10, time: 0.881, data_time: 0.031, memory: 10707, loss_rpn_cls: 0.0217, loss_rpn_bbox: 0.0334, loss_cls: 0.1541, acc: 94.1833, loss_bbox: 0.2092, loss_mask: 0.2131, loss: 0.6316 2023-11-17 04:13:53,394 - mmdet - INFO - Epoch [24][1300/1833] lr: 5.563e-06, eta: 5:26:26, time: 0.881, data_time: 0.037, memory: 10707, loss_rpn_cls: 0.0225, loss_rpn_bbox: 0.0337, loss_cls: 0.1538, acc: 94.2413, loss_bbox: 0.2077, loss_mask: 0.2110, loss: 0.6286 2023-11-17 04:14:42,489 - mmdet - INFO - Epoch [24][1350/1833] lr: 5.563e-06, eta: 5:25:46, time: 0.982, data_time: 0.054, memory: 10707, loss_rpn_cls: 0.0228, loss_rpn_bbox: 0.0324, loss_cls: 0.1549, acc: 94.2235, loss_bbox: 0.2052, loss_mask: 0.2130, loss: 0.6284 2023-11-17 04:15:27,211 - mmdet - INFO - Epoch [24][1400/1833] lr: 5.563e-06, eta: 5:25:03, time: 0.894, data_time: 0.031, memory: 10707, loss_rpn_cls: 0.0218, loss_rpn_bbox: 0.0325, loss_cls: 0.1538, acc: 94.2856, loss_bbox: 0.2079, loss_mask: 0.2132, loss: 0.6291 2023-11-17 04:16:11,511 - mmdet - INFO - Epoch [24][1450/1833] lr: 5.563e-06, eta: 5:24:20, time: 0.886, data_time: 0.033, memory: 10707, loss_rpn_cls: 0.0209, loss_rpn_bbox: 0.0322, loss_cls: 0.1534, acc: 94.2837, loss_bbox: 0.2063, loss_mask: 0.2150, loss: 0.6278 2023-11-17 04:16:55,314 - mmdet - INFO - Epoch [24][1500/1833] lr: 5.563e-06, eta: 5:23:37, time: 0.876, data_time: 0.036, memory: 10707, loss_rpn_cls: 0.0210, loss_rpn_bbox: 0.0317, loss_cls: 0.1529, acc: 94.2952, loss_bbox: 0.2051, loss_mask: 0.2128, loss: 0.6234 2023-11-17 04:17:39,765 - mmdet - INFO - Epoch [24][1550/1833] lr: 5.563e-06, eta: 5:22:54, time: 0.889, data_time: 0.042, memory: 10707, loss_rpn_cls: 0.0211, loss_rpn_bbox: 0.0320, loss_cls: 0.1507, acc: 94.3578, loss_bbox: 0.2019, loss_mask: 0.2140, loss: 0.6197 2023-11-17 04:18:24,018 - mmdet - INFO - Epoch [24][1600/1833] lr: 5.563e-06, eta: 5:22:11, time: 0.885, data_time: 0.034, memory: 10707, loss_rpn_cls: 0.0220, loss_rpn_bbox: 0.0324, loss_cls: 0.1541, acc: 94.2055, loss_bbox: 0.2081, loss_mask: 0.2146, loss: 0.6312 2023-11-17 04:19:08,060 - mmdet - INFO - Epoch [24][1650/1833] lr: 5.563e-06, eta: 5:21:27, time: 0.881, data_time: 0.041, memory: 10707, loss_rpn_cls: 0.0215, loss_rpn_bbox: 0.0329, loss_cls: 0.1562, acc: 94.1292, loss_bbox: 0.2094, loss_mask: 0.2134, loss: 0.6334 2023-11-17 04:19:52,547 - mmdet - INFO - Epoch [24][1700/1833] lr: 5.563e-06, eta: 5:20:44, time: 0.890, data_time: 0.032, memory: 10707, loss_rpn_cls: 0.0217, loss_rpn_bbox: 0.0329, loss_cls: 0.1551, acc: 94.2126, loss_bbox: 0.2062, loss_mask: 0.2128, loss: 0.6288 2023-11-17 04:20:36,813 - mmdet - INFO - Epoch [24][1750/1833] lr: 5.563e-06, eta: 5:20:01, time: 0.885, data_time: 0.032, memory: 10707, loss_rpn_cls: 0.0207, loss_rpn_bbox: 0.0331, loss_cls: 0.1518, acc: 94.3093, loss_bbox: 0.2074, loss_mask: 0.2126, loss: 0.6256 2023-11-17 04:21:21,528 - mmdet - INFO - Epoch [24][1800/1833] lr: 5.563e-06, eta: 5:19:19, time: 0.894, data_time: 0.035, memory: 10707, loss_rpn_cls: 0.0215, loss_rpn_bbox: 0.0328, loss_cls: 0.1517, acc: 94.3218, loss_bbox: 0.2030, loss_mask: 0.2127, loss: 0.6217 2023-11-17 04:21:51,017 - mmdet - INFO - Saving checkpoint at 24 epochs 2023-11-17 04:22:24,681 - mmdet - INFO - Evaluating bbox... 2023-11-17 04:22:55,214 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.494 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.718 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.546 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.351 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.536 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.634 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.614 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.614 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.614 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.461 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.655 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.760 2023-11-17 04:22:55,217 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.584 | bicycle | 0.404 | car | 0.505 | | motorcycle | 0.506 | airplane | 0.699 | bus | 0.689 | | train | 0.700 | truck | 0.462 | boat | 0.332 | | traffic light | 0.316 | fire hydrant | 0.716 | stop sign | 0.654 | | parking meter | 0.501 | bench | 0.305 | bird | 0.432 | | cat | 0.751 | dog | 0.700 | horse | 0.640 | | sheep | 0.610 | cow | 0.645 | elephant | 0.710 | | bear | 0.778 | zebra | 0.688 | giraffe | 0.720 | | backpack | 0.232 | umbrella | 0.479 | handbag | 0.260 | | tie | 0.415 | suitcase | 0.488 | frisbee | 0.725 | | skis | 0.326 | snowboard | 0.473 | sports ball | 0.479 | | kite | 0.478 | baseball bat | 0.412 | baseball glove | 0.461 | | skateboard | 0.598 | surfboard | 0.488 | tennis racket | 0.564 | | bottle | 0.475 | wine glass | 0.439 | cup | 0.519 | | fork | 0.488 | knife | 0.344 | spoon | 0.293 | | bowl | 0.493 | banana | 0.308 | apple | 0.281 | | sandwich | 0.455 | orange | 0.357 | broccoli | 0.283 | | carrot | 0.275 | hot dog | 0.473 | pizza | 0.558 | | donut | 0.580 | cake | 0.458 | chair | 0.374 | | couch | 0.494 | potted plant | 0.341 | bed | 0.474 | | dining table | 0.316 | toilet | 0.666 | tv | 0.650 | | laptop | 0.677 | mouse | 0.658 | remote | 0.460 | | keyboard | 0.571 | cell phone | 0.449 | microwave | 0.676 | | oven | 0.412 | toaster | 0.479 | sink | 0.458 | | refrigerator | 0.674 | book | 0.206 | clock | 0.534 | | vase | 0.433 | scissors | 0.432 | teddy bear | 0.570 | | hair drier | 0.175 | toothbrush | 0.316 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-17 04:22:55,217 - mmdet - INFO - Evaluating segm... 2023-11-17 04:23:28,502 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.445 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.691 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.481 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.262 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.483 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.630 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.559 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.559 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.559 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.392 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.602 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.718 2023-11-17 04:23:28,504 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.514 | bicycle | 0.241 | car | 0.463 | | motorcycle | 0.416 | airplane | 0.551 | bus | 0.671 | | train | 0.700 | truck | 0.448 | boat | 0.319 | | traffic light | 0.308 | fire hydrant | 0.705 | stop sign | 0.639 | | parking meter | 0.519 | bench | 0.239 | bird | 0.355 | | cat | 0.742 | dog | 0.654 | horse | 0.480 | | sheep | 0.541 | cow | 0.547 | elephant | 0.642 | | bear | 0.752 | zebra | 0.588 | giraffe | 0.568 | | backpack | 0.231 | umbrella | 0.526 | handbag | 0.239 | | tie | 0.371 | suitcase | 0.526 | frisbee | 0.670 | | skis | 0.067 | snowboard | 0.302 | sports ball | 0.463 | | kite | 0.333 | baseball bat | 0.325 | baseball glove | 0.466 | | skateboard | 0.395 | surfboard | 0.387 | tennis racket | 0.592 | | bottle | 0.451 | wine glass | 0.395 | cup | 0.513 | | fork | 0.269 | knife | 0.229 | spoon | 0.212 | | bowl | 0.454 | banana | 0.266 | apple | 0.280 | | sandwich | 0.475 | orange | 0.352 | broccoli | 0.260 | | carrot | 0.241 | hot dog | 0.379 | pizza | 0.537 | | donut | 0.571 | cake | 0.465 | chair | 0.273 | | couch | 0.410 | potted plant | 0.293 | bed | 0.385 | | dining table | 0.190 | toilet | 0.652 | tv | 0.680 | | laptop | 0.671 | mouse | 0.624 | remote | 0.414 | | keyboard | 0.559 | cell phone | 0.422 | microwave | 0.690 | | oven | 0.387 | toaster | 0.533 | sink | 0.435 | | refrigerator | 0.692 | book | 0.153 | clock | 0.537 | | vase | 0.414 | scissors | 0.334 | teddy bear | 0.541 | | hair drier | 0.212 | toothbrush | 0.240 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-17 04:23:28,879 - mmdet - INFO - Exp name: mask_rcnn_flash_internimage_b_fpn_3x_coco_0.4_0.9-4x16.py 2023-11-17 04:23:28,880 - mmdet - INFO - Epoch(val) [24][313] bbox_mAP: 0.4938, bbox_mAP_50: 0.7183, bbox_mAP_75: 0.5456, bbox_mAP_s: 0.3506, bbox_mAP_m: 0.5355, bbox_mAP_l: 0.6340, bbox_mAP_copypaste: 0.4938 0.7183 0.5456 0.3506 0.5355 0.6340, segm_mAP: 0.4449, segm_mAP_50: 0.6908, segm_mAP_75: 0.4809, segm_mAP_s: 0.2617, segm_mAP_m: 0.4830, segm_mAP_l: 0.6295, segm_mAP_copypaste: 0.4449 0.6908 0.4809 0.2617 0.4830 0.6295 2023-11-17 04:24:15,960 - mmdet - INFO - Epoch [25][50/1833] lr: 5.563e-06, eta: 5:17:54, time: 0.941, data_time: 0.094, memory: 10707, loss_rpn_cls: 0.0211, loss_rpn_bbox: 0.0326, loss_cls: 0.1533, acc: 94.2157, loss_bbox: 0.2083, loss_mask: 0.2124, loss: 0.6278 2023-11-17 04:25:00,561 - mmdet - INFO - Epoch [25][100/1833] lr: 5.563e-06, eta: 5:17:11, time: 0.892, data_time: 0.031, memory: 10707, loss_rpn_cls: 0.0205, loss_rpn_bbox: 0.0317, loss_cls: 0.1473, acc: 94.4227, loss_bbox: 0.2015, loss_mask: 0.2087, loss: 0.6097 2023-11-17 04:25:44,895 - mmdet - INFO - Epoch [25][150/1833] lr: 5.563e-06, eta: 5:16:28, time: 0.887, data_time: 0.033, memory: 10707, loss_rpn_cls: 0.0212, loss_rpn_bbox: 0.0330, loss_cls: 0.1514, acc: 94.3079, loss_bbox: 0.2060, loss_mask: 0.2118, loss: 0.6234 2023-11-17 04:26:29,416 - mmdet - INFO - Epoch [25][200/1833] lr: 5.563e-06, eta: 5:15:45, time: 0.890, data_time: 0.041, memory: 10707, loss_rpn_cls: 0.0216, loss_rpn_bbox: 0.0324, loss_cls: 0.1524, acc: 94.2933, loss_bbox: 0.2077, loss_mask: 0.2121, loss: 0.6262 2023-11-17 04:27:13,403 - mmdet - INFO - Epoch [25][250/1833] lr: 5.563e-06, eta: 5:15:02, time: 0.880, data_time: 0.037, memory: 10707, loss_rpn_cls: 0.0213, loss_rpn_bbox: 0.0331, loss_cls: 0.1548, acc: 94.1738, loss_bbox: 0.2082, loss_mask: 0.2136, loss: 0.6310 2023-11-17 04:27:57,546 - mmdet - INFO - Epoch [25][300/1833] lr: 5.563e-06, eta: 5:14:19, time: 0.883, data_time: 0.038, memory: 10707, loss_rpn_cls: 0.0209, loss_rpn_bbox: 0.0335, loss_cls: 0.1518, acc: 94.2618, loss_bbox: 0.2060, loss_mask: 0.2122, loss: 0.6245 2023-11-17 04:28:42,078 - mmdet - INFO - Epoch [25][350/1833] lr: 5.563e-06, eta: 5:13:36, time: 0.891, data_time: 0.037, memory: 10707, loss_rpn_cls: 0.0204, loss_rpn_bbox: 0.0321, loss_cls: 0.1495, acc: 94.3581, loss_bbox: 0.2046, loss_mask: 0.2100, loss: 0.6165 2023-11-17 04:29:26,541 - mmdet - INFO - Epoch [25][400/1833] lr: 5.563e-06, eta: 5:12:53, time: 0.889, data_time: 0.039, memory: 10707, loss_rpn_cls: 0.0204, loss_rpn_bbox: 0.0326, loss_cls: 0.1498, acc: 94.3375, loss_bbox: 0.2022, loss_mask: 0.2118, loss: 0.6168 2023-11-17 04:30:10,697 - mmdet - INFO - Epoch [25][450/1833] lr: 5.563e-06, eta: 5:12:10, time: 0.883, data_time: 0.036, memory: 10707, loss_rpn_cls: 0.0213, loss_rpn_bbox: 0.0330, loss_cls: 0.1479, acc: 94.3910, loss_bbox: 0.2034, loss_mask: 0.2138, loss: 0.6195 2023-11-17 04:30:54,657 - mmdet - INFO - Epoch [25][500/1833] lr: 5.563e-06, eta: 5:11:26, time: 0.879, data_time: 0.034, memory: 10707, loss_rpn_cls: 0.0212, loss_rpn_bbox: 0.0323, loss_cls: 0.1475, acc: 94.4369, loss_bbox: 0.2011, loss_mask: 0.2090, loss: 0.6113 2023-11-17 04:31:39,185 - mmdet - INFO - Epoch [25][550/1833] lr: 5.563e-06, eta: 5:10:43, time: 0.891, data_time: 0.035, memory: 10707, loss_rpn_cls: 0.0217, loss_rpn_bbox: 0.0327, loss_cls: 0.1563, acc: 94.1521, loss_bbox: 0.2105, loss_mask: 0.2151, loss: 0.6363 2023-11-17 04:32:23,845 - mmdet - INFO - Epoch [25][600/1833] lr: 5.563e-06, eta: 5:10:00, time: 0.893, data_time: 0.033, memory: 10707, loss_rpn_cls: 0.0214, loss_rpn_bbox: 0.0331, loss_cls: 0.1546, acc: 94.1524, loss_bbox: 0.2104, loss_mask: 0.2132, loss: 0.6327 2023-11-17 04:33:08,638 - mmdet - INFO - Epoch [25][650/1833] lr: 5.563e-06, eta: 5:09:18, time: 0.896, data_time: 0.038, memory: 10707, loss_rpn_cls: 0.0216, loss_rpn_bbox: 0.0339, loss_cls: 0.1552, acc: 94.1778, loss_bbox: 0.2110, loss_mask: 0.2125, loss: 0.6343 2023-11-17 04:33:53,309 - mmdet - INFO - Epoch [25][700/1833] lr: 5.563e-06, eta: 5:08:35, time: 0.894, data_time: 0.035, memory: 10707, loss_rpn_cls: 0.0214, loss_rpn_bbox: 0.0327, loss_cls: 0.1507, acc: 94.3233, loss_bbox: 0.2048, loss_mask: 0.2121, loss: 0.6217 2023-11-17 04:34:37,280 - mmdet - INFO - Epoch [25][750/1833] lr: 5.563e-06, eta: 5:07:52, time: 0.879, data_time: 0.036, memory: 10707, loss_rpn_cls: 0.0216, loss_rpn_bbox: 0.0323, loss_cls: 0.1534, acc: 94.2686, loss_bbox: 0.2061, loss_mask: 0.2111, loss: 0.6245 2023-11-17 04:35:21,664 - mmdet - INFO - Epoch [25][800/1833] lr: 5.563e-06, eta: 5:07:08, time: 0.888, data_time: 0.040, memory: 10707, loss_rpn_cls: 0.0220, loss_rpn_bbox: 0.0333, loss_cls: 0.1532, acc: 94.2491, loss_bbox: 0.2054, loss_mask: 0.2134, loss: 0.6273 2023-11-17 04:36:05,959 - mmdet - INFO - Epoch [25][850/1833] lr: 5.563e-06, eta: 5:06:25, time: 0.886, data_time: 0.033, memory: 10707, loss_rpn_cls: 0.0199, loss_rpn_bbox: 0.0318, loss_cls: 0.1485, acc: 94.4413, loss_bbox: 0.2015, loss_mask: 0.2101, loss: 0.6119 2023-11-17 04:36:50,300 - mmdet - INFO - Epoch [25][900/1833] lr: 5.563e-06, eta: 5:05:42, time: 0.887, data_time: 0.035, memory: 10707, loss_rpn_cls: 0.0220, loss_rpn_bbox: 0.0332, loss_cls: 0.1532, acc: 94.2163, loss_bbox: 0.2070, loss_mask: 0.2134, loss: 0.6288 2023-11-17 04:37:34,611 - mmdet - INFO - Epoch [25][950/1833] lr: 5.563e-06, eta: 5:04:59, time: 0.886, data_time: 0.034, memory: 10707, loss_rpn_cls: 0.0213, loss_rpn_bbox: 0.0328, loss_cls: 0.1511, acc: 94.3470, loss_bbox: 0.2042, loss_mask: 0.2114, loss: 0.6207 2023-11-17 04:38:18,808 - mmdet - INFO - Epoch [25][1000/1833] lr: 5.563e-06, eta: 5:04:16, time: 0.884, data_time: 0.032, memory: 10707, loss_rpn_cls: 0.0205, loss_rpn_bbox: 0.0331, loss_cls: 0.1521, acc: 94.2891, loss_bbox: 0.2046, loss_mask: 0.2114, loss: 0.6217 2023-11-17 04:39:03,011 - mmdet - INFO - Epoch [25][1050/1833] lr: 5.563e-06, eta: 5:03:33, time: 0.884, data_time: 0.039, memory: 10707, loss_rpn_cls: 0.0217, loss_rpn_bbox: 0.0329, loss_cls: 0.1530, acc: 94.2014, loss_bbox: 0.2065, loss_mask: 0.2113, loss: 0.6252 2023-11-17 04:39:47,995 - mmdet - INFO - Epoch [25][1100/1833] lr: 5.563e-06, eta: 5:02:50, time: 0.900, data_time: 0.034, memory: 10707, loss_rpn_cls: 0.0223, loss_rpn_bbox: 0.0329, loss_cls: 0.1535, acc: 94.2753, loss_bbox: 0.2075, loss_mask: 0.2158, loss: 0.6319 2023-11-17 04:40:32,643 - mmdet - INFO - Epoch [25][1150/1833] lr: 5.563e-06, eta: 5:02:07, time: 0.893, data_time: 0.034, memory: 10707, loss_rpn_cls: 0.0213, loss_rpn_bbox: 0.0319, loss_cls: 0.1522, acc: 94.3480, loss_bbox: 0.2028, loss_mask: 0.2082, loss: 0.6164 2023-11-17 04:41:16,689 - mmdet - INFO - Epoch [25][1200/1833] lr: 5.563e-06, eta: 5:01:24, time: 0.881, data_time: 0.036, memory: 10707, loss_rpn_cls: 0.0214, loss_rpn_bbox: 0.0331, loss_cls: 0.1544, acc: 94.1812, loss_bbox: 0.2056, loss_mask: 0.2104, loss: 0.6248 2023-11-17 04:42:01,080 - mmdet - INFO - Epoch [25][1250/1833] lr: 5.563e-06, eta: 5:00:41, time: 0.888, data_time: 0.031, memory: 10707, loss_rpn_cls: 0.0220, loss_rpn_bbox: 0.0326, loss_cls: 0.1534, acc: 94.2357, loss_bbox: 0.2072, loss_mask: 0.2120, loss: 0.6272 2023-11-17 04:42:45,091 - mmdet - INFO - Epoch [25][1300/1833] lr: 5.563e-06, eta: 4:59:58, time: 0.880, data_time: 0.031, memory: 10707, loss_rpn_cls: 0.0209, loss_rpn_bbox: 0.0320, loss_cls: 0.1494, acc: 94.4200, loss_bbox: 0.2013, loss_mask: 0.2098, loss: 0.6134 2023-11-17 04:43:29,086 - mmdet - INFO - Epoch [25][1350/1833] lr: 5.563e-06, eta: 4:59:14, time: 0.880, data_time: 0.034, memory: 10707, loss_rpn_cls: 0.0213, loss_rpn_bbox: 0.0324, loss_cls: 0.1534, acc: 94.2532, loss_bbox: 0.2078, loss_mask: 0.2156, loss: 0.6304 2023-11-17 04:44:13,103 - mmdet - INFO - Epoch [25][1400/1833] lr: 5.563e-06, eta: 4:58:31, time: 0.880, data_time: 0.033, memory: 10707, loss_rpn_cls: 0.0210, loss_rpn_bbox: 0.0320, loss_cls: 0.1500, acc: 94.3253, loss_bbox: 0.2030, loss_mask: 0.2105, loss: 0.6166 2023-11-17 04:44:57,489 - mmdet - INFO - Epoch [25][1450/1833] lr: 5.563e-06, eta: 4:57:48, time: 0.888, data_time: 0.033, memory: 10707, loss_rpn_cls: 0.0225, loss_rpn_bbox: 0.0324, loss_cls: 0.1514, acc: 94.3810, loss_bbox: 0.2040, loss_mask: 0.2136, loss: 0.6239 2023-11-17 04:45:41,755 - mmdet - INFO - Epoch [25][1500/1833] lr: 5.563e-06, eta: 4:57:05, time: 0.885, data_time: 0.031, memory: 10707, loss_rpn_cls: 0.0220, loss_rpn_bbox: 0.0332, loss_cls: 0.1554, acc: 94.1653, loss_bbox: 0.2084, loss_mask: 0.2132, loss: 0.6322 2023-11-17 04:46:26,569 - mmdet - INFO - Epoch [25][1550/1833] lr: 5.563e-06, eta: 4:56:22, time: 0.896, data_time: 0.035, memory: 10707, loss_rpn_cls: 0.0215, loss_rpn_bbox: 0.0328, loss_cls: 0.1550, acc: 94.2400, loss_bbox: 0.2087, loss_mask: 0.2118, loss: 0.6299 2023-11-17 04:47:10,624 - mmdet - INFO - Epoch [25][1600/1833] lr: 5.563e-06, eta: 4:55:39, time: 0.881, data_time: 0.037, memory: 10707, loss_rpn_cls: 0.0206, loss_rpn_bbox: 0.0322, loss_cls: 0.1507, acc: 94.3795, loss_bbox: 0.2032, loss_mask: 0.2099, loss: 0.6165 2023-11-17 04:47:54,793 - mmdet - INFO - Epoch [25][1650/1833] lr: 5.563e-06, eta: 4:54:56, time: 0.883, data_time: 0.032, memory: 10707, loss_rpn_cls: 0.0214, loss_rpn_bbox: 0.0339, loss_cls: 0.1584, acc: 94.0433, loss_bbox: 0.2151, loss_mask: 0.2137, loss: 0.6425 2023-11-17 04:48:39,038 - mmdet - INFO - Epoch [25][1700/1833] lr: 5.563e-06, eta: 4:54:13, time: 0.886, data_time: 0.035, memory: 10707, loss_rpn_cls: 0.0223, loss_rpn_bbox: 0.0326, loss_cls: 0.1505, acc: 94.3637, loss_bbox: 0.2034, loss_mask: 0.2134, loss: 0.6222 2023-11-17 04:49:23,135 - mmdet - INFO - Epoch [25][1750/1833] lr: 5.563e-06, eta: 4:53:29, time: 0.882, data_time: 0.032, memory: 10707, loss_rpn_cls: 0.0204, loss_rpn_bbox: 0.0313, loss_cls: 0.1488, acc: 94.4344, loss_bbox: 0.2011, loss_mask: 0.2108, loss: 0.6124 2023-11-17 04:50:07,524 - mmdet - INFO - Epoch [25][1800/1833] lr: 5.563e-06, eta: 4:52:46, time: 0.888, data_time: 0.033, memory: 10707, loss_rpn_cls: 0.0215, loss_rpn_bbox: 0.0327, loss_cls: 0.1539, acc: 94.2267, loss_bbox: 0.2070, loss_mask: 0.2126, loss: 0.6276 2023-11-17 04:50:37,221 - mmdet - INFO - Saving checkpoint at 25 epochs 2023-11-17 04:51:08,672 - mmdet - INFO - Evaluating bbox... 2023-11-17 04:51:40,241 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.494 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.718 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.544 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.351 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.537 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.638 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.619 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.619 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.619 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.465 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.663 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.767 2023-11-17 04:51:40,244 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.585 | bicycle | 0.403 | car | 0.498 | | motorcycle | 0.503 | airplane | 0.704 | bus | 0.698 | | train | 0.712 | truck | 0.454 | boat | 0.338 | | traffic light | 0.315 | fire hydrant | 0.730 | stop sign | 0.673 | | parking meter | 0.520 | bench | 0.312 | bird | 0.423 | | cat | 0.736 | dog | 0.700 | horse | 0.623 | | sheep | 0.596 | cow | 0.632 | elephant | 0.690 | | bear | 0.786 | zebra | 0.679 | giraffe | 0.692 | | backpack | 0.238 | umbrella | 0.485 | handbag | 0.251 | | tie | 0.408 | suitcase | 0.495 | frisbee | 0.728 | | skis | 0.314 | snowboard | 0.453 | sports ball | 0.467 | | kite | 0.454 | baseball bat | 0.424 | baseball glove | 0.447 | | skateboard | 0.603 | surfboard | 0.506 | tennis racket | 0.562 | | bottle | 0.467 | wine glass | 0.421 | cup | 0.516 | | fork | 0.470 | knife | 0.319 | spoon | 0.318 | | bowl | 0.484 | banana | 0.300 | apple | 0.278 | | sandwich | 0.468 | orange | 0.343 | broccoli | 0.268 | | carrot | 0.260 | hot dog | 0.459 | pizza | 0.570 | | donut | 0.557 | cake | 0.467 | chair | 0.369 | | couch | 0.499 | potted plant | 0.357 | bed | 0.477 | | dining table | 0.338 | toilet | 0.663 | tv | 0.641 | | laptop | 0.694 | mouse | 0.655 | remote | 0.453 | | keyboard | 0.569 | cell phone | 0.464 | microwave | 0.689 | | oven | 0.422 | toaster | 0.486 | sink | 0.443 | | refrigerator | 0.677 | book | 0.206 | clock | 0.542 | | vase | 0.435 | scissors | 0.476 | teddy bear | 0.573 | | hair drier | 0.196 | toothbrush | 0.359 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-17 04:51:40,244 - mmdet - INFO - Evaluating segm... 2023-11-17 04:52:11,993 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.447 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.691 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.484 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.266 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.486 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.635 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.568 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.568 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.568 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.403 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.614 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.728 2023-11-17 04:52:11,996 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.516 | bicycle | 0.254 | car | 0.464 | | motorcycle | 0.419 | airplane | 0.560 | bus | 0.691 | | train | 0.699 | truck | 0.445 | boat | 0.320 | | traffic light | 0.307 | fire hydrant | 0.706 | stop sign | 0.663 | | parking meter | 0.524 | bench | 0.241 | bird | 0.354 | | cat | 0.734 | dog | 0.649 | horse | 0.474 | | sheep | 0.539 | cow | 0.552 | elephant | 0.636 | | bear | 0.760 | zebra | 0.597 | giraffe | 0.551 | | backpack | 0.242 | umbrella | 0.532 | handbag | 0.232 | | tie | 0.380 | suitcase | 0.511 | frisbee | 0.675 | | skis | 0.070 | snowboard | 0.301 | sports ball | 0.464 | | kite | 0.319 | baseball bat | 0.333 | baseball glove | 0.475 | | skateboard | 0.405 | surfboard | 0.414 | tennis racket | 0.582 | | bottle | 0.449 | wine glass | 0.382 | cup | 0.518 | | fork | 0.260 | knife | 0.229 | spoon | 0.211 | | bowl | 0.451 | banana | 0.255 | apple | 0.277 | | sandwich | 0.495 | orange | 0.343 | broccoli | 0.244 | | carrot | 0.223 | hot dog | 0.383 | pizza | 0.549 | | donut | 0.566 | cake | 0.492 | chair | 0.275 | | couch | 0.430 | potted plant | 0.298 | bed | 0.400 | | dining table | 0.202 | toilet | 0.653 | tv | 0.678 | | laptop | 0.691 | mouse | 0.634 | remote | 0.416 | | keyboard | 0.555 | cell phone | 0.445 | microwave | 0.710 | | oven | 0.387 | toaster | 0.525 | sink | 0.420 | | refrigerator | 0.706 | book | 0.163 | clock | 0.541 | | vase | 0.433 | scissors | 0.334 | teddy bear | 0.542 | | hair drier | 0.173 | toothbrush | 0.247 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-17 04:52:12,422 - mmdet - INFO - Exp name: mask_rcnn_flash_internimage_b_fpn_3x_coco_0.4_0.9-4x16.py 2023-11-17 04:52:12,423 - mmdet - INFO - Epoch(val) [25][313] bbox_mAP: 0.4936, bbox_mAP_50: 0.7183, bbox_mAP_75: 0.5439, bbox_mAP_s: 0.3507, bbox_mAP_m: 0.5375, bbox_mAP_l: 0.6376, bbox_mAP_copypaste: 0.4936 0.7183 0.5439 0.3507 0.5375 0.6376, segm_mAP: 0.4472, segm_mAP_50: 0.6910, segm_mAP_75: 0.4837, segm_mAP_s: 0.2657, segm_mAP_m: 0.4858, segm_mAP_l: 0.6353, segm_mAP_copypaste: 0.4472 0.6910 0.4837 0.2657 0.4858 0.6353 2023-11-17 04:52:59,094 - mmdet - INFO - Epoch [26][50/1833] lr: 5.563e-06, eta: 4:51:23, time: 0.933, data_time: 0.098, memory: 10707, loss_rpn_cls: 0.0203, loss_rpn_bbox: 0.0330, loss_cls: 0.1504, acc: 94.3573, loss_bbox: 0.2066, loss_mask: 0.2098, loss: 0.6201 2023-11-17 04:53:43,277 - mmdet - INFO - Epoch [26][100/1833] lr: 5.563e-06, eta: 4:50:40, time: 0.884, data_time: 0.034, memory: 10707, loss_rpn_cls: 0.0213, loss_rpn_bbox: 0.0327, loss_cls: 0.1495, acc: 94.3248, loss_bbox: 0.2065, loss_mask: 0.2137, loss: 0.6237 2023-11-17 04:54:26,937 - mmdet - INFO - Epoch [26][150/1833] lr: 5.563e-06, eta: 4:49:56, time: 0.873, data_time: 0.036, memory: 10707, loss_rpn_cls: 0.0203, loss_rpn_bbox: 0.0320, loss_cls: 0.1492, acc: 94.3765, loss_bbox: 0.2053, loss_mask: 0.2109, loss: 0.6177 2023-11-17 04:55:11,114 - mmdet - INFO - Epoch [26][200/1833] lr: 5.563e-06, eta: 4:49:13, time: 0.884, data_time: 0.036, memory: 10707, loss_rpn_cls: 0.0212, loss_rpn_bbox: 0.0321, loss_cls: 0.1482, acc: 94.4169, loss_bbox: 0.2028, loss_mask: 0.2101, loss: 0.6144 2023-11-17 04:55:55,309 - mmdet - INFO - Epoch [26][250/1833] lr: 5.563e-06, eta: 4:48:30, time: 0.884, data_time: 0.036, memory: 10707, loss_rpn_cls: 0.0206, loss_rpn_bbox: 0.0318, loss_cls: 0.1501, acc: 94.3234, loss_bbox: 0.2049, loss_mask: 0.2118, loss: 0.6192 2023-11-17 04:56:38,860 - mmdet - INFO - Epoch [26][300/1833] lr: 5.563e-06, eta: 4:47:47, time: 0.871, data_time: 0.039, memory: 10707, loss_rpn_cls: 0.0199, loss_rpn_bbox: 0.0321, loss_cls: 0.1508, acc: 94.3291, loss_bbox: 0.2050, loss_mask: 0.2122, loss: 0.6201 2023-11-17 04:57:22,528 - mmdet - INFO - Epoch [26][350/1833] lr: 5.563e-06, eta: 4:47:03, time: 0.874, data_time: 0.035, memory: 10707, loss_rpn_cls: 0.0215, loss_rpn_bbox: 0.0325, loss_cls: 0.1497, acc: 94.3804, loss_bbox: 0.2029, loss_mask: 0.2088, loss: 0.6155 2023-11-17 04:58:06,449 - mmdet - INFO - Epoch [26][400/1833] lr: 5.563e-06, eta: 4:46:20, time: 0.878, data_time: 0.032, memory: 10707, loss_rpn_cls: 0.0212, loss_rpn_bbox: 0.0333, loss_cls: 0.1508, acc: 94.3194, loss_bbox: 0.2049, loss_mask: 0.2131, loss: 0.6233 2023-11-17 04:58:50,720 - mmdet - INFO - Epoch [26][450/1833] lr: 5.563e-06, eta: 4:45:37, time: 0.886, data_time: 0.037, memory: 10707, loss_rpn_cls: 0.0216, loss_rpn_bbox: 0.0328, loss_cls: 0.1532, acc: 94.2613, loss_bbox: 0.2064, loss_mask: 0.2123, loss: 0.6262 2023-11-17 04:59:35,232 - mmdet - INFO - Epoch [26][500/1833] lr: 5.563e-06, eta: 4:44:54, time: 0.890, data_time: 0.031, memory: 10707, loss_rpn_cls: 0.0208, loss_rpn_bbox: 0.0331, loss_cls: 0.1492, acc: 94.3729, loss_bbox: 0.2038, loss_mask: 0.2113, loss: 0.6180 2023-11-17 05:00:19,347 - mmdet - INFO - Epoch [26][550/1833] lr: 5.563e-06, eta: 4:44:11, time: 0.882, data_time: 0.037, memory: 10707, loss_rpn_cls: 0.0225, loss_rpn_bbox: 0.0336, loss_cls: 0.1537, acc: 94.1465, loss_bbox: 0.2069, loss_mask: 0.2112, loss: 0.6279 2023-11-17 05:01:03,615 - mmdet - INFO - Epoch [26][600/1833] lr: 5.563e-06, eta: 4:43:27, time: 0.885, data_time: 0.034, memory: 10707, loss_rpn_cls: 0.0211, loss_rpn_bbox: 0.0329, loss_cls: 0.1528, acc: 94.2800, loss_bbox: 0.2058, loss_mask: 0.2128, loss: 0.6255 2023-11-17 05:01:47,509 - mmdet - INFO - Epoch [26][650/1833] lr: 5.563e-06, eta: 4:42:44, time: 0.878, data_time: 0.037, memory: 10707, loss_rpn_cls: 0.0214, loss_rpn_bbox: 0.0329, loss_cls: 0.1517, acc: 94.2801, loss_bbox: 0.2069, loss_mask: 0.2122, loss: 0.6252 2023-11-17 05:02:31,498 - mmdet - INFO - Epoch [26][700/1833] lr: 5.563e-06, eta: 4:42:01, time: 0.880, data_time: 0.034, memory: 10707, loss_rpn_cls: 0.0203, loss_rpn_bbox: 0.0317, loss_cls: 0.1492, acc: 94.3720, loss_bbox: 0.2052, loss_mask: 0.2096, loss: 0.6160 2023-11-17 05:03:15,489 - mmdet - INFO - Epoch [26][750/1833] lr: 5.563e-06, eta: 4:41:18, time: 0.880, data_time: 0.033, memory: 10707, loss_rpn_cls: 0.0205, loss_rpn_bbox: 0.0320, loss_cls: 0.1491, acc: 94.3969, loss_bbox: 0.2031, loss_mask: 0.2118, loss: 0.6166 2023-11-17 05:03:59,192 - mmdet - INFO - Epoch [26][800/1833] lr: 5.563e-06, eta: 4:40:34, time: 0.874, data_time: 0.033, memory: 10707, loss_rpn_cls: 0.0206, loss_rpn_bbox: 0.0318, loss_cls: 0.1487, acc: 94.4543, loss_bbox: 0.1988, loss_mask: 0.2110, loss: 0.6109 2023-11-17 05:04:43,615 - mmdet - INFO - Epoch [26][850/1833] lr: 5.563e-06, eta: 4:39:51, time: 0.888, data_time: 0.039, memory: 10707, loss_rpn_cls: 0.0220, loss_rpn_bbox: 0.0335, loss_cls: 0.1516, acc: 94.2869, loss_bbox: 0.2052, loss_mask: 0.2127, loss: 0.6250 2023-11-17 05:05:27,411 - mmdet - INFO - Epoch [26][900/1833] lr: 5.563e-06, eta: 4:39:08, time: 0.875, data_time: 0.035, memory: 10707, loss_rpn_cls: 0.0221, loss_rpn_bbox: 0.0335, loss_cls: 0.1525, acc: 94.2085, loss_bbox: 0.2070, loss_mask: 0.2149, loss: 0.6299 2023-11-17 05:06:11,328 - mmdet - INFO - Epoch [26][950/1833] lr: 5.563e-06, eta: 4:38:25, time: 0.879, data_time: 0.043, memory: 10707, loss_rpn_cls: 0.0207, loss_rpn_bbox: 0.0321, loss_cls: 0.1502, acc: 94.3472, loss_bbox: 0.2023, loss_mask: 0.2109, loss: 0.6161 2023-11-17 05:06:55,351 - mmdet - INFO - Epoch [26][1000/1833] lr: 5.563e-06, eta: 4:37:41, time: 0.880, data_time: 0.036, memory: 10707, loss_rpn_cls: 0.0198, loss_rpn_bbox: 0.0322, loss_cls: 0.1506, acc: 94.3165, loss_bbox: 0.2042, loss_mask: 0.2125, loss: 0.6194 2023-11-17 05:07:39,176 - mmdet - INFO - Epoch [26][1050/1833] lr: 5.563e-06, eta: 4:36:58, time: 0.877, data_time: 0.034, memory: 10707, loss_rpn_cls: 0.0212, loss_rpn_bbox: 0.0332, loss_cls: 0.1522, acc: 94.2796, loss_bbox: 0.2052, loss_mask: 0.2122, loss: 0.6240 2023-11-17 05:08:23,092 - mmdet - INFO - Epoch [26][1100/1833] lr: 5.563e-06, eta: 4:36:15, time: 0.878, data_time: 0.037, memory: 10707, loss_rpn_cls: 0.0207, loss_rpn_bbox: 0.0324, loss_cls: 0.1518, acc: 94.2632, loss_bbox: 0.2042, loss_mask: 0.2107, loss: 0.6197 2023-11-17 05:09:07,062 - mmdet - INFO - Epoch [26][1150/1833] lr: 5.563e-06, eta: 4:35:31, time: 0.879, data_time: 0.034, memory: 10707, loss_rpn_cls: 0.0212, loss_rpn_bbox: 0.0324, loss_cls: 0.1526, acc: 94.2787, loss_bbox: 0.2068, loss_mask: 0.2121, loss: 0.6251 2023-11-17 05:09:51,273 - mmdet - INFO - Epoch [26][1200/1833] lr: 5.563e-06, eta: 4:34:48, time: 0.884, data_time: 0.032, memory: 10707, loss_rpn_cls: 0.0216, loss_rpn_bbox: 0.0328, loss_cls: 0.1551, acc: 94.1843, loss_bbox: 0.2105, loss_mask: 0.2126, loss: 0.6325 2023-11-17 05:10:35,195 - mmdet - INFO - Epoch [26][1250/1833] lr: 5.563e-06, eta: 4:34:05, time: 0.878, data_time: 0.040, memory: 10707, loss_rpn_cls: 0.0215, loss_rpn_bbox: 0.0337, loss_cls: 0.1523, acc: 94.2447, loss_bbox: 0.2080, loss_mask: 0.2126, loss: 0.6282 2023-11-17 05:11:18,373 - mmdet - INFO - Epoch [26][1300/1833] lr: 5.563e-06, eta: 4:33:21, time: 0.864, data_time: 0.034, memory: 10707, loss_rpn_cls: 0.0219, loss_rpn_bbox: 0.0328, loss_cls: 0.1524, acc: 94.2856, loss_bbox: 0.2052, loss_mask: 0.2114, loss: 0.6237 2023-11-17 05:12:02,336 - mmdet - INFO - Epoch [26][1350/1833] lr: 5.563e-06, eta: 4:32:38, time: 0.879, data_time: 0.034, memory: 10707, loss_rpn_cls: 0.0205, loss_rpn_bbox: 0.0319, loss_cls: 0.1506, acc: 94.3821, loss_bbox: 0.2025, loss_mask: 0.2115, loss: 0.6171 2023-11-17 05:12:46,004 - mmdet - INFO - Epoch [26][1400/1833] lr: 5.563e-06, eta: 4:31:55, time: 0.873, data_time: 0.037, memory: 10707, loss_rpn_cls: 0.0201, loss_rpn_bbox: 0.0321, loss_cls: 0.1501, acc: 94.3239, loss_bbox: 0.2059, loss_mask: 0.2126, loss: 0.6209 2023-11-17 05:13:29,601 - mmdet - INFO - Epoch [26][1450/1833] lr: 5.563e-06, eta: 4:31:11, time: 0.872, data_time: 0.034, memory: 10707, loss_rpn_cls: 0.0207, loss_rpn_bbox: 0.0319, loss_cls: 0.1481, acc: 94.4643, loss_bbox: 0.2009, loss_mask: 0.2088, loss: 0.6104 2023-11-17 05:14:13,282 - mmdet - INFO - Epoch [26][1500/1833] lr: 5.563e-06, eta: 4:30:28, time: 0.874, data_time: 0.029, memory: 10707, loss_rpn_cls: 0.0206, loss_rpn_bbox: 0.0323, loss_cls: 0.1528, acc: 94.2606, loss_bbox: 0.2074, loss_mask: 0.2124, loss: 0.6254 2023-11-17 05:14:57,356 - mmdet - INFO - Epoch [26][1550/1833] lr: 5.563e-06, eta: 4:29:45, time: 0.881, data_time: 0.037, memory: 10707, loss_rpn_cls: 0.0204, loss_rpn_bbox: 0.0337, loss_cls: 0.1530, acc: 94.2054, loss_bbox: 0.2073, loss_mask: 0.2127, loss: 0.6272 2023-11-17 05:15:41,040 - mmdet - INFO - Epoch [26][1600/1833] lr: 5.563e-06, eta: 4:29:01, time: 0.874, data_time: 0.035, memory: 10707, loss_rpn_cls: 0.0210, loss_rpn_bbox: 0.0325, loss_cls: 0.1522, acc: 94.2927, loss_bbox: 0.2040, loss_mask: 0.2108, loss: 0.6206 2023-11-17 05:16:24,982 - mmdet - INFO - Epoch [26][1650/1833] lr: 5.563e-06, eta: 4:28:18, time: 0.879, data_time: 0.033, memory: 10707, loss_rpn_cls: 0.0214, loss_rpn_bbox: 0.0328, loss_cls: 0.1517, acc: 94.3398, loss_bbox: 0.2040, loss_mask: 0.2124, loss: 0.6222 2023-11-17 05:17:08,708 - mmdet - INFO - Epoch [26][1700/1833] lr: 5.563e-06, eta: 4:27:35, time: 0.875, data_time: 0.034, memory: 10707, loss_rpn_cls: 0.0212, loss_rpn_bbox: 0.0314, loss_cls: 0.1495, acc: 94.3921, loss_bbox: 0.2007, loss_mask: 0.2117, loss: 0.6145 2023-11-17 05:17:52,877 - mmdet - INFO - Epoch [26][1750/1833] lr: 5.563e-06, eta: 4:26:51, time: 0.883, data_time: 0.033, memory: 10707, loss_rpn_cls: 0.0214, loss_rpn_bbox: 0.0329, loss_cls: 0.1519, acc: 94.3249, loss_bbox: 0.2059, loss_mask: 0.2122, loss: 0.6244 2023-11-17 05:18:36,817 - mmdet - INFO - Epoch [26][1800/1833] lr: 5.563e-06, eta: 4:26:08, time: 0.879, data_time: 0.036, memory: 10707, loss_rpn_cls: 0.0214, loss_rpn_bbox: 0.0338, loss_cls: 0.1519, acc: 94.3127, loss_bbox: 0.2044, loss_mask: 0.2140, loss: 0.6255 2023-11-17 05:19:05,845 - mmdet - INFO - Saving checkpoint at 26 epochs 2023-11-17 05:19:38,720 - mmdet - INFO - Evaluating bbox... 2023-11-17 05:20:10,264 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.495 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.722 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.547 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.346 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.540 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.638 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.617 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.617 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.617 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.469 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.661 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.760 2023-11-17 05:20:10,267 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.585 | bicycle | 0.387 | car | 0.503 | | motorcycle | 0.497 | airplane | 0.695 | bus | 0.693 | | train | 0.706 | truck | 0.457 | boat | 0.344 | | traffic light | 0.317 | fire hydrant | 0.738 | stop sign | 0.668 | | parking meter | 0.512 | bench | 0.306 | bird | 0.427 | | cat | 0.747 | dog | 0.688 | horse | 0.630 | | sheep | 0.612 | cow | 0.641 | elephant | 0.702 | | bear | 0.779 | zebra | 0.683 | giraffe | 0.698 | | backpack | 0.240 | umbrella | 0.468 | handbag | 0.253 | | tie | 0.417 | suitcase | 0.490 | frisbee | 0.725 | | skis | 0.321 | snowboard | 0.459 | sports ball | 0.481 | | kite | 0.466 | baseball bat | 0.423 | baseball glove | 0.452 | | skateboard | 0.603 | surfboard | 0.506 | tennis racket | 0.565 | | bottle | 0.481 | wine glass | 0.419 | cup | 0.516 | | fork | 0.485 | knife | 0.326 | spoon | 0.304 | | bowl | 0.488 | banana | 0.290 | apple | 0.277 | | sandwich | 0.481 | orange | 0.361 | broccoli | 0.290 | | carrot | 0.273 | hot dog | 0.437 | pizza | 0.553 | | donut | 0.568 | cake | 0.472 | chair | 0.375 | | couch | 0.506 | potted plant | 0.348 | bed | 0.503 | | dining table | 0.324 | toilet | 0.679 | tv | 0.651 | | laptop | 0.687 | mouse | 0.648 | remote | 0.455 | | keyboard | 0.542 | cell phone | 0.468 | microwave | 0.655 | | oven | 0.419 | toaster | 0.533 | sink | 0.451 | | refrigerator | 0.685 | book | 0.203 | clock | 0.544 | | vase | 0.419 | scissors | 0.469 | teddy bear | 0.569 | | hair drier | 0.187 | toothbrush | 0.368 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-17 05:20:10,267 - mmdet - INFO - Evaluating segm... 2023-11-17 05:20:44,174 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.446 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.692 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.487 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.258 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.485 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.636 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.563 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.563 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.563 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.402 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.607 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.721 2023-11-17 05:20:44,177 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.511 | bicycle | 0.245 | car | 0.462 | | motorcycle | 0.414 | airplane | 0.554 | bus | 0.681 | | train | 0.687 | truck | 0.443 | boat | 0.325 | | traffic light | 0.310 | fire hydrant | 0.699 | stop sign | 0.645 | | parking meter | 0.500 | bench | 0.238 | bird | 0.350 | | cat | 0.744 | dog | 0.651 | horse | 0.475 | | sheep | 0.542 | cow | 0.555 | elephant | 0.629 | | bear | 0.761 | zebra | 0.580 | giraffe | 0.546 | | backpack | 0.240 | umbrella | 0.512 | handbag | 0.231 | | tie | 0.385 | suitcase | 0.507 | frisbee | 0.669 | | skis | 0.068 | snowboard | 0.292 | sports ball | 0.470 | | kite | 0.333 | baseball bat | 0.329 | baseball glove | 0.465 | | skateboard | 0.397 | surfboard | 0.405 | tennis racket | 0.588 | | bottle | 0.456 | wine glass | 0.386 | cup | 0.515 | | fork | 0.258 | knife | 0.216 | spoon | 0.218 | | bowl | 0.457 | banana | 0.252 | apple | 0.277 | | sandwich | 0.509 | orange | 0.355 | broccoli | 0.272 | | carrot | 0.239 | hot dog | 0.359 | pizza | 0.539 | | donut | 0.573 | cake | 0.484 | chair | 0.271 | | couch | 0.438 | potted plant | 0.304 | bed | 0.416 | | dining table | 0.196 | toilet | 0.643 | tv | 0.684 | | laptop | 0.683 | mouse | 0.621 | remote | 0.410 | | keyboard | 0.547 | cell phone | 0.444 | microwave | 0.672 | | oven | 0.395 | toaster | 0.607 | sink | 0.422 | | refrigerator | 0.702 | book | 0.158 | clock | 0.537 | | vase | 0.408 | scissors | 0.356 | teddy bear | 0.542 | | hair drier | 0.198 | toothbrush | 0.248 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-17 05:20:44,589 - mmdet - INFO - Exp name: mask_rcnn_flash_internimage_b_fpn_3x_coco_0.4_0.9-4x16.py 2023-11-17 05:20:44,589 - mmdet - INFO - Epoch(val) [26][313] bbox_mAP: 0.4948, bbox_mAP_50: 0.7220, bbox_mAP_75: 0.5474, bbox_mAP_s: 0.3455, bbox_mAP_m: 0.5396, bbox_mAP_l: 0.6384, bbox_mAP_copypaste: 0.4948 0.7220 0.5474 0.3455 0.5396 0.6384, segm_mAP: 0.4463, segm_mAP_50: 0.6916, segm_mAP_75: 0.4870, segm_mAP_s: 0.2578, segm_mAP_m: 0.4852, segm_mAP_l: 0.6357, segm_mAP_copypaste: 0.4463 0.6916 0.4870 0.2578 0.4852 0.6357 2023-11-17 05:21:31,423 - mmdet - INFO - Epoch [27][50/1833] lr: 5.563e-06, eta: 4:24:46, time: 0.936, data_time: 0.095, memory: 10707, loss_rpn_cls: 0.0214, loss_rpn_bbox: 0.0329, loss_cls: 0.1523, acc: 94.2689, loss_bbox: 0.2065, loss_mask: 0.2111, loss: 0.6242 2023-11-17 05:22:15,254 - mmdet - INFO - Epoch [27][100/1833] lr: 5.563e-06, eta: 4:24:03, time: 0.876, data_time: 0.033, memory: 10707, loss_rpn_cls: 0.0209, loss_rpn_bbox: 0.0320, loss_cls: 0.1491, acc: 94.3921, loss_bbox: 0.2016, loss_mask: 0.2073, loss: 0.6107 2023-11-17 05:22:59,394 - mmdet - INFO - Epoch [27][150/1833] lr: 5.563e-06, eta: 4:23:20, time: 0.883, data_time: 0.037, memory: 10707, loss_rpn_cls: 0.0204, loss_rpn_bbox: 0.0323, loss_cls: 0.1481, acc: 94.4094, loss_bbox: 0.2018, loss_mask: 0.2090, loss: 0.6116 2023-11-17 05:23:43,875 - mmdet - INFO - Epoch [27][200/1833] lr: 5.563e-06, eta: 4:22:37, time: 0.890, data_time: 0.038, memory: 10707, loss_rpn_cls: 0.0210, loss_rpn_bbox: 0.0323, loss_cls: 0.1458, acc: 94.4711, loss_bbox: 0.2000, loss_mask: 0.2050, loss: 0.6041 2023-11-17 05:24:28,675 - mmdet - INFO - Epoch [27][250/1833] lr: 5.563e-06, eta: 4:21:54, time: 0.896, data_time: 0.036, memory: 10707, loss_rpn_cls: 0.0200, loss_rpn_bbox: 0.0325, loss_cls: 0.1492, acc: 94.3784, loss_bbox: 0.2051, loss_mask: 0.2132, loss: 0.6201 2023-11-17 05:25:12,618 - mmdet - INFO - Epoch [27][300/1833] lr: 5.563e-06, eta: 4:21:10, time: 0.879, data_time: 0.036, memory: 10707, loss_rpn_cls: 0.0207, loss_rpn_bbox: 0.0327, loss_cls: 0.1490, acc: 94.3978, loss_bbox: 0.2054, loss_mask: 0.2132, loss: 0.6210 2023-11-17 05:25:56,364 - mmdet - INFO - Epoch [27][350/1833] lr: 5.563e-06, eta: 4:20:27, time: 0.875, data_time: 0.034, memory: 10707, loss_rpn_cls: 0.0210, loss_rpn_bbox: 0.0323, loss_cls: 0.1461, acc: 94.5510, loss_bbox: 0.2001, loss_mask: 0.2087, loss: 0.6083 2023-11-17 05:26:40,968 - mmdet - INFO - Epoch [27][400/1833] lr: 5.563e-06, eta: 4:19:44, time: 0.892, data_time: 0.036, memory: 10707, loss_rpn_cls: 0.0208, loss_rpn_bbox: 0.0325, loss_cls: 0.1482, acc: 94.4256, loss_bbox: 0.2057, loss_mask: 0.2116, loss: 0.6188 2023-11-17 05:27:24,958 - mmdet - INFO - Epoch [27][450/1833] lr: 5.563e-06, eta: 4:19:01, time: 0.880, data_time: 0.038, memory: 10707, loss_rpn_cls: 0.0221, loss_rpn_bbox: 0.0346, loss_cls: 0.1569, acc: 94.1164, loss_bbox: 0.2124, loss_mask: 0.2144, loss: 0.6404 2023-11-17 05:28:08,889 - mmdet - INFO - Epoch [27][500/1833] lr: 5.563e-06, eta: 4:18:17, time: 0.879, data_time: 0.036, memory: 10707, loss_rpn_cls: 0.0205, loss_rpn_bbox: 0.0324, loss_cls: 0.1470, acc: 94.4573, loss_bbox: 0.2036, loss_mask: 0.2107, loss: 0.6142 2023-11-17 05:28:53,094 - mmdet - INFO - Epoch [27][550/1833] lr: 5.563e-06, eta: 4:17:34, time: 0.884, data_time: 0.039, memory: 10707, loss_rpn_cls: 0.0209, loss_rpn_bbox: 0.0323, loss_cls: 0.1517, acc: 94.3325, loss_bbox: 0.2039, loss_mask: 0.2119, loss: 0.6207 2023-11-17 05:29:37,323 - mmdet - INFO - Epoch [27][600/1833] lr: 5.563e-06, eta: 4:16:51, time: 0.885, data_time: 0.042, memory: 10707, loss_rpn_cls: 0.0213, loss_rpn_bbox: 0.0327, loss_cls: 0.1549, acc: 94.1802, loss_bbox: 0.2098, loss_mask: 0.2143, loss: 0.6329 2023-11-17 05:30:21,510 - mmdet - INFO - Epoch [27][650/1833] lr: 5.563e-06, eta: 4:16:08, time: 0.884, data_time: 0.034, memory: 10707, loss_rpn_cls: 0.0211, loss_rpn_bbox: 0.0322, loss_cls: 0.1514, acc: 94.3638, loss_bbox: 0.2025, loss_mask: 0.2122, loss: 0.6194 2023-11-17 05:31:05,626 - mmdet - INFO - Epoch [27][700/1833] lr: 5.563e-06, eta: 4:15:25, time: 0.882, data_time: 0.037, memory: 10707, loss_rpn_cls: 0.0211, loss_rpn_bbox: 0.0329, loss_cls: 0.1512, acc: 94.3030, loss_bbox: 0.2036, loss_mask: 0.2109, loss: 0.6196 2023-11-17 05:31:49,337 - mmdet - INFO - Epoch [27][750/1833] lr: 5.563e-06, eta: 4:14:41, time: 0.874, data_time: 0.038, memory: 10707, loss_rpn_cls: 0.0218, loss_rpn_bbox: 0.0329, loss_cls: 0.1487, acc: 94.4078, loss_bbox: 0.2020, loss_mask: 0.2105, loss: 0.6160 2023-11-17 05:32:33,120 - mmdet - INFO - Epoch [27][800/1833] lr: 5.563e-06, eta: 4:13:58, time: 0.876, data_time: 0.040, memory: 10707, loss_rpn_cls: 0.0195, loss_rpn_bbox: 0.0327, loss_cls: 0.1507, acc: 94.3411, loss_bbox: 0.2022, loss_mask: 0.2117, loss: 0.6169 2023-11-17 05:33:17,053 - mmdet - INFO - Epoch [27][850/1833] lr: 5.563e-06, eta: 4:13:15, time: 0.879, data_time: 0.041, memory: 10707, loss_rpn_cls: 0.0200, loss_rpn_bbox: 0.0324, loss_cls: 0.1499, acc: 94.3369, loss_bbox: 0.2051, loss_mask: 0.2112, loss: 0.6186 2023-11-17 05:34:00,585 - mmdet - INFO - Epoch [27][900/1833] lr: 5.563e-06, eta: 4:12:31, time: 0.871, data_time: 0.034, memory: 10707, loss_rpn_cls: 0.0203, loss_rpn_bbox: 0.0319, loss_cls: 0.1467, acc: 94.4482, loss_bbox: 0.2028, loss_mask: 0.2118, loss: 0.6134 2023-11-17 05:34:44,370 - mmdet - INFO - Epoch [27][950/1833] lr: 5.563e-06, eta: 4:11:48, time: 0.876, data_time: 0.041, memory: 10707, loss_rpn_cls: 0.0208, loss_rpn_bbox: 0.0323, loss_cls: 0.1485, acc: 94.4083, loss_bbox: 0.2036, loss_mask: 0.2120, loss: 0.6172 2023-11-17 05:35:28,087 - mmdet - INFO - Epoch [27][1000/1833] lr: 5.563e-06, eta: 4:11:04, time: 0.874, data_time: 0.030, memory: 10707, loss_rpn_cls: 0.0193, loss_rpn_bbox: 0.0313, loss_cls: 0.1456, acc: 94.5530, loss_bbox: 0.1989, loss_mask: 0.2092, loss: 0.6042 2023-11-17 05:36:12,579 - mmdet - INFO - Epoch [27][1050/1833] lr: 5.563e-06, eta: 4:10:21, time: 0.890, data_time: 0.034, memory: 10707, loss_rpn_cls: 0.0211, loss_rpn_bbox: 0.0324, loss_cls: 0.1513, acc: 94.2874, loss_bbox: 0.2063, loss_mask: 0.2126, loss: 0.6235 2023-11-17 05:36:56,431 - mmdet - INFO - Epoch [27][1100/1833] lr: 5.563e-06, eta: 4:09:38, time: 0.877, data_time: 0.034, memory: 10707, loss_rpn_cls: 0.0202, loss_rpn_bbox: 0.0317, loss_cls: 0.1504, acc: 94.3926, loss_bbox: 0.2032, loss_mask: 0.2112, loss: 0.6167 2023-11-17 05:37:40,738 - mmdet - INFO - Epoch [27][1150/1833] lr: 5.563e-06, eta: 4:08:55, time: 0.886, data_time: 0.033, memory: 10707, loss_rpn_cls: 0.0205, loss_rpn_bbox: 0.0325, loss_cls: 0.1478, acc: 94.4146, loss_bbox: 0.2023, loss_mask: 0.2114, loss: 0.6144 2023-11-17 05:38:24,953 - mmdet - INFO - Epoch [27][1200/1833] lr: 5.563e-06, eta: 4:08:12, time: 0.884, data_time: 0.036, memory: 10707, loss_rpn_cls: 0.0211, loss_rpn_bbox: 0.0328, loss_cls: 0.1513, acc: 94.3308, loss_bbox: 0.2054, loss_mask: 0.2129, loss: 0.6235 2023-11-17 05:39:08,776 - mmdet - INFO - Epoch [27][1250/1833] lr: 5.563e-06, eta: 4:07:28, time: 0.876, data_time: 0.032, memory: 10707, loss_rpn_cls: 0.0190, loss_rpn_bbox: 0.0311, loss_cls: 0.1466, acc: 94.4617, loss_bbox: 0.2021, loss_mask: 0.2107, loss: 0.6095 2023-11-17 05:39:52,786 - mmdet - INFO - Epoch [27][1300/1833] lr: 5.563e-06, eta: 4:06:45, time: 0.880, data_time: 0.035, memory: 10707, loss_rpn_cls: 0.0208, loss_rpn_bbox: 0.0338, loss_cls: 0.1508, acc: 94.2902, loss_bbox: 0.2052, loss_mask: 0.2087, loss: 0.6192 2023-11-17 05:40:36,745 - mmdet - INFO - Epoch [27][1350/1833] lr: 5.563e-06, eta: 4:06:02, time: 0.879, data_time: 0.039, memory: 10744, loss_rpn_cls: 0.0209, loss_rpn_bbox: 0.0320, loss_cls: 0.1496, acc: 94.3634, loss_bbox: 0.2039, loss_mask: 0.2132, loss: 0.6196 2023-11-17 05:41:20,619 - mmdet - INFO - Epoch [27][1400/1833] lr: 5.563e-06, eta: 4:05:18, time: 0.878, data_time: 0.033, memory: 10744, loss_rpn_cls: 0.0201, loss_rpn_bbox: 0.0324, loss_cls: 0.1485, acc: 94.4224, loss_bbox: 0.2011, loss_mask: 0.2099, loss: 0.6121 2023-11-17 05:42:04,701 - mmdet - INFO - Epoch [27][1450/1833] lr: 5.563e-06, eta: 4:04:35, time: 0.882, data_time: 0.033, memory: 10744, loss_rpn_cls: 0.0192, loss_rpn_bbox: 0.0312, loss_cls: 0.1454, acc: 94.4965, loss_bbox: 0.1985, loss_mask: 0.2069, loss: 0.6012 2023-11-17 05:42:51,582 - mmdet - INFO - Epoch [27][1500/1833] lr: 5.563e-06, eta: 4:03:53, time: 0.938, data_time: 0.035, memory: 10744, loss_rpn_cls: 0.0200, loss_rpn_bbox: 0.0325, loss_cls: 0.1472, acc: 94.4540, loss_bbox: 0.2018, loss_mask: 0.2093, loss: 0.6108 2023-11-17 05:43:35,496 - mmdet - INFO - Epoch [27][1550/1833] lr: 5.563e-06, eta: 4:03:09, time: 0.878, data_time: 0.033, memory: 10744, loss_rpn_cls: 0.0196, loss_rpn_bbox: 0.0317, loss_cls: 0.1477, acc: 94.4598, loss_bbox: 0.2004, loss_mask: 0.2100, loss: 0.6094 2023-11-17 05:44:20,034 - mmdet - INFO - Epoch [27][1600/1833] lr: 5.563e-06, eta: 4:02:26, time: 0.891, data_time: 0.035, memory: 10744, loss_rpn_cls: 0.0205, loss_rpn_bbox: 0.0325, loss_cls: 0.1487, acc: 94.3988, loss_bbox: 0.2011, loss_mask: 0.2103, loss: 0.6131 2023-11-17 05:45:06,612 - mmdet - INFO - Epoch [27][1650/1833] lr: 5.563e-06, eta: 4:01:44, time: 0.932, data_time: 0.039, memory: 10744, loss_rpn_cls: 0.0217, loss_rpn_bbox: 0.0338, loss_cls: 0.1560, acc: 94.0982, loss_bbox: 0.2121, loss_mask: 0.2147, loss: 0.6383 2023-11-17 05:45:50,578 - mmdet - INFO - Epoch [27][1700/1833] lr: 5.563e-06, eta: 4:01:01, time: 0.879, data_time: 0.034, memory: 10744, loss_rpn_cls: 0.0210, loss_rpn_bbox: 0.0321, loss_cls: 0.1519, acc: 94.3141, loss_bbox: 0.2052, loss_mask: 0.2109, loss: 0.6211 2023-11-17 05:46:34,576 - mmdet - INFO - Epoch [27][1750/1833] lr: 5.563e-06, eta: 4:00:17, time: 0.880, data_time: 0.033, memory: 10744, loss_rpn_cls: 0.0214, loss_rpn_bbox: 0.0331, loss_cls: 0.1504, acc: 94.3575, loss_bbox: 0.2027, loss_mask: 0.2086, loss: 0.6163 2023-11-17 05:47:18,280 - mmdet - INFO - Epoch [27][1800/1833] lr: 5.563e-06, eta: 3:59:34, time: 0.874, data_time: 0.034, memory: 10744, loss_rpn_cls: 0.0210, loss_rpn_bbox: 0.0318, loss_cls: 0.1482, acc: 94.4050, loss_bbox: 0.1990, loss_mask: 0.2126, loss: 0.6126 2023-11-17 05:47:47,850 - mmdet - INFO - Saving checkpoint at 27 epochs 2023-11-17 05:48:23,825 - mmdet - INFO - Evaluating bbox... 2023-11-17 05:48:56,098 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.493 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.718 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.544 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.347 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.535 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.636 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.615 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.615 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.615 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.467 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.657 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.755 2023-11-17 05:48:56,101 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.587 | bicycle | 0.398 | car | 0.502 | | motorcycle | 0.499 | airplane | 0.700 | bus | 0.692 | | train | 0.713 | truck | 0.455 | boat | 0.338 | | traffic light | 0.317 | fire hydrant | 0.720 | stop sign | 0.667 | | parking meter | 0.526 | bench | 0.305 | bird | 0.431 | | cat | 0.742 | dog | 0.693 | horse | 0.619 | | sheep | 0.614 | cow | 0.632 | elephant | 0.698 | | bear | 0.750 | zebra | 0.688 | giraffe | 0.694 | | backpack | 0.242 | umbrella | 0.467 | handbag | 0.260 | | tie | 0.414 | suitcase | 0.494 | frisbee | 0.721 | | skis | 0.329 | snowboard | 0.460 | sports ball | 0.479 | | kite | 0.475 | baseball bat | 0.443 | baseball glove | 0.462 | | skateboard | 0.593 | surfboard | 0.497 | tennis racket | 0.565 | | bottle | 0.483 | wine glass | 0.434 | cup | 0.518 | | fork | 0.479 | knife | 0.314 | spoon | 0.289 | | bowl | 0.487 | banana | 0.289 | apple | 0.263 | | sandwich | 0.457 | orange | 0.359 | broccoli | 0.289 | | carrot | 0.253 | hot dog | 0.453 | pizza | 0.547 | | donut | 0.584 | cake | 0.472 | chair | 0.378 | | couch | 0.507 | potted plant | 0.355 | bed | 0.460 | | dining table | 0.326 | toilet | 0.670 | tv | 0.646 | | laptop | 0.685 | mouse | 0.651 | remote | 0.466 | | keyboard | 0.582 | cell phone | 0.468 | microwave | 0.659 | | oven | 0.407 | toaster | 0.431 | sink | 0.455 | | refrigerator | 0.694 | book | 0.209 | clock | 0.537 | | vase | 0.414 | scissors | 0.461 | teddy bear | 0.587 | | hair drier | 0.201 | toothbrush | 0.328 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-17 05:48:56,101 - mmdet - INFO - Evaluating segm... 2023-11-17 05:49:27,900 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.444 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.689 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.480 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.259 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.487 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.632 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.560 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.560 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.560 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.395 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.606 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.716 2023-11-17 05:49:27,903 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.516 | bicycle | 0.245 | car | 0.460 | | motorcycle | 0.416 | airplane | 0.550 | bus | 0.680 | | train | 0.709 | truck | 0.438 | boat | 0.318 | | traffic light | 0.305 | fire hydrant | 0.705 | stop sign | 0.652 | | parking meter | 0.531 | bench | 0.234 | bird | 0.355 | | cat | 0.732 | dog | 0.659 | horse | 0.465 | | sheep | 0.541 | cow | 0.533 | elephant | 0.641 | | bear | 0.727 | zebra | 0.593 | giraffe | 0.545 | | backpack | 0.244 | umbrella | 0.520 | handbag | 0.247 | | tie | 0.379 | suitcase | 0.510 | frisbee | 0.674 | | skis | 0.064 | snowboard | 0.303 | sports ball | 0.473 | | kite | 0.332 | baseball bat | 0.330 | baseball glove | 0.479 | | skateboard | 0.409 | surfboard | 0.401 | tennis racket | 0.591 | | bottle | 0.460 | wine glass | 0.395 | cup | 0.518 | | fork | 0.262 | knife | 0.218 | spoon | 0.221 | | bowl | 0.451 | banana | 0.248 | apple | 0.260 | | sandwich | 0.482 | orange | 0.362 | broccoli | 0.267 | | carrot | 0.229 | hot dog | 0.364 | pizza | 0.532 | | donut | 0.582 | cake | 0.484 | chair | 0.270 | | couch | 0.433 | potted plant | 0.304 | bed | 0.380 | | dining table | 0.200 | toilet | 0.654 | tv | 0.677 | | laptop | 0.679 | mouse | 0.632 | remote | 0.412 | | keyboard | 0.570 | cell phone | 0.448 | microwave | 0.685 | | oven | 0.382 | toaster | 0.457 | sink | 0.402 | | refrigerator | 0.689 | book | 0.151 | clock | 0.541 | | vase | 0.410 | scissors | 0.344 | teddy bear | 0.539 | | hair drier | 0.181 | toothbrush | 0.241 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-17 05:49:28,322 - mmdet - INFO - Exp name: mask_rcnn_flash_internimage_b_fpn_3x_coco_0.4_0.9-4x16.py 2023-11-17 05:49:28,322 - mmdet - INFO - Epoch(val) [27][313] bbox_mAP: 0.4928, bbox_mAP_50: 0.7183, bbox_mAP_75: 0.5441, bbox_mAP_s: 0.3474, bbox_mAP_m: 0.5349, bbox_mAP_l: 0.6360, bbox_mAP_copypaste: 0.4928 0.7183 0.5441 0.3474 0.5349 0.6360, segm_mAP: 0.4440, segm_mAP_50: 0.6895, segm_mAP_75: 0.4799, segm_mAP_s: 0.2593, segm_mAP_m: 0.4868, segm_mAP_l: 0.6321, segm_mAP_copypaste: 0.4440 0.6895 0.4799 0.2593 0.4868 0.6321 2023-11-17 05:50:18,477 - mmdet - INFO - Epoch [28][50/1833] lr: 5.563e-07, eta: 3:58:14, time: 1.001, data_time: 0.128, memory: 10744, loss_rpn_cls: 0.0196, loss_rpn_bbox: 0.0321, loss_cls: 0.1467, acc: 94.4352, loss_bbox: 0.2001, loss_mask: 0.2081, loss: 0.6066 2023-11-17 05:51:02,467 - mmdet - INFO - Epoch [28][100/1833] lr: 5.563e-07, eta: 3:57:31, time: 0.880, data_time: 0.036, memory: 10744, loss_rpn_cls: 0.0201, loss_rpn_bbox: 0.0317, loss_cls: 0.1445, acc: 94.5070, loss_bbox: 0.1987, loss_mask: 0.2069, loss: 0.6019 2023-11-17 05:51:47,203 - mmdet - INFO - Epoch [28][150/1833] lr: 5.563e-07, eta: 3:56:48, time: 0.895, data_time: 0.033, memory: 10744, loss_rpn_cls: 0.0196, loss_rpn_bbox: 0.0318, loss_cls: 0.1463, acc: 94.4394, loss_bbox: 0.2020, loss_mask: 0.2090, loss: 0.6087 2023-11-17 05:52:31,183 - mmdet - INFO - Epoch [28][200/1833] lr: 5.563e-07, eta: 3:56:05, time: 0.880, data_time: 0.042, memory: 10744, loss_rpn_cls: 0.0205, loss_rpn_bbox: 0.0328, loss_cls: 0.1501, acc: 94.3220, loss_bbox: 0.2032, loss_mask: 0.2097, loss: 0.6164 2023-11-17 05:53:15,770 - mmdet - INFO - Epoch [28][250/1833] lr: 5.563e-07, eta: 3:55:22, time: 0.892, data_time: 0.035, memory: 10744, loss_rpn_cls: 0.0208, loss_rpn_bbox: 0.0323, loss_cls: 0.1461, acc: 94.4467, loss_bbox: 0.1996, loss_mask: 0.2081, loss: 0.6069 2023-11-17 05:53:59,775 - mmdet - INFO - Epoch [28][300/1833] lr: 5.563e-07, eta: 3:54:38, time: 0.880, data_time: 0.039, memory: 10744, loss_rpn_cls: 0.0195, loss_rpn_bbox: 0.0313, loss_cls: 0.1421, acc: 94.6224, loss_bbox: 0.1941, loss_mask: 0.2040, loss: 0.5911 2023-11-17 05:54:45,523 - mmdet - INFO - Epoch [28][350/1833] lr: 5.563e-07, eta: 3:53:56, time: 0.915, data_time: 0.040, memory: 10744, loss_rpn_cls: 0.0209, loss_rpn_bbox: 0.0314, loss_cls: 0.1484, acc: 94.3849, loss_bbox: 0.1999, loss_mask: 0.2063, loss: 0.6069 2023-11-17 05:55:30,093 - mmdet - INFO - Epoch [28][400/1833] lr: 5.563e-07, eta: 3:53:13, time: 0.891, data_time: 0.037, memory: 10744, loss_rpn_cls: 0.0200, loss_rpn_bbox: 0.0320, loss_cls: 0.1447, acc: 94.5063, loss_bbox: 0.1982, loss_mask: 0.2071, loss: 0.6021 2023-11-17 05:56:14,315 - mmdet - INFO - Epoch [28][450/1833] lr: 5.563e-07, eta: 3:52:29, time: 0.885, data_time: 0.039, memory: 10744, loss_rpn_cls: 0.0196, loss_rpn_bbox: 0.0314, loss_cls: 0.1421, acc: 94.6113, loss_bbox: 0.1973, loss_mask: 0.2047, loss: 0.5951 2023-11-17 05:56:58,477 - mmdet - INFO - Epoch [28][500/1833] lr: 5.563e-07, eta: 3:51:46, time: 0.883, data_time: 0.037, memory: 10744, loss_rpn_cls: 0.0193, loss_rpn_bbox: 0.0306, loss_cls: 0.1427, acc: 94.5839, loss_bbox: 0.1952, loss_mask: 0.2061, loss: 0.5938 2023-11-17 05:57:43,149 - mmdet - INFO - Epoch [28][550/1833] lr: 5.563e-07, eta: 3:51:03, time: 0.894, data_time: 0.035, memory: 10744, loss_rpn_cls: 0.0202, loss_rpn_bbox: 0.0319, loss_cls: 0.1454, acc: 94.4471, loss_bbox: 0.1983, loss_mask: 0.2085, loss: 0.6043 2023-11-17 05:58:27,905 - mmdet - INFO - Epoch [28][600/1833] lr: 5.563e-07, eta: 3:50:20, time: 0.895, data_time: 0.033, memory: 10744, loss_rpn_cls: 0.0195, loss_rpn_bbox: 0.0310, loss_cls: 0.1422, acc: 94.5949, loss_bbox: 0.1974, loss_mask: 0.2060, loss: 0.5960 2023-11-17 05:59:12,213 - mmdet - INFO - Epoch [28][650/1833] lr: 5.563e-07, eta: 3:49:37, time: 0.887, data_time: 0.032, memory: 10744, loss_rpn_cls: 0.0199, loss_rpn_bbox: 0.0318, loss_cls: 0.1429, acc: 94.5527, loss_bbox: 0.1971, loss_mask: 0.2072, loss: 0.5989 2023-11-17 05:59:56,830 - mmdet - INFO - Epoch [28][700/1833] lr: 5.563e-07, eta: 3:48:54, time: 0.892, data_time: 0.037, memory: 10744, loss_rpn_cls: 0.0186, loss_rpn_bbox: 0.0310, loss_cls: 0.1451, acc: 94.4922, loss_bbox: 0.2009, loss_mask: 0.2069, loss: 0.6025 2023-11-17 06:00:40,804 - mmdet - INFO - Epoch [28][750/1833] lr: 5.563e-07, eta: 3:48:10, time: 0.879, data_time: 0.038, memory: 10744, loss_rpn_cls: 0.0193, loss_rpn_bbox: 0.0299, loss_cls: 0.1405, acc: 94.6721, loss_bbox: 0.1936, loss_mask: 0.2059, loss: 0.5892 2023-11-17 06:01:27,871 - mmdet - INFO - Epoch [28][800/1833] lr: 5.563e-07, eta: 3:47:28, time: 0.942, data_time: 0.038, memory: 10744, loss_rpn_cls: 0.0193, loss_rpn_bbox: 0.0305, loss_cls: 0.1393, acc: 94.6988, loss_bbox: 0.1951, loss_mask: 0.2048, loss: 0.5891 2023-11-17 06:02:11,893 - mmdet - INFO - Epoch [28][850/1833] lr: 5.563e-07, eta: 3:46:45, time: 0.880, data_time: 0.035, memory: 10744, loss_rpn_cls: 0.0182, loss_rpn_bbox: 0.0302, loss_cls: 0.1406, acc: 94.6655, loss_bbox: 0.1953, loss_mask: 0.2043, loss: 0.5885 2023-11-17 06:02:56,173 - mmdet - INFO - Epoch [28][900/1833] lr: 5.563e-07, eta: 3:46:01, time: 0.886, data_time: 0.036, memory: 10744, loss_rpn_cls: 0.0193, loss_rpn_bbox: 0.0322, loss_cls: 0.1438, acc: 94.4937, loss_bbox: 0.2009, loss_mask: 0.2072, loss: 0.6034 2023-11-17 06:03:40,734 - mmdet - INFO - Epoch [28][950/1833] lr: 5.563e-07, eta: 3:45:18, time: 0.891, data_time: 0.036, memory: 10744, loss_rpn_cls: 0.0199, loss_rpn_bbox: 0.0316, loss_cls: 0.1442, acc: 94.5030, loss_bbox: 0.1974, loss_mask: 0.2056, loss: 0.5988 2023-11-17 06:04:25,301 - mmdet - INFO - Epoch [28][1000/1833] lr: 5.563e-07, eta: 3:44:35, time: 0.891, data_time: 0.038, memory: 10744, loss_rpn_cls: 0.0193, loss_rpn_bbox: 0.0310, loss_cls: 0.1431, acc: 94.5592, loss_bbox: 0.1972, loss_mask: 0.2050, loss: 0.5956 2023-11-17 06:05:10,190 - mmdet - INFO - Epoch [28][1050/1833] lr: 5.563e-07, eta: 3:43:52, time: 0.898, data_time: 0.038, memory: 10744, loss_rpn_cls: 0.0213, loss_rpn_bbox: 0.0322, loss_cls: 0.1439, acc: 94.5359, loss_bbox: 0.2005, loss_mask: 0.2071, loss: 0.6050 2023-11-17 06:05:54,426 - mmdet - INFO - Epoch [28][1100/1833] lr: 5.563e-07, eta: 3:43:09, time: 0.885, data_time: 0.036, memory: 10744, loss_rpn_cls: 0.0198, loss_rpn_bbox: 0.0314, loss_cls: 0.1433, acc: 94.5443, loss_bbox: 0.1976, loss_mask: 0.2063, loss: 0.5983 2023-11-17 06:06:39,186 - mmdet - INFO - Epoch [28][1150/1833] lr: 5.563e-07, eta: 3:42:26, time: 0.895, data_time: 0.038, memory: 10744, loss_rpn_cls: 0.0196, loss_rpn_bbox: 0.0303, loss_cls: 0.1421, acc: 94.5999, loss_bbox: 0.1966, loss_mask: 0.2043, loss: 0.5929 2023-11-17 06:07:23,235 - mmdet - INFO - Epoch [28][1200/1833] lr: 5.563e-07, eta: 3:41:42, time: 0.881, data_time: 0.032, memory: 10744, loss_rpn_cls: 0.0193, loss_rpn_bbox: 0.0317, loss_cls: 0.1411, acc: 94.6078, loss_bbox: 0.1958, loss_mask: 0.2080, loss: 0.5959 2023-11-17 06:08:07,720 - mmdet - INFO - Epoch [28][1250/1833] lr: 5.563e-07, eta: 3:40:59, time: 0.890, data_time: 0.030, memory: 10744, loss_rpn_cls: 0.0203, loss_rpn_bbox: 0.0319, loss_cls: 0.1430, acc: 94.5757, loss_bbox: 0.1987, loss_mask: 0.2099, loss: 0.6039 2023-11-17 06:08:52,036 - mmdet - INFO - Epoch [28][1300/1833] lr: 5.563e-07, eta: 3:40:16, time: 0.886, data_time: 0.029, memory: 10744, loss_rpn_cls: 0.0203, loss_rpn_bbox: 0.0312, loss_cls: 0.1424, acc: 94.6014, loss_bbox: 0.1955, loss_mask: 0.2051, loss: 0.5945 2023-11-17 06:09:36,304 - mmdet - INFO - Epoch [28][1350/1833] lr: 5.563e-07, eta: 3:39:33, time: 0.885, data_time: 0.034, memory: 10998, loss_rpn_cls: 0.0196, loss_rpn_bbox: 0.0309, loss_cls: 0.1432, acc: 94.5616, loss_bbox: 0.1967, loss_mask: 0.2080, loss: 0.5984 2023-11-17 06:10:20,995 - mmdet - INFO - Epoch [28][1400/1833] lr: 5.563e-07, eta: 3:38:50, time: 0.894, data_time: 0.032, memory: 10998, loss_rpn_cls: 0.0197, loss_rpn_bbox: 0.0317, loss_cls: 0.1432, acc: 94.5596, loss_bbox: 0.1983, loss_mask: 0.2071, loss: 0.5999 2023-11-17 06:11:05,229 - mmdet - INFO - Epoch [28][1450/1833] lr: 5.563e-07, eta: 3:38:06, time: 0.885, data_time: 0.034, memory: 10998, loss_rpn_cls: 0.0192, loss_rpn_bbox: 0.0303, loss_cls: 0.1384, acc: 94.7458, loss_bbox: 0.1920, loss_mask: 0.2062, loss: 0.5861 2023-11-17 06:11:49,647 - mmdet - INFO - Epoch [28][1500/1833] lr: 5.563e-07, eta: 3:37:23, time: 0.888, data_time: 0.031, memory: 10998, loss_rpn_cls: 0.0202, loss_rpn_bbox: 0.0317, loss_cls: 0.1432, acc: 94.5546, loss_bbox: 0.1985, loss_mask: 0.2075, loss: 0.6011 2023-11-17 06:12:33,779 - mmdet - INFO - Epoch [28][1550/1833] lr: 5.563e-07, eta: 3:36:40, time: 0.883, data_time: 0.036, memory: 10998, loss_rpn_cls: 0.0196, loss_rpn_bbox: 0.0314, loss_cls: 0.1417, acc: 94.6021, loss_bbox: 0.1974, loss_mask: 0.2056, loss: 0.5956 2023-11-17 06:13:17,974 - mmdet - INFO - Epoch [28][1600/1833] lr: 5.563e-07, eta: 3:35:57, time: 0.884, data_time: 0.032, memory: 10998, loss_rpn_cls: 0.0186, loss_rpn_bbox: 0.0304, loss_cls: 0.1398, acc: 94.6866, loss_bbox: 0.1946, loss_mask: 0.2038, loss: 0.5871 2023-11-17 06:14:02,008 - mmdet - INFO - Epoch [28][1650/1833] lr: 5.563e-07, eta: 3:35:13, time: 0.881, data_time: 0.030, memory: 10998, loss_rpn_cls: 0.0196, loss_rpn_bbox: 0.0311, loss_cls: 0.1419, acc: 94.6354, loss_bbox: 0.1947, loss_mask: 0.2055, loss: 0.5930 2023-11-17 06:14:46,066 - mmdet - INFO - Epoch [28][1700/1833] lr: 5.563e-07, eta: 3:34:30, time: 0.881, data_time: 0.032, memory: 10998, loss_rpn_cls: 0.0203, loss_rpn_bbox: 0.0310, loss_cls: 0.1419, acc: 94.6147, loss_bbox: 0.1955, loss_mask: 0.2064, loss: 0.5951 2023-11-17 06:15:30,491 - mmdet - INFO - Epoch [28][1750/1833] lr: 5.563e-07, eta: 3:33:47, time: 0.888, data_time: 0.031, memory: 10998, loss_rpn_cls: 0.0203, loss_rpn_bbox: 0.0314, loss_cls: 0.1443, acc: 94.5071, loss_bbox: 0.1994, loss_mask: 0.2090, loss: 0.6045 2023-11-17 06:16:14,901 - mmdet - INFO - Epoch [28][1800/1833] lr: 5.563e-07, eta: 3:33:04, time: 0.888, data_time: 0.030, memory: 10998, loss_rpn_cls: 0.0187, loss_rpn_bbox: 0.0307, loss_cls: 0.1391, acc: 94.6848, loss_bbox: 0.1935, loss_mask: 0.2038, loss: 0.5859 2023-11-17 06:16:44,560 - mmdet - INFO - Saving checkpoint at 28 epochs 2023-11-17 06:17:18,563 - mmdet - INFO - Evaluating bbox... 2023-11-17 06:17:49,139 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.505 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.725 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.555 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.358 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.546 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.651 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.624 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.624 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.624 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.479 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.661 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.766 2023-11-17 06:17:49,142 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.595 | bicycle | 0.409 | car | 0.506 | | motorcycle | 0.514 | airplane | 0.696 | bus | 0.711 | | train | 0.724 | truck | 0.470 | boat | 0.351 | | traffic light | 0.317 | fire hydrant | 0.745 | stop sign | 0.689 | | parking meter | 0.522 | bench | 0.318 | bird | 0.430 | | cat | 0.754 | dog | 0.711 | horse | 0.647 | | sheep | 0.610 | cow | 0.649 | elephant | 0.712 | | bear | 0.792 | zebra | 0.697 | giraffe | 0.714 | | backpack | 0.245 | umbrella | 0.483 | handbag | 0.262 | | tie | 0.424 | suitcase | 0.507 | frisbee | 0.738 | | skis | 0.343 | snowboard | 0.467 | sports ball | 0.483 | | kite | 0.482 | baseball bat | 0.443 | baseball glove | 0.468 | | skateboard | 0.615 | surfboard | 0.506 | tennis racket | 0.578 | | bottle | 0.490 | wine glass | 0.440 | cup | 0.525 | | fork | 0.496 | knife | 0.340 | spoon | 0.312 | | bowl | 0.498 | banana | 0.298 | apple | 0.275 | | sandwich | 0.479 | orange | 0.360 | broccoli | 0.289 | | carrot | 0.261 | hot dog | 0.465 | pizza | 0.564 | | donut | 0.575 | cake | 0.475 | chair | 0.383 | | couch | 0.510 | potted plant | 0.364 | bed | 0.507 | | dining table | 0.327 | toilet | 0.691 | tv | 0.659 | | laptop | 0.710 | mouse | 0.671 | remote | 0.467 | | keyboard | 0.581 | cell phone | 0.476 | microwave | 0.682 | | oven | 0.421 | toaster | 0.504 | sink | 0.462 | | refrigerator | 0.699 | book | 0.215 | clock | 0.542 | | vase | 0.422 | scissors | 0.475 | teddy bear | 0.589 | | hair drier | 0.233 | toothbrush | 0.354 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-17 06:17:49,142 - mmdet - INFO - Evaluating segm... 2023-11-17 06:18:19,974 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.452 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.697 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.489 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.267 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.489 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.637 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.565 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.565 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.565 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.405 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.607 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.720 2023-11-17 06:18:19,977 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.519 | bicycle | 0.256 | car | 0.462 | | motorcycle | 0.418 | airplane | 0.560 | bus | 0.687 | | train | 0.710 | truck | 0.456 | boat | 0.327 | | traffic light | 0.304 | fire hydrant | 0.710 | stop sign | 0.657 | | parking meter | 0.526 | bench | 0.244 | bird | 0.354 | | cat | 0.735 | dog | 0.661 | horse | 0.483 | | sheep | 0.549 | cow | 0.551 | elephant | 0.648 | | bear | 0.772 | zebra | 0.598 | giraffe | 0.568 | | backpack | 0.243 | umbrella | 0.524 | handbag | 0.246 | | tie | 0.390 | suitcase | 0.517 | frisbee | 0.682 | | skis | 0.073 | snowboard | 0.308 | sports ball | 0.469 | | kite | 0.336 | baseball bat | 0.332 | baseball glove | 0.476 | | skateboard | 0.410 | surfboard | 0.412 | tennis racket | 0.600 | | bottle | 0.461 | wine glass | 0.399 | cup | 0.525 | | fork | 0.257 | knife | 0.226 | spoon | 0.222 | | bowl | 0.457 | banana | 0.255 | apple | 0.267 | | sandwich | 0.513 | orange | 0.355 | broccoli | 0.264 | | carrot | 0.231 | hot dog | 0.373 | pizza | 0.543 | | donut | 0.575 | cake | 0.488 | chair | 0.280 | | couch | 0.425 | potted plant | 0.307 | bed | 0.412 | | dining table | 0.203 | toilet | 0.663 | tv | 0.678 | | laptop | 0.690 | mouse | 0.635 | remote | 0.414 | | keyboard | 0.570 | cell phone | 0.454 | microwave | 0.699 | | oven | 0.381 | toaster | 0.533 | sink | 0.423 | | refrigerator | 0.705 | book | 0.157 | clock | 0.539 | | vase | 0.411 | scissors | 0.330 | teddy bear | 0.554 | | hair drier | 0.246 | toothbrush | 0.246 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-17 06:18:20,372 - mmdet - INFO - The previous best checkpoint /mnt/petrelfs/lizhiqi/DINO/detection/work_dirs/mask_rcnn_flash_internimage_b_fpn_3x_cocoo_0.4_0.9_4x16/best_bbox_mAP_epoch_22.pth was removed 2023-11-17 06:18:23,963 - mmdet - INFO - Now best checkpoint is saved as best_bbox_mAP_epoch_28.pth. 2023-11-17 06:18:23,963 - mmdet - INFO - Best bbox_mAP is 0.5051 at 28 epoch. 2023-11-17 06:18:23,963 - mmdet - INFO - Exp name: mask_rcnn_flash_internimage_b_fpn_3x_coco_0.4_0.9-4x16.py 2023-11-17 06:18:23,963 - mmdet - INFO - Epoch(val) [28][313] bbox_mAP: 0.5051, bbox_mAP_50: 0.7255, bbox_mAP_75: 0.5550, bbox_mAP_s: 0.3585, bbox_mAP_m: 0.5458, bbox_mAP_l: 0.6509, bbox_mAP_copypaste: 0.5051 0.7255 0.5550 0.3585 0.5458 0.6509, segm_mAP: 0.4517, segm_mAP_50: 0.6972, segm_mAP_75: 0.4887, segm_mAP_s: 0.2666, segm_mAP_m: 0.4886, segm_mAP_l: 0.6368, segm_mAP_copypaste: 0.4517 0.6972 0.4887 0.2666 0.4886 0.6368 2023-11-17 06:19:11,197 - mmdet - INFO - Epoch [29][50/1833] lr: 5.563e-07, eta: 3:31:44, time: 0.944, data_time: 0.094, memory: 10998, loss_rpn_cls: 0.0194, loss_rpn_bbox: 0.0321, loss_cls: 0.1433, acc: 94.5343, loss_bbox: 0.1998, loss_mask: 0.2074, loss: 0.6018 2023-11-17 06:19:55,829 - mmdet - INFO - Epoch [29][100/1833] lr: 5.563e-07, eta: 3:31:01, time: 0.893, data_time: 0.037, memory: 10998, loss_rpn_cls: 0.0204, loss_rpn_bbox: 0.0324, loss_cls: 0.1475, acc: 94.4141, loss_bbox: 0.2022, loss_mask: 0.2100, loss: 0.6125 2023-11-17 06:20:39,876 - mmdet - INFO - Epoch [29][150/1833] lr: 5.563e-07, eta: 3:30:18, time: 0.881, data_time: 0.037, memory: 10998, loss_rpn_cls: 0.0192, loss_rpn_bbox: 0.0310, loss_cls: 0.1402, acc: 94.6885, loss_bbox: 0.1978, loss_mask: 0.2054, loss: 0.5934 2023-11-17 06:21:24,470 - mmdet - INFO - Epoch [29][200/1833] lr: 5.563e-07, eta: 3:29:35, time: 0.892, data_time: 0.037, memory: 10998, loss_rpn_cls: 0.0198, loss_rpn_bbox: 0.0315, loss_cls: 0.1397, acc: 94.6879, loss_bbox: 0.1925, loss_mask: 0.2059, loss: 0.5895 2023-11-17 06:22:08,467 - mmdet - INFO - Epoch [29][250/1833] lr: 5.563e-07, eta: 3:28:51, time: 0.880, data_time: 0.038, memory: 10998, loss_rpn_cls: 0.0194, loss_rpn_bbox: 0.0309, loss_cls: 0.1421, acc: 94.5977, loss_bbox: 0.1966, loss_mask: 0.2066, loss: 0.5956 2023-11-17 06:22:52,347 - mmdet - INFO - Epoch [29][300/1833] lr: 5.563e-07, eta: 3:28:08, time: 0.878, data_time: 0.032, memory: 10998, loss_rpn_cls: 0.0191, loss_rpn_bbox: 0.0307, loss_cls: 0.1367, acc: 94.7695, loss_bbox: 0.1901, loss_mask: 0.2035, loss: 0.5801 2023-11-17 06:23:36,397 - mmdet - INFO - Epoch [29][350/1833] lr: 5.563e-07, eta: 3:27:25, time: 0.881, data_time: 0.034, memory: 10998, loss_rpn_cls: 0.0193, loss_rpn_bbox: 0.0297, loss_cls: 0.1394, acc: 94.7086, loss_bbox: 0.1932, loss_mask: 0.2047, loss: 0.5865 2023-11-17 06:24:20,845 - mmdet - INFO - Epoch [29][400/1833] lr: 5.563e-07, eta: 3:26:41, time: 0.889, data_time: 0.040, memory: 10998, loss_rpn_cls: 0.0193, loss_rpn_bbox: 0.0311, loss_cls: 0.1410, acc: 94.6605, loss_bbox: 0.1940, loss_mask: 0.2035, loss: 0.5889 2023-11-17 06:25:05,502 - mmdet - INFO - Epoch [29][450/1833] lr: 5.563e-07, eta: 3:25:58, time: 0.893, data_time: 0.039, memory: 10998, loss_rpn_cls: 0.0202, loss_rpn_bbox: 0.0318, loss_cls: 0.1411, acc: 94.6368, loss_bbox: 0.1958, loss_mask: 0.2055, loss: 0.5943 2023-11-17 06:25:49,495 - mmdet - INFO - Epoch [29][500/1833] lr: 5.563e-07, eta: 3:25:15, time: 0.880, data_time: 0.034, memory: 10998, loss_rpn_cls: 0.0192, loss_rpn_bbox: 0.0312, loss_cls: 0.1404, acc: 94.6442, loss_bbox: 0.1946, loss_mask: 0.2060, loss: 0.5914 2023-11-17 06:26:33,894 - mmdet - INFO - Epoch [29][550/1833] lr: 5.563e-07, eta: 3:24:32, time: 0.888, data_time: 0.034, memory: 10998, loss_rpn_cls: 0.0187, loss_rpn_bbox: 0.0303, loss_cls: 0.1390, acc: 94.6949, loss_bbox: 0.1930, loss_mask: 0.2036, loss: 0.5846 2023-11-17 06:27:17,853 - mmdet - INFO - Epoch [29][600/1833] lr: 5.563e-07, eta: 3:23:48, time: 0.879, data_time: 0.033, memory: 10998, loss_rpn_cls: 0.0202, loss_rpn_bbox: 0.0318, loss_cls: 0.1412, acc: 94.6345, loss_bbox: 0.1952, loss_mask: 0.2049, loss: 0.5933 2023-11-17 06:28:01,797 - mmdet - INFO - Epoch [29][650/1833] lr: 5.563e-07, eta: 3:23:05, time: 0.879, data_time: 0.037, memory: 10998, loss_rpn_cls: 0.0201, loss_rpn_bbox: 0.0313, loss_cls: 0.1411, acc: 94.6091, loss_bbox: 0.1986, loss_mask: 0.2056, loss: 0.5967 2023-11-17 06:28:49,348 - mmdet - INFO - Epoch [29][700/1833] lr: 5.563e-07, eta: 3:22:23, time: 0.950, data_time: 0.033, memory: 10998, loss_rpn_cls: 0.0188, loss_rpn_bbox: 0.0310, loss_cls: 0.1415, acc: 94.6193, loss_bbox: 0.1964, loss_mask: 0.2064, loss: 0.5941 2023-11-17 06:29:33,441 - mmdet - INFO - Epoch [29][750/1833] lr: 5.563e-07, eta: 3:21:39, time: 0.882, data_time: 0.035, memory: 10998, loss_rpn_cls: 0.0199, loss_rpn_bbox: 0.0315, loss_cls: 0.1423, acc: 94.5869, loss_bbox: 0.1952, loss_mask: 0.2059, loss: 0.5949 2023-11-17 06:30:17,291 - mmdet - INFO - Epoch [29][800/1833] lr: 5.563e-07, eta: 3:20:56, time: 0.877, data_time: 0.034, memory: 10998, loss_rpn_cls: 0.0189, loss_rpn_bbox: 0.0301, loss_cls: 0.1411, acc: 94.6387, loss_bbox: 0.1947, loss_mask: 0.2034, loss: 0.5882 2023-11-17 06:31:01,235 - mmdet - INFO - Epoch [29][850/1833] lr: 5.563e-07, eta: 3:20:13, time: 0.879, data_time: 0.036, memory: 10998, loss_rpn_cls: 0.0195, loss_rpn_bbox: 0.0315, loss_cls: 0.1410, acc: 94.6141, loss_bbox: 0.1955, loss_mask: 0.2050, loss: 0.5925 2023-11-17 06:31:45,055 - mmdet - INFO - Epoch [29][900/1833] lr: 5.563e-07, eta: 3:19:29, time: 0.876, data_time: 0.034, memory: 10998, loss_rpn_cls: 0.0197, loss_rpn_bbox: 0.0320, loss_cls: 0.1413, acc: 94.6525, loss_bbox: 0.1951, loss_mask: 0.2081, loss: 0.5962 2023-11-17 06:32:31,246 - mmdet - INFO - Epoch [29][950/1833] lr: 5.563e-07, eta: 3:18:46, time: 0.924, data_time: 0.034, memory: 10998, loss_rpn_cls: 0.0189, loss_rpn_bbox: 0.0308, loss_cls: 0.1420, acc: 94.6290, loss_bbox: 0.1972, loss_mask: 0.2067, loss: 0.5957 2023-11-17 06:33:15,355 - mmdet - INFO - Epoch [29][1000/1833] lr: 5.563e-07, eta: 3:18:03, time: 0.882, data_time: 0.035, memory: 10998, loss_rpn_cls: 0.0185, loss_rpn_bbox: 0.0309, loss_cls: 0.1426, acc: 94.5809, loss_bbox: 0.1982, loss_mask: 0.2049, loss: 0.5951 2023-11-17 06:33:59,953 - mmdet - INFO - Epoch [29][1050/1833] lr: 5.563e-07, eta: 3:17:20, time: 0.892, data_time: 0.034, memory: 10998, loss_rpn_cls: 0.0192, loss_rpn_bbox: 0.0299, loss_cls: 0.1398, acc: 94.6992, loss_bbox: 0.1940, loss_mask: 0.2036, loss: 0.5865 2023-11-17 06:34:43,950 - mmdet - INFO - Epoch [29][1100/1833] lr: 5.563e-07, eta: 3:16:37, time: 0.880, data_time: 0.035, memory: 10998, loss_rpn_cls: 0.0201, loss_rpn_bbox: 0.0304, loss_cls: 0.1422, acc: 94.6095, loss_bbox: 0.1950, loss_mask: 0.2036, loss: 0.5913 2023-11-17 06:35:28,729 - mmdet - INFO - Epoch [29][1150/1833] lr: 5.563e-07, eta: 3:15:53, time: 0.896, data_time: 0.032, memory: 10998, loss_rpn_cls: 0.0179, loss_rpn_bbox: 0.0297, loss_cls: 0.1362, acc: 94.8119, loss_bbox: 0.1914, loss_mask: 0.2063, loss: 0.5815 2023-11-17 06:36:12,723 - mmdet - INFO - Epoch [29][1200/1833] lr: 5.563e-07, eta: 3:15:10, time: 0.880, data_time: 0.040, memory: 10998, loss_rpn_cls: 0.0189, loss_rpn_bbox: 0.0308, loss_cls: 0.1427, acc: 94.5707, loss_bbox: 0.1953, loss_mask: 0.2032, loss: 0.5909 2023-11-17 06:36:57,035 - mmdet - INFO - Epoch [29][1250/1833] lr: 5.563e-07, eta: 3:14:27, time: 0.887, data_time: 0.037, memory: 10998, loss_rpn_cls: 0.0206, loss_rpn_bbox: 0.0321, loss_cls: 0.1425, acc: 94.5608, loss_bbox: 0.1973, loss_mask: 0.2062, loss: 0.5986 2023-11-17 06:37:41,166 - mmdet - INFO - Epoch [29][1300/1833] lr: 5.563e-07, eta: 3:13:43, time: 0.883, data_time: 0.032, memory: 10998, loss_rpn_cls: 0.0194, loss_rpn_bbox: 0.0317, loss_cls: 0.1384, acc: 94.6979, loss_bbox: 0.1920, loss_mask: 0.2031, loss: 0.5846 2023-11-17 06:38:25,038 - mmdet - INFO - Epoch [29][1350/1833] lr: 5.563e-07, eta: 3:13:00, time: 0.877, data_time: 0.034, memory: 10998, loss_rpn_cls: 0.0193, loss_rpn_bbox: 0.0308, loss_cls: 0.1414, acc: 94.6064, loss_bbox: 0.1971, loss_mask: 0.2053, loss: 0.5938 2023-11-17 06:39:09,274 - mmdet - INFO - Epoch [29][1400/1833] lr: 5.563e-07, eta: 3:12:17, time: 0.885, data_time: 0.044, memory: 10998, loss_rpn_cls: 0.0204, loss_rpn_bbox: 0.0318, loss_cls: 0.1449, acc: 94.4961, loss_bbox: 0.1980, loss_mask: 0.2052, loss: 0.6003 2023-11-17 06:39:54,012 - mmdet - INFO - Epoch [29][1450/1833] lr: 5.563e-07, eta: 3:11:34, time: 0.895, data_time: 0.032, memory: 10998, loss_rpn_cls: 0.0200, loss_rpn_bbox: 0.0318, loss_cls: 0.1447, acc: 94.5409, loss_bbox: 0.1990, loss_mask: 0.2061, loss: 0.6016 2023-11-17 06:40:38,161 - mmdet - INFO - Epoch [29][1500/1833] lr: 5.563e-07, eta: 3:10:50, time: 0.883, data_time: 0.038, memory: 10998, loss_rpn_cls: 0.0192, loss_rpn_bbox: 0.0310, loss_cls: 0.1392, acc: 94.7219, loss_bbox: 0.1913, loss_mask: 0.2027, loss: 0.5834 2023-11-17 06:41:22,651 - mmdet - INFO - Epoch [29][1550/1833] lr: 5.563e-07, eta: 3:10:07, time: 0.890, data_time: 0.035, memory: 10998, loss_rpn_cls: 0.0197, loss_rpn_bbox: 0.0307, loss_cls: 0.1388, acc: 94.6608, loss_bbox: 0.1948, loss_mask: 0.2054, loss: 0.5894 2023-11-17 06:42:06,882 - mmdet - INFO - Epoch [29][1600/1833] lr: 5.563e-07, eta: 3:09:24, time: 0.885, data_time: 0.035, memory: 10998, loss_rpn_cls: 0.0201, loss_rpn_bbox: 0.0318, loss_cls: 0.1425, acc: 94.5740, loss_bbox: 0.1985, loss_mask: 0.2058, loss: 0.5987 2023-11-17 06:42:50,756 - mmdet - INFO - Epoch [29][1650/1833] lr: 5.563e-07, eta: 3:08:40, time: 0.878, data_time: 0.037, memory: 10998, loss_rpn_cls: 0.0186, loss_rpn_bbox: 0.0304, loss_cls: 0.1370, acc: 94.7700, loss_bbox: 0.1938, loss_mask: 0.2042, loss: 0.5840 2023-11-17 06:43:34,906 - mmdet - INFO - Epoch [29][1700/1833] lr: 5.563e-07, eta: 3:07:57, time: 0.882, data_time: 0.036, memory: 10998, loss_rpn_cls: 0.0184, loss_rpn_bbox: 0.0301, loss_cls: 0.1389, acc: 94.6871, loss_bbox: 0.1935, loss_mask: 0.2016, loss: 0.5825 2023-11-17 06:44:19,229 - mmdet - INFO - Epoch [29][1750/1833] lr: 5.563e-07, eta: 3:07:14, time: 0.887, data_time: 0.035, memory: 10998, loss_rpn_cls: 0.0196, loss_rpn_bbox: 0.0312, loss_cls: 0.1399, acc: 94.7120, loss_bbox: 0.1943, loss_mask: 0.2042, loss: 0.5892 2023-11-17 06:45:03,205 - mmdet - INFO - Epoch [29][1800/1833] lr: 5.563e-07, eta: 3:06:30, time: 0.880, data_time: 0.030, memory: 10998, loss_rpn_cls: 0.0188, loss_rpn_bbox: 0.0303, loss_cls: 0.1378, acc: 94.7932, loss_bbox: 0.1924, loss_mask: 0.2025, loss: 0.5818 2023-11-17 06:45:32,910 - mmdet - INFO - Saving checkpoint at 29 epochs 2023-11-17 06:46:06,975 - mmdet - INFO - Evaluating bbox... 2023-11-17 06:46:35,283 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.505 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.724 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.554 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.360 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.547 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.651 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.621 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.621 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.621 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.477 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.661 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.764 2023-11-17 06:46:35,286 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.595 | bicycle | 0.412 | car | 0.508 | | motorcycle | 0.513 | airplane | 0.699 | bus | 0.705 | | train | 0.732 | truck | 0.469 | boat | 0.353 | | traffic light | 0.323 | fire hydrant | 0.749 | stop sign | 0.688 | | parking meter | 0.526 | bench | 0.323 | bird | 0.434 | | cat | 0.749 | dog | 0.700 | horse | 0.644 | | sheep | 0.609 | cow | 0.651 | elephant | 0.713 | | bear | 0.810 | zebra | 0.695 | giraffe | 0.720 | | backpack | 0.240 | umbrella | 0.481 | handbag | 0.265 | | tie | 0.426 | suitcase | 0.508 | frisbee | 0.725 | | skis | 0.337 | snowboard | 0.472 | sports ball | 0.484 | | kite | 0.481 | baseball bat | 0.442 | baseball glove | 0.470 | | skateboard | 0.607 | surfboard | 0.508 | tennis racket | 0.582 | | bottle | 0.489 | wine glass | 0.444 | cup | 0.525 | | fork | 0.492 | knife | 0.345 | spoon | 0.318 | | bowl | 0.497 | banana | 0.292 | apple | 0.279 | | sandwich | 0.496 | orange | 0.363 | broccoli | 0.291 | | carrot | 0.267 | hot dog | 0.481 | pizza | 0.567 | | donut | 0.579 | cake | 0.470 | chair | 0.385 | | couch | 0.510 | potted plant | 0.356 | bed | 0.499 | | dining table | 0.329 | toilet | 0.677 | tv | 0.649 | | laptop | 0.709 | mouse | 0.671 | remote | 0.473 | | keyboard | 0.586 | cell phone | 0.477 | microwave | 0.683 | | oven | 0.423 | toaster | 0.465 | sink | 0.455 | | refrigerator | 0.697 | book | 0.219 | clock | 0.539 | | vase | 0.429 | scissors | 0.474 | teddy bear | 0.583 | | hair drier | 0.203 | toothbrush | 0.366 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-17 06:46:35,286 - mmdet - INFO - Evaluating segm... 2023-11-17 06:47:08,443 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.453 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.699 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.490 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.270 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.491 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.636 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.564 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.564 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.564 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.406 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.608 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.716 2023-11-17 06:47:08,446 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.519 | bicycle | 0.257 | car | 0.465 | | motorcycle | 0.417 | airplane | 0.560 | bus | 0.686 | | train | 0.711 | truck | 0.452 | boat | 0.330 | | traffic light | 0.311 | fire hydrant | 0.707 | stop sign | 0.659 | | parking meter | 0.529 | bench | 0.245 | bird | 0.355 | | cat | 0.744 | dog | 0.656 | horse | 0.484 | | sheep | 0.546 | cow | 0.555 | elephant | 0.651 | | bear | 0.776 | zebra | 0.602 | giraffe | 0.568 | | backpack | 0.239 | umbrella | 0.527 | handbag | 0.249 | | tie | 0.391 | suitcase | 0.523 | frisbee | 0.677 | | skis | 0.077 | snowboard | 0.305 | sports ball | 0.470 | | kite | 0.337 | baseball bat | 0.334 | baseball glove | 0.477 | | skateboard | 0.412 | surfboard | 0.420 | tennis racket | 0.601 | | bottle | 0.463 | wine glass | 0.399 | cup | 0.528 | | fork | 0.264 | knife | 0.235 | spoon | 0.222 | | bowl | 0.456 | banana | 0.251 | apple | 0.277 | | sandwich | 0.523 | orange | 0.357 | broccoli | 0.266 | | carrot | 0.234 | hot dog | 0.394 | pizza | 0.547 | | donut | 0.580 | cake | 0.486 | chair | 0.281 | | couch | 0.427 | potted plant | 0.307 | bed | 0.406 | | dining table | 0.201 | toilet | 0.655 | tv | 0.677 | | laptop | 0.697 | mouse | 0.638 | remote | 0.421 | | keyboard | 0.567 | cell phone | 0.455 | microwave | 0.704 | | oven | 0.382 | toaster | 0.515 | sink | 0.421 | | refrigerator | 0.701 | book | 0.161 | clock | 0.539 | | vase | 0.415 | scissors | 0.333 | teddy bear | 0.546 | | hair drier | 0.208 | toothbrush | 0.260 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-17 06:47:08,812 - mmdet - INFO - Exp name: mask_rcnn_flash_internimage_b_fpn_3x_coco_0.4_0.9-4x16.py 2023-11-17 06:47:08,812 - mmdet - INFO - Epoch(val) [29][313] bbox_mAP: 0.5050, bbox_mAP_50: 0.7243, bbox_mAP_75: 0.5542, bbox_mAP_s: 0.3600, bbox_mAP_m: 0.5473, bbox_mAP_l: 0.6514, bbox_mAP_copypaste: 0.5050 0.7243 0.5542 0.3600 0.5473 0.6514, segm_mAP: 0.4528, segm_mAP_50: 0.6988, segm_mAP_75: 0.4903, segm_mAP_s: 0.2698, segm_mAP_m: 0.4911, segm_mAP_l: 0.6361, segm_mAP_copypaste: 0.4528 0.6988 0.4903 0.2698 0.4911 0.6361 2023-11-17 06:47:55,938 - mmdet - INFO - Epoch [30][50/1833] lr: 5.563e-07, eta: 3:05:12, time: 0.942, data_time: 0.091, memory: 10998, loss_rpn_cls: 0.0198, loss_rpn_bbox: 0.0321, loss_cls: 0.1411, acc: 94.6259, loss_bbox: 0.1985, loss_mask: 0.2070, loss: 0.5986 2023-11-17 06:48:39,815 - mmdet - INFO - Epoch [30][100/1833] lr: 5.563e-07, eta: 3:04:29, time: 0.878, data_time: 0.034, memory: 10998, loss_rpn_cls: 0.0198, loss_rpn_bbox: 0.0312, loss_cls: 0.1423, acc: 94.5892, loss_bbox: 0.1985, loss_mask: 0.2082, loss: 0.6001 2023-11-17 06:49:24,250 - mmdet - INFO - Epoch [30][150/1833] lr: 5.563e-07, eta: 3:03:45, time: 0.889, data_time: 0.034, memory: 10998, loss_rpn_cls: 0.0186, loss_rpn_bbox: 0.0310, loss_cls: 0.1389, acc: 94.6980, loss_bbox: 0.1960, loss_mask: 0.2051, loss: 0.5895 2023-11-17 06:50:07,980 - mmdet - INFO - Epoch [30][200/1833] lr: 5.563e-07, eta: 3:03:02, time: 0.875, data_time: 0.040, memory: 10998, loss_rpn_cls: 0.0197, loss_rpn_bbox: 0.0311, loss_cls: 0.1397, acc: 94.6917, loss_bbox: 0.1955, loss_mask: 0.2063, loss: 0.5924 2023-11-17 06:50:52,195 - mmdet - INFO - Epoch [30][250/1833] lr: 5.563e-07, eta: 3:02:19, time: 0.884, data_time: 0.033, memory: 10998, loss_rpn_cls: 0.0185, loss_rpn_bbox: 0.0307, loss_cls: 0.1386, acc: 94.7019, loss_bbox: 0.1932, loss_mask: 0.2058, loss: 0.5868 2023-11-17 06:51:36,197 - mmdet - INFO - Epoch [30][300/1833] lr: 5.563e-07, eta: 3:01:35, time: 0.880, data_time: 0.035, memory: 10998, loss_rpn_cls: 0.0190, loss_rpn_bbox: 0.0313, loss_cls: 0.1385, acc: 94.7141, loss_bbox: 0.1940, loss_mask: 0.2034, loss: 0.5862 2023-11-17 06:52:19,874 - mmdet - INFO - Epoch [30][350/1833] lr: 5.563e-07, eta: 3:00:52, time: 0.874, data_time: 0.034, memory: 10998, loss_rpn_cls: 0.0202, loss_rpn_bbox: 0.0314, loss_cls: 0.1406, acc: 94.6676, loss_bbox: 0.1934, loss_mask: 0.2043, loss: 0.5899 2023-11-17 06:53:03,968 - mmdet - INFO - Epoch [30][400/1833] lr: 5.563e-07, eta: 3:00:09, time: 0.882, data_time: 0.035, memory: 10998, loss_rpn_cls: 0.0186, loss_rpn_bbox: 0.0306, loss_cls: 0.1367, acc: 94.7837, loss_bbox: 0.1908, loss_mask: 0.2020, loss: 0.5787 2023-11-17 06:53:47,927 - mmdet - INFO - Epoch [30][450/1833] lr: 5.563e-07, eta: 2:59:25, time: 0.879, data_time: 0.036, memory: 10998, loss_rpn_cls: 0.0178, loss_rpn_bbox: 0.0301, loss_cls: 0.1363, acc: 94.8122, loss_bbox: 0.1922, loss_mask: 0.2040, loss: 0.5806 2023-11-17 06:54:31,893 - mmdet - INFO - Epoch [30][500/1833] lr: 5.563e-07, eta: 2:58:42, time: 0.879, data_time: 0.033, memory: 10998, loss_rpn_cls: 0.0187, loss_rpn_bbox: 0.0305, loss_cls: 0.1376, acc: 94.7820, loss_bbox: 0.1902, loss_mask: 0.2033, loss: 0.5803 2023-11-17 06:55:16,078 - mmdet - INFO - Epoch [30][550/1833] lr: 5.563e-07, eta: 2:57:59, time: 0.884, data_time: 0.036, memory: 10998, loss_rpn_cls: 0.0202, loss_rpn_bbox: 0.0308, loss_cls: 0.1405, acc: 94.6592, loss_bbox: 0.1943, loss_mask: 0.2039, loss: 0.5897 2023-11-17 06:56:00,226 - mmdet - INFO - Epoch [30][600/1833] lr: 5.563e-07, eta: 2:57:15, time: 0.883, data_time: 0.035, memory: 10998, loss_rpn_cls: 0.0191, loss_rpn_bbox: 0.0301, loss_cls: 0.1366, acc: 94.8217, loss_bbox: 0.1914, loss_mask: 0.2040, loss: 0.5811 2023-11-17 06:56:44,865 - mmdet - INFO - Epoch [30][650/1833] lr: 5.563e-07, eta: 2:56:32, time: 0.893, data_time: 0.035, memory: 10998, loss_rpn_cls: 0.0204, loss_rpn_bbox: 0.0327, loss_cls: 0.1444, acc: 94.4899, loss_bbox: 0.1996, loss_mask: 0.2057, loss: 0.6028 2023-11-17 06:57:28,787 - mmdet - INFO - Epoch [30][700/1833] lr: 5.563e-07, eta: 2:55:49, time: 0.878, data_time: 0.035, memory: 10998, loss_rpn_cls: 0.0203, loss_rpn_bbox: 0.0325, loss_cls: 0.1417, acc: 94.6243, loss_bbox: 0.1968, loss_mask: 0.2049, loss: 0.5961 2023-11-17 06:58:13,021 - mmdet - INFO - Epoch [30][750/1833] lr: 5.563e-07, eta: 2:55:05, time: 0.885, data_time: 0.033, memory: 10998, loss_rpn_cls: 0.0195, loss_rpn_bbox: 0.0305, loss_cls: 0.1403, acc: 94.6779, loss_bbox: 0.1943, loss_mask: 0.2037, loss: 0.5883 2023-11-17 06:58:57,634 - mmdet - INFO - Epoch [30][800/1833] lr: 5.563e-07, eta: 2:54:22, time: 0.892, data_time: 0.032, memory: 10998, loss_rpn_cls: 0.0188, loss_rpn_bbox: 0.0311, loss_cls: 0.1399, acc: 94.6611, loss_bbox: 0.1951, loss_mask: 0.2037, loss: 0.5886 2023-11-17 06:59:41,894 - mmdet - INFO - Epoch [30][850/1833] lr: 5.563e-07, eta: 2:53:39, time: 0.885, data_time: 0.033, memory: 10998, loss_rpn_cls: 0.0195, loss_rpn_bbox: 0.0307, loss_cls: 0.1385, acc: 94.6815, loss_bbox: 0.1930, loss_mask: 0.2041, loss: 0.5857 2023-11-17 07:00:25,985 - mmdet - INFO - Epoch [30][900/1833] lr: 5.563e-07, eta: 2:52:55, time: 0.881, data_time: 0.037, memory: 10998, loss_rpn_cls: 0.0181, loss_rpn_bbox: 0.0304, loss_cls: 0.1378, acc: 94.7437, loss_bbox: 0.1958, loss_mask: 0.2048, loss: 0.5869 2023-11-17 07:01:10,387 - mmdet - INFO - Epoch [30][950/1833] lr: 5.563e-07, eta: 2:52:12, time: 0.888, data_time: 0.038, memory: 10998, loss_rpn_cls: 0.0185, loss_rpn_bbox: 0.0296, loss_cls: 0.1369, acc: 94.8471, loss_bbox: 0.1888, loss_mask: 0.2006, loss: 0.5744 2023-11-17 07:01:54,095 - mmdet - INFO - Epoch [30][1000/1833] lr: 5.563e-07, eta: 2:51:29, time: 0.874, data_time: 0.035, memory: 10998, loss_rpn_cls: 0.0198, loss_rpn_bbox: 0.0308, loss_cls: 0.1397, acc: 94.6400, loss_bbox: 0.1927, loss_mask: 0.2064, loss: 0.5895 2023-11-17 07:02:38,023 - mmdet - INFO - Epoch [30][1050/1833] lr: 5.563e-07, eta: 2:50:45, time: 0.878, data_time: 0.034, memory: 10998, loss_rpn_cls: 0.0185, loss_rpn_bbox: 0.0302, loss_cls: 0.1384, acc: 94.7045, loss_bbox: 0.1966, loss_mask: 0.2071, loss: 0.5908 2023-11-17 07:03:22,073 - mmdet - INFO - Epoch [30][1100/1833] lr: 5.563e-07, eta: 2:50:02, time: 0.881, data_time: 0.036, memory: 10998, loss_rpn_cls: 0.0183, loss_rpn_bbox: 0.0302, loss_cls: 0.1364, acc: 94.8051, loss_bbox: 0.1907, loss_mask: 0.2040, loss: 0.5796 2023-11-17 07:04:06,179 - mmdet - INFO - Epoch [30][1150/1833] lr: 5.563e-07, eta: 2:49:19, time: 0.882, data_time: 0.034, memory: 10998, loss_rpn_cls: 0.0188, loss_rpn_bbox: 0.0300, loss_cls: 0.1374, acc: 94.7857, loss_bbox: 0.1909, loss_mask: 0.2033, loss: 0.5804 2023-11-17 07:04:50,434 - mmdet - INFO - Epoch [30][1200/1833] lr: 5.563e-07, eta: 2:48:35, time: 0.886, data_time: 0.035, memory: 10998, loss_rpn_cls: 0.0201, loss_rpn_bbox: 0.0321, loss_cls: 0.1437, acc: 94.4957, loss_bbox: 0.1989, loss_mask: 0.2058, loss: 0.6006 2023-11-17 07:05:37,000 - mmdet - INFO - Epoch [30][1250/1833] lr: 5.563e-07, eta: 2:47:52, time: 0.931, data_time: 0.033, memory: 10998, loss_rpn_cls: 0.0184, loss_rpn_bbox: 0.0303, loss_cls: 0.1383, acc: 94.7205, loss_bbox: 0.1928, loss_mask: 0.2021, loss: 0.5819 2023-11-17 07:06:20,804 - mmdet - INFO - Epoch [30][1300/1833] lr: 5.563e-07, eta: 2:47:09, time: 0.876, data_time: 0.033, memory: 10998, loss_rpn_cls: 0.0190, loss_rpn_bbox: 0.0312, loss_cls: 0.1432, acc: 94.5426, loss_bbox: 0.1983, loss_mask: 0.2074, loss: 0.5990 2023-11-17 07:07:04,740 - mmdet - INFO - Epoch [30][1350/1833] lr: 5.563e-07, eta: 2:46:26, time: 0.879, data_time: 0.031, memory: 10998, loss_rpn_cls: 0.0194, loss_rpn_bbox: 0.0320, loss_cls: 0.1400, acc: 94.6717, loss_bbox: 0.1972, loss_mask: 0.2073, loss: 0.5958 2023-11-17 07:07:50,845 - mmdet - INFO - Epoch [30][1400/1833] lr: 5.563e-07, eta: 2:45:43, time: 0.922, data_time: 0.032, memory: 10998, loss_rpn_cls: 0.0189, loss_rpn_bbox: 0.0297, loss_cls: 0.1374, acc: 94.7894, loss_bbox: 0.1928, loss_mask: 0.2029, loss: 0.5818 2023-11-17 07:08:35,265 - mmdet - INFO - Epoch [30][1450/1833] lr: 5.563e-07, eta: 2:44:59, time: 0.888, data_time: 0.032, memory: 10998, loss_rpn_cls: 0.0189, loss_rpn_bbox: 0.0307, loss_cls: 0.1403, acc: 94.6788, loss_bbox: 0.1941, loss_mask: 0.2039, loss: 0.5879 2023-11-17 07:09:19,561 - mmdet - INFO - Epoch [30][1500/1833] lr: 5.563e-07, eta: 2:44:16, time: 0.886, data_time: 0.037, memory: 10998, loss_rpn_cls: 0.0205, loss_rpn_bbox: 0.0315, loss_cls: 0.1426, acc: 94.5308, loss_bbox: 0.1983, loss_mask: 0.2054, loss: 0.5983 2023-11-17 07:10:03,800 - mmdet - INFO - Epoch [30][1550/1833] lr: 5.563e-07, eta: 2:43:33, time: 0.885, data_time: 0.031, memory: 10998, loss_rpn_cls: 0.0197, loss_rpn_bbox: 0.0322, loss_cls: 0.1418, acc: 94.5923, loss_bbox: 0.1958, loss_mask: 0.2061, loss: 0.5956 2023-11-17 07:10:47,916 - mmdet - INFO - Epoch [30][1600/1833] lr: 5.563e-07, eta: 2:42:49, time: 0.882, data_time: 0.038, memory: 10998, loss_rpn_cls: 0.0188, loss_rpn_bbox: 0.0297, loss_cls: 0.1356, acc: 94.8299, loss_bbox: 0.1894, loss_mask: 0.2011, loss: 0.5745 2023-11-17 07:11:31,959 - mmdet - INFO - Epoch [30][1650/1833] lr: 5.563e-07, eta: 2:42:06, time: 0.881, data_time: 0.035, memory: 10998, loss_rpn_cls: 0.0191, loss_rpn_bbox: 0.0308, loss_cls: 0.1396, acc: 94.7014, loss_bbox: 0.1932, loss_mask: 0.2037, loss: 0.5863 2023-11-17 07:12:16,202 - mmdet - INFO - Epoch [30][1700/1833] lr: 5.563e-07, eta: 2:41:23, time: 0.885, data_time: 0.035, memory: 10998, loss_rpn_cls: 0.0191, loss_rpn_bbox: 0.0310, loss_cls: 0.1411, acc: 94.5807, loss_bbox: 0.1961, loss_mask: 0.2044, loss: 0.5918 2023-11-17 07:13:00,316 - mmdet - INFO - Epoch [30][1750/1833] lr: 5.563e-07, eta: 2:40:39, time: 0.882, data_time: 0.031, memory: 10998, loss_rpn_cls: 0.0190, loss_rpn_bbox: 0.0310, loss_cls: 0.1388, acc: 94.7232, loss_bbox: 0.1929, loss_mask: 0.2049, loss: 0.5865 2023-11-17 07:13:44,697 - mmdet - INFO - Epoch [30][1800/1833] lr: 5.563e-07, eta: 2:39:56, time: 0.888, data_time: 0.034, memory: 10998, loss_rpn_cls: 0.0201, loss_rpn_bbox: 0.0323, loss_cls: 0.1442, acc: 94.4855, loss_bbox: 0.2015, loss_mask: 0.2080, loss: 0.6060 2023-11-17 07:14:14,284 - mmdet - INFO - Saving checkpoint at 30 epochs 2023-11-17 07:14:45,146 - mmdet - INFO - Evaluating bbox... 2023-11-17 07:15:15,432 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.505 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.726 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.555 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.362 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.548 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.649 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.623 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.623 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.623 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.479 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.664 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.763 2023-11-17 07:15:15,435 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.595 | bicycle | 0.414 | car | 0.509 | | motorcycle | 0.516 | airplane | 0.700 | bus | 0.705 | | train | 0.722 | truck | 0.469 | boat | 0.357 | | traffic light | 0.324 | fire hydrant | 0.746 | stop sign | 0.703 | | parking meter | 0.524 | bench | 0.326 | bird | 0.436 | | cat | 0.760 | dog | 0.709 | horse | 0.655 | | sheep | 0.613 | cow | 0.649 | elephant | 0.700 | | bear | 0.791 | zebra | 0.692 | giraffe | 0.696 | | backpack | 0.242 | umbrella | 0.482 | handbag | 0.265 | | tie | 0.430 | suitcase | 0.507 | frisbee | 0.729 | | skis | 0.332 | snowboard | 0.470 | sports ball | 0.487 | | kite | 0.482 | baseball bat | 0.450 | baseball glove | 0.473 | | skateboard | 0.606 | surfboard | 0.516 | tennis racket | 0.581 | | bottle | 0.486 | wine glass | 0.447 | cup | 0.523 | | fork | 0.496 | knife | 0.342 | spoon | 0.316 | | bowl | 0.500 | banana | 0.298 | apple | 0.269 | | sandwich | 0.491 | orange | 0.371 | broccoli | 0.292 | | carrot | 0.268 | hot dog | 0.468 | pizza | 0.566 | | donut | 0.577 | cake | 0.473 | chair | 0.383 | | couch | 0.506 | potted plant | 0.361 | bed | 0.496 | | dining table | 0.328 | toilet | 0.689 | tv | 0.655 | | laptop | 0.708 | mouse | 0.674 | remote | 0.479 | | keyboard | 0.589 | cell phone | 0.480 | microwave | 0.695 | | oven | 0.427 | toaster | 0.455 | sink | 0.456 | | refrigerator | 0.704 | book | 0.215 | clock | 0.538 | | vase | 0.429 | scissors | 0.478 | teddy bear | 0.584 | | hair drier | 0.203 | toothbrush | 0.364 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-17 07:15:15,435 - mmdet - INFO - Evaluating segm... 2023-11-17 07:15:45,961 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.453 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.697 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.491 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.271 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.490 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.637 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.566 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.566 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.566 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.410 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.608 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.718 2023-11-17 07:15:45,963 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.521 | bicycle | 0.254 | car | 0.465 | | motorcycle | 0.418 | airplane | 0.565 | bus | 0.685 | | train | 0.707 | truck | 0.455 | boat | 0.331 | | traffic light | 0.309 | fire hydrant | 0.706 | stop sign | 0.661 | | parking meter | 0.526 | bench | 0.247 | bird | 0.358 | | cat | 0.743 | dog | 0.657 | horse | 0.486 | | sheep | 0.547 | cow | 0.554 | elephant | 0.635 | | bear | 0.774 | zebra | 0.596 | giraffe | 0.550 | | backpack | 0.237 | umbrella | 0.531 | handbag | 0.244 | | tie | 0.391 | suitcase | 0.526 | frisbee | 0.680 | | skis | 0.073 | snowboard | 0.313 | sports ball | 0.480 | | kite | 0.338 | baseball bat | 0.335 | baseball glove | 0.478 | | skateboard | 0.409 | surfboard | 0.422 | tennis racket | 0.601 | | bottle | 0.458 | wine glass | 0.402 | cup | 0.523 | | fork | 0.267 | knife | 0.228 | spoon | 0.220 | | bowl | 0.460 | banana | 0.255 | apple | 0.270 | | sandwich | 0.524 | orange | 0.363 | broccoli | 0.266 | | carrot | 0.233 | hot dog | 0.367 | pizza | 0.547 | | donut | 0.575 | cake | 0.490 | chair | 0.280 | | couch | 0.429 | potted plant | 0.306 | bed | 0.416 | | dining table | 0.203 | toilet | 0.660 | tv | 0.677 | | laptop | 0.692 | mouse | 0.640 | remote | 0.425 | | keyboard | 0.578 | cell phone | 0.458 | microwave | 0.705 | | oven | 0.388 | toaster | 0.480 | sink | 0.425 | | refrigerator | 0.712 | book | 0.158 | clock | 0.543 | | vase | 0.421 | scissors | 0.342 | teddy bear | 0.550 | | hair drier | 0.222 | toothbrush | 0.253 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-17 07:15:46,466 - mmdet - INFO - The previous best checkpoint /mnt/petrelfs/lizhiqi/DINO/detection/work_dirs/mask_rcnn_flash_internimage_b_fpn_3x_cocoo_0.4_0.9_4x16/best_bbox_mAP_epoch_28.pth was removed 2023-11-17 07:15:50,299 - mmdet - INFO - Now best checkpoint is saved as best_bbox_mAP_epoch_30.pth. 2023-11-17 07:15:50,299 - mmdet - INFO - Best bbox_mAP is 0.5054 at 30 epoch. 2023-11-17 07:15:50,299 - mmdet - INFO - Exp name: mask_rcnn_flash_internimage_b_fpn_3x_coco_0.4_0.9-4x16.py 2023-11-17 07:15:50,299 - mmdet - INFO - Epoch(val) [30][313] bbox_mAP: 0.5054, bbox_mAP_50: 0.7261, bbox_mAP_75: 0.5549, bbox_mAP_s: 0.3619, bbox_mAP_m: 0.5484, bbox_mAP_l: 0.6491, bbox_mAP_copypaste: 0.5054 0.7261 0.5549 0.3619 0.5484 0.6491, segm_mAP: 0.4527, segm_mAP_50: 0.6971, segm_mAP_75: 0.4915, segm_mAP_s: 0.2710, segm_mAP_m: 0.4900, segm_mAP_l: 0.6373, segm_mAP_copypaste: 0.4527 0.6971 0.4915 0.2710 0.4900 0.6373 2023-11-17 07:16:37,017 - mmdet - INFO - Epoch [31][50/1833] lr: 5.563e-07, eta: 2:38:39, time: 0.934, data_time: 0.092, memory: 10998, loss_rpn_cls: 0.0194, loss_rpn_bbox: 0.0311, loss_cls: 0.1414, acc: 94.6144, loss_bbox: 0.1956, loss_mask: 0.2027, loss: 0.5902 2023-11-17 07:17:21,160 - mmdet - INFO - Epoch [31][100/1833] lr: 5.563e-07, eta: 2:37:55, time: 0.883, data_time: 0.042, memory: 10998, loss_rpn_cls: 0.0202, loss_rpn_bbox: 0.0316, loss_cls: 0.1419, acc: 94.6287, loss_bbox: 0.1983, loss_mask: 0.2043, loss: 0.5964 2023-11-17 07:18:05,903 - mmdet - INFO - Epoch [31][150/1833] lr: 5.563e-07, eta: 2:37:12, time: 0.895, data_time: 0.034, memory: 10998, loss_rpn_cls: 0.0187, loss_rpn_bbox: 0.0304, loss_cls: 0.1377, acc: 94.7374, loss_bbox: 0.1925, loss_mask: 0.2041, loss: 0.5835 2023-11-17 07:18:49,695 - mmdet - INFO - Epoch [31][200/1833] lr: 5.563e-07, eta: 2:36:29, time: 0.876, data_time: 0.030, memory: 10998, loss_rpn_cls: 0.0184, loss_rpn_bbox: 0.0300, loss_cls: 0.1342, acc: 94.8836, loss_bbox: 0.1908, loss_mask: 0.2018, loss: 0.5751 2023-11-17 07:19:34,147 - mmdet - INFO - Epoch [31][250/1833] lr: 5.563e-07, eta: 2:35:45, time: 0.889, data_time: 0.033, memory: 10998, loss_rpn_cls: 0.0188, loss_rpn_bbox: 0.0303, loss_cls: 0.1368, acc: 94.7811, loss_bbox: 0.1920, loss_mask: 0.2043, loss: 0.5822 2023-11-17 07:20:18,685 - mmdet - INFO - Epoch [31][300/1833] lr: 5.563e-07, eta: 2:35:02, time: 0.891, data_time: 0.033, memory: 10998, loss_rpn_cls: 0.0197, loss_rpn_bbox: 0.0321, loss_cls: 0.1420, acc: 94.5593, loss_bbox: 0.1981, loss_mask: 0.2067, loss: 0.5986 2023-11-17 07:21:03,060 - mmdet - INFO - Epoch [31][350/1833] lr: 5.563e-07, eta: 2:34:19, time: 0.887, data_time: 0.035, memory: 10998, loss_rpn_cls: 0.0187, loss_rpn_bbox: 0.0306, loss_cls: 0.1401, acc: 94.6794, loss_bbox: 0.1946, loss_mask: 0.2065, loss: 0.5905 2023-11-17 07:21:47,389 - mmdet - INFO - Epoch [31][400/1833] lr: 5.563e-07, eta: 2:33:35, time: 0.887, data_time: 0.035, memory: 10998, loss_rpn_cls: 0.0181, loss_rpn_bbox: 0.0300, loss_cls: 0.1352, acc: 94.8209, loss_bbox: 0.1908, loss_mask: 0.2029, loss: 0.5769 2023-11-17 07:22:31,970 - mmdet - INFO - Epoch [31][450/1833] lr: 5.563e-07, eta: 2:32:52, time: 0.892, data_time: 0.035, memory: 10998, loss_rpn_cls: 0.0187, loss_rpn_bbox: 0.0304, loss_cls: 0.1360, acc: 94.8198, loss_bbox: 0.1889, loss_mask: 0.2026, loss: 0.5766 2023-11-17 07:23:16,298 - mmdet - INFO - Epoch [31][500/1833] lr: 5.563e-07, eta: 2:32:09, time: 0.887, data_time: 0.032, memory: 10998, loss_rpn_cls: 0.0197, loss_rpn_bbox: 0.0308, loss_cls: 0.1407, acc: 94.6265, loss_bbox: 0.1950, loss_mask: 0.2033, loss: 0.5896 2023-11-17 07:24:01,003 - mmdet - INFO - Epoch [31][550/1833] lr: 5.563e-07, eta: 2:31:26, time: 0.894, data_time: 0.033, memory: 10998, loss_rpn_cls: 0.0188, loss_rpn_bbox: 0.0309, loss_cls: 0.1380, acc: 94.7209, loss_bbox: 0.1930, loss_mask: 0.2024, loss: 0.5831 2023-11-17 07:24:45,480 - mmdet - INFO - Epoch [31][600/1833] lr: 5.563e-07, eta: 2:30:42, time: 0.889, data_time: 0.031, memory: 10998, loss_rpn_cls: 0.0196, loss_rpn_bbox: 0.0317, loss_cls: 0.1407, acc: 94.6620, loss_bbox: 0.1938, loss_mask: 0.2038, loss: 0.5896 2023-11-17 07:25:33,751 - mmdet - INFO - Epoch [31][650/1833] lr: 5.563e-07, eta: 2:30:00, time: 0.965, data_time: 0.034, memory: 10998, loss_rpn_cls: 0.0187, loss_rpn_bbox: 0.0304, loss_cls: 0.1388, acc: 94.6890, loss_bbox: 0.1931, loss_mask: 0.2041, loss: 0.5851 2023-11-17 07:26:22,637 - mmdet - INFO - Epoch [31][700/1833] lr: 5.563e-07, eta: 2:29:17, time: 0.978, data_time: 0.052, memory: 10998, loss_rpn_cls: 0.0186, loss_rpn_bbox: 0.0307, loss_cls: 0.1393, acc: 94.6994, loss_bbox: 0.1945, loss_mask: 0.2049, loss: 0.5881 2023-11-17 07:27:09,829 - mmdet - INFO - Epoch [31][750/1833] lr: 5.563e-07, eta: 2:28:34, time: 0.944, data_time: 0.035, memory: 10998, loss_rpn_cls: 0.0197, loss_rpn_bbox: 0.0305, loss_cls: 0.1411, acc: 94.6075, loss_bbox: 0.1959, loss_mask: 0.2070, loss: 0.5942 2023-11-17 07:27:54,107 - mmdet - INFO - Epoch [31][800/1833] lr: 5.563e-07, eta: 2:27:51, time: 0.886, data_time: 0.034, memory: 10998, loss_rpn_cls: 0.0185, loss_rpn_bbox: 0.0313, loss_cls: 0.1396, acc: 94.6593, loss_bbox: 0.1942, loss_mask: 0.2042, loss: 0.5878 2023-11-17 07:28:38,248 - mmdet - INFO - Epoch [31][850/1833] lr: 5.563e-07, eta: 2:27:08, time: 0.883, data_time: 0.030, memory: 10998, loss_rpn_cls: 0.0185, loss_rpn_bbox: 0.0299, loss_cls: 0.1355, acc: 94.8538, loss_bbox: 0.1887, loss_mask: 0.2041, loss: 0.5767 2023-11-17 07:29:22,380 - mmdet - INFO - Epoch [31][900/1833] lr: 5.563e-07, eta: 2:26:24, time: 0.883, data_time: 0.032, memory: 10998, loss_rpn_cls: 0.0193, loss_rpn_bbox: 0.0307, loss_cls: 0.1388, acc: 94.7083, loss_bbox: 0.1941, loss_mask: 0.2061, loss: 0.5890 2023-11-17 07:30:06,296 - mmdet - INFO - Epoch [31][950/1833] lr: 5.563e-07, eta: 2:25:41, time: 0.878, data_time: 0.032, memory: 10998, loss_rpn_cls: 0.0188, loss_rpn_bbox: 0.0312, loss_cls: 0.1404, acc: 94.6349, loss_bbox: 0.1975, loss_mask: 0.2058, loss: 0.5937 2023-11-17 07:30:49,976 - mmdet - INFO - Epoch [31][1000/1833] lr: 5.563e-07, eta: 2:24:57, time: 0.874, data_time: 0.031, memory: 10998, loss_rpn_cls: 0.0183, loss_rpn_bbox: 0.0300, loss_cls: 0.1357, acc: 94.8326, loss_bbox: 0.1881, loss_mask: 0.2026, loss: 0.5746 2023-11-17 07:31:34,427 - mmdet - INFO - Epoch [31][1050/1833] lr: 5.563e-07, eta: 2:24:14, time: 0.889, data_time: 0.039, memory: 10998, loss_rpn_cls: 0.0188, loss_rpn_bbox: 0.0308, loss_cls: 0.1384, acc: 94.7074, loss_bbox: 0.1924, loss_mask: 0.2022, loss: 0.5825 2023-11-17 07:32:18,594 - mmdet - INFO - Epoch [31][1100/1833] lr: 5.563e-07, eta: 2:23:31, time: 0.883, data_time: 0.032, memory: 10998, loss_rpn_cls: 0.0189, loss_rpn_bbox: 0.0308, loss_cls: 0.1395, acc: 94.6368, loss_bbox: 0.1941, loss_mask: 0.2039, loss: 0.5873 2023-11-17 07:33:03,057 - mmdet - INFO - Epoch [31][1150/1833] lr: 5.563e-07, eta: 2:22:47, time: 0.889, data_time: 0.035, memory: 10998, loss_rpn_cls: 0.0192, loss_rpn_bbox: 0.0315, loss_cls: 0.1425, acc: 94.5574, loss_bbox: 0.1973, loss_mask: 0.2073, loss: 0.5979 2023-11-17 07:33:47,374 - mmdet - INFO - Epoch [31][1200/1833] lr: 5.563e-07, eta: 2:22:04, time: 0.886, data_time: 0.034, memory: 10998, loss_rpn_cls: 0.0190, loss_rpn_bbox: 0.0307, loss_cls: 0.1395, acc: 94.6353, loss_bbox: 0.1945, loss_mask: 0.2021, loss: 0.5858 2023-11-17 07:34:31,939 - mmdet - INFO - Epoch [31][1250/1833] lr: 5.563e-07, eta: 2:21:21, time: 0.891, data_time: 0.030, memory: 10998, loss_rpn_cls: 0.0186, loss_rpn_bbox: 0.0300, loss_cls: 0.1384, acc: 94.7651, loss_bbox: 0.1907, loss_mask: 0.2017, loss: 0.5794 2023-11-17 07:35:16,144 - mmdet - INFO - Epoch [31][1300/1833] lr: 5.563e-07, eta: 2:20:37, time: 0.884, data_time: 0.042, memory: 10998, loss_rpn_cls: 0.0190, loss_rpn_bbox: 0.0306, loss_cls: 0.1395, acc: 94.6851, loss_bbox: 0.1958, loss_mask: 0.2041, loss: 0.5890 2023-11-17 07:36:00,273 - mmdet - INFO - Epoch [31][1350/1833] lr: 5.563e-07, eta: 2:19:54, time: 0.882, data_time: 0.037, memory: 10998, loss_rpn_cls: 0.0191, loss_rpn_bbox: 0.0320, loss_cls: 0.1425, acc: 94.5757, loss_bbox: 0.1986, loss_mask: 0.2064, loss: 0.5986 2023-11-17 07:36:44,356 - mmdet - INFO - Epoch [31][1400/1833] lr: 5.563e-07, eta: 2:19:11, time: 0.881, data_time: 0.034, memory: 10998, loss_rpn_cls: 0.0199, loss_rpn_bbox: 0.0323, loss_cls: 0.1441, acc: 94.4908, loss_bbox: 0.1993, loss_mask: 0.2058, loss: 0.6014 2023-11-17 07:37:28,135 - mmdet - INFO - Epoch [31][1450/1833] lr: 5.563e-07, eta: 2:18:27, time: 0.876, data_time: 0.032, memory: 10998, loss_rpn_cls: 0.0186, loss_rpn_bbox: 0.0302, loss_cls: 0.1367, acc: 94.7989, loss_bbox: 0.1909, loss_mask: 0.2017, loss: 0.5782 2023-11-17 07:38:12,309 - mmdet - INFO - Epoch [31][1500/1833] lr: 5.563e-07, eta: 2:17:44, time: 0.883, data_time: 0.030, memory: 10998, loss_rpn_cls: 0.0188, loss_rpn_bbox: 0.0302, loss_cls: 0.1350, acc: 94.8586, loss_bbox: 0.1902, loss_mask: 0.2031, loss: 0.5773 2023-11-17 07:38:56,766 - mmdet - INFO - Epoch [31][1550/1833] lr: 5.563e-07, eta: 2:17:00, time: 0.889, data_time: 0.033, memory: 10998, loss_rpn_cls: 0.0189, loss_rpn_bbox: 0.0313, loss_cls: 0.1382, acc: 94.7053, loss_bbox: 0.1956, loss_mask: 0.2041, loss: 0.5881 2023-11-17 07:39:40,894 - mmdet - INFO - Epoch [31][1600/1833] lr: 5.563e-07, eta: 2:16:17, time: 0.883, data_time: 0.034, memory: 10998, loss_rpn_cls: 0.0187, loss_rpn_bbox: 0.0304, loss_cls: 0.1384, acc: 94.7094, loss_bbox: 0.1947, loss_mask: 0.2059, loss: 0.5880 2023-11-17 07:40:25,351 - mmdet - INFO - Epoch [31][1650/1833] lr: 5.563e-07, eta: 2:15:34, time: 0.889, data_time: 0.033, memory: 10998, loss_rpn_cls: 0.0184, loss_rpn_bbox: 0.0304, loss_cls: 0.1394, acc: 94.6929, loss_bbox: 0.1937, loss_mask: 0.2024, loss: 0.5843 2023-11-17 07:41:09,623 - mmdet - INFO - Epoch [31][1700/1833] lr: 5.563e-07, eta: 2:14:50, time: 0.885, data_time: 0.030, memory: 10998, loss_rpn_cls: 0.0195, loss_rpn_bbox: 0.0316, loss_cls: 0.1417, acc: 94.6082, loss_bbox: 0.1989, loss_mask: 0.2055, loss: 0.5972 2023-11-17 07:41:53,443 - mmdet - INFO - Epoch [31][1750/1833] lr: 5.563e-07, eta: 2:14:07, time: 0.876, data_time: 0.035, memory: 10998, loss_rpn_cls: 0.0185, loss_rpn_bbox: 0.0300, loss_cls: 0.1367, acc: 94.7497, loss_bbox: 0.1923, loss_mask: 0.2035, loss: 0.5810 2023-11-17 07:42:37,913 - mmdet - INFO - Epoch [31][1800/1833] lr: 5.563e-07, eta: 2:13:23, time: 0.889, data_time: 0.035, memory: 10998, loss_rpn_cls: 0.0199, loss_rpn_bbox: 0.0321, loss_cls: 0.1427, acc: 94.5154, loss_bbox: 0.1999, loss_mask: 0.2049, loss: 0.5996 2023-11-17 07:43:07,499 - mmdet - INFO - Saving checkpoint at 31 epochs 2023-11-17 07:43:40,304 - mmdet - INFO - Evaluating bbox... 2023-11-17 07:44:07,682 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.505 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.724 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.554 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.362 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.546 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.648 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.621 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.621 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.621 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.478 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.659 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.764 2023-11-17 07:44:07,685 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.595 | bicycle | 0.407 | car | 0.509 | | motorcycle | 0.509 | airplane | 0.701 | bus | 0.708 | | train | 0.722 | truck | 0.473 | boat | 0.350 | | traffic light | 0.318 | fire hydrant | 0.746 | stop sign | 0.690 | | parking meter | 0.526 | bench | 0.322 | bird | 0.434 | | cat | 0.757 | dog | 0.711 | horse | 0.654 | | sheep | 0.614 | cow | 0.651 | elephant | 0.699 | | bear | 0.804 | zebra | 0.693 | giraffe | 0.710 | | backpack | 0.247 | umbrella | 0.485 | handbag | 0.268 | | tie | 0.428 | suitcase | 0.502 | frisbee | 0.733 | | skis | 0.330 | snowboard | 0.476 | sports ball | 0.479 | | kite | 0.478 | baseball bat | 0.443 | baseball glove | 0.472 | | skateboard | 0.612 | surfboard | 0.508 | tennis racket | 0.571 | | bottle | 0.483 | wine glass | 0.444 | cup | 0.527 | | fork | 0.493 | knife | 0.344 | spoon | 0.313 | | bowl | 0.494 | banana | 0.299 | apple | 0.273 | | sandwich | 0.489 | orange | 0.362 | broccoli | 0.286 | | carrot | 0.262 | hot dog | 0.486 | pizza | 0.566 | | donut | 0.576 | cake | 0.477 | chair | 0.382 | | couch | 0.504 | potted plant | 0.362 | bed | 0.497 | | dining table | 0.335 | toilet | 0.679 | tv | 0.647 | | laptop | 0.709 | mouse | 0.669 | remote | 0.472 | | keyboard | 0.579 | cell phone | 0.480 | microwave | 0.689 | | oven | 0.427 | toaster | 0.491 | sink | 0.443 | | refrigerator | 0.700 | book | 0.214 | clock | 0.537 | | vase | 0.422 | scissors | 0.463 | teddy bear | 0.583 | | hair drier | 0.205 | toothbrush | 0.369 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-17 07:44:07,685 - mmdet - INFO - Evaluating segm... 2023-11-17 07:44:40,533 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.452 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.697 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.490 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.271 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.489 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.635 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.564 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.564 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.564 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.408 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.605 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.718 2023-11-17 07:44:40,536 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.520 | bicycle | 0.257 | car | 0.463 | | motorcycle | 0.413 | airplane | 0.566 | bus | 0.686 | | train | 0.707 | truck | 0.454 | boat | 0.331 | | traffic light | 0.310 | fire hydrant | 0.705 | stop sign | 0.651 | | parking meter | 0.523 | bench | 0.245 | bird | 0.357 | | cat | 0.741 | dog | 0.658 | horse | 0.487 | | sheep | 0.551 | cow | 0.552 | elephant | 0.634 | | bear | 0.778 | zebra | 0.593 | giraffe | 0.565 | | backpack | 0.243 | umbrella | 0.530 | handbag | 0.246 | | tie | 0.390 | suitcase | 0.524 | frisbee | 0.675 | | skis | 0.073 | snowboard | 0.312 | sports ball | 0.474 | | kite | 0.333 | baseball bat | 0.332 | baseball glove | 0.476 | | skateboard | 0.413 | surfboard | 0.414 | tennis racket | 0.601 | | bottle | 0.459 | wine glass | 0.401 | cup | 0.526 | | fork | 0.261 | knife | 0.230 | spoon | 0.219 | | bowl | 0.456 | banana | 0.257 | apple | 0.271 | | sandwich | 0.514 | orange | 0.356 | broccoli | 0.264 | | carrot | 0.228 | hot dog | 0.385 | pizza | 0.541 | | donut | 0.575 | cake | 0.486 | chair | 0.280 | | couch | 0.432 | potted plant | 0.308 | bed | 0.412 | | dining table | 0.204 | toilet | 0.661 | tv | 0.679 | | laptop | 0.694 | mouse | 0.634 | remote | 0.420 | | keyboard | 0.566 | cell phone | 0.457 | microwave | 0.707 | | oven | 0.385 | toaster | 0.518 | sink | 0.414 | | refrigerator | 0.712 | book | 0.162 | clock | 0.538 | | vase | 0.413 | scissors | 0.341 | teddy bear | 0.546 | | hair drier | 0.240 | toothbrush | 0.250 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-17 07:44:40,945 - mmdet - INFO - Exp name: mask_rcnn_flash_internimage_b_fpn_3x_coco_0.4_0.9-4x16.py 2023-11-17 07:44:40,945 - mmdet - INFO - Epoch(val) [31][313] bbox_mAP: 0.5046, bbox_mAP_50: 0.7238, bbox_mAP_75: 0.5542, bbox_mAP_s: 0.3618, bbox_mAP_m: 0.5462, bbox_mAP_l: 0.6484, bbox_mAP_copypaste: 0.5046 0.7238 0.5542 0.3618 0.5462 0.6484, segm_mAP: 0.4523, segm_mAP_50: 0.6967, segm_mAP_75: 0.4902, segm_mAP_s: 0.2707, segm_mAP_m: 0.4891, segm_mAP_l: 0.6353, segm_mAP_copypaste: 0.4523 0.6967 0.4902 0.2707 0.4891 0.6353 2023-11-17 07:45:27,698 - mmdet - INFO - Epoch [32][50/1833] lr: 5.563e-07, eta: 2:12:07, time: 0.935, data_time: 0.091, memory: 10998, loss_rpn_cls: 0.0174, loss_rpn_bbox: 0.0293, loss_cls: 0.1358, acc: 94.8138, loss_bbox: 0.1897, loss_mask: 0.1982, loss: 0.5704 2023-11-17 07:46:11,073 - mmdet - INFO - Epoch [32][100/1833] lr: 5.563e-07, eta: 2:11:24, time: 0.868, data_time: 0.031, memory: 10998, loss_rpn_cls: 0.0187, loss_rpn_bbox: 0.0300, loss_cls: 0.1367, acc: 94.7849, loss_bbox: 0.1903, loss_mask: 0.2036, loss: 0.5793 2023-11-17 07:46:55,526 - mmdet - INFO - Epoch [32][150/1833] lr: 5.563e-07, eta: 2:10:40, time: 0.889, data_time: 0.033, memory: 10998, loss_rpn_cls: 0.0195, loss_rpn_bbox: 0.0302, loss_cls: 0.1403, acc: 94.6535, loss_bbox: 0.1946, loss_mask: 0.2052, loss: 0.5898 2023-11-17 07:47:39,729 - mmdet - INFO - Epoch [32][200/1833] lr: 5.563e-07, eta: 2:09:57, time: 0.884, data_time: 0.037, memory: 10998, loss_rpn_cls: 0.0193, loss_rpn_bbox: 0.0311, loss_cls: 0.1392, acc: 94.7110, loss_bbox: 0.1934, loss_mask: 0.2059, loss: 0.5890 2023-11-17 07:48:24,647 - mmdet - INFO - Epoch [32][250/1833] lr: 5.563e-07, eta: 2:09:14, time: 0.898, data_time: 0.036, memory: 10998, loss_rpn_cls: 0.0184, loss_rpn_bbox: 0.0303, loss_cls: 0.1381, acc: 94.7703, loss_bbox: 0.1941, loss_mask: 0.2041, loss: 0.5850 2023-11-17 07:49:08,539 - mmdet - INFO - Epoch [32][300/1833] lr: 5.563e-07, eta: 2:08:30, time: 0.878, data_time: 0.033, memory: 10998, loss_rpn_cls: 0.0197, loss_rpn_bbox: 0.0317, loss_cls: 0.1424, acc: 94.5146, loss_bbox: 0.2006, loss_mask: 0.2078, loss: 0.6022 2023-11-17 07:49:52,604 - mmdet - INFO - Epoch [32][350/1833] lr: 5.563e-07, eta: 2:07:47, time: 0.881, data_time: 0.035, memory: 10998, loss_rpn_cls: 0.0190, loss_rpn_bbox: 0.0306, loss_cls: 0.1380, acc: 94.7125, loss_bbox: 0.1953, loss_mask: 0.2029, loss: 0.5858 2023-11-17 07:50:36,494 - mmdet - INFO - Epoch [32][400/1833] lr: 5.563e-07, eta: 2:07:03, time: 0.878, data_time: 0.029, memory: 10998, loss_rpn_cls: 0.0193, loss_rpn_bbox: 0.0303, loss_cls: 0.1383, acc: 94.6853, loss_bbox: 0.1926, loss_mask: 0.2051, loss: 0.5855 2023-11-17 07:51:20,567 - mmdet - INFO - Epoch [32][450/1833] lr: 5.563e-07, eta: 2:06:20, time: 0.881, data_time: 0.029, memory: 10998, loss_rpn_cls: 0.0193, loss_rpn_bbox: 0.0315, loss_cls: 0.1391, acc: 94.7224, loss_bbox: 0.1959, loss_mask: 0.2060, loss: 0.5918 2023-11-17 07:52:04,726 - mmdet - INFO - Epoch [32][500/1833] lr: 5.563e-07, eta: 2:05:37, time: 0.883, data_time: 0.037, memory: 10998, loss_rpn_cls: 0.0182, loss_rpn_bbox: 0.0301, loss_cls: 0.1372, acc: 94.7451, loss_bbox: 0.1938, loss_mask: 0.2043, loss: 0.5837 2023-11-17 07:52:48,610 - mmdet - INFO - Epoch [32][550/1833] lr: 5.563e-07, eta: 2:04:53, time: 0.878, data_time: 0.033, memory: 10998, loss_rpn_cls: 0.0184, loss_rpn_bbox: 0.0304, loss_cls: 0.1388, acc: 94.7158, loss_bbox: 0.1912, loss_mask: 0.2034, loss: 0.5823 2023-11-17 07:53:32,981 - mmdet - INFO - Epoch [32][600/1833] lr: 5.563e-07, eta: 2:04:10, time: 0.887, data_time: 0.038, memory: 10998, loss_rpn_cls: 0.0181, loss_rpn_bbox: 0.0311, loss_cls: 0.1378, acc: 94.7919, loss_bbox: 0.1936, loss_mask: 0.2034, loss: 0.5840 2023-11-17 07:54:17,423 - mmdet - INFO - Epoch [32][650/1833] lr: 5.563e-07, eta: 2:03:26, time: 0.889, data_time: 0.036, memory: 10998, loss_rpn_cls: 0.0190, loss_rpn_bbox: 0.0316, loss_cls: 0.1384, acc: 94.6923, loss_bbox: 0.1946, loss_mask: 0.2047, loss: 0.5882 2023-11-17 07:55:01,415 - mmdet - INFO - Epoch [32][700/1833] lr: 5.563e-07, eta: 2:02:43, time: 0.880, data_time: 0.033, memory: 10998, loss_rpn_cls: 0.0177, loss_rpn_bbox: 0.0300, loss_cls: 0.1357, acc: 94.8382, loss_bbox: 0.1912, loss_mask: 0.2009, loss: 0.5755 2023-11-17 07:55:45,324 - mmdet - INFO - Epoch [32][750/1833] lr: 5.563e-07, eta: 2:02:00, time: 0.878, data_time: 0.031, memory: 10998, loss_rpn_cls: 0.0187, loss_rpn_bbox: 0.0310, loss_cls: 0.1404, acc: 94.6097, loss_bbox: 0.1980, loss_mask: 0.2060, loss: 0.5941 2023-11-17 07:56:29,336 - mmdet - INFO - Epoch [32][800/1833] lr: 5.563e-07, eta: 2:01:16, time: 0.880, data_time: 0.035, memory: 10998, loss_rpn_cls: 0.0194, loss_rpn_bbox: 0.0311, loss_cls: 0.1390, acc: 94.6559, loss_bbox: 0.1954, loss_mask: 0.2042, loss: 0.5890 2023-11-17 07:57:13,693 - mmdet - INFO - Epoch [32][850/1833] lr: 5.563e-07, eta: 2:00:33, time: 0.887, data_time: 0.036, memory: 10998, loss_rpn_cls: 0.0187, loss_rpn_bbox: 0.0305, loss_cls: 0.1385, acc: 94.7184, loss_bbox: 0.1925, loss_mask: 0.2033, loss: 0.5835 2023-11-17 07:57:57,551 - mmdet - INFO - Epoch [32][900/1833] lr: 5.563e-07, eta: 1:59:49, time: 0.877, data_time: 0.038, memory: 10998, loss_rpn_cls: 0.0190, loss_rpn_bbox: 0.0308, loss_cls: 0.1395, acc: 94.7037, loss_bbox: 0.1938, loss_mask: 0.2041, loss: 0.5872 2023-11-17 07:58:41,681 - mmdet - INFO - Epoch [32][950/1833] lr: 5.563e-07, eta: 1:59:06, time: 0.883, data_time: 0.034, memory: 10998, loss_rpn_cls: 0.0185, loss_rpn_bbox: 0.0303, loss_cls: 0.1379, acc: 94.7544, loss_bbox: 0.1908, loss_mask: 0.2015, loss: 0.5789 2023-11-17 07:59:25,854 - mmdet - INFO - Epoch [32][1000/1833] lr: 5.563e-07, eta: 1:58:23, time: 0.883, data_time: 0.031, memory: 10998, loss_rpn_cls: 0.0192, loss_rpn_bbox: 0.0320, loss_cls: 0.1410, acc: 94.6166, loss_bbox: 0.1975, loss_mask: 0.2087, loss: 0.5983 2023-11-17 08:00:09,575 - mmdet - INFO - Epoch [32][1050/1833] lr: 5.563e-07, eta: 1:57:39, time: 0.874, data_time: 0.034, memory: 10998, loss_rpn_cls: 0.0197, loss_rpn_bbox: 0.0304, loss_cls: 0.1380, acc: 94.7795, loss_bbox: 0.1916, loss_mask: 0.2032, loss: 0.5830 2023-11-17 08:00:53,616 - mmdet - INFO - Epoch [32][1100/1833] lr: 5.563e-07, eta: 1:56:56, time: 0.881, data_time: 0.031, memory: 10998, loss_rpn_cls: 0.0188, loss_rpn_bbox: 0.0307, loss_cls: 0.1362, acc: 94.7668, loss_bbox: 0.1946, loss_mask: 0.2056, loss: 0.5859 2023-11-17 08:01:37,566 - mmdet - INFO - Epoch [32][1150/1833] lr: 5.563e-07, eta: 1:56:12, time: 0.879, data_time: 0.035, memory: 10998, loss_rpn_cls: 0.0189, loss_rpn_bbox: 0.0306, loss_cls: 0.1342, acc: 94.8851, loss_bbox: 0.1880, loss_mask: 0.2034, loss: 0.5752 2023-11-17 08:02:21,604 - mmdet - INFO - Epoch [32][1200/1833] lr: 5.563e-07, eta: 1:55:29, time: 0.880, data_time: 0.031, memory: 10998, loss_rpn_cls: 0.0193, loss_rpn_bbox: 0.0305, loss_cls: 0.1394, acc: 94.6801, loss_bbox: 0.1918, loss_mask: 0.2039, loss: 0.5850 2023-11-17 08:03:06,020 - mmdet - INFO - Epoch [32][1250/1833] lr: 5.563e-07, eta: 1:54:45, time: 0.888, data_time: 0.041, memory: 10998, loss_rpn_cls: 0.0196, loss_rpn_bbox: 0.0309, loss_cls: 0.1383, acc: 94.7736, loss_bbox: 0.1948, loss_mask: 0.2043, loss: 0.5879 2023-11-17 08:03:50,440 - mmdet - INFO - Epoch [32][1300/1833] lr: 5.563e-07, eta: 1:54:02, time: 0.888, data_time: 0.036, memory: 10998, loss_rpn_cls: 0.0191, loss_rpn_bbox: 0.0309, loss_cls: 0.1390, acc: 94.6926, loss_bbox: 0.1943, loss_mask: 0.2056, loss: 0.5890 2023-11-17 08:04:34,536 - mmdet - INFO - Epoch [32][1350/1833] lr: 5.563e-07, eta: 1:53:19, time: 0.882, data_time: 0.037, memory: 10998, loss_rpn_cls: 0.0188, loss_rpn_bbox: 0.0302, loss_cls: 0.1368, acc: 94.7803, loss_bbox: 0.1903, loss_mask: 0.2024, loss: 0.5784 2023-11-17 08:05:18,073 - mmdet - INFO - Epoch [32][1400/1833] lr: 5.563e-07, eta: 1:52:35, time: 0.871, data_time: 0.037, memory: 10998, loss_rpn_cls: 0.0189, loss_rpn_bbox: 0.0315, loss_cls: 0.1386, acc: 94.7166, loss_bbox: 0.1926, loss_mask: 0.2036, loss: 0.5852 2023-11-17 08:06:02,234 - mmdet - INFO - Epoch [32][1450/1833] lr: 5.563e-07, eta: 1:51:52, time: 0.883, data_time: 0.037, memory: 10998, loss_rpn_cls: 0.0193, loss_rpn_bbox: 0.0323, loss_cls: 0.1414, acc: 94.6259, loss_bbox: 0.1961, loss_mask: 0.2058, loss: 0.5949 2023-11-17 08:06:46,441 - mmdet - INFO - Epoch [32][1500/1833] lr: 5.563e-07, eta: 1:51:08, time: 0.884, data_time: 0.036, memory: 10998, loss_rpn_cls: 0.0185, loss_rpn_bbox: 0.0302, loss_cls: 0.1372, acc: 94.7658, loss_bbox: 0.1916, loss_mask: 0.2012, loss: 0.5785 2023-11-17 08:07:30,738 - mmdet - INFO - Epoch [32][1550/1833] lr: 5.563e-07, eta: 1:50:25, time: 0.885, data_time: 0.036, memory: 10998, loss_rpn_cls: 0.0187, loss_rpn_bbox: 0.0313, loss_cls: 0.1389, acc: 94.6825, loss_bbox: 0.1961, loss_mask: 0.2026, loss: 0.5877 2023-11-17 08:08:14,527 - mmdet - INFO - Epoch [32][1600/1833] lr: 5.563e-07, eta: 1:49:41, time: 0.876, data_time: 0.040, memory: 10998, loss_rpn_cls: 0.0190, loss_rpn_bbox: 0.0313, loss_cls: 0.1422, acc: 94.5753, loss_bbox: 0.1977, loss_mask: 0.2050, loss: 0.5952 2023-11-17 08:08:58,221 - mmdet - INFO - Epoch [32][1650/1833] lr: 5.563e-07, eta: 1:48:58, time: 0.874, data_time: 0.037, memory: 10998, loss_rpn_cls: 0.0193, loss_rpn_bbox: 0.0301, loss_cls: 0.1349, acc: 94.8224, loss_bbox: 0.1892, loss_mask: 0.2025, loss: 0.5760 2023-11-17 08:09:41,732 - mmdet - INFO - Epoch [32][1700/1833] lr: 5.563e-07, eta: 1:48:14, time: 0.870, data_time: 0.034, memory: 10998, loss_rpn_cls: 0.0201, loss_rpn_bbox: 0.0315, loss_cls: 0.1419, acc: 94.5536, loss_bbox: 0.1985, loss_mask: 0.2078, loss: 0.5998 2023-11-17 08:10:26,092 - mmdet - INFO - Epoch [32][1750/1833] lr: 5.563e-07, eta: 1:47:31, time: 0.887, data_time: 0.039, memory: 10998, loss_rpn_cls: 0.0190, loss_rpn_bbox: 0.0312, loss_cls: 0.1365, acc: 94.7751, loss_bbox: 0.1928, loss_mask: 0.2022, loss: 0.5817 2023-11-17 08:11:10,385 - mmdet - INFO - Epoch [32][1800/1833] lr: 5.563e-07, eta: 1:46:48, time: 0.886, data_time: 0.036, memory: 10998, loss_rpn_cls: 0.0199, loss_rpn_bbox: 0.0310, loss_cls: 0.1395, acc: 94.6676, loss_bbox: 0.1946, loss_mask: 0.2027, loss: 0.5879 2023-11-17 08:11:39,716 - mmdet - INFO - Saving checkpoint at 32 epochs 2023-11-17 08:12:10,534 - mmdet - INFO - Evaluating bbox... 2023-11-17 08:12:41,252 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.505 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.725 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.555 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.361 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.549 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.649 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.621 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.621 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.621 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.474 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.663 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.762 2023-11-17 08:12:41,255 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.593 | bicycle | 0.409 | car | 0.506 | | motorcycle | 0.513 | airplane | 0.701 | bus | 0.705 | | train | 0.712 | truck | 0.470 | boat | 0.353 | | traffic light | 0.319 | fire hydrant | 0.746 | stop sign | 0.698 | | parking meter | 0.537 | bench | 0.325 | bird | 0.431 | | cat | 0.751 | dog | 0.709 | horse | 0.653 | | sheep | 0.614 | cow | 0.641 | elephant | 0.701 | | bear | 0.803 | zebra | 0.689 | giraffe | 0.708 | | backpack | 0.247 | umbrella | 0.485 | handbag | 0.272 | | tie | 0.429 | suitcase | 0.504 | frisbee | 0.725 | | skis | 0.340 | snowboard | 0.463 | sports ball | 0.484 | | kite | 0.481 | baseball bat | 0.445 | baseball glove | 0.466 | | skateboard | 0.621 | surfboard | 0.515 | tennis racket | 0.572 | | bottle | 0.486 | wine glass | 0.445 | cup | 0.530 | | fork | 0.502 | knife | 0.349 | spoon | 0.307 | | bowl | 0.496 | banana | 0.298 | apple | 0.280 | | sandwich | 0.496 | orange | 0.357 | broccoli | 0.292 | | carrot | 0.262 | hot dog | 0.481 | pizza | 0.569 | | donut | 0.578 | cake | 0.472 | chair | 0.383 | | couch | 0.510 | potted plant | 0.361 | bed | 0.491 | | dining table | 0.333 | toilet | 0.670 | tv | 0.648 | | laptop | 0.710 | mouse | 0.671 | remote | 0.473 | | keyboard | 0.586 | cell phone | 0.484 | microwave | 0.688 | | oven | 0.423 | toaster | 0.482 | sink | 0.452 | | refrigerator | 0.697 | book | 0.216 | clock | 0.536 | | vase | 0.421 | scissors | 0.471 | teddy bear | 0.583 | | hair drier | 0.207 | toothbrush | 0.371 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-17 08:12:41,255 - mmdet - INFO - Evaluating segm... 2023-11-17 08:13:11,757 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.453 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.696 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.491 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.272 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.490 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.639 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.565 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.565 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.565 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.405 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.607 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.718 2023-11-17 08:13:11,759 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.520 | bicycle | 0.255 | car | 0.465 | | motorcycle | 0.420 | airplane | 0.568 | bus | 0.687 | | train | 0.707 | truck | 0.455 | boat | 0.328 | | traffic light | 0.310 | fire hydrant | 0.713 | stop sign | 0.664 | | parking meter | 0.530 | bench | 0.249 | bird | 0.355 | | cat | 0.738 | dog | 0.660 | horse | 0.490 | | sheep | 0.552 | cow | 0.547 | elephant | 0.636 | | bear | 0.779 | zebra | 0.590 | giraffe | 0.561 | | backpack | 0.244 | umbrella | 0.531 | handbag | 0.248 | | tie | 0.390 | suitcase | 0.524 | frisbee | 0.676 | | skis | 0.073 | snowboard | 0.310 | sports ball | 0.475 | | kite | 0.335 | baseball bat | 0.333 | baseball glove | 0.478 | | skateboard | 0.413 | surfboard | 0.421 | tennis racket | 0.600 | | bottle | 0.461 | wine glass | 0.408 | cup | 0.530 | | fork | 0.265 | knife | 0.235 | spoon | 0.219 | | bowl | 0.454 | banana | 0.255 | apple | 0.272 | | sandwich | 0.518 | orange | 0.355 | broccoli | 0.267 | | carrot | 0.229 | hot dog | 0.384 | pizza | 0.550 | | donut | 0.582 | cake | 0.484 | chair | 0.280 | | couch | 0.430 | potted plant | 0.306 | bed | 0.413 | | dining table | 0.200 | toilet | 0.649 | tv | 0.682 | | laptop | 0.692 | mouse | 0.632 | remote | 0.422 | | keyboard | 0.570 | cell phone | 0.459 | microwave | 0.702 | | oven | 0.382 | toaster | 0.504 | sink | 0.422 | | refrigerator | 0.705 | book | 0.162 | clock | 0.542 | | vase | 0.413 | scissors | 0.352 | teddy bear | 0.545 | | hair drier | 0.241 | toothbrush | 0.256 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-17 08:13:12,172 - mmdet - INFO - Exp name: mask_rcnn_flash_internimage_b_fpn_3x_coco_0.4_0.9-4x16.py 2023-11-17 08:13:12,172 - mmdet - INFO - Epoch(val) [32][313] bbox_mAP: 0.5050, bbox_mAP_50: 0.7246, bbox_mAP_75: 0.5548, bbox_mAP_s: 0.3607, bbox_mAP_m: 0.5488, bbox_mAP_l: 0.6491, bbox_mAP_copypaste: 0.5050 0.7246 0.5548 0.3607 0.5488 0.6491, segm_mAP: 0.4532, segm_mAP_50: 0.6964, segm_mAP_75: 0.4907, segm_mAP_s: 0.2723, segm_mAP_m: 0.4899, segm_mAP_l: 0.6385, segm_mAP_copypaste: 0.4532 0.6964 0.4907 0.2723 0.4899 0.6385 2023-11-17 08:13:59,001 - mmdet - INFO - Epoch [33][50/1833] lr: 5.563e-07, eta: 1:45:32, time: 0.936, data_time: 0.093, memory: 10998, loss_rpn_cls: 0.0181, loss_rpn_bbox: 0.0293, loss_cls: 0.1359, acc: 94.8201, loss_bbox: 0.1898, loss_mask: 0.2045, loss: 0.5776 2023-11-17 08:14:42,703 - mmdet - INFO - Epoch [33][100/1833] lr: 5.563e-07, eta: 1:44:49, time: 0.874, data_time: 0.035, memory: 10998, loss_rpn_cls: 0.0185, loss_rpn_bbox: 0.0304, loss_cls: 0.1347, acc: 94.8543, loss_bbox: 0.1886, loss_mask: 0.2009, loss: 0.5731 2023-11-17 08:15:27,105 - mmdet - INFO - Epoch [33][150/1833] lr: 5.563e-07, eta: 1:44:05, time: 0.888, data_time: 0.036, memory: 10998, loss_rpn_cls: 0.0193, loss_rpn_bbox: 0.0308, loss_cls: 0.1405, acc: 94.6198, loss_bbox: 0.1955, loss_mask: 0.2071, loss: 0.5933 2023-11-17 08:16:11,090 - mmdet - INFO - Epoch [33][200/1833] lr: 5.563e-07, eta: 1:43:22, time: 0.880, data_time: 0.034, memory: 10998, loss_rpn_cls: 0.0200, loss_rpn_bbox: 0.0318, loss_cls: 0.1418, acc: 94.6279, loss_bbox: 0.1988, loss_mask: 0.2056, loss: 0.5979 2023-11-17 08:16:55,006 - mmdet - INFO - Epoch [33][250/1833] lr: 5.563e-07, eta: 1:42:39, time: 0.878, data_time: 0.040, memory: 10998, loss_rpn_cls: 0.0190, loss_rpn_bbox: 0.0301, loss_cls: 0.1403, acc: 94.6620, loss_bbox: 0.1944, loss_mask: 0.2051, loss: 0.5890 2023-11-17 08:17:38,901 - mmdet - INFO - Epoch [33][300/1833] lr: 5.563e-07, eta: 1:41:55, time: 0.878, data_time: 0.033, memory: 10998, loss_rpn_cls: 0.0196, loss_rpn_bbox: 0.0307, loss_cls: 0.1397, acc: 94.7021, loss_bbox: 0.1942, loss_mask: 0.2037, loss: 0.5880 2023-11-17 08:18:22,975 - mmdet - INFO - Epoch [33][350/1833] lr: 5.563e-07, eta: 1:41:12, time: 0.881, data_time: 0.032, memory: 10998, loss_rpn_cls: 0.0191, loss_rpn_bbox: 0.0306, loss_cls: 0.1368, acc: 94.7896, loss_bbox: 0.1895, loss_mask: 0.2030, loss: 0.5791 2023-11-17 08:19:07,604 - mmdet - INFO - Epoch [33][400/1833] lr: 5.563e-07, eta: 1:40:28, time: 0.893, data_time: 0.034, memory: 10998, loss_rpn_cls: 0.0179, loss_rpn_bbox: 0.0297, loss_cls: 0.1357, acc: 94.7688, loss_bbox: 0.1917, loss_mask: 0.2031, loss: 0.5780 2023-11-17 08:19:51,140 - mmdet - INFO - Epoch [33][450/1833] lr: 5.563e-07, eta: 1:39:45, time: 0.871, data_time: 0.029, memory: 10998, loss_rpn_cls: 0.0187, loss_rpn_bbox: 0.0308, loss_cls: 0.1380, acc: 94.7700, loss_bbox: 0.1936, loss_mask: 0.2055, loss: 0.5867 2023-11-17 08:20:34,980 - mmdet - INFO - Epoch [33][500/1833] lr: 5.563e-07, eta: 1:39:01, time: 0.877, data_time: 0.035, memory: 10998, loss_rpn_cls: 0.0183, loss_rpn_bbox: 0.0303, loss_cls: 0.1356, acc: 94.8604, loss_bbox: 0.1893, loss_mask: 0.2018, loss: 0.5753 2023-11-17 08:21:19,400 - mmdet - INFO - Epoch [33][550/1833] lr: 5.563e-07, eta: 1:38:18, time: 0.888, data_time: 0.034, memory: 10998, loss_rpn_cls: 0.0188, loss_rpn_bbox: 0.0314, loss_cls: 0.1396, acc: 94.6544, loss_bbox: 0.1956, loss_mask: 0.2054, loss: 0.5908 2023-11-17 08:22:03,647 - mmdet - INFO - Epoch [33][600/1833] lr: 5.563e-07, eta: 1:37:35, time: 0.885, data_time: 0.040, memory: 10998, loss_rpn_cls: 0.0185, loss_rpn_bbox: 0.0295, loss_cls: 0.1368, acc: 94.7671, loss_bbox: 0.1895, loss_mask: 0.2024, loss: 0.5766 2023-11-17 08:22:48,169 - mmdet - INFO - Epoch [33][650/1833] lr: 5.563e-07, eta: 1:36:51, time: 0.890, data_time: 0.033, memory: 10998, loss_rpn_cls: 0.0196, loss_rpn_bbox: 0.0312, loss_cls: 0.1406, acc: 94.6283, loss_bbox: 0.1969, loss_mask: 0.2039, loss: 0.5922 2023-11-17 08:23:32,294 - mmdet - INFO - Epoch [33][700/1833] lr: 5.563e-07, eta: 1:36:08, time: 0.883, data_time: 0.033, memory: 10998, loss_rpn_cls: 0.0181, loss_rpn_bbox: 0.0302, loss_cls: 0.1353, acc: 94.8499, loss_bbox: 0.1876, loss_mask: 0.2015, loss: 0.5728 2023-11-17 08:24:16,205 - mmdet - INFO - Epoch [33][750/1833] lr: 5.563e-07, eta: 1:35:24, time: 0.878, data_time: 0.033, memory: 10998, loss_rpn_cls: 0.0193, loss_rpn_bbox: 0.0307, loss_cls: 0.1374, acc: 94.7576, loss_bbox: 0.1934, loss_mask: 0.2025, loss: 0.5833 2023-11-17 08:25:00,257 - mmdet - INFO - Epoch [33][800/1833] lr: 5.563e-07, eta: 1:34:41, time: 0.881, data_time: 0.036, memory: 10998, loss_rpn_cls: 0.0187, loss_rpn_bbox: 0.0310, loss_cls: 0.1395, acc: 94.6927, loss_bbox: 0.1957, loss_mask: 0.2055, loss: 0.5903 2023-11-17 08:25:44,323 - mmdet - INFO - Epoch [33][850/1833] lr: 5.563e-07, eta: 1:33:58, time: 0.881, data_time: 0.038, memory: 10998, loss_rpn_cls: 0.0193, loss_rpn_bbox: 0.0320, loss_cls: 0.1423, acc: 94.5637, loss_bbox: 0.1988, loss_mask: 0.2063, loss: 0.5986 2023-11-17 08:26:28,199 - mmdet - INFO - Epoch [33][900/1833] lr: 5.563e-07, eta: 1:33:14, time: 0.877, data_time: 0.037, memory: 10998, loss_rpn_cls: 0.0185, loss_rpn_bbox: 0.0305, loss_cls: 0.1381, acc: 94.6932, loss_bbox: 0.1940, loss_mask: 0.2030, loss: 0.5841 2023-11-17 08:27:12,236 - mmdet - INFO - Epoch [33][950/1833] lr: 5.563e-07, eta: 1:32:31, time: 0.881, data_time: 0.036, memory: 10998, loss_rpn_cls: 0.0196, loss_rpn_bbox: 0.0318, loss_cls: 0.1398, acc: 94.6482, loss_bbox: 0.1962, loss_mask: 0.2060, loss: 0.5935 2023-11-17 08:27:56,860 - mmdet - INFO - Epoch [33][1000/1833] lr: 5.563e-07, eta: 1:31:47, time: 0.892, data_time: 0.035, memory: 10998, loss_rpn_cls: 0.0197, loss_rpn_bbox: 0.0312, loss_cls: 0.1393, acc: 94.7256, loss_bbox: 0.1934, loss_mask: 0.2031, loss: 0.5866 2023-11-17 08:28:40,686 - mmdet - INFO - Epoch [33][1050/1833] lr: 5.563e-07, eta: 1:31:04, time: 0.876, data_time: 0.030, memory: 10998, loss_rpn_cls: 0.0177, loss_rpn_bbox: 0.0288, loss_cls: 0.1326, acc: 94.9381, loss_bbox: 0.1864, loss_mask: 0.1996, loss: 0.5651 2023-11-17 08:29:24,544 - mmdet - INFO - Epoch [33][1100/1833] lr: 5.563e-07, eta: 1:30:20, time: 0.877, data_time: 0.034, memory: 10998, loss_rpn_cls: 0.0193, loss_rpn_bbox: 0.0316, loss_cls: 0.1370, acc: 94.7739, loss_bbox: 0.1931, loss_mask: 0.2053, loss: 0.5862 2023-11-17 08:30:09,037 - mmdet - INFO - Epoch [33][1150/1833] lr: 5.563e-07, eta: 1:29:37, time: 0.890, data_time: 0.031, memory: 10998, loss_rpn_cls: 0.0199, loss_rpn_bbox: 0.0323, loss_cls: 0.1424, acc: 94.5331, loss_bbox: 0.2005, loss_mask: 0.2058, loss: 0.6009 2023-11-17 08:30:53,306 - mmdet - INFO - Epoch [33][1200/1833] lr: 5.563e-07, eta: 1:28:54, time: 0.885, data_time: 0.029, memory: 10998, loss_rpn_cls: 0.0188, loss_rpn_bbox: 0.0308, loss_cls: 0.1371, acc: 94.7565, loss_bbox: 0.1922, loss_mask: 0.2033, loss: 0.5822 2023-11-17 08:31:37,411 - mmdet - INFO - Epoch [33][1250/1833] lr: 5.563e-07, eta: 1:28:10, time: 0.882, data_time: 0.031, memory: 10998, loss_rpn_cls: 0.0191, loss_rpn_bbox: 0.0307, loss_cls: 0.1373, acc: 94.6865, loss_bbox: 0.1923, loss_mask: 0.2051, loss: 0.5845 2023-11-17 08:32:21,267 - mmdet - INFO - Epoch [33][1300/1833] lr: 5.563e-07, eta: 1:27:27, time: 0.877, data_time: 0.034, memory: 10998, loss_rpn_cls: 0.0193, loss_rpn_bbox: 0.0303, loss_cls: 0.1367, acc: 94.7927, loss_bbox: 0.1923, loss_mask: 0.2055, loss: 0.5842 2023-11-17 08:33:07,763 - mmdet - INFO - Epoch [33][1350/1833] lr: 5.563e-07, eta: 1:26:44, time: 0.930, data_time: 0.040, memory: 10998, loss_rpn_cls: 0.0195, loss_rpn_bbox: 0.0310, loss_cls: 0.1377, acc: 94.7305, loss_bbox: 0.1936, loss_mask: 0.2041, loss: 0.5860 2023-11-17 08:33:51,201 - mmdet - INFO - Epoch [33][1400/1833] lr: 5.563e-07, eta: 1:26:00, time: 0.868, data_time: 0.033, memory: 10998, loss_rpn_cls: 0.0201, loss_rpn_bbox: 0.0314, loss_cls: 0.1426, acc: 94.5745, loss_bbox: 0.1991, loss_mask: 0.2072, loss: 0.6004 2023-11-17 08:34:34,963 - mmdet - INFO - Epoch [33][1450/1833] lr: 5.563e-07, eta: 1:25:17, time: 0.876, data_time: 0.032, memory: 10998, loss_rpn_cls: 0.0179, loss_rpn_bbox: 0.0299, loss_cls: 0.1333, acc: 94.9160, loss_bbox: 0.1867, loss_mask: 0.2009, loss: 0.5687 2023-11-17 08:35:19,330 - mmdet - INFO - Epoch [33][1500/1833] lr: 5.563e-07, eta: 1:24:33, time: 0.887, data_time: 0.034, memory: 10998, loss_rpn_cls: 0.0193, loss_rpn_bbox: 0.0315, loss_cls: 0.1374, acc: 94.7169, loss_bbox: 0.1952, loss_mask: 0.2037, loss: 0.5872 2023-11-17 08:36:03,332 - mmdet - INFO - Epoch [33][1550/1833] lr: 5.563e-07, eta: 1:23:50, time: 0.880, data_time: 0.037, memory: 10998, loss_rpn_cls: 0.0188, loss_rpn_bbox: 0.0317, loss_cls: 0.1390, acc: 94.7078, loss_bbox: 0.1950, loss_mask: 0.2048, loss: 0.5893 2023-11-17 08:36:47,175 - mmdet - INFO - Epoch [33][1600/1833] lr: 5.563e-07, eta: 1:23:06, time: 0.877, data_time: 0.032, memory: 10998, loss_rpn_cls: 0.0190, loss_rpn_bbox: 0.0307, loss_cls: 0.1349, acc: 94.8290, loss_bbox: 0.1899, loss_mask: 0.2020, loss: 0.5765 2023-11-17 08:37:31,330 - mmdet - INFO - Epoch [33][1650/1833] lr: 5.563e-07, eta: 1:22:23, time: 0.883, data_time: 0.030, memory: 10998, loss_rpn_cls: 0.0192, loss_rpn_bbox: 0.0309, loss_cls: 0.1377, acc: 94.7224, loss_bbox: 0.1915, loss_mask: 0.2031, loss: 0.5824 2023-11-17 08:38:15,044 - mmdet - INFO - Epoch [33][1700/1833] lr: 5.563e-07, eta: 1:21:39, time: 0.874, data_time: 0.035, memory: 10998, loss_rpn_cls: 0.0197, loss_rpn_bbox: 0.0312, loss_cls: 0.1395, acc: 94.6685, loss_bbox: 0.1945, loss_mask: 0.2041, loss: 0.5890 2023-11-17 08:38:59,735 - mmdet - INFO - Epoch [33][1750/1833] lr: 5.563e-07, eta: 1:20:56, time: 0.894, data_time: 0.035, memory: 10998, loss_rpn_cls: 0.0176, loss_rpn_bbox: 0.0297, loss_cls: 0.1366, acc: 94.8239, loss_bbox: 0.1912, loss_mask: 0.2033, loss: 0.5784 2023-11-17 08:39:43,433 - mmdet - INFO - Epoch [33][1800/1833] lr: 5.563e-07, eta: 1:20:12, time: 0.874, data_time: 0.033, memory: 10998, loss_rpn_cls: 0.0178, loss_rpn_bbox: 0.0304, loss_cls: 0.1359, acc: 94.8349, loss_bbox: 0.1907, loss_mask: 0.2017, loss: 0.5766 2023-11-17 08:40:13,032 - mmdet - INFO - Saving checkpoint at 33 epochs 2023-11-17 08:40:43,505 - mmdet - INFO - Evaluating bbox... 2023-11-17 08:41:13,379 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.504 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.725 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.551 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.360 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.546 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.647 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.621 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.621 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.621 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.475 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.660 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.761 2023-11-17 08:41:13,382 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.594 | bicycle | 0.407 | car | 0.505 | | motorcycle | 0.508 | airplane | 0.702 | bus | 0.706 | | train | 0.718 | truck | 0.469 | boat | 0.350 | | traffic light | 0.318 | fire hydrant | 0.741 | stop sign | 0.702 | | parking meter | 0.529 | bench | 0.327 | bird | 0.433 | | cat | 0.750 | dog | 0.713 | horse | 0.652 | | sheep | 0.611 | cow | 0.649 | elephant | 0.702 | | bear | 0.801 | zebra | 0.687 | giraffe | 0.707 | | backpack | 0.244 | umbrella | 0.487 | handbag | 0.269 | | tie | 0.427 | suitcase | 0.505 | frisbee | 0.727 | | skis | 0.331 | snowboard | 0.480 | sports ball | 0.477 | | kite | 0.483 | baseball bat | 0.445 | baseball glove | 0.473 | | skateboard | 0.616 | surfboard | 0.512 | tennis racket | 0.567 | | bottle | 0.485 | wine glass | 0.440 | cup | 0.526 | | fork | 0.499 | knife | 0.344 | spoon | 0.312 | | bowl | 0.499 | banana | 0.302 | apple | 0.272 | | sandwich | 0.491 | orange | 0.359 | broccoli | 0.281 | | carrot | 0.267 | hot dog | 0.471 | pizza | 0.560 | | donut | 0.582 | cake | 0.476 | chair | 0.382 | | couch | 0.501 | potted plant | 0.363 | bed | 0.492 | | dining table | 0.336 | toilet | 0.669 | tv | 0.651 | | laptop | 0.706 | mouse | 0.673 | remote | 0.474 | | keyboard | 0.579 | cell phone | 0.485 | microwave | 0.682 | | oven | 0.423 | toaster | 0.452 | sink | 0.450 | | refrigerator | 0.701 | book | 0.214 | clock | 0.545 | | vase | 0.420 | scissors | 0.477 | teddy bear | 0.583 | | hair drier | 0.214 | toothbrush | 0.360 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-17 08:41:13,382 - mmdet - INFO - Evaluating segm... 2023-11-17 08:41:46,048 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.452 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.697 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.490 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.272 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.490 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.636 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.564 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.564 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.564 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.404 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.608 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.716 2023-11-17 08:41:46,051 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.520 | bicycle | 0.252 | car | 0.462 | | motorcycle | 0.414 | airplane | 0.571 | bus | 0.685 | | train | 0.704 | truck | 0.453 | boat | 0.331 | | traffic light | 0.308 | fire hydrant | 0.709 | stop sign | 0.673 | | parking meter | 0.524 | bench | 0.246 | bird | 0.354 | | cat | 0.739 | dog | 0.661 | horse | 0.488 | | sheep | 0.547 | cow | 0.555 | elephant | 0.634 | | bear | 0.780 | zebra | 0.598 | giraffe | 0.562 | | backpack | 0.237 | umbrella | 0.526 | handbag | 0.248 | | tie | 0.392 | suitcase | 0.523 | frisbee | 0.674 | | skis | 0.073 | snowboard | 0.323 | sports ball | 0.469 | | kite | 0.337 | baseball bat | 0.327 | baseball glove | 0.484 | | skateboard | 0.407 | surfboard | 0.422 | tennis racket | 0.601 | | bottle | 0.460 | wine glass | 0.403 | cup | 0.526 | | fork | 0.262 | knife | 0.233 | spoon | 0.222 | | bowl | 0.460 | banana | 0.257 | apple | 0.270 | | sandwich | 0.523 | orange | 0.356 | broccoli | 0.258 | | carrot | 0.232 | hot dog | 0.378 | pizza | 0.543 | | donut | 0.577 | cake | 0.487 | chair | 0.279 | | couch | 0.426 | potted plant | 0.306 | bed | 0.413 | | dining table | 0.205 | toilet | 0.651 | tv | 0.679 | | laptop | 0.691 | mouse | 0.640 | remote | 0.420 | | keyboard | 0.560 | cell phone | 0.459 | microwave | 0.702 | | oven | 0.381 | toaster | 0.498 | sink | 0.421 | | refrigerator | 0.712 | book | 0.158 | clock | 0.537 | | vase | 0.412 | scissors | 0.338 | teddy bear | 0.547 | | hair drier | 0.218 | toothbrush | 0.255 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-17 08:41:46,456 - mmdet - INFO - Exp name: mask_rcnn_flash_internimage_b_fpn_3x_coco_0.4_0.9-4x16.py 2023-11-17 08:41:46,456 - mmdet - INFO - Epoch(val) [33][313] bbox_mAP: 0.5040, bbox_mAP_50: 0.7247, bbox_mAP_75: 0.5512, bbox_mAP_s: 0.3596, bbox_mAP_m: 0.5458, bbox_mAP_l: 0.6468, bbox_mAP_copypaste: 0.5040 0.7247 0.5512 0.3596 0.5458 0.6468, segm_mAP: 0.4521, segm_mAP_50: 0.6973, segm_mAP_75: 0.4901, segm_mAP_s: 0.2716, segm_mAP_m: 0.4902, segm_mAP_l: 0.6362, segm_mAP_copypaste: 0.4521 0.6973 0.4901 0.2716 0.4902 0.6362 2023-11-17 08:42:33,274 - mmdet - INFO - Epoch [34][50/1833] lr: 5.563e-08, eta: 1:18:58, time: 0.936, data_time: 0.099, memory: 10998, loss_rpn_cls: 0.0191, loss_rpn_bbox: 0.0310, loss_cls: 0.1361, acc: 94.7886, loss_bbox: 0.1926, loss_mask: 0.2031, loss: 0.5817 2023-11-17 08:43:17,061 - mmdet - INFO - Epoch [34][100/1833] lr: 5.563e-08, eta: 1:18:15, time: 0.875, data_time: 0.035, memory: 10998, loss_rpn_cls: 0.0183, loss_rpn_bbox: 0.0300, loss_cls: 0.1370, acc: 94.7344, loss_bbox: 0.1926, loss_mask: 0.2018, loss: 0.5796 2023-11-17 08:44:01,089 - mmdet - INFO - Epoch [34][150/1833] lr: 5.563e-08, eta: 1:17:31, time: 0.881, data_time: 0.031, memory: 10998, loss_rpn_cls: 0.0198, loss_rpn_bbox: 0.0320, loss_cls: 0.1395, acc: 94.6368, loss_bbox: 0.1973, loss_mask: 0.2056, loss: 0.5942 2023-11-17 08:44:44,997 - mmdet - INFO - Epoch [34][200/1833] lr: 5.563e-08, eta: 1:16:48, time: 0.878, data_time: 0.033, memory: 10998, loss_rpn_cls: 0.0188, loss_rpn_bbox: 0.0296, loss_cls: 0.1383, acc: 94.7603, loss_bbox: 0.1917, loss_mask: 0.2026, loss: 0.5810 2023-11-17 08:45:29,237 - mmdet - INFO - Epoch [34][250/1833] lr: 5.563e-08, eta: 1:16:04, time: 0.885, data_time: 0.034, memory: 10998, loss_rpn_cls: 0.0186, loss_rpn_bbox: 0.0299, loss_cls: 0.1370, acc: 94.7811, loss_bbox: 0.1914, loss_mask: 0.2005, loss: 0.5773 2023-11-17 08:46:13,288 - mmdet - INFO - Epoch [34][300/1833] lr: 5.563e-08, eta: 1:15:21, time: 0.881, data_time: 0.032, memory: 10998, loss_rpn_cls: 0.0197, loss_rpn_bbox: 0.0312, loss_cls: 0.1386, acc: 94.6878, loss_bbox: 0.1962, loss_mask: 0.2059, loss: 0.5916 2023-11-17 08:46:57,521 - mmdet - INFO - Epoch [34][350/1833] lr: 5.563e-08, eta: 1:14:37, time: 0.884, data_time: 0.034, memory: 10998, loss_rpn_cls: 0.0193, loss_rpn_bbox: 0.0313, loss_cls: 0.1400, acc: 94.6851, loss_bbox: 0.1967, loss_mask: 0.2044, loss: 0.5916 2023-11-17 08:47:42,138 - mmdet - INFO - Epoch [34][400/1833] lr: 5.563e-08, eta: 1:13:54, time: 0.893, data_time: 0.031, memory: 10998, loss_rpn_cls: 0.0192, loss_rpn_bbox: 0.0310, loss_cls: 0.1392, acc: 94.7047, loss_bbox: 0.1910, loss_mask: 0.2014, loss: 0.5819 2023-11-17 08:48:26,813 - mmdet - INFO - Epoch [34][450/1833] lr: 5.563e-08, eta: 1:13:11, time: 0.894, data_time: 0.038, memory: 10998, loss_rpn_cls: 0.0184, loss_rpn_bbox: 0.0297, loss_cls: 0.1359, acc: 94.7795, loss_bbox: 0.1901, loss_mask: 0.2017, loss: 0.5758 2023-11-17 08:49:11,721 - mmdet - INFO - Epoch [34][500/1833] lr: 5.563e-08, eta: 1:12:27, time: 0.898, data_time: 0.031, memory: 10998, loss_rpn_cls: 0.0194, loss_rpn_bbox: 0.0308, loss_cls: 0.1377, acc: 94.7593, loss_bbox: 0.1939, loss_mask: 0.2037, loss: 0.5855 2023-11-17 08:49:55,704 - mmdet - INFO - Epoch [34][550/1833] lr: 5.563e-08, eta: 1:11:44, time: 0.880, data_time: 0.034, memory: 10998, loss_rpn_cls: 0.0193, loss_rpn_bbox: 0.0313, loss_cls: 0.1380, acc: 94.7590, loss_bbox: 0.1932, loss_mask: 0.2047, loss: 0.5866 2023-11-17 08:50:40,285 - mmdet - INFO - Epoch [34][600/1833] lr: 5.563e-08, eta: 1:11:00, time: 0.892, data_time: 0.037, memory: 10998, loss_rpn_cls: 0.0177, loss_rpn_bbox: 0.0304, loss_cls: 0.1354, acc: 94.8169, loss_bbox: 0.1898, loss_mask: 0.2028, loss: 0.5761 2023-11-17 08:51:24,722 - mmdet - INFO - Epoch [34][650/1833] lr: 5.563e-08, eta: 1:10:17, time: 0.889, data_time: 0.032, memory: 10998, loss_rpn_cls: 0.0192, loss_rpn_bbox: 0.0311, loss_cls: 0.1386, acc: 94.7197, loss_bbox: 0.1960, loss_mask: 0.2019, loss: 0.5868 2023-11-17 08:52:09,149 - mmdet - INFO - Epoch [34][700/1833] lr: 5.563e-08, eta: 1:09:34, time: 0.888, data_time: 0.034, memory: 10998, loss_rpn_cls: 0.0187, loss_rpn_bbox: 0.0314, loss_cls: 0.1398, acc: 94.6611, loss_bbox: 0.1953, loss_mask: 0.2061, loss: 0.5913 2023-11-17 08:52:53,319 - mmdet - INFO - Epoch [34][750/1833] lr: 5.563e-08, eta: 1:08:50, time: 0.884, data_time: 0.032, memory: 10998, loss_rpn_cls: 0.0183, loss_rpn_bbox: 0.0303, loss_cls: 0.1334, acc: 94.9179, loss_bbox: 0.1874, loss_mask: 0.1997, loss: 0.5690 2023-11-17 08:53:37,714 - mmdet - INFO - Epoch [34][800/1833] lr: 5.563e-08, eta: 1:08:07, time: 0.888, data_time: 0.034, memory: 10998, loss_rpn_cls: 0.0192, loss_rpn_bbox: 0.0308, loss_cls: 0.1379, acc: 94.7134, loss_bbox: 0.1944, loss_mask: 0.2034, loss: 0.5857 2023-11-17 08:54:21,753 - mmdet - INFO - Epoch [34][850/1833] lr: 5.563e-08, eta: 1:07:23, time: 0.881, data_time: 0.033, memory: 10998, loss_rpn_cls: 0.0182, loss_rpn_bbox: 0.0301, loss_cls: 0.1367, acc: 94.7977, loss_bbox: 0.1909, loss_mask: 0.2018, loss: 0.5777 2023-11-17 08:55:06,235 - mmdet - INFO - Epoch [34][900/1833] lr: 5.563e-08, eta: 1:06:40, time: 0.890, data_time: 0.031, memory: 10998, loss_rpn_cls: 0.0191, loss_rpn_bbox: 0.0308, loss_cls: 0.1367, acc: 94.7697, loss_bbox: 0.1930, loss_mask: 0.2025, loss: 0.5821 2023-11-17 08:55:50,786 - mmdet - INFO - Epoch [34][950/1833] lr: 5.563e-08, eta: 1:05:56, time: 0.891, data_time: 0.033, memory: 10998, loss_rpn_cls: 0.0186, loss_rpn_bbox: 0.0299, loss_cls: 0.1374, acc: 94.7827, loss_bbox: 0.1901, loss_mask: 0.2043, loss: 0.5802 2023-11-17 08:56:34,593 - mmdet - INFO - Epoch [34][1000/1833] lr: 5.563e-08, eta: 1:05:13, time: 0.876, data_time: 0.032, memory: 10998, loss_rpn_cls: 0.0194, loss_rpn_bbox: 0.0307, loss_cls: 0.1378, acc: 94.7507, loss_bbox: 0.1913, loss_mask: 0.2035, loss: 0.5827 2023-11-17 08:57:18,881 - mmdet - INFO - Epoch [34][1050/1833] lr: 5.563e-08, eta: 1:04:30, time: 0.886, data_time: 0.033, memory: 10998, loss_rpn_cls: 0.0187, loss_rpn_bbox: 0.0306, loss_cls: 0.1355, acc: 94.8254, loss_bbox: 0.1913, loss_mask: 0.2031, loss: 0.5792 2023-11-17 08:58:06,224 - mmdet - INFO - Epoch [34][1100/1833] lr: 5.563e-08, eta: 1:03:46, time: 0.947, data_time: 0.033, memory: 10998, loss_rpn_cls: 0.0190, loss_rpn_bbox: 0.0306, loss_cls: 0.1406, acc: 94.6064, loss_bbox: 0.1977, loss_mask: 0.2050, loss: 0.5929 2023-11-17 08:58:50,630 - mmdet - INFO - Epoch [34][1150/1833] lr: 5.563e-08, eta: 1:03:03, time: 0.888, data_time: 0.037, memory: 10998, loss_rpn_cls: 0.0184, loss_rpn_bbox: 0.0317, loss_cls: 0.1381, acc: 94.7335, loss_bbox: 0.1935, loss_mask: 0.2044, loss: 0.5860 2023-11-17 08:59:35,084 - mmdet - INFO - Epoch [34][1200/1833] lr: 5.563e-08, eta: 1:02:19, time: 0.888, data_time: 0.037, memory: 10998, loss_rpn_cls: 0.0183, loss_rpn_bbox: 0.0305, loss_cls: 0.1358, acc: 94.7952, loss_bbox: 0.1900, loss_mask: 0.2005, loss: 0.5752 2023-11-17 09:00:19,326 - mmdet - INFO - Epoch [34][1250/1833] lr: 5.563e-08, eta: 1:01:36, time: 0.885, data_time: 0.045, memory: 10998, loss_rpn_cls: 0.0193, loss_rpn_bbox: 0.0314, loss_cls: 0.1378, acc: 94.7300, loss_bbox: 0.1935, loss_mask: 0.2034, loss: 0.5854 2023-11-17 09:01:03,991 - mmdet - INFO - Epoch [34][1300/1833] lr: 5.563e-08, eta: 1:00:53, time: 0.893, data_time: 0.036, memory: 10998, loss_rpn_cls: 0.0191, loss_rpn_bbox: 0.0312, loss_cls: 0.1384, acc: 94.7152, loss_bbox: 0.1937, loss_mask: 0.2032, loss: 0.5856 2023-11-17 09:01:47,961 - mmdet - INFO - Epoch [34][1350/1833] lr: 5.563e-08, eta: 1:00:09, time: 0.879, data_time: 0.039, memory: 10998, loss_rpn_cls: 0.0174, loss_rpn_bbox: 0.0292, loss_cls: 0.1347, acc: 94.8563, loss_bbox: 0.1905, loss_mask: 0.2008, loss: 0.5727 2023-11-17 09:02:32,147 - mmdet - INFO - Epoch [34][1400/1833] lr: 5.563e-08, eta: 0:59:26, time: 0.884, data_time: 0.031, memory: 10998, loss_rpn_cls: 0.0183, loss_rpn_bbox: 0.0299, loss_cls: 0.1340, acc: 94.8461, loss_bbox: 0.1890, loss_mask: 0.2000, loss: 0.5713 2023-11-17 09:03:16,186 - mmdet - INFO - Epoch [34][1450/1833] lr: 5.563e-08, eta: 0:58:42, time: 0.881, data_time: 0.032, memory: 10998, loss_rpn_cls: 0.0190, loss_rpn_bbox: 0.0311, loss_cls: 0.1379, acc: 94.7239, loss_bbox: 0.1939, loss_mask: 0.2042, loss: 0.5861 2023-11-17 09:04:00,674 - mmdet - INFO - Epoch [34][1500/1833] lr: 5.563e-08, eta: 0:57:59, time: 0.890, data_time: 0.036, memory: 10998, loss_rpn_cls: 0.0194, loss_rpn_bbox: 0.0310, loss_cls: 0.1372, acc: 94.7335, loss_bbox: 0.1918, loss_mask: 0.2047, loss: 0.5840 2023-11-17 09:04:45,263 - mmdet - INFO - Epoch [34][1550/1833] lr: 5.563e-08, eta: 0:57:15, time: 0.892, data_time: 0.032, memory: 10998, loss_rpn_cls: 0.0191, loss_rpn_bbox: 0.0305, loss_cls: 0.1348, acc: 94.8535, loss_bbox: 0.1882, loss_mask: 0.1990, loss: 0.5716 2023-11-17 09:05:29,869 - mmdet - INFO - Epoch [34][1600/1833] lr: 5.563e-08, eta: 0:56:32, time: 0.892, data_time: 0.041, memory: 10998, loss_rpn_cls: 0.0190, loss_rpn_bbox: 0.0307, loss_cls: 0.1377, acc: 94.7746, loss_bbox: 0.1932, loss_mask: 0.2046, loss: 0.5852 2023-11-17 09:06:13,949 - mmdet - INFO - Epoch [34][1650/1833] lr: 5.563e-08, eta: 0:55:48, time: 0.882, data_time: 0.035, memory: 10998, loss_rpn_cls: 0.0185, loss_rpn_bbox: 0.0305, loss_cls: 0.1341, acc: 94.8727, loss_bbox: 0.1877, loss_mask: 0.2031, loss: 0.5739 2023-11-17 09:06:58,233 - mmdet - INFO - Epoch [34][1700/1833] lr: 5.563e-08, eta: 0:55:05, time: 0.886, data_time: 0.038, memory: 10998, loss_rpn_cls: 0.0188, loss_rpn_bbox: 0.0317, loss_cls: 0.1396, acc: 94.6744, loss_bbox: 0.1952, loss_mask: 0.2050, loss: 0.5905 2023-11-17 09:07:42,968 - mmdet - INFO - Epoch [34][1750/1833] lr: 5.563e-08, eta: 0:54:22, time: 0.895, data_time: 0.035, memory: 10998, loss_rpn_cls: 0.0187, loss_rpn_bbox: 0.0316, loss_cls: 0.1369, acc: 94.7328, loss_bbox: 0.1913, loss_mask: 0.2032, loss: 0.5816 2023-11-17 09:08:27,069 - mmdet - INFO - Epoch [34][1800/1833] lr: 5.563e-08, eta: 0:53:38, time: 0.882, data_time: 0.037, memory: 10998, loss_rpn_cls: 0.0189, loss_rpn_bbox: 0.0312, loss_cls: 0.1354, acc: 94.7940, loss_bbox: 0.1914, loss_mask: 0.2027, loss: 0.5795 2023-11-17 09:08:56,776 - mmdet - INFO - Saving checkpoint at 34 epochs 2023-11-17 09:09:27,117 - mmdet - INFO - Evaluating bbox... 2023-11-17 09:09:56,882 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.506 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.726 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.554 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.361 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.548 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.651 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.622 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.622 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.622 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.476 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.662 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.764 2023-11-17 09:09:56,885 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.595 | bicycle | 0.411 | car | 0.508 | | motorcycle | 0.504 | airplane | 0.703 | bus | 0.706 | | train | 0.722 | truck | 0.473 | boat | 0.354 | | traffic light | 0.316 | fire hydrant | 0.745 | stop sign | 0.708 | | parking meter | 0.534 | bench | 0.327 | bird | 0.437 | | cat | 0.750 | dog | 0.710 | horse | 0.654 | | sheep | 0.614 | cow | 0.644 | elephant | 0.705 | | bear | 0.804 | zebra | 0.692 | giraffe | 0.708 | | backpack | 0.247 | umbrella | 0.482 | handbag | 0.269 | | tie | 0.431 | suitcase | 0.505 | frisbee | 0.727 | | skis | 0.336 | snowboard | 0.473 | sports ball | 0.482 | | kite | 0.485 | baseball bat | 0.443 | baseball glove | 0.469 | | skateboard | 0.612 | surfboard | 0.508 | tennis racket | 0.571 | | bottle | 0.486 | wine glass | 0.442 | cup | 0.529 | | fork | 0.502 | knife | 0.346 | spoon | 0.316 | | bowl | 0.500 | banana | 0.303 | apple | 0.276 | | sandwich | 0.488 | orange | 0.364 | broccoli | 0.280 | | carrot | 0.271 | hot dog | 0.475 | pizza | 0.558 | | donut | 0.581 | cake | 0.476 | chair | 0.384 | | couch | 0.497 | potted plant | 0.362 | bed | 0.498 | | dining table | 0.336 | toilet | 0.674 | tv | 0.644 | | laptop | 0.705 | mouse | 0.682 | remote | 0.473 | | keyboard | 0.590 | cell phone | 0.483 | microwave | 0.691 | | oven | 0.424 | toaster | 0.460 | sink | 0.451 | | refrigerator | 0.700 | book | 0.215 | clock | 0.540 | | vase | 0.421 | scissors | 0.479 | teddy bear | 0.580 | | hair drier | 0.235 | toothbrush | 0.373 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-17 09:09:56,885 - mmdet - INFO - Evaluating segm... 2023-11-17 09:10:26,945 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.454 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.700 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.492 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.270 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.492 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.638 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.565 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.565 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.565 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.406 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.608 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.718 2023-11-17 09:10:26,947 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.521 | bicycle | 0.255 | car | 0.464 | | motorcycle | 0.416 | airplane | 0.569 | bus | 0.686 | | train | 0.705 | truck | 0.455 | boat | 0.330 | | traffic light | 0.308 | fire hydrant | 0.708 | stop sign | 0.668 | | parking meter | 0.534 | bench | 0.246 | bird | 0.356 | | cat | 0.742 | dog | 0.658 | horse | 0.491 | | sheep | 0.548 | cow | 0.556 | elephant | 0.641 | | bear | 0.782 | zebra | 0.595 | giraffe | 0.566 | | backpack | 0.244 | umbrella | 0.528 | handbag | 0.250 | | tie | 0.393 | suitcase | 0.522 | frisbee | 0.675 | | skis | 0.074 | snowboard | 0.321 | sports ball | 0.474 | | kite | 0.338 | baseball bat | 0.336 | baseball glove | 0.480 | | skateboard | 0.409 | surfboard | 0.417 | tennis racket | 0.596 | | bottle | 0.461 | wine glass | 0.406 | cup | 0.525 | | fork | 0.266 | knife | 0.235 | spoon | 0.221 | | bowl | 0.458 | banana | 0.259 | apple | 0.270 | | sandwich | 0.516 | orange | 0.355 | broccoli | 0.259 | | carrot | 0.234 | hot dog | 0.373 | pizza | 0.542 | | donut | 0.580 | cake | 0.487 | chair | 0.282 | | couch | 0.428 | potted plant | 0.306 | bed | 0.410 | | dining table | 0.204 | toilet | 0.657 | tv | 0.680 | | laptop | 0.690 | mouse | 0.640 | remote | 0.422 | | keyboard | 0.568 | cell phone | 0.458 | microwave | 0.706 | | oven | 0.387 | toaster | 0.498 | sink | 0.422 | | refrigerator | 0.712 | book | 0.159 | clock | 0.537 | | vase | 0.410 | scissors | 0.350 | teddy bear | 0.546 | | hair drier | 0.245 | toothbrush | 0.262 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-17 09:10:27,343 - mmdet - INFO - The previous best checkpoint /mnt/petrelfs/lizhiqi/DINO/detection/work_dirs/mask_rcnn_flash_internimage_b_fpn_3x_cocoo_0.4_0.9_4x16/best_bbox_mAP_epoch_30.pth was removed 2023-11-17 09:10:31,036 - mmdet - INFO - Now best checkpoint is saved as best_bbox_mAP_epoch_34.pth. 2023-11-17 09:10:31,036 - mmdet - INFO - Best bbox_mAP is 0.5057 at 34 epoch. 2023-11-17 09:10:31,036 - mmdet - INFO - Exp name: mask_rcnn_flash_internimage_b_fpn_3x_coco_0.4_0.9-4x16.py 2023-11-17 09:10:31,036 - mmdet - INFO - Epoch(val) [34][313] bbox_mAP: 0.5057, bbox_mAP_50: 0.7256, bbox_mAP_75: 0.5539, bbox_mAP_s: 0.3615, bbox_mAP_m: 0.5481, bbox_mAP_l: 0.6505, bbox_mAP_copypaste: 0.5057 0.7256 0.5539 0.3615 0.5481 0.6505, segm_mAP: 0.4536, segm_mAP_50: 0.6996, segm_mAP_75: 0.4916, segm_mAP_s: 0.2699, segm_mAP_m: 0.4918, segm_mAP_l: 0.6385, segm_mAP_copypaste: 0.4536 0.6996 0.4916 0.2699 0.4918 0.6385 2023-11-17 09:11:18,315 - mmdet - INFO - Epoch [35][50/1833] lr: 5.563e-08, eta: 0:52:24, time: 0.945, data_time: 0.094, memory: 10998, loss_rpn_cls: 0.0191, loss_rpn_bbox: 0.0316, loss_cls: 0.1382, acc: 94.7007, loss_bbox: 0.1925, loss_mask: 0.2049, loss: 0.5863 2023-11-17 09:12:02,682 - mmdet - INFO - Epoch [35][100/1833] lr: 5.563e-08, eta: 0:51:41, time: 0.887, data_time: 0.035, memory: 10998, loss_rpn_cls: 0.0186, loss_rpn_bbox: 0.0302, loss_cls: 0.1344, acc: 94.8775, loss_bbox: 0.1907, loss_mask: 0.2027, loss: 0.5766 2023-11-17 09:12:47,205 - mmdet - INFO - Epoch [35][150/1833] lr: 5.563e-08, eta: 0:50:58, time: 0.891, data_time: 0.035, memory: 10998, loss_rpn_cls: 0.0181, loss_rpn_bbox: 0.0301, loss_cls: 0.1367, acc: 94.7755, loss_bbox: 0.1926, loss_mask: 0.2035, loss: 0.5810 2023-11-17 09:13:31,315 - mmdet - INFO - Epoch [35][200/1833] lr: 5.563e-08, eta: 0:50:14, time: 0.882, data_time: 0.041, memory: 10998, loss_rpn_cls: 0.0186, loss_rpn_bbox: 0.0311, loss_cls: 0.1372, acc: 94.7679, loss_bbox: 0.1919, loss_mask: 0.2047, loss: 0.5835 2023-11-17 09:14:15,403 - mmdet - INFO - Epoch [35][250/1833] lr: 5.563e-08, eta: 0:49:31, time: 0.882, data_time: 0.034, memory: 10998, loss_rpn_cls: 0.0188, loss_rpn_bbox: 0.0306, loss_cls: 0.1354, acc: 94.8185, loss_bbox: 0.1914, loss_mask: 0.2048, loss: 0.5810 2023-11-17 09:14:59,943 - mmdet - INFO - Epoch [35][300/1833] lr: 5.563e-08, eta: 0:48:47, time: 0.891, data_time: 0.035, memory: 10998, loss_rpn_cls: 0.0190, loss_rpn_bbox: 0.0309, loss_cls: 0.1407, acc: 94.6379, loss_bbox: 0.1964, loss_mask: 0.2036, loss: 0.5905 2023-11-17 09:15:46,628 - mmdet - INFO - Epoch [35][350/1833] lr: 5.563e-08, eta: 0:48:04, time: 0.934, data_time: 0.033, memory: 10998, loss_rpn_cls: 0.0175, loss_rpn_bbox: 0.0311, loss_cls: 0.1364, acc: 94.7806, loss_bbox: 0.1935, loss_mask: 0.2043, loss: 0.5829 2023-11-17 09:16:30,390 - mmdet - INFO - Epoch [35][400/1833] lr: 5.563e-08, eta: 0:47:20, time: 0.875, data_time: 0.035, memory: 10998, loss_rpn_cls: 0.0194, loss_rpn_bbox: 0.0315, loss_cls: 0.1400, acc: 94.6878, loss_bbox: 0.1945, loss_mask: 0.2049, loss: 0.5903 2023-11-17 09:17:15,058 - mmdet - INFO - Epoch [35][450/1833] lr: 5.563e-08, eta: 0:46:37, time: 0.894, data_time: 0.039, memory: 10998, loss_rpn_cls: 0.0191, loss_rpn_bbox: 0.0319, loss_cls: 0.1392, acc: 94.6642, loss_bbox: 0.1944, loss_mask: 0.2026, loss: 0.5872 2023-11-17 09:17:59,338 - mmdet - INFO - Epoch [35][500/1833] lr: 5.563e-08, eta: 0:45:54, time: 0.886, data_time: 0.034, memory: 10998, loss_rpn_cls: 0.0185, loss_rpn_bbox: 0.0316, loss_cls: 0.1389, acc: 94.7037, loss_bbox: 0.1927, loss_mask: 0.2025, loss: 0.5841 2023-11-17 09:18:43,889 - mmdet - INFO - Epoch [35][550/1833] lr: 5.563e-08, eta: 0:45:10, time: 0.891, data_time: 0.032, memory: 10998, loss_rpn_cls: 0.0182, loss_rpn_bbox: 0.0300, loss_cls: 0.1336, acc: 94.9038, loss_bbox: 0.1872, loss_mask: 0.2005, loss: 0.5697 2023-11-17 09:19:28,365 - mmdet - INFO - Epoch [35][600/1833] lr: 5.563e-08, eta: 0:44:27, time: 0.889, data_time: 0.029, memory: 10998, loss_rpn_cls: 0.0195, loss_rpn_bbox: 0.0317, loss_cls: 0.1396, acc: 94.6573, loss_bbox: 0.1954, loss_mask: 0.2036, loss: 0.5898 2023-11-17 09:20:12,856 - mmdet - INFO - Epoch [35][650/1833] lr: 5.563e-08, eta: 0:43:43, time: 0.890, data_time: 0.032, memory: 10998, loss_rpn_cls: 0.0201, loss_rpn_bbox: 0.0316, loss_cls: 0.1408, acc: 94.6077, loss_bbox: 0.1954, loss_mask: 0.2045, loss: 0.5924 2023-11-17 09:21:00,106 - mmdet - INFO - Epoch [35][700/1833] lr: 5.563e-08, eta: 0:43:00, time: 0.945, data_time: 0.034, memory: 10998, loss_rpn_cls: 0.0187, loss_rpn_bbox: 0.0305, loss_cls: 0.1389, acc: 94.6685, loss_bbox: 0.1929, loss_mask: 0.2017, loss: 0.5826 2023-11-17 09:21:43,731 - mmdet - INFO - Epoch [35][750/1833] lr: 5.563e-08, eta: 0:42:16, time: 0.873, data_time: 0.032, memory: 10998, loss_rpn_cls: 0.0197, loss_rpn_bbox: 0.0310, loss_cls: 0.1383, acc: 94.7062, loss_bbox: 0.1955, loss_mask: 0.2046, loss: 0.5891 2023-11-17 09:22:27,444 - mmdet - INFO - Epoch [35][800/1833] lr: 5.563e-08, eta: 0:41:33, time: 0.874, data_time: 0.030, memory: 10998, loss_rpn_cls: 0.0182, loss_rpn_bbox: 0.0296, loss_cls: 0.1342, acc: 94.8828, loss_bbox: 0.1885, loss_mask: 0.1999, loss: 0.5704 2023-11-17 09:23:11,376 - mmdet - INFO - Epoch [35][850/1833] lr: 5.563e-08, eta: 0:40:49, time: 0.879, data_time: 0.035, memory: 10998, loss_rpn_cls: 0.0189, loss_rpn_bbox: 0.0310, loss_cls: 0.1354, acc: 94.8145, loss_bbox: 0.1914, loss_mask: 0.2015, loss: 0.5781 2023-11-17 09:23:55,361 - mmdet - INFO - Epoch [35][900/1833] lr: 5.563e-08, eta: 0:40:06, time: 0.880, data_time: 0.034, memory: 10998, loss_rpn_cls: 0.0180, loss_rpn_bbox: 0.0298, loss_cls: 0.1318, acc: 94.9425, loss_bbox: 0.1859, loss_mask: 0.2019, loss: 0.5675 2023-11-17 09:24:39,596 - mmdet - INFO - Epoch [35][950/1833] lr: 5.563e-08, eta: 0:39:22, time: 0.885, data_time: 0.035, memory: 10998, loss_rpn_cls: 0.0194, loss_rpn_bbox: 0.0309, loss_cls: 0.1393, acc: 94.6493, loss_bbox: 0.1961, loss_mask: 0.2032, loss: 0.5888 2023-11-17 09:25:23,651 - mmdet - INFO - Epoch [35][1000/1833] lr: 5.563e-08, eta: 0:38:39, time: 0.881, data_time: 0.032, memory: 10998, loss_rpn_cls: 0.0190, loss_rpn_bbox: 0.0297, loss_cls: 0.1365, acc: 94.7699, loss_bbox: 0.1917, loss_mask: 0.2042, loss: 0.5812 2023-11-17 09:26:08,241 - mmdet - INFO - Epoch [35][1050/1833] lr: 5.563e-08, eta: 0:37:56, time: 0.892, data_time: 0.037, memory: 10998, loss_rpn_cls: 0.0184, loss_rpn_bbox: 0.0294, loss_cls: 0.1360, acc: 94.8157, loss_bbox: 0.1894, loss_mask: 0.2034, loss: 0.5765 2023-11-17 09:26:52,544 - mmdet - INFO - Epoch [35][1100/1833] lr: 5.563e-08, eta: 0:37:12, time: 0.886, data_time: 0.035, memory: 10998, loss_rpn_cls: 0.0186, loss_rpn_bbox: 0.0310, loss_cls: 0.1388, acc: 94.7065, loss_bbox: 0.1977, loss_mask: 0.2037, loss: 0.5898 2023-11-17 09:27:37,292 - mmdet - INFO - Epoch [35][1150/1833] lr: 5.563e-08, eta: 0:36:29, time: 0.895, data_time: 0.036, memory: 10998, loss_rpn_cls: 0.0184, loss_rpn_bbox: 0.0309, loss_cls: 0.1375, acc: 94.7321, loss_bbox: 0.1949, loss_mask: 0.2035, loss: 0.5852 2023-11-17 09:28:21,465 - mmdet - INFO - Epoch [35][1200/1833] lr: 5.563e-08, eta: 0:35:45, time: 0.883, data_time: 0.033, memory: 10998, loss_rpn_cls: 0.0185, loss_rpn_bbox: 0.0302, loss_cls: 0.1395, acc: 94.6496, loss_bbox: 0.1941, loss_mask: 0.2032, loss: 0.5854 2023-11-17 09:29:08,939 - mmdet - INFO - Epoch [35][1250/1833] lr: 5.563e-08, eta: 0:35:02, time: 0.949, data_time: 0.035, memory: 10998, loss_rpn_cls: 0.0177, loss_rpn_bbox: 0.0302, loss_cls: 0.1351, acc: 94.7983, loss_bbox: 0.1901, loss_mask: 0.2007, loss: 0.5739 2023-11-17 09:29:53,123 - mmdet - INFO - Epoch [35][1300/1833] lr: 5.563e-08, eta: 0:34:18, time: 0.884, data_time: 0.028, memory: 10998, loss_rpn_cls: 0.0195, loss_rpn_bbox: 0.0311, loss_cls: 0.1361, acc: 94.8203, loss_bbox: 0.1928, loss_mask: 0.2037, loss: 0.5832 2023-11-17 09:30:38,035 - mmdet - INFO - Epoch [35][1350/1833] lr: 5.563e-08, eta: 0:33:35, time: 0.898, data_time: 0.035, memory: 10998, loss_rpn_cls: 0.0202, loss_rpn_bbox: 0.0315, loss_cls: 0.1387, acc: 94.6963, loss_bbox: 0.1941, loss_mask: 0.2024, loss: 0.5869 2023-11-17 09:31:21,973 - mmdet - INFO - Epoch [35][1400/1833] lr: 5.563e-08, eta: 0:32:51, time: 0.879, data_time: 0.038, memory: 10998, loss_rpn_cls: 0.0199, loss_rpn_bbox: 0.0312, loss_cls: 0.1402, acc: 94.6348, loss_bbox: 0.1948, loss_mask: 0.2037, loss: 0.5899 2023-11-17 09:32:06,508 - mmdet - INFO - Epoch [35][1450/1833] lr: 5.563e-08, eta: 0:32:08, time: 0.891, data_time: 0.037, memory: 10998, loss_rpn_cls: 0.0176, loss_rpn_bbox: 0.0299, loss_cls: 0.1359, acc: 94.8257, loss_bbox: 0.1925, loss_mask: 0.2029, loss: 0.5788 2023-11-17 09:32:50,954 - mmdet - INFO - Epoch [35][1500/1833] lr: 5.563e-08, eta: 0:31:24, time: 0.889, data_time: 0.033, memory: 10998, loss_rpn_cls: 0.0177, loss_rpn_bbox: 0.0303, loss_cls: 0.1346, acc: 94.8469, loss_bbox: 0.1904, loss_mask: 0.2031, loss: 0.5762 2023-11-17 09:33:34,988 - mmdet - INFO - Epoch [35][1550/1833] lr: 5.563e-08, eta: 0:30:41, time: 0.881, data_time: 0.038, memory: 10998, loss_rpn_cls: 0.0174, loss_rpn_bbox: 0.0297, loss_cls: 0.1338, acc: 94.8696, loss_bbox: 0.1866, loss_mask: 0.2003, loss: 0.5678 2023-11-17 09:34:19,071 - mmdet - INFO - Epoch [35][1600/1833] lr: 5.563e-08, eta: 0:29:57, time: 0.882, data_time: 0.034, memory: 10998, loss_rpn_cls: 0.0189, loss_rpn_bbox: 0.0307, loss_cls: 0.1375, acc: 94.7227, loss_bbox: 0.1933, loss_mask: 0.2053, loss: 0.5857 2023-11-17 09:35:02,970 - mmdet - INFO - Epoch [35][1650/1833] lr: 5.563e-08, eta: 0:29:14, time: 0.878, data_time: 0.033, memory: 10998, loss_rpn_cls: 0.0201, loss_rpn_bbox: 0.0312, loss_cls: 0.1376, acc: 94.7454, loss_bbox: 0.1937, loss_mask: 0.2048, loss: 0.5874 2023-11-17 09:35:47,030 - mmdet - INFO - Epoch [35][1700/1833] lr: 5.563e-08, eta: 0:28:30, time: 0.881, data_time: 0.032, memory: 10998, loss_rpn_cls: 0.0183, loss_rpn_bbox: 0.0310, loss_cls: 0.1357, acc: 94.8046, loss_bbox: 0.1927, loss_mask: 0.2017, loss: 0.5793 2023-11-17 09:36:31,099 - mmdet - INFO - Epoch [35][1750/1833] lr: 5.563e-08, eta: 0:27:47, time: 0.881, data_time: 0.031, memory: 10998, loss_rpn_cls: 0.0193, loss_rpn_bbox: 0.0305, loss_cls: 0.1364, acc: 94.8079, loss_bbox: 0.1914, loss_mask: 0.2022, loss: 0.5797 2023-11-17 09:37:15,041 - mmdet - INFO - Epoch [35][1800/1833] lr: 5.563e-08, eta: 0:27:03, time: 0.879, data_time: 0.033, memory: 10998, loss_rpn_cls: 0.0186, loss_rpn_bbox: 0.0294, loss_cls: 0.1348, acc: 94.8683, loss_bbox: 0.1872, loss_mask: 0.1999, loss: 0.5699 2023-11-17 09:37:44,669 - mmdet - INFO - Saving checkpoint at 35 epochs 2023-11-17 09:38:17,754 - mmdet - INFO - Evaluating bbox... 2023-11-17 09:38:45,433 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.506 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.726 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.555 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.361 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.549 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.651 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.622 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.622 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.622 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.476 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.661 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.764 2023-11-17 09:38:45,436 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.594 | bicycle | 0.413 | car | 0.508 | | motorcycle | 0.507 | airplane | 0.704 | bus | 0.706 | | train | 0.716 | truck | 0.471 | boat | 0.351 | | traffic light | 0.317 | fire hydrant | 0.750 | stop sign | 0.706 | | parking meter | 0.535 | bench | 0.328 | bird | 0.434 | | cat | 0.754 | dog | 0.709 | horse | 0.655 | | sheep | 0.613 | cow | 0.647 | elephant | 0.709 | | bear | 0.802 | zebra | 0.694 | giraffe | 0.709 | | backpack | 0.249 | umbrella | 0.483 | handbag | 0.268 | | tie | 0.436 | suitcase | 0.504 | frisbee | 0.731 | | skis | 0.338 | snowboard | 0.476 | sports ball | 0.486 | | kite | 0.486 | baseball bat | 0.439 | baseball glove | 0.469 | | skateboard | 0.611 | surfboard | 0.505 | tennis racket | 0.575 | | bottle | 0.485 | wine glass | 0.444 | cup | 0.528 | | fork | 0.496 | knife | 0.343 | spoon | 0.316 | | bowl | 0.499 | banana | 0.301 | apple | 0.278 | | sandwich | 0.490 | orange | 0.363 | broccoli | 0.279 | | carrot | 0.269 | hot dog | 0.477 | pizza | 0.560 | | donut | 0.583 | cake | 0.472 | chair | 0.384 | | couch | 0.499 | potted plant | 0.360 | bed | 0.498 | | dining table | 0.337 | toilet | 0.673 | tv | 0.647 | | laptop | 0.704 | mouse | 0.680 | remote | 0.473 | | keyboard | 0.583 | cell phone | 0.483 | microwave | 0.694 | | oven | 0.426 | toaster | 0.475 | sink | 0.451 | | refrigerator | 0.700 | book | 0.214 | clock | 0.537 | | vase | 0.424 | scissors | 0.479 | teddy bear | 0.584 | | hair drier | 0.235 | toothbrush | 0.375 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-17 09:38:45,436 - mmdet - INFO - Evaluating segm... 2023-11-17 09:39:18,246 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.454 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.700 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.493 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.270 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.492 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.639 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.565 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.565 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.565 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.408 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.607 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.717 2023-11-17 09:39:18,249 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.521 | bicycle | 0.258 | car | 0.465 | | motorcycle | 0.419 | airplane | 0.571 | bus | 0.686 | | train | 0.704 | truck | 0.456 | boat | 0.330 | | traffic light | 0.310 | fire hydrant | 0.706 | stop sign | 0.667 | | parking meter | 0.534 | bench | 0.247 | bird | 0.356 | | cat | 0.744 | dog | 0.657 | horse | 0.493 | | sheep | 0.546 | cow | 0.557 | elephant | 0.642 | | bear | 0.782 | zebra | 0.597 | giraffe | 0.567 | | backpack | 0.244 | umbrella | 0.530 | handbag | 0.252 | | tie | 0.397 | suitcase | 0.524 | frisbee | 0.678 | | skis | 0.071 | snowboard | 0.322 | sports ball | 0.477 | | kite | 0.335 | baseball bat | 0.336 | baseball glove | 0.480 | | skateboard | 0.409 | surfboard | 0.416 | tennis racket | 0.599 | | bottle | 0.461 | wine glass | 0.405 | cup | 0.526 | | fork | 0.264 | knife | 0.233 | spoon | 0.222 | | bowl | 0.459 | banana | 0.258 | apple | 0.275 | | sandwich | 0.518 | orange | 0.354 | broccoli | 0.260 | | carrot | 0.236 | hot dog | 0.373 | pizza | 0.546 | | donut | 0.579 | cake | 0.483 | chair | 0.281 | | couch | 0.428 | potted plant | 0.308 | bed | 0.415 | | dining table | 0.206 | toilet | 0.655 | tv | 0.682 | | laptop | 0.690 | mouse | 0.642 | remote | 0.423 | | keyboard | 0.570 | cell phone | 0.458 | microwave | 0.710 | | oven | 0.385 | toaster | 0.512 | sink | 0.425 | | refrigerator | 0.712 | book | 0.160 | clock | 0.537 | | vase | 0.413 | scissors | 0.342 | teddy bear | 0.548 | | hair drier | 0.244 | toothbrush | 0.264 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-17 09:39:18,704 - mmdet - INFO - The previous best checkpoint /mnt/petrelfs/lizhiqi/DINO/detection/work_dirs/mask_rcnn_flash_internimage_b_fpn_3x_cocoo_0.4_0.9_4x16/best_bbox_mAP_epoch_34.pth was removed 2023-11-17 09:39:22,458 - mmdet - INFO - Now best checkpoint is saved as best_bbox_mAP_epoch_35.pth. 2023-11-17 09:39:22,459 - mmdet - INFO - Best bbox_mAP is 0.5061 at 35 epoch. 2023-11-17 09:39:22,459 - mmdet - INFO - Exp name: mask_rcnn_flash_internimage_b_fpn_3x_coco_0.4_0.9-4x16.py 2023-11-17 09:39:22,459 - mmdet - INFO - Epoch(val) [35][313] bbox_mAP: 0.5061, bbox_mAP_50: 0.7256, bbox_mAP_75: 0.5545, bbox_mAP_s: 0.3612, bbox_mAP_m: 0.5486, bbox_mAP_l: 0.6506, bbox_mAP_copypaste: 0.5061 0.7256 0.5545 0.3612 0.5486 0.6506, segm_mAP: 0.4543, segm_mAP_50: 0.7002, segm_mAP_75: 0.4926, segm_mAP_s: 0.2704, segm_mAP_m: 0.4915, segm_mAP_l: 0.6385, segm_mAP_copypaste: 0.4543 0.7002 0.4926 0.2704 0.4915 0.6385 2023-11-17 09:40:09,611 - mmdet - INFO - Epoch [36][50/1833] lr: 5.563e-08, eta: 0:25:50, time: 0.943, data_time: 0.095, memory: 10998, loss_rpn_cls: 0.0182, loss_rpn_bbox: 0.0309, loss_cls: 0.1377, acc: 94.7430, loss_bbox: 0.1915, loss_mask: 0.2034, loss: 0.5818 2023-11-17 09:40:53,901 - mmdet - INFO - Epoch [36][100/1833] lr: 5.563e-08, eta: 0:25:07, time: 0.886, data_time: 0.041, memory: 10998, loss_rpn_cls: 0.0188, loss_rpn_bbox: 0.0306, loss_cls: 0.1370, acc: 94.7999, loss_bbox: 0.1887, loss_mask: 0.2032, loss: 0.5783 2023-11-17 09:41:37,959 - mmdet - INFO - Epoch [36][150/1833] lr: 5.563e-08, eta: 0:24:24, time: 0.881, data_time: 0.036, memory: 10998, loss_rpn_cls: 0.0191, loss_rpn_bbox: 0.0304, loss_cls: 0.1366, acc: 94.7640, loss_bbox: 0.1916, loss_mask: 0.2029, loss: 0.5806 2023-11-17 09:42:21,835 - mmdet - INFO - Epoch [36][200/1833] lr: 5.563e-08, eta: 0:23:40, time: 0.877, data_time: 0.036, memory: 10998, loss_rpn_cls: 0.0182, loss_rpn_bbox: 0.0288, loss_cls: 0.1339, acc: 94.9051, loss_bbox: 0.1879, loss_mask: 0.2004, loss: 0.5693 2023-11-17 09:43:08,892 - mmdet - INFO - Epoch [36][250/1833] lr: 5.563e-08, eta: 0:22:57, time: 0.941, data_time: 0.038, memory: 10998, loss_rpn_cls: 0.0178, loss_rpn_bbox: 0.0294, loss_cls: 0.1337, acc: 94.8835, loss_bbox: 0.1874, loss_mask: 0.1981, loss: 0.5664 2023-11-17 09:43:52,931 - mmdet - INFO - Epoch [36][300/1833] lr: 5.563e-08, eta: 0:22:13, time: 0.881, data_time: 0.039, memory: 10998, loss_rpn_cls: 0.0190, loss_rpn_bbox: 0.0295, loss_cls: 0.1354, acc: 94.8351, loss_bbox: 0.1889, loss_mask: 0.2019, loss: 0.5747 2023-11-17 09:44:37,408 - mmdet - INFO - Epoch [36][350/1833] lr: 5.563e-08, eta: 0:21:30, time: 0.889, data_time: 0.035, memory: 10998, loss_rpn_cls: 0.0194, loss_rpn_bbox: 0.0314, loss_cls: 0.1418, acc: 94.6243, loss_bbox: 0.1962, loss_mask: 0.2040, loss: 0.5927 2023-11-17 09:45:21,140 - mmdet - INFO - Epoch [36][400/1833] lr: 5.563e-08, eta: 0:20:46, time: 0.875, data_time: 0.032, memory: 10998, loss_rpn_cls: 0.0181, loss_rpn_bbox: 0.0302, loss_cls: 0.1329, acc: 94.9179, loss_bbox: 0.1875, loss_mask: 0.2009, loss: 0.5696 2023-11-17 09:46:05,704 - mmdet - INFO - Epoch [36][450/1833] lr: 5.563e-08, eta: 0:20:03, time: 0.891, data_time: 0.040, memory: 10998, loss_rpn_cls: 0.0186, loss_rpn_bbox: 0.0304, loss_cls: 0.1363, acc: 94.7487, loss_bbox: 0.1910, loss_mask: 0.2032, loss: 0.5795 2023-11-17 09:46:49,626 - mmdet - INFO - Epoch [36][500/1833] lr: 5.563e-08, eta: 0:19:19, time: 0.878, data_time: 0.034, memory: 10998, loss_rpn_cls: 0.0179, loss_rpn_bbox: 0.0299, loss_cls: 0.1356, acc: 94.8590, loss_bbox: 0.1901, loss_mask: 0.2016, loss: 0.5752 2023-11-17 09:47:33,746 - mmdet - INFO - Epoch [36][550/1833] lr: 5.563e-08, eta: 0:18:36, time: 0.882, data_time: 0.035, memory: 10998, loss_rpn_cls: 0.0184, loss_rpn_bbox: 0.0302, loss_cls: 0.1375, acc: 94.7420, loss_bbox: 0.1917, loss_mask: 0.2006, loss: 0.5784 2023-11-17 09:48:17,549 - mmdet - INFO - Epoch [36][600/1833] lr: 5.563e-08, eta: 0:17:52, time: 0.876, data_time: 0.040, memory: 10998, loss_rpn_cls: 0.0192, loss_rpn_bbox: 0.0308, loss_cls: 0.1384, acc: 94.7111, loss_bbox: 0.1955, loss_mask: 0.2068, loss: 0.5906 2023-11-17 09:49:01,899 - mmdet - INFO - Epoch [36][650/1833] lr: 5.563e-08, eta: 0:17:09, time: 0.887, data_time: 0.036, memory: 10998, loss_rpn_cls: 0.0178, loss_rpn_bbox: 0.0294, loss_cls: 0.1345, acc: 94.8846, loss_bbox: 0.1898, loss_mask: 0.2020, loss: 0.5735 2023-11-17 09:49:46,302 - mmdet - INFO - Epoch [36][700/1833] lr: 5.563e-08, eta: 0:16:25, time: 0.888, data_time: 0.035, memory: 10998, loss_rpn_cls: 0.0197, loss_rpn_bbox: 0.0313, loss_cls: 0.1372, acc: 94.7872, loss_bbox: 0.1923, loss_mask: 0.2038, loss: 0.5842 2023-11-17 09:50:30,405 - mmdet - INFO - Epoch [36][750/1833] lr: 5.563e-08, eta: 0:15:42, time: 0.882, data_time: 0.039, memory: 10998, loss_rpn_cls: 0.0185, loss_rpn_bbox: 0.0308, loss_cls: 0.1398, acc: 94.6801, loss_bbox: 0.1956, loss_mask: 0.2012, loss: 0.5859 2023-11-17 09:51:14,099 - mmdet - INFO - Epoch [36][800/1833] lr: 5.563e-08, eta: 0:14:58, time: 0.874, data_time: 0.040, memory: 10998, loss_rpn_cls: 0.0190, loss_rpn_bbox: 0.0306, loss_cls: 0.1378, acc: 94.7441, loss_bbox: 0.1926, loss_mask: 0.2050, loss: 0.5849 2023-11-17 09:51:58,030 - mmdet - INFO - Epoch [36][850/1833] lr: 5.563e-08, eta: 0:14:15, time: 0.879, data_time: 0.032, memory: 10998, loss_rpn_cls: 0.0183, loss_rpn_bbox: 0.0306, loss_cls: 0.1373, acc: 94.7338, loss_bbox: 0.1944, loss_mask: 0.2040, loss: 0.5846 2023-11-17 09:52:41,727 - mmdet - INFO - Epoch [36][900/1833] lr: 5.563e-08, eta: 0:13:31, time: 0.874, data_time: 0.038, memory: 10998, loss_rpn_cls: 0.0185, loss_rpn_bbox: 0.0306, loss_cls: 0.1392, acc: 94.6833, loss_bbox: 0.1940, loss_mask: 0.2015, loss: 0.5838 2023-11-17 09:53:25,566 - mmdet - INFO - Epoch [36][950/1833] lr: 5.563e-08, eta: 0:12:48, time: 0.877, data_time: 0.037, memory: 10998, loss_rpn_cls: 0.0185, loss_rpn_bbox: 0.0301, loss_cls: 0.1358, acc: 94.8137, loss_bbox: 0.1899, loss_mask: 0.2027, loss: 0.5770 2023-11-17 09:54:09,929 - mmdet - INFO - Epoch [36][1000/1833] lr: 5.563e-08, eta: 0:12:04, time: 0.887, data_time: 0.036, memory: 10998, loss_rpn_cls: 0.0198, loss_rpn_bbox: 0.0317, loss_cls: 0.1383, acc: 94.7284, loss_bbox: 0.1928, loss_mask: 0.2065, loss: 0.5891 2023-11-17 09:54:53,952 - mmdet - INFO - Epoch [36][1050/1833] lr: 5.563e-08, eta: 0:11:21, time: 0.881, data_time: 0.032, memory: 10998, loss_rpn_cls: 0.0190, loss_rpn_bbox: 0.0313, loss_cls: 0.1387, acc: 94.7217, loss_bbox: 0.1928, loss_mask: 0.2033, loss: 0.5852 2023-11-17 09:55:37,850 - mmdet - INFO - Epoch [36][1100/1833] lr: 5.563e-08, eta: 0:10:37, time: 0.877, data_time: 0.039, memory: 10998, loss_rpn_cls: 0.0190, loss_rpn_bbox: 0.0312, loss_cls: 0.1395, acc: 94.6710, loss_bbox: 0.1964, loss_mask: 0.2064, loss: 0.5926 2023-11-17 09:56:21,874 - mmdet - INFO - Epoch [36][1150/1833] lr: 5.563e-08, eta: 0:09:54, time: 0.881, data_time: 0.032, memory: 10998, loss_rpn_cls: 0.0186, loss_rpn_bbox: 0.0302, loss_cls: 0.1370, acc: 94.7610, loss_bbox: 0.1922, loss_mask: 0.2030, loss: 0.5811 2023-11-17 09:57:05,820 - mmdet - INFO - Epoch [36][1200/1833] lr: 5.563e-08, eta: 0:09:10, time: 0.879, data_time: 0.034, memory: 10998, loss_rpn_cls: 0.0169, loss_rpn_bbox: 0.0286, loss_cls: 0.1302, acc: 95.0295, loss_bbox: 0.1826, loss_mask: 0.1993, loss: 0.5575 2023-11-17 09:57:49,869 - mmdet - INFO - Epoch [36][1250/1833] lr: 5.563e-08, eta: 0:08:27, time: 0.881, data_time: 0.037, memory: 10998, loss_rpn_cls: 0.0185, loss_rpn_bbox: 0.0301, loss_cls: 0.1330, acc: 94.9211, loss_bbox: 0.1881, loss_mask: 0.2019, loss: 0.5715 2023-11-17 09:58:33,868 - mmdet - INFO - Epoch [36][1300/1833] lr: 5.563e-08, eta: 0:07:43, time: 0.880, data_time: 0.039, memory: 10998, loss_rpn_cls: 0.0183, loss_rpn_bbox: 0.0305, loss_cls: 0.1384, acc: 94.7354, loss_bbox: 0.1918, loss_mask: 0.2015, loss: 0.5806 2023-11-17 09:59:18,096 - mmdet - INFO - Epoch [36][1350/1833] lr: 5.563e-08, eta: 0:07:00, time: 0.885, data_time: 0.034, memory: 10998, loss_rpn_cls: 0.0191, loss_rpn_bbox: 0.0308, loss_cls: 0.1367, acc: 94.7685, loss_bbox: 0.1942, loss_mask: 0.2042, loss: 0.5850 2023-11-17 10:00:02,565 - mmdet - INFO - Epoch [36][1400/1833] lr: 5.563e-08, eta: 0:06:16, time: 0.889, data_time: 0.039, memory: 10998, loss_rpn_cls: 0.0196, loss_rpn_bbox: 0.0318, loss_cls: 0.1400, acc: 94.6534, loss_bbox: 0.1950, loss_mask: 0.2027, loss: 0.5891 2023-11-17 10:00:46,623 - mmdet - INFO - Epoch [36][1450/1833] lr: 5.563e-08, eta: 0:05:33, time: 0.881, data_time: 0.037, memory: 10998, loss_rpn_cls: 0.0188, loss_rpn_bbox: 0.0311, loss_cls: 0.1381, acc: 94.6811, loss_bbox: 0.1952, loss_mask: 0.2066, loss: 0.5898 2023-11-17 10:01:30,883 - mmdet - INFO - Epoch [36][1500/1833] lr: 5.563e-08, eta: 0:04:49, time: 0.885, data_time: 0.037, memory: 10998, loss_rpn_cls: 0.0195, loss_rpn_bbox: 0.0304, loss_cls: 0.1383, acc: 94.6721, loss_bbox: 0.1935, loss_mask: 0.2041, loss: 0.5858 2023-11-17 10:02:15,258 - mmdet - INFO - Epoch [36][1550/1833] lr: 5.563e-08, eta: 0:04:06, time: 0.888, data_time: 0.035, memory: 10998, loss_rpn_cls: 0.0186, loss_rpn_bbox: 0.0314, loss_cls: 0.1392, acc: 94.6637, loss_bbox: 0.1955, loss_mask: 0.2049, loss: 0.5896 2023-11-17 10:02:59,568 - mmdet - INFO - Epoch [36][1600/1833] lr: 5.563e-08, eta: 0:03:22, time: 0.886, data_time: 0.036, memory: 10998, loss_rpn_cls: 0.0184, loss_rpn_bbox: 0.0312, loss_cls: 0.1363, acc: 94.7360, loss_bbox: 0.1923, loss_mask: 0.2032, loss: 0.5813 2023-11-17 10:03:43,392 - mmdet - INFO - Epoch [36][1650/1833] lr: 5.563e-08, eta: 0:02:39, time: 0.876, data_time: 0.035, memory: 10998, loss_rpn_cls: 0.0181, loss_rpn_bbox: 0.0306, loss_cls: 0.1349, acc: 94.8011, loss_bbox: 0.1920, loss_mask: 0.2046, loss: 0.5801 2023-11-17 10:04:26,587 - mmdet - INFO - Epoch [36][1700/1833] lr: 5.563e-08, eta: 0:01:55, time: 0.864, data_time: 0.042, memory: 10998, loss_rpn_cls: 0.0190, loss_rpn_bbox: 0.0308, loss_cls: 0.1385, acc: 94.6876, loss_bbox: 0.1918, loss_mask: 0.2017, loss: 0.5818 2023-11-17 10:05:10,643 - mmdet - INFO - Epoch [36][1750/1833] lr: 5.563e-08, eta: 0:01:12, time: 0.881, data_time: 0.041, memory: 10998, loss_rpn_cls: 0.0203, loss_rpn_bbox: 0.0321, loss_cls: 0.1427, acc: 94.5535, loss_bbox: 0.1996, loss_mask: 0.2056, loss: 0.6003 2023-11-17 10:05:54,923 - mmdet - INFO - Epoch [36][1800/1833] lr: 5.563e-08, eta: 0:00:28, time: 0.886, data_time: 0.037, memory: 10998, loss_rpn_cls: 0.0202, loss_rpn_bbox: 0.0320, loss_cls: 0.1409, acc: 94.6458, loss_bbox: 0.1960, loss_mask: 0.2055, loss: 0.5946 2023-11-17 10:06:24,313 - mmdet - INFO - Saving checkpoint at 36 epochs 2023-11-17 10:06:54,711 - mmdet - INFO - Evaluating bbox... 2023-11-17 10:07:24,375 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.505 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.726 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.552 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.361 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.549 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.649 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.621 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.621 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.621 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.477 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.662 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.761 2023-11-17 10:07:24,378 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.594 | bicycle | 0.413 | car | 0.509 | | motorcycle | 0.509 | airplane | 0.693 | bus | 0.704 | | train | 0.720 | truck | 0.469 | boat | 0.352 | | traffic light | 0.316 | fire hydrant | 0.749 | stop sign | 0.709 | | parking meter | 0.540 | bench | 0.327 | bird | 0.436 | | cat | 0.752 | dog | 0.712 | horse | 0.652 | | sheep | 0.615 | cow | 0.646 | elephant | 0.707 | | bear | 0.801 | zebra | 0.691 | giraffe | 0.713 | | backpack | 0.247 | umbrella | 0.484 | handbag | 0.268 | | tie | 0.437 | suitcase | 0.502 | frisbee | 0.728 | | skis | 0.339 | snowboard | 0.477 | sports ball | 0.486 | | kite | 0.485 | baseball bat | 0.444 | baseball glove | 0.470 | | skateboard | 0.614 | surfboard | 0.509 | tennis racket | 0.572 | | bottle | 0.485 | wine glass | 0.445 | cup | 0.528 | | fork | 0.497 | knife | 0.344 | spoon | 0.311 | | bowl | 0.498 | banana | 0.300 | apple | 0.275 | | sandwich | 0.484 | orange | 0.364 | broccoli | 0.281 | | carrot | 0.268 | hot dog | 0.473 | pizza | 0.563 | | donut | 0.580 | cake | 0.472 | chair | 0.384 | | couch | 0.499 | potted plant | 0.358 | bed | 0.499 | | dining table | 0.336 | toilet | 0.670 | tv | 0.646 | | laptop | 0.708 | mouse | 0.680 | remote | 0.477 | | keyboard | 0.585 | cell phone | 0.483 | microwave | 0.691 | | oven | 0.428 | toaster | 0.461 | sink | 0.451 | | refrigerator | 0.699 | book | 0.216 | clock | 0.543 | | vase | 0.419 | scissors | 0.471 | teddy bear | 0.582 | | hair drier | 0.213 | toothbrush | 0.372 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-17 10:07:24,378 - mmdet - INFO - Evaluating segm... 2023-11-17 10:07:54,374 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.454 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.699 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.492 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.271 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.492 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.636 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.565 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.565 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.565 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.408 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.608 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.717 2023-11-17 10:07:54,377 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.521 | bicycle | 0.257 | car | 0.465 | | motorcycle | 0.419 | airplane | 0.564 | bus | 0.687 | | train | 0.708 | truck | 0.454 | boat | 0.331 | | traffic light | 0.310 | fire hydrant | 0.710 | stop sign | 0.670 | | parking meter | 0.538 | bench | 0.246 | bird | 0.359 | | cat | 0.743 | dog | 0.657 | horse | 0.492 | | sheep | 0.550 | cow | 0.556 | elephant | 0.644 | | bear | 0.783 | zebra | 0.595 | giraffe | 0.568 | | backpack | 0.242 | umbrella | 0.529 | handbag | 0.251 | | tie | 0.395 | suitcase | 0.525 | frisbee | 0.674 | | skis | 0.070 | snowboard | 0.326 | sports ball | 0.477 | | kite | 0.337 | baseball bat | 0.335 | baseball glove | 0.482 | | skateboard | 0.413 | surfboard | 0.418 | tennis racket | 0.600 | | bottle | 0.460 | wine glass | 0.406 | cup | 0.526 | | fork | 0.266 | knife | 0.233 | spoon | 0.222 | | bowl | 0.458 | banana | 0.260 | apple | 0.272 | | sandwich | 0.512 | orange | 0.355 | broccoli | 0.260 | | carrot | 0.234 | hot dog | 0.375 | pizza | 0.545 | | donut | 0.576 | cake | 0.486 | chair | 0.282 | | couch | 0.428 | potted plant | 0.308 | bed | 0.409 | | dining table | 0.207 | toilet | 0.654 | tv | 0.680 | | laptop | 0.692 | mouse | 0.642 | remote | 0.426 | | keyboard | 0.570 | cell phone | 0.460 | microwave | 0.703 | | oven | 0.387 | toaster | 0.512 | sink | 0.423 | | refrigerator | 0.715 | book | 0.160 | clock | 0.538 | | vase | 0.412 | scissors | 0.347 | teddy bear | 0.549 | | hair drier | 0.215 | toothbrush | 0.261 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-17 10:07:54,741 - mmdet - INFO - Exp name: mask_rcnn_flash_internimage_b_fpn_3x_coco_0.4_0.9-4x16.py 2023-11-17 10:07:54,741 - mmdet - INFO - Epoch(val) [36][313] bbox_mAP: 0.5054, bbox_mAP_50: 0.7260, bbox_mAP_75: 0.5524, bbox_mAP_s: 0.3614, bbox_mAP_m: 0.5489, bbox_mAP_l: 0.6486, bbox_mAP_copypaste: 0.5054 0.7260 0.5524 0.3614 0.5489 0.6486, segm_mAP: 0.4541, segm_mAP_50: 0.6992, segm_mAP_75: 0.4921, segm_mAP_s: 0.2706, segm_mAP_m: 0.4921, segm_mAP_l: 0.6363, segm_mAP_copypaste: 0.4541 0.6992 0.4921 0.2706 0.4921 0.6363