2023-11-15 13:34:27,066 - 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+a85a748 ------------------------------------------------------------ 2023-11-15 13:34:29,682 - mmdet - INFO - Distributed training: True 2023-11-15 13:34:32,268 - mmdet - INFO - Config: model = dict( type='MaskRCNN', backbone=dict( type='Flash_InternImage_nsmx', core_op='FlashDCNv3', channels=80, depths=[4, 4, 21, 4], groups=[5, 10, 20, 40], mlp_ratio=4.0, drop_path_rate=0.4, norm_layer='LN', layer_scale=1.0, offset_scale=1.0, 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_s_1k_224_nosmx_dw/ckpt_epoch_ema_best.pth' )), neck=dict( type='FPN_vitdet', in_channels=[80, 160, 320, 640], 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=8, 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=1.0, depths=[4, 4, 21, 4])) 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_s_1k_224_nosmx_dw/ckpt_epoch_ema_best.pth' work_dir = './work_dirs/mask_rcnn_flash_internimage_s_fpn_3x_coco_0.4' auto_resume = False gpu_ids = range(0, 8) 2023-11-15 13:34:36,778 - mmdet - INFO - Set random seed to 1228021307, deterministic: False 2023-11-15 13:34:36,778 - mmdet - INFO - using core type: FlashDCNv3 2023-11-15 13:34:36,778 - mmdet - INFO - using activation layer: GELU 2023-11-15 13:34:36,778 - mmdet - INFO - using main norm layer: LN 2023-11-15 13:34:36,778 - mmdet - INFO - using dpr: linear, 0.4 2023-11-15 13:34:36,778 - mmdet - INFO - level2_post_norm: False 2023-11-15 13:34:36,778 - mmdet - INFO - level2_post_norm_block_ids: None 2023-11-15 13:34:36,778 - mmdet - INFO - res_post_norm: False 2023-11-15 13:34:37,810 - mmdet - INFO - load checkpoint from local path: /mnt/petrelfs/share_data/xiongyuwen/checkpoint/flash_internimage_s_1k_224_nosmx_dw/ckpt_epoch_ema_best.pth 2023-11-15 13:34:39,525 - 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']) 2023-11-15 13:34:39,551 - mmdet - INFO - initialize FPN_vitdet with init_cfg {'type': 'Xavier', 'layer': 'Conv2d', 'distribution': 'uniform'} 2023-11-15 13:34:39,567 - mmdet - INFO - initialize RPNHead with init_cfg {'type': 'Normal', 'layer': 'Conv2d', 'std': 0.01} 2023-11-15 13:34:39,570 - 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([40, 3, 3, 3]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.patch_embed.conv1.bias - torch.Size([40]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.patch_embed.norm1.1.weight - torch.Size([40]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.patch_embed.norm1.1.bias - torch.Size([40]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.patch_embed.conv2.weight - torch.Size([80, 40, 3, 3]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.patch_embed.conv2.bias - torch.Size([80]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.patch_embed.norm2.1.weight - torch.Size([80]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.patch_embed.norm2.1.bias - torch.Size([80]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.0.gamma1 - torch.Size([80]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.0.gamma2 - torch.Size([80]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.0.norm1.0.weight - torch.Size([80]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.0.norm1.0.bias - torch.Size([80]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.0.dcn.offset_mask_dw.weight - torch.Size([80, 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([80]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.0.dcn.offset_mask.weight - torch.Size([135, 80]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.0.dcn.offset_mask.bias - torch.Size([135]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.0.dcn.value_proj.weight - torch.Size([80, 80]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.0.dcn.value_proj.bias - torch.Size([80]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.0.dcn.output_proj.weight - torch.Size([80, 80]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.0.norm2.0.weight - torch.Size([80]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.0.norm2.0.bias - torch.Size([80]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.0.mlp.fc1.weight - torch.Size([320, 80]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.0.mlp.fc1.bias - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.0.mlp.fc2.weight - torch.Size([80, 320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.1.gamma1 - torch.Size([80]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.1.gamma2 - torch.Size([80]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.1.norm1.0.weight - torch.Size([80]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.1.norm1.0.bias - torch.Size([80]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.1.dcn.offset_mask_dw.weight - torch.Size([80, 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([80]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.1.dcn.offset_mask.weight - torch.Size([135, 80]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.1.dcn.offset_mask.bias - torch.Size([135]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.1.dcn.value_proj.weight - torch.Size([80, 80]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.1.dcn.value_proj.bias - torch.Size([80]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.1.dcn.output_proj.weight - torch.Size([80, 80]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.1.norm2.0.weight - torch.Size([80]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.1.norm2.0.bias - torch.Size([80]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.1.mlp.fc1.weight - torch.Size([320, 80]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.1.mlp.fc1.bias - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.1.mlp.fc2.weight - torch.Size([80, 320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.2.gamma1 - torch.Size([80]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.2.gamma2 - torch.Size([80]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.2.norm1.0.weight - torch.Size([80]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.2.norm1.0.bias - torch.Size([80]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.2.dcn.offset_mask_dw.weight - torch.Size([80, 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([80]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.2.dcn.offset_mask.weight - torch.Size([135, 80]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.2.dcn.offset_mask.bias - torch.Size([135]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.2.dcn.value_proj.weight - torch.Size([80, 80]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.2.dcn.value_proj.bias - torch.Size([80]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.2.dcn.output_proj.weight - torch.Size([80, 80]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.2.norm2.0.weight - torch.Size([80]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.2.norm2.0.bias - torch.Size([80]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.2.mlp.fc1.weight - torch.Size([320, 80]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.2.mlp.fc1.bias - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.2.mlp.fc2.weight - torch.Size([80, 320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.3.gamma1 - torch.Size([80]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.3.gamma2 - torch.Size([80]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.3.norm1.0.weight - torch.Size([80]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.3.norm1.0.bias - torch.Size([80]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.3.dcn.offset_mask_dw.weight - torch.Size([80, 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([80]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.3.dcn.offset_mask.weight - torch.Size([135, 80]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.3.dcn.offset_mask.bias - torch.Size([135]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.3.dcn.value_proj.weight - torch.Size([80, 80]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.3.dcn.value_proj.bias - torch.Size([80]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.3.dcn.output_proj.weight - torch.Size([80, 80]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.3.norm2.0.weight - torch.Size([80]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.3.norm2.0.bias - torch.Size([80]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.3.mlp.fc1.weight - torch.Size([320, 80]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.3.mlp.fc1.bias - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.blocks.3.mlp.fc2.weight - torch.Size([80, 320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.downsample.conv.weight - torch.Size([160, 80, 3, 3]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.downsample.norm.1.weight - torch.Size([160]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.0.downsample.norm.1.bias - torch.Size([160]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.0.gamma1 - torch.Size([160]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.0.gamma2 - torch.Size([160]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.0.norm1.0.weight - torch.Size([160]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.0.norm1.0.bias - torch.Size([160]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.0.dcn.offset_mask_dw.weight - torch.Size([160, 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([160]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.0.dcn.offset_mask.weight - torch.Size([270, 160]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.0.dcn.offset_mask.bias - torch.Size([270]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.0.dcn.value_proj.weight - torch.Size([160, 160]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.0.dcn.value_proj.bias - torch.Size([160]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.0.dcn.output_proj.weight - torch.Size([160, 160]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.0.norm2.0.weight - torch.Size([160]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.0.norm2.0.bias - torch.Size([160]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.0.mlp.fc1.weight - torch.Size([640, 160]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.0.mlp.fc1.bias - torch.Size([640]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.0.mlp.fc2.weight - torch.Size([160, 640]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.1.gamma1 - torch.Size([160]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.1.gamma2 - torch.Size([160]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.1.norm1.0.weight - torch.Size([160]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.1.norm1.0.bias - torch.Size([160]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.1.dcn.offset_mask_dw.weight - torch.Size([160, 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([160]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.1.dcn.offset_mask.weight - torch.Size([270, 160]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.1.dcn.offset_mask.bias - torch.Size([270]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.1.dcn.value_proj.weight - torch.Size([160, 160]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.1.dcn.value_proj.bias - torch.Size([160]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.1.dcn.output_proj.weight - torch.Size([160, 160]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.1.norm2.0.weight - torch.Size([160]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.1.norm2.0.bias - torch.Size([160]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.1.mlp.fc1.weight - torch.Size([640, 160]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.1.mlp.fc1.bias - torch.Size([640]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.1.mlp.fc2.weight - torch.Size([160, 640]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.2.gamma1 - torch.Size([160]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.2.gamma2 - torch.Size([160]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.2.norm1.0.weight - torch.Size([160]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.2.norm1.0.bias - torch.Size([160]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.2.dcn.offset_mask_dw.weight - torch.Size([160, 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([160]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.2.dcn.offset_mask.weight - torch.Size([270, 160]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.2.dcn.offset_mask.bias - torch.Size([270]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.2.dcn.value_proj.weight - torch.Size([160, 160]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.2.dcn.value_proj.bias - torch.Size([160]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.2.dcn.output_proj.weight - torch.Size([160, 160]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.2.norm2.0.weight - torch.Size([160]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.2.norm2.0.bias - torch.Size([160]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.2.mlp.fc1.weight - torch.Size([640, 160]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.2.mlp.fc1.bias - torch.Size([640]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.2.mlp.fc2.weight - torch.Size([160, 640]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.3.gamma1 - torch.Size([160]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.3.gamma2 - torch.Size([160]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.3.norm1.0.weight - torch.Size([160]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.3.norm1.0.bias - torch.Size([160]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.3.dcn.offset_mask_dw.weight - torch.Size([160, 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([160]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.3.dcn.offset_mask.weight - torch.Size([270, 160]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.3.dcn.offset_mask.bias - torch.Size([270]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.3.dcn.value_proj.weight - torch.Size([160, 160]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.3.dcn.value_proj.bias - torch.Size([160]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.3.dcn.output_proj.weight - torch.Size([160, 160]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.3.norm2.0.weight - torch.Size([160]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.3.norm2.0.bias - torch.Size([160]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.3.mlp.fc1.weight - torch.Size([640, 160]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.3.mlp.fc1.bias - torch.Size([640]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.blocks.3.mlp.fc2.weight - torch.Size([160, 640]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.downsample.conv.weight - torch.Size([320, 160, 3, 3]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.downsample.norm.1.weight - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.1.downsample.norm.1.bias - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.0.gamma1 - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.0.gamma2 - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.0.norm1.0.weight - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.0.norm1.0.bias - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.0.dcn.offset_mask_dw.weight - torch.Size([320, 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([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.0.dcn.offset_mask.weight - torch.Size([540, 320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.0.dcn.offset_mask.bias - torch.Size([540]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.0.dcn.value_proj.weight - torch.Size([320, 320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.0.dcn.value_proj.bias - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.0.dcn.output_proj.weight - torch.Size([320, 320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.0.norm2.0.weight - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.0.norm2.0.bias - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.0.mlp.fc1.weight - torch.Size([1280, 320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.0.mlp.fc1.bias - torch.Size([1280]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.0.mlp.fc2.weight - torch.Size([320, 1280]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.1.gamma1 - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.1.gamma2 - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.1.norm1.0.weight - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.1.norm1.0.bias - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.1.dcn.offset_mask_dw.weight - torch.Size([320, 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([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.1.dcn.offset_mask.weight - torch.Size([540, 320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.1.dcn.offset_mask.bias - torch.Size([540]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.1.dcn.value_proj.weight - torch.Size([320, 320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.1.dcn.value_proj.bias - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.1.dcn.output_proj.weight - torch.Size([320, 320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.1.norm2.0.weight - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.1.norm2.0.bias - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.1.mlp.fc1.weight - torch.Size([1280, 320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.1.mlp.fc1.bias - torch.Size([1280]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.1.mlp.fc2.weight - torch.Size([320, 1280]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.2.gamma1 - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.2.gamma2 - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.2.norm1.0.weight - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.2.norm1.0.bias - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.2.dcn.offset_mask_dw.weight - torch.Size([320, 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([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.2.dcn.offset_mask.weight - torch.Size([540, 320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.2.dcn.offset_mask.bias - torch.Size([540]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.2.dcn.value_proj.weight - torch.Size([320, 320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.2.dcn.value_proj.bias - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.2.dcn.output_proj.weight - torch.Size([320, 320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.2.norm2.0.weight - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.2.norm2.0.bias - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.2.mlp.fc1.weight - torch.Size([1280, 320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.2.mlp.fc1.bias - torch.Size([1280]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.2.mlp.fc2.weight - torch.Size([320, 1280]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.3.gamma1 - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.3.gamma2 - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.3.norm1.0.weight - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.3.norm1.0.bias - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.3.dcn.offset_mask_dw.weight - torch.Size([320, 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([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.3.dcn.offset_mask.weight - torch.Size([540, 320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.3.dcn.offset_mask.bias - torch.Size([540]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.3.dcn.value_proj.weight - torch.Size([320, 320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.3.dcn.value_proj.bias - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.3.dcn.output_proj.weight - torch.Size([320, 320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.3.norm2.0.weight - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.3.norm2.0.bias - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.3.mlp.fc1.weight - torch.Size([1280, 320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.3.mlp.fc1.bias - torch.Size([1280]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.3.mlp.fc2.weight - torch.Size([320, 1280]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.4.gamma1 - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.4.gamma2 - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.4.norm1.0.weight - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.4.norm1.0.bias - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.4.dcn.offset_mask_dw.weight - torch.Size([320, 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([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.4.dcn.offset_mask.weight - torch.Size([540, 320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.4.dcn.offset_mask.bias - torch.Size([540]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.4.dcn.value_proj.weight - torch.Size([320, 320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.4.dcn.value_proj.bias - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.4.dcn.output_proj.weight - torch.Size([320, 320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.4.norm2.0.weight - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.4.norm2.0.bias - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.4.mlp.fc1.weight - torch.Size([1280, 320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.4.mlp.fc1.bias - torch.Size([1280]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.4.mlp.fc2.weight - torch.Size([320, 1280]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.5.gamma1 - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.5.gamma2 - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.5.norm1.0.weight - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.5.norm1.0.bias - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.5.dcn.offset_mask_dw.weight - torch.Size([320, 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([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.5.dcn.offset_mask.weight - torch.Size([540, 320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.5.dcn.offset_mask.bias - torch.Size([540]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.5.dcn.value_proj.weight - torch.Size([320, 320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.5.dcn.value_proj.bias - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.5.dcn.output_proj.weight - torch.Size([320, 320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.5.norm2.0.weight - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.5.norm2.0.bias - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.5.mlp.fc1.weight - torch.Size([1280, 320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.5.mlp.fc1.bias - torch.Size([1280]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.5.mlp.fc2.weight - torch.Size([320, 1280]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.6.gamma1 - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.6.gamma2 - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.6.norm1.0.weight - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.6.norm1.0.bias - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.6.dcn.offset_mask_dw.weight - torch.Size([320, 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([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.6.dcn.offset_mask.weight - torch.Size([540, 320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.6.dcn.offset_mask.bias - torch.Size([540]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.6.dcn.value_proj.weight - torch.Size([320, 320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.6.dcn.value_proj.bias - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.6.dcn.output_proj.weight - torch.Size([320, 320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.6.norm2.0.weight - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.6.norm2.0.bias - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.6.mlp.fc1.weight - torch.Size([1280, 320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.6.mlp.fc1.bias - torch.Size([1280]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.6.mlp.fc2.weight - torch.Size([320, 1280]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.7.gamma1 - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.7.gamma2 - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.7.norm1.0.weight - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.7.norm1.0.bias - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.7.dcn.offset_mask_dw.weight - torch.Size([320, 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([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.7.dcn.offset_mask.weight - torch.Size([540, 320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.7.dcn.offset_mask.bias - torch.Size([540]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.7.dcn.value_proj.weight - torch.Size([320, 320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.7.dcn.value_proj.bias - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.7.dcn.output_proj.weight - torch.Size([320, 320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.7.norm2.0.weight - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.7.norm2.0.bias - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.7.mlp.fc1.weight - torch.Size([1280, 320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.7.mlp.fc1.bias - torch.Size([1280]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.7.mlp.fc2.weight - torch.Size([320, 1280]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.8.gamma1 - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.8.gamma2 - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.8.norm1.0.weight - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.8.norm1.0.bias - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.8.dcn.offset_mask_dw.weight - torch.Size([320, 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([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.8.dcn.offset_mask.weight - torch.Size([540, 320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.8.dcn.offset_mask.bias - torch.Size([540]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.8.dcn.value_proj.weight - torch.Size([320, 320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.8.dcn.value_proj.bias - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.8.dcn.output_proj.weight - torch.Size([320, 320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.8.norm2.0.weight - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.8.norm2.0.bias - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.8.mlp.fc1.weight - torch.Size([1280, 320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.8.mlp.fc1.bias - torch.Size([1280]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.8.mlp.fc2.weight - torch.Size([320, 1280]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.9.gamma1 - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.9.gamma2 - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.9.norm1.0.weight - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.9.norm1.0.bias - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.9.dcn.offset_mask_dw.weight - torch.Size([320, 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([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.9.dcn.offset_mask.weight - torch.Size([540, 320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.9.dcn.offset_mask.bias - torch.Size([540]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.9.dcn.value_proj.weight - torch.Size([320, 320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.9.dcn.value_proj.bias - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.9.dcn.output_proj.weight - torch.Size([320, 320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.9.norm2.0.weight - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.9.norm2.0.bias - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.9.mlp.fc1.weight - torch.Size([1280, 320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.9.mlp.fc1.bias - torch.Size([1280]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.9.mlp.fc2.weight - torch.Size([320, 1280]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.10.gamma1 - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.10.gamma2 - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.10.norm1.0.weight - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.10.norm1.0.bias - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.10.dcn.offset_mask_dw.weight - torch.Size([320, 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([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.10.dcn.offset_mask.weight - torch.Size([540, 320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.10.dcn.offset_mask.bias - torch.Size([540]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.10.dcn.value_proj.weight - torch.Size([320, 320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.10.dcn.value_proj.bias - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.10.dcn.output_proj.weight - torch.Size([320, 320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.10.norm2.0.weight - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.10.norm2.0.bias - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.10.mlp.fc1.weight - torch.Size([1280, 320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.10.mlp.fc1.bias - torch.Size([1280]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.10.mlp.fc2.weight - torch.Size([320, 1280]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.11.gamma1 - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.11.gamma2 - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.11.norm1.0.weight - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.11.norm1.0.bias - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.11.dcn.offset_mask_dw.weight - torch.Size([320, 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([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.11.dcn.offset_mask.weight - torch.Size([540, 320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.11.dcn.offset_mask.bias - torch.Size([540]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.11.dcn.value_proj.weight - torch.Size([320, 320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.11.dcn.value_proj.bias - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.11.dcn.output_proj.weight - torch.Size([320, 320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.11.norm2.0.weight - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.11.norm2.0.bias - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.11.mlp.fc1.weight - torch.Size([1280, 320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.11.mlp.fc1.bias - torch.Size([1280]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.11.mlp.fc2.weight - torch.Size([320, 1280]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.12.gamma1 - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.12.gamma2 - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.12.norm1.0.weight - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.12.norm1.0.bias - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.12.dcn.offset_mask_dw.weight - torch.Size([320, 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([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.12.dcn.offset_mask.weight - torch.Size([540, 320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.12.dcn.offset_mask.bias - torch.Size([540]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.12.dcn.value_proj.weight - torch.Size([320, 320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.12.dcn.value_proj.bias - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.12.dcn.output_proj.weight - torch.Size([320, 320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.12.norm2.0.weight - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.12.norm2.0.bias - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.12.mlp.fc1.weight - torch.Size([1280, 320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.12.mlp.fc1.bias - torch.Size([1280]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.12.mlp.fc2.weight - torch.Size([320, 1280]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.13.gamma1 - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.13.gamma2 - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.13.norm1.0.weight - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.13.norm1.0.bias - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.13.dcn.offset_mask_dw.weight - torch.Size([320, 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([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.13.dcn.offset_mask.weight - torch.Size([540, 320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.13.dcn.offset_mask.bias - torch.Size([540]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.13.dcn.value_proj.weight - torch.Size([320, 320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.13.dcn.value_proj.bias - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.13.dcn.output_proj.weight - torch.Size([320, 320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.13.norm2.0.weight - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.13.norm2.0.bias - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.13.mlp.fc1.weight - torch.Size([1280, 320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.13.mlp.fc1.bias - torch.Size([1280]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.13.mlp.fc2.weight - torch.Size([320, 1280]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.14.gamma1 - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.14.gamma2 - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.14.norm1.0.weight - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.14.norm1.0.bias - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.14.dcn.offset_mask_dw.weight - torch.Size([320, 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([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.14.dcn.offset_mask.weight - torch.Size([540, 320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.14.dcn.offset_mask.bias - torch.Size([540]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.14.dcn.value_proj.weight - torch.Size([320, 320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.14.dcn.value_proj.bias - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.14.dcn.output_proj.weight - torch.Size([320, 320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.14.norm2.0.weight - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.14.norm2.0.bias - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.14.mlp.fc1.weight - torch.Size([1280, 320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.14.mlp.fc1.bias - torch.Size([1280]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.14.mlp.fc2.weight - torch.Size([320, 1280]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.15.gamma1 - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.15.gamma2 - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.15.norm1.0.weight - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.15.norm1.0.bias - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.15.dcn.offset_mask_dw.weight - torch.Size([320, 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([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.15.dcn.offset_mask.weight - torch.Size([540, 320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.15.dcn.offset_mask.bias - torch.Size([540]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.15.dcn.value_proj.weight - torch.Size([320, 320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.15.dcn.value_proj.bias - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.15.dcn.output_proj.weight - torch.Size([320, 320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.15.norm2.0.weight - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.15.norm2.0.bias - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.15.mlp.fc1.weight - torch.Size([1280, 320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.15.mlp.fc1.bias - torch.Size([1280]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.15.mlp.fc2.weight - torch.Size([320, 1280]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.16.gamma1 - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.16.gamma2 - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.16.norm1.0.weight - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.16.norm1.0.bias - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.16.dcn.offset_mask_dw.weight - torch.Size([320, 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([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.16.dcn.offset_mask.weight - torch.Size([540, 320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.16.dcn.offset_mask.bias - torch.Size([540]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.16.dcn.value_proj.weight - torch.Size([320, 320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.16.dcn.value_proj.bias - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.16.dcn.output_proj.weight - torch.Size([320, 320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.16.norm2.0.weight - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.16.norm2.0.bias - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.16.mlp.fc1.weight - torch.Size([1280, 320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.16.mlp.fc1.bias - torch.Size([1280]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.16.mlp.fc2.weight - torch.Size([320, 1280]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.17.gamma1 - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.17.gamma2 - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.17.norm1.0.weight - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.17.norm1.0.bias - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.17.dcn.offset_mask_dw.weight - torch.Size([320, 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([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.17.dcn.offset_mask.weight - torch.Size([540, 320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.17.dcn.offset_mask.bias - torch.Size([540]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.17.dcn.value_proj.weight - torch.Size([320, 320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.17.dcn.value_proj.bias - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.17.dcn.output_proj.weight - torch.Size([320, 320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.17.norm2.0.weight - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.17.norm2.0.bias - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.17.mlp.fc1.weight - torch.Size([1280, 320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.17.mlp.fc1.bias - torch.Size([1280]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.17.mlp.fc2.weight - torch.Size([320, 1280]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.18.gamma1 - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.18.gamma2 - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.18.norm1.0.weight - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.18.norm1.0.bias - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.18.dcn.offset_mask_dw.weight - torch.Size([320, 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([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.18.dcn.offset_mask.weight - torch.Size([540, 320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.18.dcn.offset_mask.bias - torch.Size([540]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.18.dcn.value_proj.weight - torch.Size([320, 320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.18.dcn.value_proj.bias - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.18.dcn.output_proj.weight - torch.Size([320, 320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.18.norm2.0.weight - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.18.norm2.0.bias - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.18.mlp.fc1.weight - torch.Size([1280, 320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.18.mlp.fc1.bias - torch.Size([1280]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.18.mlp.fc2.weight - torch.Size([320, 1280]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.19.gamma1 - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.19.gamma2 - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.19.norm1.0.weight - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.19.norm1.0.bias - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.19.dcn.offset_mask_dw.weight - torch.Size([320, 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([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.19.dcn.offset_mask.weight - torch.Size([540, 320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.19.dcn.offset_mask.bias - torch.Size([540]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.19.dcn.value_proj.weight - torch.Size([320, 320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.19.dcn.value_proj.bias - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.19.dcn.output_proj.weight - torch.Size([320, 320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.19.norm2.0.weight - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.19.norm2.0.bias - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.19.mlp.fc1.weight - torch.Size([1280, 320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.19.mlp.fc1.bias - torch.Size([1280]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.19.mlp.fc2.weight - torch.Size([320, 1280]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.20.gamma1 - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.20.gamma2 - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.20.norm1.0.weight - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.20.norm1.0.bias - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.20.dcn.offset_mask_dw.weight - torch.Size([320, 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([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.20.dcn.offset_mask.weight - torch.Size([540, 320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.20.dcn.offset_mask.bias - torch.Size([540]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.20.dcn.value_proj.weight - torch.Size([320, 320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.20.dcn.value_proj.bias - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.20.dcn.output_proj.weight - torch.Size([320, 320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.20.norm2.0.weight - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.20.norm2.0.bias - torch.Size([320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.20.mlp.fc1.weight - torch.Size([1280, 320]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.20.mlp.fc1.bias - torch.Size([1280]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.blocks.20.mlp.fc2.weight - torch.Size([320, 1280]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.downsample.conv.weight - torch.Size([640, 320, 3, 3]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.downsample.norm.1.weight - torch.Size([640]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.2.downsample.norm.1.bias - torch.Size([640]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.0.gamma1 - torch.Size([640]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.0.gamma2 - torch.Size([640]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.0.norm1.0.weight - torch.Size([640]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.0.norm1.0.bias - torch.Size([640]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.0.dcn.offset_mask_dw.weight - torch.Size([640, 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([640]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.0.dcn.offset_mask.weight - torch.Size([1080, 640]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.0.dcn.offset_mask.bias - torch.Size([1080]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.0.dcn.value_proj.weight - torch.Size([640, 640]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.0.dcn.value_proj.bias - torch.Size([640]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.0.dcn.output_proj.weight - torch.Size([640, 640]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.0.norm2.0.weight - torch.Size([640]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.0.norm2.0.bias - torch.Size([640]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.0.mlp.fc1.weight - torch.Size([2560, 640]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.0.mlp.fc1.bias - torch.Size([2560]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.0.mlp.fc2.weight - torch.Size([640, 2560]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.1.gamma1 - torch.Size([640]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.1.gamma2 - torch.Size([640]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.1.norm1.0.weight - torch.Size([640]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.1.norm1.0.bias - torch.Size([640]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.1.dcn.offset_mask_dw.weight - torch.Size([640, 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([640]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.1.dcn.offset_mask.weight - torch.Size([1080, 640]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.1.dcn.offset_mask.bias - torch.Size([1080]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.1.dcn.value_proj.weight - torch.Size([640, 640]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.1.dcn.value_proj.bias - torch.Size([640]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.1.dcn.output_proj.weight - torch.Size([640, 640]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.1.norm2.0.weight - torch.Size([640]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.1.norm2.0.bias - torch.Size([640]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.1.mlp.fc1.weight - torch.Size([2560, 640]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.1.mlp.fc1.bias - torch.Size([2560]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.1.mlp.fc2.weight - torch.Size([640, 2560]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.2.gamma1 - torch.Size([640]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.2.gamma2 - torch.Size([640]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.2.norm1.0.weight - torch.Size([640]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.2.norm1.0.bias - torch.Size([640]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.2.dcn.offset_mask_dw.weight - torch.Size([640, 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([640]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.2.dcn.offset_mask.weight - torch.Size([1080, 640]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.2.dcn.offset_mask.bias - torch.Size([1080]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.2.dcn.value_proj.weight - torch.Size([640, 640]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.2.dcn.value_proj.bias - torch.Size([640]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.2.dcn.output_proj.weight - torch.Size([640, 640]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.2.norm2.0.weight - torch.Size([640]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.2.norm2.0.bias - torch.Size([640]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.2.mlp.fc1.weight - torch.Size([2560, 640]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.2.mlp.fc1.bias - torch.Size([2560]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.2.mlp.fc2.weight - torch.Size([640, 2560]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.3.gamma1 - torch.Size([640]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.3.gamma2 - torch.Size([640]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.3.norm1.0.weight - torch.Size([640]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.3.norm1.0.bias - torch.Size([640]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.3.dcn.offset_mask_dw.weight - torch.Size([640, 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([640]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.3.dcn.offset_mask.weight - torch.Size([1080, 640]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.3.dcn.offset_mask.bias - torch.Size([1080]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.3.dcn.value_proj.weight - torch.Size([640, 640]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.3.dcn.value_proj.bias - torch.Size([640]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.3.dcn.output_proj.weight - torch.Size([640, 640]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.3.norm2.0.weight - torch.Size([640]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.3.norm2.0.bias - torch.Size([640]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.3.mlp.fc1.weight - torch.Size([2560, 640]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.3.mlp.fc1.bias - torch.Size([2560]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx backbone.levels.3.blocks.3.mlp.fc2.weight - torch.Size([640, 2560]): Initialized by user-defined `init_weights` in Flash_InternImage_nsmx neck.lateral_convs.0.conv.weight - torch.Size([256, 80, 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, 160, 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, 320, 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, 640, 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 2023-11-15 13:34:39,684 - mmdet - INFO - MaskRCNN( (backbone): Flash_InternImage_nsmx( (patch_embed): StemLayer( (conv1): Conv2d(3, 40, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1)) (norm1): Sequential( (0): to_channels_last() (1): LayerNorm((40,), eps=1e-06, elementwise_affine=True) (2): to_channels_first() ) (act): GELU(approximate=none) (conv2): Conv2d(40, 80, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1)) (norm2): Sequential( (0): to_channels_last() (1): LayerNorm((80,), 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((80,), eps=1e-06, elementwise_affine=True) ) (dcn): FlashDCNv3( (offset_mask_dw): Conv2d(80, 80, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=80) (offset_mask): Linear(in_features=80, out_features=135, bias=True) (value_proj): Linear(in_features=80, out_features=80, bias=True) (output_proj): Linear(in_features=80, out_features=80, bias=False) ) (drop_path): Identity() (norm2): Sequential( (0): LayerNorm((80,), eps=1e-06, elementwise_affine=True) ) (mlp): MLPLayer( (fc1): Linear(in_features=80, out_features=320, bias=True) (act): GELU(approximate=none) (fc2): Linear(in_features=320, out_features=80, bias=False) (drop): Dropout(p=0.0, inplace=False) ) ) (1): InternImageLayer( (norm1): Sequential( (0): LayerNorm((80,), eps=1e-06, elementwise_affine=True) ) (dcn): FlashDCNv3( (offset_mask_dw): Conv2d(80, 80, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=80) (offset_mask): Linear(in_features=80, out_features=135, bias=True) (value_proj): Linear(in_features=80, out_features=80, bias=True) (output_proj): Linear(in_features=80, out_features=80, bias=False) ) (drop_path): DropPath(drop_prob=0.013) (norm2): Sequential( (0): LayerNorm((80,), eps=1e-06, elementwise_affine=True) ) (mlp): MLPLayer( (fc1): Linear(in_features=80, out_features=320, bias=True) (act): GELU(approximate=none) (fc2): Linear(in_features=320, out_features=80, bias=False) (drop): Dropout(p=0.0, inplace=False) ) ) (2): InternImageLayer( (norm1): Sequential( (0): LayerNorm((80,), eps=1e-06, elementwise_affine=True) ) (dcn): FlashDCNv3( (offset_mask_dw): Conv2d(80, 80, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=80) (offset_mask): Linear(in_features=80, out_features=135, bias=True) (value_proj): Linear(in_features=80, out_features=80, bias=True) (output_proj): Linear(in_features=80, out_features=80, bias=False) ) (drop_path): DropPath(drop_prob=0.025) (norm2): Sequential( (0): LayerNorm((80,), eps=1e-06, elementwise_affine=True) ) (mlp): MLPLayer( (fc1): Linear(in_features=80, out_features=320, bias=True) (act): GELU(approximate=none) (fc2): Linear(in_features=320, out_features=80, bias=False) (drop): Dropout(p=0.0, inplace=False) ) ) (3): InternImageLayer( (norm1): Sequential( (0): LayerNorm((80,), eps=1e-06, elementwise_affine=True) ) (dcn): FlashDCNv3( (offset_mask_dw): Conv2d(80, 80, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=80) (offset_mask): Linear(in_features=80, out_features=135, bias=True) (value_proj): Linear(in_features=80, out_features=80, bias=True) (output_proj): Linear(in_features=80, out_features=80, bias=False) ) (drop_path): DropPath(drop_prob=0.038) (norm2): Sequential( (0): LayerNorm((80,), eps=1e-06, elementwise_affine=True) ) (mlp): MLPLayer( (fc1): Linear(in_features=80, out_features=320, bias=True) (act): GELU(approximate=none) (fc2): Linear(in_features=320, out_features=80, bias=False) (drop): Dropout(p=0.0, inplace=False) ) ) ) (downsample): DownsampleLayer( (conv): Conv2d(80, 160, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) (norm): Sequential( (0): to_channels_last() (1): LayerNorm((160,), eps=1e-06, elementwise_affine=True) (2): to_channels_first() ) ) ) (1): InternImageBlock( (blocks): ModuleList( (0): InternImageLayer( (norm1): Sequential( (0): LayerNorm((160,), eps=1e-06, elementwise_affine=True) ) (dcn): FlashDCNv3( (offset_mask_dw): Conv2d(160, 160, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=160) (offset_mask): Linear(in_features=160, out_features=270, bias=True) (value_proj): Linear(in_features=160, out_features=160, bias=True) (output_proj): Linear(in_features=160, out_features=160, bias=False) ) (drop_path): DropPath(drop_prob=0.050) (norm2): Sequential( (0): LayerNorm((160,), eps=1e-06, elementwise_affine=True) ) (mlp): MLPLayer( (fc1): Linear(in_features=160, out_features=640, bias=True) (act): GELU(approximate=none) (fc2): Linear(in_features=640, out_features=160, bias=False) (drop): Dropout(p=0.0, inplace=False) ) ) (1): InternImageLayer( (norm1): Sequential( (0): LayerNorm((160,), eps=1e-06, elementwise_affine=True) ) (dcn): FlashDCNv3( (offset_mask_dw): Conv2d(160, 160, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=160) (offset_mask): Linear(in_features=160, out_features=270, bias=True) (value_proj): Linear(in_features=160, out_features=160, bias=True) (output_proj): Linear(in_features=160, out_features=160, bias=False) ) (drop_path): DropPath(drop_prob=0.062) (norm2): Sequential( (0): LayerNorm((160,), eps=1e-06, elementwise_affine=True) ) (mlp): MLPLayer( (fc1): Linear(in_features=160, out_features=640, bias=True) (act): GELU(approximate=none) (fc2): Linear(in_features=640, out_features=160, bias=False) (drop): Dropout(p=0.0, inplace=False) ) ) (2): InternImageLayer( (norm1): Sequential( (0): LayerNorm((160,), eps=1e-06, elementwise_affine=True) ) (dcn): FlashDCNv3( (offset_mask_dw): Conv2d(160, 160, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=160) (offset_mask): Linear(in_features=160, out_features=270, bias=True) (value_proj): Linear(in_features=160, out_features=160, bias=True) (output_proj): Linear(in_features=160, out_features=160, bias=False) ) (drop_path): DropPath(drop_prob=0.075) (norm2): Sequential( (0): LayerNorm((160,), eps=1e-06, elementwise_affine=True) ) (mlp): MLPLayer( (fc1): Linear(in_features=160, out_features=640, bias=True) (act): GELU(approximate=none) (fc2): Linear(in_features=640, out_features=160, bias=False) (drop): Dropout(p=0.0, inplace=False) ) ) (3): InternImageLayer( (norm1): Sequential( (0): LayerNorm((160,), eps=1e-06, elementwise_affine=True) ) (dcn): FlashDCNv3( (offset_mask_dw): Conv2d(160, 160, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=160) (offset_mask): Linear(in_features=160, out_features=270, bias=True) (value_proj): Linear(in_features=160, out_features=160, bias=True) (output_proj): Linear(in_features=160, out_features=160, bias=False) ) (drop_path): DropPath(drop_prob=0.087) (norm2): Sequential( (0): LayerNorm((160,), eps=1e-06, elementwise_affine=True) ) (mlp): MLPLayer( (fc1): Linear(in_features=160, out_features=640, bias=True) (act): GELU(approximate=none) (fc2): Linear(in_features=640, out_features=160, bias=False) (drop): Dropout(p=0.0, inplace=False) ) ) ) (downsample): DownsampleLayer( (conv): Conv2d(160, 320, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) (norm): Sequential( (0): to_channels_last() (1): LayerNorm((320,), eps=1e-06, elementwise_affine=True) (2): to_channels_first() ) ) ) (2): InternImageBlock( (blocks): ModuleList( (0): InternImageLayer( (norm1): Sequential( (0): LayerNorm((320,), eps=1e-06, elementwise_affine=True) ) (dcn): FlashDCNv3( (offset_mask_dw): Conv2d(320, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=320) (offset_mask): Linear(in_features=320, out_features=540, bias=True) (value_proj): Linear(in_features=320, out_features=320, bias=True) (output_proj): Linear(in_features=320, out_features=320, bias=False) ) (drop_path): DropPath(drop_prob=0.100) (norm2): Sequential( (0): LayerNorm((320,), eps=1e-06, elementwise_affine=True) ) (mlp): MLPLayer( (fc1): Linear(in_features=320, out_features=1280, bias=True) (act): GELU(approximate=none) (fc2): Linear(in_features=1280, out_features=320, bias=False) (drop): Dropout(p=0.0, inplace=False) ) ) (1): InternImageLayer( (norm1): Sequential( (0): LayerNorm((320,), eps=1e-06, elementwise_affine=True) ) (dcn): FlashDCNv3( (offset_mask_dw): Conv2d(320, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=320) (offset_mask): Linear(in_features=320, out_features=540, bias=True) (value_proj): Linear(in_features=320, out_features=320, bias=True) (output_proj): Linear(in_features=320, out_features=320, bias=False) ) (drop_path): DropPath(drop_prob=0.113) (norm2): Sequential( (0): LayerNorm((320,), eps=1e-06, elementwise_affine=True) ) (mlp): MLPLayer( (fc1): Linear(in_features=320, out_features=1280, bias=True) (act): GELU(approximate=none) (fc2): Linear(in_features=1280, out_features=320, bias=False) (drop): Dropout(p=0.0, inplace=False) ) ) (2): InternImageLayer( (norm1): Sequential( (0): LayerNorm((320,), eps=1e-06, elementwise_affine=True) ) (dcn): FlashDCNv3( (offset_mask_dw): Conv2d(320, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=320) (offset_mask): Linear(in_features=320, out_features=540, bias=True) (value_proj): Linear(in_features=320, out_features=320, bias=True) (output_proj): Linear(in_features=320, out_features=320, bias=False) ) (drop_path): DropPath(drop_prob=0.125) (norm2): Sequential( (0): LayerNorm((320,), eps=1e-06, elementwise_affine=True) ) (mlp): MLPLayer( (fc1): Linear(in_features=320, out_features=1280, bias=True) (act): GELU(approximate=none) (fc2): Linear(in_features=1280, out_features=320, bias=False) (drop): Dropout(p=0.0, inplace=False) ) ) (3): InternImageLayer( (norm1): Sequential( (0): LayerNorm((320,), eps=1e-06, elementwise_affine=True) ) (dcn): FlashDCNv3( (offset_mask_dw): Conv2d(320, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=320) (offset_mask): Linear(in_features=320, out_features=540, bias=True) (value_proj): Linear(in_features=320, out_features=320, bias=True) (output_proj): Linear(in_features=320, out_features=320, bias=False) ) (drop_path): DropPath(drop_prob=0.138) (norm2): Sequential( (0): LayerNorm((320,), eps=1e-06, elementwise_affine=True) ) (mlp): MLPLayer( (fc1): Linear(in_features=320, out_features=1280, bias=True) (act): GELU(approximate=none) (fc2): Linear(in_features=1280, out_features=320, bias=False) (drop): Dropout(p=0.0, inplace=False) ) ) (4): InternImageLayer( (norm1): Sequential( (0): LayerNorm((320,), eps=1e-06, elementwise_affine=True) ) (dcn): FlashDCNv3( (offset_mask_dw): Conv2d(320, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=320) (offset_mask): Linear(in_features=320, out_features=540, bias=True) (value_proj): Linear(in_features=320, out_features=320, bias=True) (output_proj): Linear(in_features=320, out_features=320, bias=False) ) (drop_path): DropPath(drop_prob=0.150) (norm2): Sequential( (0): LayerNorm((320,), eps=1e-06, elementwise_affine=True) ) (mlp): MLPLayer( (fc1): Linear(in_features=320, out_features=1280, bias=True) (act): GELU(approximate=none) (fc2): Linear(in_features=1280, out_features=320, bias=False) (drop): Dropout(p=0.0, inplace=False) ) ) (5): InternImageLayer( (norm1): Sequential( (0): LayerNorm((320,), eps=1e-06, elementwise_affine=True) ) (dcn): FlashDCNv3( (offset_mask_dw): Conv2d(320, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=320) (offset_mask): Linear(in_features=320, out_features=540, bias=True) (value_proj): Linear(in_features=320, out_features=320, bias=True) (output_proj): Linear(in_features=320, out_features=320, bias=False) ) (drop_path): DropPath(drop_prob=0.162) (norm2): Sequential( (0): LayerNorm((320,), eps=1e-06, elementwise_affine=True) ) (mlp): MLPLayer( (fc1): Linear(in_features=320, out_features=1280, bias=True) (act): GELU(approximate=none) (fc2): Linear(in_features=1280, out_features=320, bias=False) (drop): Dropout(p=0.0, inplace=False) ) ) (6): InternImageLayer( (norm1): Sequential( (0): LayerNorm((320,), eps=1e-06, elementwise_affine=True) ) (dcn): FlashDCNv3( (offset_mask_dw): Conv2d(320, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=320) (offset_mask): Linear(in_features=320, out_features=540, bias=True) (value_proj): Linear(in_features=320, out_features=320, bias=True) (output_proj): Linear(in_features=320, out_features=320, bias=False) ) (drop_path): DropPath(drop_prob=0.175) (norm2): Sequential( (0): LayerNorm((320,), eps=1e-06, elementwise_affine=True) ) (mlp): MLPLayer( (fc1): Linear(in_features=320, out_features=1280, bias=True) (act): GELU(approximate=none) (fc2): Linear(in_features=1280, out_features=320, bias=False) (drop): Dropout(p=0.0, inplace=False) ) ) (7): InternImageLayer( (norm1): Sequential( (0): LayerNorm((320,), eps=1e-06, elementwise_affine=True) ) (dcn): FlashDCNv3( (offset_mask_dw): Conv2d(320, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=320) (offset_mask): Linear(in_features=320, out_features=540, bias=True) (value_proj): Linear(in_features=320, out_features=320, bias=True) (output_proj): Linear(in_features=320, out_features=320, bias=False) ) (drop_path): DropPath(drop_prob=0.188) (norm2): Sequential( (0): LayerNorm((320,), eps=1e-06, elementwise_affine=True) ) (mlp): MLPLayer( (fc1): Linear(in_features=320, out_features=1280, bias=True) (act): GELU(approximate=none) (fc2): Linear(in_features=1280, out_features=320, bias=False) (drop): Dropout(p=0.0, inplace=False) ) ) (8): InternImageLayer( (norm1): Sequential( (0): LayerNorm((320,), eps=1e-06, elementwise_affine=True) ) (dcn): FlashDCNv3( (offset_mask_dw): Conv2d(320, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=320) (offset_mask): Linear(in_features=320, out_features=540, bias=True) (value_proj): Linear(in_features=320, out_features=320, bias=True) (output_proj): Linear(in_features=320, out_features=320, bias=False) ) (drop_path): DropPath(drop_prob=0.200) (norm2): Sequential( (0): LayerNorm((320,), eps=1e-06, elementwise_affine=True) ) (mlp): MLPLayer( (fc1): Linear(in_features=320, out_features=1280, bias=True) (act): GELU(approximate=none) (fc2): Linear(in_features=1280, out_features=320, bias=False) (drop): Dropout(p=0.0, inplace=False) ) ) (9): InternImageLayer( (norm1): Sequential( (0): LayerNorm((320,), eps=1e-06, elementwise_affine=True) ) (dcn): FlashDCNv3( (offset_mask_dw): Conv2d(320, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=320) (offset_mask): Linear(in_features=320, out_features=540, bias=True) (value_proj): Linear(in_features=320, out_features=320, bias=True) (output_proj): Linear(in_features=320, out_features=320, bias=False) ) (drop_path): DropPath(drop_prob=0.213) (norm2): Sequential( (0): LayerNorm((320,), eps=1e-06, elementwise_affine=True) ) (mlp): MLPLayer( (fc1): Linear(in_features=320, out_features=1280, bias=True) (act): GELU(approximate=none) (fc2): Linear(in_features=1280, out_features=320, bias=False) (drop): Dropout(p=0.0, inplace=False) ) ) (10): InternImageLayer( (norm1): Sequential( (0): LayerNorm((320,), eps=1e-06, elementwise_affine=True) ) (dcn): FlashDCNv3( (offset_mask_dw): Conv2d(320, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=320) (offset_mask): Linear(in_features=320, out_features=540, bias=True) (value_proj): Linear(in_features=320, out_features=320, bias=True) (output_proj): Linear(in_features=320, out_features=320, bias=False) ) (drop_path): DropPath(drop_prob=0.225) (norm2): Sequential( (0): LayerNorm((320,), eps=1e-06, elementwise_affine=True) ) (mlp): MLPLayer( (fc1): Linear(in_features=320, out_features=1280, bias=True) (act): GELU(approximate=none) (fc2): Linear(in_features=1280, out_features=320, bias=False) (drop): Dropout(p=0.0, inplace=False) ) ) (11): InternImageLayer( (norm1): Sequential( (0): LayerNorm((320,), eps=1e-06, elementwise_affine=True) ) (dcn): FlashDCNv3( (offset_mask_dw): Conv2d(320, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=320) (offset_mask): Linear(in_features=320, out_features=540, bias=True) (value_proj): Linear(in_features=320, out_features=320, bias=True) (output_proj): Linear(in_features=320, out_features=320, bias=False) ) (drop_path): DropPath(drop_prob=0.238) (norm2): Sequential( (0): LayerNorm((320,), eps=1e-06, elementwise_affine=True) ) (mlp): MLPLayer( (fc1): Linear(in_features=320, out_features=1280, bias=True) (act): GELU(approximate=none) (fc2): Linear(in_features=1280, out_features=320, bias=False) (drop): Dropout(p=0.0, inplace=False) ) ) (12): InternImageLayer( (norm1): Sequential( (0): LayerNorm((320,), eps=1e-06, elementwise_affine=True) ) (dcn): FlashDCNv3( (offset_mask_dw): Conv2d(320, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=320) (offset_mask): Linear(in_features=320, out_features=540, bias=True) (value_proj): Linear(in_features=320, out_features=320, bias=True) (output_proj): Linear(in_features=320, out_features=320, bias=False) ) (drop_path): DropPath(drop_prob=0.250) (norm2): Sequential( (0): LayerNorm((320,), eps=1e-06, elementwise_affine=True) ) (mlp): MLPLayer( (fc1): Linear(in_features=320, out_features=1280, bias=True) (act): GELU(approximate=none) (fc2): Linear(in_features=1280, out_features=320, bias=False) (drop): Dropout(p=0.0, inplace=False) ) ) (13): InternImageLayer( (norm1): Sequential( (0): LayerNorm((320,), eps=1e-06, elementwise_affine=True) ) (dcn): FlashDCNv3( (offset_mask_dw): Conv2d(320, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=320) (offset_mask): Linear(in_features=320, out_features=540, bias=True) (value_proj): Linear(in_features=320, out_features=320, bias=True) (output_proj): Linear(in_features=320, out_features=320, bias=False) ) (drop_path): DropPath(drop_prob=0.262) (norm2): Sequential( (0): LayerNorm((320,), eps=1e-06, elementwise_affine=True) ) (mlp): MLPLayer( (fc1): Linear(in_features=320, out_features=1280, bias=True) (act): GELU(approximate=none) (fc2): Linear(in_features=1280, out_features=320, bias=False) (drop): Dropout(p=0.0, inplace=False) ) ) (14): InternImageLayer( (norm1): Sequential( (0): LayerNorm((320,), eps=1e-06, elementwise_affine=True) ) (dcn): FlashDCNv3( (offset_mask_dw): Conv2d(320, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=320) (offset_mask): Linear(in_features=320, out_features=540, bias=True) (value_proj): Linear(in_features=320, out_features=320, bias=True) (output_proj): Linear(in_features=320, out_features=320, bias=False) ) (drop_path): DropPath(drop_prob=0.275) (norm2): Sequential( (0): LayerNorm((320,), eps=1e-06, elementwise_affine=True) ) (mlp): MLPLayer( (fc1): Linear(in_features=320, out_features=1280, bias=True) (act): GELU(approximate=none) (fc2): Linear(in_features=1280, out_features=320, bias=False) (drop): Dropout(p=0.0, inplace=False) ) ) (15): InternImageLayer( (norm1): Sequential( (0): LayerNorm((320,), eps=1e-06, elementwise_affine=True) ) (dcn): FlashDCNv3( (offset_mask_dw): Conv2d(320, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=320) (offset_mask): Linear(in_features=320, out_features=540, bias=True) (value_proj): Linear(in_features=320, out_features=320, bias=True) (output_proj): Linear(in_features=320, out_features=320, bias=False) ) (drop_path): DropPath(drop_prob=0.287) (norm2): Sequential( (0): LayerNorm((320,), eps=1e-06, elementwise_affine=True) ) (mlp): MLPLayer( (fc1): Linear(in_features=320, out_features=1280, bias=True) (act): GELU(approximate=none) (fc2): Linear(in_features=1280, out_features=320, bias=False) (drop): Dropout(p=0.0, inplace=False) ) ) (16): InternImageLayer( (norm1): Sequential( (0): LayerNorm((320,), eps=1e-06, elementwise_affine=True) ) (dcn): FlashDCNv3( (offset_mask_dw): Conv2d(320, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=320) (offset_mask): Linear(in_features=320, out_features=540, bias=True) (value_proj): Linear(in_features=320, out_features=320, bias=True) (output_proj): Linear(in_features=320, out_features=320, bias=False) ) (drop_path): DropPath(drop_prob=0.300) (norm2): Sequential( (0): LayerNorm((320,), eps=1e-06, elementwise_affine=True) ) (mlp): MLPLayer( (fc1): Linear(in_features=320, out_features=1280, bias=True) (act): GELU(approximate=none) (fc2): Linear(in_features=1280, out_features=320, bias=False) (drop): Dropout(p=0.0, inplace=False) ) ) (17): InternImageLayer( (norm1): Sequential( (0): LayerNorm((320,), eps=1e-06, elementwise_affine=True) ) (dcn): FlashDCNv3( (offset_mask_dw): Conv2d(320, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=320) (offset_mask): Linear(in_features=320, out_features=540, bias=True) (value_proj): Linear(in_features=320, out_features=320, bias=True) (output_proj): Linear(in_features=320, out_features=320, bias=False) ) (drop_path): DropPath(drop_prob=0.312) (norm2): Sequential( (0): LayerNorm((320,), eps=1e-06, elementwise_affine=True) ) (mlp): MLPLayer( (fc1): Linear(in_features=320, out_features=1280, bias=True) (act): GELU(approximate=none) (fc2): Linear(in_features=1280, out_features=320, bias=False) (drop): Dropout(p=0.0, inplace=False) ) ) (18): InternImageLayer( (norm1): Sequential( (0): LayerNorm((320,), eps=1e-06, elementwise_affine=True) ) (dcn): FlashDCNv3( (offset_mask_dw): Conv2d(320, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=320) (offset_mask): Linear(in_features=320, out_features=540, bias=True) (value_proj): Linear(in_features=320, out_features=320, bias=True) (output_proj): Linear(in_features=320, out_features=320, bias=False) ) (drop_path): DropPath(drop_prob=0.325) (norm2): Sequential( (0): LayerNorm((320,), eps=1e-06, elementwise_affine=True) ) (mlp): MLPLayer( (fc1): Linear(in_features=320, out_features=1280, bias=True) (act): GELU(approximate=none) (fc2): Linear(in_features=1280, out_features=320, bias=False) (drop): Dropout(p=0.0, inplace=False) ) ) (19): InternImageLayer( (norm1): Sequential( (0): LayerNorm((320,), eps=1e-06, elementwise_affine=True) ) (dcn): FlashDCNv3( (offset_mask_dw): Conv2d(320, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=320) (offset_mask): Linear(in_features=320, out_features=540, bias=True) (value_proj): Linear(in_features=320, out_features=320, bias=True) (output_proj): Linear(in_features=320, out_features=320, bias=False) ) (drop_path): DropPath(drop_prob=0.338) (norm2): Sequential( (0): LayerNorm((320,), eps=1e-06, elementwise_affine=True) ) (mlp): MLPLayer( (fc1): Linear(in_features=320, out_features=1280, bias=True) (act): GELU(approximate=none) (fc2): Linear(in_features=1280, out_features=320, bias=False) (drop): Dropout(p=0.0, inplace=False) ) ) (20): InternImageLayer( (norm1): Sequential( (0): LayerNorm((320,), eps=1e-06, elementwise_affine=True) ) (dcn): FlashDCNv3( (offset_mask_dw): Conv2d(320, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=320) (offset_mask): Linear(in_features=320, out_features=540, bias=True) (value_proj): Linear(in_features=320, out_features=320, bias=True) (output_proj): Linear(in_features=320, out_features=320, bias=False) ) (drop_path): DropPath(drop_prob=0.350) (norm2): Sequential( (0): LayerNorm((320,), eps=1e-06, elementwise_affine=True) ) (mlp): MLPLayer( (fc1): Linear(in_features=320, out_features=1280, bias=True) (act): GELU(approximate=none) (fc2): Linear(in_features=1280, out_features=320, bias=False) (drop): Dropout(p=0.0, inplace=False) ) ) ) (downsample): DownsampleLayer( (conv): Conv2d(320, 640, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) (norm): Sequential( (0): to_channels_last() (1): LayerNorm((640,), eps=1e-06, elementwise_affine=True) (2): to_channels_first() ) ) ) (3): InternImageBlock( (blocks): ModuleList( (0): InternImageLayer( (norm1): Sequential( (0): LayerNorm((640,), eps=1e-06, elementwise_affine=True) ) (dcn): FlashDCNv3( (offset_mask_dw): Conv2d(640, 640, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=640) (offset_mask): Linear(in_features=640, out_features=1080, bias=True) (value_proj): Linear(in_features=640, out_features=640, bias=True) (output_proj): Linear(in_features=640, out_features=640, bias=False) ) (drop_path): DropPath(drop_prob=0.363) (norm2): Sequential( (0): LayerNorm((640,), eps=1e-06, elementwise_affine=True) ) (mlp): MLPLayer( (fc1): Linear(in_features=640, out_features=2560, bias=True) (act): GELU(approximate=none) (fc2): Linear(in_features=2560, out_features=640, bias=False) (drop): Dropout(p=0.0, inplace=False) ) ) (1): InternImageLayer( (norm1): Sequential( (0): LayerNorm((640,), eps=1e-06, elementwise_affine=True) ) (dcn): FlashDCNv3( (offset_mask_dw): Conv2d(640, 640, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=640) (offset_mask): Linear(in_features=640, out_features=1080, bias=True) (value_proj): Linear(in_features=640, out_features=640, bias=True) (output_proj): Linear(in_features=640, out_features=640, bias=False) ) (drop_path): DropPath(drop_prob=0.375) (norm2): Sequential( (0): LayerNorm((640,), eps=1e-06, elementwise_affine=True) ) (mlp): MLPLayer( (fc1): Linear(in_features=640, out_features=2560, bias=True) (act): GELU(approximate=none) (fc2): Linear(in_features=2560, out_features=640, bias=False) (drop): Dropout(p=0.0, inplace=False) ) ) (2): InternImageLayer( (norm1): Sequential( (0): LayerNorm((640,), eps=1e-06, elementwise_affine=True) ) (dcn): FlashDCNv3( (offset_mask_dw): Conv2d(640, 640, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=640) (offset_mask): Linear(in_features=640, out_features=1080, bias=True) (value_proj): Linear(in_features=640, out_features=640, bias=True) (output_proj): Linear(in_features=640, out_features=640, bias=False) ) (drop_path): DropPath(drop_prob=0.388) (norm2): Sequential( (0): LayerNorm((640,), eps=1e-06, elementwise_affine=True) ) (mlp): MLPLayer( (fc1): Linear(in_features=640, out_features=2560, bias=True) (act): GELU(approximate=none) (fc2): Linear(in_features=2560, out_features=640, bias=False) (drop): Dropout(p=0.0, inplace=False) ) ) (3): InternImageLayer( (norm1): Sequential( (0): LayerNorm((640,), eps=1e-06, elementwise_affine=True) ) (dcn): FlashDCNv3( (offset_mask_dw): Conv2d(640, 640, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=640) (offset_mask): Linear(in_features=640, out_features=1080, bias=True) (value_proj): Linear(in_features=640, out_features=640, bias=True) (output_proj): Linear(in_features=640, out_features=640, bias=False) ) (drop_path): DropPath(drop_prob=0.400) (norm2): Sequential( (0): LayerNorm((640,), eps=1e-06, elementwise_affine=True) ) (mlp): MLPLayer( (fc1): Linear(in_features=640, out_features=2560, bias=True) (act): GELU(approximate=none) (fc2): Linear(in_features=2560, out_features=640, bias=False) (drop): Dropout(p=0.0, inplace=False) ) ) ) ) ) ) (neck): FPN_vitdet( (lateral_convs): ModuleList( (0): ConvModule_Norm( (conv): Conv2d(80, 256, kernel_size=(1, 1), stride=(1, 1), bias=False) (ln): LayerNorm((256,), eps=1e-05, elementwise_affine=True) ) (1): ConvModule_Norm( (conv): Conv2d(160, 256, kernel_size=(1, 1), stride=(1, 1), bias=False) (ln): LayerNorm((256,), eps=1e-05, elementwise_affine=True) ) (2): ConvModule_Norm( (conv): Conv2d(320, 256, kernel_size=(1, 1), stride=(1, 1), bias=False) (ln): LayerNorm((256,), eps=1e-05, elementwise_affine=True) ) (3): ConvModule_Norm( (conv): Conv2d(640, 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) ) ) ) 2023-11-15 13:34:57,267 - mmdet - INFO - Automatic scaling of learning rate (LR) has been disabled. 2023-11-15 13:34:57,268 - mmdet - INFO - {'num_layers': 33, 'layer_decay_rate': 1.0, 'depths': [4, 4, 21, 4]} 2023-11-15 13:34:57,268 - mmdet - INFO - Build CustomLayerDecayOptimizerConstructor 1.000000 - 35 2023-11-15 13:34:57,272 - mmdet - INFO - Param groups = { "layer_0_decay": { "param_names": [ "backbone.patch_embed.conv1.weight", "backbone.patch_embed.conv2.weight" ], "lr_scale": 1.0, "lr": 0.0002, "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": 1.0, "lr": 0.0002, "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": 1.0, "lr": 0.0002, "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": 1.0, "lr": 0.0002, "weight_decay": 0.05 }, "layer_1_decay_offset_lr_scale": { "param_names": [ "backbone.levels.0.blocks.0.dcn.offset_mask.weight" ], "lr_scale": 1.0, "lr": 0.0002, "weight_decay": 0.05 }, "layer_1_no_decay_offset_lr_scale": { "param_names": [ "backbone.levels.0.blocks.0.dcn.offset_mask.bias" ], "lr_scale": 1.0, "lr": 0.0002, "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": 1.0, "lr": 0.0002, "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": 1.0, "lr": 0.0002, "weight_decay": 0.05 }, "layer_2_decay_offset_lr_scale": { "param_names": [ "backbone.levels.0.blocks.1.dcn.offset_mask.weight" ], "lr_scale": 1.0, "lr": 0.0002, "weight_decay": 0.05 }, "layer_2_no_decay_offset_lr_scale": { "param_names": [ "backbone.levels.0.blocks.1.dcn.offset_mask.bias" ], "lr_scale": 1.0, "lr": 0.0002, "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": 1.0, "lr": 0.0002, "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": 1.0, "lr": 0.0002, "weight_decay": 0.05 }, "layer_3_decay_offset_lr_scale": { "param_names": [ "backbone.levels.0.blocks.2.dcn.offset_mask.weight" ], "lr_scale": 1.0, "lr": 0.0002, "weight_decay": 0.05 }, "layer_3_no_decay_offset_lr_scale": { "param_names": [ "backbone.levels.0.blocks.2.dcn.offset_mask.bias" ], "lr_scale": 1.0, "lr": 0.0002, "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": 1.0, "lr": 0.0002, "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": 1.0, "lr": 0.0002, "weight_decay": 0.05 }, "layer_4_decay_offset_lr_scale": { "param_names": [ "backbone.levels.0.blocks.3.dcn.offset_mask.weight" ], "lr_scale": 1.0, "lr": 0.0002, "weight_decay": 0.05 }, "layer_4_no_decay_offset_lr_scale": { "param_names": [ "backbone.levels.0.blocks.3.dcn.offset_mask.bias" ], "lr_scale": 1.0, "lr": 0.0002, "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": 1.0, "lr": 0.0002, "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": 1.0, "lr": 0.0002, "weight_decay": 0.0 }, "layer_5_decay_offset_lr_scale": { "param_names": [ "backbone.levels.1.blocks.0.dcn.offset_mask.weight" ], "lr_scale": 1.0, "lr": 0.0002, "weight_decay": 0.05 }, "layer_5_no_decay_offset_lr_scale": { "param_names": [ "backbone.levels.1.blocks.0.dcn.offset_mask.bias" ], "lr_scale": 1.0, "lr": 0.0002, "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": 1.0, "lr": 0.0002, "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": 1.0, "lr": 0.0002, "weight_decay": 0.05 }, "layer_6_decay_offset_lr_scale": { "param_names": [ "backbone.levels.1.blocks.1.dcn.offset_mask.weight" ], "lr_scale": 1.0, "lr": 0.0002, "weight_decay": 0.05 }, "layer_6_no_decay_offset_lr_scale": { "param_names": [ "backbone.levels.1.blocks.1.dcn.offset_mask.bias" ], "lr_scale": 1.0, "lr": 0.0002, "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": 1.0, "lr": 0.0002, "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": 1.0, "lr": 0.0002, "weight_decay": 0.05 }, "layer_7_decay_offset_lr_scale": { "param_names": [ "backbone.levels.1.blocks.2.dcn.offset_mask.weight" ], "lr_scale": 1.0, "lr": 0.0002, "weight_decay": 0.05 }, "layer_7_no_decay_offset_lr_scale": { "param_names": [ "backbone.levels.1.blocks.2.dcn.offset_mask.bias" ], "lr_scale": 1.0, "lr": 0.0002, "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": 1.0, "lr": 0.0002, "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": 1.0, "lr": 0.0002, "weight_decay": 0.05 }, "layer_8_decay_offset_lr_scale": { "param_names": [ "backbone.levels.1.blocks.3.dcn.offset_mask.weight" ], "lr_scale": 1.0, "lr": 0.0002, "weight_decay": 0.05 }, "layer_8_no_decay_offset_lr_scale": { "param_names": [ "backbone.levels.1.blocks.3.dcn.offset_mask.bias" ], "lr_scale": 1.0, "lr": 0.0002, "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": 1.0, "lr": 0.0002, "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": 1.0, "lr": 0.0002, "weight_decay": 0.0 }, "layer_9_decay_offset_lr_scale": { "param_names": [ "backbone.levels.2.blocks.0.dcn.offset_mask.weight" ], "lr_scale": 1.0, "lr": 0.0002, "weight_decay": 0.05 }, "layer_9_no_decay_offset_lr_scale": { "param_names": [ "backbone.levels.2.blocks.0.dcn.offset_mask.bias" ], "lr_scale": 1.0, "lr": 0.0002, "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": 1.0, "lr": 0.0002, "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": 1.0, "lr": 0.0002, "weight_decay": 0.05 }, "layer_10_decay_offset_lr_scale": { "param_names": [ "backbone.levels.2.blocks.1.dcn.offset_mask.weight" ], "lr_scale": 1.0, "lr": 0.0002, "weight_decay": 0.05 }, "layer_10_no_decay_offset_lr_scale": { "param_names": [ "backbone.levels.2.blocks.1.dcn.offset_mask.bias" ], "lr_scale": 1.0, "lr": 0.0002, "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": 1.0, "lr": 0.0002, "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": 1.0, "lr": 0.0002, "weight_decay": 0.05 }, "layer_11_decay_offset_lr_scale": { "param_names": [ "backbone.levels.2.blocks.2.dcn.offset_mask.weight" ], "lr_scale": 1.0, "lr": 0.0002, "weight_decay": 0.05 }, "layer_11_no_decay_offset_lr_scale": { "param_names": [ "backbone.levels.2.blocks.2.dcn.offset_mask.bias" ], "lr_scale": 1.0, "lr": 0.0002, "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": 1.0, "lr": 0.0002, "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": 1.0, "lr": 0.0002, "weight_decay": 0.05 }, "layer_12_decay_offset_lr_scale": { "param_names": [ "backbone.levels.2.blocks.3.dcn.offset_mask.weight" ], "lr_scale": 1.0, "lr": 0.0002, "weight_decay": 0.05 }, "layer_12_no_decay_offset_lr_scale": { "param_names": [ "backbone.levels.2.blocks.3.dcn.offset_mask.bias" ], "lr_scale": 1.0, "lr": 0.0002, "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": 1.0, "lr": 0.0002, "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": 1.0, "lr": 0.0002, "weight_decay": 0.05 }, "layer_13_decay_offset_lr_scale": { "param_names": [ "backbone.levels.2.blocks.4.dcn.offset_mask.weight" ], "lr_scale": 1.0, "lr": 0.0002, "weight_decay": 0.05 }, "layer_13_no_decay_offset_lr_scale": { "param_names": [ "backbone.levels.2.blocks.4.dcn.offset_mask.bias" ], "lr_scale": 1.0, "lr": 0.0002, "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": 1.0, "lr": 0.0002, "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": 1.0, "lr": 0.0002, "weight_decay": 0.05 }, "layer_14_decay_offset_lr_scale": { "param_names": [ "backbone.levels.2.blocks.5.dcn.offset_mask.weight" ], "lr_scale": 1.0, "lr": 0.0002, "weight_decay": 0.05 }, "layer_14_no_decay_offset_lr_scale": { "param_names": [ "backbone.levels.2.blocks.5.dcn.offset_mask.bias" ], "lr_scale": 1.0, "lr": 0.0002, "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": 1.0, "lr": 0.0002, "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": 1.0, "lr": 0.0002, "weight_decay": 0.05 }, "layer_15_decay_offset_lr_scale": { "param_names": [ "backbone.levels.2.blocks.6.dcn.offset_mask.weight" ], "lr_scale": 1.0, "lr": 0.0002, "weight_decay": 0.05 }, "layer_15_no_decay_offset_lr_scale": { "param_names": [ "backbone.levels.2.blocks.6.dcn.offset_mask.bias" ], "lr_scale": 1.0, "lr": 0.0002, "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": 1.0, "lr": 0.0002, "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": 1.0, "lr": 0.0002, "weight_decay": 0.05 }, "layer_16_decay_offset_lr_scale": { "param_names": [ "backbone.levels.2.blocks.7.dcn.offset_mask.weight" ], "lr_scale": 1.0, "lr": 0.0002, "weight_decay": 0.05 }, "layer_16_no_decay_offset_lr_scale": { "param_names": [ "backbone.levels.2.blocks.7.dcn.offset_mask.bias" ], "lr_scale": 1.0, "lr": 0.0002, "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": 1.0, "lr": 0.0002, "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": 1.0, "lr": 0.0002, "weight_decay": 0.05 }, "layer_17_decay_offset_lr_scale": { "param_names": [ "backbone.levels.2.blocks.8.dcn.offset_mask.weight" ], "lr_scale": 1.0, "lr": 0.0002, "weight_decay": 0.05 }, "layer_17_no_decay_offset_lr_scale": { "param_names": [ "backbone.levels.2.blocks.8.dcn.offset_mask.bias" ], "lr_scale": 1.0, "lr": 0.0002, "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": 1.0, "lr": 0.0002, "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": 1.0, "lr": 0.0002, "weight_decay": 0.05 }, "layer_18_decay_offset_lr_scale": { "param_names": [ "backbone.levels.2.blocks.9.dcn.offset_mask.weight" ], "lr_scale": 1.0, "lr": 0.0002, "weight_decay": 0.05 }, "layer_18_no_decay_offset_lr_scale": { "param_names": [ "backbone.levels.2.blocks.9.dcn.offset_mask.bias" ], "lr_scale": 1.0, "lr": 0.0002, "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": 1.0, "lr": 0.0002, "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": 1.0, "lr": 0.0002, "weight_decay": 0.05 }, "layer_19_decay_offset_lr_scale": { "param_names": [ "backbone.levels.2.blocks.10.dcn.offset_mask.weight" ], "lr_scale": 1.0, "lr": 0.0002, "weight_decay": 0.05 }, "layer_19_no_decay_offset_lr_scale": { "param_names": [ "backbone.levels.2.blocks.10.dcn.offset_mask.bias" ], "lr_scale": 1.0, "lr": 0.0002, "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": 1.0, "lr": 0.0002, "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": 1.0, "lr": 0.0002, "weight_decay": 0.05 }, "layer_20_decay_offset_lr_scale": { "param_names": [ "backbone.levels.2.blocks.11.dcn.offset_mask.weight" ], "lr_scale": 1.0, "lr": 0.0002, "weight_decay": 0.05 }, "layer_20_no_decay_offset_lr_scale": { "param_names": [ "backbone.levels.2.blocks.11.dcn.offset_mask.bias" ], "lr_scale": 1.0, "lr": 0.0002, "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": 1.0, "lr": 0.0002, "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": 1.0, "lr": 0.0002, "weight_decay": 0.05 }, "layer_21_decay_offset_lr_scale": { "param_names": [ "backbone.levels.2.blocks.12.dcn.offset_mask.weight" ], "lr_scale": 1.0, "lr": 0.0002, "weight_decay": 0.05 }, "layer_21_no_decay_offset_lr_scale": { "param_names": [ "backbone.levels.2.blocks.12.dcn.offset_mask.bias" ], "lr_scale": 1.0, "lr": 0.0002, "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": 1.0, "lr": 0.0002, "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": 1.0, "lr": 0.0002, "weight_decay": 0.05 }, "layer_22_decay_offset_lr_scale": { "param_names": [ "backbone.levels.2.blocks.13.dcn.offset_mask.weight" ], "lr_scale": 1.0, "lr": 0.0002, "weight_decay": 0.05 }, "layer_22_no_decay_offset_lr_scale": { "param_names": [ "backbone.levels.2.blocks.13.dcn.offset_mask.bias" ], "lr_scale": 1.0, "lr": 0.0002, "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": 1.0, "lr": 0.0002, "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": 1.0, "lr": 0.0002, "weight_decay": 0.05 }, "layer_23_decay_offset_lr_scale": { "param_names": [ "backbone.levels.2.blocks.14.dcn.offset_mask.weight" ], "lr_scale": 1.0, "lr": 0.0002, "weight_decay": 0.05 }, "layer_23_no_decay_offset_lr_scale": { "param_names": [ "backbone.levels.2.blocks.14.dcn.offset_mask.bias" ], "lr_scale": 1.0, "lr": 0.0002, "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": 1.0, "lr": 0.0002, "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": 1.0, "lr": 0.0002, "weight_decay": 0.05 }, "layer_24_decay_offset_lr_scale": { "param_names": [ "backbone.levels.2.blocks.15.dcn.offset_mask.weight" ], "lr_scale": 1.0, "lr": 0.0002, "weight_decay": 0.05 }, "layer_24_no_decay_offset_lr_scale": { "param_names": [ "backbone.levels.2.blocks.15.dcn.offset_mask.bias" ], "lr_scale": 1.0, "lr": 0.0002, "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": 1.0, "lr": 0.0002, "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": 1.0, "lr": 0.0002, "weight_decay": 0.05 }, "layer_25_decay_offset_lr_scale": { "param_names": [ "backbone.levels.2.blocks.16.dcn.offset_mask.weight" ], "lr_scale": 1.0, "lr": 0.0002, "weight_decay": 0.05 }, "layer_25_no_decay_offset_lr_scale": { "param_names": [ "backbone.levels.2.blocks.16.dcn.offset_mask.bias" ], "lr_scale": 1.0, "lr": 0.0002, "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": 1.0, "lr": 0.0002, "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": 1.0, "lr": 0.0002, "weight_decay": 0.05 }, "layer_26_decay_offset_lr_scale": { "param_names": [ "backbone.levels.2.blocks.17.dcn.offset_mask.weight" ], "lr_scale": 1.0, "lr": 0.0002, "weight_decay": 0.05 }, "layer_26_no_decay_offset_lr_scale": { "param_names": [ "backbone.levels.2.blocks.17.dcn.offset_mask.bias" ], "lr_scale": 1.0, "lr": 0.0002, "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": 1.0, "lr": 0.0002, "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": 1.0, "lr": 0.0002, "weight_decay": 0.05 }, "layer_27_decay_offset_lr_scale": { "param_names": [ "backbone.levels.2.blocks.18.dcn.offset_mask.weight" ], "lr_scale": 1.0, "lr": 0.0002, "weight_decay": 0.05 }, "layer_27_no_decay_offset_lr_scale": { "param_names": [ "backbone.levels.2.blocks.18.dcn.offset_mask.bias" ], "lr_scale": 1.0, "lr": 0.0002, "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": 1.0, "lr": 0.0002, "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": 1.0, "lr": 0.0002, "weight_decay": 0.05 }, "layer_28_decay_offset_lr_scale": { "param_names": [ "backbone.levels.2.blocks.19.dcn.offset_mask.weight" ], "lr_scale": 1.0, "lr": 0.0002, "weight_decay": 0.05 }, "layer_28_no_decay_offset_lr_scale": { "param_names": [ "backbone.levels.2.blocks.19.dcn.offset_mask.bias" ], "lr_scale": 1.0, "lr": 0.0002, "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": 1.0, "lr": 0.0002, "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": 1.0, "lr": 0.0002, "weight_decay": 0.05 }, "layer_29_decay_offset_lr_scale": { "param_names": [ "backbone.levels.2.blocks.20.dcn.offset_mask.weight" ], "lr_scale": 1.0, "lr": 0.0002, "weight_decay": 0.05 }, "layer_29_no_decay_offset_lr_scale": { "param_names": [ "backbone.levels.2.blocks.20.dcn.offset_mask.bias" ], "lr_scale": 1.0, "lr": 0.0002, "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": 1.0, "lr": 0.0002, "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": 1.0, "lr": 0.0002, "weight_decay": 0.0 }, "layer_30_decay_offset_lr_scale": { "param_names": [ "backbone.levels.3.blocks.0.dcn.offset_mask.weight" ], "lr_scale": 1.0, "lr": 0.0002, "weight_decay": 0.05 }, "layer_30_no_decay_offset_lr_scale": { "param_names": [ "backbone.levels.3.blocks.0.dcn.offset_mask.bias" ], "lr_scale": 1.0, "lr": 0.0002, "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": 1.0, "lr": 0.0002, "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": 1.0, "lr": 0.0002, "weight_decay": 0.05 }, "layer_31_decay_offset_lr_scale": { "param_names": [ "backbone.levels.3.blocks.1.dcn.offset_mask.weight" ], "lr_scale": 1.0, "lr": 0.0002, "weight_decay": 0.05 }, "layer_31_no_decay_offset_lr_scale": { "param_names": [ "backbone.levels.3.blocks.1.dcn.offset_mask.bias" ], "lr_scale": 1.0, "lr": 0.0002, "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": 1.0, "lr": 0.0002, "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": 1.0, "lr": 0.0002, "weight_decay": 0.05 }, "layer_32_decay_offset_lr_scale": { "param_names": [ "backbone.levels.3.blocks.2.dcn.offset_mask.weight" ], "lr_scale": 1.0, "lr": 0.0002, "weight_decay": 0.05 }, "layer_32_no_decay_offset_lr_scale": { "param_names": [ "backbone.levels.3.blocks.2.dcn.offset_mask.bias" ], "lr_scale": 1.0, "lr": 0.0002, "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": 1.0, "lr": 0.0002, "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": 1.0, "lr": 0.0002, "weight_decay": 0.05 }, "layer_33_decay_offset_lr_scale": { "param_names": [ "backbone.levels.3.blocks.3.dcn.offset_mask.weight" ], "lr_scale": 1.0, "lr": 0.0002, "weight_decay": 0.05 }, "layer_33_no_decay_offset_lr_scale": { "param_names": [ "backbone.levels.3.blocks.3.dcn.offset_mask.bias" ], "lr_scale": 1.0, "lr": 0.0002, "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 } } 2023-11-15 13:34:57,767 - mmdet - INFO - Start running, host: lizhiqi@SH-IDC1-10-140-37-105, work_dir: /mnt/petrelfs/lizhiqi/DINO/detection/work_dirs/mask_rcnn_flash_internimage_s_fpn_3x_coco_0.4 2023-11-15 13:34:57,768 - 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 -------------------- 2023-11-15 13:34:57,768 - mmdet - INFO - workflow: [('train', 1)], max: 36 epochs 2023-11-15 13:34:57,768 - mmdet - INFO - Checkpoints will be saved to /mnt/petrelfs/lizhiqi/DINO/detection/work_dirs/mask_rcnn_flash_internimage_s_fpn_3x_coco_0.4 by HardDiskBackend. 2023-11-15 13:36:03,389 - mmdet - INFO - Epoch [1][50/1833] lr: 1.978e-05, eta: 1 day, 0:02:08, time: 1.312, data_time: 0.140, memory: 13747, loss_rpn_cls: 0.6318, loss_rpn_bbox: 0.0799, loss_cls: 2.3118, acc: 87.2625, loss_bbox: 0.0809, loss_mask: 0.7328, loss: 3.8372 2023-11-15 13:37:03,553 - mmdet - INFO - Epoch [1][100/1833] lr: 3.976e-05, eta: 23:01:12, time: 1.203, data_time: 0.094, memory: 13747, loss_rpn_cls: 0.3160, loss_rpn_bbox: 0.0800, loss_cls: 0.4698, acc: 94.0131, loss_bbox: 0.2113, loss_mask: 0.6794, loss: 1.7565 2023-11-15 13:38:02,302 - mmdet - INFO - Epoch [1][150/1833] lr: 5.974e-05, eta: 22:29:50, time: 1.175, data_time: 0.074, memory: 13823, loss_rpn_cls: 0.1840, loss_rpn_bbox: 0.0789, loss_cls: 0.4628, acc: 92.5727, loss_bbox: 0.2733, loss_mask: 0.6256, loss: 1.6246 2023-11-15 13:39:01,200 - mmdet - INFO - Epoch [1][200/1833] lr: 7.972e-05, eta: 22:14:29, time: 1.178, data_time: 0.078, memory: 13823, loss_rpn_cls: 0.1173, loss_rpn_bbox: 0.0743, loss_cls: 0.4831, acc: 91.5405, loss_bbox: 0.3228, loss_mask: 0.5644, loss: 1.5618 2023-11-15 13:40:00,781 - mmdet - INFO - Epoch [1][250/1833] lr: 9.970e-05, eta: 22:07:54, time: 1.192, data_time: 0.077, memory: 14126, loss_rpn_cls: 0.0973, loss_rpn_bbox: 0.0729, loss_cls: 0.4759, acc: 90.8941, loss_bbox: 0.3477, loss_mask: 0.5012, loss: 1.4951 2023-11-15 13:40:59,757 - mmdet - INFO - Epoch [1][300/1833] lr: 1.197e-04, eta: 22:00:57, time: 1.180, data_time: 0.090, memory: 14497, loss_rpn_cls: 0.0842, loss_rpn_bbox: 0.0660, loss_cls: 0.4312, acc: 90.4229, loss_bbox: 0.3535, loss_mask: 0.4467, loss: 1.3816 2023-11-15 13:41:57,541 - mmdet - INFO - Epoch [1][350/1833] lr: 1.397e-04, eta: 21:52:00, time: 1.156, data_time: 0.078, memory: 14874, loss_rpn_cls: 0.0762, loss_rpn_bbox: 0.0633, loss_cls: 0.3887, acc: 90.0533, loss_bbox: 0.3623, loss_mask: 0.4164, loss: 1.3068 2023-11-15 13:42:56,344 - mmdet - INFO - Epoch [1][400/1833] lr: 1.596e-04, eta: 21:47:48, time: 1.176, data_time: 0.076, memory: 14874, loss_rpn_cls: 0.0691, loss_rpn_bbox: 0.0604, loss_cls: 0.3556, acc: 90.2200, loss_bbox: 0.3537, loss_mask: 0.3986, loss: 1.2374 2023-11-15 13:43:54,624 - mmdet - INFO - Epoch [1][450/1833] lr: 1.796e-04, eta: 21:43:05, time: 1.166, data_time: 0.069, memory: 14874, loss_rpn_cls: 0.0692, loss_rpn_bbox: 0.0595, loss_cls: 0.3364, acc: 90.2536, loss_bbox: 0.3516, loss_mask: 0.3818, loss: 1.1985 2023-11-15 13:44:54,066 - mmdet - INFO - Epoch [1][500/1833] lr: 1.996e-04, eta: 21:41:38, time: 1.189, data_time: 0.076, memory: 14874, loss_rpn_cls: 0.0668, loss_rpn_bbox: 0.0591, loss_cls: 0.3174, acc: 90.3878, loss_bbox: 0.3519, loss_mask: 0.3646, loss: 1.1599 2023-11-15 13:45:53,082 - mmdet - INFO - Epoch [1][550/1833] lr: 2.000e-04, eta: 21:39:26, time: 1.180, data_time: 0.083, memory: 14874, loss_rpn_cls: 0.0636, loss_rpn_bbox: 0.0590, loss_cls: 0.3090, acc: 90.5594, loss_bbox: 0.3408, loss_mask: 0.3561, loss: 1.1284 2023-11-15 13:46:50,659 - mmdet - INFO - Epoch [1][600/1833] lr: 2.000e-04, eta: 21:34:48, time: 1.151, data_time: 0.068, memory: 14874, loss_rpn_cls: 0.0594, loss_rpn_bbox: 0.0559, loss_cls: 0.2982, acc: 90.7421, loss_bbox: 0.3295, loss_mask: 0.3450, loss: 1.0880 2023-11-15 13:47:49,301 - mmdet - INFO - Epoch [1][650/1833] lr: 2.000e-04, eta: 21:32:32, time: 1.173, data_time: 0.083, memory: 14874, loss_rpn_cls: 0.0576, loss_rpn_bbox: 0.0559, loss_cls: 0.2952, acc: 90.7638, loss_bbox: 0.3306, loss_mask: 0.3415, loss: 1.0807 2023-11-15 13:48:49,068 - mmdet - INFO - Epoch [1][700/1833] lr: 2.000e-04, eta: 21:32:12, time: 1.195, data_time: 0.088, memory: 14874, loss_rpn_cls: 0.0581, loss_rpn_bbox: 0.0566, loss_cls: 0.2962, acc: 90.6279, loss_bbox: 0.3312, loss_mask: 0.3320, loss: 1.0741 2023-11-15 13:49:48,614 - mmdet - INFO - Epoch [1][750/1833] lr: 2.000e-04, eta: 21:31:27, time: 1.191, data_time: 0.083, memory: 14874, loss_rpn_cls: 0.0592, loss_rpn_bbox: 0.0559, loss_cls: 0.2896, acc: 90.7877, loss_bbox: 0.3242, loss_mask: 0.3289, loss: 1.0578 2023-11-15 13:50:47,623 - mmdet - INFO - Epoch [1][800/1833] lr: 2.000e-04, eta: 21:29:57, time: 1.180, data_time: 0.076, memory: 14874, loss_rpn_cls: 0.0536, loss_rpn_bbox: 0.0524, loss_cls: 0.2807, acc: 90.9749, loss_bbox: 0.3155, loss_mask: 0.3226, loss: 1.0248 2023-11-15 13:51:47,059 - mmdet - INFO - Epoch [1][850/1833] lr: 2.000e-04, eta: 21:29:03, time: 1.189, data_time: 0.073, memory: 14876, loss_rpn_cls: 0.0552, loss_rpn_bbox: 0.0540, loss_cls: 0.2749, acc: 91.1953, loss_bbox: 0.3060, loss_mask: 0.3162, loss: 1.0063 2023-11-15 13:52:46,683 - mmdet - INFO - Epoch [1][900/1833] lr: 2.000e-04, eta: 21:28:22, time: 1.192, data_time: 0.085, memory: 14876, loss_rpn_cls: 0.0540, loss_rpn_bbox: 0.0536, loss_cls: 0.2729, acc: 91.2281, loss_bbox: 0.3060, loss_mask: 0.3153, loss: 1.0018 2023-11-15 13:53:46,488 - mmdet - INFO - Epoch [1][950/1833] lr: 2.000e-04, eta: 21:27:51, time: 1.196, data_time: 0.076, memory: 14876, loss_rpn_cls: 0.0511, loss_rpn_bbox: 0.0516, loss_cls: 0.2702, acc: 91.2120, loss_bbox: 0.3058, loss_mask: 0.3071, loss: 0.9857 2023-11-15 13:54:45,271 - mmdet - INFO - Exp name: mask_rcnn_flash_internimage_s_fpn_3x_coco_0.4.py 2023-11-15 13:54:45,271 - mmdet - INFO - Epoch [1][1000/1833] lr: 2.000e-04, eta: 21:26:11, time: 1.176, data_time: 0.084, memory: 14876, loss_rpn_cls: 0.0531, loss_rpn_bbox: 0.0513, loss_cls: 0.2704, acc: 91.2875, loss_bbox: 0.3063, loss_mask: 0.3117, loss: 0.9928 2023-11-15 13:55:43,733 - mmdet - INFO - Epoch [1][1050/1833] lr: 2.000e-04, eta: 21:24:16, time: 1.169, data_time: 0.077, memory: 14876, loss_rpn_cls: 0.0510, loss_rpn_bbox: 0.0507, loss_cls: 0.2679, acc: 91.2899, loss_bbox: 0.3046, loss_mask: 0.3064, loss: 0.9805 2023-11-15 13:56:42,059 - mmdet - INFO - Epoch [1][1100/1833] lr: 2.000e-04, eta: 21:22:17, time: 1.167, data_time: 0.079, memory: 14876, loss_rpn_cls: 0.0489, loss_rpn_bbox: 0.0499, loss_cls: 0.2633, acc: 91.4725, loss_bbox: 0.2965, loss_mask: 0.3015, loss: 0.9602 2023-11-15 13:57:41,365 - mmdet - INFO - Epoch [1][1150/1833] lr: 2.000e-04, eta: 21:21:19, time: 1.186, data_time: 0.080, memory: 14876, loss_rpn_cls: 0.0515, loss_rpn_bbox: 0.0511, loss_cls: 0.2647, acc: 91.3652, loss_bbox: 0.3012, loss_mask: 0.3042, loss: 0.9726 2023-11-15 13:58:40,336 - mmdet - INFO - Epoch [1][1200/1833] lr: 2.000e-04, eta: 21:20:03, time: 1.179, data_time: 0.070, memory: 14876, loss_rpn_cls: 0.0498, loss_rpn_bbox: 0.0509, loss_cls: 0.2584, acc: 91.4805, loss_bbox: 0.2970, loss_mask: 0.3034, loss: 0.9595 2023-11-15 13:59:40,143 - mmdet - INFO - Epoch [1][1250/1833] lr: 2.000e-04, eta: 21:19:31, time: 1.196, data_time: 0.079, memory: 14876, loss_rpn_cls: 0.0497, loss_rpn_bbox: 0.0512, loss_cls: 0.2644, acc: 91.3287, loss_bbox: 0.3021, loss_mask: 0.3013, loss: 0.9688 2023-11-15 14:00:38,936 - mmdet - INFO - Epoch [1][1300/1833] lr: 2.000e-04, eta: 21:18:07, time: 1.176, data_time: 0.074, memory: 14876, loss_rpn_cls: 0.0485, loss_rpn_bbox: 0.0499, loss_cls: 0.2638, acc: 91.3410, loss_bbox: 0.2990, loss_mask: 0.2996, loss: 0.9608 2023-11-15 14:01:37,241 - mmdet - INFO - Epoch [1][1350/1833] lr: 2.000e-04, eta: 21:16:21, time: 1.166, data_time: 0.088, memory: 16000, loss_rpn_cls: 0.0491, loss_rpn_bbox: 0.0491, loss_cls: 0.2565, acc: 91.4429, loss_bbox: 0.2964, loss_mask: 0.2950, loss: 0.9461 2023-11-15 14:02:37,145 - mmdet - INFO - Epoch [1][1400/1833] lr: 2.000e-04, eta: 21:15:52, time: 1.198, data_time: 0.078, memory: 16000, loss_rpn_cls: 0.0481, loss_rpn_bbox: 0.0483, loss_cls: 0.2661, acc: 91.3378, loss_bbox: 0.2969, loss_mask: 0.2963, loss: 0.9557 2023-11-15 14:03:37,211 - mmdet - INFO - Epoch [1][1450/1833] lr: 2.000e-04, eta: 21:15:29, time: 1.201, data_time: 0.082, memory: 16000, loss_rpn_cls: 0.0464, loss_rpn_bbox: 0.0470, loss_cls: 0.2522, acc: 91.6769, loss_bbox: 0.2858, loss_mask: 0.2918, loss: 0.9232 2023-11-15 14:04:36,391 - mmdet - INFO - Epoch [1][1500/1833] lr: 2.000e-04, eta: 21:14:25, time: 1.184, data_time: 0.084, memory: 16000, loss_rpn_cls: 0.0460, loss_rpn_bbox: 0.0482, loss_cls: 0.2550, acc: 91.5651, loss_bbox: 0.2940, loss_mask: 0.2937, loss: 0.9369 2023-11-15 14:05:34,858 - mmdet - INFO - Epoch [1][1550/1833] lr: 2.000e-04, eta: 21:12:52, time: 1.169, data_time: 0.071, memory: 16000, loss_rpn_cls: 0.0465, loss_rpn_bbox: 0.0482, loss_cls: 0.2503, acc: 91.6886, loss_bbox: 0.2922, loss_mask: 0.2892, loss: 0.9265 2023-11-15 14:06:33,870 - mmdet - INFO - Epoch [1][1600/1833] lr: 2.000e-04, eta: 21:11:42, time: 1.180, data_time: 0.071, memory: 16000, loss_rpn_cls: 0.0468, loss_rpn_bbox: 0.0474, loss_cls: 0.2571, acc: 91.5317, loss_bbox: 0.2912, loss_mask: 0.2897, loss: 0.9322 2023-11-15 14:07:32,760 - mmdet - INFO - Epoch [1][1650/1833] lr: 2.000e-04, eta: 21:10:29, time: 1.178, data_time: 0.075, memory: 16000, loss_rpn_cls: 0.0461, loss_rpn_bbox: 0.0483, loss_cls: 0.2497, acc: 91.7017, loss_bbox: 0.2877, loss_mask: 0.2927, loss: 0.9245 2023-11-15 14:08:32,377 - mmdet - INFO - Epoch [1][1700/1833] lr: 2.000e-04, eta: 21:09:44, time: 1.192, data_time: 0.088, memory: 16000, loss_rpn_cls: 0.0459, loss_rpn_bbox: 0.0480, loss_cls: 0.2528, acc: 91.5209, loss_bbox: 0.2912, loss_mask: 0.2879, loss: 0.9257 2023-11-15 14:09:33,157 - mmdet - INFO - Epoch [1][1750/1833] lr: 2.000e-04, eta: 21:09:41, time: 1.216, data_time: 0.086, memory: 16000, loss_rpn_cls: 0.0465, loss_rpn_bbox: 0.0468, loss_cls: 0.2515, acc: 91.6110, loss_bbox: 0.2912, loss_mask: 0.2883, loss: 0.9243 2023-11-15 14:10:33,205 - mmdet - INFO - Epoch [1][1800/1833] lr: 2.000e-04, eta: 21:09:08, time: 1.201, data_time: 0.078, memory: 16000, loss_rpn_cls: 0.0472, loss_rpn_bbox: 0.0478, loss_cls: 0.2496, acc: 91.7360, loss_bbox: 0.2845, loss_mask: 0.2878, loss: 0.9170 2023-11-15 14:11:13,521 - mmdet - INFO - Saving checkpoint at 1 epochs 2023-11-15 14:12:09,653 - mmdet - INFO - Evaluating bbox... 2023-11-15 14:12:49,662 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.340 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.586 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.359 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.210 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.383 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.432 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.489 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.489 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.489 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.319 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.534 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.614 2023-11-15 14:12:49,666 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.495 | bicycle | 0.259 | car | 0.377 | | motorcycle | 0.349 | airplane | 0.513 | bus | 0.575 | | train | 0.511 | truck | 0.284 | boat | 0.207 | | traffic light | 0.257 | fire hydrant | 0.573 | stop sign | 0.498 | | parking meter | 0.426 | bench | 0.173 | bird | 0.330 | | cat | 0.572 | dog | 0.551 | horse | 0.475 | | sheep | 0.477 | cow | 0.472 | elephant | 0.594 | | bear | 0.596 | zebra | 0.580 | giraffe | 0.606 | | backpack | 0.128 | umbrella | 0.315 | handbag | 0.105 | | tie | 0.232 | suitcase | 0.290 | frisbee | 0.597 | | skis | 0.133 | snowboard | 0.227 | sports ball | 0.424 | | kite | 0.380 | baseball bat | 0.229 | baseball glove | 0.329 | | skateboard | 0.373 | surfboard | 0.268 | tennis racket | 0.377 | | bottle | 0.340 | wine glass | 0.287 | cup | 0.406 | | fork | 0.218 | knife | 0.119 | spoon | 0.091 | | bowl | 0.356 | banana | 0.188 | apple | 0.165 | | sandwich | 0.301 | orange | 0.247 | broccoli | 0.211 | | carrot | 0.172 | hot dog | 0.249 | pizza | 0.419 | | donut | 0.329 | cake | 0.297 | chair | 0.232 | | couch | 0.329 | potted plant | 0.217 | bed | 0.362 | | dining table | 0.198 | toilet | 0.454 | tv | 0.504 | | laptop | 0.503 | mouse | 0.546 | remote | 0.240 | | keyboard | 0.387 | cell phone | 0.315 | microwave | 0.503 | | oven | 0.246 | toaster | 0.275 | sink | 0.300 | | refrigerator | 0.402 | book | 0.105 | clock | 0.464 | | vase | 0.324 | scissors | 0.202 | teddy bear | 0.377 | | hair drier | 0.062 | toothbrush | 0.088 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-15 14:12:49,666 - mmdet - INFO - Evaluating segm... 2023-11-15 14:13:32,891 - 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 ] = 0.550 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.339 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.154 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.363 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.473 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.462 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.462 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.462 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.275 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.511 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.610 2023-11-15 14:13:32,893 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.431 | bicycle | 0.152 | car | 0.353 | | motorcycle | 0.272 | airplane | 0.433 | bus | 0.614 | | train | 0.550 | truck | 0.298 | boat | 0.188 | | traffic light | 0.241 | fire hydrant | 0.596 | stop sign | 0.560 | | parking meter | 0.450 | bench | 0.121 | bird | 0.280 | | cat | 0.628 | dog | 0.551 | horse | 0.359 | | sheep | 0.429 | cow | 0.413 | elephant | 0.531 | | bear | 0.672 | zebra | 0.473 | giraffe | 0.456 | | backpack | 0.148 | umbrella | 0.431 | handbag | 0.122 | | tie | 0.242 | suitcase | 0.314 | frisbee | 0.584 | | skis | 0.004 | snowboard | 0.144 | sports ball | 0.395 | | kite | 0.248 | baseball bat | 0.171 | baseball glove | 0.364 | | skateboard | 0.178 | surfboard | 0.233 | tennis racket | 0.497 | | bottle | 0.348 | wine glass | 0.263 | cup | 0.417 | | fork | 0.087 | knife | 0.076 | spoon | 0.052 | | bowl | 0.349 | banana | 0.141 | apple | 0.175 | | sandwich | 0.334 | orange | 0.263 | broccoli | 0.198 | | carrot | 0.160 | hot dog | 0.219 | pizza | 0.427 | | donut | 0.392 | cake | 0.341 | chair | 0.163 | | couch | 0.285 | potted plant | 0.186 | bed | 0.278 | | dining table | 0.107 | toilet | 0.520 | tv | 0.558 | | laptop | 0.565 | mouse | 0.551 | remote | 0.233 | | keyboard | 0.436 | cell phone | 0.312 | microwave | 0.564 | | oven | 0.246 | toaster | 0.334 | sink | 0.323 | | refrigerator | 0.440 | book | 0.064 | clock | 0.477 | | vase | 0.343 | scissors | 0.170 | teddy bear | 0.384 | | hair drier | 0.017 | toothbrush | 0.058 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-15 14:13:35,484 - mmdet - INFO - Now best checkpoint is saved as best_bbox_mAP_epoch_1.pth. 2023-11-15 14:13:35,485 - mmdet - INFO - Best bbox_mAP is 0.3398 at 1 epoch. 2023-11-15 14:13:35,485 - mmdet - INFO - Exp name: mask_rcnn_flash_internimage_s_fpn_3x_coco_0.4.py 2023-11-15 14:13:35,485 - mmdet - INFO - Epoch(val) [1][625] bbox_mAP: 0.3398, bbox_mAP_50: 0.5855, bbox_mAP_75: 0.3589, bbox_mAP_s: 0.2101, bbox_mAP_m: 0.3828, bbox_mAP_l: 0.4317, bbox_mAP_copypaste: 0.3398 0.5855 0.3589 0.2101 0.3828 0.4317, segm_mAP: 0.3247, segm_mAP_50: 0.5496, segm_mAP_75: 0.3394, segm_mAP_s: 0.1538, segm_mAP_m: 0.3634, segm_mAP_l: 0.4735, segm_mAP_copypaste: 0.3247 0.5496 0.3394 0.1538 0.3634 0.4735 2023-11-15 14:14:38,435 - mmdet - INFO - Epoch [2][50/1833] lr: 2.000e-04, eta: 20:47:20, time: 1.259, data_time: 0.137, memory: 16000, loss_rpn_cls: 0.0454, loss_rpn_bbox: 0.0468, loss_cls: 0.2372, acc: 92.0426, loss_bbox: 0.2782, loss_mask: 0.2797, loss: 0.8872 2023-11-15 14:15:41,676 - mmdet - INFO - Epoch [2][100/1833] lr: 2.000e-04, eta: 20:49:03, time: 1.265, data_time: 0.068, memory: 16000, loss_rpn_cls: 0.0439, loss_rpn_bbox: 0.0450, loss_cls: 0.2383, acc: 91.9764, loss_bbox: 0.2765, loss_mask: 0.2794, loss: 0.8830 2023-11-15 14:16:40,994 - mmdet - INFO - Epoch [2][150/1833] lr: 2.000e-04, eta: 20:48:31, time: 1.186, data_time: 0.070, memory: 16000, loss_rpn_cls: 0.0440, loss_rpn_bbox: 0.0453, loss_cls: 0.2370, acc: 91.9445, loss_bbox: 0.2784, loss_mask: 0.2820, loss: 0.8867 2023-11-15 14:17:42,654 - mmdet - INFO - Epoch [2][200/1833] lr: 2.000e-04, eta: 20:49:11, time: 1.233, data_time: 0.074, memory: 16000, loss_rpn_cls: 0.0453, loss_rpn_bbox: 0.0478, loss_cls: 0.2396, acc: 91.8936, loss_bbox: 0.2843, loss_mask: 0.2826, loss: 0.8996 2023-11-15 14:18:42,875 - mmdet - INFO - Epoch [2][250/1833] lr: 2.000e-04, eta: 20:49:02, time: 1.204, data_time: 0.071, memory: 16000, loss_rpn_cls: 0.0437, loss_rpn_bbox: 0.0450, loss_cls: 0.2351, acc: 92.1115, loss_bbox: 0.2745, loss_mask: 0.2809, loss: 0.8793 2023-11-15 14:19:43,220 - mmdet - INFO - Epoch [2][300/1833] lr: 2.000e-04, eta: 20:48:55, time: 1.207, data_time: 0.065, memory: 16000, loss_rpn_cls: 0.0428, loss_rpn_bbox: 0.0460, loss_cls: 0.2388, acc: 91.9602, loss_bbox: 0.2786, loss_mask: 0.2768, loss: 0.8830 2023-11-15 14:20:41,939 - mmdet - INFO - Epoch [2][350/1833] lr: 2.000e-04, eta: 20:47:57, time: 1.174, data_time: 0.079, memory: 16000, loss_rpn_cls: 0.0421, loss_rpn_bbox: 0.0462, loss_cls: 0.2411, acc: 91.9213, loss_bbox: 0.2747, loss_mask: 0.2835, loss: 0.8877 2023-11-15 14:21:41,348 - mmdet - INFO - Epoch [2][400/1833] lr: 2.000e-04, eta: 20:47:19, time: 1.188, data_time: 0.060, memory: 16000, loss_rpn_cls: 0.0421, loss_rpn_bbox: 0.0446, loss_cls: 0.2327, acc: 92.0862, loss_bbox: 0.2735, loss_mask: 0.2789, loss: 0.8718 2023-11-15 14:22:41,422 - mmdet - INFO - Epoch [2][450/1833] lr: 2.000e-04, eta: 20:46:59, time: 1.201, data_time: 0.073, memory: 16000, loss_rpn_cls: 0.0420, loss_rpn_bbox: 0.0454, loss_cls: 0.2318, acc: 92.2143, loss_bbox: 0.2692, loss_mask: 0.2767, loss: 0.8651 2023-11-15 14:23:41,304 - mmdet - INFO - Epoch [2][500/1833] lr: 2.000e-04, eta: 20:46:32, time: 1.198, data_time: 0.085, memory: 16000, loss_rpn_cls: 0.0411, loss_rpn_bbox: 0.0437, loss_cls: 0.2347, acc: 92.0677, loss_bbox: 0.2739, loss_mask: 0.2761, loss: 0.8696 2023-11-15 14:24:42,107 - mmdet - INFO - Epoch [2][550/1833] lr: 2.000e-04, eta: 20:46:28, time: 1.216, data_time: 0.082, memory: 16000, loss_rpn_cls: 0.0432, loss_rpn_bbox: 0.0449, loss_cls: 0.2408, acc: 91.9575, loss_bbox: 0.2773, loss_mask: 0.2811, loss: 0.8873 2023-11-15 14:25:41,215 - mmdet - INFO - Epoch [2][600/1833] lr: 2.000e-04, eta: 20:45:38, time: 1.182, data_time: 0.070, memory: 16000, loss_rpn_cls: 0.0408, loss_rpn_bbox: 0.0431, loss_cls: 0.2304, acc: 92.1682, loss_bbox: 0.2702, loss_mask: 0.2778, loss: 0.8623 2023-11-15 14:26:41,293 - mmdet - INFO - Epoch [2][650/1833] lr: 2.000e-04, eta: 20:45:11, time: 1.202, data_time: 0.072, memory: 16000, loss_rpn_cls: 0.0426, loss_rpn_bbox: 0.0456, loss_cls: 0.2336, acc: 92.0693, loss_bbox: 0.2738, loss_mask: 0.2763, loss: 0.8719 2023-11-15 14:27:41,111 - mmdet - INFO - Epoch [2][700/1833] lr: 2.000e-04, eta: 20:44:37, time: 1.196, data_time: 0.065, memory: 16000, loss_rpn_cls: 0.0421, loss_rpn_bbox: 0.0449, loss_cls: 0.2339, acc: 92.1348, loss_bbox: 0.2679, loss_mask: 0.2769, loss: 0.8656 2023-11-15 14:28:40,777 - mmdet - INFO - Epoch [2][750/1833] lr: 2.000e-04, eta: 20:43:59, time: 1.193, data_time: 0.076, memory: 16000, loss_rpn_cls: 0.0421, loss_rpn_bbox: 0.0443, loss_cls: 0.2360, acc: 92.0820, loss_bbox: 0.2700, loss_mask: 0.2778, loss: 0.8702 2023-11-15 14:29:40,857 - mmdet - INFO - Epoch [2][800/1833] lr: 2.000e-04, eta: 20:43:29, time: 1.201, data_time: 0.070, memory: 16000, loss_rpn_cls: 0.0425, loss_rpn_bbox: 0.0449, loss_cls: 0.2339, acc: 92.0798, loss_bbox: 0.2726, loss_mask: 0.2749, loss: 0.8688 2023-11-15 14:30:40,793 - mmdet - INFO - Epoch [2][850/1833] lr: 2.000e-04, eta: 20:42:55, time: 1.199, data_time: 0.064, memory: 16000, loss_rpn_cls: 0.0406, loss_rpn_bbox: 0.0433, loss_cls: 0.2287, acc: 92.2100, loss_bbox: 0.2664, loss_mask: 0.2735, loss: 0.8525 2023-11-15 14:31:40,615 - mmdet - INFO - Epoch [2][900/1833] lr: 2.000e-04, eta: 20:42:18, time: 1.197, data_time: 0.069, memory: 16000, loss_rpn_cls: 0.0397, loss_rpn_bbox: 0.0435, loss_cls: 0.2292, acc: 92.2095, loss_bbox: 0.2694, loss_mask: 0.2733, loss: 0.8551 2023-11-15 14:32:41,073 - mmdet - INFO - Epoch [2][950/1833] lr: 2.000e-04, eta: 20:41:54, time: 1.209, data_time: 0.077, memory: 16000, loss_rpn_cls: 0.0413, loss_rpn_bbox: 0.0424, loss_cls: 0.2272, acc: 92.2794, loss_bbox: 0.2665, loss_mask: 0.2731, loss: 0.8504 2023-11-15 14:33:42,054 - mmdet - INFO - Epoch [2][1000/1833] lr: 2.000e-04, eta: 20:41:40, time: 1.220, data_time: 0.066, memory: 16000, loss_rpn_cls: 0.0394, loss_rpn_bbox: 0.0426, loss_cls: 0.2268, acc: 92.2917, loss_bbox: 0.2657, loss_mask: 0.2699, loss: 0.8444 2023-11-15 14:34:42,316 - mmdet - INFO - Epoch [2][1050/1833] lr: 2.000e-04, eta: 20:41:09, time: 1.205, data_time: 0.070, memory: 16000, loss_rpn_cls: 0.0406, loss_rpn_bbox: 0.0431, loss_cls: 0.2248, acc: 92.3785, loss_bbox: 0.2652, loss_mask: 0.2705, loss: 0.8443 2023-11-15 14:35:44,325 - mmdet - INFO - Epoch [2][1100/1833] lr: 2.000e-04, eta: 20:41:15, time: 1.240, data_time: 0.073, memory: 16000, loss_rpn_cls: 0.0393, loss_rpn_bbox: 0.0428, loss_cls: 0.2254, acc: 92.2939, loss_bbox: 0.2677, loss_mask: 0.2710, loss: 0.8462 2023-11-15 14:36:45,082 - mmdet - INFO - Epoch [2][1150/1833] lr: 2.000e-04, eta: 20:40:52, time: 1.215, data_time: 0.064, memory: 16000, loss_rpn_cls: 0.0408, loss_rpn_bbox: 0.0447, loss_cls: 0.2301, acc: 92.1686, loss_bbox: 0.2693, loss_mask: 0.2747, loss: 0.8596 2023-11-15 14:37:46,140 - mmdet - INFO - Epoch [2][1200/1833] lr: 2.000e-04, eta: 20:40:33, time: 1.221, data_time: 0.073, memory: 16000, loss_rpn_cls: 0.0417, loss_rpn_bbox: 0.0439, loss_cls: 0.2341, acc: 92.1000, loss_bbox: 0.2721, loss_mask: 0.2740, loss: 0.8657 2023-11-15 14:38:46,685 - mmdet - INFO - Epoch [2][1250/1833] lr: 2.000e-04, eta: 20:40:03, time: 1.211, data_time: 0.078, memory: 16000, loss_rpn_cls: 0.0415, loss_rpn_bbox: 0.0440, loss_cls: 0.2335, acc: 92.0436, loss_bbox: 0.2691, loss_mask: 0.2703, loss: 0.8584 2023-11-15 14:39:46,751 - mmdet - INFO - Epoch [2][1300/1833] lr: 2.000e-04, eta: 20:39:23, time: 1.201, data_time: 0.070, memory: 16000, loss_rpn_cls: 0.0396, loss_rpn_bbox: 0.0428, loss_cls: 0.2247, acc: 92.3325, loss_bbox: 0.2622, loss_mask: 0.2659, loss: 0.8351 2023-11-15 14:40:46,190 - mmdet - INFO - Epoch [2][1350/1833] lr: 2.000e-04, eta: 20:38:29, time: 1.189, data_time: 0.082, memory: 16000, loss_rpn_cls: 0.0389, loss_rpn_bbox: 0.0432, loss_cls: 0.2293, acc: 92.1686, loss_bbox: 0.2688, loss_mask: 0.2678, loss: 0.8480 2023-11-15 14:41:45,379 - mmdet - INFO - Epoch [2][1400/1833] lr: 2.000e-04, eta: 20:37:31, time: 1.184, data_time: 0.069, memory: 16000, loss_rpn_cls: 0.0405, loss_rpn_bbox: 0.0428, loss_cls: 0.2261, acc: 92.3233, loss_bbox: 0.2640, loss_mask: 0.2698, loss: 0.8433 2023-11-15 14:42:45,623 - mmdet - INFO - Epoch [2][1450/1833] lr: 2.000e-04, eta: 20:36:52, time: 1.205, data_time: 0.073, memory: 16000, loss_rpn_cls: 0.0397, loss_rpn_bbox: 0.0437, loss_cls: 0.2266, acc: 92.3026, loss_bbox: 0.2611, loss_mask: 0.2689, loss: 0.8401 2023-11-15 14:43:45,726 - mmdet - INFO - Epoch [2][1500/1833] lr: 2.000e-04, eta: 20:36:11, time: 1.202, data_time: 0.069, memory: 16000, loss_rpn_cls: 0.0390, loss_rpn_bbox: 0.0428, loss_cls: 0.2245, acc: 92.3318, loss_bbox: 0.2634, loss_mask: 0.2675, loss: 0.8372 2023-11-15 14:44:45,029 - mmdet - INFO - Epoch [2][1550/1833] lr: 2.000e-04, eta: 20:35:13, time: 1.186, data_time: 0.065, memory: 16000, loss_rpn_cls: 0.0378, loss_rpn_bbox: 0.0412, loss_cls: 0.2220, acc: 92.4584, loss_bbox: 0.2593, loss_mask: 0.2651, loss: 0.8254 2023-11-15 14:45:45,470 - mmdet - INFO - Epoch [2][1600/1833] lr: 2.000e-04, eta: 20:34:37, time: 1.209, data_time: 0.074, memory: 16000, loss_rpn_cls: 0.0402, loss_rpn_bbox: 0.0437, loss_cls: 0.2308, acc: 92.2005, loss_bbox: 0.2657, loss_mask: 0.2706, loss: 0.8510 2023-11-15 14:46:45,633 - mmdet - INFO - Epoch [2][1650/1833] lr: 2.000e-04, eta: 20:33:55, time: 1.203, data_time: 0.073, memory: 16000, loss_rpn_cls: 0.0385, loss_rpn_bbox: 0.0417, loss_cls: 0.2233, acc: 92.3752, loss_bbox: 0.2598, loss_mask: 0.2687, loss: 0.8320 2023-11-15 14:47:45,578 - mmdet - INFO - Epoch [2][1700/1833] lr: 2.000e-04, eta: 20:33:08, time: 1.199, data_time: 0.073, memory: 16000, loss_rpn_cls: 0.0393, loss_rpn_bbox: 0.0420, loss_cls: 0.2224, acc: 92.4351, loss_bbox: 0.2616, loss_mask: 0.2662, loss: 0.8314 2023-11-15 14:48:45,884 - mmdet - INFO - Epoch [2][1750/1833] lr: 2.000e-04, eta: 20:32:28, time: 1.206, data_time: 0.075, memory: 16000, loss_rpn_cls: 0.0383, loss_rpn_bbox: 0.0415, loss_cls: 0.2260, acc: 92.3363, loss_bbox: 0.2628, loss_mask: 0.2667, loss: 0.8353 2023-11-15 14:49:45,959 - mmdet - INFO - Epoch [2][1800/1833] lr: 2.000e-04, eta: 20:31:43, time: 1.201, data_time: 0.076, memory: 16000, loss_rpn_cls: 0.0376, loss_rpn_bbox: 0.0412, loss_cls: 0.2188, acc: 92.5585, loss_bbox: 0.2549, loss_mask: 0.2653, loss: 0.8178 2023-11-15 14:50:26,440 - mmdet - INFO - Saving checkpoint at 2 epochs 2023-11-15 14:51:20,416 - mmdet - INFO - Evaluating bbox... 2023-11-15 14:51:58,635 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.389 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.633 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.422 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 ] = 0.435 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 ] = 0.536 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.536 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.536 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.370 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.584 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.661 2023-11-15 14:51:58,638 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.520 | bicycle | 0.306 | car | 0.423 | | motorcycle | 0.392 | airplane | 0.555 | bus | 0.648 | | train | 0.573 | truck | 0.288 | boat | 0.263 | | traffic light | 0.261 | fire hydrant | 0.661 | stop sign | 0.597 | | parking meter | 0.501 | bench | 0.216 | bird | 0.361 | | cat | 0.645 | dog | 0.578 | horse | 0.548 | | sheep | 0.492 | cow | 0.536 | elephant | 0.626 | | bear | 0.684 | zebra | 0.601 | giraffe | 0.625 | | backpack | 0.138 | umbrella | 0.348 | handbag | 0.146 | | tie | 0.287 | suitcase | 0.350 | frisbee | 0.600 | | skis | 0.179 | snowboard | 0.323 | sports ball | 0.449 | | kite | 0.396 | baseball bat | 0.301 | baseball glove | 0.379 | | skateboard | 0.447 | surfboard | 0.339 | tennis racket | 0.429 | | bottle | 0.387 | wine glass | 0.356 | cup | 0.434 | | fork | 0.299 | knife | 0.185 | spoon | 0.181 | | bowl | 0.386 | banana | 0.224 | apple | 0.158 | | sandwich | 0.389 | orange | 0.309 | broccoli | 0.237 | | carrot | 0.211 | hot dog | 0.317 | pizza | 0.445 | | donut | 0.474 | cake | 0.347 | chair | 0.282 | | couch | 0.357 | potted plant | 0.260 | bed | 0.382 | | dining table | 0.232 | toilet | 0.520 | tv | 0.545 | | laptop | 0.545 | mouse | 0.592 | remote | 0.304 | | keyboard | 0.446 | cell phone | 0.343 | microwave | 0.519 | | oven | 0.300 | toaster | 0.350 | sink | 0.367 | | refrigerator | 0.498 | book | 0.116 | clock | 0.483 | | vase | 0.359 | scissors | 0.289 | teddy bear | 0.417 | | hair drier | 0.107 | toothbrush | 0.163 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-15 14:51:58,638 - mmdet - INFO - Evaluating segm... 2023-11-15 14:52:41,901 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.363 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.598 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.384 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.185 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.405 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 ] = 0.499 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.499 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.499 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.314 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.553 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.643 2023-11-15 14:52:41,904 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.456 | bicycle | 0.172 | car | 0.398 | | motorcycle | 0.325 | airplane | 0.466 | bus | 0.649 | | train | 0.589 | truck | 0.296 | boat | 0.229 | | traffic light | 0.252 | fire hydrant | 0.641 | stop sign | 0.625 | | parking meter | 0.523 | bench | 0.166 | bird | 0.302 | | cat | 0.676 | dog | 0.565 | horse | 0.405 | | sheep | 0.444 | cow | 0.465 | elephant | 0.572 | | bear | 0.692 | zebra | 0.549 | giraffe | 0.466 | | backpack | 0.150 | umbrella | 0.457 | handbag | 0.152 | | tie | 0.271 | suitcase | 0.408 | frisbee | 0.609 | | skis | 0.018 | snowboard | 0.217 | sports ball | 0.420 | | kite | 0.271 | baseball bat | 0.225 | baseball glove | 0.401 | | skateboard | 0.274 | surfboard | 0.278 | tennis racket | 0.535 | | bottle | 0.371 | wine glass | 0.304 | cup | 0.446 | | fork | 0.162 | knife | 0.122 | spoon | 0.128 | | bowl | 0.377 | banana | 0.174 | apple | 0.163 | | sandwich | 0.410 | orange | 0.314 | broccoli | 0.227 | | carrot | 0.189 | hot dog | 0.293 | pizza | 0.434 | | donut | 0.492 | cake | 0.364 | chair | 0.201 | | couch | 0.320 | potted plant | 0.226 | bed | 0.316 | | dining table | 0.131 | toilet | 0.554 | tv | 0.584 | | laptop | 0.601 | mouse | 0.597 | remote | 0.281 | | keyboard | 0.464 | cell phone | 0.350 | microwave | 0.562 | | oven | 0.288 | toaster | 0.373 | sink | 0.353 | | refrigerator | 0.524 | book | 0.086 | clock | 0.496 | | vase | 0.367 | scissors | 0.237 | teddy bear | 0.439 | | hair drier | 0.020 | toothbrush | 0.103 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-15 14:52:42,467 - mmdet - INFO - The previous best checkpoint /mnt/petrelfs/lizhiqi/DINO/detection/work_dirs/mask_rcnn_flash_internimage_s_fpn_3x_coco_0.4/best_bbox_mAP_epoch_1.pth was removed 2023-11-15 14:52:44,551 - mmdet - INFO - Now best checkpoint is saved as best_bbox_mAP_epoch_2.pth. 2023-11-15 14:52:44,551 - mmdet - INFO - Best bbox_mAP is 0.3891 at 2 epoch. 2023-11-15 14:52:44,551 - mmdet - INFO - Exp name: mask_rcnn_flash_internimage_s_fpn_3x_coco_0.4.py 2023-11-15 14:52:44,551 - mmdet - INFO - Epoch(val) [2][625] bbox_mAP: 0.3891, bbox_mAP_50: 0.6329, bbox_mAP_75: 0.4215, bbox_mAP_s: 0.2578, bbox_mAP_m: 0.4349, bbox_mAP_l: 0.4912, bbox_mAP_copypaste: 0.3891 0.6329 0.4215 0.2578 0.4349 0.4912, segm_mAP: 0.3632, segm_mAP_50: 0.5980, segm_mAP_75: 0.3841, segm_mAP_s: 0.1853, segm_mAP_m: 0.4050, segm_mAP_l: 0.5267, segm_mAP_copypaste: 0.3632 0.5980 0.3841 0.1853 0.4050 0.5267 2023-11-15 14:53:47,905 - mmdet - INFO - Epoch [3][50/1833] lr: 2.000e-04, eta: 20:20:17, time: 1.267, data_time: 0.151, memory: 16000, loss_rpn_cls: 0.0385, loss_rpn_bbox: 0.0418, loss_cls: 0.2204, acc: 92.3981, loss_bbox: 0.2600, loss_mask: 0.2610, loss: 0.8217 2023-11-15 14:54:46,694 - mmdet - INFO - Epoch [3][100/1833] lr: 2.000e-04, eta: 20:19:18, time: 1.176, data_time: 0.081, memory: 16000, loss_rpn_cls: 0.0350, loss_rpn_bbox: 0.0397, loss_cls: 0.2114, acc: 92.6931, loss_bbox: 0.2498, loss_mask: 0.2644, loss: 0.8004 2023-11-15 14:55:45,591 - mmdet - INFO - Epoch [3][150/1833] lr: 2.000e-04, eta: 20:18:21, time: 1.178, data_time: 0.085, memory: 16000, loss_rpn_cls: 0.0375, loss_rpn_bbox: 0.0420, loss_cls: 0.2182, acc: 92.4825, loss_bbox: 0.2574, loss_mask: 0.2633, loss: 0.8185 2023-11-15 14:56:45,115 - mmdet - INFO - Epoch [3][200/1833] lr: 2.000e-04, eta: 20:17:34, time: 1.191, data_time: 0.075, memory: 16000, loss_rpn_cls: 0.0364, loss_rpn_bbox: 0.0411, loss_cls: 0.2145, acc: 92.6168, loss_bbox: 0.2528, loss_mask: 0.2614, loss: 0.8063 2023-11-15 14:57:45,435 - mmdet - INFO - Epoch [3][250/1833] lr: 2.000e-04, eta: 20:17:00, time: 1.206, data_time: 0.089, memory: 16000, loss_rpn_cls: 0.0383, loss_rpn_bbox: 0.0419, loss_cls: 0.2184, acc: 92.4617, loss_bbox: 0.2571, loss_mask: 0.2635, loss: 0.8193 2023-11-15 14:58:45,421 - mmdet - INFO - Epoch [3][300/1833] lr: 2.000e-04, eta: 20:16:19, time: 1.200, data_time: 0.085, memory: 16000, loss_rpn_cls: 0.0392, loss_rpn_bbox: 0.0428, loss_cls: 0.2237, acc: 92.2540, loss_bbox: 0.2636, loss_mask: 0.2651, loss: 0.8344 2023-11-15 14:59:44,620 - mmdet - INFO - Epoch [3][350/1833] lr: 2.000e-04, eta: 20:15:26, time: 1.184, data_time: 0.091, memory: 16000, loss_rpn_cls: 0.0371, loss_rpn_bbox: 0.0416, loss_cls: 0.2144, acc: 92.5226, loss_bbox: 0.2565, loss_mask: 0.2624, loss: 0.8121 2023-11-15 15:00:43,048 - mmdet - INFO - Epoch [3][400/1833] lr: 2.000e-04, eta: 20:14:21, time: 1.169, data_time: 0.087, memory: 16000, loss_rpn_cls: 0.0370, loss_rpn_bbox: 0.0416, loss_cls: 0.2136, acc: 92.6745, loss_bbox: 0.2543, loss_mask: 0.2619, loss: 0.8085 2023-11-15 15:01:42,332 - mmdet - INFO - Epoch [3][450/1833] lr: 2.000e-04, eta: 20:13:29, time: 1.186, data_time: 0.086, memory: 16000, loss_rpn_cls: 0.0369, loss_rpn_bbox: 0.0415, loss_cls: 0.2141, acc: 92.6395, loss_bbox: 0.2549, loss_mask: 0.2606, loss: 0.8079 2023-11-15 15:02:41,762 - mmdet - INFO - Epoch [3][500/1833] lr: 2.000e-04, eta: 20:12:39, time: 1.189, data_time: 0.083, memory: 16000, loss_rpn_cls: 0.0360, loss_rpn_bbox: 0.0416, loss_cls: 0.2111, acc: 92.6925, loss_bbox: 0.2513, loss_mask: 0.2610, loss: 0.8012 2023-11-15 15:03:42,426 - mmdet - INFO - Epoch [3][550/1833] lr: 2.000e-04, eta: 20:12:06, time: 1.213, data_time: 0.084, memory: 16000, loss_rpn_cls: 0.0356, loss_rpn_bbox: 0.0404, loss_cls: 0.2137, acc: 92.5997, loss_bbox: 0.2535, loss_mask: 0.2585, loss: 0.8017 2023-11-15 15:04:41,440 - mmdet - INFO - Epoch [3][600/1833] lr: 2.000e-04, eta: 20:11:10, time: 1.180, data_time: 0.069, memory: 16000, loss_rpn_cls: 0.0376, loss_rpn_bbox: 0.0400, loss_cls: 0.2097, acc: 92.7865, loss_bbox: 0.2477, loss_mask: 0.2560, loss: 0.7910 2023-11-15 15:05:40,798 - mmdet - INFO - Epoch [3][650/1833] lr: 2.000e-04, eta: 20:10:18, time: 1.187, data_time: 0.074, memory: 16000, loss_rpn_cls: 0.0392, loss_rpn_bbox: 0.0425, loss_cls: 0.2177, acc: 92.5277, loss_bbox: 0.2594, loss_mask: 0.2618, loss: 0.8205 2023-11-15 15:06:40,133 - mmdet - INFO - Epoch [3][700/1833] lr: 2.000e-04, eta: 20:09:25, time: 1.187, data_time: 0.080, memory: 16000, loss_rpn_cls: 0.0366, loss_rpn_bbox: 0.0407, loss_cls: 0.2169, acc: 92.4904, loss_bbox: 0.2549, loss_mask: 0.2605, loss: 0.8097 2023-11-15 15:07:40,992 - mmdet - INFO - Epoch [3][750/1833] lr: 2.000e-04, eta: 20:08:54, time: 1.217, data_time: 0.077, memory: 16000, loss_rpn_cls: 0.0357, loss_rpn_bbox: 0.0402, loss_cls: 0.2161, acc: 92.5989, loss_bbox: 0.2541, loss_mask: 0.2608, loss: 0.8069 2023-11-15 15:08:41,262 - mmdet - INFO - Epoch [3][800/1833] lr: 2.000e-04, eta: 20:08:14, time: 1.205, data_time: 0.080, memory: 16000, loss_rpn_cls: 0.0362, loss_rpn_bbox: 0.0410, loss_cls: 0.2149, acc: 92.5096, loss_bbox: 0.2558, loss_mask: 0.2602, loss: 0.8082 2023-11-15 15:09:40,868 - mmdet - INFO - Epoch [3][850/1833] lr: 2.000e-04, eta: 20:07:24, time: 1.192, data_time: 0.088, memory: 16000, loss_rpn_cls: 0.0379, loss_rpn_bbox: 0.0397, loss_cls: 0.2174, acc: 92.5847, loss_bbox: 0.2522, loss_mask: 0.2589, loss: 0.8061 2023-11-15 15:10:40,409 - mmdet - INFO - Epoch [3][900/1833] lr: 2.000e-04, eta: 20:06:34, time: 1.191, data_time: 0.083, memory: 16000, loss_rpn_cls: 0.0353, loss_rpn_bbox: 0.0408, loss_cls: 0.2149, acc: 92.5377, loss_bbox: 0.2571, loss_mask: 0.2558, loss: 0.8039 2023-11-15 15:11:41,038 - mmdet - INFO - Epoch [3][950/1833] lr: 2.000e-04, eta: 20:05:57, time: 1.213, data_time: 0.078, memory: 16000, loss_rpn_cls: 0.0366, loss_rpn_bbox: 0.0405, loss_cls: 0.2115, acc: 92.7428, loss_bbox: 0.2497, loss_mask: 0.2569, loss: 0.7951 2023-11-15 15:12:40,128 - mmdet - INFO - Epoch [3][1000/1833] lr: 2.000e-04, eta: 20:05:00, time: 1.182, data_time: 0.076, memory: 16000, loss_rpn_cls: 0.0363, loss_rpn_bbox: 0.0398, loss_cls: 0.2130, acc: 92.6626, loss_bbox: 0.2513, loss_mask: 0.2590, loss: 0.7994 2023-11-15 15:13:39,708 - mmdet - INFO - Epoch [3][1050/1833] lr: 2.000e-04, eta: 20:04:09, time: 1.192, data_time: 0.076, memory: 16000, loss_rpn_cls: 0.0359, loss_rpn_bbox: 0.0401, loss_cls: 0.2103, acc: 92.7422, loss_bbox: 0.2513, loss_mask: 0.2590, loss: 0.7966 2023-11-15 15:14:38,732 - mmdet - INFO - Epoch [3][1100/1833] lr: 2.000e-04, eta: 20:03:11, time: 1.180, data_time: 0.081, memory: 16000, loss_rpn_cls: 0.0355, loss_rpn_bbox: 0.0405, loss_cls: 0.2207, acc: 92.4586, loss_bbox: 0.2582, loss_mask: 0.2578, loss: 0.8126 2023-11-15 15:15:38,359 - mmdet - INFO - Epoch [3][1150/1833] lr: 2.000e-04, eta: 20:02:21, time: 1.193, data_time: 0.080, memory: 16000, loss_rpn_cls: 0.0381, loss_rpn_bbox: 0.0426, loss_cls: 0.2247, acc: 92.1776, loss_bbox: 0.2643, loss_mask: 0.2628, loss: 0.8324 2023-11-15 15:16:37,613 - mmdet - INFO - Epoch [3][1200/1833] lr: 2.000e-04, eta: 20:01:25, time: 1.185, data_time: 0.074, memory: 16000, loss_rpn_cls: 0.0359, loss_rpn_bbox: 0.0396, loss_cls: 0.2105, acc: 92.7820, loss_bbox: 0.2505, loss_mask: 0.2568, loss: 0.7933 2023-11-15 15:17:36,554 - mmdet - INFO - Epoch [3][1250/1833] lr: 2.000e-04, eta: 20:00:26, time: 1.179, data_time: 0.074, memory: 16000, loss_rpn_cls: 0.0344, loss_rpn_bbox: 0.0399, loss_cls: 0.2131, acc: 92.6025, loss_bbox: 0.2525, loss_mask: 0.2587, loss: 0.7985 2023-11-15 15:18:35,784 - mmdet - INFO - Epoch [3][1300/1833] lr: 2.000e-04, eta: 19:59:30, time: 1.185, data_time: 0.074, memory: 16000, loss_rpn_cls: 0.0357, loss_rpn_bbox: 0.0388, loss_cls: 0.2105, acc: 92.7031, loss_bbox: 0.2492, loss_mask: 0.2542, loss: 0.7885 2023-11-15 15:19:35,912 - mmdet - INFO - Epoch [3][1350/1833] lr: 2.000e-04, eta: 19:58:45, time: 1.203, data_time: 0.083, memory: 16000, loss_rpn_cls: 0.0359, loss_rpn_bbox: 0.0405, loss_cls: 0.2153, acc: 92.5621, loss_bbox: 0.2548, loss_mask: 0.2587, loss: 0.8052 2023-11-15 15:20:35,540 - mmdet - INFO - Epoch [3][1400/1833] lr: 2.000e-04, eta: 19:57:54, time: 1.192, data_time: 0.070, memory: 16000, loss_rpn_cls: 0.0360, loss_rpn_bbox: 0.0403, loss_cls: 0.2137, acc: 92.6232, loss_bbox: 0.2513, loss_mask: 0.2611, loss: 0.8024 2023-11-15 15:21:34,204 - mmdet - INFO - Epoch [3][1450/1833] lr: 2.000e-04, eta: 19:56:51, time: 1.173, data_time: 0.075, memory: 16000, loss_rpn_cls: 0.0360, loss_rpn_bbox: 0.0401, loss_cls: 0.2114, acc: 92.7570, loss_bbox: 0.2461, loss_mask: 0.2545, loss: 0.7881 2023-11-15 15:22:34,696 - mmdet - INFO - Epoch [3][1500/1833] lr: 2.000e-04, eta: 19:56:10, time: 1.210, data_time: 0.085, memory: 16000, loss_rpn_cls: 0.0357, loss_rpn_bbox: 0.0402, loss_cls: 0.2116, acc: 92.7171, loss_bbox: 0.2494, loss_mask: 0.2529, loss: 0.7898 2023-11-15 15:23:33,633 - mmdet - INFO - Epoch [3][1550/1833] lr: 2.000e-04, eta: 19:55:10, time: 1.179, data_time: 0.069, memory: 16000, loss_rpn_cls: 0.0354, loss_rpn_bbox: 0.0407, loss_cls: 0.2115, acc: 92.7173, loss_bbox: 0.2494, loss_mask: 0.2571, loss: 0.7941 2023-11-15 15:24:33,533 - mmdet - INFO - Epoch [3][1600/1833] lr: 2.000e-04, eta: 19:54:22, time: 1.198, data_time: 0.078, memory: 16000, loss_rpn_cls: 0.0345, loss_rpn_bbox: 0.0405, loss_cls: 0.2119, acc: 92.6755, loss_bbox: 0.2528, loss_mask: 0.2566, loss: 0.7962 2023-11-15 15:25:33,557 - mmdet - INFO - Epoch [3][1650/1833] lr: 2.000e-04, eta: 19:53:34, time: 1.200, data_time: 0.066, memory: 16000, loss_rpn_cls: 0.0359, loss_rpn_bbox: 0.0405, loss_cls: 0.2157, acc: 92.5614, loss_bbox: 0.2557, loss_mask: 0.2576, loss: 0.8053 2023-11-15 15:26:33,175 - mmdet - INFO - Epoch [3][1700/1833] lr: 2.000e-04, eta: 19:52:42, time: 1.192, data_time: 0.071, memory: 16000, loss_rpn_cls: 0.0361, loss_rpn_bbox: 0.0400, loss_cls: 0.2091, acc: 92.7379, loss_bbox: 0.2491, loss_mask: 0.2566, loss: 0.7909 2023-11-15 15:27:32,990 - mmdet - INFO - Epoch [3][1750/1833] lr: 2.000e-04, eta: 19:51:52, time: 1.196, data_time: 0.078, memory: 16000, loss_rpn_cls: 0.0366, loss_rpn_bbox: 0.0402, loss_cls: 0.2096, acc: 92.7794, loss_bbox: 0.2472, loss_mask: 0.2577, loss: 0.7913 2023-11-15 15:28:33,038 - mmdet - INFO - Epoch [3][1800/1833] lr: 2.000e-04, eta: 19:51:04, time: 1.201, data_time: 0.076, memory: 16000, loss_rpn_cls: 0.0362, loss_rpn_bbox: 0.0411, loss_cls: 0.2080, acc: 92.8091, loss_bbox: 0.2476, loss_mask: 0.2564, loss: 0.7893 2023-11-15 15:29:13,374 - mmdet - INFO - Saving checkpoint at 3 epochs 2023-11-15 15:30:01,348 - mmdet - INFO - Evaluating bbox... 2023-11-15 15:30:36,060 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.416 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.651 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.459 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.272 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.460 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.528 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.551 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.551 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.551 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 ] = 0.595 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.680 2023-11-15 15:30:36,063 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.542 | bicycle | 0.320 | car | 0.435 | | motorcycle | 0.421 | airplane | 0.621 | bus | 0.655 | | train | 0.602 | truck | 0.368 | boat | 0.275 | | traffic light | 0.271 | fire hydrant | 0.669 | stop sign | 0.617 | | parking meter | 0.465 | bench | 0.244 | bird | 0.373 | | cat | 0.663 | dog | 0.646 | horse | 0.542 | | sheep | 0.513 | cow | 0.583 | elephant | 0.660 | | bear | 0.628 | zebra | 0.646 | giraffe | 0.649 | | backpack | 0.156 | umbrella | 0.394 | handbag | 0.159 | | tie | 0.319 | suitcase | 0.372 | frisbee | 0.648 | | skis | 0.216 | snowboard | 0.356 | sports ball | 0.443 | | kite | 0.416 | baseball bat | 0.330 | baseball glove | 0.388 | | skateboard | 0.498 | surfboard | 0.377 | tennis racket | 0.437 | | bottle | 0.405 | wine glass | 0.378 | cup | 0.461 | | fork | 0.350 | knife | 0.198 | spoon | 0.195 | | bowl | 0.417 | banana | 0.242 | apple | 0.227 | | sandwich | 0.411 | orange | 0.310 | broccoli | 0.239 | | carrot | 0.230 | hot dog | 0.370 | pizza | 0.489 | | donut | 0.469 | cake | 0.384 | chair | 0.302 | | couch | 0.403 | potted plant | 0.277 | bed | 0.401 | | dining table | 0.254 | toilet | 0.590 | tv | 0.592 | | laptop | 0.606 | mouse | 0.588 | remote | 0.337 | | keyboard | 0.493 | cell phone | 0.355 | microwave | 0.590 | | oven | 0.331 | toaster | 0.429 | sink | 0.398 | | refrigerator | 0.543 | book | 0.142 | clock | 0.483 | | vase | 0.397 | scissors | 0.301 | teddy bear | 0.465 | | hair drier | 0.077 | toothbrush | 0.194 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-15 15:30:36,063 - mmdet - INFO - Evaluating segm... 2023-11-15 15:31:12,368 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.387 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.619 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.414 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.196 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.427 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.559 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.513 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.513 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.513 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.328 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.562 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.666 2023-11-15 15:31:12,371 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.467 | bicycle | 0.186 | car | 0.400 | | motorcycle | 0.338 | airplane | 0.514 | bus | 0.661 | | train | 0.605 | truck | 0.371 | boat | 0.266 | | traffic light | 0.261 | fire hydrant | 0.666 | stop sign | 0.628 | | parking meter | 0.504 | bench | 0.180 | bird | 0.309 | | cat | 0.685 | dog | 0.602 | horse | 0.404 | | sheep | 0.470 | cow | 0.489 | elephant | 0.606 | | bear | 0.692 | zebra | 0.574 | giraffe | 0.501 | | backpack | 0.166 | umbrella | 0.482 | handbag | 0.176 | | tie | 0.296 | suitcase | 0.409 | frisbee | 0.635 | | skis | 0.026 | snowboard | 0.250 | sports ball | 0.434 | | kite | 0.283 | baseball bat | 0.250 | baseball glove | 0.440 | | skateboard | 0.312 | surfboard | 0.306 | tennis racket | 0.549 | | bottle | 0.388 | wine glass | 0.318 | cup | 0.476 | | fork | 0.175 | knife | 0.136 | spoon | 0.139 | | bowl | 0.415 | banana | 0.186 | apple | 0.229 | | sandwich | 0.442 | orange | 0.324 | broccoli | 0.234 | | carrot | 0.206 | hot dog | 0.299 | pizza | 0.494 | | donut | 0.492 | cake | 0.398 | chair | 0.219 | | couch | 0.353 | potted plant | 0.240 | bed | 0.348 | | dining table | 0.149 | toilet | 0.617 | tv | 0.625 | | laptop | 0.631 | mouse | 0.616 | remote | 0.315 | | keyboard | 0.502 | cell phone | 0.368 | microwave | 0.613 | | oven | 0.334 | toaster | 0.482 | sink | 0.381 | | refrigerator | 0.600 | book | 0.105 | clock | 0.512 | | vase | 0.400 | scissors | 0.211 | teddy bear | 0.455 | | hair drier | 0.015 | toothbrush | 0.109 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-15 15:31:12,880 - mmdet - INFO - The previous best checkpoint /mnt/petrelfs/lizhiqi/DINO/detection/work_dirs/mask_rcnn_flash_internimage_s_fpn_3x_coco_0.4/best_bbox_mAP_epoch_2.pth was removed 2023-11-15 15:31:15,146 - mmdet - INFO - Now best checkpoint is saved as best_bbox_mAP_epoch_3.pth. 2023-11-15 15:31:15,147 - mmdet - INFO - Best bbox_mAP is 0.4155 at 3 epoch. 2023-11-15 15:31:15,147 - mmdet - INFO - Exp name: mask_rcnn_flash_internimage_s_fpn_3x_coco_0.4.py 2023-11-15 15:31:15,147 - mmdet - INFO - Epoch(val) [3][625] bbox_mAP: 0.4155, bbox_mAP_50: 0.6510, bbox_mAP_75: 0.4589, bbox_mAP_s: 0.2722, bbox_mAP_m: 0.4596, bbox_mAP_l: 0.5282, bbox_mAP_copypaste: 0.4155 0.6510 0.4589 0.2722 0.4596 0.5282, segm_mAP: 0.3868, segm_mAP_50: 0.6193, segm_mAP_75: 0.4136, segm_mAP_s: 0.1960, segm_mAP_m: 0.4271, segm_mAP_l: 0.5590, segm_mAP_copypaste: 0.3868 0.6193 0.4136 0.1960 0.4271 0.5590 2023-11-15 15:32:18,693 - mmdet - INFO - Epoch [4][50/1833] lr: 2.000e-04, eta: 19:43:10, time: 1.270, data_time: 0.137, memory: 16000, loss_rpn_cls: 0.0343, loss_rpn_bbox: 0.0394, loss_cls: 0.1996, acc: 93.0249, loss_bbox: 0.2408, loss_mask: 0.2513, loss: 0.7655 2023-11-15 15:33:18,590 - mmdet - INFO - Epoch [4][100/1833] lr: 2.000e-04, eta: 19:42:24, time: 1.198, data_time: 0.084, memory: 16000, loss_rpn_cls: 0.0340, loss_rpn_bbox: 0.0391, loss_cls: 0.2025, acc: 92.9479, loss_bbox: 0.2441, loss_mask: 0.2520, loss: 0.7716 2023-11-15 15:34:18,601 - mmdet - INFO - Epoch [4][150/1833] lr: 2.000e-04, eta: 19:41:39, time: 1.200, data_time: 0.094, memory: 16000, loss_rpn_cls: 0.0341, loss_rpn_bbox: 0.0388, loss_cls: 0.2055, acc: 92.7975, loss_bbox: 0.2475, loss_mask: 0.2505, loss: 0.7764 2023-11-15 15:35:18,630 - mmdet - INFO - Epoch [4][200/1833] lr: 2.000e-04, eta: 19:40:54, time: 1.200, data_time: 0.078, memory: 16000, loss_rpn_cls: 0.0334, loss_rpn_bbox: 0.0399, loss_cls: 0.2079, acc: 92.7855, loss_bbox: 0.2502, loss_mask: 0.2528, loss: 0.7843 2023-11-15 15:36:19,262 - mmdet - INFO - Epoch [4][250/1833] lr: 2.000e-04, eta: 19:40:15, time: 1.213, data_time: 0.082, memory: 16000, loss_rpn_cls: 0.0329, loss_rpn_bbox: 0.0385, loss_cls: 0.2016, acc: 92.9811, loss_bbox: 0.2432, loss_mask: 0.2493, loss: 0.7655 2023-11-15 15:37:20,075 - mmdet - INFO - Epoch [4][300/1833] lr: 2.000e-04, eta: 19:39:37, time: 1.216, data_time: 0.079, memory: 16000, loss_rpn_cls: 0.0363, loss_rpn_bbox: 0.0412, loss_cls: 0.2086, acc: 92.6614, loss_bbox: 0.2510, loss_mask: 0.2560, loss: 0.7931 2023-11-15 15:38:19,662 - mmdet - INFO - Epoch [4][350/1833] lr: 2.000e-04, eta: 19:38:46, time: 1.192, data_time: 0.079, memory: 16000, loss_rpn_cls: 0.0333, loss_rpn_bbox: 0.0384, loss_cls: 0.2020, acc: 92.9738, loss_bbox: 0.2424, loss_mask: 0.2491, loss: 0.7651 2023-11-15 15:39:20,630 - mmdet - INFO - Epoch [4][400/1833] lr: 2.000e-04, eta: 19:38:10, time: 1.219, data_time: 0.090, memory: 16000, loss_rpn_cls: 0.0344, loss_rpn_bbox: 0.0405, loss_cls: 0.2119, acc: 92.5927, loss_bbox: 0.2530, loss_mask: 0.2534, loss: 0.7932 2023-11-15 15:40:20,283 - mmdet - INFO - Epoch [4][450/1833] lr: 2.000e-04, eta: 19:37:19, time: 1.193, data_time: 0.075, memory: 16000, loss_rpn_cls: 0.0314, loss_rpn_bbox: 0.0376, loss_cls: 0.1993, acc: 93.0134, loss_bbox: 0.2414, loss_mask: 0.2500, loss: 0.7597 2023-11-15 15:41:20,165 - mmdet - INFO - Epoch [4][500/1833] lr: 2.000e-04, eta: 19:36:31, time: 1.198, data_time: 0.090, memory: 16000, loss_rpn_cls: 0.0338, loss_rpn_bbox: 0.0387, loss_cls: 0.2060, acc: 92.8392, loss_bbox: 0.2450, loss_mask: 0.2524, loss: 0.7758 2023-11-15 15:42:19,877 - mmdet - INFO - Epoch [4][550/1833] lr: 2.000e-04, eta: 19:35:41, time: 1.194, data_time: 0.074, memory: 16000, loss_rpn_cls: 0.0329, loss_rpn_bbox: 0.0392, loss_cls: 0.2063, acc: 92.8713, loss_bbox: 0.2462, loss_mask: 0.2536, loss: 0.7784 2023-11-15 15:43:18,817 - mmdet - INFO - Epoch [4][600/1833] lr: 2.000e-04, eta: 19:34:43, time: 1.179, data_time: 0.076, memory: 16000, loss_rpn_cls: 0.0335, loss_rpn_bbox: 0.0382, loss_cls: 0.2009, acc: 93.0168, loss_bbox: 0.2435, loss_mask: 0.2515, loss: 0.7676 2023-11-15 15:44:18,482 - mmdet - INFO - Epoch [4][650/1833] lr: 2.000e-04, eta: 19:33:52, time: 1.193, data_time: 0.080, memory: 16000, loss_rpn_cls: 0.0335, loss_rpn_bbox: 0.0391, loss_cls: 0.2033, acc: 92.9240, loss_bbox: 0.2444, loss_mask: 0.2504, loss: 0.7706 2023-11-15 15:45:19,027 - mmdet - INFO - Epoch [4][700/1833] lr: 2.000e-04, eta: 19:33:09, time: 1.211, data_time: 0.072, memory: 16000, loss_rpn_cls: 0.0327, loss_rpn_bbox: 0.0380, loss_cls: 0.2056, acc: 92.8394, loss_bbox: 0.2424, loss_mask: 0.2519, loss: 0.7706 2023-11-15 15:46:20,180 - mmdet - INFO - Epoch [4][750/1833] lr: 2.000e-04, eta: 19:32:32, time: 1.223, data_time: 0.075, memory: 16000, loss_rpn_cls: 0.0340, loss_rpn_bbox: 0.0392, loss_cls: 0.2066, acc: 92.8232, loss_bbox: 0.2455, loss_mask: 0.2528, loss: 0.7780 2023-11-15 15:47:19,695 - mmdet - INFO - Epoch [4][800/1833] lr: 2.000e-04, eta: 19:31:39, time: 1.190, data_time: 0.085, memory: 16000, loss_rpn_cls: 0.0350, loss_rpn_bbox: 0.0402, loss_cls: 0.2092, acc: 92.6796, loss_bbox: 0.2499, loss_mask: 0.2537, loss: 0.7880 2023-11-15 15:48:19,034 - mmdet - INFO - Epoch [4][850/1833] lr: 2.000e-04, eta: 19:30:45, time: 1.187, data_time: 0.072, memory: 16000, loss_rpn_cls: 0.0329, loss_rpn_bbox: 0.0383, loss_cls: 0.2042, acc: 92.9144, loss_bbox: 0.2427, loss_mask: 0.2517, loss: 0.7698 2023-11-15 15:49:18,356 - mmdet - INFO - Epoch [4][900/1833] lr: 2.000e-04, eta: 19:29:50, time: 1.186, data_time: 0.077, memory: 16000, loss_rpn_cls: 0.0334, loss_rpn_bbox: 0.0388, loss_cls: 0.1996, acc: 92.9902, loss_bbox: 0.2443, loss_mask: 0.2546, loss: 0.7708 2023-11-15 15:50:18,512 - mmdet - INFO - Epoch [4][950/1833] lr: 2.000e-04, eta: 19:29:03, time: 1.203, data_time: 0.080, memory: 16000, loss_rpn_cls: 0.0332, loss_rpn_bbox: 0.0388, loss_cls: 0.2020, acc: 92.9985, loss_bbox: 0.2424, loss_mask: 0.2534, loss: 0.7698 2023-11-15 15:51:17,834 - mmdet - INFO - Epoch [4][1000/1833] lr: 2.000e-04, eta: 19:28:08, time: 1.186, data_time: 0.074, memory: 16000, loss_rpn_cls: 0.0340, loss_rpn_bbox: 0.0380, loss_cls: 0.2059, acc: 92.8678, loss_bbox: 0.2452, loss_mask: 0.2525, loss: 0.7755 2023-11-15 15:52:18,061 - mmdet - INFO - Epoch [4][1050/1833] lr: 2.000e-04, eta: 19:27:21, time: 1.204, data_time: 0.080, memory: 16000, loss_rpn_cls: 0.0315, loss_rpn_bbox: 0.0381, loss_cls: 0.2038, acc: 92.8815, loss_bbox: 0.2445, loss_mask: 0.2488, loss: 0.7669 2023-11-15 15:53:17,046 - mmdet - INFO - Epoch [4][1100/1833] lr: 2.000e-04, eta: 19:26:22, time: 1.180, data_time: 0.069, memory: 16000, loss_rpn_cls: 0.0343, loss_rpn_bbox: 0.0401, loss_cls: 0.2057, acc: 92.8536, loss_bbox: 0.2442, loss_mask: 0.2511, loss: 0.7755 2023-11-15 15:54:15,732 - mmdet - INFO - Epoch [4][1150/1833] lr: 2.000e-04, eta: 19:25:21, time: 1.174, data_time: 0.075, memory: 16000, loss_rpn_cls: 0.0318, loss_rpn_bbox: 0.0381, loss_cls: 0.2044, acc: 92.9155, loss_bbox: 0.2417, loss_mask: 0.2484, loss: 0.7644 2023-11-15 15:55:15,254 - mmdet - INFO - Epoch [4][1200/1833] lr: 2.000e-04, eta: 19:24:28, time: 1.190, data_time: 0.081, memory: 16000, loss_rpn_cls: 0.0334, loss_rpn_bbox: 0.0378, loss_cls: 0.2025, acc: 92.9818, loss_bbox: 0.2401, loss_mask: 0.2499, loss: 0.7636 2023-11-15 15:56:14,836 - mmdet - INFO - Epoch [4][1250/1833] lr: 2.000e-04, eta: 19:23:35, time: 1.192, data_time: 0.075, memory: 16000, loss_rpn_cls: 0.0329, loss_rpn_bbox: 0.0392, loss_cls: 0.2032, acc: 92.9052, loss_bbox: 0.2436, loss_mask: 0.2509, loss: 0.7699 2023-11-15 15:57:17,732 - mmdet - INFO - Epoch [4][1300/1833] lr: 2.000e-04, eta: 19:23:10, time: 1.258, data_time: 0.076, memory: 16000, loss_rpn_cls: 0.0332, loss_rpn_bbox: 0.0388, loss_cls: 0.2009, acc: 93.0152, loss_bbox: 0.2410, loss_mask: 0.2510, loss: 0.7649 2023-11-15 15:58:18,021 - mmdet - INFO - Epoch [4][1350/1833] lr: 2.000e-04, eta: 19:22:23, time: 1.206, data_time: 0.079, memory: 16000, loss_rpn_cls: 0.0319, loss_rpn_bbox: 0.0396, loss_cls: 0.2036, acc: 92.8227, loss_bbox: 0.2465, loss_mask: 0.2532, loss: 0.7748 2023-11-15 15:59:17,421 - mmdet - INFO - Epoch [4][1400/1833] lr: 2.000e-04, eta: 19:21:28, time: 1.188, data_time: 0.077, memory: 16000, loss_rpn_cls: 0.0327, loss_rpn_bbox: 0.0391, loss_cls: 0.2020, acc: 92.9600, loss_bbox: 0.2444, loss_mask: 0.2529, loss: 0.7711 2023-11-15 16:00:16,297 - mmdet - INFO - Epoch [4][1450/1833] lr: 2.000e-04, eta: 19:20:28, time: 1.177, data_time: 0.084, memory: 16000, loss_rpn_cls: 0.0321, loss_rpn_bbox: 0.0385, loss_cls: 0.1965, acc: 93.1503, loss_bbox: 0.2404, loss_mask: 0.2481, loss: 0.7556 2023-11-15 16:01:16,964 - mmdet - INFO - Epoch [4][1500/1833] lr: 2.000e-04, eta: 19:19:43, time: 1.213, data_time: 0.074, memory: 16000, loss_rpn_cls: 0.0315, loss_rpn_bbox: 0.0378, loss_cls: 0.1996, acc: 93.0247, loss_bbox: 0.2385, loss_mask: 0.2487, loss: 0.7560 2023-11-15 16:02:16,610 - mmdet - INFO - Epoch [4][1550/1833] lr: 2.000e-04, eta: 19:18:50, time: 1.193, data_time: 0.066, memory: 16000, loss_rpn_cls: 0.0337, loss_rpn_bbox: 0.0380, loss_cls: 0.1984, acc: 93.0778, loss_bbox: 0.2372, loss_mask: 0.2496, loss: 0.7570 2023-11-15 16:03:16,368 - mmdet - INFO - Epoch [4][1600/1833] lr: 2.000e-04, eta: 19:17:57, time: 1.195, data_time: 0.078, memory: 16000, loss_rpn_cls: 0.0332, loss_rpn_bbox: 0.0375, loss_cls: 0.1997, acc: 93.0355, loss_bbox: 0.2378, loss_mask: 0.2484, loss: 0.7566 2023-11-15 16:04:16,484 - mmdet - INFO - Epoch [4][1650/1833] lr: 2.000e-04, eta: 19:17:07, time: 1.202, data_time: 0.075, memory: 16000, loss_rpn_cls: 0.0352, loss_rpn_bbox: 0.0399, loss_cls: 0.2083, acc: 92.7130, loss_bbox: 0.2495, loss_mask: 0.2524, loss: 0.7853 2023-11-15 16:05:15,613 - mmdet - INFO - Epoch [4][1700/1833] lr: 2.000e-04, eta: 19:16:09, time: 1.183, data_time: 0.075, memory: 16000, loss_rpn_cls: 0.0324, loss_rpn_bbox: 0.0372, loss_cls: 0.2011, acc: 93.0524, loss_bbox: 0.2385, loss_mask: 0.2479, loss: 0.7571 2023-11-15 16:06:16,115 - mmdet - INFO - Epoch [4][1750/1833] lr: 2.000e-04, eta: 19:15:23, time: 1.210, data_time: 0.082, memory: 16000, loss_rpn_cls: 0.0342, loss_rpn_bbox: 0.0396, loss_cls: 0.2039, acc: 92.8683, loss_bbox: 0.2443, loss_mask: 0.2521, loss: 0.7740 2023-11-15 16:07:15,876 - mmdet - INFO - Epoch [4][1800/1833] lr: 2.000e-04, eta: 19:14:30, time: 1.195, data_time: 0.085, memory: 16000, loss_rpn_cls: 0.0334, loss_rpn_bbox: 0.0396, loss_cls: 0.2075, acc: 92.7480, loss_bbox: 0.2488, loss_mask: 0.2508, loss: 0.7800 2023-11-15 16:07:56,284 - mmdet - INFO - Saving checkpoint at 4 epochs 2023-11-15 16:08:49,468 - mmdet - INFO - Evaluating bbox... 2023-11-15 16:09:28,306 - 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 ] = 0.668 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.478 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.288 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 ] = 0.554 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.571 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.571 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.571 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.409 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.613 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.708 2023-11-15 16:09:28,309 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.555 | bicycle | 0.351 | car | 0.466 | | motorcycle | 0.458 | airplane | 0.638 | bus | 0.659 | | train | 0.608 | truck | 0.389 | boat | 0.302 | | traffic light | 0.290 | fire hydrant | 0.648 | stop sign | 0.627 | | parking meter | 0.505 | bench | 0.251 | bird | 0.395 | | cat | 0.694 | dog | 0.657 | horse | 0.568 | | sheep | 0.539 | cow | 0.586 | elephant | 0.671 | | bear | 0.634 | zebra | 0.662 | giraffe | 0.663 | | backpack | 0.172 | umbrella | 0.405 | handbag | 0.180 | | tie | 0.330 | suitcase | 0.419 | frisbee | 0.702 | | skis | 0.250 | snowboard | 0.370 | sports ball | 0.449 | | kite | 0.439 | baseball bat | 0.333 | baseball glove | 0.427 | | skateboard | 0.518 | surfboard | 0.398 | tennis racket | 0.488 | | bottle | 0.425 | wine glass | 0.380 | cup | 0.469 | | fork | 0.376 | knife | 0.206 | spoon | 0.255 | | bowl | 0.454 | banana | 0.268 | apple | 0.229 | | sandwich | 0.397 | orange | 0.313 | broccoli | 0.247 | | carrot | 0.240 | hot dog | 0.381 | pizza | 0.515 | | donut | 0.488 | cake | 0.406 | chair | 0.320 | | couch | 0.454 | potted plant | 0.292 | bed | 0.413 | | dining table | 0.282 | toilet | 0.600 | tv | 0.576 | | laptop | 0.625 | mouse | 0.631 | remote | 0.352 | | keyboard | 0.500 | cell phone | 0.385 | microwave | 0.576 | | oven | 0.359 | toaster | 0.403 | sink | 0.398 | | refrigerator | 0.563 | book | 0.168 | clock | 0.512 | | vase | 0.412 | scissors | 0.333 | teddy bear | 0.481 | | hair drier | 0.087 | toothbrush | 0.221 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-15 16:09:28,309 - mmdet - INFO - Evaluating segm... 2023-11-15 16:10:05,351 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.396 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.634 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.424 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.204 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.437 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.576 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.526 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.526 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.526 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.346 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.573 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.681 2023-11-15 16:10:05,354 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.478 | bicycle | 0.209 | car | 0.426 | | motorcycle | 0.374 | airplane | 0.503 | bus | 0.652 | | train | 0.622 | truck | 0.386 | boat | 0.277 | | traffic light | 0.272 | fire hydrant | 0.666 | stop sign | 0.637 | | parking meter | 0.506 | bench | 0.196 | bird | 0.322 | | cat | 0.716 | dog | 0.625 | horse | 0.438 | | sheep | 0.486 | cow | 0.505 | elephant | 0.593 | | bear | 0.698 | zebra | 0.579 | giraffe | 0.516 | | backpack | 0.180 | umbrella | 0.493 | handbag | 0.182 | | tie | 0.304 | suitcase | 0.435 | frisbee | 0.660 | | skis | 0.032 | snowboard | 0.219 | sports ball | 0.437 | | kite | 0.302 | baseball bat | 0.260 | baseball glove | 0.440 | | skateboard | 0.327 | surfboard | 0.323 | tennis racket | 0.563 | | bottle | 0.406 | wine glass | 0.339 | cup | 0.480 | | fork | 0.192 | knife | 0.128 | spoon | 0.169 | | bowl | 0.428 | banana | 0.209 | apple | 0.220 | | sandwich | 0.436 | orange | 0.325 | broccoli | 0.231 | | carrot | 0.209 | hot dog | 0.312 | pizza | 0.504 | | donut | 0.493 | cake | 0.416 | chair | 0.229 | | couch | 0.379 | potted plant | 0.244 | bed | 0.336 | | dining table | 0.171 | toilet | 0.620 | tv | 0.606 | | laptop | 0.636 | mouse | 0.621 | remote | 0.328 | | keyboard | 0.502 | cell phone | 0.382 | microwave | 0.615 | | oven | 0.351 | toaster | 0.409 | sink | 0.388 | | refrigerator | 0.611 | book | 0.127 | clock | 0.506 | | vase | 0.414 | scissors | 0.262 | teddy bear | 0.467 | | hair drier | 0.047 | toothbrush | 0.125 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-15 16:10:05,931 - mmdet - INFO - The previous best checkpoint /mnt/petrelfs/lizhiqi/DINO/detection/work_dirs/mask_rcnn_flash_internimage_s_fpn_3x_coco_0.4/best_bbox_mAP_epoch_3.pth was removed 2023-11-15 16:10:08,156 - mmdet - INFO - Now best checkpoint is saved as best_bbox_mAP_epoch_4.pth. 2023-11-15 16:10:08,157 - mmdet - INFO - Best bbox_mAP is 0.4336 at 4 epoch. 2023-11-15 16:10:08,157 - mmdet - INFO - Exp name: mask_rcnn_flash_internimage_s_fpn_3x_coco_0.4.py 2023-11-15 16:10:08,157 - mmdet - INFO - Epoch(val) [4][625] bbox_mAP: 0.4336, bbox_mAP_50: 0.6681, bbox_mAP_75: 0.4779, bbox_mAP_s: 0.2878, bbox_mAP_m: 0.4775, bbox_mAP_l: 0.5541, bbox_mAP_copypaste: 0.4336 0.6681 0.4779 0.2878 0.4775 0.5541, segm_mAP: 0.3963, segm_mAP_50: 0.6340, segm_mAP_75: 0.4235, segm_mAP_s: 0.2040, segm_mAP_m: 0.4367, segm_mAP_l: 0.5758, segm_mAP_copypaste: 0.3963 0.6340 0.4235 0.2040 0.4367 0.5758 2023-11-15 16:11:12,432 - mmdet - INFO - Epoch [5][50/1833] lr: 2.000e-04, eta: 19:08:24, time: 1.285, data_time: 0.132, memory: 16000, loss_rpn_cls: 0.0322, loss_rpn_bbox: 0.0400, loss_cls: 0.1997, acc: 92.9448, loss_bbox: 0.2448, loss_mask: 0.2480, loss: 0.7648 2023-11-15 16:12:12,671 - mmdet - INFO - Epoch [5][100/1833] lr: 2.000e-04, eta: 19:07:37, time: 1.205, data_time: 0.085, memory: 16000, loss_rpn_cls: 0.0312, loss_rpn_bbox: 0.0376, loss_cls: 0.1934, acc: 93.2002, loss_bbox: 0.2379, loss_mask: 0.2466, loss: 0.7467 2023-11-15 16:13:11,913 - mmdet - INFO - Epoch [5][150/1833] lr: 2.000e-04, eta: 19:06:41, time: 1.185, data_time: 0.080, memory: 16000, loss_rpn_cls: 0.0308, loss_rpn_bbox: 0.0370, loss_cls: 0.1946, acc: 93.0659, loss_bbox: 0.2379, loss_mask: 0.2449, loss: 0.7451 2023-11-15 16:14:11,870 - mmdet - INFO - Epoch [5][200/1833] lr: 2.000e-04, eta: 19:05:52, time: 1.199, data_time: 0.075, memory: 16000, loss_rpn_cls: 0.0314, loss_rpn_bbox: 0.0382, loss_cls: 0.1963, acc: 93.0822, loss_bbox: 0.2397, loss_mask: 0.2462, loss: 0.7518 2023-11-15 16:15:11,600 - mmdet - INFO - Epoch [5][250/1833] lr: 2.000e-04, eta: 19:05:00, time: 1.195, data_time: 0.074, memory: 16000, loss_rpn_cls: 0.0310, loss_rpn_bbox: 0.0373, loss_cls: 0.1959, acc: 93.0944, loss_bbox: 0.2385, loss_mask: 0.2461, loss: 0.7488 2023-11-15 16:16:10,411 - mmdet - INFO - Epoch [5][300/1833] lr: 2.000e-04, eta: 19:04:01, time: 1.176, data_time: 0.084, memory: 16000, loss_rpn_cls: 0.0329, loss_rpn_bbox: 0.0384, loss_cls: 0.1971, acc: 93.0870, loss_bbox: 0.2364, loss_mask: 0.2458, loss: 0.7506 2023-11-15 16:17:09,963 - mmdet - INFO - Epoch [5][350/1833] lr: 2.000e-04, eta: 19:03:08, time: 1.191, data_time: 0.081, memory: 16000, loss_rpn_cls: 0.0307, loss_rpn_bbox: 0.0378, loss_cls: 0.1999, acc: 92.9688, loss_bbox: 0.2411, loss_mask: 0.2487, loss: 0.7583 2023-11-15 16:18:09,245 - mmdet - INFO - Epoch [5][400/1833] lr: 2.000e-04, eta: 19:02:12, time: 1.186, data_time: 0.077, memory: 16000, loss_rpn_cls: 0.0314, loss_rpn_bbox: 0.0379, loss_cls: 0.1963, acc: 93.0936, loss_bbox: 0.2389, loss_mask: 0.2481, loss: 0.7526 2023-11-15 16:19:08,270 - mmdet - INFO - Epoch [5][450/1833] lr: 2.000e-04, eta: 19:01:15, time: 1.181, data_time: 0.082, memory: 16000, loss_rpn_cls: 0.0316, loss_rpn_bbox: 0.0372, loss_cls: 0.1966, acc: 93.1188, loss_bbox: 0.2378, loss_mask: 0.2454, loss: 0.7486 2023-11-15 16:20:07,029 - mmdet - INFO - Epoch [5][500/1833] lr: 2.000e-04, eta: 19:00:16, time: 1.175, data_time: 0.074, memory: 16000, loss_rpn_cls: 0.0313, loss_rpn_bbox: 0.0369, loss_cls: 0.1943, acc: 93.1749, loss_bbox: 0.2323, loss_mask: 0.2425, loss: 0.7373 2023-11-15 16:21:07,720 - mmdet - INFO - Epoch [5][550/1833] lr: 2.000e-04, eta: 18:59:31, time: 1.214, data_time: 0.074, memory: 16000, loss_rpn_cls: 0.0315, loss_rpn_bbox: 0.0374, loss_cls: 0.1947, acc: 93.2136, loss_bbox: 0.2339, loss_mask: 0.2430, loss: 0.7406 2023-11-15 16:22:06,131 - mmdet - INFO - Epoch [5][600/1833] lr: 2.000e-04, eta: 18:58:29, time: 1.168, data_time: 0.071, memory: 16000, loss_rpn_cls: 0.0311, loss_rpn_bbox: 0.0384, loss_cls: 0.2004, acc: 92.9088, loss_bbox: 0.2434, loss_mask: 0.2475, loss: 0.7608 2023-11-15 16:23:04,442 - mmdet - INFO - Epoch [5][650/1833] lr: 2.000e-04, eta: 18:57:26, time: 1.166, data_time: 0.074, memory: 16000, loss_rpn_cls: 0.0303, loss_rpn_bbox: 0.0377, loss_cls: 0.1936, acc: 93.1383, loss_bbox: 0.2352, loss_mask: 0.2468, loss: 0.7437 2023-11-15 16:24:04,285 - mmdet - INFO - Epoch [5][700/1833] lr: 2.000e-04, eta: 18:56:35, time: 1.197, data_time: 0.074, memory: 16000, loss_rpn_cls: 0.0307, loss_rpn_bbox: 0.0388, loss_cls: 0.1994, acc: 92.9587, loss_bbox: 0.2419, loss_mask: 0.2476, loss: 0.7584 2023-11-15 16:25:03,888 - mmdet - INFO - Epoch [5][750/1833] lr: 2.000e-04, eta: 18:55:41, time: 1.192, data_time: 0.075, memory: 16000, loss_rpn_cls: 0.0317, loss_rpn_bbox: 0.0377, loss_cls: 0.1979, acc: 93.0070, loss_bbox: 0.2431, loss_mask: 0.2447, loss: 0.7551 2023-11-15 16:26:03,147 - mmdet - INFO - Epoch [5][800/1833] lr: 2.000e-04, eta: 18:54:46, time: 1.185, data_time: 0.077, memory: 16000, loss_rpn_cls: 0.0317, loss_rpn_bbox: 0.0365, loss_cls: 0.1921, acc: 93.2904, loss_bbox: 0.2291, loss_mask: 0.2434, loss: 0.7327 2023-11-15 16:27:02,718 - mmdet - INFO - Epoch [5][850/1833] lr: 2.000e-04, eta: 18:53:52, time: 1.191, data_time: 0.078, memory: 16000, loss_rpn_cls: 0.0332, loss_rpn_bbox: 0.0389, loss_cls: 0.1961, acc: 93.1006, loss_bbox: 0.2377, loss_mask: 0.2474, loss: 0.7532 2023-11-15 16:28:01,932 - mmdet - INFO - Epoch [5][900/1833] lr: 2.000e-04, eta: 18:52:56, time: 1.184, data_time: 0.077, memory: 16000, loss_rpn_cls: 0.0309, loss_rpn_bbox: 0.0362, loss_cls: 0.1914, acc: 93.2661, loss_bbox: 0.2282, loss_mask: 0.2429, loss: 0.7297 2023-11-15 16:29:01,110 - mmdet - INFO - Epoch [5][950/1833] lr: 2.000e-04, eta: 18:51:59, time: 1.183, data_time: 0.082, memory: 16000, loss_rpn_cls: 0.0302, loss_rpn_bbox: 0.0362, loss_cls: 0.1923, acc: 93.2607, loss_bbox: 0.2331, loss_mask: 0.2457, loss: 0.7375 2023-11-15 16:30:00,822 - mmdet - INFO - Epoch [5][1000/1833] lr: 2.000e-04, eta: 18:51:06, time: 1.194, data_time: 0.081, memory: 16000, loss_rpn_cls: 0.0322, loss_rpn_bbox: 0.0379, loss_cls: 0.1967, acc: 93.0372, loss_bbox: 0.2400, loss_mask: 0.2474, loss: 0.7542 2023-11-15 16:31:00,586 - mmdet - INFO - Epoch [5][1050/1833] lr: 2.000e-04, eta: 18:50:14, time: 1.195, data_time: 0.081, memory: 16000, loss_rpn_cls: 0.0311, loss_rpn_bbox: 0.0375, loss_cls: 0.1937, acc: 93.2324, loss_bbox: 0.2334, loss_mask: 0.2441, loss: 0.7396 2023-11-15 16:31:59,622 - mmdet - INFO - Epoch [5][1100/1833] lr: 2.000e-04, eta: 18:49:16, time: 1.181, data_time: 0.079, memory: 16000, loss_rpn_cls: 0.0327, loss_rpn_bbox: 0.0384, loss_cls: 0.1978, acc: 93.0352, loss_bbox: 0.2399, loss_mask: 0.2478, loss: 0.7567 2023-11-15 16:32:58,525 - mmdet - INFO - Epoch [5][1150/1833] lr: 2.000e-04, eta: 18:48:17, time: 1.178, data_time: 0.071, memory: 16000, loss_rpn_cls: 0.0295, loss_rpn_bbox: 0.0361, loss_cls: 0.1958, acc: 93.1030, loss_bbox: 0.2354, loss_mask: 0.2401, loss: 0.7369 2023-11-15 16:33:57,166 - mmdet - INFO - Epoch [5][1200/1833] lr: 2.000e-04, eta: 18:47:17, time: 1.173, data_time: 0.081, memory: 16000, loss_rpn_cls: 0.0310, loss_rpn_bbox: 0.0373, loss_cls: 0.1942, acc: 93.2025, loss_bbox: 0.2324, loss_mask: 0.2424, loss: 0.7371 2023-11-15 16:34:57,851 - mmdet - INFO - Epoch [5][1250/1833] lr: 2.000e-04, eta: 18:46:30, time: 1.214, data_time: 0.076, memory: 16000, loss_rpn_cls: 0.0319, loss_rpn_bbox: 0.0381, loss_cls: 0.1950, acc: 93.1514, loss_bbox: 0.2361, loss_mask: 0.2486, loss: 0.7496 2023-11-15 16:36:02,184 - mmdet - INFO - Epoch [5][1300/1833] lr: 2.000e-04, eta: 18:46:08, time: 1.287, data_time: 0.080, memory: 16000, loss_rpn_cls: 0.0295, loss_rpn_bbox: 0.0364, loss_cls: 0.1966, acc: 93.1656, loss_bbox: 0.2366, loss_mask: 0.2435, loss: 0.7426 2023-11-15 16:37:02,473 - mmdet - INFO - Epoch [5][1350/1833] lr: 2.000e-04, eta: 18:45:18, time: 1.206, data_time: 0.080, memory: 16000, loss_rpn_cls: 0.0305, loss_rpn_bbox: 0.0370, loss_cls: 0.1908, acc: 93.2839, loss_bbox: 0.2326, loss_mask: 0.2439, loss: 0.7348 2023-11-15 16:38:02,001 - mmdet - INFO - Epoch [5][1400/1833] lr: 2.000e-04, eta: 18:44:23, time: 1.191, data_time: 0.080, memory: 16000, loss_rpn_cls: 0.0323, loss_rpn_bbox: 0.0382, loss_cls: 0.1961, acc: 93.0887, loss_bbox: 0.2388, loss_mask: 0.2450, loss: 0.7505 2023-11-15 16:39:03,634 - mmdet - INFO - Epoch [5][1450/1833] lr: 2.000e-04, eta: 18:43:42, time: 1.233, data_time: 0.083, memory: 16000, loss_rpn_cls: 0.0306, loss_rpn_bbox: 0.0366, loss_cls: 0.1932, acc: 93.1920, loss_bbox: 0.2344, loss_mask: 0.2446, loss: 0.7395 2023-11-15 16:40:03,164 - mmdet - INFO - Epoch [5][1500/1833] lr: 2.000e-04, eta: 18:42:47, time: 1.191, data_time: 0.081, memory: 16000, loss_rpn_cls: 0.0306, loss_rpn_bbox: 0.0380, loss_cls: 0.1959, acc: 93.1257, loss_bbox: 0.2362, loss_mask: 0.2410, loss: 0.7417 2023-11-15 16:41:02,309 - mmdet - INFO - Epoch [5][1550/1833] lr: 2.000e-04, eta: 18:41:49, time: 1.183, data_time: 0.078, memory: 16000, loss_rpn_cls: 0.0305, loss_rpn_bbox: 0.0378, loss_cls: 0.1960, acc: 93.1203, loss_bbox: 0.2362, loss_mask: 0.2472, loss: 0.7477 2023-11-15 16:42:03,111 - mmdet - INFO - Epoch [5][1600/1833] lr: 2.000e-04, eta: 18:41:02, time: 1.216, data_time: 0.079, memory: 16000, loss_rpn_cls: 0.0315, loss_rpn_bbox: 0.0376, loss_cls: 0.1981, acc: 93.0835, loss_bbox: 0.2392, loss_mask: 0.2446, loss: 0.7510 2023-11-15 16:43:02,061 - mmdet - INFO - Epoch [5][1650/1833] lr: 2.000e-04, eta: 18:40:03, time: 1.179, data_time: 0.077, memory: 16000, loss_rpn_cls: 0.0313, loss_rpn_bbox: 0.0374, loss_cls: 0.1978, acc: 93.0534, loss_bbox: 0.2373, loss_mask: 0.2432, loss: 0.7470 2023-11-15 16:44:01,072 - mmdet - INFO - Epoch [5][1700/1833] lr: 2.000e-04, eta: 18:39:05, time: 1.180, data_time: 0.072, memory: 16000, loss_rpn_cls: 0.0316, loss_rpn_bbox: 0.0375, loss_cls: 0.1971, acc: 93.1334, loss_bbox: 0.2344, loss_mask: 0.2434, loss: 0.7440 2023-11-15 16:45:01,751 - mmdet - INFO - Epoch [5][1750/1833] lr: 2.000e-04, eta: 18:38:17, time: 1.213, data_time: 0.077, memory: 16000, loss_rpn_cls: 0.0334, loss_rpn_bbox: 0.0378, loss_cls: 0.1997, acc: 93.0062, loss_bbox: 0.2392, loss_mask: 0.2441, loss: 0.7542 2023-11-15 16:46:00,583 - mmdet - INFO - Epoch [5][1800/1833] lr: 2.000e-04, eta: 18:37:17, time: 1.177, data_time: 0.079, memory: 16000, loss_rpn_cls: 0.0328, loss_rpn_bbox: 0.0384, loss_cls: 0.1986, acc: 92.9839, loss_bbox: 0.2365, loss_mask: 0.2460, loss: 0.7523 2023-11-15 16:46:39,840 - mmdet - INFO - Saving checkpoint at 5 epochs 2023-11-15 16:47:32,560 - mmdet - INFO - Evaluating bbox... 2023-11-15 16:48:07,752 - 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 ] = 0.678 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.495 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.294 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 ] = 0.577 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.581 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.581 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.581 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.418 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.623 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.719 2023-11-15 16:48:07,755 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.561 | bicycle | 0.354 | car | 0.464 | | motorcycle | 0.453 | airplane | 0.680 | bus | 0.671 | | train | 0.645 | truck | 0.407 | boat | 0.311 | | traffic light | 0.296 | fire hydrant | 0.692 | stop sign | 0.658 | | parking meter | 0.498 | bench | 0.268 | bird | 0.388 | | cat | 0.705 | dog | 0.656 | horse | 0.607 | | sheep | 0.563 | cow | 0.606 | elephant | 0.655 | | bear | 0.727 | zebra | 0.664 | giraffe | 0.702 | | backpack | 0.182 | umbrella | 0.419 | handbag | 0.187 | | tie | 0.355 | suitcase | 0.438 | frisbee | 0.686 | | skis | 0.264 | snowboard | 0.363 | sports ball | 0.450 | | kite | 0.421 | baseball bat | 0.382 | baseball glove | 0.430 | | skateboard | 0.546 | surfboard | 0.424 | tennis racket | 0.508 | | bottle | 0.425 | wine glass | 0.399 | cup | 0.480 | | fork | 0.393 | knife | 0.242 | spoon | 0.240 | | bowl | 0.439 | banana | 0.276 | apple | 0.229 | | sandwich | 0.426 | orange | 0.349 | broccoli | 0.242 | | carrot | 0.229 | hot dog | 0.407 | pizza | 0.535 | | donut | 0.522 | cake | 0.407 | chair | 0.323 | | couch | 0.431 | potted plant | 0.311 | bed | 0.455 | | dining table | 0.279 | toilet | 0.612 | tv | 0.599 | | laptop | 0.643 | mouse | 0.616 | remote | 0.369 | | keyboard | 0.501 | cell phone | 0.418 | microwave | 0.610 | | oven | 0.352 | toaster | 0.418 | sink | 0.421 | | refrigerator | 0.607 | book | 0.173 | clock | 0.509 | | vase | 0.429 | scissors | 0.355 | teddy bear | 0.482 | | hair drier | 0.054 | toothbrush | 0.283 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-15 16:48:07,755 - mmdet - INFO - Evaluating segm... 2023-11-15 16:48:43,319 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.404 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.643 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.431 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.206 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 ] = 0.589 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 ] = 0.348 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 ] = 0.686 2023-11-15 16:48:43,321 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.477 | bicycle | 0.202 | car | 0.424 | | motorcycle | 0.376 | airplane | 0.511 | bus | 0.663 | | train | 0.644 | truck | 0.400 | boat | 0.275 | | traffic light | 0.275 | fire hydrant | 0.660 | stop sign | 0.645 | | parking meter | 0.515 | bench | 0.203 | bird | 0.310 | | cat | 0.702 | dog | 0.626 | horse | 0.436 | | sheep | 0.495 | cow | 0.501 | elephant | 0.602 | | bear | 0.722 | zebra | 0.597 | giraffe | 0.542 | | backpack | 0.190 | umbrella | 0.494 | handbag | 0.190 | | tie | 0.328 | suitcase | 0.471 | frisbee | 0.647 | | skis | 0.032 | snowboard | 0.249 | sports ball | 0.433 | | kite | 0.280 | baseball bat | 0.258 | baseball glove | 0.445 | | skateboard | 0.348 | surfboard | 0.347 | tennis racket | 0.567 | | bottle | 0.404 | wine glass | 0.340 | cup | 0.480 | | fork | 0.198 | knife | 0.159 | spoon | 0.165 | | bowl | 0.416 | banana | 0.216 | apple | 0.232 | | sandwich | 0.444 | orange | 0.350 | broccoli | 0.239 | | carrot | 0.200 | hot dog | 0.313 | pizza | 0.511 | | donut | 0.524 | cake | 0.414 | chair | 0.229 | | couch | 0.384 | potted plant | 0.271 | bed | 0.367 | | dining table | 0.166 | toilet | 0.614 | tv | 0.624 | | laptop | 0.635 | mouse | 0.623 | remote | 0.334 | | keyboard | 0.511 | cell phone | 0.393 | microwave | 0.627 | | oven | 0.333 | toaster | 0.487 | sink | 0.409 | | refrigerator | 0.621 | book | 0.125 | clock | 0.512 | | vase | 0.426 | scissors | 0.263 | teddy bear | 0.479 | | hair drier | 0.030 | toothbrush | 0.157 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-15 16:48:43,874 - mmdet - INFO - The previous best checkpoint /mnt/petrelfs/lizhiqi/DINO/detection/work_dirs/mask_rcnn_flash_internimage_s_fpn_3x_coco_0.4/best_bbox_mAP_epoch_4.pth was removed 2023-11-15 16:48:45,908 - mmdet - INFO - Now best checkpoint is saved as best_bbox_mAP_epoch_5.pth. 2023-11-15 16:48:45,909 - mmdet - INFO - Best bbox_mAP is 0.4472 at 5 epoch. 2023-11-15 16:48:45,909 - mmdet - INFO - Exp name: mask_rcnn_flash_internimage_s_fpn_3x_coco_0.4.py 2023-11-15 16:48:45,909 - mmdet - INFO - Epoch(val) [5][625] bbox_mAP: 0.4472, bbox_mAP_50: 0.6783, bbox_mAP_75: 0.4946, bbox_mAP_s: 0.2943, bbox_mAP_m: 0.4906, bbox_mAP_l: 0.5769, bbox_mAP_copypaste: 0.4472 0.6783 0.4946 0.2943 0.4906 0.5769, segm_mAP: 0.4038, segm_mAP_50: 0.6434, segm_mAP_75: 0.4313, segm_mAP_s: 0.2055, segm_mAP_m: 0.4421, segm_mAP_l: 0.5894, segm_mAP_copypaste: 0.4038 0.6434 0.4313 0.2055 0.4421 0.5894 2023-11-15 16:49:49,724 - mmdet - INFO - Epoch [6][50/1833] lr: 2.000e-04, eta: 18:32:09, time: 1.276, data_time: 0.140, memory: 16000, loss_rpn_cls: 0.0293, loss_rpn_bbox: 0.0365, loss_cls: 0.1874, acc: 93.3201, loss_bbox: 0.2313, loss_mask: 0.2420, loss: 0.7265 2023-11-15 16:50:49,687 - mmdet - INFO - Epoch [6][100/1833] lr: 2.000e-04, eta: 18:31:18, time: 1.199, data_time: 0.080, memory: 16000, loss_rpn_cls: 0.0303, loss_rpn_bbox: 0.0370, loss_cls: 0.1905, acc: 93.2701, loss_bbox: 0.2291, loss_mask: 0.2386, loss: 0.7255 2023-11-15 16:51:48,883 - mmdet - INFO - Epoch [6][150/1833] lr: 2.000e-04, eta: 18:30:22, time: 1.184, data_time: 0.070, memory: 16000, loss_rpn_cls: 0.0291, loss_rpn_bbox: 0.0368, loss_cls: 0.1900, acc: 93.2916, loss_bbox: 0.2304, loss_mask: 0.2392, loss: 0.7255 2023-11-15 16:52:50,296 - mmdet - INFO - Epoch [6][200/1833] lr: 2.000e-04, eta: 18:29:39, time: 1.228, data_time: 0.071, memory: 16000, loss_rpn_cls: 0.0272, loss_rpn_bbox: 0.0346, loss_cls: 0.1854, acc: 93.4031, loss_bbox: 0.2279, loss_mask: 0.2360, loss: 0.7111 2023-11-15 16:53:51,634 - mmdet - INFO - Epoch [6][250/1833] lr: 2.000e-04, eta: 18:28:55, time: 1.227, data_time: 0.075, memory: 16000, loss_rpn_cls: 0.0310, loss_rpn_bbox: 0.0373, loss_cls: 0.1955, acc: 93.0286, loss_bbox: 0.2412, loss_mask: 0.2419, loss: 0.7469 2023-11-15 16:54:51,001 - mmdet - INFO - Epoch [6][300/1833] lr: 2.000e-04, eta: 18:28:00, time: 1.187, data_time: 0.071, memory: 16000, loss_rpn_cls: 0.0286, loss_rpn_bbox: 0.0365, loss_cls: 0.1888, acc: 93.3040, loss_bbox: 0.2322, loss_mask: 0.2421, loss: 0.7282 2023-11-15 16:55:50,411 - mmdet - INFO - Epoch [6][350/1833] lr: 2.000e-04, eta: 18:27:05, time: 1.188, data_time: 0.066, memory: 16000, loss_rpn_cls: 0.0303, loss_rpn_bbox: 0.0370, loss_cls: 0.1893, acc: 93.2484, loss_bbox: 0.2322, loss_mask: 0.2407, loss: 0.7295 2023-11-15 16:56:51,311 - mmdet - INFO - Epoch [6][400/1833] lr: 2.000e-04, eta: 18:26:18, time: 1.218, data_time: 0.074, memory: 16000, loss_rpn_cls: 0.0302, loss_rpn_bbox: 0.0376, loss_cls: 0.1871, acc: 93.3775, loss_bbox: 0.2312, loss_mask: 0.2407, loss: 0.7268 2023-11-15 16:57:52,532 - mmdet - INFO - Epoch [6][450/1833] lr: 2.000e-04, eta: 18:25:33, time: 1.224, data_time: 0.065, memory: 16000, loss_rpn_cls: 0.0303, loss_rpn_bbox: 0.0368, loss_cls: 0.1918, acc: 93.1665, loss_bbox: 0.2328, loss_mask: 0.2407, loss: 0.7324 2023-11-15 16:58:52,303 - mmdet - INFO - Epoch [6][500/1833] lr: 2.000e-04, eta: 18:24:40, time: 1.195, data_time: 0.063, memory: 16000, loss_rpn_cls: 0.0300, loss_rpn_bbox: 0.0353, loss_cls: 0.1811, acc: 93.5647, loss_bbox: 0.2259, loss_mask: 0.2405, loss: 0.7129 2023-11-15 16:59:52,364 - mmdet - INFO - Epoch [6][550/1833] lr: 2.000e-04, eta: 18:23:48, time: 1.201, data_time: 0.071, memory: 16000, loss_rpn_cls: 0.0292, loss_rpn_bbox: 0.0357, loss_cls: 0.1857, acc: 93.4336, loss_bbox: 0.2265, loss_mask: 0.2395, loss: 0.7166 2023-11-15 17:00:52,459 - mmdet - INFO - Epoch [6][600/1833] lr: 2.000e-04, eta: 18:22:56, time: 1.202, data_time: 0.065, memory: 16000, loss_rpn_cls: 0.0297, loss_rpn_bbox: 0.0359, loss_cls: 0.1886, acc: 93.3478, loss_bbox: 0.2287, loss_mask: 0.2396, loss: 0.7224 2023-11-15 17:01:53,159 - mmdet - INFO - Epoch [6][650/1833] lr: 2.000e-04, eta: 18:22:08, time: 1.214, data_time: 0.074, memory: 16000, loss_rpn_cls: 0.0319, loss_rpn_bbox: 0.0377, loss_cls: 0.1906, acc: 93.2860, loss_bbox: 0.2331, loss_mask: 0.2424, loss: 0.7357 2023-11-15 17:02:53,054 - mmdet - INFO - Epoch [6][700/1833] lr: 2.000e-04, eta: 18:21:15, time: 1.198, data_time: 0.063, memory: 16000, loss_rpn_cls: 0.0299, loss_rpn_bbox: 0.0366, loss_cls: 0.1906, acc: 93.2784, loss_bbox: 0.2338, loss_mask: 0.2406, loss: 0.7315 2023-11-15 17:03:53,043 - mmdet - INFO - Epoch [6][750/1833] lr: 2.000e-04, eta: 18:20:23, time: 1.200, data_time: 0.067, memory: 16000, loss_rpn_cls: 0.0297, loss_rpn_bbox: 0.0367, loss_cls: 0.1891, acc: 93.3084, loss_bbox: 0.2291, loss_mask: 0.2393, loss: 0.7240 2023-11-15 17:04:53,476 - mmdet - INFO - Epoch [6][800/1833] lr: 2.000e-04, eta: 18:19:33, time: 1.209, data_time: 0.076, memory: 16000, loss_rpn_cls: 0.0299, loss_rpn_bbox: 0.0369, loss_cls: 0.1899, acc: 93.2521, loss_bbox: 0.2343, loss_mask: 0.2430, loss: 0.7340 2023-11-15 17:05:53,181 - mmdet - INFO - Epoch [6][850/1833] lr: 2.000e-04, eta: 18:18:38, time: 1.194, data_time: 0.070, memory: 16000, loss_rpn_cls: 0.0296, loss_rpn_bbox: 0.0369, loss_cls: 0.1907, acc: 93.2359, loss_bbox: 0.2348, loss_mask: 0.2428, loss: 0.7349 2023-11-15 17:06:53,834 - mmdet - INFO - Epoch [6][900/1833] lr: 2.000e-04, eta: 18:17:49, time: 1.213, data_time: 0.070, memory: 16000, loss_rpn_cls: 0.0307, loss_rpn_bbox: 0.0371, loss_cls: 0.1935, acc: 93.1723, loss_bbox: 0.2383, loss_mask: 0.2426, loss: 0.7422 2023-11-15 17:07:54,898 - mmdet - INFO - Epoch [6][950/1833] lr: 2.000e-04, eta: 18:17:02, time: 1.221, data_time: 0.066, memory: 16000, loss_rpn_cls: 0.0307, loss_rpn_bbox: 0.0365, loss_cls: 0.1919, acc: 93.2269, loss_bbox: 0.2347, loss_mask: 0.2402, loss: 0.7340 2023-11-15 17:08:54,880 - mmdet - INFO - Epoch [6][1000/1833] lr: 2.000e-04, eta: 18:16:09, time: 1.200, data_time: 0.067, memory: 16000, loss_rpn_cls: 0.0293, loss_rpn_bbox: 0.0365, loss_cls: 0.1894, acc: 93.3297, loss_bbox: 0.2304, loss_mask: 0.2381, loss: 0.7237 2023-11-15 17:09:53,550 - mmdet - INFO - Epoch [6][1050/1833] lr: 2.000e-04, eta: 18:15:09, time: 1.173, data_time: 0.065, memory: 16000, loss_rpn_cls: 0.0304, loss_rpn_bbox: 0.0365, loss_cls: 0.1880, acc: 93.3412, loss_bbox: 0.2285, loss_mask: 0.2417, loss: 0.7252 2023-11-15 17:10:51,589 - mmdet - INFO - Epoch [6][1100/1833] lr: 2.000e-04, eta: 18:14:05, time: 1.161, data_time: 0.059, memory: 16000, loss_rpn_cls: 0.0293, loss_rpn_bbox: 0.0356, loss_cls: 0.1835, acc: 93.5486, loss_bbox: 0.2245, loss_mask: 0.2387, loss: 0.7117 2023-11-15 17:11:51,164 - mmdet - INFO - Epoch [6][1150/1833] lr: 2.000e-04, eta: 18:13:10, time: 1.192, data_time: 0.068, memory: 16000, loss_rpn_cls: 0.0303, loss_rpn_bbox: 0.0375, loss_cls: 0.1914, acc: 93.1918, loss_bbox: 0.2359, loss_mask: 0.2430, loss: 0.7381 2023-11-15 17:12:53,072 - mmdet - INFO - Epoch [6][1200/1833] lr: 2.000e-04, eta: 18:12:27, time: 1.238, data_time: 0.091, memory: 16000, loss_rpn_cls: 0.0299, loss_rpn_bbox: 0.0368, loss_cls: 0.1889, acc: 93.3219, loss_bbox: 0.2304, loss_mask: 0.2410, loss: 0.7270 2023-11-15 17:13:52,875 - mmdet - INFO - Epoch [6][1250/1833] lr: 2.000e-04, eta: 18:11:33, time: 1.196, data_time: 0.073, memory: 16000, loss_rpn_cls: 0.0296, loss_rpn_bbox: 0.0371, loss_cls: 0.1874, acc: 93.3685, loss_bbox: 0.2302, loss_mask: 0.2416, loss: 0.7259 2023-11-15 17:14:51,859 - mmdet - INFO - Epoch [6][1300/1833] lr: 2.000e-04, eta: 18:10:35, time: 1.180, data_time: 0.070, memory: 16000, loss_rpn_cls: 0.0273, loss_rpn_bbox: 0.0357, loss_cls: 0.1895, acc: 93.2584, loss_bbox: 0.2325, loss_mask: 0.2396, loss: 0.7246 2023-11-15 17:15:51,852 - mmdet - INFO - Epoch [6][1350/1833] lr: 2.000e-04, eta: 18:09:41, time: 1.200, data_time: 0.069, memory: 16000, loss_rpn_cls: 0.0300, loss_rpn_bbox: 0.0373, loss_cls: 0.1945, acc: 93.0248, loss_bbox: 0.2365, loss_mask: 0.2425, loss: 0.7409 2023-11-15 17:16:50,625 - mmdet - INFO - Epoch [6][1400/1833] lr: 2.000e-04, eta: 18:08:41, time: 1.175, data_time: 0.070, memory: 16000, loss_rpn_cls: 0.0308, loss_rpn_bbox: 0.0377, loss_cls: 0.1968, acc: 93.1328, loss_bbox: 0.2360, loss_mask: 0.2448, loss: 0.7461 2023-11-15 17:17:49,675 - mmdet - INFO - Epoch [6][1450/1833] lr: 2.000e-04, eta: 18:07:43, time: 1.181, data_time: 0.075, memory: 16000, loss_rpn_cls: 0.0281, loss_rpn_bbox: 0.0367, loss_cls: 0.1917, acc: 93.2201, loss_bbox: 0.2342, loss_mask: 0.2435, loss: 0.7341 2023-11-15 17:18:50,116 - mmdet - INFO - Epoch [6][1500/1833] lr: 2.000e-04, eta: 18:06:52, time: 1.209, data_time: 0.068, memory: 16000, loss_rpn_cls: 0.0289, loss_rpn_bbox: 0.0361, loss_cls: 0.1926, acc: 93.1943, loss_bbox: 0.2349, loss_mask: 0.2428, loss: 0.7353 2023-11-15 17:19:49,682 - mmdet - INFO - Epoch [6][1550/1833] lr: 2.000e-04, eta: 18:05:56, time: 1.191, data_time: 0.065, memory: 16000, loss_rpn_cls: 0.0304, loss_rpn_bbox: 0.0352, loss_cls: 0.1888, acc: 93.3472, loss_bbox: 0.2279, loss_mask: 0.2410, loss: 0.7234 2023-11-15 17:20:49,465 - mmdet - INFO - Epoch [6][1600/1833] lr: 2.000e-04, eta: 18:05:02, time: 1.196, data_time: 0.068, memory: 16000, loss_rpn_cls: 0.0289, loss_rpn_bbox: 0.0343, loss_cls: 0.1848, acc: 93.4917, loss_bbox: 0.2237, loss_mask: 0.2374, loss: 0.7091 2023-11-15 17:21:48,925 - mmdet - INFO - Epoch [6][1650/1833] lr: 2.000e-04, eta: 18:04:05, time: 1.189, data_time: 0.068, memory: 16000, loss_rpn_cls: 0.0307, loss_rpn_bbox: 0.0370, loss_cls: 0.1909, acc: 93.2591, loss_bbox: 0.2311, loss_mask: 0.2390, loss: 0.7288 2023-11-15 17:22:48,017 - mmdet - INFO - Epoch [6][1700/1833] lr: 2.000e-04, eta: 18:03:07, time: 1.182, data_time: 0.076, memory: 16000, loss_rpn_cls: 0.0291, loss_rpn_bbox: 0.0375, loss_cls: 0.1921, acc: 93.1873, loss_bbox: 0.2325, loss_mask: 0.2410, loss: 0.7322 2023-11-15 17:23:47,653 - mmdet - INFO - Epoch [6][1750/1833] lr: 2.000e-04, eta: 18:02:12, time: 1.193, data_time: 0.066, memory: 16000, loss_rpn_cls: 0.0294, loss_rpn_bbox: 0.0362, loss_cls: 0.1891, acc: 93.3192, loss_bbox: 0.2298, loss_mask: 0.2402, loss: 0.7247 2023-11-15 17:24:46,697 - mmdet - INFO - Epoch [6][1800/1833] lr: 2.000e-04, eta: 18:01:13, time: 1.181, data_time: 0.070, memory: 16000, loss_rpn_cls: 0.0297, loss_rpn_bbox: 0.0366, loss_cls: 0.1928, acc: 93.2083, loss_bbox: 0.2323, loss_mask: 0.2402, loss: 0.7316 2023-11-15 17:25:27,215 - mmdet - INFO - Saving checkpoint at 6 epochs 2023-11-15 17:26:17,858 - mmdet - INFO - Evaluating bbox... 2023-11-15 17:26:51,387 - 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 ] = 0.683 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.504 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.291 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.497 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.580 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.586 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.586 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.586 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 ] = 0.631 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.726 2023-11-15 17:26:51,389 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.567 | bicycle | 0.368 | car | 0.475 | | motorcycle | 0.456 | airplane | 0.650 | bus | 0.654 | | train | 0.639 | truck | 0.408 | boat | 0.298 | | traffic light | 0.301 | fire hydrant | 0.695 | stop sign | 0.646 | | parking meter | 0.486 | bench | 0.292 | bird | 0.395 | | cat | 0.731 | dog | 0.653 | horse | 0.586 | | sheep | 0.570 | cow | 0.600 | elephant | 0.675 | | bear | 0.715 | zebra | 0.682 | giraffe | 0.695 | | backpack | 0.178 | umbrella | 0.432 | handbag | 0.188 | | tie | 0.354 | suitcase | 0.460 | frisbee | 0.705 | | skis | 0.267 | snowboard | 0.352 | sports ball | 0.463 | | kite | 0.447 | baseball bat | 0.412 | baseball glove | 0.443 | | skateboard | 0.550 | surfboard | 0.429 | tennis racket | 0.517 | | bottle | 0.430 | wine glass | 0.402 | cup | 0.472 | | fork | 0.421 | knife | 0.258 | spoon | 0.254 | | bowl | 0.463 | banana | 0.256 | apple | 0.231 | | sandwich | 0.396 | orange | 0.328 | broccoli | 0.260 | | carrot | 0.238 | hot dog | 0.410 | pizza | 0.521 | | donut | 0.523 | cake | 0.421 | chair | 0.327 | | couch | 0.461 | potted plant | 0.317 | bed | 0.441 | | dining table | 0.277 | toilet | 0.598 | tv | 0.606 | | laptop | 0.640 | mouse | 0.644 | remote | 0.371 | | keyboard | 0.478 | cell phone | 0.413 | microwave | 0.618 | | oven | 0.383 | toaster | 0.490 | sink | 0.409 | | refrigerator | 0.599 | book | 0.185 | clock | 0.523 | | vase | 0.432 | scissors | 0.337 | teddy bear | 0.521 | | hair drier | 0.092 | toothbrush | 0.286 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-15 17:26:51,389 - mmdet - INFO - Evaluating segm... 2023-11-15 17:27:26,806 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.413 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.653 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.442 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.213 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.455 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.593 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.539 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.539 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.539 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.351 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.587 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.694 2023-11-15 17:27:26,808 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.489 | bicycle | 0.216 | car | 0.440 | | motorcycle | 0.367 | airplane | 0.508 | bus | 0.664 | | train | 0.656 | truck | 0.402 | boat | 0.281 | | traffic light | 0.284 | fire hydrant | 0.683 | stop sign | 0.650 | | parking meter | 0.504 | bench | 0.219 | bird | 0.333 | | cat | 0.727 | dog | 0.645 | horse | 0.448 | | sheep | 0.508 | cow | 0.526 | elephant | 0.617 | | bear | 0.723 | zebra | 0.605 | giraffe | 0.545 | | backpack | 0.188 | umbrella | 0.506 | handbag | 0.192 | | tie | 0.338 | suitcase | 0.486 | frisbee | 0.677 | | skis | 0.042 | snowboard | 0.246 | sports ball | 0.445 | | kite | 0.301 | baseball bat | 0.293 | baseball glove | 0.452 | | skateboard | 0.348 | surfboard | 0.339 | tennis racket | 0.571 | | bottle | 0.412 | wine glass | 0.358 | cup | 0.476 | | fork | 0.211 | knife | 0.182 | spoon | 0.169 | | bowl | 0.445 | banana | 0.216 | apple | 0.230 | | sandwich | 0.434 | orange | 0.329 | broccoli | 0.255 | | carrot | 0.202 | hot dog | 0.349 | pizza | 0.511 | | donut | 0.538 | cake | 0.428 | chair | 0.240 | | couch | 0.405 | potted plant | 0.278 | bed | 0.349 | | dining table | 0.165 | toilet | 0.610 | tv | 0.634 | | laptop | 0.656 | mouse | 0.642 | remote | 0.336 | | keyboard | 0.494 | cell phone | 0.391 | microwave | 0.634 | | oven | 0.350 | toaster | 0.517 | sink | 0.400 | | refrigerator | 0.619 | book | 0.140 | clock | 0.521 | | vase | 0.431 | scissors | 0.279 | teddy bear | 0.502 | | hair drier | 0.037 | toothbrush | 0.171 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-15 17:27:27,352 - mmdet - INFO - The previous best checkpoint /mnt/petrelfs/lizhiqi/DINO/detection/work_dirs/mask_rcnn_flash_internimage_s_fpn_3x_coco_0.4/best_bbox_mAP_epoch_5.pth was removed 2023-11-15 17:27:29,485 - mmdet - INFO - Now best checkpoint is saved as best_bbox_mAP_epoch_6.pth. 2023-11-15 17:27:29,485 - mmdet - INFO - Best bbox_mAP is 0.4521 at 6 epoch. 2023-11-15 17:27:29,485 - mmdet - INFO - Exp name: mask_rcnn_flash_internimage_s_fpn_3x_coco_0.4.py 2023-11-15 17:27:29,485 - mmdet - INFO - Epoch(val) [6][625] bbox_mAP: 0.4521, bbox_mAP_50: 0.6829, bbox_mAP_75: 0.5036, bbox_mAP_s: 0.2906, bbox_mAP_m: 0.4972, bbox_mAP_l: 0.5801, bbox_mAP_copypaste: 0.4521 0.6829 0.5036 0.2906 0.4972 0.5801, segm_mAP: 0.4127, segm_mAP_50: 0.6532, segm_mAP_75: 0.4423, segm_mAP_s: 0.2128, segm_mAP_m: 0.4547, segm_mAP_l: 0.5929, segm_mAP_copypaste: 0.4127 0.6532 0.4423 0.2128 0.4547 0.5929 2023-11-15 17:28:33,766 - mmdet - INFO - Epoch [7][50/1833] lr: 2.000e-04, eta: 17:56:48, time: 1.285, data_time: 0.139, memory: 16000, loss_rpn_cls: 0.0296, loss_rpn_bbox: 0.0377, loss_cls: 0.1890, acc: 93.2966, loss_bbox: 0.2325, loss_mask: 0.2389, loss: 0.7276 2023-11-15 17:29:33,798 - mmdet - INFO - Epoch [7][100/1833] lr: 2.000e-04, eta: 17:55:56, time: 1.201, data_time: 0.079, memory: 16000, loss_rpn_cls: 0.0294, loss_rpn_bbox: 0.0361, loss_cls: 0.1846, acc: 93.3890, loss_bbox: 0.2280, loss_mask: 0.2359, loss: 0.7141 2023-11-15 17:30:34,018 - mmdet - INFO - Epoch [7][150/1833] lr: 2.000e-04, eta: 17:55:04, time: 1.204, data_time: 0.065, memory: 16000, loss_rpn_cls: 0.0283, loss_rpn_bbox: 0.0359, loss_cls: 0.1850, acc: 93.3980, loss_bbox: 0.2283, loss_mask: 0.2372, loss: 0.7147 2023-11-15 17:31:35,657 - mmdet - INFO - Epoch [7][200/1833] lr: 2.000e-04, eta: 17:54:19, time: 1.233, data_time: 0.078, memory: 16000, loss_rpn_cls: 0.0284, loss_rpn_bbox: 0.0355, loss_cls: 0.1839, acc: 93.3935, loss_bbox: 0.2289, loss_mask: 0.2394, loss: 0.7161 2023-11-15 17:32:35,865 - mmdet - INFO - Epoch [7][250/1833] lr: 2.000e-04, eta: 17:53:27, time: 1.204, data_time: 0.075, memory: 16000, loss_rpn_cls: 0.0289, loss_rpn_bbox: 0.0369, loss_cls: 0.1884, acc: 93.2867, loss_bbox: 0.2306, loss_mask: 0.2405, loss: 0.7254 2023-11-15 17:33:36,670 - mmdet - INFO - Epoch [7][300/1833] lr: 2.000e-04, eta: 17:52:37, time: 1.216, data_time: 0.067, memory: 16000, loss_rpn_cls: 0.0289, loss_rpn_bbox: 0.0355, loss_cls: 0.1839, acc: 93.4254, loss_bbox: 0.2291, loss_mask: 0.2363, loss: 0.7137 2023-11-15 17:34:37,476 - mmdet - INFO - Epoch [7][350/1833] lr: 2.000e-04, eta: 17:51:48, time: 1.216, data_time: 0.075, memory: 16000, loss_rpn_cls: 0.0294, loss_rpn_bbox: 0.0365, loss_cls: 0.1859, acc: 93.3646, loss_bbox: 0.2292, loss_mask: 0.2400, loss: 0.7211 2023-11-15 17:35:38,438 - mmdet - INFO - Epoch [7][400/1833] lr: 2.000e-04, eta: 17:50:59, time: 1.219, data_time: 0.073, memory: 16000, loss_rpn_cls: 0.0291, loss_rpn_bbox: 0.0363, loss_cls: 0.1836, acc: 93.4322, loss_bbox: 0.2260, loss_mask: 0.2350, loss: 0.7099 2023-11-15 17:36:38,138 - mmdet - INFO - Epoch [7][450/1833] lr: 2.000e-04, eta: 17:50:04, time: 1.194, data_time: 0.072, memory: 16000, loss_rpn_cls: 0.0284, loss_rpn_bbox: 0.0344, loss_cls: 0.1811, acc: 93.6040, loss_bbox: 0.2213, loss_mask: 0.2372, loss: 0.7024 2023-11-15 17:37:38,361 - mmdet - INFO - Epoch [7][500/1833] lr: 2.000e-04, eta: 17:49:12, time: 1.204, data_time: 0.067, memory: 16000, loss_rpn_cls: 0.0289, loss_rpn_bbox: 0.0360, loss_cls: 0.1865, acc: 93.3301, loss_bbox: 0.2287, loss_mask: 0.2388, loss: 0.7191 2023-11-15 17:38:38,942 - mmdet - INFO - Epoch [7][550/1833] lr: 2.000e-04, eta: 17:48:21, time: 1.212, data_time: 0.069, memory: 16000, loss_rpn_cls: 0.0283, loss_rpn_bbox: 0.0356, loss_cls: 0.1815, acc: 93.5765, loss_bbox: 0.2254, loss_mask: 0.2395, loss: 0.7104 2023-11-15 17:39:37,932 - mmdet - INFO - Epoch [7][600/1833] lr: 2.000e-04, eta: 17:47:23, time: 1.180, data_time: 0.072, memory: 16000, loss_rpn_cls: 0.0293, loss_rpn_bbox: 0.0363, loss_cls: 0.1910, acc: 93.2195, loss_bbox: 0.2340, loss_mask: 0.2364, loss: 0.7269 2023-11-15 17:40:37,769 - mmdet - INFO - Epoch [7][650/1833] lr: 2.000e-04, eta: 17:46:29, time: 1.197, data_time: 0.076, memory: 16000, loss_rpn_cls: 0.0283, loss_rpn_bbox: 0.0362, loss_cls: 0.1857, acc: 93.3653, loss_bbox: 0.2323, loss_mask: 0.2391, loss: 0.7217 2023-11-15 17:41:37,951 - mmdet - INFO - Epoch [7][700/1833] lr: 2.000e-04, eta: 17:45:36, time: 1.204, data_time: 0.068, memory: 16000, loss_rpn_cls: 0.0276, loss_rpn_bbox: 0.0351, loss_cls: 0.1841, acc: 93.4589, loss_bbox: 0.2255, loss_mask: 0.2373, loss: 0.7096 2023-11-15 17:42:38,619 - mmdet - INFO - Epoch [7][750/1833] lr: 2.000e-04, eta: 17:44:45, time: 1.213, data_time: 0.075, memory: 16000, loss_rpn_cls: 0.0285, loss_rpn_bbox: 0.0358, loss_cls: 0.1866, acc: 93.3439, loss_bbox: 0.2290, loss_mask: 0.2383, loss: 0.7182 2023-11-15 17:43:38,664 - mmdet - INFO - Epoch [7][800/1833] lr: 2.000e-04, eta: 17:43:51, time: 1.201, data_time: 0.065, memory: 16000, loss_rpn_cls: 0.0283, loss_rpn_bbox: 0.0347, loss_cls: 0.1794, acc: 93.6359, loss_bbox: 0.2208, loss_mask: 0.2357, loss: 0.6989 2023-11-15 17:44:38,282 - mmdet - INFO - Epoch [7][850/1833] lr: 2.000e-04, eta: 17:42:56, time: 1.192, data_time: 0.069, memory: 16000, loss_rpn_cls: 0.0280, loss_rpn_bbox: 0.0354, loss_cls: 0.1854, acc: 93.4449, loss_bbox: 0.2265, loss_mask: 0.2347, loss: 0.7100 2023-11-15 17:45:38,520 - mmdet - INFO - Epoch [7][900/1833] lr: 2.000e-04, eta: 17:42:03, time: 1.205, data_time: 0.068, memory: 16000, loss_rpn_cls: 0.0274, loss_rpn_bbox: 0.0355, loss_cls: 0.1835, acc: 93.4744, loss_bbox: 0.2243, loss_mask: 0.2389, loss: 0.7097 2023-11-15 17:46:39,423 - mmdet - INFO - Epoch [7][950/1833] lr: 2.000e-04, eta: 17:41:13, time: 1.218, data_time: 0.075, memory: 16000, loss_rpn_cls: 0.0288, loss_rpn_bbox: 0.0356, loss_cls: 0.1847, acc: 93.4608, loss_bbox: 0.2236, loss_mask: 0.2346, loss: 0.7073 2023-11-15 17:47:40,002 - mmdet - INFO - Epoch [7][1000/1833] lr: 2.000e-04, eta: 17:40:22, time: 1.212, data_time: 0.066, memory: 16000, loss_rpn_cls: 0.0277, loss_rpn_bbox: 0.0351, loss_cls: 0.1852, acc: 93.4217, loss_bbox: 0.2273, loss_mask: 0.2373, loss: 0.7126 2023-11-15 17:48:39,212 - mmdet - INFO - Epoch [7][1050/1833] lr: 2.000e-04, eta: 17:39:24, time: 1.184, data_time: 0.062, memory: 16000, loss_rpn_cls: 0.0286, loss_rpn_bbox: 0.0351, loss_cls: 0.1826, acc: 93.5422, loss_bbox: 0.2237, loss_mask: 0.2367, loss: 0.7066 2023-11-15 17:49:38,249 - mmdet - INFO - Epoch [7][1100/1833] lr: 2.000e-04, eta: 17:38:26, time: 1.181, data_time: 0.061, memory: 16000, loss_rpn_cls: 0.0288, loss_rpn_bbox: 0.0351, loss_cls: 0.1849, acc: 93.4636, loss_bbox: 0.2237, loss_mask: 0.2337, loss: 0.7061 2023-11-15 17:50:38,442 - mmdet - INFO - Epoch [7][1150/1833] lr: 2.000e-04, eta: 17:37:32, time: 1.204, data_time: 0.067, memory: 16000, loss_rpn_cls: 0.0277, loss_rpn_bbox: 0.0353, loss_cls: 0.1834, acc: 93.4354, loss_bbox: 0.2268, loss_mask: 0.2350, loss: 0.7082 2023-11-15 17:51:39,826 - mmdet - INFO - Epoch [7][1200/1833] lr: 2.000e-04, eta: 17:36:44, time: 1.228, data_time: 0.071, memory: 16000, loss_rpn_cls: 0.0276, loss_rpn_bbox: 0.0346, loss_cls: 0.1802, acc: 93.6008, loss_bbox: 0.2224, loss_mask: 0.2344, loss: 0.6992 2023-11-15 17:52:40,447 - mmdet - INFO - Epoch [7][1250/1833] lr: 2.000e-04, eta: 17:35:53, time: 1.213, data_time: 0.064, memory: 16000, loss_rpn_cls: 0.0278, loss_rpn_bbox: 0.0354, loss_cls: 0.1843, acc: 93.4704, loss_bbox: 0.2249, loss_mask: 0.2364, loss: 0.7088 2023-11-15 17:53:40,784 - mmdet - INFO - Epoch [7][1300/1833] lr: 2.000e-04, eta: 17:35:00, time: 1.207, data_time: 0.069, memory: 16000, loss_rpn_cls: 0.0279, loss_rpn_bbox: 0.0350, loss_cls: 0.1844, acc: 93.4869, loss_bbox: 0.2241, loss_mask: 0.2354, loss: 0.7067 2023-11-15 17:54:41,858 - mmdet - INFO - Epoch [7][1350/1833] lr: 2.000e-04, eta: 17:34:10, time: 1.222, data_time: 0.071, memory: 16000, loss_rpn_cls: 0.0296, loss_rpn_bbox: 0.0374, loss_cls: 0.1898, acc: 93.3195, loss_bbox: 0.2319, loss_mask: 0.2381, loss: 0.7268 2023-11-15 17:55:42,134 - mmdet - INFO - Epoch [7][1400/1833] lr: 2.000e-04, eta: 17:33:17, time: 1.205, data_time: 0.077, memory: 16000, loss_rpn_cls: 0.0282, loss_rpn_bbox: 0.0367, loss_cls: 0.1864, acc: 93.3203, loss_bbox: 0.2300, loss_mask: 0.2405, loss: 0.7217 2023-11-15 17:56:41,625 - mmdet - INFO - Epoch [7][1450/1833] lr: 2.000e-04, eta: 17:32:20, time: 1.190, data_time: 0.067, memory: 16000, loss_rpn_cls: 0.0295, loss_rpn_bbox: 0.0361, loss_cls: 0.1866, acc: 93.3193, loss_bbox: 0.2292, loss_mask: 0.2367, loss: 0.7182 2023-11-15 17:57:40,158 - mmdet - INFO - Epoch [7][1500/1833] lr: 2.000e-04, eta: 17:31:19, time: 1.171, data_time: 0.061, memory: 16000, loss_rpn_cls: 0.0251, loss_rpn_bbox: 0.0343, loss_cls: 0.1803, acc: 93.5961, loss_bbox: 0.2215, loss_mask: 0.2377, loss: 0.6989 2023-11-15 17:58:40,593 - mmdet - INFO - Epoch [7][1550/1833] lr: 2.000e-04, eta: 17:30:27, time: 1.209, data_time: 0.068, memory: 16000, loss_rpn_cls: 0.0299, loss_rpn_bbox: 0.0368, loss_cls: 0.1915, acc: 93.1821, loss_bbox: 0.2323, loss_mask: 0.2390, loss: 0.7295 2023-11-15 17:59:40,994 - mmdet - INFO - Epoch [7][1600/1833] lr: 2.000e-04, eta: 17:29:34, time: 1.208, data_time: 0.071, memory: 16000, loss_rpn_cls: 0.0289, loss_rpn_bbox: 0.0366, loss_cls: 0.1874, acc: 93.4143, loss_bbox: 0.2276, loss_mask: 0.2380, loss: 0.7185 2023-11-15 18:00:41,221 - mmdet - INFO - Epoch [7][1650/1833] lr: 2.000e-04, eta: 17:28:40, time: 1.205, data_time: 0.078, memory: 16000, loss_rpn_cls: 0.0276, loss_rpn_bbox: 0.0350, loss_cls: 0.1859, acc: 93.4110, loss_bbox: 0.2264, loss_mask: 0.2348, loss: 0.7098 2023-11-15 18:01:40,170 - mmdet - INFO - Epoch [7][1700/1833] lr: 2.000e-04, eta: 17:27:41, time: 1.179, data_time: 0.071, memory: 16000, loss_rpn_cls: 0.0306, loss_rpn_bbox: 0.0358, loss_cls: 0.1861, acc: 93.4263, loss_bbox: 0.2271, loss_mask: 0.2400, loss: 0.7197 2023-11-15 18:02:40,539 - mmdet - INFO - Epoch [7][1750/1833] lr: 2.000e-04, eta: 17:26:48, time: 1.207, data_time: 0.073, memory: 16000, loss_rpn_cls: 0.0285, loss_rpn_bbox: 0.0354, loss_cls: 0.1876, acc: 93.3177, loss_bbox: 0.2299, loss_mask: 0.2378, loss: 0.7191 2023-11-15 18:03:40,153 - mmdet - INFO - Epoch [7][1800/1833] lr: 2.000e-04, eta: 17:25:51, time: 1.192, data_time: 0.071, memory: 16000, loss_rpn_cls: 0.0273, loss_rpn_bbox: 0.0353, loss_cls: 0.1816, acc: 93.5265, loss_bbox: 0.2216, loss_mask: 0.2375, loss: 0.7033 2023-11-15 18:04:20,670 - mmdet - INFO - Saving checkpoint at 7 epochs 2023-11-15 18:05:09,393 - mmdet - INFO - Evaluating bbox... 2023-11-15 18:05:40,392 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.462 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.690 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.510 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.317 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.501 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.589 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.595 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.595 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.595 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.443 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 ] = 0.727 2023-11-15 18:05:40,395 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.570 | bicycle | 0.368 | car | 0.474 | | motorcycle | 0.463 | airplane | 0.683 | bus | 0.690 | | train | 0.654 | truck | 0.424 | boat | 0.316 | | traffic light | 0.314 | fire hydrant | 0.707 | stop sign | 0.664 | | parking meter | 0.470 | bench | 0.290 | bird | 0.389 | | cat | 0.710 | dog | 0.669 | horse | 0.588 | | sheep | 0.581 | cow | 0.595 | elephant | 0.685 | | bear | 0.747 | zebra | 0.684 | giraffe | 0.679 | | backpack | 0.202 | umbrella | 0.434 | handbag | 0.196 | | tie | 0.363 | suitcase | 0.487 | frisbee | 0.711 | | skis | 0.261 | snowboard | 0.409 | sports ball | 0.464 | | kite | 0.453 | baseball bat | 0.381 | baseball glove | 0.431 | | skateboard | 0.570 | surfboard | 0.421 | tennis racket | 0.517 | | bottle | 0.444 | wine glass | 0.403 | cup | 0.483 | | fork | 0.424 | knife | 0.265 | spoon | 0.259 | | bowl | 0.456 | banana | 0.278 | apple | 0.247 | | sandwich | 0.425 | orange | 0.354 | broccoli | 0.256 | | carrot | 0.256 | hot dog | 0.458 | pizza | 0.533 | | donut | 0.568 | cake | 0.436 | chair | 0.338 | | couch | 0.448 | potted plant | 0.316 | bed | 0.477 | | dining table | 0.287 | toilet | 0.619 | tv | 0.610 | | laptop | 0.638 | mouse | 0.643 | remote | 0.403 | | keyboard | 0.505 | cell phone | 0.406 | microwave | 0.619 | | oven | 0.373 | toaster | 0.549 | sink | 0.451 | | refrigerator | 0.615 | book | 0.176 | clock | 0.519 | | vase | 0.433 | scissors | 0.379 | teddy bear | 0.493 | | hair drier | 0.106 | toothbrush | 0.259 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-15 18:05:40,395 - mmdet - INFO - Evaluating segm... 2023-11-15 18:06:15,543 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.419 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.660 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 ] = 0.454 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.595 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.545 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.545 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.545 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.378 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.585 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.690 2023-11-15 18:06:15,546 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.497 | bicycle | 0.209 | car | 0.438 | | motorcycle | 0.386 | airplane | 0.532 | bus | 0.687 | | train | 0.669 | truck | 0.415 | boat | 0.292 | | traffic light | 0.299 | fire hydrant | 0.685 | stop sign | 0.648 | | parking meter | 0.491 | bench | 0.215 | bird | 0.327 | | cat | 0.725 | dog | 0.635 | horse | 0.446 | | sheep | 0.515 | cow | 0.511 | elephant | 0.629 | | bear | 0.741 | zebra | 0.605 | giraffe | 0.539 | | backpack | 0.202 | umbrella | 0.514 | handbag | 0.194 | | tie | 0.342 | suitcase | 0.496 | frisbee | 0.674 | | skis | 0.038 | snowboard | 0.259 | sports ball | 0.451 | | kite | 0.320 | baseball bat | 0.283 | baseball glove | 0.455 | | skateboard | 0.374 | surfboard | 0.333 | tennis racket | 0.582 | | bottle | 0.419 | wine glass | 0.367 | cup | 0.484 | | fork | 0.211 | knife | 0.185 | spoon | 0.170 | | bowl | 0.433 | banana | 0.228 | apple | 0.241 | | sandwich | 0.457 | orange | 0.354 | broccoli | 0.256 | | carrot | 0.222 | hot dog | 0.395 | pizza | 0.509 | | donut | 0.571 | cake | 0.449 | chair | 0.244 | | couch | 0.393 | potted plant | 0.269 | bed | 0.381 | | dining table | 0.169 | toilet | 0.617 | tv | 0.644 | | laptop | 0.640 | mouse | 0.628 | remote | 0.353 | | keyboard | 0.512 | cell phone | 0.383 | microwave | 0.649 | | oven | 0.348 | toaster | 0.581 | sink | 0.426 | | refrigerator | 0.630 | book | 0.129 | clock | 0.516 | | vase | 0.429 | scissors | 0.260 | teddy bear | 0.497 | | hair drier | 0.052 | toothbrush | 0.191 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-15 18:06:16,047 - mmdet - INFO - The previous best checkpoint /mnt/petrelfs/lizhiqi/DINO/detection/work_dirs/mask_rcnn_flash_internimage_s_fpn_3x_coco_0.4/best_bbox_mAP_epoch_6.pth was removed 2023-11-15 18:06:18,133 - mmdet - INFO - Now best checkpoint is saved as best_bbox_mAP_epoch_7.pth. 2023-11-15 18:06:18,133 - mmdet - INFO - Best bbox_mAP is 0.4615 at 7 epoch. 2023-11-15 18:06:18,133 - mmdet - INFO - Exp name: mask_rcnn_flash_internimage_s_fpn_3x_coco_0.4.py 2023-11-15 18:06:18,133 - mmdet - INFO - Epoch(val) [7][625] bbox_mAP: 0.4615, bbox_mAP_50: 0.6899, bbox_mAP_75: 0.5101, bbox_mAP_s: 0.3170, bbox_mAP_m: 0.5011, bbox_mAP_l: 0.5888, bbox_mAP_copypaste: 0.4615 0.6899 0.5101 0.3170 0.5011 0.5888, segm_mAP: 0.4193, segm_mAP_50: 0.6600, segm_mAP_75: 0.4491, segm_mAP_s: 0.2363, segm_mAP_m: 0.4537, segm_mAP_l: 0.5953, segm_mAP_copypaste: 0.4193 0.6600 0.4491 0.2363 0.4537 0.5953 2023-11-15 18:07:21,134 - mmdet - INFO - Epoch [8][50/1833] lr: 2.000e-04, eta: 17:21:49, time: 1.260, data_time: 0.137, memory: 16000, loss_rpn_cls: 0.0281, loss_rpn_bbox: 0.0346, loss_cls: 0.1800, acc: 93.5300, loss_bbox: 0.2240, loss_mask: 0.2350, loss: 0.7017 2023-11-15 18:08:21,524 - mmdet - INFO - Epoch [8][100/1833] lr: 2.000e-04, eta: 17:20:57, time: 1.208, data_time: 0.078, memory: 16000, loss_rpn_cls: 0.0272, loss_rpn_bbox: 0.0342, loss_cls: 0.1775, acc: 93.6235, loss_bbox: 0.2211, loss_mask: 0.2337, loss: 0.6938 2023-11-15 18:09:22,167 - mmdet - INFO - Epoch [8][150/1833] lr: 2.000e-04, eta: 17:20:05, time: 1.213, data_time: 0.074, memory: 16000, loss_rpn_cls: 0.0271, loss_rpn_bbox: 0.0343, loss_cls: 0.1810, acc: 93.5535, loss_bbox: 0.2226, loss_mask: 0.2319, loss: 0.6968 2023-11-15 18:10:22,434 - mmdet - INFO - Epoch [8][200/1833] lr: 2.000e-04, eta: 17:19:12, time: 1.205, data_time: 0.069, memory: 16000, loss_rpn_cls: 0.0281, loss_rpn_bbox: 0.0366, loss_cls: 0.1806, acc: 93.5170, loss_bbox: 0.2260, loss_mask: 0.2362, loss: 0.7075 2023-11-15 18:11:23,332 - mmdet - INFO - Epoch [8][250/1833] lr: 2.000e-04, eta: 17:18:21, time: 1.218, data_time: 0.074, memory: 16000, loss_rpn_cls: 0.0278, loss_rpn_bbox: 0.0357, loss_cls: 0.1813, acc: 93.5467, loss_bbox: 0.2259, loss_mask: 0.2335, loss: 0.7042 2023-11-15 18:12:23,052 - mmdet - INFO - Epoch [8][300/1833] lr: 2.000e-04, eta: 17:17:26, time: 1.194, data_time: 0.069, memory: 16000, loss_rpn_cls: 0.0279, loss_rpn_bbox: 0.0352, loss_cls: 0.1803, acc: 93.5616, loss_bbox: 0.2250, loss_mask: 0.2339, loss: 0.7023 2023-11-15 18:13:22,961 - mmdet - INFO - Epoch [8][350/1833] lr: 2.000e-04, eta: 17:16:31, time: 1.198, data_time: 0.067, memory: 16000, loss_rpn_cls: 0.0266, loss_rpn_bbox: 0.0347, loss_cls: 0.1782, acc: 93.5724, loss_bbox: 0.2226, loss_mask: 0.2340, loss: 0.6961 2023-11-15 18:14:24,429 - mmdet - INFO - Epoch [8][400/1833] lr: 2.000e-04, eta: 17:15:43, time: 1.229, data_time: 0.070, memory: 16000, loss_rpn_cls: 0.0283, loss_rpn_bbox: 0.0362, loss_cls: 0.1828, acc: 93.4320, loss_bbox: 0.2251, loss_mask: 0.2347, loss: 0.7069 2023-11-15 18:15:24,295 - mmdet - INFO - Epoch [8][450/1833] lr: 2.000e-04, eta: 17:14:48, time: 1.197, data_time: 0.076, memory: 16000, loss_rpn_cls: 0.0280, loss_rpn_bbox: 0.0359, loss_cls: 0.1801, acc: 93.5685, loss_bbox: 0.2225, loss_mask: 0.2342, loss: 0.7007 2023-11-15 18:16:24,481 - mmdet - INFO - Epoch [8][500/1833] lr: 2.000e-04, eta: 17:13:54, time: 1.204, data_time: 0.062, memory: 16000, loss_rpn_cls: 0.0286, loss_rpn_bbox: 0.0365, loss_cls: 0.1830, acc: 93.5287, loss_bbox: 0.2256, loss_mask: 0.2380, loss: 0.7116 2023-11-15 18:17:24,087 - mmdet - INFO - Epoch [8][550/1833] lr: 2.000e-04, eta: 17:12:58, time: 1.192, data_time: 0.063, memory: 16000, loss_rpn_cls: 0.0272, loss_rpn_bbox: 0.0338, loss_cls: 0.1819, acc: 93.5430, loss_bbox: 0.2240, loss_mask: 0.2324, loss: 0.6993 2023-11-15 18:18:23,706 - mmdet - INFO - Epoch [8][600/1833] lr: 2.000e-04, eta: 17:12:01, time: 1.192, data_time: 0.073, memory: 16000, loss_rpn_cls: 0.0281, loss_rpn_bbox: 0.0362, loss_cls: 0.1884, acc: 93.3026, loss_bbox: 0.2307, loss_mask: 0.2368, loss: 0.7202 2023-11-15 18:19:24,086 - mmdet - INFO - Epoch [8][650/1833] lr: 2.000e-04, eta: 17:11:08, time: 1.208, data_time: 0.067, memory: 16000, loss_rpn_cls: 0.0273, loss_rpn_bbox: 0.0359, loss_cls: 0.1866, acc: 93.3407, loss_bbox: 0.2280, loss_mask: 0.2348, loss: 0.7126 2023-11-15 18:20:23,913 - mmdet - INFO - Epoch [8][700/1833] lr: 2.000e-04, eta: 17:10:13, time: 1.197, data_time: 0.076, memory: 16000, loss_rpn_cls: 0.0269, loss_rpn_bbox: 0.0343, loss_cls: 0.1788, acc: 93.6192, loss_bbox: 0.2186, loss_mask: 0.2324, loss: 0.6911 2023-11-15 18:21:23,364 - mmdet - INFO - Epoch [8][750/1833] lr: 2.000e-04, eta: 17:09:16, time: 1.189, data_time: 0.063, memory: 16000, loss_rpn_cls: 0.0260, loss_rpn_bbox: 0.0347, loss_cls: 0.1770, acc: 93.6458, loss_bbox: 0.2198, loss_mask: 0.2311, loss: 0.6886 2023-11-15 18:22:23,449 - mmdet - INFO - Epoch [8][800/1833] lr: 2.000e-04, eta: 17:08:22, time: 1.202, data_time: 0.060, memory: 16000, loss_rpn_cls: 0.0269, loss_rpn_bbox: 0.0344, loss_cls: 0.1744, acc: 93.7636, loss_bbox: 0.2170, loss_mask: 0.2340, loss: 0.6867 2023-11-15 18:23:24,250 - mmdet - INFO - Epoch [8][850/1833] lr: 2.000e-04, eta: 17:07:30, time: 1.216, data_time: 0.071, memory: 16000, loss_rpn_cls: 0.0275, loss_rpn_bbox: 0.0349, loss_cls: 0.1794, acc: 93.5748, loss_bbox: 0.2201, loss_mask: 0.2364, loss: 0.6983 2023-11-15 18:24:24,266 - mmdet - INFO - Epoch [8][900/1833] lr: 2.000e-04, eta: 17:06:35, time: 1.200, data_time: 0.064, memory: 16000, loss_rpn_cls: 0.0275, loss_rpn_bbox: 0.0352, loss_cls: 0.1800, acc: 93.5744, loss_bbox: 0.2220, loss_mask: 0.2359, loss: 0.7006 2023-11-15 18:25:24,634 - mmdet - INFO - Epoch [8][950/1833] lr: 2.000e-04, eta: 17:05:42, time: 1.207, data_time: 0.071, memory: 16000, loss_rpn_cls: 0.0280, loss_rpn_bbox: 0.0360, loss_cls: 0.1887, acc: 93.2808, loss_bbox: 0.2300, loss_mask: 0.2345, loss: 0.7172 2023-11-15 18:26:24,674 - mmdet - INFO - Epoch [8][1000/1833] lr: 2.000e-04, eta: 17:04:47, time: 1.201, data_time: 0.065, memory: 16000, loss_rpn_cls: 0.0280, loss_rpn_bbox: 0.0358, loss_cls: 0.1821, acc: 93.5180, loss_bbox: 0.2233, loss_mask: 0.2315, loss: 0.7007 2023-11-15 18:27:25,194 - mmdet - INFO - Epoch [8][1050/1833] lr: 2.000e-04, eta: 17:03:54, time: 1.210, data_time: 0.066, memory: 16000, loss_rpn_cls: 0.0278, loss_rpn_bbox: 0.0350, loss_cls: 0.1837, acc: 93.4147, loss_bbox: 0.2271, loss_mask: 0.2339, loss: 0.7076 2023-11-15 18:28:25,230 - mmdet - INFO - Epoch [8][1100/1833] lr: 2.000e-04, eta: 17:02:59, time: 1.201, data_time: 0.066, memory: 16000, loss_rpn_cls: 0.0268, loss_rpn_bbox: 0.0343, loss_cls: 0.1836, acc: 93.4883, loss_bbox: 0.2249, loss_mask: 0.2348, loss: 0.7043 2023-11-15 18:29:25,740 - mmdet - INFO - Epoch [8][1150/1833] lr: 2.000e-04, eta: 17:02:06, time: 1.210, data_time: 0.063, memory: 16000, loss_rpn_cls: 0.0286, loss_rpn_bbox: 0.0358, loss_cls: 0.1822, acc: 93.4561, loss_bbox: 0.2237, loss_mask: 0.2342, loss: 0.7045 2023-11-15 18:30:26,382 - mmdet - INFO - Epoch [8][1200/1833] lr: 2.000e-04, eta: 17:01:13, time: 1.213, data_time: 0.074, memory: 16000, loss_rpn_cls: 0.0261, loss_rpn_bbox: 0.0346, loss_cls: 0.1782, acc: 93.6611, loss_bbox: 0.2189, loss_mask: 0.2351, loss: 0.6928 2023-11-15 18:31:28,079 - mmdet - INFO - Epoch [8][1250/1833] lr: 2.000e-04, eta: 17:00:24, time: 1.234, data_time: 0.070, memory: 16000, loss_rpn_cls: 0.0275, loss_rpn_bbox: 0.0353, loss_cls: 0.1787, acc: 93.5989, loss_bbox: 0.2222, loss_mask: 0.2362, loss: 0.6999 2023-11-15 18:32:27,304 - mmdet - INFO - Epoch [8][1300/1833] lr: 2.000e-04, eta: 16:59:26, time: 1.184, data_time: 0.069, memory: 16000, loss_rpn_cls: 0.0277, loss_rpn_bbox: 0.0345, loss_cls: 0.1817, acc: 93.5284, loss_bbox: 0.2246, loss_mask: 0.2336, loss: 0.7020 2023-11-15 18:33:27,745 - mmdet - INFO - Epoch [8][1350/1833] lr: 2.000e-04, eta: 16:58:32, time: 1.209, data_time: 0.070, memory: 16000, loss_rpn_cls: 0.0276, loss_rpn_bbox: 0.0348, loss_cls: 0.1793, acc: 93.6025, loss_bbox: 0.2200, loss_mask: 0.2343, loss: 0.6960 2023-11-15 18:34:28,139 - mmdet - INFO - Epoch [8][1400/1833] lr: 2.000e-04, eta: 16:57:38, time: 1.208, data_time: 0.069, memory: 16000, loss_rpn_cls: 0.0275, loss_rpn_bbox: 0.0349, loss_cls: 0.1810, acc: 93.5220, loss_bbox: 0.2213, loss_mask: 0.2322, loss: 0.6969 2023-11-15 18:35:28,290 - mmdet - INFO - Epoch [8][1450/1833] lr: 2.000e-04, eta: 16:56:44, time: 1.203, data_time: 0.067, memory: 16000, loss_rpn_cls: 0.0272, loss_rpn_bbox: 0.0356, loss_cls: 0.1802, acc: 93.6098, loss_bbox: 0.2221, loss_mask: 0.2351, loss: 0.7003 2023-11-15 18:36:28,807 - mmdet - INFO - Epoch [8][1500/1833] lr: 2.000e-04, eta: 16:55:50, time: 1.210, data_time: 0.074, memory: 16000, loss_rpn_cls: 0.0269, loss_rpn_bbox: 0.0351, loss_cls: 0.1803, acc: 93.5419, loss_bbox: 0.2229, loss_mask: 0.2347, loss: 0.6999 2023-11-15 18:37:28,869 - mmdet - INFO - Epoch [8][1550/1833] lr: 2.000e-04, eta: 16:54:55, time: 1.201, data_time: 0.062, memory: 16000, loss_rpn_cls: 0.0267, loss_rpn_bbox: 0.0350, loss_cls: 0.1803, acc: 93.5215, loss_bbox: 0.2246, loss_mask: 0.2359, loss: 0.7024 2023-11-15 18:38:29,149 - mmdet - INFO - Epoch [8][1600/1833] lr: 2.000e-04, eta: 16:54:01, time: 1.206, data_time: 0.070, memory: 16000, loss_rpn_cls: 0.0278, loss_rpn_bbox: 0.0354, loss_cls: 0.1814, acc: 93.4847, loss_bbox: 0.2266, loss_mask: 0.2364, loss: 0.7076 2023-11-15 18:39:29,742 - mmdet - INFO - Epoch [8][1650/1833] lr: 2.000e-04, eta: 16:53:07, time: 1.212, data_time: 0.062, memory: 16000, loss_rpn_cls: 0.0272, loss_rpn_bbox: 0.0344, loss_cls: 0.1800, acc: 93.6123, loss_bbox: 0.2216, loss_mask: 0.2350, loss: 0.6981 2023-11-15 18:40:29,060 - mmdet - INFO - Epoch [8][1700/1833] lr: 2.000e-04, eta: 16:52:09, time: 1.186, data_time: 0.068, memory: 16000, loss_rpn_cls: 0.0271, loss_rpn_bbox: 0.0342, loss_cls: 0.1787, acc: 93.6531, loss_bbox: 0.2200, loss_mask: 0.2311, loss: 0.6912 2023-11-15 18:41:29,912 - mmdet - INFO - Epoch [8][1750/1833] lr: 2.000e-04, eta: 16:51:17, time: 1.217, data_time: 0.073, memory: 16000, loss_rpn_cls: 0.0283, loss_rpn_bbox: 0.0360, loss_cls: 0.1857, acc: 93.4132, loss_bbox: 0.2254, loss_mask: 0.2365, loss: 0.7119 2023-11-15 18:42:30,067 - mmdet - INFO - Epoch [8][1800/1833] lr: 2.000e-04, eta: 16:50:22, time: 1.203, data_time: 0.074, memory: 16000, loss_rpn_cls: 0.0280, loss_rpn_bbox: 0.0343, loss_cls: 0.1808, acc: 93.6002, loss_bbox: 0.2199, loss_mask: 0.2334, loss: 0.6963 2023-11-15 18:43:10,660 - mmdet - INFO - Saving checkpoint at 8 epochs 2023-11-15 18:44:00,608 - mmdet - INFO - Evaluating bbox... 2023-11-15 18:44:30,599 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.463 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.689 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.511 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.313 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.503 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.595 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.597 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.597 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.597 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 ] = 0.738 2023-11-15 18:44:30,601 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.572 | bicycle | 0.362 | car | 0.464 | | motorcycle | 0.481 | airplane | 0.695 | bus | 0.686 | | train | 0.666 | truck | 0.420 | boat | 0.316 | | traffic light | 0.310 | fire hydrant | 0.723 | stop sign | 0.640 | | parking meter | 0.510 | bench | 0.296 | bird | 0.394 | | cat | 0.709 | dog | 0.673 | horse | 0.623 | | sheep | 0.584 | cow | 0.591 | elephant | 0.658 | | bear | 0.747 | zebra | 0.700 | giraffe | 0.695 | | backpack | 0.216 | umbrella | 0.445 | handbag | 0.205 | | tie | 0.353 | suitcase | 0.455 | frisbee | 0.701 | | skis | 0.275 | snowboard | 0.422 | sports ball | 0.471 | | kite | 0.432 | baseball bat | 0.372 | baseball glove | 0.427 | | skateboard | 0.579 | surfboard | 0.429 | tennis racket | 0.535 | | bottle | 0.439 | wine glass | 0.408 | cup | 0.489 | | fork | 0.418 | knife | 0.257 | spoon | 0.265 | | bowl | 0.474 | banana | 0.266 | apple | 0.228 | | sandwich | 0.443 | orange | 0.344 | broccoli | 0.246 | | carrot | 0.259 | hot dog | 0.462 | pizza | 0.513 | | donut | 0.549 | cake | 0.433 | chair | 0.344 | | couch | 0.485 | potted plant | 0.326 | bed | 0.461 | | dining table | 0.284 | toilet | 0.641 | tv | 0.616 | | laptop | 0.659 | mouse | 0.627 | remote | 0.394 | | keyboard | 0.508 | cell phone | 0.407 | microwave | 0.633 | | oven | 0.391 | toaster | 0.404 | sink | 0.438 | | refrigerator | 0.632 | book | 0.183 | clock | 0.539 | | vase | 0.422 | scissors | 0.360 | teddy bear | 0.525 | | hair drier | 0.134 | toothbrush | 0.266 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-15 18:44:30,601 - mmdet - INFO - Evaluating segm... 2023-11-15 18:45:04,394 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.419 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.660 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.450 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 ] = 0.456 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 ] = 0.545 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.545 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.545 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.383 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.585 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.702 2023-11-15 18:45:04,396 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.493 | bicycle | 0.213 | car | 0.421 | | motorcycle | 0.393 | airplane | 0.534 | bus | 0.672 | | train | 0.667 | truck | 0.408 | boat | 0.274 | | traffic light | 0.293 | fire hydrant | 0.691 | stop sign | 0.644 | | parking meter | 0.522 | bench | 0.225 | bird | 0.327 | | cat | 0.722 | dog | 0.640 | horse | 0.453 | | sheep | 0.518 | cow | 0.501 | elephant | 0.604 | | bear | 0.740 | zebra | 0.598 | giraffe | 0.525 | | backpack | 0.219 | umbrella | 0.505 | handbag | 0.201 | | tie | 0.321 | suitcase | 0.469 | frisbee | 0.657 | | skis | 0.039 | snowboard | 0.293 | sports ball | 0.450 | | kite | 0.303 | baseball bat | 0.302 | baseball glove | 0.442 | | skateboard | 0.343 | surfboard | 0.339 | tennis racket | 0.584 | | bottle | 0.420 | wine glass | 0.360 | cup | 0.485 | | fork | 0.206 | knife | 0.160 | spoon | 0.187 | | bowl | 0.441 | banana | 0.220 | apple | 0.221 | | sandwich | 0.468 | orange | 0.348 | broccoli | 0.237 | | carrot | 0.226 | hot dog | 0.416 | pizza | 0.499 | | donut | 0.544 | cake | 0.439 | chair | 0.242 | | couch | 0.414 | potted plant | 0.280 | bed | 0.376 | | dining table | 0.179 | toilet | 0.626 | tv | 0.640 | | laptop | 0.659 | mouse | 0.619 | remote | 0.353 | | keyboard | 0.516 | cell phone | 0.378 | microwave | 0.652 | | oven | 0.375 | toaster | 0.551 | sink | 0.422 | | refrigerator | 0.638 | book | 0.141 | clock | 0.534 | | vase | 0.419 | scissors | 0.253 | teddy bear | 0.488 | | hair drier | 0.113 | toothbrush | 0.201 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-15 18:45:04,879 - mmdet - INFO - The previous best checkpoint /mnt/petrelfs/lizhiqi/DINO/detection/work_dirs/mask_rcnn_flash_internimage_s_fpn_3x_coco_0.4/best_bbox_mAP_epoch_7.pth was removed 2023-11-15 18:45:06,853 - mmdet - INFO - Now best checkpoint is saved as best_bbox_mAP_epoch_8.pth. 2023-11-15 18:45:06,853 - mmdet - INFO - Best bbox_mAP is 0.4625 at 8 epoch. 2023-11-15 18:45:06,853 - mmdet - INFO - Exp name: mask_rcnn_flash_internimage_s_fpn_3x_coco_0.4.py 2023-11-15 18:45:06,853 - mmdet - INFO - Epoch(val) [8][625] bbox_mAP: 0.4625, bbox_mAP_50: 0.6894, bbox_mAP_75: 0.5114, bbox_mAP_s: 0.3128, bbox_mAP_m: 0.5031, bbox_mAP_l: 0.5953, bbox_mAP_copypaste: 0.4625 0.6894 0.5114 0.3128 0.5031 0.5953, segm_mAP: 0.4186, segm_mAP_50: 0.6603, segm_mAP_75: 0.4496, segm_mAP_s: 0.2231, segm_mAP_m: 0.4565, segm_mAP_l: 0.6010, segm_mAP_copypaste: 0.4186 0.6603 0.4496 0.2231 0.4565 0.6010 2023-11-15 18:46:09,530 - mmdet - INFO - Epoch [9][50/1833] lr: 2.000e-04, eta: 16:46:41, time: 1.253, data_time: 0.133, memory: 16000, loss_rpn_cls: 0.0271, loss_rpn_bbox: 0.0342, loss_cls: 0.1758, acc: 93.6627, loss_bbox: 0.2194, loss_mask: 0.2294, loss: 0.6860 2023-11-15 18:47:10,609 - mmdet - INFO - Epoch [9][100/1833] lr: 2.000e-04, eta: 16:45:49, time: 1.222, data_time: 0.091, memory: 16000, loss_rpn_cls: 0.0262, loss_rpn_bbox: 0.0341, loss_cls: 0.1733, acc: 93.7408, loss_bbox: 0.2160, loss_mask: 0.2302, loss: 0.6799 2023-11-15 18:48:11,839 - mmdet - INFO - Epoch [9][150/1833] lr: 2.000e-04, eta: 16:44:58, time: 1.225, data_time: 0.081, memory: 16000, loss_rpn_cls: 0.0261, loss_rpn_bbox: 0.0350, loss_cls: 0.1805, acc: 93.4959, loss_bbox: 0.2240, loss_mask: 0.2328, loss: 0.6985 2023-11-15 18:49:12,747 - mmdet - INFO - Epoch [9][200/1833] lr: 2.000e-04, eta: 16:44:06, time: 1.218, data_time: 0.076, memory: 16000, loss_rpn_cls: 0.0270, loss_rpn_bbox: 0.0344, loss_cls: 0.1773, acc: 93.6404, loss_bbox: 0.2207, loss_mask: 0.2279, loss: 0.6873 2023-11-15 18:50:16,418 - mmdet - INFO - Epoch [9][250/1833] lr: 2.000e-04, eta: 16:43:24, time: 1.273, data_time: 0.081, memory: 16000, loss_rpn_cls: 0.0271, loss_rpn_bbox: 0.0345, loss_cls: 0.1762, acc: 93.7057, loss_bbox: 0.2188, loss_mask: 0.2350, loss: 0.6916 2023-11-15 18:51:17,181 - mmdet - INFO - Epoch [9][300/1833] lr: 2.000e-04, eta: 16:42:31, time: 1.215, data_time: 0.077, memory: 16000, loss_rpn_cls: 0.0270, loss_rpn_bbox: 0.0341, loss_cls: 0.1769, acc: 93.6612, loss_bbox: 0.2199, loss_mask: 0.2321, loss: 0.6900 2023-11-15 18:52:16,314 - mmdet - INFO - Epoch [9][350/1833] lr: 2.000e-04, eta: 16:41:33, time: 1.183, data_time: 0.074, memory: 16000, loss_rpn_cls: 0.0278, loss_rpn_bbox: 0.0347, loss_cls: 0.1752, acc: 93.7419, loss_bbox: 0.2205, loss_mask: 0.2340, loss: 0.6923 2023-11-15 18:53:17,178 - mmdet - INFO - Epoch [9][400/1833] lr: 2.000e-04, eta: 16:40:40, time: 1.217, data_time: 0.081, memory: 16000, loss_rpn_cls: 0.0283, loss_rpn_bbox: 0.0357, loss_cls: 0.1780, acc: 93.6110, loss_bbox: 0.2215, loss_mask: 0.2340, loss: 0.6975 2023-11-15 18:54:17,737 - mmdet - INFO - Epoch [9][450/1833] lr: 2.000e-04, eta: 16:39:47, time: 1.211, data_time: 0.083, memory: 16000, loss_rpn_cls: 0.0272, loss_rpn_bbox: 0.0354, loss_cls: 0.1804, acc: 93.5328, loss_bbox: 0.2261, loss_mask: 0.2343, loss: 0.7034 2023-11-15 18:55:17,599 - mmdet - INFO - Epoch [9][500/1833] lr: 2.000e-04, eta: 16:38:51, time: 1.197, data_time: 0.079, memory: 16000, loss_rpn_cls: 0.0261, loss_rpn_bbox: 0.0328, loss_cls: 0.1721, acc: 93.7828, loss_bbox: 0.2183, loss_mask: 0.2308, loss: 0.6800 2023-11-15 18:56:18,111 - mmdet - INFO - Epoch [9][550/1833] lr: 2.000e-04, eta: 16:37:57, time: 1.210, data_time: 0.076, memory: 16000, loss_rpn_cls: 0.0278, loss_rpn_bbox: 0.0351, loss_cls: 0.1766, acc: 93.6167, loss_bbox: 0.2219, loss_mask: 0.2332, loss: 0.6947 2023-11-15 18:57:19,912 - mmdet - INFO - Epoch [9][600/1833] lr: 2.000e-04, eta: 16:37:07, time: 1.236, data_time: 0.074, memory: 16000, loss_rpn_cls: 0.0273, loss_rpn_bbox: 0.0348, loss_cls: 0.1786, acc: 93.5566, loss_bbox: 0.2227, loss_mask: 0.2328, loss: 0.6962 2023-11-15 18:58:20,515 - mmdet - INFO - Epoch [9][650/1833] lr: 2.000e-04, eta: 16:36:14, time: 1.212, data_time: 0.080, memory: 16000, loss_rpn_cls: 0.0262, loss_rpn_bbox: 0.0340, loss_cls: 0.1782, acc: 93.5643, loss_bbox: 0.2212, loss_mask: 0.2308, loss: 0.6904 2023-11-15 18:59:21,832 - mmdet - INFO - Epoch [9][700/1833] lr: 2.000e-04, eta: 16:35:23, time: 1.226, data_time: 0.071, memory: 16000, loss_rpn_cls: 0.0270, loss_rpn_bbox: 0.0340, loss_cls: 0.1754, acc: 93.7398, loss_bbox: 0.2157, loss_mask: 0.2325, loss: 0.6845 2023-11-15 19:00:22,856 - mmdet - INFO - Epoch [9][750/1833] lr: 2.000e-04, eta: 16:34:30, time: 1.220, data_time: 0.084, memory: 16000, loss_rpn_cls: 0.0277, loss_rpn_bbox: 0.0357, loss_cls: 0.1786, acc: 93.6509, loss_bbox: 0.2214, loss_mask: 0.2336, loss: 0.6970 2023-11-15 19:01:23,514 - mmdet - INFO - Epoch [9][800/1833] lr: 2.000e-04, eta: 16:33:37, time: 1.213, data_time: 0.071, memory: 16000, loss_rpn_cls: 0.0258, loss_rpn_bbox: 0.0331, loss_cls: 0.1741, acc: 93.7861, loss_bbox: 0.2171, loss_mask: 0.2306, loss: 0.6807 2023-11-15 19:02:23,953 - mmdet - INFO - Epoch [9][850/1833] lr: 2.000e-04, eta: 16:32:42, time: 1.209, data_time: 0.077, memory: 16000, loss_rpn_cls: 0.0263, loss_rpn_bbox: 0.0348, loss_cls: 0.1746, acc: 93.7440, loss_bbox: 0.2165, loss_mask: 0.2330, loss: 0.6852 2023-11-15 19:03:24,513 - mmdet - INFO - Epoch [9][900/1833] lr: 2.000e-04, eta: 16:31:48, time: 1.211, data_time: 0.079, memory: 16000, loss_rpn_cls: 0.0278, loss_rpn_bbox: 0.0356, loss_cls: 0.1815, acc: 93.4541, loss_bbox: 0.2241, loss_mask: 0.2354, loss: 0.7044 2023-11-15 19:04:27,440 - mmdet - INFO - Epoch [9][950/1833] lr: 2.000e-04, eta: 16:31:02, time: 1.259, data_time: 0.074, memory: 16000, loss_rpn_cls: 0.0267, loss_rpn_bbox: 0.0340, loss_cls: 0.1771, acc: 93.6487, loss_bbox: 0.2201, loss_mask: 0.2316, loss: 0.6895 2023-11-15 19:05:28,068 - mmdet - INFO - Epoch [9][1000/1833] lr: 2.000e-04, eta: 16:30:08, time: 1.213, data_time: 0.073, memory: 16000, loss_rpn_cls: 0.0266, loss_rpn_bbox: 0.0350, loss_cls: 0.1770, acc: 93.6888, loss_bbox: 0.2200, loss_mask: 0.2297, loss: 0.6883 2023-11-15 19:06:27,836 - mmdet - INFO - Epoch [9][1050/1833] lr: 2.000e-04, eta: 16:29:12, time: 1.195, data_time: 0.078, memory: 16000, loss_rpn_cls: 0.0272, loss_rpn_bbox: 0.0349, loss_cls: 0.1759, acc: 93.7379, loss_bbox: 0.2167, loss_mask: 0.2352, loss: 0.6899 2023-11-15 19:07:27,958 - mmdet - INFO - Epoch [9][1100/1833] lr: 2.000e-04, eta: 16:28:16, time: 1.202, data_time: 0.080, memory: 16000, loss_rpn_cls: 0.0268, loss_rpn_bbox: 0.0352, loss_cls: 0.1791, acc: 93.5443, loss_bbox: 0.2242, loss_mask: 0.2323, loss: 0.6976 2023-11-15 19:08:28,165 - mmdet - INFO - Epoch [9][1150/1833] lr: 2.000e-04, eta: 16:27:21, time: 1.204, data_time: 0.083, memory: 16000, loss_rpn_cls: 0.0271, loss_rpn_bbox: 0.0363, loss_cls: 0.1771, acc: 93.6713, loss_bbox: 0.2221, loss_mask: 0.2328, loss: 0.6954 2023-11-15 19:09:29,352 - mmdet - INFO - Epoch [9][1200/1833] lr: 2.000e-04, eta: 16:26:28, time: 1.224, data_time: 0.071, memory: 16000, loss_rpn_cls: 0.0263, loss_rpn_bbox: 0.0343, loss_cls: 0.1740, acc: 93.7266, loss_bbox: 0.2163, loss_mask: 0.2299, loss: 0.6808 2023-11-15 19:10:30,099 - mmdet - INFO - Epoch [9][1250/1833] lr: 2.000e-04, eta: 16:25:35, time: 1.215, data_time: 0.076, memory: 16000, loss_rpn_cls: 0.0261, loss_rpn_bbox: 0.0344, loss_cls: 0.1769, acc: 93.6383, loss_bbox: 0.2193, loss_mask: 0.2324, loss: 0.6891 2023-11-15 19:11:30,661 - mmdet - INFO - Epoch [9][1300/1833] lr: 2.000e-04, eta: 16:24:40, time: 1.211, data_time: 0.081, memory: 16000, loss_rpn_cls: 0.0282, loss_rpn_bbox: 0.0363, loss_cls: 0.1813, acc: 93.4810, loss_bbox: 0.2262, loss_mask: 0.2348, loss: 0.7068 2023-11-15 19:12:32,244 - mmdet - INFO - Epoch [9][1350/1833] lr: 2.000e-04, eta: 16:23:49, time: 1.232, data_time: 0.073, memory: 16000, loss_rpn_cls: 0.0253, loss_rpn_bbox: 0.0340, loss_cls: 0.1762, acc: 93.6312, loss_bbox: 0.2164, loss_mask: 0.2285, loss: 0.6804 2023-11-15 19:13:34,639 - mmdet - INFO - Epoch [9][1400/1833] lr: 2.000e-04, eta: 16:23:01, time: 1.248, data_time: 0.070, memory: 16000, loss_rpn_cls: 0.0262, loss_rpn_bbox: 0.0329, loss_cls: 0.1752, acc: 93.7440, loss_bbox: 0.2164, loss_mask: 0.2303, loss: 0.6810 2023-11-15 19:14:35,153 - mmdet - INFO - Epoch [9][1450/1833] lr: 2.000e-04, eta: 16:22:06, time: 1.210, data_time: 0.084, memory: 16000, loss_rpn_cls: 0.0270, loss_rpn_bbox: 0.0339, loss_cls: 0.1751, acc: 93.7323, loss_bbox: 0.2162, loss_mask: 0.2316, loss: 0.6838 2023-11-15 19:15:35,852 - mmdet - INFO - Epoch [9][1500/1833] lr: 2.000e-04, eta: 16:21:12, time: 1.214, data_time: 0.073, memory: 16000, loss_rpn_cls: 0.0257, loss_rpn_bbox: 0.0348, loss_cls: 0.1794, acc: 93.5436, loss_bbox: 0.2211, loss_mask: 0.2309, loss: 0.6918 2023-11-15 19:16:36,619 - mmdet - INFO - Epoch [9][1550/1833] lr: 2.000e-04, eta: 16:20:18, time: 1.215, data_time: 0.075, memory: 16000, loss_rpn_cls: 0.0264, loss_rpn_bbox: 0.0339, loss_cls: 0.1767, acc: 93.6814, loss_bbox: 0.2184, loss_mask: 0.2318, loss: 0.6872 2023-11-15 19:17:36,798 - mmdet - INFO - Epoch [9][1600/1833] lr: 2.000e-04, eta: 16:19:22, time: 1.204, data_time: 0.080, memory: 16000, loss_rpn_cls: 0.0274, loss_rpn_bbox: 0.0345, loss_cls: 0.1803, acc: 93.4597, loss_bbox: 0.2240, loss_mask: 0.2309, loss: 0.6972 2023-11-15 19:18:37,000 - mmdet - INFO - Epoch [9][1650/1833] lr: 2.000e-04, eta: 16:18:27, time: 1.204, data_time: 0.076, memory: 16000, loss_rpn_cls: 0.0268, loss_rpn_bbox: 0.0348, loss_cls: 0.1779, acc: 93.6417, loss_bbox: 0.2193, loss_mask: 0.2318, loss: 0.6906 2023-11-15 19:19:37,374 - mmdet - INFO - Epoch [9][1700/1833] lr: 2.000e-04, eta: 16:17:31, time: 1.207, data_time: 0.071, memory: 16000, loss_rpn_cls: 0.0266, loss_rpn_bbox: 0.0338, loss_cls: 0.1755, acc: 93.6949, loss_bbox: 0.2189, loss_mask: 0.2308, loss: 0.6856 2023-11-15 19:20:37,966 - mmdet - INFO - Epoch [9][1750/1833] lr: 2.000e-04, eta: 16:16:37, time: 1.212, data_time: 0.078, memory: 16000, loss_rpn_cls: 0.0263, loss_rpn_bbox: 0.0339, loss_cls: 0.1776, acc: 93.6398, loss_bbox: 0.2181, loss_mask: 0.2297, loss: 0.6857 2023-11-15 19:21:37,801 - mmdet - INFO - Epoch [9][1800/1833] lr: 2.000e-04, eta: 16:15:40, time: 1.197, data_time: 0.074, memory: 16000, loss_rpn_cls: 0.0271, loss_rpn_bbox: 0.0340, loss_cls: 0.1800, acc: 93.5290, loss_bbox: 0.2232, loss_mask: 0.2316, loss: 0.6959 2023-11-15 19:22:19,305 - mmdet - INFO - Saving checkpoint at 9 epochs 2023-11-15 19:23:11,590 - mmdet - INFO - Evaluating bbox... 2023-11-15 19:23:44,290 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.467 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.696 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.514 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.324 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 ] = 0.597 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.601 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.601 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.601 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 ] = 0.640 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.746 2023-11-15 19:23:44,293 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.570 | bicycle | 0.383 | car | 0.488 | | motorcycle | 0.474 | airplane | 0.671 | bus | 0.664 | | train | 0.667 | truck | 0.402 | boat | 0.304 | | traffic light | 0.314 | fire hydrant | 0.723 | stop sign | 0.674 | | parking meter | 0.538 | bench | 0.300 | bird | 0.398 | | cat | 0.715 | dog | 0.682 | horse | 0.607 | | sheep | 0.589 | cow | 0.621 | elephant | 0.679 | | bear | 0.752 | zebra | 0.695 | giraffe | 0.682 | | backpack | 0.205 | umbrella | 0.459 | handbag | 0.221 | | tie | 0.374 | suitcase | 0.456 | frisbee | 0.683 | | skis | 0.269 | snowboard | 0.455 | sports ball | 0.470 | | kite | 0.451 | baseball bat | 0.384 | baseball glove | 0.449 | | skateboard | 0.581 | surfboard | 0.437 | tennis racket | 0.534 | | bottle | 0.443 | wine glass | 0.411 | cup | 0.482 | | fork | 0.441 | knife | 0.249 | spoon | 0.252 | | bowl | 0.459 | banana | 0.297 | apple | 0.243 | | sandwich | 0.409 | orange | 0.347 | broccoli | 0.267 | | carrot | 0.251 | hot dog | 0.454 | pizza | 0.535 | | donut | 0.557 | cake | 0.435 | chair | 0.355 | | couch | 0.453 | potted plant | 0.328 | bed | 0.451 | | dining table | 0.300 | toilet | 0.631 | tv | 0.614 | | laptop | 0.663 | mouse | 0.612 | remote | 0.399 | | keyboard | 0.540 | cell phone | 0.395 | microwave | 0.593 | | oven | 0.399 | toaster | 0.536 | sink | 0.425 | | refrigerator | 0.631 | book | 0.189 | clock | 0.504 | | vase | 0.421 | scissors | 0.408 | teddy bear | 0.528 | | hair drier | 0.124 | toothbrush | 0.296 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-15 19:23:44,293 - mmdet - INFO - Evaluating segm... 2023-11-15 19:24:22,235 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.422 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.665 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.451 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.239 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.461 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.602 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 ] = 0.383 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.596 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.704 2023-11-15 19:24:22,237 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.499 | bicycle | 0.218 | car | 0.441 | | motorcycle | 0.395 | airplane | 0.547 | bus | 0.663 | | train | 0.664 | truck | 0.396 | boat | 0.280 | | traffic light | 0.296 | fire hydrant | 0.689 | stop sign | 0.662 | | parking meter | 0.518 | bench | 0.224 | bird | 0.327 | | cat | 0.720 | dog | 0.648 | horse | 0.461 | | sheep | 0.521 | cow | 0.520 | elephant | 0.616 | | bear | 0.746 | zebra | 0.614 | giraffe | 0.544 | | backpack | 0.204 | umbrella | 0.522 | handbag | 0.207 | | tie | 0.350 | suitcase | 0.470 | frisbee | 0.656 | | skis | 0.043 | snowboard | 0.297 | sports ball | 0.459 | | kite | 0.320 | baseball bat | 0.294 | baseball glove | 0.454 | | skateboard | 0.357 | surfboard | 0.355 | tennis racket | 0.586 | | bottle | 0.418 | wine glass | 0.373 | cup | 0.485 | | fork | 0.210 | knife | 0.163 | spoon | 0.190 | | bowl | 0.435 | banana | 0.239 | apple | 0.247 | | sandwich | 0.437 | orange | 0.355 | broccoli | 0.251 | | carrot | 0.219 | hot dog | 0.369 | pizza | 0.523 | | donut | 0.561 | cake | 0.452 | chair | 0.254 | | couch | 0.384 | potted plant | 0.271 | bed | 0.366 | | dining table | 0.169 | toilet | 0.615 | tv | 0.643 | | laptop | 0.668 | mouse | 0.624 | remote | 0.350 | | keyboard | 0.536 | cell phone | 0.376 | microwave | 0.640 | | oven | 0.371 | toaster | 0.526 | sink | 0.404 | | refrigerator | 0.645 | book | 0.140 | clock | 0.517 | | vase | 0.413 | scissors | 0.290 | teddy bear | 0.511 | | hair drier | 0.092 | toothbrush | 0.216 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-15 19:24:22,778 - mmdet - INFO - The previous best checkpoint /mnt/petrelfs/lizhiqi/DINO/detection/work_dirs/mask_rcnn_flash_internimage_s_fpn_3x_coco_0.4/best_bbox_mAP_epoch_8.pth was removed 2023-11-15 19:24:24,884 - mmdet - INFO - Now best checkpoint is saved as best_bbox_mAP_epoch_9.pth. 2023-11-15 19:24:24,884 - mmdet - INFO - Best bbox_mAP is 0.4668 at 9 epoch. 2023-11-15 19:24:24,884 - mmdet - INFO - Exp name: mask_rcnn_flash_internimage_s_fpn_3x_coco_0.4.py 2023-11-15 19:24:24,884 - mmdet - INFO - Epoch(val) [9][625] bbox_mAP: 0.4668, bbox_mAP_50: 0.6956, bbox_mAP_75: 0.5138, bbox_mAP_s: 0.3242, bbox_mAP_m: 0.5087, bbox_mAP_l: 0.5969, bbox_mAP_copypaste: 0.4668 0.6956 0.5138 0.3242 0.5087 0.5969, segm_mAP: 0.4216, segm_mAP_50: 0.6649, segm_mAP_75: 0.4511, segm_mAP_s: 0.2392, segm_mAP_m: 0.4606, segm_mAP_l: 0.6020, segm_mAP_copypaste: 0.4216 0.6649 0.4511 0.2392 0.4606 0.6020 2023-11-15 19:25:28,547 - mmdet - INFO - Epoch [10][50/1833] lr: 2.000e-04, eta: 16:12:19, time: 1.273, data_time: 0.129, memory: 16000, loss_rpn_cls: 0.0253, loss_rpn_bbox: 0.0345, loss_cls: 0.1729, acc: 93.7489, loss_bbox: 0.2178, loss_mask: 0.2278, loss: 0.6782 2023-11-15 19:26:28,735 - mmdet - INFO - Epoch [10][100/1833] lr: 2.000e-04, eta: 16:11:23, time: 1.204, data_time: 0.080, memory: 16000, loss_rpn_cls: 0.0263, loss_rpn_bbox: 0.0337, loss_cls: 0.1758, acc: 93.6702, loss_bbox: 0.2204, loss_mask: 0.2309, loss: 0.6871 2023-11-15 19:27:30,029 - mmdet - INFO - Epoch [10][150/1833] lr: 2.000e-04, eta: 16:10:31, time: 1.226, data_time: 0.067, memory: 16000, loss_rpn_cls: 0.0256, loss_rpn_bbox: 0.0339, loss_cls: 0.1698, acc: 93.8832, loss_bbox: 0.2173, loss_mask: 0.2295, loss: 0.6761 2023-11-15 19:28:30,193 - mmdet - INFO - Epoch [10][200/1833] lr: 2.000e-04, eta: 16:09:36, time: 1.203, data_time: 0.074, memory: 16000, loss_rpn_cls: 0.0244, loss_rpn_bbox: 0.0333, loss_cls: 0.1697, acc: 93.9222, loss_bbox: 0.2158, loss_mask: 0.2294, loss: 0.6727 2023-11-15 19:29:30,832 - mmdet - INFO - Epoch [10][250/1833] lr: 2.000e-04, eta: 16:08:41, time: 1.213, data_time: 0.071, memory: 16000, loss_rpn_cls: 0.0262, loss_rpn_bbox: 0.0347, loss_cls: 0.1752, acc: 93.6796, loss_bbox: 0.2218, loss_mask: 0.2296, loss: 0.6875 2023-11-15 19:30:32,555 - mmdet - INFO - Epoch [10][300/1833] lr: 2.000e-04, eta: 16:07:50, time: 1.234, data_time: 0.063, memory: 16000, loss_rpn_cls: 0.0260, loss_rpn_bbox: 0.0345, loss_cls: 0.1693, acc: 93.8246, loss_bbox: 0.2181, loss_mask: 0.2292, loss: 0.6771 2023-11-15 19:31:31,798 - mmdet - INFO - Epoch [10][350/1833] lr: 2.000e-04, eta: 16:06:52, time: 1.185, data_time: 0.066, memory: 16000, loss_rpn_cls: 0.0246, loss_rpn_bbox: 0.0335, loss_cls: 0.1751, acc: 93.6330, loss_bbox: 0.2198, loss_mask: 0.2292, loss: 0.6823 2023-11-15 19:32:32,178 - mmdet - INFO - Epoch [10][400/1833] lr: 2.000e-04, eta: 16:05:57, time: 1.208, data_time: 0.076, memory: 16000, loss_rpn_cls: 0.0249, loss_rpn_bbox: 0.0339, loss_cls: 0.1701, acc: 93.8452, loss_bbox: 0.2123, loss_mask: 0.2295, loss: 0.6705 2023-11-15 19:33:32,590 - mmdet - INFO - Epoch [10][450/1833] lr: 2.000e-04, eta: 16:05:02, time: 1.208, data_time: 0.069, memory: 16000, loss_rpn_cls: 0.0260, loss_rpn_bbox: 0.0348, loss_cls: 0.1742, acc: 93.7010, loss_bbox: 0.2183, loss_mask: 0.2274, loss: 0.6808 2023-11-15 19:34:32,167 - mmdet - INFO - Epoch [10][500/1833] lr: 2.000e-04, eta: 16:04:04, time: 1.192, data_time: 0.066, memory: 16000, loss_rpn_cls: 0.0257, loss_rpn_bbox: 0.0343, loss_cls: 0.1733, acc: 93.7059, loss_bbox: 0.2183, loss_mask: 0.2286, loss: 0.6803 2023-11-15 19:35:33,262 - mmdet - INFO - Epoch [10][550/1833] lr: 2.000e-04, eta: 16:03:11, time: 1.222, data_time: 0.067, memory: 16000, loss_rpn_cls: 0.0255, loss_rpn_bbox: 0.0338, loss_cls: 0.1714, acc: 93.8157, loss_bbox: 0.2157, loss_mask: 0.2259, loss: 0.6722 2023-11-15 19:36:32,631 - mmdet - INFO - Epoch [10][600/1833] lr: 2.000e-04, eta: 16:02:13, time: 1.187, data_time: 0.071, memory: 16000, loss_rpn_cls: 0.0244, loss_rpn_bbox: 0.0321, loss_cls: 0.1704, acc: 93.8431, loss_bbox: 0.2180, loss_mask: 0.2282, loss: 0.6732 2023-11-15 19:37:32,028 - mmdet - INFO - Epoch [10][650/1833] lr: 2.000e-04, eta: 16:01:15, time: 1.188, data_time: 0.076, memory: 16000, loss_rpn_cls: 0.0260, loss_rpn_bbox: 0.0336, loss_cls: 0.1770, acc: 93.6203, loss_bbox: 0.2201, loss_mask: 0.2302, loss: 0.6869 2023-11-15 19:38:32,094 - mmdet - INFO - Epoch [10][700/1833] lr: 2.000e-04, eta: 16:00:19, time: 1.201, data_time: 0.068, memory: 16000, loss_rpn_cls: 0.0264, loss_rpn_bbox: 0.0338, loss_cls: 0.1735, acc: 93.7188, loss_bbox: 0.2169, loss_mask: 0.2302, loss: 0.6807 2023-11-15 19:39:33,129 - mmdet - INFO - Epoch [10][750/1833] lr: 2.000e-04, eta: 15:59:25, time: 1.221, data_time: 0.070, memory: 16000, loss_rpn_cls: 0.0252, loss_rpn_bbox: 0.0355, loss_cls: 0.1826, acc: 93.3720, loss_bbox: 0.2288, loss_mask: 0.2323, loss: 0.7045 2023-11-15 19:40:33,448 - mmdet - INFO - Epoch [10][800/1833] lr: 2.000e-04, eta: 15:58:30, time: 1.206, data_time: 0.065, memory: 16000, loss_rpn_cls: 0.0259, loss_rpn_bbox: 0.0350, loss_cls: 0.1775, acc: 93.6096, loss_bbox: 0.2217, loss_mask: 0.2296, loss: 0.6896 2023-11-15 19:41:34,195 - mmdet - INFO - Epoch [10][850/1833] lr: 2.000e-04, eta: 15:57:36, time: 1.215, data_time: 0.065, memory: 16000, loss_rpn_cls: 0.0267, loss_rpn_bbox: 0.0341, loss_cls: 0.1804, acc: 93.4964, loss_bbox: 0.2230, loss_mask: 0.2314, loss: 0.6956 2023-11-15 19:42:34,192 - mmdet - INFO - Epoch [10][900/1833] lr: 2.000e-04, eta: 15:56:39, time: 1.200, data_time: 0.073, memory: 16000, loss_rpn_cls: 0.0262, loss_rpn_bbox: 0.0348, loss_cls: 0.1746, acc: 93.6968, loss_bbox: 0.2181, loss_mask: 0.2307, loss: 0.6843 2023-11-15 19:43:33,910 - mmdet - INFO - Epoch [10][950/1833] lr: 2.000e-04, eta: 15:55:42, time: 1.194, data_time: 0.071, memory: 16000, loss_rpn_cls: 0.0263, loss_rpn_bbox: 0.0341, loss_cls: 0.1765, acc: 93.7040, loss_bbox: 0.2166, loss_mask: 0.2309, loss: 0.6845 2023-11-15 19:44:34,709 - mmdet - INFO - Epoch [10][1000/1833] lr: 2.000e-04, eta: 15:54:48, time: 1.216, data_time: 0.063, memory: 16000, loss_rpn_cls: 0.0256, loss_rpn_bbox: 0.0342, loss_cls: 0.1743, acc: 93.7379, loss_bbox: 0.2172, loss_mask: 0.2289, loss: 0.6802 2023-11-15 19:45:34,484 - mmdet - INFO - Epoch [10][1050/1833] lr: 2.000e-04, eta: 15:53:50, time: 1.196, data_time: 0.064, memory: 16000, loss_rpn_cls: 0.0254, loss_rpn_bbox: 0.0329, loss_cls: 0.1688, acc: 93.9224, loss_bbox: 0.2118, loss_mask: 0.2295, loss: 0.6683 2023-11-15 19:46:33,972 - mmdet - INFO - Epoch [10][1100/1833] lr: 2.000e-04, eta: 15:52:53, time: 1.190, data_time: 0.061, memory: 16000, loss_rpn_cls: 0.0262, loss_rpn_bbox: 0.0339, loss_cls: 0.1762, acc: 93.7147, loss_bbox: 0.2181, loss_mask: 0.2286, loss: 0.6830 2023-11-15 19:47:34,288 - mmdet - INFO - Epoch [10][1150/1833] lr: 2.000e-04, eta: 15:51:57, time: 1.206, data_time: 0.067, memory: 16000, loss_rpn_cls: 0.0272, loss_rpn_bbox: 0.0347, loss_cls: 0.1764, acc: 93.7108, loss_bbox: 0.2148, loss_mask: 0.2302, loss: 0.6832 2023-11-15 19:48:34,904 - mmdet - INFO - Epoch [10][1200/1833] lr: 2.000e-04, eta: 15:51:02, time: 1.212, data_time: 0.066, memory: 16000, loss_rpn_cls: 0.0260, loss_rpn_bbox: 0.0335, loss_cls: 0.1744, acc: 93.7782, loss_bbox: 0.2172, loss_mask: 0.2261, loss: 0.6772 2023-11-15 19:49:35,716 - mmdet - INFO - Epoch [10][1250/1833] lr: 2.000e-04, eta: 15:50:08, time: 1.216, data_time: 0.067, memory: 16000, loss_rpn_cls: 0.0247, loss_rpn_bbox: 0.0343, loss_cls: 0.1728, acc: 93.7726, loss_bbox: 0.2163, loss_mask: 0.2304, loss: 0.6785 2023-11-15 19:50:35,037 - mmdet - INFO - Epoch [10][1300/1833] lr: 2.000e-04, eta: 15:49:09, time: 1.186, data_time: 0.066, memory: 16000, loss_rpn_cls: 0.0244, loss_rpn_bbox: 0.0324, loss_cls: 0.1745, acc: 93.7496, loss_bbox: 0.2154, loss_mask: 0.2268, loss: 0.6735 2023-11-15 19:51:35,005 - mmdet - INFO - Epoch [10][1350/1833] lr: 2.000e-04, eta: 15:48:12, time: 1.199, data_time: 0.082, memory: 16000, loss_rpn_cls: 0.0259, loss_rpn_bbox: 0.0338, loss_cls: 0.1782, acc: 93.6547, loss_bbox: 0.2186, loss_mask: 0.2295, loss: 0.6860 2023-11-15 19:52:35,882 - mmdet - INFO - Epoch [10][1400/1833] lr: 2.000e-04, eta: 15:47:18, time: 1.218, data_time: 0.065, memory: 16000, loss_rpn_cls: 0.0259, loss_rpn_bbox: 0.0339, loss_cls: 0.1776, acc: 93.6414, loss_bbox: 0.2185, loss_mask: 0.2272, loss: 0.6831 2023-11-15 19:53:37,049 - mmdet - INFO - Epoch [10][1450/1833] lr: 2.000e-04, eta: 15:46:25, time: 1.223, data_time: 0.073, memory: 16000, loss_rpn_cls: 0.0263, loss_rpn_bbox: 0.0345, loss_cls: 0.1754, acc: 93.6827, loss_bbox: 0.2177, loss_mask: 0.2303, loss: 0.6841 2023-11-15 19:54:37,728 - mmdet - INFO - Epoch [10][1500/1833] lr: 2.000e-04, eta: 15:45:30, time: 1.214, data_time: 0.089, memory: 16000, loss_rpn_cls: 0.0258, loss_rpn_bbox: 0.0327, loss_cls: 0.1677, acc: 93.9702, loss_bbox: 0.2096, loss_mask: 0.2309, loss: 0.6666 2023-11-15 19:55:38,438 - mmdet - INFO - Epoch [10][1550/1833] lr: 2.000e-04, eta: 15:44:35, time: 1.214, data_time: 0.072, memory: 16000, loss_rpn_cls: 0.0265, loss_rpn_bbox: 0.0339, loss_cls: 0.1723, acc: 93.8259, loss_bbox: 0.2125, loss_mask: 0.2296, loss: 0.6749 2023-11-15 19:56:39,391 - mmdet - INFO - Epoch [10][1600/1833] lr: 2.000e-04, eta: 15:43:41, time: 1.219, data_time: 0.063, memory: 16000, loss_rpn_cls: 0.0267, loss_rpn_bbox: 0.0340, loss_cls: 0.1754, acc: 93.7074, loss_bbox: 0.2170, loss_mask: 0.2295, loss: 0.6826 2023-11-15 19:57:39,496 - mmdet - INFO - Epoch [10][1650/1833] lr: 2.000e-04, eta: 15:42:44, time: 1.202, data_time: 0.066, memory: 16000, loss_rpn_cls: 0.0243, loss_rpn_bbox: 0.0335, loss_cls: 0.1716, acc: 93.8729, loss_bbox: 0.2124, loss_mask: 0.2287, loss: 0.6706 2023-11-15 19:58:38,481 - mmdet - INFO - Epoch [10][1700/1833] lr: 2.000e-04, eta: 15:41:45, time: 1.180, data_time: 0.073, memory: 16000, loss_rpn_cls: 0.0261, loss_rpn_bbox: 0.0341, loss_cls: 0.1762, acc: 93.6887, loss_bbox: 0.2165, loss_mask: 0.2304, loss: 0.6833 2023-11-15 19:59:38,821 - mmdet - INFO - Epoch [10][1750/1833] lr: 2.000e-04, eta: 15:40:49, time: 1.207, data_time: 0.072, memory: 16000, loss_rpn_cls: 0.0258, loss_rpn_bbox: 0.0335, loss_cls: 0.1740, acc: 93.7274, loss_bbox: 0.2136, loss_mask: 0.2270, loss: 0.6739 2023-11-15 20:00:37,896 - mmdet - INFO - Epoch [10][1800/1833] lr: 2.000e-04, eta: 15:39:49, time: 1.182, data_time: 0.073, memory: 16000, loss_rpn_cls: 0.0264, loss_rpn_bbox: 0.0337, loss_cls: 0.1767, acc: 93.6161, loss_bbox: 0.2180, loss_mask: 0.2291, loss: 0.6839 2023-11-15 20:01:18,048 - mmdet - INFO - Saving checkpoint at 10 epochs 2023-11-15 20:02:06,524 - mmdet - INFO - Evaluating bbox... 2023-11-15 20:02:35,319 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.472 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.697 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.523 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.330 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.514 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.610 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.601 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.601 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.601 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.450 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 ] = 0.747 2023-11-15 20:02:35,321 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.576 | bicycle | 0.364 | car | 0.485 | | motorcycle | 0.484 | airplane | 0.669 | bus | 0.700 | | train | 0.661 | truck | 0.422 | boat | 0.322 | | traffic light | 0.316 | fire hydrant | 0.733 | stop sign | 0.671 | | parking meter | 0.536 | bench | 0.296 | bird | 0.400 | | cat | 0.720 | dog | 0.676 | horse | 0.624 | | sheep | 0.593 | cow | 0.633 | elephant | 0.682 | | bear | 0.732 | zebra | 0.678 | giraffe | 0.697 | | backpack | 0.206 | umbrella | 0.462 | handbag | 0.211 | | tie | 0.362 | suitcase | 0.463 | frisbee | 0.698 | | skis | 0.288 | snowboard | 0.443 | sports ball | 0.467 | | kite | 0.469 | baseball bat | 0.393 | baseball glove | 0.440 | | skateboard | 0.563 | surfboard | 0.440 | tennis racket | 0.531 | | bottle | 0.444 | wine glass | 0.428 | cup | 0.492 | | fork | 0.444 | knife | 0.267 | spoon | 0.288 | | bowl | 0.459 | banana | 0.281 | apple | 0.261 | | sandwich | 0.419 | orange | 0.345 | broccoli | 0.256 | | carrot | 0.272 | hot dog | 0.466 | pizza | 0.547 | | donut | 0.529 | cake | 0.411 | chair | 0.353 | | couch | 0.449 | potted plant | 0.353 | bed | 0.495 | | dining table | 0.310 | toilet | 0.619 | tv | 0.617 | | laptop | 0.678 | mouse | 0.651 | remote | 0.400 | | keyboard | 0.532 | cell phone | 0.430 | microwave | 0.626 | | oven | 0.411 | toaster | 0.573 | sink | 0.414 | | refrigerator | 0.621 | book | 0.180 | clock | 0.512 | | vase | 0.423 | scissors | 0.428 | teddy bear | 0.523 | | hair drier | 0.148 | toothbrush | 0.293 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-15 20:02:35,321 - mmdet - INFO - Evaluating segm... 2023-11-15 20:03:09,930 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.425 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.667 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.457 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.243 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.462 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.608 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.548 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.548 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.548 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 ] = 0.590 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.703 2023-11-15 20:03:09,932 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.497 | bicycle | 0.216 | car | 0.448 | | motorcycle | 0.402 | airplane | 0.527 | bus | 0.690 | | train | 0.657 | truck | 0.409 | boat | 0.298 | | traffic light | 0.297 | fire hydrant | 0.695 | stop sign | 0.648 | | parking meter | 0.544 | bench | 0.229 | bird | 0.333 | | cat | 0.719 | dog | 0.641 | horse | 0.463 | | sheep | 0.531 | cow | 0.528 | elephant | 0.621 | | bear | 0.727 | zebra | 0.593 | giraffe | 0.546 | | backpack | 0.217 | umbrella | 0.525 | handbag | 0.207 | | tie | 0.337 | suitcase | 0.481 | frisbee | 0.666 | | skis | 0.048 | snowboard | 0.284 | sports ball | 0.439 | | kite | 0.328 | baseball bat | 0.295 | baseball glove | 0.457 | | skateboard | 0.364 | surfboard | 0.367 | tennis racket | 0.599 | | bottle | 0.422 | wine glass | 0.390 | cup | 0.493 | | fork | 0.209 | knife | 0.178 | spoon | 0.189 | | bowl | 0.434 | banana | 0.226 | apple | 0.254 | | sandwich | 0.448 | orange | 0.346 | broccoli | 0.245 | | carrot | 0.234 | hot dog | 0.383 | pizza | 0.532 | | donut | 0.534 | cake | 0.413 | chair | 0.263 | | couch | 0.393 | potted plant | 0.300 | bed | 0.385 | | dining table | 0.172 | toilet | 0.607 | tv | 0.648 | | laptop | 0.670 | mouse | 0.631 | remote | 0.361 | | keyboard | 0.537 | cell phone | 0.405 | microwave | 0.629 | | oven | 0.386 | toaster | 0.601 | sink | 0.391 | | refrigerator | 0.643 | book | 0.130 | clock | 0.520 | | vase | 0.424 | scissors | 0.304 | teddy bear | 0.509 | | hair drier | 0.081 | toothbrush | 0.193 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-15 20:03:10,388 - mmdet - INFO - The previous best checkpoint /mnt/petrelfs/lizhiqi/DINO/detection/work_dirs/mask_rcnn_flash_internimage_s_fpn_3x_coco_0.4/best_bbox_mAP_epoch_9.pth was removed 2023-11-15 20:03:12,450 - mmdet - INFO - Now best checkpoint is saved as best_bbox_mAP_epoch_10.pth. 2023-11-15 20:03:12,451 - mmdet - INFO - Best bbox_mAP is 0.4719 at 10 epoch. 2023-11-15 20:03:12,451 - mmdet - INFO - Exp name: mask_rcnn_flash_internimage_s_fpn_3x_coco_0.4.py 2023-11-15 20:03:12,451 - mmdet - INFO - Epoch(val) [10][625] bbox_mAP: 0.4719, bbox_mAP_50: 0.6965, bbox_mAP_75: 0.5233, bbox_mAP_s: 0.3296, bbox_mAP_m: 0.5142, bbox_mAP_l: 0.6097, bbox_mAP_copypaste: 0.4719 0.6965 0.5233 0.3296 0.5142 0.6097, segm_mAP: 0.4249, segm_mAP_50: 0.6666, segm_mAP_75: 0.4565, segm_mAP_s: 0.2428, segm_mAP_m: 0.4621, segm_mAP_l: 0.6077, segm_mAP_copypaste: 0.4249 0.6666 0.4565 0.2428 0.4621 0.6077 2023-11-15 20:04:16,552 - mmdet - INFO - Epoch [11][50/1833] lr: 2.000e-04, eta: 15:36:43, time: 1.282, data_time: 0.138, memory: 16000, loss_rpn_cls: 0.0240, loss_rpn_bbox: 0.0330, loss_cls: 0.1687, acc: 93.8917, loss_bbox: 0.2133, loss_mask: 0.2285, loss: 0.6676 2023-11-15 20:05:16,299 - mmdet - INFO - Epoch [11][100/1833] lr: 2.000e-04, eta: 15:35:46, time: 1.195, data_time: 0.078, memory: 16000, loss_rpn_cls: 0.0256, loss_rpn_bbox: 0.0336, loss_cls: 0.1701, acc: 93.8472, loss_bbox: 0.2147, loss_mask: 0.2285, loss: 0.6725 2023-11-15 20:06:17,177 - mmdet - INFO - Epoch [11][150/1833] lr: 2.000e-04, eta: 15:34:52, time: 1.218, data_time: 0.086, memory: 16000, loss_rpn_cls: 0.0256, loss_rpn_bbox: 0.0356, loss_cls: 0.1728, acc: 93.6838, loss_bbox: 0.2197, loss_mask: 0.2316, loss: 0.6852 2023-11-15 20:07:17,956 - mmdet - INFO - Epoch [11][200/1833] lr: 2.000e-04, eta: 15:33:57, time: 1.216, data_time: 0.076, memory: 16000, loss_rpn_cls: 0.0247, loss_rpn_bbox: 0.0330, loss_cls: 0.1682, acc: 93.9072, loss_bbox: 0.2139, loss_mask: 0.2244, loss: 0.6642 2023-11-15 20:08:18,229 - mmdet - INFO - Epoch [11][250/1833] lr: 2.000e-04, eta: 15:33:01, time: 1.205, data_time: 0.075, memory: 16000, loss_rpn_cls: 0.0264, loss_rpn_bbox: 0.0351, loss_cls: 0.1710, acc: 93.7939, loss_bbox: 0.2157, loss_mask: 0.2284, loss: 0.6766 2023-11-15 20:09:18,864 - mmdet - INFO - Epoch [11][300/1833] lr: 2.000e-04, eta: 15:32:06, time: 1.213, data_time: 0.076, memory: 16000, loss_rpn_cls: 0.0247, loss_rpn_bbox: 0.0339, loss_cls: 0.1654, acc: 94.0199, loss_bbox: 0.2111, loss_mask: 0.2268, loss: 0.6618 2023-11-15 20:10:19,248 - mmdet - INFO - Epoch [11][350/1833] lr: 2.000e-04, eta: 15:31:11, time: 1.208, data_time: 0.080, memory: 16000, loss_rpn_cls: 0.0254, loss_rpn_bbox: 0.0331, loss_cls: 0.1696, acc: 93.9386, loss_bbox: 0.2111, loss_mask: 0.2243, loss: 0.6634 2023-11-15 20:11:19,191 - mmdet - INFO - Epoch [11][400/1833] lr: 2.000e-04, eta: 15:30:14, time: 1.199, data_time: 0.082, memory: 16000, loss_rpn_cls: 0.0265, loss_rpn_bbox: 0.0343, loss_cls: 0.1732, acc: 93.7136, loss_bbox: 0.2194, loss_mask: 0.2304, loss: 0.6837 2023-11-15 20:12:19,601 - mmdet - INFO - Epoch [11][450/1833] lr: 2.000e-04, eta: 15:29:18, time: 1.208, data_time: 0.085, memory: 16000, loss_rpn_cls: 0.0264, loss_rpn_bbox: 0.0344, loss_cls: 0.1741, acc: 93.6626, loss_bbox: 0.2198, loss_mask: 0.2272, loss: 0.6820 2023-11-15 20:13:19,867 - mmdet - INFO - Epoch [11][500/1833] lr: 2.000e-04, eta: 15:28:22, time: 1.205, data_time: 0.082, memory: 16000, loss_rpn_cls: 0.0244, loss_rpn_bbox: 0.0327, loss_cls: 0.1689, acc: 93.9023, loss_bbox: 0.2141, loss_mask: 0.2254, loss: 0.6655 2023-11-15 20:14:20,795 - mmdet - INFO - Epoch [11][550/1833] lr: 2.000e-04, eta: 15:27:28, time: 1.218, data_time: 0.078, memory: 16000, loss_rpn_cls: 0.0263, loss_rpn_bbox: 0.0348, loss_cls: 0.1752, acc: 93.6550, loss_bbox: 0.2192, loss_mask: 0.2296, loss: 0.6850 2023-11-15 20:15:18,700 - mmdet - INFO - Epoch [11][600/1833] lr: 2.000e-04, eta: 15:26:26, time: 1.158, data_time: 0.073, memory: 16000, loss_rpn_cls: 0.0245, loss_rpn_bbox: 0.0327, loss_cls: 0.1682, acc: 93.9597, loss_bbox: 0.2123, loss_mask: 0.2271, loss: 0.6648 2023-11-15 20:16:19,159 - mmdet - INFO - Epoch [11][650/1833] lr: 2.000e-04, eta: 15:25:30, time: 1.209, data_time: 0.077, memory: 16000, loss_rpn_cls: 0.0255, loss_rpn_bbox: 0.0334, loss_cls: 0.1688, acc: 93.9084, loss_bbox: 0.2129, loss_mask: 0.2274, loss: 0.6680 2023-11-15 20:17:19,459 - mmdet - INFO - Epoch [11][700/1833] lr: 2.000e-04, eta: 15:24:34, time: 1.206, data_time: 0.074, memory: 16000, loss_rpn_cls: 0.0257, loss_rpn_bbox: 0.0338, loss_cls: 0.1705, acc: 93.8506, loss_bbox: 0.2164, loss_mask: 0.2287, loss: 0.6751 2023-11-15 20:18:20,776 - mmdet - INFO - Epoch [11][750/1833] lr: 2.000e-04, eta: 15:23:41, time: 1.226, data_time: 0.080, memory: 16000, loss_rpn_cls: 0.0251, loss_rpn_bbox: 0.0338, loss_cls: 0.1729, acc: 93.7487, loss_bbox: 0.2171, loss_mask: 0.2263, loss: 0.6752 2023-11-15 20:19:19,967 - mmdet - INFO - Epoch [11][800/1833] lr: 2.000e-04, eta: 15:22:42, time: 1.184, data_time: 0.070, memory: 16000, loss_rpn_cls: 0.0253, loss_rpn_bbox: 0.0327, loss_cls: 0.1707, acc: 93.8510, loss_bbox: 0.2129, loss_mask: 0.2256, loss: 0.6673 2023-11-15 20:20:19,502 - mmdet - INFO - Epoch [11][850/1833] lr: 2.000e-04, eta: 15:21:44, time: 1.191, data_time: 0.075, memory: 16000, loss_rpn_cls: 0.0249, loss_rpn_bbox: 0.0342, loss_cls: 0.1739, acc: 93.7183, loss_bbox: 0.2173, loss_mask: 0.2282, loss: 0.6785 2023-11-15 20:21:19,631 - mmdet - INFO - Epoch [11][900/1833] lr: 2.000e-04, eta: 15:20:47, time: 1.203, data_time: 0.084, memory: 16000, loss_rpn_cls: 0.0252, loss_rpn_bbox: 0.0336, loss_cls: 0.1727, acc: 93.7756, loss_bbox: 0.2149, loss_mask: 0.2293, loss: 0.6757 2023-11-15 20:22:20,304 - mmdet - INFO - Epoch [11][950/1833] lr: 2.000e-04, eta: 15:19:52, time: 1.213, data_time: 0.082, memory: 16000, loss_rpn_cls: 0.0253, loss_rpn_bbox: 0.0341, loss_cls: 0.1734, acc: 93.7459, loss_bbox: 0.2154, loss_mask: 0.2264, loss: 0.6745 2023-11-15 20:23:19,433 - mmdet - INFO - Epoch [11][1000/1833] lr: 2.000e-04, eta: 15:18:53, time: 1.183, data_time: 0.073, memory: 16000, loss_rpn_cls: 0.0244, loss_rpn_bbox: 0.0325, loss_cls: 0.1698, acc: 93.8754, loss_bbox: 0.2132, loss_mask: 0.2275, loss: 0.6675 2023-11-15 20:24:19,428 - mmdet - INFO - Epoch [11][1050/1833] lr: 2.000e-04, eta: 15:17:56, time: 1.200, data_time: 0.075, memory: 16000, loss_rpn_cls: 0.0247, loss_rpn_bbox: 0.0326, loss_cls: 0.1712, acc: 93.8282, loss_bbox: 0.2153, loss_mask: 0.2279, loss: 0.6718 2023-11-15 20:25:18,705 - mmdet - INFO - Epoch [11][1100/1833] lr: 2.000e-04, eta: 15:16:58, time: 1.185, data_time: 0.095, memory: 16000, loss_rpn_cls: 0.0247, loss_rpn_bbox: 0.0340, loss_cls: 0.1681, acc: 93.9120, loss_bbox: 0.2138, loss_mask: 0.2268, loss: 0.6674 2023-11-15 20:26:19,349 - mmdet - INFO - Epoch [11][1150/1833] lr: 2.000e-04, eta: 15:16:02, time: 1.213, data_time: 0.090, memory: 16000, loss_rpn_cls: 0.0259, loss_rpn_bbox: 0.0361, loss_cls: 0.1734, acc: 93.6831, loss_bbox: 0.2197, loss_mask: 0.2317, loss: 0.6868 2023-11-15 20:27:19,284 - mmdet - INFO - Epoch [11][1200/1833] lr: 2.000e-04, eta: 15:15:05, time: 1.199, data_time: 0.083, memory: 16000, loss_rpn_cls: 0.0248, loss_rpn_bbox: 0.0335, loss_cls: 0.1742, acc: 93.7004, loss_bbox: 0.2166, loss_mask: 0.2284, loss: 0.6775 2023-11-15 20:28:19,728 - mmdet - INFO - Epoch [11][1250/1833] lr: 2.000e-04, eta: 15:14:09, time: 1.209, data_time: 0.079, memory: 16000, loss_rpn_cls: 0.0250, loss_rpn_bbox: 0.0330, loss_cls: 0.1703, acc: 93.7844, loss_bbox: 0.2143, loss_mask: 0.2267, loss: 0.6693 2023-11-15 20:29:20,877 - mmdet - INFO - Epoch [11][1300/1833] lr: 2.000e-04, eta: 15:13:15, time: 1.223, data_time: 0.074, memory: 16000, loss_rpn_cls: 0.0247, loss_rpn_bbox: 0.0330, loss_cls: 0.1686, acc: 93.9212, loss_bbox: 0.2130, loss_mask: 0.2217, loss: 0.6609 2023-11-15 20:30:22,141 - mmdet - INFO - Epoch [11][1350/1833] lr: 2.000e-04, eta: 15:12:21, time: 1.225, data_time: 0.074, memory: 16000, loss_rpn_cls: 0.0245, loss_rpn_bbox: 0.0330, loss_cls: 0.1675, acc: 93.9533, loss_bbox: 0.2119, loss_mask: 0.2266, loss: 0.6636 2023-11-15 20:31:22,674 - mmdet - INFO - Epoch [11][1400/1833] lr: 2.000e-04, eta: 15:11:25, time: 1.211, data_time: 0.071, memory: 16000, loss_rpn_cls: 0.0254, loss_rpn_bbox: 0.0334, loss_cls: 0.1725, acc: 93.8270, loss_bbox: 0.2145, loss_mask: 0.2265, loss: 0.6722 2023-11-15 20:32:23,297 - mmdet - INFO - Epoch [11][1450/1833] lr: 2.000e-04, eta: 15:10:30, time: 1.212, data_time: 0.074, memory: 16000, loss_rpn_cls: 0.0261, loss_rpn_bbox: 0.0338, loss_cls: 0.1713, acc: 93.7806, loss_bbox: 0.2150, loss_mask: 0.2276, loss: 0.6738 2023-11-15 20:33:23,909 - mmdet - INFO - Epoch [11][1500/1833] lr: 2.000e-04, eta: 15:09:34, time: 1.212, data_time: 0.078, memory: 16000, loss_rpn_cls: 0.0256, loss_rpn_bbox: 0.0339, loss_cls: 0.1744, acc: 93.7396, loss_bbox: 0.2136, loss_mask: 0.2290, loss: 0.6765 2023-11-15 20:34:23,793 - mmdet - INFO - Epoch [11][1550/1833] lr: 2.000e-04, eta: 15:08:37, time: 1.198, data_time: 0.083, memory: 16000, loss_rpn_cls: 0.0254, loss_rpn_bbox: 0.0333, loss_cls: 0.1713, acc: 93.8542, loss_bbox: 0.2117, loss_mask: 0.2264, loss: 0.6682 2023-11-15 20:35:23,921 - mmdet - INFO - Epoch [11][1600/1833] lr: 2.000e-04, eta: 15:07:40, time: 1.203, data_time: 0.073, memory: 16000, loss_rpn_cls: 0.0255, loss_rpn_bbox: 0.0340, loss_cls: 0.1714, acc: 93.8385, loss_bbox: 0.2126, loss_mask: 0.2276, loss: 0.6711 2023-11-15 20:36:23,850 - mmdet - INFO - Epoch [11][1650/1833] lr: 2.000e-04, eta: 15:06:43, time: 1.198, data_time: 0.079, memory: 16000, loss_rpn_cls: 0.0256, loss_rpn_bbox: 0.0334, loss_cls: 0.1716, acc: 93.8112, loss_bbox: 0.2142, loss_mask: 0.2274, loss: 0.6722 2023-11-15 20:37:24,328 - mmdet - INFO - Epoch [11][1700/1833] lr: 2.000e-04, eta: 15:05:47, time: 1.210, data_time: 0.076, memory: 16000, loss_rpn_cls: 0.0252, loss_rpn_bbox: 0.0353, loss_cls: 0.1726, acc: 93.7688, loss_bbox: 0.2178, loss_mask: 0.2279, loss: 0.6788 2023-11-15 20:38:24,346 - mmdet - INFO - Epoch [11][1750/1833] lr: 2.000e-04, eta: 15:04:50, time: 1.200, data_time: 0.072, memory: 16000, loss_rpn_cls: 0.0248, loss_rpn_bbox: 0.0331, loss_cls: 0.1718, acc: 93.8694, loss_bbox: 0.2101, loss_mask: 0.2251, loss: 0.6648 2023-11-15 20:39:24,075 - mmdet - INFO - Epoch [11][1800/1833] lr: 2.000e-04, eta: 15:03:52, time: 1.195, data_time: 0.081, memory: 16000, loss_rpn_cls: 0.0254, loss_rpn_bbox: 0.0341, loss_cls: 0.1736, acc: 93.7554, loss_bbox: 0.2164, loss_mask: 0.2288, loss: 0.6781 2023-11-15 20:40:04,400 - mmdet - INFO - Saving checkpoint at 11 epochs 2023-11-15 20:40:54,951 - mmdet - INFO - Evaluating bbox... 2023-11-15 20:41:26,115 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.475 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.698 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.525 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.325 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 ] = 0.610 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 ] = 0.442 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.648 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.746 2023-11-15 20:41:26,118 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.575 | bicycle | 0.357 | car | 0.490 | | motorcycle | 0.480 | airplane | 0.685 | bus | 0.691 | | train | 0.663 | truck | 0.410 | boat | 0.318 | | traffic light | 0.319 | fire hydrant | 0.736 | stop sign | 0.651 | | parking meter | 0.532 | bench | 0.297 | bird | 0.421 | | cat | 0.725 | dog | 0.666 | horse | 0.629 | | sheep | 0.582 | cow | 0.619 | elephant | 0.667 | | bear | 0.741 | zebra | 0.704 | giraffe | 0.713 | | backpack | 0.195 | umbrella | 0.454 | handbag | 0.233 | | tie | 0.378 | suitcase | 0.473 | frisbee | 0.725 | | skis | 0.293 | snowboard | 0.452 | sports ball | 0.467 | | kite | 0.470 | baseball bat | 0.400 | baseball glove | 0.445 | | skateboard | 0.584 | surfboard | 0.430 | tennis racket | 0.549 | | bottle | 0.452 | wine glass | 0.429 | cup | 0.496 | | fork | 0.429 | knife | 0.265 | spoon | 0.295 | | bowl | 0.472 | banana | 0.285 | apple | 0.269 | | sandwich | 0.466 | orange | 0.356 | broccoli | 0.258 | | carrot | 0.274 | hot dog | 0.446 | pizza | 0.533 | | donut | 0.555 | cake | 0.413 | chair | 0.359 | | couch | 0.416 | potted plant | 0.346 | bed | 0.450 | | dining table | 0.304 | toilet | 0.655 | tv | 0.618 | | laptop | 0.677 | mouse | 0.638 | remote | 0.425 | | keyboard | 0.555 | cell phone | 0.432 | microwave | 0.650 | | oven | 0.400 | toaster | 0.456 | sink | 0.455 | | refrigerator | 0.656 | book | 0.184 | clock | 0.539 | | vase | 0.442 | scissors | 0.425 | teddy bear | 0.534 | | hair drier | 0.193 | toothbrush | 0.274 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-15 20:41:26,118 - mmdet - INFO - Evaluating segm... 2023-11-15 20:42:00,480 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.425 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.667 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.458 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.234 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.463 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.612 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 ] = 0.374 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.594 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.707 2023-11-15 20:42:00,483 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.499 | bicycle | 0.211 | car | 0.444 | | motorcycle | 0.396 | airplane | 0.533 | bus | 0.679 | | train | 0.659 | truck | 0.387 | boat | 0.284 | | traffic light | 0.311 | fire hydrant | 0.701 | stop sign | 0.644 | | parking meter | 0.534 | bench | 0.226 | bird | 0.330 | | cat | 0.726 | dog | 0.633 | horse | 0.467 | | sheep | 0.518 | cow | 0.511 | elephant | 0.629 | | bear | 0.733 | zebra | 0.615 | giraffe | 0.546 | | backpack | 0.201 | umbrella | 0.516 | handbag | 0.216 | | tie | 0.343 | suitcase | 0.481 | frisbee | 0.663 | | skis | 0.048 | snowboard | 0.272 | sports ball | 0.454 | | kite | 0.328 | baseball bat | 0.295 | baseball glove | 0.455 | | skateboard | 0.356 | surfboard | 0.346 | tennis racket | 0.584 | | bottle | 0.428 | wine glass | 0.386 | cup | 0.491 | | fork | 0.217 | knife | 0.192 | spoon | 0.191 | | bowl | 0.447 | banana | 0.246 | apple | 0.266 | | sandwich | 0.480 | orange | 0.358 | broccoli | 0.249 | | carrot | 0.242 | hot dog | 0.371 | pizza | 0.511 | | donut | 0.561 | cake | 0.416 | chair | 0.257 | | couch | 0.343 | potted plant | 0.292 | bed | 0.370 | | dining table | 0.183 | toilet | 0.631 | tv | 0.645 | | laptop | 0.662 | mouse | 0.617 | remote | 0.370 | | keyboard | 0.536 | cell phone | 0.406 | microwave | 0.676 | | oven | 0.367 | toaster | 0.542 | sink | 0.427 | | refrigerator | 0.647 | book | 0.136 | clock | 0.528 | | vase | 0.435 | scissors | 0.309 | teddy bear | 0.518 | | hair drier | 0.083 | toothbrush | 0.186 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-15 20:42:00,946 - mmdet - INFO - The previous best checkpoint /mnt/petrelfs/lizhiqi/DINO/detection/work_dirs/mask_rcnn_flash_internimage_s_fpn_3x_coco_0.4/best_bbox_mAP_epoch_10.pth was removed 2023-11-15 20:42:03,044 - mmdet - INFO - Now best checkpoint is saved as best_bbox_mAP_epoch_11.pth. 2023-11-15 20:42:03,045 - mmdet - INFO - Best bbox_mAP is 0.4749 at 11 epoch. 2023-11-15 20:42:03,045 - mmdet - INFO - Exp name: mask_rcnn_flash_internimage_s_fpn_3x_coco_0.4.py 2023-11-15 20:42:03,045 - mmdet - INFO - Epoch(val) [11][625] bbox_mAP: 0.4749, bbox_mAP_50: 0.6984, bbox_mAP_75: 0.5254, bbox_mAP_s: 0.3252, bbox_mAP_m: 0.5186, bbox_mAP_l: 0.6105, bbox_mAP_copypaste: 0.4749 0.6984 0.5254 0.3252 0.5186 0.6105, segm_mAP: 0.4249, segm_mAP_50: 0.6665, segm_mAP_75: 0.4578, segm_mAP_s: 0.2340, segm_mAP_m: 0.4628, segm_mAP_l: 0.6120, segm_mAP_copypaste: 0.4249 0.6665 0.4578 0.2340 0.4628 0.6120 2023-11-15 20:43:06,761 - mmdet - INFO - Epoch [12][50/1833] lr: 2.000e-04, eta: 15:00:56, time: 1.274, data_time: 0.130, memory: 16000, loss_rpn_cls: 0.0235, loss_rpn_bbox: 0.0332, loss_cls: 0.1656, acc: 93.9842, loss_bbox: 0.2114, loss_mask: 0.2222, loss: 0.6559 2023-11-15 20:44:06,704 - mmdet - INFO - Epoch [12][100/1833] lr: 2.000e-04, eta: 14:59:59, time: 1.199, data_time: 0.084, memory: 16000, loss_rpn_cls: 0.0247, loss_rpn_bbox: 0.0333, loss_cls: 0.1657, acc: 93.9471, loss_bbox: 0.2127, loss_mask: 0.2264, loss: 0.6628 2023-11-15 20:45:07,752 - mmdet - INFO - Epoch [12][150/1833] lr: 2.000e-04, eta: 14:59:04, time: 1.221, data_time: 0.080, memory: 16000, loss_rpn_cls: 0.0251, loss_rpn_bbox: 0.0336, loss_cls: 0.1655, acc: 93.9635, loss_bbox: 0.2129, loss_mask: 0.2248, loss: 0.6619 2023-11-15 20:46:08,794 - mmdet - INFO - Epoch [12][200/1833] lr: 2.000e-04, eta: 14:58:09, time: 1.221, data_time: 0.066, memory: 16000, loss_rpn_cls: 0.0249, loss_rpn_bbox: 0.0327, loss_cls: 0.1675, acc: 93.9868, loss_bbox: 0.2115, loss_mask: 0.2247, loss: 0.6612 2023-11-15 20:47:09,081 - mmdet - INFO - Epoch [12][250/1833] lr: 2.000e-04, eta: 14:57:13, time: 1.206, data_time: 0.070, memory: 16000, loss_rpn_cls: 0.0254, loss_rpn_bbox: 0.0343, loss_cls: 0.1720, acc: 93.7410, loss_bbox: 0.2171, loss_mask: 0.2282, loss: 0.6770 2023-11-15 20:48:09,802 - mmdet - INFO - Epoch [12][300/1833] lr: 2.000e-04, eta: 14:56:18, time: 1.214, data_time: 0.067, memory: 16000, loss_rpn_cls: 0.0254, loss_rpn_bbox: 0.0350, loss_cls: 0.1701, acc: 93.7705, loss_bbox: 0.2168, loss_mask: 0.2301, loss: 0.6774 2023-11-15 20:49:09,740 - mmdet - INFO - Epoch [12][350/1833] lr: 2.000e-04, eta: 14:55:21, time: 1.199, data_time: 0.070, memory: 16000, loss_rpn_cls: 0.0255, loss_rpn_bbox: 0.0340, loss_cls: 0.1685, acc: 93.9371, loss_bbox: 0.2125, loss_mask: 0.2268, loss: 0.6673 2023-11-15 20:50:09,768 - mmdet - INFO - Epoch [12][400/1833] lr: 2.000e-04, eta: 14:54:24, time: 1.200, data_time: 0.070, memory: 16000, loss_rpn_cls: 0.0231, loss_rpn_bbox: 0.0324, loss_cls: 0.1657, acc: 94.0247, loss_bbox: 0.2087, loss_mask: 0.2255, loss: 0.6554 2023-11-15 20:51:10,702 - mmdet - INFO - Epoch [12][450/1833] lr: 2.000e-04, eta: 14:53:29, time: 1.219, data_time: 0.080, memory: 16000, loss_rpn_cls: 0.0250, loss_rpn_bbox: 0.0340, loss_cls: 0.1732, acc: 93.6496, loss_bbox: 0.2180, loss_mask: 0.2291, loss: 0.6793 2023-11-15 20:52:10,931 - mmdet - INFO - Epoch [12][500/1833] lr: 2.000e-04, eta: 14:52:32, time: 1.205, data_time: 0.063, memory: 16000, loss_rpn_cls: 0.0245, loss_rpn_bbox: 0.0325, loss_cls: 0.1672, acc: 93.9880, loss_bbox: 0.2078, loss_mask: 0.2222, loss: 0.6542 2023-11-15 20:53:11,481 - mmdet - INFO - Epoch [12][550/1833] lr: 2.000e-04, eta: 14:51:36, time: 1.211, data_time: 0.062, memory: 16000, loss_rpn_cls: 0.0255, loss_rpn_bbox: 0.0336, loss_cls: 0.1703, acc: 93.8344, loss_bbox: 0.2135, loss_mask: 0.2233, loss: 0.6663 2023-11-15 20:54:10,758 - mmdet - INFO - Epoch [12][600/1833] lr: 2.000e-04, eta: 14:50:38, time: 1.185, data_time: 0.071, memory: 16000, loss_rpn_cls: 0.0234, loss_rpn_bbox: 0.0337, loss_cls: 0.1689, acc: 93.7834, loss_bbox: 0.2169, loss_mask: 0.2279, loss: 0.6708 2023-11-15 20:55:11,094 - mmdet - INFO - Epoch [12][650/1833] lr: 2.000e-04, eta: 14:49:41, time: 1.207, data_time: 0.067, memory: 16000, loss_rpn_cls: 0.0262, loss_rpn_bbox: 0.0340, loss_cls: 0.1685, acc: 93.8894, loss_bbox: 0.2155, loss_mask: 0.2279, loss: 0.6720 2023-11-15 20:56:11,789 - mmdet - INFO - Epoch [12][700/1833] lr: 2.000e-04, eta: 14:48:46, time: 1.214, data_time: 0.073, memory: 16000, loss_rpn_cls: 0.0268, loss_rpn_bbox: 0.0356, loss_cls: 0.1695, acc: 93.8415, loss_bbox: 0.2160, loss_mask: 0.2272, loss: 0.6751 2023-11-15 20:57:13,107 - mmdet - INFO - Epoch [12][750/1833] lr: 2.000e-04, eta: 14:47:51, time: 1.226, data_time: 0.066, memory: 16000, loss_rpn_cls: 0.0247, loss_rpn_bbox: 0.0325, loss_cls: 0.1668, acc: 93.9589, loss_bbox: 0.2104, loss_mask: 0.2240, loss: 0.6584 2023-11-15 20:58:12,896 - mmdet - INFO - Epoch [12][800/1833] lr: 2.000e-04, eta: 14:46:54, time: 1.196, data_time: 0.067, memory: 16000, loss_rpn_cls: 0.0243, loss_rpn_bbox: 0.0339, loss_cls: 0.1663, acc: 93.9515, loss_bbox: 0.2080, loss_mask: 0.2228, loss: 0.6554 2023-11-15 20:59:13,468 - mmdet - INFO - Epoch [12][850/1833] lr: 2.000e-04, eta: 14:45:58, time: 1.211, data_time: 0.072, memory: 16000, loss_rpn_cls: 0.0255, loss_rpn_bbox: 0.0338, loss_cls: 0.1714, acc: 93.8534, loss_bbox: 0.2131, loss_mask: 0.2256, loss: 0.6693 2023-11-15 21:00:12,542 - mmdet - INFO - Epoch [12][900/1833] lr: 2.000e-04, eta: 14:44:59, time: 1.182, data_time: 0.078, memory: 16000, loss_rpn_cls: 0.0249, loss_rpn_bbox: 0.0332, loss_cls: 0.1655, acc: 94.0609, loss_bbox: 0.2066, loss_mask: 0.2241, loss: 0.6543 2023-11-15 21:01:15,762 - mmdet - INFO - Epoch [12][950/1833] lr: 2.000e-04, eta: 14:44:08, time: 1.264, data_time: 0.079, memory: 16000, loss_rpn_cls: 0.0254, loss_rpn_bbox: 0.0343, loss_cls: 0.1698, acc: 93.8349, loss_bbox: 0.2149, loss_mask: 0.2264, loss: 0.6708 2023-11-15 21:02:16,097 - mmdet - INFO - Epoch [12][1000/1833] lr: 2.000e-04, eta: 14:43:12, time: 1.207, data_time: 0.072, memory: 16000, loss_rpn_cls: 0.0241, loss_rpn_bbox: 0.0325, loss_cls: 0.1658, acc: 93.9617, loss_bbox: 0.2075, loss_mask: 0.2218, loss: 0.6517 2023-11-15 21:03:16,466 - mmdet - INFO - Epoch [12][1050/1833] lr: 2.000e-04, eta: 14:42:15, time: 1.207, data_time: 0.067, memory: 16000, loss_rpn_cls: 0.0240, loss_rpn_bbox: 0.0325, loss_cls: 0.1648, acc: 94.0355, loss_bbox: 0.2078, loss_mask: 0.2237, loss: 0.6529 2023-11-15 21:04:16,881 - mmdet - INFO - Epoch [12][1100/1833] lr: 2.000e-04, eta: 14:41:19, time: 1.208, data_time: 0.069, memory: 16000, loss_rpn_cls: 0.0251, loss_rpn_bbox: 0.0331, loss_cls: 0.1705, acc: 93.8670, loss_bbox: 0.2139, loss_mask: 0.2282, loss: 0.6707 2023-11-15 21:05:16,705 - mmdet - INFO - Epoch [12][1150/1833] lr: 2.000e-04, eta: 14:40:21, time: 1.197, data_time: 0.063, memory: 16000, loss_rpn_cls: 0.0243, loss_rpn_bbox: 0.0319, loss_cls: 0.1653, acc: 94.0418, loss_bbox: 0.2096, loss_mask: 0.2232, loss: 0.6543 2023-11-15 21:06:17,677 - mmdet - INFO - Epoch [12][1200/1833] lr: 2.000e-04, eta: 14:39:26, time: 1.219, data_time: 0.072, memory: 16000, loss_rpn_cls: 0.0235, loss_rpn_bbox: 0.0324, loss_cls: 0.1652, acc: 94.0645, loss_bbox: 0.2073, loss_mask: 0.2259, loss: 0.6543 2023-11-15 21:07:17,897 - mmdet - INFO - Epoch [12][1250/1833] lr: 2.000e-04, eta: 14:38:29, time: 1.204, data_time: 0.071, memory: 16000, loss_rpn_cls: 0.0247, loss_rpn_bbox: 0.0337, loss_cls: 0.1682, acc: 93.8928, loss_bbox: 0.2116, loss_mask: 0.2256, loss: 0.6638 2023-11-15 21:08:18,472 - mmdet - INFO - Epoch [12][1300/1833] lr: 2.000e-04, eta: 14:37:33, time: 1.211, data_time: 0.069, memory: 16000, loss_rpn_cls: 0.0246, loss_rpn_bbox: 0.0327, loss_cls: 0.1712, acc: 93.8723, loss_bbox: 0.2131, loss_mask: 0.2264, loss: 0.6680 2023-11-15 21:09:17,931 - mmdet - INFO - Epoch [12][1350/1833] lr: 2.000e-04, eta: 14:36:35, time: 1.189, data_time: 0.066, memory: 16000, loss_rpn_cls: 0.0239, loss_rpn_bbox: 0.0326, loss_cls: 0.1660, acc: 94.0193, loss_bbox: 0.2076, loss_mask: 0.2231, loss: 0.6532 2023-11-15 21:10:18,082 - mmdet - INFO - Epoch [12][1400/1833] lr: 2.000e-04, eta: 14:35:38, time: 1.203, data_time: 0.064, memory: 16000, loss_rpn_cls: 0.0250, loss_rpn_bbox: 0.0335, loss_cls: 0.1718, acc: 93.7460, loss_bbox: 0.2185, loss_mask: 0.2256, loss: 0.6744 2023-11-15 21:11:18,960 - mmdet - INFO - Epoch [12][1450/1833] lr: 2.000e-04, eta: 14:34:42, time: 1.218, data_time: 0.077, memory: 16000, loss_rpn_cls: 0.0254, loss_rpn_bbox: 0.0337, loss_cls: 0.1716, acc: 93.7928, loss_bbox: 0.2149, loss_mask: 0.2265, loss: 0.6721 2023-11-15 21:12:18,701 - mmdet - INFO - Epoch [12][1500/1833] lr: 2.000e-04, eta: 14:33:44, time: 1.195, data_time: 0.071, memory: 16000, loss_rpn_cls: 0.0247, loss_rpn_bbox: 0.0321, loss_cls: 0.1725, acc: 93.7811, loss_bbox: 0.2132, loss_mask: 0.2256, loss: 0.6682 2023-11-15 21:13:18,670 - mmdet - INFO - Epoch [12][1550/1833] lr: 2.000e-04, eta: 14:32:47, time: 1.199, data_time: 0.061, memory: 16000, loss_rpn_cls: 0.0234, loss_rpn_bbox: 0.0328, loss_cls: 0.1680, acc: 93.9413, loss_bbox: 0.2129, loss_mask: 0.2250, loss: 0.6623 2023-11-15 21:14:18,106 - mmdet - INFO - Epoch [12][1600/1833] lr: 2.000e-04, eta: 14:31:48, time: 1.189, data_time: 0.063, memory: 16000, loss_rpn_cls: 0.0248, loss_rpn_bbox: 0.0330, loss_cls: 0.1711, acc: 93.8188, loss_bbox: 0.2151, loss_mask: 0.2271, loss: 0.6712 2023-11-15 21:15:18,648 - mmdet - INFO - Epoch [12][1650/1833] lr: 2.000e-04, eta: 14:30:52, time: 1.211, data_time: 0.061, memory: 16000, loss_rpn_cls: 0.0250, loss_rpn_bbox: 0.0331, loss_cls: 0.1702, acc: 93.8106, loss_bbox: 0.2127, loss_mask: 0.2269, loss: 0.6678 2023-11-15 21:16:17,964 - mmdet - INFO - Epoch [12][1700/1833] lr: 2.000e-04, eta: 14:29:53, time: 1.186, data_time: 0.066, memory: 16000, loss_rpn_cls: 0.0249, loss_rpn_bbox: 0.0331, loss_cls: 0.1709, acc: 93.8345, loss_bbox: 0.2127, loss_mask: 0.2252, loss: 0.6667 2023-11-15 21:17:18,055 - mmdet - INFO - Epoch [12][1750/1833] lr: 2.000e-04, eta: 14:28:56, time: 1.202, data_time: 0.072, memory: 16000, loss_rpn_cls: 0.0241, loss_rpn_bbox: 0.0320, loss_cls: 0.1688, acc: 93.9169, loss_bbox: 0.2105, loss_mask: 0.2252, loss: 0.6604 2023-11-15 21:18:19,120 - mmdet - INFO - Epoch [12][1800/1833] lr: 2.000e-04, eta: 14:28:01, time: 1.221, data_time: 0.072, memory: 16000, loss_rpn_cls: 0.0242, loss_rpn_bbox: 0.0325, loss_cls: 0.1685, acc: 93.9102, loss_bbox: 0.2110, loss_mask: 0.2254, loss: 0.6616 2023-11-15 21:19:00,483 - mmdet - INFO - Saving checkpoint at 12 epochs 2023-11-15 21:19:49,747 - mmdet - INFO - Evaluating bbox... 2023-11-15 21:20:18,814 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.480 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.703 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.532 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.321 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 ] = 0.616 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.607 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.607 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.607 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.447 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 ] = 0.751 2023-11-15 21:20:18,817 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.578 | bicycle | 0.365 | car | 0.496 | | motorcycle | 0.501 | airplane | 0.689 | bus | 0.695 | | train | 0.670 | truck | 0.410 | boat | 0.325 | | traffic light | 0.321 | fire hydrant | 0.728 | stop sign | 0.681 | | parking meter | 0.500 | bench | 0.299 | bird | 0.415 | | cat | 0.734 | dog | 0.686 | horse | 0.623 | | sheep | 0.595 | cow | 0.630 | elephant | 0.689 | | bear | 0.752 | zebra | 0.694 | giraffe | 0.701 | | backpack | 0.222 | umbrella | 0.454 | handbag | 0.228 | | tie | 0.375 | suitcase | 0.469 | frisbee | 0.700 | | skis | 0.284 | snowboard | 0.436 | sports ball | 0.480 | | kite | 0.472 | baseball bat | 0.418 | baseball glove | 0.436 | | skateboard | 0.578 | surfboard | 0.448 | tennis racket | 0.561 | | bottle | 0.457 | wine glass | 0.423 | cup | 0.511 | | fork | 0.458 | knife | 0.263 | spoon | 0.292 | | bowl | 0.474 | banana | 0.293 | apple | 0.264 | | sandwich | 0.488 | orange | 0.370 | broccoli | 0.278 | | carrot | 0.269 | hot dog | 0.469 | pizza | 0.547 | | donut | 0.550 | cake | 0.447 | chair | 0.368 | | couch | 0.475 | potted plant | 0.356 | bed | 0.463 | | dining table | 0.315 | toilet | 0.664 | tv | 0.623 | | laptop | 0.686 | mouse | 0.663 | remote | 0.416 | | keyboard | 0.547 | cell phone | 0.450 | microwave | 0.641 | | oven | 0.416 | toaster | 0.555 | sink | 0.440 | | refrigerator | 0.635 | book | 0.180 | clock | 0.515 | | vase | 0.414 | scissors | 0.410 | teddy bear | 0.541 | | hair drier | 0.156 | toothbrush | 0.298 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-15 21:20:18,817 - mmdet - INFO - Evaluating segm... 2023-11-15 21:20:53,828 - 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 ] = 0.676 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.467 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.236 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.470 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 ] = 0.555 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 ] = 0.383 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.596 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.710 2023-11-15 21:20:53,831 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.498 | bicycle | 0.234 | car | 0.451 | | motorcycle | 0.413 | airplane | 0.538 | bus | 0.686 | | train | 0.670 | truck | 0.394 | boat | 0.311 | | traffic light | 0.303 | fire hydrant | 0.697 | stop sign | 0.673 | | parking meter | 0.508 | bench | 0.234 | bird | 0.340 | | cat | 0.728 | dog | 0.639 | horse | 0.463 | | sheep | 0.531 | cow | 0.530 | elephant | 0.618 | | bear | 0.744 | zebra | 0.618 | giraffe | 0.552 | | backpack | 0.226 | umbrella | 0.515 | handbag | 0.215 | | tie | 0.347 | suitcase | 0.502 | frisbee | 0.673 | | skis | 0.060 | snowboard | 0.284 | sports ball | 0.466 | | kite | 0.337 | baseball bat | 0.305 | baseball glove | 0.461 | | skateboard | 0.385 | surfboard | 0.364 | tennis racket | 0.615 | | bottle | 0.430 | wine glass | 0.376 | cup | 0.510 | | fork | 0.242 | knife | 0.174 | spoon | 0.212 | | bowl | 0.445 | banana | 0.240 | apple | 0.258 | | sandwich | 0.500 | orange | 0.374 | broccoli | 0.266 | | carrot | 0.235 | hot dog | 0.399 | pizza | 0.530 | | donut | 0.556 | cake | 0.467 | chair | 0.269 | | couch | 0.408 | potted plant | 0.295 | bed | 0.370 | | dining table | 0.180 | toilet | 0.658 | tv | 0.652 | | laptop | 0.673 | mouse | 0.649 | remote | 0.373 | | keyboard | 0.534 | cell phone | 0.428 | microwave | 0.661 | | oven | 0.380 | toaster | 0.588 | sink | 0.416 | | refrigerator | 0.640 | book | 0.137 | clock | 0.510 | | vase | 0.411 | scissors | 0.298 | teddy bear | 0.518 | | hair drier | 0.135 | toothbrush | 0.222 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-15 21:20:54,320 - mmdet - INFO - The previous best checkpoint /mnt/petrelfs/lizhiqi/DINO/detection/work_dirs/mask_rcnn_flash_internimage_s_fpn_3x_coco_0.4/best_bbox_mAP_epoch_11.pth was removed 2023-11-15 21:20:56,556 - mmdet - INFO - Now best checkpoint is saved as best_bbox_mAP_epoch_12.pth. 2023-11-15 21:20:56,557 - mmdet - INFO - Best bbox_mAP is 0.4802 at 12 epoch. 2023-11-15 21:20:56,557 - mmdet - INFO - Exp name: mask_rcnn_flash_internimage_s_fpn_3x_coco_0.4.py 2023-11-15 21:20:56,557 - mmdet - INFO - Epoch(val) [12][625] bbox_mAP: 0.4802, bbox_mAP_50: 0.7033, bbox_mAP_75: 0.5322, bbox_mAP_s: 0.3215, bbox_mAP_m: 0.5221, bbox_mAP_l: 0.6162, bbox_mAP_copypaste: 0.4802 0.7033 0.5322 0.3215 0.5221 0.6162, segm_mAP: 0.4344, segm_mAP_50: 0.6758, segm_mAP_75: 0.4665, segm_mAP_s: 0.2360, segm_mAP_m: 0.4703, segm_mAP_l: 0.6190, segm_mAP_copypaste: 0.4344 0.6758 0.4665 0.2360 0.4703 0.6190 2023-11-15 21:22:01,631 - mmdet - INFO - Epoch [13][50/1833] lr: 2.000e-04, eta: 14:25:16, time: 1.301, data_time: 0.137, memory: 16000, loss_rpn_cls: 0.0244, loss_rpn_bbox: 0.0331, loss_cls: 0.1620, acc: 94.1223, loss_bbox: 0.2075, loss_mask: 0.2219, loss: 0.6489 2023-11-15 21:23:02,612 - mmdet - INFO - Epoch [13][100/1833] lr: 2.000e-04, eta: 14:24:21, time: 1.220, data_time: 0.089, memory: 16000, loss_rpn_cls: 0.0249, loss_rpn_bbox: 0.0323, loss_cls: 0.1618, acc: 94.1411, loss_bbox: 0.2062, loss_mask: 0.2233, loss: 0.6484 2023-11-15 21:24:04,034 - mmdet - INFO - Epoch [13][150/1833] lr: 2.000e-04, eta: 14:23:27, time: 1.228, data_time: 0.075, memory: 16000, loss_rpn_cls: 0.0240, loss_rpn_bbox: 0.0330, loss_cls: 0.1644, acc: 93.9654, loss_bbox: 0.2100, loss_mask: 0.2255, loss: 0.6569 2023-11-15 21:25:05,625 - mmdet - INFO - Epoch [13][200/1833] lr: 2.000e-04, eta: 14:22:33, time: 1.232, data_time: 0.077, memory: 16000, loss_rpn_cls: 0.0244, loss_rpn_bbox: 0.0330, loss_cls: 0.1665, acc: 93.9250, loss_bbox: 0.2118, loss_mask: 0.2224, loss: 0.6581 2023-11-15 21:26:06,063 - mmdet - INFO - Epoch [13][250/1833] lr: 2.000e-04, eta: 14:21:36, time: 1.209, data_time: 0.074, memory: 16000, loss_rpn_cls: 0.0243, loss_rpn_bbox: 0.0325, loss_cls: 0.1655, acc: 93.9778, loss_bbox: 0.2106, loss_mask: 0.2259, loss: 0.6586 2023-11-15 21:27:06,136 - mmdet - INFO - Epoch [13][300/1833] lr: 2.000e-04, eta: 14:20:39, time: 1.202, data_time: 0.083, memory: 16000, loss_rpn_cls: 0.0241, loss_rpn_bbox: 0.0328, loss_cls: 0.1644, acc: 94.0371, loss_bbox: 0.2094, loss_mask: 0.2229, loss: 0.6537 2023-11-15 21:28:06,993 - mmdet - INFO - Epoch [13][350/1833] lr: 2.000e-04, eta: 14:19:43, time: 1.217, data_time: 0.072, memory: 16000, loss_rpn_cls: 0.0241, loss_rpn_bbox: 0.0320, loss_cls: 0.1627, acc: 94.1152, loss_bbox: 0.2059, loss_mask: 0.2215, loss: 0.6463 2023-11-15 21:29:08,734 - mmdet - INFO - Epoch [13][400/1833] lr: 2.000e-04, eta: 14:18:49, time: 1.235, data_time: 0.078, memory: 16000, loss_rpn_cls: 0.0249, loss_rpn_bbox: 0.0333, loss_cls: 0.1671, acc: 93.9062, loss_bbox: 0.2116, loss_mask: 0.2271, loss: 0.6639 2023-11-15 21:30:10,762 - mmdet - INFO - Epoch [13][450/1833] lr: 2.000e-04, eta: 14:17:56, time: 1.241, data_time: 0.082, memory: 16000, loss_rpn_cls: 0.0244, loss_rpn_bbox: 0.0319, loss_cls: 0.1618, acc: 94.1099, loss_bbox: 0.2069, loss_mask: 0.2207, loss: 0.6457 2023-11-15 21:31:11,850 - mmdet - INFO - Epoch [13][500/1833] lr: 2.000e-04, eta: 14:17:01, time: 1.222, data_time: 0.078, memory: 16000, loss_rpn_cls: 0.0244, loss_rpn_bbox: 0.0328, loss_cls: 0.1658, acc: 93.9708, loss_bbox: 0.2104, loss_mask: 0.2234, loss: 0.6568 2023-11-15 21:32:12,512 - mmdet - INFO - Epoch [13][550/1833] lr: 2.000e-04, eta: 14:16:04, time: 1.213, data_time: 0.079, memory: 16000, loss_rpn_cls: 0.0251, loss_rpn_bbox: 0.0341, loss_cls: 0.1669, acc: 93.9240, loss_bbox: 0.2116, loss_mask: 0.2212, loss: 0.6589 2023-11-15 21:33:12,418 - mmdet - INFO - Epoch [13][600/1833] lr: 2.000e-04, eta: 14:15:07, time: 1.198, data_time: 0.074, memory: 16000, loss_rpn_cls: 0.0236, loss_rpn_bbox: 0.0331, loss_cls: 0.1666, acc: 94.0112, loss_bbox: 0.2108, loss_mask: 0.2238, loss: 0.6580 2023-11-15 21:34:13,543 - mmdet - INFO - Epoch [13][650/1833] lr: 2.000e-04, eta: 14:14:12, time: 1.223, data_time: 0.080, memory: 16000, loss_rpn_cls: 0.0252, loss_rpn_bbox: 0.0340, loss_cls: 0.1714, acc: 93.8127, loss_bbox: 0.2131, loss_mask: 0.2248, loss: 0.6686 2023-11-15 21:35:14,196 - mmdet - INFO - Epoch [13][700/1833] lr: 2.000e-04, eta: 14:13:15, time: 1.213, data_time: 0.079, memory: 16000, loss_rpn_cls: 0.0243, loss_rpn_bbox: 0.0330, loss_cls: 0.1664, acc: 93.9692, loss_bbox: 0.2096, loss_mask: 0.2224, loss: 0.6556 2023-11-15 21:36:16,316 - mmdet - INFO - Epoch [13][750/1833] lr: 2.000e-04, eta: 14:12:22, time: 1.242, data_time: 0.077, memory: 16000, loss_rpn_cls: 0.0232, loss_rpn_bbox: 0.0329, loss_cls: 0.1623, acc: 94.0767, loss_bbox: 0.2069, loss_mask: 0.2222, loss: 0.6475 2023-11-15 21:37:16,532 - mmdet - INFO - Epoch [13][800/1833] lr: 2.000e-04, eta: 14:11:25, time: 1.204, data_time: 0.076, memory: 16000, loss_rpn_cls: 0.0238, loss_rpn_bbox: 0.0334, loss_cls: 0.1701, acc: 93.8305, loss_bbox: 0.2126, loss_mask: 0.2243, loss: 0.6641 2023-11-15 21:38:16,505 - mmdet - INFO - Epoch [13][850/1833] lr: 2.000e-04, eta: 14:10:27, time: 1.199, data_time: 0.073, memory: 16000, loss_rpn_cls: 0.0247, loss_rpn_bbox: 0.0332, loss_cls: 0.1647, acc: 94.0275, loss_bbox: 0.2094, loss_mask: 0.2258, loss: 0.6577 2023-11-15 21:39:17,607 - mmdet - INFO - Epoch [13][900/1833] lr: 2.000e-04, eta: 14:09:32, time: 1.222, data_time: 0.073, memory: 16000, loss_rpn_cls: 0.0242, loss_rpn_bbox: 0.0331, loss_cls: 0.1664, acc: 93.9701, loss_bbox: 0.2097, loss_mask: 0.2243, loss: 0.6576 2023-11-15 21:40:18,839 - mmdet - INFO - Epoch [13][950/1833] lr: 2.000e-04, eta: 14:08:37, time: 1.225, data_time: 0.072, memory: 16000, loss_rpn_cls: 0.0229, loss_rpn_bbox: 0.0322, loss_cls: 0.1660, acc: 93.9540, loss_bbox: 0.2112, loss_mask: 0.2239, loss: 0.6561 2023-11-15 21:41:19,061 - mmdet - INFO - Epoch [13][1000/1833] lr: 2.000e-04, eta: 14:07:39, time: 1.204, data_time: 0.076, memory: 16000, loss_rpn_cls: 0.0245, loss_rpn_bbox: 0.0327, loss_cls: 0.1684, acc: 93.8999, loss_bbox: 0.2100, loss_mask: 0.2261, loss: 0.6618 2023-11-15 21:42:18,467 - mmdet - INFO - Epoch [13][1050/1833] lr: 2.000e-04, eta: 14:06:41, time: 1.188, data_time: 0.074, memory: 16000, loss_rpn_cls: 0.0246, loss_rpn_bbox: 0.0324, loss_cls: 0.1635, acc: 94.0545, loss_bbox: 0.2081, loss_mask: 0.2228, loss: 0.6513 2023-11-15 21:43:18,750 - mmdet - INFO - Epoch [13][1100/1833] lr: 2.000e-04, eta: 14:05:44, time: 1.206, data_time: 0.074, memory: 16000, loss_rpn_cls: 0.0236, loss_rpn_bbox: 0.0322, loss_cls: 0.1671, acc: 93.9644, loss_bbox: 0.2103, loss_mask: 0.2234, loss: 0.6566 2023-11-15 21:44:19,138 - mmdet - INFO - Epoch [13][1150/1833] lr: 2.000e-04, eta: 14:04:47, time: 1.208, data_time: 0.074, memory: 16000, loss_rpn_cls: 0.0245, loss_rpn_bbox: 0.0333, loss_cls: 0.1665, acc: 93.9745, loss_bbox: 0.2100, loss_mask: 0.2238, loss: 0.6581 2023-11-15 21:45:19,065 - mmdet - INFO - Epoch [13][1200/1833] lr: 2.000e-04, eta: 14:03:49, time: 1.199, data_time: 0.074, memory: 16000, loss_rpn_cls: 0.0237, loss_rpn_bbox: 0.0315, loss_cls: 0.1651, acc: 94.0394, loss_bbox: 0.2079, loss_mask: 0.2246, loss: 0.6528 2023-11-15 21:46:19,545 - mmdet - INFO - Epoch [13][1250/1833] lr: 2.000e-04, eta: 14:02:52, time: 1.210, data_time: 0.079, memory: 16000, loss_rpn_cls: 0.0246, loss_rpn_bbox: 0.0338, loss_cls: 0.1709, acc: 93.8378, loss_bbox: 0.2149, loss_mask: 0.2266, loss: 0.6708 2023-11-15 21:47:18,929 - mmdet - INFO - Epoch [13][1300/1833] lr: 2.000e-04, eta: 14:01:54, time: 1.188, data_time: 0.075, memory: 16000, loss_rpn_cls: 0.0252, loss_rpn_bbox: 0.0330, loss_cls: 0.1652, acc: 94.0486, loss_bbox: 0.2076, loss_mask: 0.2238, loss: 0.6548 2023-11-15 21:48:20,340 - mmdet - INFO - Epoch [13][1350/1833] lr: 2.000e-04, eta: 14:00:59, time: 1.228, data_time: 0.070, memory: 16000, loss_rpn_cls: 0.0245, loss_rpn_bbox: 0.0332, loss_cls: 0.1720, acc: 93.8010, loss_bbox: 0.2147, loss_mask: 0.2276, loss: 0.6719 2023-11-15 21:49:24,900 - mmdet - INFO - Epoch [13][1400/1833] lr: 2.000e-04, eta: 14:00:09, time: 1.291, data_time: 0.077, memory: 16000, loss_rpn_cls: 0.0244, loss_rpn_bbox: 0.0337, loss_cls: 0.1681, acc: 93.9202, loss_bbox: 0.2109, loss_mask: 0.2248, loss: 0.6620 2023-11-15 21:50:25,188 - mmdet - INFO - Epoch [13][1450/1833] lr: 2.000e-04, eta: 13:59:12, time: 1.206, data_time: 0.076, memory: 16000, loss_rpn_cls: 0.0247, loss_rpn_bbox: 0.0331, loss_cls: 0.1685, acc: 93.8969, loss_bbox: 0.2124, loss_mask: 0.2272, loss: 0.6659 2023-11-15 21:51:26,054 - mmdet - INFO - Epoch [13][1500/1833] lr: 2.000e-04, eta: 13:58:16, time: 1.217, data_time: 0.072, memory: 16000, loss_rpn_cls: 0.0243, loss_rpn_bbox: 0.0326, loss_cls: 0.1692, acc: 93.9033, loss_bbox: 0.2106, loss_mask: 0.2235, loss: 0.6602 2023-11-15 21:52:27,087 - mmdet - INFO - Epoch [13][1550/1833] lr: 2.000e-04, eta: 13:57:20, time: 1.221, data_time: 0.080, memory: 16000, loss_rpn_cls: 0.0251, loss_rpn_bbox: 0.0329, loss_cls: 0.1642, acc: 94.0665, loss_bbox: 0.2071, loss_mask: 0.2229, loss: 0.6521 2023-11-15 21:53:27,146 - mmdet - INFO - Epoch [13][1600/1833] lr: 2.000e-04, eta: 13:56:22, time: 1.201, data_time: 0.075, memory: 16000, loss_rpn_cls: 0.0252, loss_rpn_bbox: 0.0337, loss_cls: 0.1677, acc: 93.9120, loss_bbox: 0.2124, loss_mask: 0.2285, loss: 0.6675 2023-11-15 21:54:27,907 - mmdet - INFO - Epoch [13][1650/1833] lr: 2.000e-04, eta: 13:55:26, time: 1.215, data_time: 0.075, memory: 16000, loss_rpn_cls: 0.0239, loss_rpn_bbox: 0.0326, loss_cls: 0.1675, acc: 93.9762, loss_bbox: 0.2102, loss_mask: 0.2248, loss: 0.6591 2023-11-15 21:55:28,057 - mmdet - INFO - Epoch [13][1700/1833] lr: 2.000e-04, eta: 13:54:29, time: 1.203, data_time: 0.067, memory: 16000, loss_rpn_cls: 0.0242, loss_rpn_bbox: 0.0325, loss_cls: 0.1663, acc: 93.9158, loss_bbox: 0.2109, loss_mask: 0.2223, loss: 0.6562 2023-11-15 21:56:28,180 - mmdet - INFO - Epoch [13][1750/1833] lr: 2.000e-04, eta: 13:53:31, time: 1.202, data_time: 0.081, memory: 16000, loss_rpn_cls: 0.0244, loss_rpn_bbox: 0.0330, loss_cls: 0.1677, acc: 93.8928, loss_bbox: 0.2122, loss_mask: 0.2253, loss: 0.6626 2023-11-15 21:57:28,724 - mmdet - INFO - Epoch [13][1800/1833] lr: 2.000e-04, eta: 13:52:34, time: 1.211, data_time: 0.075, memory: 16000, loss_rpn_cls: 0.0243, loss_rpn_bbox: 0.0327, loss_cls: 0.1641, acc: 94.0818, loss_bbox: 0.2087, loss_mask: 0.2265, loss: 0.6563 2023-11-15 21:58:09,515 - mmdet - INFO - Saving checkpoint at 13 epochs 2023-11-15 21:58:56,626 - mmdet - INFO - Evaluating bbox... 2023-11-15 21:59:29,221 - 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 ] = 0.701 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.527 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.311 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.523 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.610 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 ] = 0.429 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.650 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.748 2023-11-15 21:59:29,223 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.582 | bicycle | 0.379 | car | 0.502 | | motorcycle | 0.490 | airplane | 0.714 | bus | 0.695 | | train | 0.676 | truck | 0.400 | boat | 0.331 | | traffic light | 0.302 | fire hydrant | 0.702 | stop sign | 0.657 | | parking meter | 0.533 | bench | 0.313 | bird | 0.427 | | cat | 0.721 | dog | 0.698 | horse | 0.639 | | sheep | 0.586 | cow | 0.626 | elephant | 0.671 | | bear | 0.731 | zebra | 0.684 | giraffe | 0.686 | | backpack | 0.216 | umbrella | 0.466 | handbag | 0.228 | | tie | 0.381 | suitcase | 0.452 | frisbee | 0.709 | | skis | 0.293 | snowboard | 0.429 | sports ball | 0.482 | | kite | 0.467 | baseball bat | 0.406 | baseball glove | 0.427 | | skateboard | 0.595 | surfboard | 0.454 | tennis racket | 0.556 | | bottle | 0.451 | wine glass | 0.428 | cup | 0.511 | | fork | 0.479 | knife | 0.290 | spoon | 0.281 | | bowl | 0.464 | banana | 0.285 | apple | 0.254 | | sandwich | 0.439 | orange | 0.335 | broccoli | 0.272 | | carrot | 0.280 | hot dog | 0.498 | pizza | 0.539 | | donut | 0.522 | cake | 0.437 | chair | 0.366 | | couch | 0.447 | potted plant | 0.335 | bed | 0.457 | | dining table | 0.312 | toilet | 0.676 | tv | 0.636 | | laptop | 0.689 | mouse | 0.643 | remote | 0.428 | | keyboard | 0.511 | cell phone | 0.453 | microwave | 0.617 | | oven | 0.413 | toaster | 0.478 | sink | 0.445 | | refrigerator | 0.634 | book | 0.196 | clock | 0.515 | | vase | 0.441 | scissors | 0.386 | teddy bear | 0.533 | | hair drier | 0.174 | toothbrush | 0.315 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-15 21:59:29,223 - mmdet - INFO - Evaluating segm... 2023-11-15 22:00:04,839 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.431 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.671 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.464 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.231 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 ] = 0.610 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.553 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.553 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.553 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 ] = 0.596 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.706 2023-11-15 22:00:04,841 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.508 | bicycle | 0.229 | car | 0.464 | | motorcycle | 0.400 | airplane | 0.556 | bus | 0.692 | | train | 0.661 | truck | 0.392 | boat | 0.295 | | traffic light | 0.295 | fire hydrant | 0.700 | stop sign | 0.657 | | parking meter | 0.556 | bench | 0.246 | bird | 0.349 | | cat | 0.729 | dog | 0.646 | horse | 0.476 | | sheep | 0.521 | cow | 0.538 | elephant | 0.619 | | bear | 0.734 | zebra | 0.592 | giraffe | 0.532 | | backpack | 0.211 | umbrella | 0.515 | handbag | 0.216 | | tie | 0.351 | suitcase | 0.495 | frisbee | 0.663 | | skis | 0.051 | snowboard | 0.274 | sports ball | 0.459 | | kite | 0.333 | baseball bat | 0.307 | baseball glove | 0.463 | | skateboard | 0.391 | surfboard | 0.379 | tennis racket | 0.608 | | bottle | 0.434 | wine glass | 0.396 | cup | 0.509 | | fork | 0.226 | knife | 0.195 | spoon | 0.196 | | bowl | 0.434 | banana | 0.229 | apple | 0.249 | | sandwich | 0.446 | orange | 0.341 | broccoli | 0.257 | | carrot | 0.242 | hot dog | 0.417 | pizza | 0.522 | | donut | 0.519 | cake | 0.446 | chair | 0.266 | | couch | 0.383 | potted plant | 0.282 | bed | 0.367 | | dining table | 0.192 | toilet | 0.668 | tv | 0.673 | | laptop | 0.662 | mouse | 0.641 | remote | 0.381 | | keyboard | 0.513 | cell phone | 0.427 | microwave | 0.654 | | oven | 0.383 | toaster | 0.512 | sink | 0.413 | | refrigerator | 0.641 | book | 0.154 | clock | 0.528 | | vase | 0.428 | scissors | 0.281 | teddy bear | 0.516 | | hair drier | 0.156 | toothbrush | 0.209 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-15 22:00:05,245 - mmdet - INFO - Exp name: mask_rcnn_flash_internimage_s_fpn_3x_coco_0.4.py 2023-11-15 22:00:05,246 - mmdet - INFO - Epoch(val) [13][625] bbox_mAP: 0.4771, bbox_mAP_50: 0.7011, bbox_mAP_75: 0.5270, bbox_mAP_s: 0.3110, bbox_mAP_m: 0.5231, bbox_mAP_l: 0.6102, bbox_mAP_copypaste: 0.4771 0.7011 0.5270 0.3110 0.5231 0.6102, segm_mAP: 0.4311, segm_mAP_50: 0.6706, segm_mAP_75: 0.4643, segm_mAP_s: 0.2312, segm_mAP_m: 0.4687, segm_mAP_l: 0.6101, segm_mAP_copypaste: 0.4311 0.6706 0.4643 0.2312 0.4687 0.6101 2023-11-15 22:01:08,886 - mmdet - INFO - Epoch [14][50/1833] lr: 2.000e-04, eta: 13:49:55, time: 1.272, data_time: 0.128, memory: 16000, loss_rpn_cls: 0.0247, loss_rpn_bbox: 0.0337, loss_cls: 0.1656, acc: 93.9565, loss_bbox: 0.2114, loss_mask: 0.2236, loss: 0.6589 2023-11-15 22:02:08,457 - mmdet - INFO - Epoch [14][100/1833] lr: 2.000e-04, eta: 13:48:57, time: 1.191, data_time: 0.069, memory: 16000, loss_rpn_cls: 0.0235, loss_rpn_bbox: 0.0319, loss_cls: 0.1614, acc: 94.0880, loss_bbox: 0.2060, loss_mask: 0.2219, loss: 0.6447 2023-11-15 22:03:08,639 - mmdet - INFO - Epoch [14][150/1833] lr: 2.000e-04, eta: 13:47:59, time: 1.204, data_time: 0.061, memory: 16000, loss_rpn_cls: 0.0226, loss_rpn_bbox: 0.0317, loss_cls: 0.1590, acc: 94.1570, loss_bbox: 0.2043, loss_mask: 0.2200, loss: 0.6377 2023-11-15 22:04:09,490 - mmdet - INFO - Epoch [14][200/1833] lr: 2.000e-04, eta: 13:47:03, time: 1.217, data_time: 0.068, memory: 16000, loss_rpn_cls: 0.0232, loss_rpn_bbox: 0.0326, loss_cls: 0.1595, acc: 94.1494, loss_bbox: 0.2056, loss_mask: 0.2220, loss: 0.6428 2023-11-15 22:05:09,693 - mmdet - INFO - Epoch [14][250/1833] lr: 2.000e-04, eta: 13:46:06, time: 1.204, data_time: 0.061, memory: 16000, loss_rpn_cls: 0.0239, loss_rpn_bbox: 0.0333, loss_cls: 0.1643, acc: 94.0543, loss_bbox: 0.2095, loss_mask: 0.2238, loss: 0.6548 2023-11-15 22:06:11,235 - mmdet - INFO - Epoch [14][300/1833] lr: 2.000e-04, eta: 13:45:11, time: 1.231, data_time: 0.070, memory: 16000, loss_rpn_cls: 0.0243, loss_rpn_bbox: 0.0346, loss_cls: 0.1672, acc: 93.8491, loss_bbox: 0.2130, loss_mask: 0.2264, loss: 0.6654 2023-11-15 22:07:13,323 - mmdet - INFO - Epoch [14][350/1833] lr: 2.000e-04, eta: 13:44:17, time: 1.242, data_time: 0.068, memory: 16000, loss_rpn_cls: 0.0232, loss_rpn_bbox: 0.0330, loss_cls: 0.1651, acc: 94.0048, loss_bbox: 0.2101, loss_mask: 0.2254, loss: 0.6569 2023-11-15 22:08:13,415 - mmdet - INFO - Epoch [14][400/1833] lr: 2.000e-04, eta: 13:43:19, time: 1.202, data_time: 0.066, memory: 16000, loss_rpn_cls: 0.0225, loss_rpn_bbox: 0.0328, loss_cls: 0.1604, acc: 94.1497, loss_bbox: 0.2066, loss_mask: 0.2246, loss: 0.6469 2023-11-15 22:09:13,501 - mmdet - INFO - Epoch [14][450/1833] lr: 2.000e-04, eta: 13:42:22, time: 1.202, data_time: 0.062, memory: 16000, loss_rpn_cls: 0.0234, loss_rpn_bbox: 0.0322, loss_cls: 0.1625, acc: 94.0691, loss_bbox: 0.2085, loss_mask: 0.2211, loss: 0.6477 2023-11-15 22:10:13,495 - mmdet - INFO - Epoch [14][500/1833] lr: 2.000e-04, eta: 13:41:24, time: 1.200, data_time: 0.064, memory: 16000, loss_rpn_cls: 0.0229, loss_rpn_bbox: 0.0320, loss_cls: 0.1637, acc: 94.0940, loss_bbox: 0.2102, loss_mask: 0.2247, loss: 0.6533 2023-11-15 22:11:13,588 - mmdet - INFO - Epoch [14][550/1833] lr: 2.000e-04, eta: 13:40:27, time: 1.202, data_time: 0.061, memory: 16000, loss_rpn_cls: 0.0239, loss_rpn_bbox: 0.0325, loss_cls: 0.1648, acc: 94.0337, loss_bbox: 0.2090, loss_mask: 0.2239, loss: 0.6540 2023-11-15 22:12:13,885 - mmdet - INFO - Epoch [14][600/1833] lr: 2.000e-04, eta: 13:39:29, time: 1.206, data_time: 0.063, memory: 16000, loss_rpn_cls: 0.0228, loss_rpn_bbox: 0.0333, loss_cls: 0.1665, acc: 93.9628, loss_bbox: 0.2118, loss_mask: 0.2238, loss: 0.6582 2023-11-15 22:13:14,203 - mmdet - INFO - Epoch [14][650/1833] lr: 2.000e-04, eta: 13:38:32, time: 1.206, data_time: 0.063, memory: 16000, loss_rpn_cls: 0.0233, loss_rpn_bbox: 0.0327, loss_cls: 0.1621, acc: 94.0568, loss_bbox: 0.2082, loss_mask: 0.2244, loss: 0.6507 2023-11-15 22:14:14,579 - mmdet - INFO - Epoch [14][700/1833] lr: 2.000e-04, eta: 13:37:35, time: 1.208, data_time: 0.067, memory: 16000, loss_rpn_cls: 0.0240, loss_rpn_bbox: 0.0326, loss_cls: 0.1651, acc: 93.9898, loss_bbox: 0.2075, loss_mask: 0.2237, loss: 0.6529 2023-11-15 22:15:15,100 - mmdet - INFO - Epoch [14][750/1833] lr: 2.000e-04, eta: 13:36:38, time: 1.210, data_time: 0.062, memory: 16000, loss_rpn_cls: 0.0234, loss_rpn_bbox: 0.0324, loss_cls: 0.1624, acc: 94.1277, loss_bbox: 0.2055, loss_mask: 0.2230, loss: 0.6466 2023-11-15 22:16:14,782 - mmdet - INFO - Epoch [14][800/1833] lr: 2.000e-04, eta: 13:35:40, time: 1.194, data_time: 0.063, memory: 16000, loss_rpn_cls: 0.0238, loss_rpn_bbox: 0.0323, loss_cls: 0.1648, acc: 93.9763, loss_bbox: 0.2098, loss_mask: 0.2211, loss: 0.6518 2023-11-15 22:17:14,080 - mmdet - INFO - Epoch [14][850/1833] lr: 2.000e-04, eta: 13:34:41, time: 1.186, data_time: 0.068, memory: 16000, loss_rpn_cls: 0.0245, loss_rpn_bbox: 0.0321, loss_cls: 0.1614, acc: 94.1186, loss_bbox: 0.2066, loss_mask: 0.2231, loss: 0.6476 2023-11-15 22:18:14,750 - mmdet - INFO - Epoch [14][900/1833] lr: 2.000e-04, eta: 13:33:44, time: 1.213, data_time: 0.061, memory: 16000, loss_rpn_cls: 0.0243, loss_rpn_bbox: 0.0323, loss_cls: 0.1631, acc: 94.0842, loss_bbox: 0.2069, loss_mask: 0.2218, loss: 0.6484 2023-11-15 22:19:14,175 - mmdet - INFO - Epoch [14][950/1833] lr: 2.000e-04, eta: 13:32:45, time: 1.189, data_time: 0.072, memory: 16000, loss_rpn_cls: 0.0230, loss_rpn_bbox: 0.0319, loss_cls: 0.1648, acc: 93.9697, loss_bbox: 0.2087, loss_mask: 0.2251, loss: 0.6534 2023-11-15 22:20:13,732 - mmdet - INFO - Epoch [14][1000/1833] lr: 2.000e-04, eta: 13:31:47, time: 1.191, data_time: 0.061, memory: 16000, loss_rpn_cls: 0.0250, loss_rpn_bbox: 0.0319, loss_cls: 0.1611, acc: 94.1448, loss_bbox: 0.2055, loss_mask: 0.2222, loss: 0.6457 2023-11-15 22:21:14,216 - mmdet - INFO - Epoch [14][1050/1833] lr: 2.000e-04, eta: 13:30:50, time: 1.210, data_time: 0.061, memory: 16000, loss_rpn_cls: 0.0242, loss_rpn_bbox: 0.0321, loss_cls: 0.1612, acc: 94.1257, loss_bbox: 0.2042, loss_mask: 0.2203, loss: 0.6419 2023-11-15 22:22:13,689 - mmdet - INFO - Epoch [14][1100/1833] lr: 2.000e-04, eta: 13:29:51, time: 1.189, data_time: 0.069, memory: 16000, loss_rpn_cls: 0.0253, loss_rpn_bbox: 0.0345, loss_cls: 0.1687, acc: 93.8470, loss_bbox: 0.2137, loss_mask: 0.2242, loss: 0.6665 2023-11-15 22:23:14,153 - mmdet - INFO - Epoch [14][1150/1833] lr: 2.000e-04, eta: 13:28:54, time: 1.209, data_time: 0.057, memory: 16000, loss_rpn_cls: 0.0238, loss_rpn_bbox: 0.0332, loss_cls: 0.1632, acc: 94.0205, loss_bbox: 0.2067, loss_mask: 0.2236, loss: 0.6506 2023-11-15 22:24:15,739 - mmdet - INFO - Epoch [14][1200/1833] lr: 2.000e-04, eta: 13:27:59, time: 1.232, data_time: 0.071, memory: 16000, loss_rpn_cls: 0.0243, loss_rpn_bbox: 0.0329, loss_cls: 0.1658, acc: 93.9442, loss_bbox: 0.2119, loss_mask: 0.2238, loss: 0.6588 2023-11-15 22:25:15,383 - mmdet - INFO - Epoch [14][1250/1833] lr: 2.000e-04, eta: 13:27:01, time: 1.193, data_time: 0.058, memory: 16000, loss_rpn_cls: 0.0233, loss_rpn_bbox: 0.0320, loss_cls: 0.1648, acc: 94.0660, loss_bbox: 0.2075, loss_mask: 0.2211, loss: 0.6488 2023-11-15 22:26:14,244 - mmdet - INFO - Epoch [14][1300/1833] lr: 2.000e-04, eta: 13:26:01, time: 1.177, data_time: 0.069, memory: 16000, loss_rpn_cls: 0.0245, loss_rpn_bbox: 0.0336, loss_cls: 0.1650, acc: 93.9672, loss_bbox: 0.2105, loss_mask: 0.2220, loss: 0.6556 2023-11-15 22:27:15,030 - mmdet - INFO - Epoch [14][1350/1833] lr: 2.000e-04, eta: 13:25:04, time: 1.216, data_time: 0.071, memory: 16000, loss_rpn_cls: 0.0232, loss_rpn_bbox: 0.0323, loss_cls: 0.1627, acc: 94.0767, loss_bbox: 0.2078, loss_mask: 0.2216, loss: 0.6475 2023-11-15 22:28:14,916 - mmdet - INFO - Epoch [14][1400/1833] lr: 2.000e-04, eta: 13:24:06, time: 1.198, data_time: 0.059, memory: 16000, loss_rpn_cls: 0.0234, loss_rpn_bbox: 0.0323, loss_cls: 0.1636, acc: 94.0058, loss_bbox: 0.2085, loss_mask: 0.2244, loss: 0.6522 2023-11-15 22:29:14,507 - mmdet - INFO - Epoch [14][1450/1833] lr: 2.000e-04, eta: 13:23:08, time: 1.192, data_time: 0.072, memory: 16000, loss_rpn_cls: 0.0231, loss_rpn_bbox: 0.0319, loss_cls: 0.1642, acc: 94.0488, loss_bbox: 0.2066, loss_mask: 0.2216, loss: 0.6473 2023-11-15 22:30:14,769 - mmdet - INFO - Epoch [14][1500/1833] lr: 2.000e-04, eta: 13:22:10, time: 1.205, data_time: 0.066, memory: 16000, loss_rpn_cls: 0.0234, loss_rpn_bbox: 0.0325, loss_cls: 0.1634, acc: 94.0336, loss_bbox: 0.2064, loss_mask: 0.2212, loss: 0.6468 2023-11-15 22:31:14,127 - mmdet - INFO - Epoch [14][1550/1833] lr: 2.000e-04, eta: 13:21:11, time: 1.187, data_time: 0.068, memory: 16000, loss_rpn_cls: 0.0246, loss_rpn_bbox: 0.0324, loss_cls: 0.1630, acc: 94.1040, loss_bbox: 0.2063, loss_mask: 0.2231, loss: 0.6493 2023-11-15 22:32:13,624 - mmdet - INFO - Epoch [14][1600/1833] lr: 2.000e-04, eta: 13:20:13, time: 1.190, data_time: 0.067, memory: 16000, loss_rpn_cls: 0.0240, loss_rpn_bbox: 0.0328, loss_cls: 0.1632, acc: 94.0936, loss_bbox: 0.2052, loss_mask: 0.2194, loss: 0.6446 2023-11-15 22:33:15,164 - mmdet - INFO - Epoch [14][1650/1833] lr: 2.000e-04, eta: 13:19:17, time: 1.231, data_time: 0.067, memory: 16000, loss_rpn_cls: 0.0252, loss_rpn_bbox: 0.0341, loss_cls: 0.1681, acc: 93.8852, loss_bbox: 0.2141, loss_mask: 0.2260, loss: 0.6675 2023-11-15 22:34:14,871 - mmdet - INFO - Epoch [14][1700/1833] lr: 2.000e-04, eta: 13:18:19, time: 1.194, data_time: 0.066, memory: 16000, loss_rpn_cls: 0.0244, loss_rpn_bbox: 0.0336, loss_cls: 0.1693, acc: 93.8546, loss_bbox: 0.2145, loss_mask: 0.2273, loss: 0.6690 2023-11-15 22:35:14,924 - mmdet - INFO - Epoch [14][1750/1833] lr: 2.000e-04, eta: 13:17:21, time: 1.201, data_time: 0.073, memory: 16000, loss_rpn_cls: 0.0245, loss_rpn_bbox: 0.0323, loss_cls: 0.1680, acc: 93.9566, loss_bbox: 0.2093, loss_mask: 0.2233, loss: 0.6575 2023-11-15 22:36:15,092 - mmdet - INFO - Epoch [14][1800/1833] lr: 2.000e-04, eta: 13:16:23, time: 1.203, data_time: 0.067, memory: 16000, loss_rpn_cls: 0.0237, loss_rpn_bbox: 0.0322, loss_cls: 0.1653, acc: 93.9720, loss_bbox: 0.2104, loss_mask: 0.2239, loss: 0.6555 2023-11-15 22:36:56,989 - mmdet - INFO - Saving checkpoint at 14 epochs 2023-11-15 22:37:43,260 - mmdet - INFO - Evaluating bbox... 2023-11-15 22:38:14,856 - 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 ] = 0.700 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.529 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.313 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.524 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.608 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 ] = 0.431 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 ] = 0.746 2023-11-15 22:38:14,858 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.576 | bicycle | 0.387 | car | 0.493 | | motorcycle | 0.489 | airplane | 0.690 | bus | 0.692 | | train | 0.654 | truck | 0.419 | boat | 0.328 | | traffic light | 0.316 | fire hydrant | 0.712 | stop sign | 0.682 | | parking meter | 0.527 | bench | 0.302 | bird | 0.409 | | cat | 0.741 | dog | 0.669 | horse | 0.629 | | sheep | 0.577 | cow | 0.622 | elephant | 0.681 | | bear | 0.744 | zebra | 0.676 | giraffe | 0.696 | | backpack | 0.213 | umbrella | 0.451 | handbag | 0.234 | | tie | 0.386 | suitcase | 0.475 | frisbee | 0.698 | | skis | 0.292 | snowboard | 0.461 | sports ball | 0.472 | | kite | 0.467 | baseball bat | 0.430 | baseball glove | 0.446 | | skateboard | 0.590 | surfboard | 0.475 | tennis racket | 0.553 | | bottle | 0.456 | wine glass | 0.419 | cup | 0.509 | | fork | 0.475 | knife | 0.277 | spoon | 0.285 | | bowl | 0.477 | banana | 0.281 | apple | 0.250 | | sandwich | 0.443 | orange | 0.345 | broccoli | 0.265 | | carrot | 0.262 | hot dog | 0.484 | pizza | 0.552 | | donut | 0.537 | cake | 0.436 | chair | 0.359 | | couch | 0.464 | potted plant | 0.341 | bed | 0.461 | | dining table | 0.325 | toilet | 0.668 | tv | 0.635 | | laptop | 0.675 | mouse | 0.640 | remote | 0.427 | | keyboard | 0.547 | cell phone | 0.426 | microwave | 0.631 | | oven | 0.397 | toaster | 0.453 | sink | 0.428 | | refrigerator | 0.647 | book | 0.195 | clock | 0.514 | | vase | 0.420 | scissors | 0.458 | teddy bear | 0.542 | | hair drier | 0.156 | toothbrush | 0.308 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-15 22:38:14,858 - mmdet - INFO - Evaluating segm... 2023-11-15 22:38:49,871 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.427 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.669 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.456 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.229 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.464 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 ] = 0.553 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.553 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.553 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.374 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.596 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.702 2023-11-15 22:38:49,874 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.498 | bicycle | 0.225 | car | 0.443 | | motorcycle | 0.404 | airplane | 0.512 | bus | 0.680 | | train | 0.648 | truck | 0.401 | boat | 0.297 | | traffic light | 0.300 | fire hydrant | 0.688 | stop sign | 0.655 | | parking meter | 0.542 | bench | 0.230 | bird | 0.340 | | cat | 0.725 | dog | 0.644 | horse | 0.457 | | sheep | 0.488 | cow | 0.510 | elephant | 0.630 | | bear | 0.730 | zebra | 0.586 | giraffe | 0.541 | | backpack | 0.219 | umbrella | 0.517 | handbag | 0.217 | | tie | 0.354 | suitcase | 0.489 | frisbee | 0.673 | | skis | 0.045 | snowboard | 0.269 | sports ball | 0.465 | | kite | 0.323 | baseball bat | 0.316 | baseball glove | 0.454 | | skateboard | 0.380 | surfboard | 0.371 | tennis racket | 0.612 | | bottle | 0.434 | wine glass | 0.377 | cup | 0.507 | | fork | 0.220 | knife | 0.196 | spoon | 0.197 | | bowl | 0.438 | banana | 0.236 | apple | 0.247 | | sandwich | 0.465 | orange | 0.342 | broccoli | 0.241 | | carrot | 0.231 | hot dog | 0.394 | pizza | 0.536 | | donut | 0.535 | cake | 0.442 | chair | 0.255 | | couch | 0.383 | potted plant | 0.279 | bed | 0.377 | | dining table | 0.194 | toilet | 0.643 | tv | 0.661 | | laptop | 0.667 | mouse | 0.629 | remote | 0.380 | | keyboard | 0.534 | cell phone | 0.409 | microwave | 0.632 | | oven | 0.369 | toaster | 0.515 | sink | 0.406 | | refrigerator | 0.657 | book | 0.140 | clock | 0.515 | | vase | 0.419 | scissors | 0.321 | teddy bear | 0.523 | | hair drier | 0.132 | toothbrush | 0.213 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-15 22:38:50,320 - mmdet - INFO - Exp name: mask_rcnn_flash_internimage_s_fpn_3x_coco_0.4.py 2023-11-15 22:38:50,320 - mmdet - INFO - Epoch(val) [14][625] bbox_mAP: 0.4778, bbox_mAP_50: 0.7001, bbox_mAP_75: 0.5288, bbox_mAP_s: 0.3128, bbox_mAP_m: 0.5239, bbox_mAP_l: 0.6083, bbox_mAP_copypaste: 0.4778 0.7001 0.5288 0.3128 0.5239 0.6083, segm_mAP: 0.4271, segm_mAP_50: 0.6691, segm_mAP_75: 0.4564, segm_mAP_s: 0.2290, segm_mAP_m: 0.4639, segm_mAP_l: 0.6112, segm_mAP_copypaste: 0.4271 0.6691 0.4564 0.2290 0.4639 0.6112 2023-11-15 22:39:54,355 - mmdet - INFO - Epoch [15][50/1833] lr: 2.000e-04, eta: 13:13:51, time: 1.280, data_time: 0.131, memory: 16000, loss_rpn_cls: 0.0230, loss_rpn_bbox: 0.0317, loss_cls: 0.1565, acc: 94.2693, loss_bbox: 0.2018, loss_mask: 0.2188, loss: 0.6319 2023-11-15 22:40:54,560 - mmdet - INFO - Epoch [15][100/1833] lr: 2.000e-04, eta: 13:12:54, time: 1.204, data_time: 0.069, memory: 16000, loss_rpn_cls: 0.0240, loss_rpn_bbox: 0.0326, loss_cls: 0.1634, acc: 94.0465, loss_bbox: 0.2095, loss_mask: 0.2217, loss: 0.6511 2023-11-15 22:41:55,391 - mmdet - INFO - Epoch [15][150/1833] lr: 2.000e-04, eta: 13:11:57, time: 1.217, data_time: 0.071, memory: 16000, loss_rpn_cls: 0.0236, loss_rpn_bbox: 0.0321, loss_cls: 0.1611, acc: 94.1111, loss_bbox: 0.2055, loss_mask: 0.2229, loss: 0.6451 2023-11-15 22:42:57,483 - mmdet - INFO - Epoch [15][200/1833] lr: 2.000e-04, eta: 13:11:03, time: 1.242, data_time: 0.075, memory: 16000, loss_rpn_cls: 0.0236, loss_rpn_bbox: 0.0331, loss_cls: 0.1583, acc: 94.1940, loss_bbox: 0.2052, loss_mask: 0.2208, loss: 0.6411 2023-11-15 22:43:57,822 - mmdet - INFO - Epoch [15][250/1833] lr: 2.000e-04, eta: 13:10:06, time: 1.207, data_time: 0.071, memory: 16000, loss_rpn_cls: 0.0233, loss_rpn_bbox: 0.0323, loss_cls: 0.1570, acc: 94.2116, loss_bbox: 0.2025, loss_mask: 0.2178, loss: 0.6329 2023-11-15 22:44:58,689 - mmdet - INFO - Epoch [15][300/1833] lr: 2.000e-04, eta: 13:09:09, time: 1.217, data_time: 0.073, memory: 16000, loss_rpn_cls: 0.0228, loss_rpn_bbox: 0.0324, loss_cls: 0.1606, acc: 94.1206, loss_bbox: 0.2073, loss_mask: 0.2194, loss: 0.6425 2023-11-15 22:45:58,591 - mmdet - INFO - Epoch [15][350/1833] lr: 2.000e-04, eta: 13:08:11, time: 1.198, data_time: 0.066, memory: 16000, loss_rpn_cls: 0.0238, loss_rpn_bbox: 0.0323, loss_cls: 0.1601, acc: 94.1441, loss_bbox: 0.2054, loss_mask: 0.2207, loss: 0.6423 2023-11-15 22:46:58,847 - mmdet - INFO - Epoch [15][400/1833] lr: 2.000e-04, eta: 13:07:14, time: 1.205, data_time: 0.074, memory: 16000, loss_rpn_cls: 0.0223, loss_rpn_bbox: 0.0315, loss_cls: 0.1562, acc: 94.3407, loss_bbox: 0.2019, loss_mask: 0.2243, loss: 0.6361 2023-11-15 22:47:59,897 - mmdet - INFO - Epoch [15][450/1833] lr: 2.000e-04, eta: 13:06:17, time: 1.221, data_time: 0.066, memory: 16000, loss_rpn_cls: 0.0232, loss_rpn_bbox: 0.0320, loss_cls: 0.1609, acc: 94.1168, loss_bbox: 0.2052, loss_mask: 0.2224, loss: 0.6437 2023-11-15 22:48:59,613 - mmdet - INFO - Epoch [15][500/1833] lr: 2.000e-04, eta: 13:05:19, time: 1.194, data_time: 0.065, memory: 16000, loss_rpn_cls: 0.0226, loss_rpn_bbox: 0.0322, loss_cls: 0.1610, acc: 94.1115, loss_bbox: 0.2072, loss_mask: 0.2189, loss: 0.6418 2023-11-15 22:49:59,071 - mmdet - INFO - Epoch [15][550/1833] lr: 2.000e-04, eta: 13:04:20, time: 1.189, data_time: 0.069, memory: 16000, loss_rpn_cls: 0.0230, loss_rpn_bbox: 0.0314, loss_cls: 0.1617, acc: 94.1176, loss_bbox: 0.2046, loss_mask: 0.2188, loss: 0.6396 2023-11-15 22:50:58,684 - mmdet - INFO - Epoch [15][600/1833] lr: 2.000e-04, eta: 13:03:22, time: 1.192, data_time: 0.073, memory: 16000, loss_rpn_cls: 0.0239, loss_rpn_bbox: 0.0316, loss_cls: 0.1598, acc: 94.1468, loss_bbox: 0.2056, loss_mask: 0.2219, loss: 0.6428 2023-11-15 22:51:58,140 - mmdet - INFO - Epoch [15][650/1833] lr: 2.000e-04, eta: 13:02:23, time: 1.189, data_time: 0.064, memory: 16000, loss_rpn_cls: 0.0232, loss_rpn_bbox: 0.0312, loss_cls: 0.1610, acc: 94.0645, loss_bbox: 0.2079, loss_mask: 0.2234, loss: 0.6466 2023-11-15 22:52:58,444 - mmdet - INFO - Epoch [15][700/1833] lr: 2.000e-04, eta: 13:01:26, time: 1.206, data_time: 0.071, memory: 16000, loss_rpn_cls: 0.0229, loss_rpn_bbox: 0.0315, loss_cls: 0.1604, acc: 94.1379, loss_bbox: 0.2041, loss_mask: 0.2178, loss: 0.6367 2023-11-15 22:53:59,484 - mmdet - INFO - Epoch [15][750/1833] lr: 2.000e-04, eta: 13:00:29, time: 1.221, data_time: 0.067, memory: 16000, loss_rpn_cls: 0.0227, loss_rpn_bbox: 0.0334, loss_cls: 0.1661, acc: 93.9327, loss_bbox: 0.2104, loss_mask: 0.2234, loss: 0.6559 2023-11-15 22:54:59,647 - mmdet - INFO - Epoch [15][800/1833] lr: 2.000e-04, eta: 12:59:32, time: 1.203, data_time: 0.063, memory: 16000, loss_rpn_cls: 0.0243, loss_rpn_bbox: 0.0338, loss_cls: 0.1650, acc: 94.0043, loss_bbox: 0.2072, loss_mask: 0.2210, loss: 0.6512 2023-11-15 22:55:59,995 - mmdet - INFO - Epoch [15][850/1833] lr: 2.000e-04, eta: 12:58:34, time: 1.207, data_time: 0.075, memory: 16000, loss_rpn_cls: 0.0231, loss_rpn_bbox: 0.0323, loss_cls: 0.1660, acc: 93.9252, loss_bbox: 0.2092, loss_mask: 0.2227, loss: 0.6533 2023-11-15 22:56:59,852 - mmdet - INFO - Epoch [15][900/1833] lr: 2.000e-04, eta: 12:57:36, time: 1.197, data_time: 0.075, memory: 16000, loss_rpn_cls: 0.0240, loss_rpn_bbox: 0.0330, loss_cls: 0.1641, acc: 94.0165, loss_bbox: 0.2093, loss_mask: 0.2229, loss: 0.6533 2023-11-15 22:58:00,442 - mmdet - INFO - Epoch [15][950/1833] lr: 2.000e-04, eta: 12:56:39, time: 1.212, data_time: 0.067, memory: 16000, loss_rpn_cls: 0.0233, loss_rpn_bbox: 0.0331, loss_cls: 0.1644, acc: 93.9807, loss_bbox: 0.2096, loss_mask: 0.2223, loss: 0.6528 2023-11-15 22:59:00,516 - mmdet - INFO - Epoch [15][1000/1833] lr: 2.000e-04, eta: 12:55:41, time: 1.201, data_time: 0.066, memory: 16000, loss_rpn_cls: 0.0234, loss_rpn_bbox: 0.0325, loss_cls: 0.1651, acc: 93.9766, loss_bbox: 0.2104, loss_mask: 0.2220, loss: 0.6533 2023-11-15 23:00:00,286 - mmdet - INFO - Epoch [15][1050/1833] lr: 2.000e-04, eta: 12:54:43, time: 1.195, data_time: 0.069, memory: 16000, loss_rpn_cls: 0.0223, loss_rpn_bbox: 0.0317, loss_cls: 0.1611, acc: 94.1409, loss_bbox: 0.2043, loss_mask: 0.2197, loss: 0.6390 2023-11-15 23:00:59,694 - mmdet - INFO - Epoch [15][1100/1833] lr: 2.000e-04, eta: 12:53:44, time: 1.188, data_time: 0.068, memory: 16000, loss_rpn_cls: 0.0237, loss_rpn_bbox: 0.0333, loss_cls: 0.1690, acc: 93.9001, loss_bbox: 0.2099, loss_mask: 0.2225, loss: 0.6584 2023-11-15 23:01:58,683 - mmdet - INFO - Epoch [15][1150/1833] lr: 2.000e-04, eta: 12:52:45, time: 1.180, data_time: 0.073, memory: 16000, loss_rpn_cls: 0.0243, loss_rpn_bbox: 0.0328, loss_cls: 0.1661, acc: 94.0331, loss_bbox: 0.2093, loss_mask: 0.2226, loss: 0.6551 2023-11-15 23:02:58,901 - mmdet - INFO - Epoch [15][1200/1833] lr: 2.000e-04, eta: 12:51:47, time: 1.204, data_time: 0.063, memory: 16000, loss_rpn_cls: 0.0229, loss_rpn_bbox: 0.0328, loss_cls: 0.1607, acc: 94.1681, loss_bbox: 0.2051, loss_mask: 0.2217, loss: 0.6433 2023-11-15 23:03:59,873 - mmdet - INFO - Epoch [15][1250/1833] lr: 2.000e-04, eta: 12:50:50, time: 1.219, data_time: 0.068, memory: 16000, loss_rpn_cls: 0.0245, loss_rpn_bbox: 0.0338, loss_cls: 0.1670, acc: 93.9093, loss_bbox: 0.2116, loss_mask: 0.2222, loss: 0.6591 2023-11-15 23:04:58,962 - mmdet - INFO - Epoch [15][1300/1833] lr: 2.000e-04, eta: 12:49:51, time: 1.182, data_time: 0.068, memory: 16000, loss_rpn_cls: 0.0226, loss_rpn_bbox: 0.0313, loss_cls: 0.1606, acc: 94.1791, loss_bbox: 0.2038, loss_mask: 0.2215, loss: 0.6397 2023-11-15 23:05:59,435 - mmdet - INFO - Epoch [15][1350/1833] lr: 2.000e-04, eta: 12:48:54, time: 1.209, data_time: 0.076, memory: 16000, loss_rpn_cls: 0.0246, loss_rpn_bbox: 0.0325, loss_cls: 0.1620, acc: 94.1336, loss_bbox: 0.2042, loss_mask: 0.2214, loss: 0.6448 2023-11-15 23:06:59,176 - mmdet - INFO - Epoch [15][1400/1833] lr: 2.000e-04, eta: 12:47:55, time: 1.195, data_time: 0.066, memory: 16000, loss_rpn_cls: 0.0231, loss_rpn_bbox: 0.0318, loss_cls: 0.1630, acc: 94.0586, loss_bbox: 0.2073, loss_mask: 0.2206, loss: 0.6458 2023-11-15 23:08:00,545 - mmdet - INFO - Epoch [15][1450/1833] lr: 2.000e-04, eta: 12:46:59, time: 1.227, data_time: 0.074, memory: 16000, loss_rpn_cls: 0.0243, loss_rpn_bbox: 0.0336, loss_cls: 0.1673, acc: 93.8468, loss_bbox: 0.2120, loss_mask: 0.2242, loss: 0.6614 2023-11-15 23:08:59,894 - mmdet - INFO - Epoch [15][1500/1833] lr: 2.000e-04, eta: 12:46:00, time: 1.187, data_time: 0.063, memory: 16000, loss_rpn_cls: 0.0224, loss_rpn_bbox: 0.0313, loss_cls: 0.1600, acc: 94.1913, loss_bbox: 0.2043, loss_mask: 0.2197, loss: 0.6377 2023-11-15 23:10:00,059 - mmdet - INFO - Epoch [15][1550/1833] lr: 2.000e-04, eta: 12:45:03, time: 1.203, data_time: 0.070, memory: 16000, loss_rpn_cls: 0.0229, loss_rpn_bbox: 0.0312, loss_cls: 0.1627, acc: 94.0709, loss_bbox: 0.2061, loss_mask: 0.2226, loss: 0.6455 2023-11-15 23:10:59,851 - mmdet - INFO - Epoch [15][1600/1833] lr: 2.000e-04, eta: 12:44:04, time: 1.196, data_time: 0.062, memory: 16000, loss_rpn_cls: 0.0227, loss_rpn_bbox: 0.0318, loss_cls: 0.1614, acc: 94.1384, loss_bbox: 0.2049, loss_mask: 0.2236, loss: 0.6444 2023-11-15 23:12:01,280 - mmdet - INFO - Epoch [15][1650/1833] lr: 2.000e-04, eta: 12:43:08, time: 1.229, data_time: 0.063, memory: 16000, loss_rpn_cls: 0.0238, loss_rpn_bbox: 0.0320, loss_cls: 0.1620, acc: 94.1047, loss_bbox: 0.2049, loss_mask: 0.2202, loss: 0.6429 2023-11-15 23:13:01,239 - mmdet - INFO - Epoch [15][1700/1833] lr: 2.000e-04, eta: 12:42:10, time: 1.199, data_time: 0.061, memory: 16000, loss_rpn_cls: 0.0245, loss_rpn_bbox: 0.0321, loss_cls: 0.1630, acc: 94.0807, loss_bbox: 0.2069, loss_mask: 0.2229, loss: 0.6494 2023-11-15 23:14:02,568 - mmdet - INFO - Epoch [15][1750/1833] lr: 2.000e-04, eta: 12:41:14, time: 1.227, data_time: 0.070, memory: 16000, loss_rpn_cls: 0.0235, loss_rpn_bbox: 0.0325, loss_cls: 0.1639, acc: 94.0291, loss_bbox: 0.2053, loss_mask: 0.2211, loss: 0.6463 2023-11-15 23:15:03,292 - mmdet - INFO - Epoch [15][1800/1833] lr: 2.000e-04, eta: 12:40:17, time: 1.215, data_time: 0.066, memory: 16000, loss_rpn_cls: 0.0249, loss_rpn_bbox: 0.0324, loss_cls: 0.1645, acc: 94.0463, loss_bbox: 0.2066, loss_mask: 0.2227, loss: 0.6510 2023-11-15 23:15:42,969 - mmdet - INFO - Saving checkpoint at 15 epochs 2023-11-15 23:16:30,580 - mmdet - INFO - Evaluating bbox... 2023-11-15 23:16:58,634 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.479 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.699 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.531 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.308 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 ] = 0.620 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.607 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.607 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.607 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.430 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 ] = 0.753 2023-11-15 23:16:58,637 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.578 | bicycle | 0.373 | car | 0.484 | | motorcycle | 0.485 | airplane | 0.695 | bus | 0.683 | | train | 0.655 | truck | 0.428 | boat | 0.336 | | traffic light | 0.306 | fire hydrant | 0.729 | stop sign | 0.681 | | parking meter | 0.512 | bench | 0.315 | bird | 0.414 | | cat | 0.730 | dog | 0.674 | horse | 0.601 | | sheep | 0.572 | cow | 0.600 | elephant | 0.691 | | bear | 0.719 | zebra | 0.666 | giraffe | 0.699 | | backpack | 0.211 | umbrella | 0.467 | handbag | 0.232 | | tie | 0.383 | suitcase | 0.478 | frisbee | 0.721 | | skis | 0.296 | snowboard | 0.461 | sports ball | 0.486 | | kite | 0.468 | baseball bat | 0.423 | baseball glove | 0.441 | | skateboard | 0.580 | surfboard | 0.448 | tennis racket | 0.582 | | bottle | 0.451 | wine glass | 0.418 | cup | 0.502 | | fork | 0.469 | knife | 0.285 | spoon | 0.296 | | bowl | 0.471 | banana | 0.295 | apple | 0.258 | | sandwich | 0.475 | orange | 0.375 | broccoli | 0.285 | | carrot | 0.245 | hot dog | 0.472 | pizza | 0.548 | | donut | 0.546 | cake | 0.448 | chair | 0.359 | | couch | 0.480 | potted plant | 0.346 | bed | 0.484 | | dining table | 0.309 | toilet | 0.644 | tv | 0.637 | | laptop | 0.673 | mouse | 0.647 | remote | 0.420 | | keyboard | 0.520 | cell phone | 0.453 | microwave | 0.660 | | oven | 0.390 | toaster | 0.448 | sink | 0.446 | | refrigerator | 0.629 | book | 0.199 | clock | 0.536 | | vase | 0.442 | scissors | 0.390 | teddy bear | 0.547 | | hair drier | 0.225 | toothbrush | 0.303 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-15 23:16:58,637 - mmdet - INFO - Evaluating segm... 2023-11-15 23:17:31,810 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.430 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.670 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.464 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.228 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.465 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.617 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.551 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.551 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.551 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.370 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 ] = 0.707 2023-11-15 23:17:31,812 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.501 | bicycle | 0.232 | car | 0.444 | | motorcycle | 0.403 | airplane | 0.530 | bus | 0.681 | | train | 0.660 | truck | 0.403 | boat | 0.296 | | traffic light | 0.290 | fire hydrant | 0.698 | stop sign | 0.670 | | parking meter | 0.535 | bench | 0.249 | bird | 0.343 | | cat | 0.731 | dog | 0.640 | horse | 0.461 | | sheep | 0.502 | cow | 0.506 | elephant | 0.626 | | bear | 0.727 | zebra | 0.583 | giraffe | 0.549 | | backpack | 0.216 | umbrella | 0.528 | handbag | 0.222 | | tie | 0.344 | suitcase | 0.500 | frisbee | 0.663 | | skis | 0.062 | snowboard | 0.281 | sports ball | 0.462 | | kite | 0.332 | baseball bat | 0.326 | baseball glove | 0.457 | | skateboard | 0.374 | surfboard | 0.359 | tennis racket | 0.611 | | bottle | 0.429 | wine glass | 0.392 | cup | 0.498 | | fork | 0.233 | knife | 0.195 | spoon | 0.204 | | bowl | 0.446 | banana | 0.243 | apple | 0.252 | | sandwich | 0.484 | orange | 0.369 | broccoli | 0.265 | | carrot | 0.214 | hot dog | 0.409 | pizza | 0.530 | | donut | 0.544 | cake | 0.453 | chair | 0.259 | | couch | 0.408 | potted plant | 0.297 | bed | 0.386 | | dining table | 0.179 | toilet | 0.624 | tv | 0.661 | | laptop | 0.666 | mouse | 0.617 | remote | 0.371 | | keyboard | 0.510 | cell phone | 0.422 | microwave | 0.674 | | oven | 0.352 | toaster | 0.490 | sink | 0.423 | | refrigerator | 0.640 | book | 0.162 | clock | 0.545 | | vase | 0.436 | scissors | 0.306 | teddy bear | 0.519 | | hair drier | 0.102 | toothbrush | 0.222 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-15 23:17:32,212 - mmdet - INFO - Exp name: mask_rcnn_flash_internimage_s_fpn_3x_coco_0.4.py 2023-11-15 23:17:32,212 - mmdet - INFO - Epoch(val) [15][625] bbox_mAP: 0.4791, bbox_mAP_50: 0.6989, bbox_mAP_75: 0.5311, bbox_mAP_s: 0.3085, bbox_mAP_m: 0.5189, bbox_mAP_l: 0.6200, bbox_mAP_copypaste: 0.4791 0.6989 0.5311 0.3085 0.5189 0.6200, segm_mAP: 0.4304, segm_mAP_50: 0.6696, segm_mAP_75: 0.4638, segm_mAP_s: 0.2284, segm_mAP_m: 0.4647, segm_mAP_l: 0.6171, segm_mAP_copypaste: 0.4304 0.6696 0.4638 0.2284 0.4647 0.6171 2023-11-15 23:18:35,659 - mmdet - INFO - Epoch [16][50/1833] lr: 2.000e-04, eta: 12:37:50, time: 1.268, data_time: 0.146, memory: 16000, loss_rpn_cls: 0.0230, loss_rpn_bbox: 0.0321, loss_cls: 0.1617, acc: 94.0645, loss_bbox: 0.2067, loss_mask: 0.2221, loss: 0.6455 2023-11-15 23:19:35,987 - mmdet - INFO - Epoch [16][100/1833] lr: 2.000e-04, eta: 12:36:52, time: 1.207, data_time: 0.089, memory: 16000, loss_rpn_cls: 0.0216, loss_rpn_bbox: 0.0320, loss_cls: 0.1598, acc: 94.1290, loss_bbox: 0.2053, loss_mask: 0.2190, loss: 0.6378 2023-11-15 23:20:37,115 - mmdet - INFO - Epoch [16][150/1833] lr: 2.000e-04, eta: 12:35:56, time: 1.223, data_time: 0.080, memory: 16000, loss_rpn_cls: 0.0215, loss_rpn_bbox: 0.0309, loss_cls: 0.1563, acc: 94.3115, loss_bbox: 0.2003, loss_mask: 0.2191, loss: 0.6280 2023-11-15 23:21:38,785 - mmdet - INFO - Epoch [16][200/1833] lr: 2.000e-04, eta: 12:35:00, time: 1.233, data_time: 0.081, memory: 16000, loss_rpn_cls: 0.0216, loss_rpn_bbox: 0.0315, loss_cls: 0.1565, acc: 94.3087, loss_bbox: 0.2005, loss_mask: 0.2180, loss: 0.6280 2023-11-15 23:22:39,173 - mmdet - INFO - Epoch [16][250/1833] lr: 2.000e-04, eta: 12:34:03, time: 1.208, data_time: 0.079, memory: 16000, loss_rpn_cls: 0.0228, loss_rpn_bbox: 0.0309, loss_cls: 0.1588, acc: 94.2377, loss_bbox: 0.2036, loss_mask: 0.2181, loss: 0.6341 2023-11-15 23:23:41,814 - mmdet - INFO - Epoch [16][300/1833] lr: 2.000e-04, eta: 12:33:09, time: 1.253, data_time: 0.124, memory: 16000, loss_rpn_cls: 0.0226, loss_rpn_bbox: 0.0334, loss_cls: 0.1656, acc: 93.9333, loss_bbox: 0.2134, loss_mask: 0.2219, loss: 0.6568 2023-11-15 23:24:41,676 - mmdet - INFO - Epoch [16][350/1833] lr: 2.000e-04, eta: 12:32:10, time: 1.197, data_time: 0.080, memory: 16000, loss_rpn_cls: 0.0230, loss_rpn_bbox: 0.0321, loss_cls: 0.1589, acc: 94.1583, loss_bbox: 0.2047, loss_mask: 0.2203, loss: 0.6390 2023-11-15 23:25:42,256 - mmdet - INFO - Epoch [16][400/1833] lr: 2.000e-04, eta: 12:31:13, time: 1.212, data_time: 0.076, memory: 16000, loss_rpn_cls: 0.0236, loss_rpn_bbox: 0.0317, loss_cls: 0.1583, acc: 94.2057, loss_bbox: 0.2043, loss_mask: 0.2187, loss: 0.6365 2023-11-15 23:26:42,740 - mmdet - INFO - Epoch [16][450/1833] lr: 2.000e-04, eta: 12:30:16, time: 1.210, data_time: 0.093, memory: 16000, loss_rpn_cls: 0.0239, loss_rpn_bbox: 0.0335, loss_cls: 0.1613, acc: 94.0694, loss_bbox: 0.2074, loss_mask: 0.2221, loss: 0.6482 2023-11-15 23:27:42,190 - mmdet - INFO - Epoch [16][500/1833] lr: 2.000e-04, eta: 12:29:17, time: 1.189, data_time: 0.078, memory: 16000, loss_rpn_cls: 0.0224, loss_rpn_bbox: 0.0321, loss_cls: 0.1591, acc: 94.1847, loss_bbox: 0.2040, loss_mask: 0.2190, loss: 0.6365 2023-11-15 23:28:43,641 - mmdet - INFO - Epoch [16][550/1833] lr: 2.000e-04, eta: 12:28:21, time: 1.229, data_time: 0.081, memory: 16000, loss_rpn_cls: 0.0228, loss_rpn_bbox: 0.0315, loss_cls: 0.1542, acc: 94.3602, loss_bbox: 0.1995, loss_mask: 0.2184, loss: 0.6263 2023-11-15 23:29:43,799 - mmdet - INFO - Epoch [16][600/1833] lr: 2.000e-04, eta: 12:27:23, time: 1.203, data_time: 0.080, memory: 16000, loss_rpn_cls: 0.0218, loss_rpn_bbox: 0.0311, loss_cls: 0.1601, acc: 94.1302, loss_bbox: 0.2046, loss_mask: 0.2191, loss: 0.6368 2023-11-15 23:30:43,703 - mmdet - INFO - Epoch [16][650/1833] lr: 2.000e-04, eta: 12:26:25, time: 1.198, data_time: 0.078, memory: 16000, loss_rpn_cls: 0.0216, loss_rpn_bbox: 0.0304, loss_cls: 0.1581, acc: 94.2505, loss_bbox: 0.2011, loss_mask: 0.2174, loss: 0.6286 2023-11-15 23:31:42,815 - mmdet - INFO - Epoch [16][700/1833] lr: 2.000e-04, eta: 12:25:26, time: 1.182, data_time: 0.074, memory: 16000, loss_rpn_cls: 0.0214, loss_rpn_bbox: 0.0313, loss_cls: 0.1574, acc: 94.2367, loss_bbox: 0.2030, loss_mask: 0.2163, loss: 0.6295 2023-11-15 23:32:43,020 - mmdet - INFO - Epoch [16][750/1833] lr: 2.000e-04, eta: 12:24:28, time: 1.204, data_time: 0.079, memory: 16000, loss_rpn_cls: 0.0236, loss_rpn_bbox: 0.0326, loss_cls: 0.1630, acc: 94.0734, loss_bbox: 0.2090, loss_mask: 0.2220, loss: 0.6502 2023-11-15 23:33:42,843 - mmdet - INFO - Epoch [16][800/1833] lr: 2.000e-04, eta: 12:23:30, time: 1.196, data_time: 0.081, memory: 16000, loss_rpn_cls: 0.0236, loss_rpn_bbox: 0.0325, loss_cls: 0.1611, acc: 94.1552, loss_bbox: 0.2066, loss_mask: 0.2237, loss: 0.6475 2023-11-15 23:34:42,627 - mmdet - INFO - Epoch [16][850/1833] lr: 2.000e-04, eta: 12:22:31, time: 1.196, data_time: 0.075, memory: 16000, loss_rpn_cls: 0.0221, loss_rpn_bbox: 0.0312, loss_cls: 0.1574, acc: 94.2529, loss_bbox: 0.2031, loss_mask: 0.2202, loss: 0.6341 2023-11-15 23:35:42,914 - mmdet - INFO - Epoch [16][900/1833] lr: 2.000e-04, eta: 12:21:34, time: 1.206, data_time: 0.078, memory: 16000, loss_rpn_cls: 0.0236, loss_rpn_bbox: 0.0324, loss_cls: 0.1654, acc: 93.9544, loss_bbox: 0.2086, loss_mask: 0.2204, loss: 0.6504 2023-11-15 23:36:43,133 - mmdet - INFO - Epoch [16][950/1833] lr: 2.000e-04, eta: 12:20:36, time: 1.204, data_time: 0.072, memory: 16000, loss_rpn_cls: 0.0234, loss_rpn_bbox: 0.0320, loss_cls: 0.1607, acc: 94.1547, loss_bbox: 0.2021, loss_mask: 0.2207, loss: 0.6389 2023-11-15 23:37:44,662 - mmdet - INFO - Epoch [16][1000/1833] lr: 2.000e-04, eta: 12:19:40, time: 1.231, data_time: 0.076, memory: 16000, loss_rpn_cls: 0.0228, loss_rpn_bbox: 0.0321, loss_cls: 0.1655, acc: 93.9356, loss_bbox: 0.2088, loss_mask: 0.2212, loss: 0.6504 2023-11-15 23:38:43,723 - mmdet - INFO - Epoch [16][1050/1833] lr: 2.000e-04, eta: 12:18:40, time: 1.181, data_time: 0.088, memory: 16000, loss_rpn_cls: 0.0229, loss_rpn_bbox: 0.0324, loss_cls: 0.1625, acc: 94.0635, loss_bbox: 0.2067, loss_mask: 0.2228, loss: 0.6473 2023-11-15 23:39:43,361 - mmdet - INFO - Epoch [16][1100/1833] lr: 2.000e-04, eta: 12:17:42, time: 1.193, data_time: 0.082, memory: 16000, loss_rpn_cls: 0.0228, loss_rpn_bbox: 0.0325, loss_cls: 0.1631, acc: 94.0175, loss_bbox: 0.2073, loss_mask: 0.2191, loss: 0.6448 2023-11-15 23:40:43,026 - mmdet - INFO - Epoch [16][1150/1833] lr: 2.000e-04, eta: 12:16:43, time: 1.193, data_time: 0.079, memory: 16000, loss_rpn_cls: 0.0225, loss_rpn_bbox: 0.0321, loss_cls: 0.1601, acc: 94.1992, loss_bbox: 0.2039, loss_mask: 0.2184, loss: 0.6370 2023-11-15 23:41:44,112 - mmdet - INFO - Epoch [16][1200/1833] lr: 2.000e-04, eta: 12:15:46, time: 1.222, data_time: 0.082, memory: 16000, loss_rpn_cls: 0.0235, loss_rpn_bbox: 0.0333, loss_cls: 0.1639, acc: 94.0468, loss_bbox: 0.2074, loss_mask: 0.2224, loss: 0.6504 2023-11-15 23:42:45,005 - mmdet - INFO - Epoch [16][1250/1833] lr: 2.000e-04, eta: 12:14:49, time: 1.218, data_time: 0.080, memory: 16000, loss_rpn_cls: 0.0230, loss_rpn_bbox: 0.0311, loss_cls: 0.1579, acc: 94.2597, loss_bbox: 0.2021, loss_mask: 0.2203, loss: 0.6344 2023-11-15 23:43:45,634 - mmdet - INFO - Epoch [16][1300/1833] lr: 2.000e-04, eta: 12:13:52, time: 1.213, data_time: 0.071, memory: 16000, loss_rpn_cls: 0.0227, loss_rpn_bbox: 0.0313, loss_cls: 0.1561, acc: 94.2686, loss_bbox: 0.2014, loss_mask: 0.2209, loss: 0.6324 2023-11-15 23:46:03,700 - mmdet - INFO - Epoch [16][1350/1833] lr: 2.000e-04, eta: 12:14:34, time: 2.761, data_time: 1.624, memory: 16000, loss_rpn_cls: 0.0246, loss_rpn_bbox: 0.0329, loss_cls: 0.1649, acc: 93.9658, loss_bbox: 0.2110, loss_mask: 0.2226, loss: 0.6559 2023-11-15 23:47:04,389 - mmdet - INFO - Epoch [16][1400/1833] lr: 2.000e-04, eta: 12:13:37, time: 1.214, data_time: 0.076, memory: 16000, loss_rpn_cls: 0.0235, loss_rpn_bbox: 0.0327, loss_cls: 0.1628, acc: 94.0693, loss_bbox: 0.2081, loss_mask: 0.2218, loss: 0.6488 2023-11-15 23:48:04,231 - mmdet - INFO - Epoch [16][1450/1833] lr: 2.000e-04, eta: 12:12:38, time: 1.197, data_time: 0.081, memory: 16000, loss_rpn_cls: 0.0237, loss_rpn_bbox: 0.0323, loss_cls: 0.1635, acc: 94.0541, loss_bbox: 0.2080, loss_mask: 0.2189, loss: 0.6465 2023-11-15 23:49:04,165 - mmdet - INFO - Epoch [16][1500/1833] lr: 2.000e-04, eta: 12:11:40, time: 1.199, data_time: 0.076, memory: 16000, loss_rpn_cls: 0.0232, loss_rpn_bbox: 0.0314, loss_cls: 0.1594, acc: 94.1599, loss_bbox: 0.2045, loss_mask: 0.2203, loss: 0.6388 2023-11-15 23:50:03,831 - mmdet - INFO - Epoch [16][1550/1833] lr: 2.000e-04, eta: 12:10:41, time: 1.193, data_time: 0.076, memory: 16000, loss_rpn_cls: 0.0228, loss_rpn_bbox: 0.0314, loss_cls: 0.1614, acc: 94.1466, loss_bbox: 0.2039, loss_mask: 0.2212, loss: 0.6407 2023-11-15 23:51:04,801 - mmdet - INFO - Epoch [16][1600/1833] lr: 2.000e-04, eta: 12:09:43, time: 1.219, data_time: 0.076, memory: 16000, loss_rpn_cls: 0.0223, loss_rpn_bbox: 0.0314, loss_cls: 0.1605, acc: 94.1411, loss_bbox: 0.2042, loss_mask: 0.2206, loss: 0.6390 2023-11-15 23:52:05,147 - mmdet - INFO - Epoch [16][1650/1833] lr: 2.000e-04, eta: 12:08:45, time: 1.207, data_time: 0.074, memory: 16000, loss_rpn_cls: 0.0223, loss_rpn_bbox: 0.0319, loss_cls: 0.1622, acc: 94.0389, loss_bbox: 0.2080, loss_mask: 0.2188, loss: 0.6433 2023-11-15 23:53:05,396 - mmdet - INFO - Epoch [16][1700/1833] lr: 2.000e-04, eta: 12:07:47, time: 1.205, data_time: 0.081, memory: 16000, loss_rpn_cls: 0.0220, loss_rpn_bbox: 0.0315, loss_cls: 0.1587, acc: 94.1537, loss_bbox: 0.2019, loss_mask: 0.2176, loss: 0.6318 2023-11-15 23:54:07,277 - mmdet - INFO - Epoch [16][1750/1833] lr: 2.000e-04, eta: 12:06:51, time: 1.238, data_time: 0.075, memory: 16000, loss_rpn_cls: 0.0237, loss_rpn_bbox: 0.0333, loss_cls: 0.1674, acc: 93.9198, loss_bbox: 0.2096, loss_mask: 0.2205, loss: 0.6546 2023-11-15 23:55:07,078 - mmdet - INFO - Epoch [16][1800/1833] lr: 2.000e-04, eta: 12:05:52, time: 1.196, data_time: 0.071, memory: 16000, loss_rpn_cls: 0.0230, loss_rpn_bbox: 0.0314, loss_cls: 0.1595, acc: 94.1599, loss_bbox: 0.2030, loss_mask: 0.2211, loss: 0.6380 2023-11-15 23:55:47,708 - mmdet - INFO - Saving checkpoint at 16 epochs 2023-11-15 23:56:36,142 - mmdet - INFO - Evaluating bbox... 2023-11-15 23:57:04,970 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.482 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.701 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.533 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.326 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.528 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 ] = 0.609 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 ] = 0.446 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.650 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.751 2023-11-15 23:57:04,972 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.583 | bicycle | 0.385 | car | 0.503 | | motorcycle | 0.493 | airplane | 0.722 | bus | 0.722 | | train | 0.669 | truck | 0.407 | boat | 0.333 | | traffic light | 0.313 | fire hydrant | 0.720 | stop sign | 0.689 | | parking meter | 0.521 | bench | 0.301 | bird | 0.416 | | cat | 0.716 | dog | 0.696 | horse | 0.630 | | sheep | 0.596 | cow | 0.617 | elephant | 0.708 | | bear | 0.759 | zebra | 0.694 | giraffe | 0.703 | | backpack | 0.200 | umbrella | 0.475 | handbag | 0.231 | | tie | 0.396 | suitcase | 0.490 | frisbee | 0.706 | | skis | 0.302 | snowboard | 0.444 | sports ball | 0.485 | | kite | 0.474 | baseball bat | 0.421 | baseball glove | 0.432 | | skateboard | 0.591 | surfboard | 0.450 | tennis racket | 0.564 | | bottle | 0.449 | wine glass | 0.433 | cup | 0.504 | | fork | 0.463 | knife | 0.282 | spoon | 0.303 | | bowl | 0.472 | banana | 0.269 | apple | 0.248 | | sandwich | 0.442 | orange | 0.358 | broccoli | 0.254 | | carrot | 0.264 | hot dog | 0.475 | pizza | 0.548 | | donut | 0.521 | cake | 0.455 | chair | 0.364 | | couch | 0.459 | potted plant | 0.346 | bed | 0.465 | | dining table | 0.317 | toilet | 0.664 | tv | 0.631 | | laptop | 0.682 | mouse | 0.669 | remote | 0.425 | | keyboard | 0.539 | cell phone | 0.438 | microwave | 0.676 | | oven | 0.406 | toaster | 0.487 | sink | 0.435 | | refrigerator | 0.647 | book | 0.207 | clock | 0.515 | | vase | 0.455 | scissors | 0.438 | teddy bear | 0.518 | | hair drier | 0.187 | toothbrush | 0.310 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-15 23:57:04,973 - mmdet - INFO - Evaluating segm... 2023-11-15 23:57:38,657 - 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 ] = 0.672 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.467 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.239 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 ] = 0.622 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.551 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.551 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.551 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 ] = 0.591 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.710 2023-11-15 23:57:38,660 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.509 | bicycle | 0.241 | car | 0.459 | | motorcycle | 0.408 | airplane | 0.560 | bus | 0.700 | | train | 0.679 | truck | 0.387 | boat | 0.306 | | traffic light | 0.299 | fire hydrant | 0.709 | stop sign | 0.664 | | parking meter | 0.512 | bench | 0.232 | bird | 0.346 | | cat | 0.712 | dog | 0.654 | horse | 0.466 | | sheep | 0.530 | cow | 0.531 | elephant | 0.640 | | bear | 0.736 | zebra | 0.613 | giraffe | 0.543 | | backpack | 0.218 | umbrella | 0.535 | handbag | 0.223 | | tie | 0.365 | suitcase | 0.507 | frisbee | 0.670 | | skis | 0.062 | snowboard | 0.284 | sports ball | 0.467 | | kite | 0.345 | baseball bat | 0.318 | baseball glove | 0.457 | | skateboard | 0.389 | surfboard | 0.377 | tennis racket | 0.601 | | bottle | 0.431 | wine glass | 0.389 | cup | 0.502 | | fork | 0.243 | knife | 0.198 | spoon | 0.215 | | bowl | 0.440 | banana | 0.227 | apple | 0.242 | | sandwich | 0.461 | orange | 0.356 | broccoli | 0.243 | | carrot | 0.233 | hot dog | 0.419 | pizza | 0.527 | | donut | 0.526 | cake | 0.456 | chair | 0.266 | | couch | 0.391 | potted plant | 0.298 | bed | 0.358 | | dining table | 0.174 | toilet | 0.643 | tv | 0.665 | | laptop | 0.669 | mouse | 0.646 | remote | 0.380 | | keyboard | 0.523 | cell phone | 0.411 | microwave | 0.675 | | oven | 0.372 | toaster | 0.488 | sink | 0.415 | | refrigerator | 0.647 | book | 0.155 | clock | 0.519 | | vase | 0.436 | scissors | 0.296 | teddy bear | 0.525 | | hair drier | 0.090 | toothbrush | 0.232 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-15 23:57:39,063 - mmdet - INFO - The previous best checkpoint /mnt/petrelfs/lizhiqi/DINO/detection/work_dirs/mask_rcnn_flash_internimage_s_fpn_3x_coco_0.4/best_bbox_mAP_epoch_12.pth was removed 2023-11-15 23:57:41,164 - mmdet - INFO - Now best checkpoint is saved as best_bbox_mAP_epoch_16.pth. 2023-11-15 23:57:41,165 - mmdet - INFO - Best bbox_mAP is 0.4822 at 16 epoch. 2023-11-15 23:57:41,165 - mmdet - INFO - Exp name: mask_rcnn_flash_internimage_s_fpn_3x_coco_0.4.py 2023-11-15 23:57:41,165 - mmdet - INFO - Epoch(val) [16][625] bbox_mAP: 0.4822, bbox_mAP_50: 0.7013, bbox_mAP_75: 0.5326, bbox_mAP_s: 0.3257, bbox_mAP_m: 0.5282, bbox_mAP_l: 0.6196, bbox_mAP_copypaste: 0.4822 0.7013 0.5326 0.3257 0.5282 0.6196, segm_mAP: 0.4329, segm_mAP_50: 0.6715, segm_mAP_75: 0.4671, segm_mAP_s: 0.2386, segm_mAP_m: 0.4659, segm_mAP_l: 0.6217, segm_mAP_copypaste: 0.4329 0.6715 0.4671 0.2386 0.4659 0.6217 2023-11-15 23:58:44,707 - mmdet - INFO - Epoch [17][50/1833] lr: 2.000e-04, eta: 12:03:30, time: 1.270, data_time: 0.128, memory: 16000, loss_rpn_cls: 0.0218, loss_rpn_bbox: 0.0321, loss_cls: 0.1603, acc: 94.1531, loss_bbox: 0.2075, loss_mask: 0.2178, loss: 0.6394 2023-11-15 23:59:45,029 - mmdet - INFO - Epoch [17][100/1833] lr: 2.000e-04, eta: 12:02:32, time: 1.206, data_time: 0.067, memory: 16000, loss_rpn_cls: 0.0229, loss_rpn_bbox: 0.0318, loss_cls: 0.1542, acc: 94.2995, loss_bbox: 0.1995, loss_mask: 0.2163, loss: 0.6248 2023-11-16 00:00:46,578 - mmdet - INFO - Epoch [17][150/1833] lr: 2.000e-04, eta: 12:01:36, time: 1.231, data_time: 0.074, memory: 16000, loss_rpn_cls: 0.0222, loss_rpn_bbox: 0.0327, loss_cls: 0.1583, acc: 94.2153, loss_bbox: 0.2044, loss_mask: 0.2199, loss: 0.6375 2023-11-16 00:01:47,194 - mmdet - INFO - Epoch [17][200/1833] lr: 2.000e-04, eta: 12:00:38, time: 1.212, data_time: 0.063, memory: 16000, loss_rpn_cls: 0.0234, loss_rpn_bbox: 0.0314, loss_cls: 0.1546, acc: 94.3593, loss_bbox: 0.1993, loss_mask: 0.2172, loss: 0.6259 2023-11-16 00:02:47,656 - mmdet - INFO - Epoch [17][250/1833] lr: 2.000e-04, eta: 11:59:40, time: 1.209, data_time: 0.070, memory: 16000, loss_rpn_cls: 0.0225, loss_rpn_bbox: 0.0317, loss_cls: 0.1598, acc: 94.1427, loss_bbox: 0.2046, loss_mask: 0.2176, loss: 0.6362 2023-11-16 00:03:48,891 - mmdet - INFO - Epoch [17][300/1833] lr: 2.000e-04, eta: 11:58:43, time: 1.225, data_time: 0.074, memory: 16000, loss_rpn_cls: 0.0231, loss_rpn_bbox: 0.0321, loss_cls: 0.1546, acc: 94.3308, loss_bbox: 0.1991, loss_mask: 0.2149, loss: 0.6238 2023-11-16 00:04:48,434 - mmdet - INFO - Epoch [17][350/1833] lr: 2.000e-04, eta: 11:57:44, time: 1.191, data_time: 0.077, memory: 16000, loss_rpn_cls: 0.0226, loss_rpn_bbox: 0.0317, loss_cls: 0.1599, acc: 94.1561, loss_bbox: 0.2066, loss_mask: 0.2178, loss: 0.6385 2023-11-16 00:05:49,302 - mmdet - INFO - Epoch [17][400/1833] lr: 2.000e-04, eta: 11:56:47, time: 1.217, data_time: 0.074, memory: 16000, loss_rpn_cls: 0.0228, loss_rpn_bbox: 0.0326, loss_cls: 0.1600, acc: 94.1885, loss_bbox: 0.2052, loss_mask: 0.2198, loss: 0.6403 2023-11-16 00:06:50,661 - mmdet - INFO - Epoch [17][450/1833] lr: 2.000e-04, eta: 11:55:50, time: 1.227, data_time: 0.090, memory: 16000, loss_rpn_cls: 0.0218, loss_rpn_bbox: 0.0321, loss_cls: 0.1602, acc: 94.1858, loss_bbox: 0.2048, loss_mask: 0.2192, loss: 0.6381 2023-11-16 00:07:50,339 - mmdet - INFO - Epoch [17][500/1833] lr: 2.000e-04, eta: 11:54:51, time: 1.194, data_time: 0.069, memory: 16000, loss_rpn_cls: 0.0226, loss_rpn_bbox: 0.0314, loss_cls: 0.1553, acc: 94.2921, loss_bbox: 0.2012, loss_mask: 0.2194, loss: 0.6299 2023-11-16 00:08:51,172 - mmdet - INFO - Epoch [17][550/1833] lr: 2.000e-04, eta: 11:53:54, time: 1.217, data_time: 0.065, memory: 16000, loss_rpn_cls: 0.0226, loss_rpn_bbox: 0.0328, loss_cls: 0.1599, acc: 94.1139, loss_bbox: 0.2052, loss_mask: 0.2217, loss: 0.6422 2023-11-16 00:09:51,316 - mmdet - INFO - Epoch [17][600/1833] lr: 2.000e-04, eta: 11:52:55, time: 1.203, data_time: 0.060, memory: 16000, loss_rpn_cls: 0.0222, loss_rpn_bbox: 0.0316, loss_cls: 0.1555, acc: 94.2946, loss_bbox: 0.2001, loss_mask: 0.2160, loss: 0.6255 2023-11-16 00:10:51,636 - mmdet - INFO - Epoch [17][650/1833] lr: 2.000e-04, eta: 11:51:57, time: 1.206, data_time: 0.064, memory: 16000, loss_rpn_cls: 0.0227, loss_rpn_bbox: 0.0309, loss_cls: 0.1565, acc: 94.3065, loss_bbox: 0.1999, loss_mask: 0.2187, loss: 0.6289 2023-11-16 00:11:51,548 - mmdet - INFO - Epoch [17][700/1833] lr: 2.000e-04, eta: 11:50:59, time: 1.198, data_time: 0.070, memory: 16000, loss_rpn_cls: 0.0220, loss_rpn_bbox: 0.0312, loss_cls: 0.1565, acc: 94.2702, loss_bbox: 0.2003, loss_mask: 0.2214, loss: 0.6314 2023-11-16 00:12:52,187 - mmdet - INFO - Epoch [17][750/1833] lr: 2.000e-04, eta: 11:50:01, time: 1.213, data_time: 0.067, memory: 16000, loss_rpn_cls: 0.0224, loss_rpn_bbox: 0.0310, loss_cls: 0.1584, acc: 94.2537, loss_bbox: 0.2004, loss_mask: 0.2192, loss: 0.6314 2023-11-16 00:13:52,700 - mmdet - INFO - Epoch [17][800/1833] lr: 2.000e-04, eta: 11:49:03, time: 1.210, data_time: 0.069, memory: 16000, loss_rpn_cls: 0.0225, loss_rpn_bbox: 0.0323, loss_cls: 0.1596, acc: 94.1592, loss_bbox: 0.2051, loss_mask: 0.2188, loss: 0.6384 2023-11-16 00:14:53,066 - mmdet - INFO - Epoch [17][850/1833] lr: 2.000e-04, eta: 11:48:05, time: 1.207, data_time: 0.072, memory: 16000, loss_rpn_cls: 0.0227, loss_rpn_bbox: 0.0316, loss_cls: 0.1595, acc: 94.1437, loss_bbox: 0.2042, loss_mask: 0.2236, loss: 0.6417 2023-11-16 00:15:54,242 - mmdet - INFO - Epoch [17][900/1833] lr: 2.000e-04, eta: 11:47:08, time: 1.223, data_time: 0.059, memory: 16000, loss_rpn_cls: 0.0234, loss_rpn_bbox: 0.0324, loss_cls: 0.1592, acc: 94.1549, loss_bbox: 0.2045, loss_mask: 0.2174, loss: 0.6370 2023-11-16 00:16:54,592 - mmdet - INFO - Epoch [17][950/1833] lr: 2.000e-04, eta: 11:46:10, time: 1.207, data_time: 0.066, memory: 16000, loss_rpn_cls: 0.0229, loss_rpn_bbox: 0.0319, loss_cls: 0.1608, acc: 94.0675, loss_bbox: 0.2080, loss_mask: 0.2198, loss: 0.6434 2023-11-16 00:17:55,813 - mmdet - INFO - Epoch [17][1000/1833] lr: 2.000e-04, eta: 11:45:13, time: 1.224, data_time: 0.069, memory: 16000, loss_rpn_cls: 0.0223, loss_rpn_bbox: 0.0320, loss_cls: 0.1570, acc: 94.2676, loss_bbox: 0.2009, loss_mask: 0.2193, loss: 0.6315 2023-11-16 00:18:56,017 - mmdet - INFO - Epoch [17][1050/1833] lr: 2.000e-04, eta: 11:44:14, time: 1.204, data_time: 0.067, memory: 16000, loss_rpn_cls: 0.0227, loss_rpn_bbox: 0.0320, loss_cls: 0.1599, acc: 94.1264, loss_bbox: 0.2056, loss_mask: 0.2197, loss: 0.6399 2023-11-16 00:19:55,316 - mmdet - INFO - Epoch [17][1100/1833] lr: 2.000e-04, eta: 11:43:15, time: 1.186, data_time: 0.067, memory: 16000, loss_rpn_cls: 0.0227, loss_rpn_bbox: 0.0329, loss_cls: 0.1631, acc: 94.0051, loss_bbox: 0.2098, loss_mask: 0.2204, loss: 0.6489 2023-11-16 00:20:56,143 - mmdet - INFO - Epoch [17][1150/1833] lr: 2.000e-04, eta: 11:42:17, time: 1.216, data_time: 0.070, memory: 16000, loss_rpn_cls: 0.0229, loss_rpn_bbox: 0.0321, loss_cls: 0.1605, acc: 94.1282, loss_bbox: 0.2052, loss_mask: 0.2217, loss: 0.6425 2023-11-16 00:21:56,686 - mmdet - INFO - Epoch [17][1200/1833] lr: 2.000e-04, eta: 11:41:19, time: 1.211, data_time: 0.067, memory: 16000, loss_rpn_cls: 0.0222, loss_rpn_bbox: 0.0316, loss_cls: 0.1584, acc: 94.2256, loss_bbox: 0.2034, loss_mask: 0.2189, loss: 0.6345 2023-11-16 00:22:56,682 - mmdet - INFO - Epoch [17][1250/1833] lr: 2.000e-04, eta: 11:40:21, time: 1.200, data_time: 0.063, memory: 16000, loss_rpn_cls: 0.0231, loss_rpn_bbox: 0.0319, loss_cls: 0.1619, acc: 94.0676, loss_bbox: 0.2055, loss_mask: 0.2212, loss: 0.6437 2023-11-16 00:23:55,874 - mmdet - INFO - Epoch [17][1300/1833] lr: 2.000e-04, eta: 11:39:21, time: 1.184, data_time: 0.064, memory: 16000, loss_rpn_cls: 0.0228, loss_rpn_bbox: 0.0315, loss_cls: 0.1635, acc: 94.0394, loss_bbox: 0.2075, loss_mask: 0.2199, loss: 0.6453 2023-11-16 00:24:56,625 - mmdet - INFO - Epoch [17][1350/1833] lr: 2.000e-04, eta: 11:38:24, time: 1.215, data_time: 0.064, memory: 16000, loss_rpn_cls: 0.0227, loss_rpn_bbox: 0.0310, loss_cls: 0.1607, acc: 94.1785, loss_bbox: 0.2018, loss_mask: 0.2208, loss: 0.6371 2023-11-16 00:25:56,407 - mmdet - INFO - Epoch [17][1400/1833] lr: 2.000e-04, eta: 11:37:25, time: 1.196, data_time: 0.069, memory: 16000, loss_rpn_cls: 0.0227, loss_rpn_bbox: 0.0317, loss_cls: 0.1597, acc: 94.2309, loss_bbox: 0.2013, loss_mask: 0.2180, loss: 0.6334 2023-11-16 00:26:55,913 - mmdet - INFO - Epoch [17][1450/1833] lr: 2.000e-04, eta: 11:36:26, time: 1.190, data_time: 0.066, memory: 16000, loss_rpn_cls: 0.0235, loss_rpn_bbox: 0.0324, loss_cls: 0.1635, acc: 94.0338, loss_bbox: 0.2051, loss_mask: 0.2187, loss: 0.6432 2023-11-16 00:27:55,450 - mmdet - INFO - Epoch [17][1500/1833] lr: 2.000e-04, eta: 11:35:27, time: 1.191, data_time: 0.057, memory: 16000, loss_rpn_cls: 0.0221, loss_rpn_bbox: 0.0308, loss_cls: 0.1559, acc: 94.2934, loss_bbox: 0.1990, loss_mask: 0.2188, loss: 0.6266 2023-11-16 00:28:56,550 - mmdet - INFO - Epoch [17][1550/1833] lr: 2.000e-04, eta: 11:34:29, time: 1.222, data_time: 0.063, memory: 16000, loss_rpn_cls: 0.0231, loss_rpn_bbox: 0.0323, loss_cls: 0.1621, acc: 94.1220, loss_bbox: 0.2057, loss_mask: 0.2214, loss: 0.6447 2023-11-16 00:29:57,138 - mmdet - INFO - Epoch [17][1600/1833] lr: 2.000e-04, eta: 11:33:31, time: 1.212, data_time: 0.071, memory: 16000, loss_rpn_cls: 0.0233, loss_rpn_bbox: 0.0314, loss_cls: 0.1594, acc: 94.1226, loss_bbox: 0.2051, loss_mask: 0.2214, loss: 0.6406 2023-11-16 00:30:57,603 - mmdet - INFO - Epoch [17][1650/1833] lr: 2.000e-04, eta: 11:32:33, time: 1.209, data_time: 0.066, memory: 16000, loss_rpn_cls: 0.0232, loss_rpn_bbox: 0.0318, loss_cls: 0.1594, acc: 94.1647, loss_bbox: 0.2046, loss_mask: 0.2232, loss: 0.6422 2023-11-16 00:31:57,676 - mmdet - INFO - Epoch [17][1700/1833] lr: 2.000e-04, eta: 11:31:35, time: 1.201, data_time: 0.066, memory: 16000, loss_rpn_cls: 0.0225, loss_rpn_bbox: 0.0318, loss_cls: 0.1601, acc: 94.1395, loss_bbox: 0.2043, loss_mask: 0.2191, loss: 0.6378 2023-11-16 00:32:57,564 - mmdet - INFO - Epoch [17][1750/1833] lr: 2.000e-04, eta: 11:30:36, time: 1.198, data_time: 0.072, memory: 16000, loss_rpn_cls: 0.0215, loss_rpn_bbox: 0.0318, loss_cls: 0.1585, acc: 94.2196, loss_bbox: 0.1990, loss_mask: 0.2179, loss: 0.6287 2023-11-16 00:33:57,238 - mmdet - INFO - Epoch [17][1800/1833] lr: 2.000e-04, eta: 11:29:37, time: 1.193, data_time: 0.067, memory: 16000, loss_rpn_cls: 0.0214, loss_rpn_bbox: 0.0306, loss_cls: 0.1580, acc: 94.2482, loss_bbox: 0.2005, loss_mask: 0.2188, loss: 0.6293 2023-11-16 00:34:37,267 - mmdet - INFO - Saving checkpoint at 17 epochs 2023-11-16 00:35:26,002 - mmdet - INFO - Evaluating bbox... 2023-11-16 00:35:54,828 - 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 ] = 0.706 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.532 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.327 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.523 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 ] = 0.611 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.611 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.611 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.453 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 ] = 0.755 2023-11-16 00:35:54,830 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.586 | bicycle | 0.379 | car | 0.488 | | motorcycle | 0.498 | airplane | 0.717 | bus | 0.706 | | train | 0.674 | truck | 0.413 | boat | 0.323 | | traffic light | 0.304 | fire hydrant | 0.719 | stop sign | 0.667 | | parking meter | 0.514 | bench | 0.316 | bird | 0.411 | | cat | 0.747 | dog | 0.704 | horse | 0.643 | | sheep | 0.596 | cow | 0.609 | elephant | 0.674 | | bear | 0.747 | zebra | 0.699 | giraffe | 0.715 | | backpack | 0.232 | umbrella | 0.468 | handbag | 0.232 | | tie | 0.394 | suitcase | 0.466 | frisbee | 0.711 | | skis | 0.308 | snowboard | 0.446 | sports ball | 0.478 | | kite | 0.469 | baseball bat | 0.387 | baseball glove | 0.447 | | skateboard | 0.565 | surfboard | 0.459 | tennis racket | 0.561 | | bottle | 0.461 | wine glass | 0.434 | cup | 0.501 | | fork | 0.446 | knife | 0.287 | spoon | 0.308 | | bowl | 0.470 | banana | 0.278 | apple | 0.269 | | sandwich | 0.447 | orange | 0.364 | broccoli | 0.241 | | carrot | 0.269 | hot dog | 0.505 | pizza | 0.555 | | donut | 0.538 | cake | 0.441 | chair | 0.373 | | couch | 0.472 | potted plant | 0.359 | bed | 0.481 | | dining table | 0.308 | toilet | 0.647 | tv | 0.644 | | laptop | 0.696 | mouse | 0.653 | remote | 0.433 | | keyboard | 0.545 | cell phone | 0.448 | microwave | 0.656 | | oven | 0.418 | toaster | 0.525 | sink | 0.437 | | refrigerator | 0.657 | book | 0.202 | clock | 0.531 | | vase | 0.448 | scissors | 0.415 | teddy bear | 0.558 | | hair drier | 0.195 | toothbrush | 0.323 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-16 00:35:54,831 - mmdet - INFO - Evaluating segm... 2023-11-16 00:36:29,537 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.435 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.675 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.468 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.240 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 ] = 0.623 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 ] = 0.384 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.597 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.712 2023-11-16 00:36:29,539 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.512 | bicycle | 0.235 | car | 0.444 | | motorcycle | 0.400 | airplane | 0.552 | bus | 0.691 | | train | 0.674 | truck | 0.402 | boat | 0.294 | | traffic light | 0.293 | fire hydrant | 0.691 | stop sign | 0.648 | | parking meter | 0.521 | bench | 0.239 | bird | 0.340 | | cat | 0.739 | dog | 0.663 | horse | 0.486 | | sheep | 0.536 | cow | 0.510 | elephant | 0.622 | | bear | 0.716 | zebra | 0.610 | giraffe | 0.565 | | backpack | 0.231 | umbrella | 0.531 | handbag | 0.223 | | tie | 0.360 | suitcase | 0.499 | frisbee | 0.675 | | skis | 0.057 | snowboard | 0.299 | sports ball | 0.457 | | kite | 0.347 | baseball bat | 0.310 | baseball glove | 0.456 | | skateboard | 0.354 | surfboard | 0.370 | tennis racket | 0.603 | | bottle | 0.436 | wine glass | 0.388 | cup | 0.498 | | fork | 0.228 | knife | 0.207 | spoon | 0.206 | | bowl | 0.441 | banana | 0.229 | apple | 0.258 | | sandwich | 0.460 | orange | 0.359 | broccoli | 0.231 | | carrot | 0.238 | hot dog | 0.422 | pizza | 0.542 | | donut | 0.537 | cake | 0.446 | chair | 0.267 | | couch | 0.411 | potted plant | 0.304 | bed | 0.388 | | dining table | 0.191 | toilet | 0.638 | tv | 0.665 | | laptop | 0.676 | mouse | 0.626 | remote | 0.389 | | keyboard | 0.537 | cell phone | 0.423 | microwave | 0.667 | | oven | 0.380 | toaster | 0.576 | sink | 0.413 | | refrigerator | 0.666 | book | 0.151 | clock | 0.531 | | vase | 0.440 | scissors | 0.302 | teddy bear | 0.524 | | hair drier | 0.113 | toothbrush | 0.231 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-16 00:36:30,074 - mmdet - INFO - The previous best checkpoint /mnt/petrelfs/lizhiqi/DINO/detection/work_dirs/mask_rcnn_flash_internimage_s_fpn_3x_coco_0.4/best_bbox_mAP_epoch_16.pth was removed 2023-11-16 00:36:32,297 - mmdet - INFO - Now best checkpoint is saved as best_bbox_mAP_epoch_17.pth. 2023-11-16 00:36:32,298 - mmdet - INFO - Best bbox_mAP is 0.4839 at 17 epoch. 2023-11-16 00:36:32,298 - mmdet - INFO - Exp name: mask_rcnn_flash_internimage_s_fpn_3x_coco_0.4.py 2023-11-16 00:36:32,298 - mmdet - INFO - Epoch(val) [17][625] bbox_mAP: 0.4839, bbox_mAP_50: 0.7061, bbox_mAP_75: 0.5322, bbox_mAP_s: 0.3269, bbox_mAP_m: 0.5230, bbox_mAP_l: 0.6290, bbox_mAP_copypaste: 0.4839 0.7061 0.5322 0.3269 0.5230 0.6290, segm_mAP: 0.4349, segm_mAP_50: 0.6752, segm_mAP_75: 0.4682, segm_mAP_s: 0.2404, segm_mAP_m: 0.4693, segm_mAP_l: 0.6229, segm_mAP_copypaste: 0.4349 0.6752 0.4682 0.2404 0.4693 0.6229 2023-11-16 00:37:37,202 - mmdet - INFO - Epoch [18][50/1833] lr: 2.000e-04, eta: 11:27:21, time: 1.297, data_time: 0.136, memory: 16000, loss_rpn_cls: 0.0225, loss_rpn_bbox: 0.0316, loss_cls: 0.1529, acc: 94.3696, loss_bbox: 0.1984, loss_mask: 0.2163, loss: 0.6216 2023-11-16 00:38:37,402 - mmdet - INFO - Epoch [18][100/1833] lr: 2.000e-04, eta: 11:26:23, time: 1.204, data_time: 0.071, memory: 16000, loss_rpn_cls: 0.0223, loss_rpn_bbox: 0.0327, loss_cls: 0.1574, acc: 94.2159, loss_bbox: 0.2022, loss_mask: 0.2193, loss: 0.6339 2023-11-16 00:39:38,166 - mmdet - INFO - Epoch [18][150/1833] lr: 2.000e-04, eta: 11:25:25, time: 1.215, data_time: 0.070, memory: 16000, loss_rpn_cls: 0.0216, loss_rpn_bbox: 0.0304, loss_cls: 0.1540, acc: 94.3317, loss_bbox: 0.2005, loss_mask: 0.2127, loss: 0.6193 2023-11-16 00:40:38,223 - mmdet - INFO - Epoch [18][200/1833] lr: 2.000e-04, eta: 11:24:26, time: 1.201, data_time: 0.078, memory: 16000, loss_rpn_cls: 0.0229, loss_rpn_bbox: 0.0315, loss_cls: 0.1524, acc: 94.4330, loss_bbox: 0.1978, loss_mask: 0.2160, loss: 0.6206 2023-11-16 00:41:38,377 - mmdet - INFO - Epoch [18][250/1833] lr: 2.000e-04, eta: 11:23:28, time: 1.203, data_time: 0.066, memory: 16000, loss_rpn_cls: 0.0226, loss_rpn_bbox: 0.0313, loss_cls: 0.1545, acc: 94.3374, loss_bbox: 0.1983, loss_mask: 0.2191, loss: 0.6257 2023-11-16 00:42:39,087 - mmdet - INFO - Epoch [18][300/1833] lr: 2.000e-04, eta: 11:22:30, time: 1.214, data_time: 0.078, memory: 16000, loss_rpn_cls: 0.0208, loss_rpn_bbox: 0.0301, loss_cls: 0.1524, acc: 94.4000, loss_bbox: 0.1997, loss_mask: 0.2176, loss: 0.6206 2023-11-16 00:43:39,475 - mmdet - INFO - Epoch [18][350/1833] lr: 2.000e-04, eta: 11:21:32, time: 1.208, data_time: 0.079, memory: 16000, loss_rpn_cls: 0.0222, loss_rpn_bbox: 0.0314, loss_cls: 0.1584, acc: 94.1499, loss_bbox: 0.2035, loss_mask: 0.2177, loss: 0.6332 2023-11-16 00:44:40,834 - mmdet - INFO - Epoch [18][400/1833] lr: 2.000e-04, eta: 11:20:35, time: 1.227, data_time: 0.078, memory: 16000, loss_rpn_cls: 0.0220, loss_rpn_bbox: 0.0317, loss_cls: 0.1596, acc: 94.1326, loss_bbox: 0.2059, loss_mask: 0.2180, loss: 0.6371 2023-11-16 00:45:41,311 - mmdet - INFO - Epoch [18][450/1833] lr: 2.000e-04, eta: 11:19:37, time: 1.210, data_time: 0.073, memory: 16000, loss_rpn_cls: 0.0227, loss_rpn_bbox: 0.0318, loss_cls: 0.1575, acc: 94.2296, loss_bbox: 0.2024, loss_mask: 0.2170, loss: 0.6314 2023-11-16 00:46:40,898 - mmdet - INFO - Epoch [18][500/1833] lr: 2.000e-04, eta: 11:18:38, time: 1.192, data_time: 0.073, memory: 16000, loss_rpn_cls: 0.0212, loss_rpn_bbox: 0.0302, loss_cls: 0.1551, acc: 94.3092, loss_bbox: 0.1995, loss_mask: 0.2166, loss: 0.6226 2023-11-16 00:47:41,814 - mmdet - INFO - Epoch [18][550/1833] lr: 2.000e-04, eta: 11:17:41, time: 1.218, data_time: 0.068, memory: 16000, loss_rpn_cls: 0.0226, loss_rpn_bbox: 0.0328, loss_cls: 0.1607, acc: 94.1082, loss_bbox: 0.2050, loss_mask: 0.2201, loss: 0.6412 2023-11-16 00:48:40,912 - mmdet - INFO - Epoch [18][600/1833] lr: 2.000e-04, eta: 11:16:41, time: 1.182, data_time: 0.072, memory: 16000, loss_rpn_cls: 0.0219, loss_rpn_bbox: 0.0314, loss_cls: 0.1575, acc: 94.2098, loss_bbox: 0.2032, loss_mask: 0.2202, loss: 0.6342 2023-11-16 00:49:41,157 - mmdet - INFO - Epoch [18][650/1833] lr: 2.000e-04, eta: 11:15:43, time: 1.205, data_time: 0.073, memory: 16000, loss_rpn_cls: 0.0217, loss_rpn_bbox: 0.0313, loss_cls: 0.1546, acc: 94.3251, loss_bbox: 0.1988, loss_mask: 0.2160, loss: 0.6225 2023-11-16 00:50:41,156 - mmdet - INFO - Epoch [18][700/1833] lr: 2.000e-04, eta: 11:14:44, time: 1.200, data_time: 0.071, memory: 16000, loss_rpn_cls: 0.0211, loss_rpn_bbox: 0.0307, loss_cls: 0.1536, acc: 94.3360, loss_bbox: 0.1998, loss_mask: 0.2164, loss: 0.6217 2023-11-16 00:51:41,941 - mmdet - INFO - Epoch [18][750/1833] lr: 2.000e-04, eta: 11:13:46, time: 1.216, data_time: 0.073, memory: 16000, loss_rpn_cls: 0.0220, loss_rpn_bbox: 0.0319, loss_cls: 0.1603, acc: 94.1275, loss_bbox: 0.2043, loss_mask: 0.2179, loss: 0.6364 2023-11-16 00:52:42,863 - mmdet - INFO - Epoch [18][800/1833] lr: 2.000e-04, eta: 11:12:49, time: 1.218, data_time: 0.082, memory: 16000, loss_rpn_cls: 0.0237, loss_rpn_bbox: 0.0325, loss_cls: 0.1601, acc: 94.1818, loss_bbox: 0.2065, loss_mask: 0.2202, loss: 0.6431 2023-11-16 00:53:43,424 - mmdet - INFO - Epoch [18][850/1833] lr: 2.000e-04, eta: 11:11:51, time: 1.211, data_time: 0.074, memory: 16000, loss_rpn_cls: 0.0228, loss_rpn_bbox: 0.0327, loss_cls: 0.1585, acc: 94.2332, loss_bbox: 0.2025, loss_mask: 0.2217, loss: 0.6382 2023-11-16 00:54:44,556 - mmdet - INFO - Epoch [18][900/1833] lr: 2.000e-04, eta: 11:10:53, time: 1.223, data_time: 0.068, memory: 16000, loss_rpn_cls: 0.0222, loss_rpn_bbox: 0.0319, loss_cls: 0.1536, acc: 94.3669, loss_bbox: 0.1990, loss_mask: 0.2198, loss: 0.6265 2023-11-16 00:55:45,652 - mmdet - INFO - Epoch [18][950/1833] lr: 2.000e-04, eta: 11:09:56, time: 1.222, data_time: 0.077, memory: 16000, loss_rpn_cls: 0.0230, loss_rpn_bbox: 0.0325, loss_cls: 0.1558, acc: 94.2885, loss_bbox: 0.2015, loss_mask: 0.2219, loss: 0.6347 2023-11-16 00:56:46,984 - mmdet - INFO - Epoch [18][1000/1833] lr: 2.000e-04, eta: 11:08:59, time: 1.227, data_time: 0.074, memory: 16000, loss_rpn_cls: 0.0230, loss_rpn_bbox: 0.0322, loss_cls: 0.1616, acc: 94.1466, loss_bbox: 0.2070, loss_mask: 0.2222, loss: 0.6459 2023-11-16 00:57:46,015 - mmdet - INFO - Epoch [18][1050/1833] lr: 2.000e-04, eta: 11:07:59, time: 1.181, data_time: 0.070, memory: 16000, loss_rpn_cls: 0.0217, loss_rpn_bbox: 0.0308, loss_cls: 0.1531, acc: 94.4297, loss_bbox: 0.1970, loss_mask: 0.2183, loss: 0.6209 2023-11-16 00:58:46,971 - mmdet - INFO - Epoch [18][1100/1833] lr: 2.000e-04, eta: 11:07:01, time: 1.219, data_time: 0.063, memory: 16000, loss_rpn_cls: 0.0225, loss_rpn_bbox: 0.0312, loss_cls: 0.1616, acc: 94.1194, loss_bbox: 0.2044, loss_mask: 0.2166, loss: 0.6363 2023-11-16 00:59:46,795 - mmdet - INFO - Epoch [18][1150/1833] lr: 2.000e-04, eta: 11:06:03, time: 1.196, data_time: 0.073, memory: 16000, loss_rpn_cls: 0.0221, loss_rpn_bbox: 0.0326, loss_cls: 0.1608, acc: 94.0692, loss_bbox: 0.2073, loss_mask: 0.2173, loss: 0.6401 2023-11-16 01:00:46,385 - mmdet - INFO - Epoch [18][1200/1833] lr: 2.000e-04, eta: 11:05:04, time: 1.192, data_time: 0.070, memory: 16000, loss_rpn_cls: 0.0211, loss_rpn_bbox: 0.0315, loss_cls: 0.1572, acc: 94.2310, loss_bbox: 0.2032, loss_mask: 0.2180, loss: 0.6309 2023-11-16 01:01:47,718 - mmdet - INFO - Epoch [18][1250/1833] lr: 2.000e-04, eta: 11:04:06, time: 1.227, data_time: 0.071, memory: 16000, loss_rpn_cls: 0.0214, loss_rpn_bbox: 0.0315, loss_cls: 0.1589, acc: 94.1912, loss_bbox: 0.2036, loss_mask: 0.2153, loss: 0.6307 2023-11-16 01:02:47,826 - mmdet - INFO - Epoch [18][1300/1833] lr: 2.000e-04, eta: 11:03:08, time: 1.202, data_time: 0.075, memory: 16000, loss_rpn_cls: 0.0229, loss_rpn_bbox: 0.0321, loss_cls: 0.1596, acc: 94.2202, loss_bbox: 0.2013, loss_mask: 0.2197, loss: 0.6356 2023-11-16 01:03:49,190 - mmdet - INFO - Epoch [18][1350/1833] lr: 2.000e-04, eta: 11:02:10, time: 1.227, data_time: 0.073, memory: 16000, loss_rpn_cls: 0.0227, loss_rpn_bbox: 0.0320, loss_cls: 0.1566, acc: 94.2642, loss_bbox: 0.2035, loss_mask: 0.2177, loss: 0.6326 2023-11-16 01:04:48,396 - mmdet - INFO - Epoch [18][1400/1833] lr: 2.000e-04, eta: 11:01:11, time: 1.184, data_time: 0.066, memory: 16000, loss_rpn_cls: 0.0225, loss_rpn_bbox: 0.0313, loss_cls: 0.1537, acc: 94.3522, loss_bbox: 0.1998, loss_mask: 0.2184, loss: 0.6257 2023-11-16 01:05:47,815 - mmdet - INFO - Epoch [18][1450/1833] lr: 2.000e-04, eta: 11:00:12, time: 1.188, data_time: 0.066, memory: 16000, loss_rpn_cls: 0.0212, loss_rpn_bbox: 0.0312, loss_cls: 0.1570, acc: 94.2960, loss_bbox: 0.1987, loss_mask: 0.2186, loss: 0.6267 2023-11-16 01:06:47,719 - mmdet - INFO - Epoch [18][1500/1833] lr: 2.000e-04, eta: 10:59:13, time: 1.198, data_time: 0.073, memory: 16000, loss_rpn_cls: 0.0223, loss_rpn_bbox: 0.0311, loss_cls: 0.1587, acc: 94.2280, loss_bbox: 0.2039, loss_mask: 0.2186, loss: 0.6346 2023-11-16 01:07:48,764 - mmdet - INFO - Epoch [18][1550/1833] lr: 2.000e-04, eta: 10:58:15, time: 1.221, data_time: 0.072, memory: 16000, loss_rpn_cls: 0.0219, loss_rpn_bbox: 0.0323, loss_cls: 0.1595, acc: 94.1104, loss_bbox: 0.2039, loss_mask: 0.2197, loss: 0.6373 2023-11-16 01:08:49,367 - mmdet - INFO - Epoch [18][1600/1833] lr: 2.000e-04, eta: 10:57:17, time: 1.212, data_time: 0.077, memory: 16000, loss_rpn_cls: 0.0218, loss_rpn_bbox: 0.0308, loss_cls: 0.1577, acc: 94.2388, loss_bbox: 0.1995, loss_mask: 0.2182, loss: 0.6279 2023-11-16 01:09:50,312 - mmdet - INFO - Epoch [18][1650/1833] lr: 2.000e-04, eta: 10:56:20, time: 1.219, data_time: 0.074, memory: 16000, loss_rpn_cls: 0.0216, loss_rpn_bbox: 0.0311, loss_cls: 0.1587, acc: 94.2228, loss_bbox: 0.2001, loss_mask: 0.2154, loss: 0.6269 2023-11-16 01:10:51,727 - mmdet - INFO - Epoch [18][1700/1833] lr: 2.000e-04, eta: 10:55:22, time: 1.228, data_time: 0.076, memory: 16000, loss_rpn_cls: 0.0239, loss_rpn_bbox: 0.0319, loss_cls: 0.1617, acc: 94.0699, loss_bbox: 0.2067, loss_mask: 0.2207, loss: 0.6450 2023-11-16 01:11:52,988 - mmdet - INFO - Epoch [18][1750/1833] lr: 2.000e-04, eta: 10:54:25, time: 1.225, data_time: 0.070, memory: 16000, loss_rpn_cls: 0.0235, loss_rpn_bbox: 0.0322, loss_cls: 0.1612, acc: 94.0937, loss_bbox: 0.2047, loss_mask: 0.2197, loss: 0.6412 2023-11-16 01:12:53,228 - mmdet - INFO - Epoch [18][1800/1833] lr: 2.000e-04, eta: 10:53:26, time: 1.205, data_time: 0.072, memory: 16000, loss_rpn_cls: 0.0217, loss_rpn_bbox: 0.0307, loss_cls: 0.1556, acc: 94.3290, loss_bbox: 0.2022, loss_mask: 0.2161, loss: 0.6263 2023-11-16 01:13:33,905 - mmdet - INFO - Saving checkpoint at 18 epochs 2023-11-16 01:14:19,667 - mmdet - INFO - Evaluating bbox... 2023-11-16 01:14:50,034 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.483 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.704 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.531 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.328 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.523 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 ] = 0.611 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.611 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.611 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.449 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 ] = 0.758 2023-11-16 01:14:50,037 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.581 | bicycle | 0.384 | car | 0.498 | | motorcycle | 0.497 | airplane | 0.691 | bus | 0.703 | | train | 0.696 | truck | 0.447 | boat | 0.325 | | traffic light | 0.315 | fire hydrant | 0.728 | stop sign | 0.683 | | parking meter | 0.508 | bench | 0.300 | bird | 0.425 | | cat | 0.723 | dog | 0.695 | horse | 0.645 | | sheep | 0.611 | cow | 0.618 | elephant | 0.693 | | bear | 0.768 | zebra | 0.667 | giraffe | 0.676 | | backpack | 0.215 | umbrella | 0.475 | handbag | 0.231 | | tie | 0.397 | suitcase | 0.473 | frisbee | 0.727 | | skis | 0.279 | snowboard | 0.438 | sports ball | 0.476 | | kite | 0.466 | baseball bat | 0.440 | baseball glove | 0.450 | | skateboard | 0.592 | surfboard | 0.450 | tennis racket | 0.567 | | bottle | 0.454 | wine glass | 0.436 | cup | 0.497 | | fork | 0.481 | knife | 0.283 | spoon | 0.289 | | bowl | 0.470 | banana | 0.286 | apple | 0.268 | | sandwich | 0.484 | orange | 0.358 | broccoli | 0.264 | | carrot | 0.261 | hot dog | 0.424 | pizza | 0.559 | | donut | 0.533 | cake | 0.450 | chair | 0.361 | | couch | 0.493 | potted plant | 0.349 | bed | 0.479 | | dining table | 0.310 | toilet | 0.656 | tv | 0.631 | | laptop | 0.679 | mouse | 0.655 | remote | 0.438 | | keyboard | 0.553 | cell phone | 0.457 | microwave | 0.623 | | oven | 0.420 | toaster | 0.457 | sink | 0.435 | | refrigerator | 0.645 | book | 0.193 | clock | 0.517 | | vase | 0.443 | scissors | 0.406 | teddy bear | 0.543 | | hair drier | 0.157 | toothbrush | 0.362 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-16 01:14:50,037 - mmdet - INFO - Evaluating segm... 2023-11-16 01:15:21,497 - 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 ] = 0.673 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.462 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 ] = 0.466 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 ] = 0.553 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.553 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.553 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 ] = 0.593 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.710 2023-11-16 01:15:21,500 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.505 | bicycle | 0.230 | car | 0.446 | | motorcycle | 0.412 | airplane | 0.544 | bus | 0.687 | | train | 0.676 | truck | 0.422 | boat | 0.294 | | traffic light | 0.310 | fire hydrant | 0.693 | stop sign | 0.672 | | parking meter | 0.513 | bench | 0.223 | bird | 0.348 | | cat | 0.729 | dog | 0.655 | horse | 0.487 | | sheep | 0.536 | cow | 0.518 | elephant | 0.635 | | bear | 0.755 | zebra | 0.588 | giraffe | 0.530 | | backpack | 0.217 | umbrella | 0.533 | handbag | 0.211 | | tie | 0.346 | suitcase | 0.503 | frisbee | 0.665 | | skis | 0.059 | snowboard | 0.287 | sports ball | 0.464 | | kite | 0.328 | baseball bat | 0.306 | baseball glove | 0.459 | | skateboard | 0.387 | surfboard | 0.362 | tennis racket | 0.611 | | bottle | 0.433 | wine glass | 0.400 | cup | 0.494 | | fork | 0.231 | knife | 0.186 | spoon | 0.187 | | bowl | 0.437 | banana | 0.234 | apple | 0.257 | | sandwich | 0.507 | orange | 0.353 | broccoli | 0.240 | | carrot | 0.223 | hot dog | 0.346 | pizza | 0.539 | | donut | 0.528 | cake | 0.451 | chair | 0.252 | | couch | 0.423 | potted plant | 0.295 | bed | 0.396 | | dining table | 0.184 | toilet | 0.637 | tv | 0.658 | | laptop | 0.672 | mouse | 0.627 | remote | 0.396 | | keyboard | 0.537 | cell phone | 0.427 | microwave | 0.662 | | oven | 0.373 | toaster | 0.506 | sink | 0.418 | | refrigerator | 0.645 | book | 0.144 | clock | 0.515 | | vase | 0.436 | scissors | 0.325 | teddy bear | 0.506 | | hair drier | 0.060 | toothbrush | 0.237 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-16 01:15:21,972 - mmdet - INFO - Exp name: mask_rcnn_flash_internimage_s_fpn_3x_coco_0.4.py 2023-11-16 01:15:21,972 - mmdet - INFO - Epoch(val) [18][625] bbox_mAP: 0.4827, bbox_mAP_50: 0.7039, bbox_mAP_75: 0.5314, bbox_mAP_s: 0.3279, bbox_mAP_m: 0.5231, bbox_mAP_l: 0.6210, bbox_mAP_copypaste: 0.4827 0.7039 0.5314 0.3279 0.5231 0.6210, segm_mAP: 0.4316, segm_mAP_50: 0.6728, segm_mAP_75: 0.4620, segm_mAP_s: 0.2361, segm_mAP_m: 0.4658, segm_mAP_l: 0.6222, segm_mAP_copypaste: 0.4316 0.6728 0.4620 0.2361 0.4658 0.6222 2023-11-16 01:16:26,063 - mmdet - INFO - Epoch [19][50/1833] lr: 2.000e-04, eta: 10:51:14, time: 1.281, data_time: 0.144, memory: 16000, loss_rpn_cls: 0.0215, loss_rpn_bbox: 0.0304, loss_cls: 0.1525, acc: 94.4210, loss_bbox: 0.1953, loss_mask: 0.2169, loss: 0.6166 2023-11-16 01:17:26,608 - mmdet - INFO - Epoch [19][100/1833] lr: 2.000e-04, eta: 10:50:15, time: 1.211, data_time: 0.068, memory: 16000, loss_rpn_cls: 0.0211, loss_rpn_bbox: 0.0312, loss_cls: 0.1533, acc: 94.3632, loss_bbox: 0.2016, loss_mask: 0.2168, loss: 0.6239 2023-11-16 01:18:27,127 - mmdet - INFO - Epoch [19][150/1833] lr: 2.000e-04, eta: 10:49:17, time: 1.210, data_time: 0.079, memory: 16000, loss_rpn_cls: 0.0211, loss_rpn_bbox: 0.0303, loss_cls: 0.1546, acc: 94.3577, loss_bbox: 0.2007, loss_mask: 0.2191, loss: 0.6258 2023-11-16 01:19:28,223 - mmdet - INFO - Epoch [19][200/1833] lr: 2.000e-04, eta: 10:48:20, time: 1.222, data_time: 0.067, memory: 16000, loss_rpn_cls: 0.0221, loss_rpn_bbox: 0.0311, loss_cls: 0.1533, acc: 94.3388, loss_bbox: 0.1976, loss_mask: 0.2131, loss: 0.6173 2023-11-16 01:20:29,191 - mmdet - INFO - Epoch [19][250/1833] lr: 2.000e-04, eta: 10:47:22, time: 1.219, data_time: 0.073, memory: 16000, loss_rpn_cls: 0.0220, loss_rpn_bbox: 0.0319, loss_cls: 0.1560, acc: 94.2285, loss_bbox: 0.2020, loss_mask: 0.2202, loss: 0.6321 2023-11-16 01:21:29,141 - mmdet - INFO - Epoch [19][300/1833] lr: 2.000e-04, eta: 10:46:23, time: 1.199, data_time: 0.067, memory: 16000, loss_rpn_cls: 0.0213, loss_rpn_bbox: 0.0306, loss_cls: 0.1548, acc: 94.3269, loss_bbox: 0.2001, loss_mask: 0.2166, loss: 0.6234 2023-11-16 01:22:29,970 - mmdet - INFO - Epoch [19][350/1833] lr: 2.000e-04, eta: 10:45:26, time: 1.217, data_time: 0.070, memory: 16000, loss_rpn_cls: 0.0212, loss_rpn_bbox: 0.0320, loss_cls: 0.1540, acc: 94.3071, loss_bbox: 0.2002, loss_mask: 0.2165, loss: 0.6240 2023-11-16 01:23:30,759 - mmdet - INFO - Epoch [19][400/1833] lr: 2.000e-04, eta: 10:44:28, time: 1.216, data_time: 0.071, memory: 16000, loss_rpn_cls: 0.0206, loss_rpn_bbox: 0.0307, loss_cls: 0.1575, acc: 94.2477, loss_bbox: 0.2044, loss_mask: 0.2190, loss: 0.6322 2023-11-16 01:24:31,685 - mmdet - INFO - Epoch [19][450/1833] lr: 2.000e-04, eta: 10:43:30, time: 1.219, data_time: 0.068, memory: 16000, loss_rpn_cls: 0.0220, loss_rpn_bbox: 0.0316, loss_cls: 0.1599, acc: 94.1527, loss_bbox: 0.2042, loss_mask: 0.2198, loss: 0.6375 2023-11-16 01:25:31,686 - mmdet - INFO - Epoch [19][500/1833] lr: 2.000e-04, eta: 10:42:31, time: 1.200, data_time: 0.075, memory: 16000, loss_rpn_cls: 0.0221, loss_rpn_bbox: 0.0313, loss_cls: 0.1547, acc: 94.3104, loss_bbox: 0.2015, loss_mask: 0.2147, loss: 0.6242 2023-11-16 01:26:31,092 - mmdet - INFO - Epoch [19][550/1833] lr: 2.000e-04, eta: 10:41:32, time: 1.188, data_time: 0.076, memory: 16000, loss_rpn_cls: 0.0220, loss_rpn_bbox: 0.0312, loss_cls: 0.1550, acc: 94.3194, loss_bbox: 0.1992, loss_mask: 0.2161, loss: 0.6235 2023-11-16 01:27:30,764 - mmdet - INFO - Epoch [19][600/1833] lr: 2.000e-04, eta: 10:40:33, time: 1.193, data_time: 0.062, memory: 16000, loss_rpn_cls: 0.0220, loss_rpn_bbox: 0.0318, loss_cls: 0.1534, acc: 94.3824, loss_bbox: 0.1986, loss_mask: 0.2164, loss: 0.6222 2023-11-16 01:28:30,391 - mmdet - INFO - Epoch [19][650/1833] lr: 2.000e-04, eta: 10:39:34, time: 1.193, data_time: 0.063, memory: 16000, loss_rpn_cls: 0.0222, loss_rpn_bbox: 0.0319, loss_cls: 0.1541, acc: 94.2968, loss_bbox: 0.2021, loss_mask: 0.2183, loss: 0.6286 2023-11-16 01:29:29,789 - mmdet - INFO - Epoch [19][700/1833] lr: 2.000e-04, eta: 10:38:35, time: 1.188, data_time: 0.071, memory: 16000, loss_rpn_cls: 0.0216, loss_rpn_bbox: 0.0310, loss_cls: 0.1552, acc: 94.2679, loss_bbox: 0.1995, loss_mask: 0.2165, loss: 0.6239 2023-11-16 01:30:29,765 - mmdet - INFO - Epoch [19][750/1833] lr: 2.000e-04, eta: 10:37:36, time: 1.200, data_time: 0.067, memory: 16000, loss_rpn_cls: 0.0234, loss_rpn_bbox: 0.0320, loss_cls: 0.1546, acc: 94.3239, loss_bbox: 0.1999, loss_mask: 0.2177, loss: 0.6277 2023-11-16 01:31:30,524 - mmdet - INFO - Epoch [19][800/1833] lr: 2.000e-04, eta: 10:36:38, time: 1.215, data_time: 0.066, memory: 16000, loss_rpn_cls: 0.0228, loss_rpn_bbox: 0.0317, loss_cls: 0.1557, acc: 94.3412, loss_bbox: 0.1978, loss_mask: 0.2188, loss: 0.6267 2023-11-16 01:32:31,106 - mmdet - INFO - Epoch [19][850/1833] lr: 2.000e-04, eta: 10:35:40, time: 1.212, data_time: 0.066, memory: 16000, loss_rpn_cls: 0.0218, loss_rpn_bbox: 0.0319, loss_cls: 0.1597, acc: 94.1470, loss_bbox: 0.2029, loss_mask: 0.2187, loss: 0.6349 2023-11-16 01:33:31,073 - mmdet - INFO - Epoch [19][900/1833] lr: 2.000e-04, eta: 10:34:41, time: 1.199, data_time: 0.070, memory: 16000, loss_rpn_cls: 0.0230, loss_rpn_bbox: 0.0322, loss_cls: 0.1581, acc: 94.2308, loss_bbox: 0.2031, loss_mask: 0.2177, loss: 0.6341 2023-11-16 01:34:30,650 - mmdet - INFO - Epoch [19][950/1833] lr: 2.000e-04, eta: 10:33:42, time: 1.191, data_time: 0.071, memory: 16000, loss_rpn_cls: 0.0219, loss_rpn_bbox: 0.0307, loss_cls: 0.1547, acc: 94.3816, loss_bbox: 0.1976, loss_mask: 0.2163, loss: 0.6212 2023-11-16 01:35:30,124 - mmdet - INFO - Epoch [19][1000/1833] lr: 2.000e-04, eta: 10:32:43, time: 1.189, data_time: 0.071, memory: 16000, loss_rpn_cls: 0.0211, loss_rpn_bbox: 0.0311, loss_cls: 0.1573, acc: 94.2405, loss_bbox: 0.2025, loss_mask: 0.2179, loss: 0.6299 2023-11-16 01:36:29,600 - mmdet - INFO - Epoch [19][1050/1833] lr: 2.000e-04, eta: 10:31:44, time: 1.190, data_time: 0.066, memory: 16000, loss_rpn_cls: 0.0225, loss_rpn_bbox: 0.0313, loss_cls: 0.1571, acc: 94.1909, loss_bbox: 0.2010, loss_mask: 0.2187, loss: 0.6306 2023-11-16 01:37:29,406 - mmdet - INFO - Epoch [19][1100/1833] lr: 2.000e-04, eta: 10:30:45, time: 1.196, data_time: 0.075, memory: 16000, loss_rpn_cls: 0.0231, loss_rpn_bbox: 0.0314, loss_cls: 0.1587, acc: 94.1937, loss_bbox: 0.2035, loss_mask: 0.2161, loss: 0.6328 2023-11-16 01:38:29,281 - mmdet - INFO - Epoch [19][1150/1833] lr: 2.000e-04, eta: 10:29:46, time: 1.197, data_time: 0.065, memory: 16000, loss_rpn_cls: 0.0199, loss_rpn_bbox: 0.0309, loss_cls: 0.1533, acc: 94.3403, loss_bbox: 0.2013, loss_mask: 0.2179, loss: 0.6233 2023-11-16 01:39:28,011 - mmdet - INFO - Epoch [19][1200/1833] lr: 2.000e-04, eta: 10:28:46, time: 1.175, data_time: 0.072, memory: 16000, loss_rpn_cls: 0.0217, loss_rpn_bbox: 0.0315, loss_cls: 0.1564, acc: 94.3378, loss_bbox: 0.1988, loss_mask: 0.2161, loss: 0.6246 2023-11-16 01:40:28,220 - mmdet - INFO - Epoch [19][1250/1833] lr: 2.000e-04, eta: 10:27:48, time: 1.204, data_time: 0.070, memory: 16000, loss_rpn_cls: 0.0219, loss_rpn_bbox: 0.0322, loss_cls: 0.1580, acc: 94.2086, loss_bbox: 0.2031, loss_mask: 0.2163, loss: 0.6314 2023-11-16 01:41:28,217 - mmdet - INFO - Epoch [19][1300/1833] lr: 2.000e-04, eta: 10:26:49, time: 1.200, data_time: 0.066, memory: 16000, loss_rpn_cls: 0.0227, loss_rpn_bbox: 0.0320, loss_cls: 0.1627, acc: 94.0487, loss_bbox: 0.2085, loss_mask: 0.2204, loss: 0.6463 2023-11-16 01:42:28,081 - mmdet - INFO - Epoch [19][1350/1833] lr: 2.000e-04, eta: 10:25:50, time: 1.197, data_time: 0.060, memory: 16000, loss_rpn_cls: 0.0213, loss_rpn_bbox: 0.0310, loss_cls: 0.1550, acc: 94.3785, loss_bbox: 0.2008, loss_mask: 0.2166, loss: 0.6247 2023-11-16 01:43:28,967 - mmdet - INFO - Epoch [19][1400/1833] lr: 2.000e-04, eta: 10:24:52, time: 1.218, data_time: 0.062, memory: 16000, loss_rpn_cls: 0.0222, loss_rpn_bbox: 0.0316, loss_cls: 0.1558, acc: 94.2724, loss_bbox: 0.2008, loss_mask: 0.2185, loss: 0.6289 2023-11-16 01:44:28,694 - mmdet - INFO - Epoch [19][1450/1833] lr: 2.000e-04, eta: 10:23:53, time: 1.195, data_time: 0.076, memory: 16000, loss_rpn_cls: 0.0228, loss_rpn_bbox: 0.0316, loss_cls: 0.1590, acc: 94.1984, loss_bbox: 0.2042, loss_mask: 0.2153, loss: 0.6328 2023-11-16 01:45:29,507 - mmdet - INFO - Epoch [19][1500/1833] lr: 2.000e-04, eta: 10:22:55, time: 1.216, data_time: 0.062, memory: 16000, loss_rpn_cls: 0.0210, loss_rpn_bbox: 0.0310, loss_cls: 0.1561, acc: 94.3216, loss_bbox: 0.1977, loss_mask: 0.2158, loss: 0.6216 2023-11-16 01:46:30,155 - mmdet - INFO - Epoch [19][1550/1833] lr: 2.000e-04, eta: 10:21:57, time: 1.213, data_time: 0.083, memory: 16000, loss_rpn_cls: 0.0220, loss_rpn_bbox: 0.0315, loss_cls: 0.1566, acc: 94.2301, loss_bbox: 0.2009, loss_mask: 0.2192, loss: 0.6303 2023-11-16 01:47:29,023 - mmdet - INFO - Epoch [19][1600/1833] lr: 2.000e-04, eta: 10:20:57, time: 1.177, data_time: 0.058, memory: 16000, loss_rpn_cls: 0.0218, loss_rpn_bbox: 0.0302, loss_cls: 0.1525, acc: 94.4637, loss_bbox: 0.1944, loss_mask: 0.2182, loss: 0.6171 2023-11-16 01:48:29,084 - mmdet - INFO - Epoch [19][1650/1833] lr: 2.000e-04, eta: 10:19:59, time: 1.201, data_time: 0.057, memory: 16000, loss_rpn_cls: 0.0225, loss_rpn_bbox: 0.0320, loss_cls: 0.1584, acc: 94.1735, loss_bbox: 0.2045, loss_mask: 0.2213, loss: 0.6386 2023-11-16 01:49:28,700 - mmdet - INFO - Epoch [19][1700/1833] lr: 2.000e-04, eta: 10:19:00, time: 1.192, data_time: 0.071, memory: 16000, loss_rpn_cls: 0.0216, loss_rpn_bbox: 0.0316, loss_cls: 0.1576, acc: 94.2732, loss_bbox: 0.2020, loss_mask: 0.2182, loss: 0.6309 2023-11-16 01:50:29,037 - mmdet - INFO - Epoch [19][1750/1833] lr: 2.000e-04, eta: 10:18:01, time: 1.207, data_time: 0.066, memory: 16000, loss_rpn_cls: 0.0213, loss_rpn_bbox: 0.0309, loss_cls: 0.1573, acc: 94.2580, loss_bbox: 0.2033, loss_mask: 0.2182, loss: 0.6311 2023-11-16 01:51:28,914 - mmdet - INFO - Epoch [19][1800/1833] lr: 2.000e-04, eta: 10:17:02, time: 1.198, data_time: 0.077, memory: 16000, loss_rpn_cls: 0.0217, loss_rpn_bbox: 0.0306, loss_cls: 0.1552, acc: 94.3295, loss_bbox: 0.2000, loss_mask: 0.2206, loss: 0.6281 2023-11-16 01:52:10,681 - mmdet - INFO - Saving checkpoint at 19 epochs 2023-11-16 01:53:00,761 - mmdet - INFO - Evaluating bbox... 2023-11-16 01:53:28,540 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.485 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.701 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.533 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.317 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.527 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 ] = 0.613 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 ] = 0.437 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.654 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.754 2023-11-16 01:53:28,543 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.591 | bicycle | 0.389 | car | 0.495 | | motorcycle | 0.482 | airplane | 0.701 | bus | 0.701 | | train | 0.706 | truck | 0.441 | boat | 0.327 | | traffic light | 0.305 | fire hydrant | 0.736 | stop sign | 0.698 | | parking meter | 0.528 | bench | 0.316 | bird | 0.420 | | cat | 0.741 | dog | 0.683 | horse | 0.623 | | sheep | 0.593 | cow | 0.612 | elephant | 0.666 | | bear | 0.707 | zebra | 0.696 | giraffe | 0.703 | | backpack | 0.214 | umbrella | 0.481 | handbag | 0.234 | | tie | 0.386 | suitcase | 0.468 | frisbee | 0.711 | | skis | 0.307 | snowboard | 0.450 | sports ball | 0.474 | | kite | 0.470 | baseball bat | 0.440 | baseball glove | 0.443 | | skateboard | 0.595 | surfboard | 0.465 | tennis racket | 0.575 | | bottle | 0.451 | wine glass | 0.413 | cup | 0.503 | | fork | 0.486 | knife | 0.289 | spoon | 0.312 | | bowl | 0.481 | banana | 0.280 | apple | 0.241 | | sandwich | 0.446 | orange | 0.335 | broccoli | 0.253 | | carrot | 0.251 | hot dog | 0.517 | pizza | 0.555 | | donut | 0.563 | cake | 0.421 | chair | 0.369 | | couch | 0.496 | potted plant | 0.358 | bed | 0.472 | | dining table | 0.311 | toilet | 0.641 | tv | 0.638 | | laptop | 0.688 | mouse | 0.674 | remote | 0.418 | | keyboard | 0.549 | cell phone | 0.448 | microwave | 0.645 | | oven | 0.426 | toaster | 0.538 | sink | 0.434 | | refrigerator | 0.643 | book | 0.207 | clock | 0.515 | | vase | 0.455 | scissors | 0.432 | teddy bear | 0.514 | | hair drier | 0.229 | toothbrush | 0.309 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-16 01:53:28,543 - mmdet - INFO - Evaluating segm... 2023-11-16 01:54:01,638 - 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 ] = 0.673 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.467 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.234 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 ] = 0.618 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.553 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.553 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.553 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.376 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.594 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.710 2023-11-16 01:54:01,641 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.512 | bicycle | 0.238 | car | 0.447 | | motorcycle | 0.401 | airplane | 0.546 | bus | 0.688 | | train | 0.691 | truck | 0.425 | boat | 0.293 | | traffic light | 0.293 | fire hydrant | 0.699 | stop sign | 0.670 | | parking meter | 0.525 | bench | 0.247 | bird | 0.348 | | cat | 0.721 | dog | 0.639 | horse | 0.463 | | sheep | 0.529 | cow | 0.517 | elephant | 0.619 | | bear | 0.708 | zebra | 0.615 | giraffe | 0.552 | | backpack | 0.221 | umbrella | 0.526 | handbag | 0.212 | | tie | 0.364 | suitcase | 0.500 | frisbee | 0.676 | | skis | 0.067 | snowboard | 0.275 | sports ball | 0.463 | | kite | 0.336 | baseball bat | 0.323 | baseball glove | 0.462 | | skateboard | 0.378 | surfboard | 0.381 | tennis racket | 0.613 | | bottle | 0.430 | wine glass | 0.385 | cup | 0.501 | | fork | 0.250 | knife | 0.198 | spoon | 0.210 | | bowl | 0.454 | banana | 0.232 | apple | 0.235 | | sandwich | 0.461 | orange | 0.335 | broccoli | 0.238 | | carrot | 0.222 | hot dog | 0.440 | pizza | 0.536 | | donut | 0.557 | cake | 0.420 | chair | 0.267 | | couch | 0.410 | potted plant | 0.297 | bed | 0.363 | | dining table | 0.184 | toilet | 0.638 | tv | 0.664 | | laptop | 0.675 | mouse | 0.643 | remote | 0.384 | | keyboard | 0.541 | cell phone | 0.416 | microwave | 0.643 | | oven | 0.371 | toaster | 0.568 | sink | 0.399 | | refrigerator | 0.629 | book | 0.158 | clock | 0.504 | | vase | 0.434 | scissors | 0.304 | teddy bear | 0.488 | | hair drier | 0.173 | toothbrush | 0.242 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-16 01:54:02,036 - mmdet - INFO - The previous best checkpoint /mnt/petrelfs/lizhiqi/DINO/detection/work_dirs/mask_rcnn_flash_internimage_s_fpn_3x_coco_0.4/best_bbox_mAP_epoch_17.pth was removed 2023-11-16 01:54:04,170 - mmdet - INFO - Now best checkpoint is saved as best_bbox_mAP_epoch_19.pth. 2023-11-16 01:54:04,170 - mmdet - INFO - Best bbox_mAP is 0.4848 at 19 epoch. 2023-11-16 01:54:04,170 - mmdet - INFO - Exp name: mask_rcnn_flash_internimage_s_fpn_3x_coco_0.4.py 2023-11-16 01:54:04,170 - mmdet - INFO - Epoch(val) [19][625] bbox_mAP: 0.4848, bbox_mAP_50: 0.7011, bbox_mAP_75: 0.5329, bbox_mAP_s: 0.3173, bbox_mAP_m: 0.5275, bbox_mAP_l: 0.6247, bbox_mAP_copypaste: 0.4848 0.7011 0.5329 0.3173 0.5275 0.6247, segm_mAP: 0.4335, segm_mAP_50: 0.6730, segm_mAP_75: 0.4666, segm_mAP_s: 0.2340, segm_mAP_m: 0.4684, segm_mAP_l: 0.6179, segm_mAP_copypaste: 0.4335 0.6730 0.4666 0.2340 0.4684 0.6179 2023-11-16 01:55:08,628 - mmdet - INFO - Epoch [20][50/1833] lr: 2.000e-04, eta: 10:14:53, time: 1.289, data_time: 0.137, memory: 16000, loss_rpn_cls: 0.0201, loss_rpn_bbox: 0.0306, loss_cls: 0.1540, acc: 94.3538, loss_bbox: 0.1997, loss_mask: 0.2139, loss: 0.6183 2023-11-16 01:56:09,472 - mmdet - INFO - Epoch [20][100/1833] lr: 2.000e-04, eta: 10:13:55, time: 1.217, data_time: 0.079, memory: 16000, loss_rpn_cls: 0.0211, loss_rpn_bbox: 0.0312, loss_cls: 0.1548, acc: 94.3323, loss_bbox: 0.2025, loss_mask: 0.2166, loss: 0.6261 2023-11-16 01:57:10,085 - mmdet - INFO - Epoch [20][150/1833] lr: 2.000e-04, eta: 10:12:57, time: 1.212, data_time: 0.080, memory: 16000, loss_rpn_cls: 0.0216, loss_rpn_bbox: 0.0311, loss_cls: 0.1510, acc: 94.4436, loss_bbox: 0.1984, loss_mask: 0.2166, loss: 0.6188 2023-11-16 01:58:11,691 - mmdet - INFO - Epoch [20][200/1833] lr: 2.000e-04, eta: 10:12:00, time: 1.232, data_time: 0.084, memory: 16000, loss_rpn_cls: 0.0214, loss_rpn_bbox: 0.0315, loss_cls: 0.1523, acc: 94.3677, loss_bbox: 0.1983, loss_mask: 0.2189, loss: 0.6225 2023-11-16 01:59:13,271 - mmdet - INFO - Epoch [20][250/1833] lr: 2.000e-04, eta: 10:11:03, time: 1.232, data_time: 0.088, memory: 16000, loss_rpn_cls: 0.0223, loss_rpn_bbox: 0.0325, loss_cls: 0.1556, acc: 94.2600, loss_bbox: 0.2033, loss_mask: 0.2167, loss: 0.6304 2023-11-16 02:00:13,403 - mmdet - INFO - Epoch [20][300/1833] lr: 2.000e-04, eta: 10:10:04, time: 1.203, data_time: 0.082, memory: 16000, loss_rpn_cls: 0.0210, loss_rpn_bbox: 0.0309, loss_cls: 0.1519, acc: 94.3660, loss_bbox: 0.1977, loss_mask: 0.2165, loss: 0.6180 2023-11-16 02:01:12,899 - mmdet - INFO - Epoch [20][350/1833] lr: 2.000e-04, eta: 10:09:05, time: 1.190, data_time: 0.080, memory: 16000, loss_rpn_cls: 0.0217, loss_rpn_bbox: 0.0321, loss_cls: 0.1523, acc: 94.4108, loss_bbox: 0.1997, loss_mask: 0.2173, loss: 0.6230 2023-11-16 02:02:14,599 - mmdet - INFO - Epoch [20][400/1833] lr: 2.000e-04, eta: 10:08:08, time: 1.234, data_time: 0.083, memory: 16000, loss_rpn_cls: 0.0212, loss_rpn_bbox: 0.0308, loss_cls: 0.1528, acc: 94.3929, loss_bbox: 0.1977, loss_mask: 0.2144, loss: 0.6170 2023-11-16 02:03:15,983 - mmdet - INFO - Epoch [20][450/1833] lr: 2.000e-04, eta: 10:07:10, time: 1.228, data_time: 0.083, memory: 16000, loss_rpn_cls: 0.0205, loss_rpn_bbox: 0.0311, loss_cls: 0.1516, acc: 94.3515, loss_bbox: 0.2012, loss_mask: 0.2164, loss: 0.6208 2023-11-16 02:04:15,718 - mmdet - INFO - Epoch [20][500/1833] lr: 2.000e-04, eta: 10:06:11, time: 1.195, data_time: 0.082, memory: 16000, loss_rpn_cls: 0.0210, loss_rpn_bbox: 0.0306, loss_cls: 0.1524, acc: 94.3660, loss_bbox: 0.1981, loss_mask: 0.2123, loss: 0.6144 2023-11-16 02:05:17,047 - mmdet - INFO - Epoch [20][550/1833] lr: 2.000e-04, eta: 10:05:14, time: 1.227, data_time: 0.077, memory: 16000, loss_rpn_cls: 0.0208, loss_rpn_bbox: 0.0312, loss_cls: 0.1546, acc: 94.3110, loss_bbox: 0.1996, loss_mask: 0.2156, loss: 0.6218 2023-11-16 02:06:17,163 - mmdet - INFO - Epoch [20][600/1833] lr: 2.000e-04, eta: 10:04:15, time: 1.202, data_time: 0.072, memory: 16000, loss_rpn_cls: 0.0211, loss_rpn_bbox: 0.0307, loss_cls: 0.1531, acc: 94.3870, loss_bbox: 0.1983, loss_mask: 0.2145, loss: 0.6178 2023-11-16 02:07:17,187 - mmdet - INFO - Epoch [20][650/1833] lr: 2.000e-04, eta: 10:03:16, time: 1.200, data_time: 0.083, memory: 16000, loss_rpn_cls: 0.0213, loss_rpn_bbox: 0.0315, loss_cls: 0.1584, acc: 94.1621, loss_bbox: 0.2038, loss_mask: 0.2187, loss: 0.6337 2023-11-16 02:08:16,717 - mmdet - INFO - Epoch [20][700/1833] lr: 2.000e-04, eta: 10:02:17, time: 1.191, data_time: 0.080, memory: 16000, loss_rpn_cls: 0.0197, loss_rpn_bbox: 0.0294, loss_cls: 0.1488, acc: 94.5567, loss_bbox: 0.1917, loss_mask: 0.2123, loss: 0.6019 2023-11-16 02:09:16,923 - mmdet - INFO - Epoch [20][750/1833] lr: 2.000e-04, eta: 10:01:19, time: 1.204, data_time: 0.089, memory: 16000, loss_rpn_cls: 0.0212, loss_rpn_bbox: 0.0311, loss_cls: 0.1525, acc: 94.3907, loss_bbox: 0.1942, loss_mask: 0.2156, loss: 0.6145 2023-11-16 02:10:17,828 - mmdet - INFO - Epoch [20][800/1833] lr: 2.000e-04, eta: 10:00:21, time: 1.218, data_time: 0.083, memory: 16000, loss_rpn_cls: 0.0208, loss_rpn_bbox: 0.0305, loss_cls: 0.1528, acc: 94.3710, loss_bbox: 0.1972, loss_mask: 0.2134, loss: 0.6147 2023-11-16 02:11:17,187 - mmdet - INFO - Epoch [20][850/1833] lr: 2.000e-04, eta: 9:59:22, time: 1.187, data_time: 0.079, memory: 16000, loss_rpn_cls: 0.0226, loss_rpn_bbox: 0.0315, loss_cls: 0.1565, acc: 94.2612, loss_bbox: 0.2017, loss_mask: 0.2154, loss: 0.6277 2023-11-16 02:12:17,668 - mmdet - INFO - Epoch [20][900/1833] lr: 2.000e-04, eta: 9:58:23, time: 1.210, data_time: 0.078, memory: 16000, loss_rpn_cls: 0.0225, loss_rpn_bbox: 0.0314, loss_cls: 0.1537, acc: 94.3517, loss_bbox: 0.1992, loss_mask: 0.2146, loss: 0.6214 2023-11-16 02:13:18,318 - mmdet - INFO - Epoch [20][950/1833] lr: 2.000e-04, eta: 9:57:25, time: 1.213, data_time: 0.081, memory: 16000, loss_rpn_cls: 0.0218, loss_rpn_bbox: 0.0317, loss_cls: 0.1551, acc: 94.3251, loss_bbox: 0.1969, loss_mask: 0.2146, loss: 0.6200 2023-11-16 02:14:19,185 - mmdet - INFO - Epoch [20][1000/1833] lr: 2.000e-04, eta: 9:56:27, time: 1.217, data_time: 0.082, memory: 16000, loss_rpn_cls: 0.0210, loss_rpn_bbox: 0.0315, loss_cls: 0.1514, acc: 94.4438, loss_bbox: 0.1983, loss_mask: 0.2189, loss: 0.6212 2023-11-16 02:15:20,039 - mmdet - INFO - Epoch [20][1050/1833] lr: 2.000e-04, eta: 9:55:29, time: 1.217, data_time: 0.076, memory: 16000, loss_rpn_cls: 0.0213, loss_rpn_bbox: 0.0316, loss_cls: 0.1574, acc: 94.2184, loss_bbox: 0.2034, loss_mask: 0.2198, loss: 0.6335 2023-11-16 02:16:20,087 - mmdet - INFO - Epoch [20][1100/1833] lr: 2.000e-04, eta: 9:54:30, time: 1.201, data_time: 0.083, memory: 16000, loss_rpn_cls: 0.0216, loss_rpn_bbox: 0.0308, loss_cls: 0.1526, acc: 94.4209, loss_bbox: 0.1960, loss_mask: 0.2165, loss: 0.6176 2023-11-16 02:17:20,491 - mmdet - INFO - Epoch [20][1150/1833] lr: 2.000e-04, eta: 9:53:32, time: 1.208, data_time: 0.087, memory: 16000, loss_rpn_cls: 0.0235, loss_rpn_bbox: 0.0335, loss_cls: 0.1592, acc: 94.1553, loss_bbox: 0.2065, loss_mask: 0.2214, loss: 0.6441 2023-11-16 02:18:21,038 - mmdet - INFO - Epoch [20][1200/1833] lr: 2.000e-04, eta: 9:52:33, time: 1.211, data_time: 0.077, memory: 16000, loss_rpn_cls: 0.0224, loss_rpn_bbox: 0.0318, loss_cls: 0.1577, acc: 94.2268, loss_bbox: 0.2008, loss_mask: 0.2175, loss: 0.6302 2023-11-16 02:19:22,285 - mmdet - INFO - Epoch [20][1250/1833] lr: 2.000e-04, eta: 9:51:36, time: 1.225, data_time: 0.081, memory: 16000, loss_rpn_cls: 0.0207, loss_rpn_bbox: 0.0302, loss_cls: 0.1560, acc: 94.2464, loss_bbox: 0.2001, loss_mask: 0.2157, loss: 0.6227 2023-11-16 02:20:22,231 - mmdet - INFO - Epoch [20][1300/1833] lr: 2.000e-04, eta: 9:50:37, time: 1.199, data_time: 0.083, memory: 16000, loss_rpn_cls: 0.0207, loss_rpn_bbox: 0.0308, loss_cls: 0.1551, acc: 94.3060, loss_bbox: 0.1995, loss_mask: 0.2118, loss: 0.6179 2023-11-16 02:21:22,125 - mmdet - INFO - Epoch [20][1350/1833] lr: 2.000e-04, eta: 9:49:38, time: 1.198, data_time: 0.078, memory: 16000, loss_rpn_cls: 0.0213, loss_rpn_bbox: 0.0312, loss_cls: 0.1581, acc: 94.2087, loss_bbox: 0.2034, loss_mask: 0.2164, loss: 0.6304 2023-11-16 02:22:23,107 - mmdet - INFO - Epoch [20][1400/1833] lr: 2.000e-04, eta: 9:48:40, time: 1.220, data_time: 0.077, memory: 16000, loss_rpn_cls: 0.0217, loss_rpn_bbox: 0.0319, loss_cls: 0.1568, acc: 94.2662, loss_bbox: 0.2012, loss_mask: 0.2167, loss: 0.6283 2023-11-16 02:23:23,047 - mmdet - INFO - Epoch [20][1450/1833] lr: 2.000e-04, eta: 9:47:41, time: 1.199, data_time: 0.077, memory: 16000, loss_rpn_cls: 0.0213, loss_rpn_bbox: 0.0305, loss_cls: 0.1545, acc: 94.3355, loss_bbox: 0.1991, loss_mask: 0.2143, loss: 0.6196 2023-11-16 02:24:23,248 - mmdet - INFO - Epoch [20][1500/1833] lr: 2.000e-04, eta: 9:46:42, time: 1.204, data_time: 0.077, memory: 16000, loss_rpn_cls: 0.0212, loss_rpn_bbox: 0.0307, loss_cls: 0.1541, acc: 94.3328, loss_bbox: 0.1983, loss_mask: 0.2148, loss: 0.6191 2023-11-16 02:25:23,457 - mmdet - INFO - Epoch [20][1550/1833] lr: 2.000e-04, eta: 9:45:44, time: 1.204, data_time: 0.078, memory: 16000, loss_rpn_cls: 0.0212, loss_rpn_bbox: 0.0311, loss_cls: 0.1534, acc: 94.3815, loss_bbox: 0.1974, loss_mask: 0.2146, loss: 0.6177 2023-11-16 02:26:25,047 - mmdet - INFO - Epoch [20][1600/1833] lr: 2.000e-04, eta: 9:44:46, time: 1.232, data_time: 0.076, memory: 16000, loss_rpn_cls: 0.0215, loss_rpn_bbox: 0.0309, loss_cls: 0.1547, acc: 94.3177, loss_bbox: 0.2016, loss_mask: 0.2177, loss: 0.6264 2023-11-16 02:27:25,079 - mmdet - INFO - Epoch [20][1650/1833] lr: 2.000e-04, eta: 9:43:48, time: 1.201, data_time: 0.084, memory: 16000, loss_rpn_cls: 0.0214, loss_rpn_bbox: 0.0314, loss_cls: 0.1576, acc: 94.2382, loss_bbox: 0.2023, loss_mask: 0.2172, loss: 0.6299 2023-11-16 02:28:25,368 - mmdet - INFO - Epoch [20][1700/1833] lr: 2.000e-04, eta: 9:42:49, time: 1.206, data_time: 0.077, memory: 16000, loss_rpn_cls: 0.0217, loss_rpn_bbox: 0.0308, loss_cls: 0.1556, acc: 94.3398, loss_bbox: 0.2001, loss_mask: 0.2183, loss: 0.6265 2023-11-16 02:29:25,824 - mmdet - INFO - Epoch [20][1750/1833] lr: 2.000e-04, eta: 9:41:50, time: 1.209, data_time: 0.075, memory: 16000, loss_rpn_cls: 0.0219, loss_rpn_bbox: 0.0312, loss_cls: 0.1554, acc: 94.3495, loss_bbox: 0.1978, loss_mask: 0.2165, loss: 0.6228 2023-11-16 02:30:26,334 - mmdet - INFO - Epoch [20][1800/1833] lr: 2.000e-04, eta: 9:40:52, time: 1.210, data_time: 0.077, memory: 16000, loss_rpn_cls: 0.0214, loss_rpn_bbox: 0.0311, loss_cls: 0.1551, acc: 94.3245, loss_bbox: 0.1998, loss_mask: 0.2193, loss: 0.6268 2023-11-16 02:31:06,319 - mmdet - INFO - Saving checkpoint at 20 epochs 2023-11-16 02:31:53,424 - mmdet - INFO - Evaluating bbox... 2023-11-16 02:32:25,270 - 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 ] = 0.707 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.532 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.321 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 ] = 0.628 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 ] = 0.448 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 ] = 0.754 2023-11-16 02:32:25,273 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.580 | bicycle | 0.377 | car | 0.500 | | motorcycle | 0.495 | airplane | 0.722 | bus | 0.718 | | train | 0.684 | truck | 0.441 | boat | 0.324 | | traffic light | 0.313 | fire hydrant | 0.733 | stop sign | 0.673 | | parking meter | 0.506 | bench | 0.320 | bird | 0.417 | | cat | 0.715 | dog | 0.663 | horse | 0.627 | | sheep | 0.585 | cow | 0.624 | elephant | 0.674 | | bear | 0.769 | zebra | 0.688 | giraffe | 0.703 | | backpack | 0.226 | umbrella | 0.476 | handbag | 0.243 | | tie | 0.393 | suitcase | 0.491 | frisbee | 0.717 | | skis | 0.302 | snowboard | 0.460 | sports ball | 0.465 | | kite | 0.470 | baseball bat | 0.427 | baseball glove | 0.451 | | skateboard | 0.581 | surfboard | 0.446 | tennis racket | 0.569 | | bottle | 0.453 | wine glass | 0.424 | cup | 0.482 | | fork | 0.468 | knife | 0.282 | spoon | 0.315 | | bowl | 0.473 | banana | 0.286 | apple | 0.241 | | sandwich | 0.466 | orange | 0.350 | broccoli | 0.258 | | carrot | 0.283 | hot dog | 0.471 | pizza | 0.533 | | donut | 0.557 | cake | 0.443 | chair | 0.368 | | couch | 0.499 | potted plant | 0.335 | bed | 0.442 | | dining table | 0.327 | toilet | 0.675 | tv | 0.651 | | laptop | 0.692 | mouse | 0.650 | remote | 0.433 | | keyboard | 0.551 | cell phone | 0.462 | microwave | 0.640 | | oven | 0.383 | toaster | 0.477 | sink | 0.442 | | refrigerator | 0.634 | book | 0.199 | clock | 0.515 | | vase | 0.444 | scissors | 0.397 | teddy bear | 0.526 | | hair drier | 0.267 | toothbrush | 0.375 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-16 02:32:25,273 - mmdet - INFO - Evaluating segm... 2023-11-16 02:32:59,718 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.436 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.679 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.471 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.238 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.473 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 ] = 0.556 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 ] = 0.389 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 ] = 0.705 2023-11-16 02:32:59,721 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.506 | bicycle | 0.234 | car | 0.460 | | motorcycle | 0.409 | airplane | 0.540 | bus | 0.702 | | train | 0.678 | truck | 0.413 | boat | 0.300 | | traffic light | 0.309 | fire hydrant | 0.696 | stop sign | 0.662 | | parking meter | 0.527 | bench | 0.248 | bird | 0.342 | | cat | 0.714 | dog | 0.652 | horse | 0.459 | | sheep | 0.522 | cow | 0.532 | elephant | 0.620 | | bear | 0.753 | zebra | 0.616 | giraffe | 0.548 | | backpack | 0.235 | umbrella | 0.527 | handbag | 0.228 | | tie | 0.370 | suitcase | 0.508 | frisbee | 0.667 | | skis | 0.075 | snowboard | 0.300 | sports ball | 0.462 | | kite | 0.342 | baseball bat | 0.326 | baseball glove | 0.464 | | skateboard | 0.371 | surfboard | 0.366 | tennis racket | 0.615 | | bottle | 0.437 | wine glass | 0.393 | cup | 0.482 | | fork | 0.246 | knife | 0.187 | spoon | 0.222 | | bowl | 0.431 | banana | 0.235 | apple | 0.245 | | sandwich | 0.479 | orange | 0.350 | broccoli | 0.241 | | carrot | 0.247 | hot dog | 0.390 | pizza | 0.521 | | donut | 0.561 | cake | 0.447 | chair | 0.267 | | couch | 0.419 | potted plant | 0.275 | bed | 0.355 | | dining table | 0.190 | toilet | 0.653 | tv | 0.668 | | laptop | 0.677 | mouse | 0.646 | remote | 0.379 | | keyboard | 0.543 | cell phone | 0.429 | microwave | 0.654 | | oven | 0.363 | toaster | 0.525 | sink | 0.416 | | refrigerator | 0.642 | book | 0.152 | clock | 0.508 | | vase | 0.435 | scissors | 0.289 | teddy bear | 0.526 | | hair drier | 0.204 | toothbrush | 0.260 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-16 02:33:00,140 - mmdet - INFO - Exp name: mask_rcnn_flash_internimage_s_fpn_3x_coco_0.4.py 2023-11-16 02:33:00,140 - mmdet - INFO - Epoch(val) [20][625] bbox_mAP: 0.4842, bbox_mAP_50: 0.7066, bbox_mAP_75: 0.5325, bbox_mAP_s: 0.3214, bbox_mAP_m: 0.5245, bbox_mAP_l: 0.6281, bbox_mAP_copypaste: 0.4842 0.7066 0.5325 0.3214 0.5245 0.6281, segm_mAP: 0.4361, segm_mAP_50: 0.6786, segm_mAP_75: 0.4710, segm_mAP_s: 0.2385, segm_mAP_m: 0.4726, segm_mAP_l: 0.6181, segm_mAP_copypaste: 0.4361 0.6786 0.4710 0.2385 0.4726 0.6181 2023-11-16 02:34:04,411 - mmdet - INFO - Epoch [21][50/1833] lr: 2.000e-04, eta: 9:38:46, time: 1.285, data_time: 0.131, memory: 16000, loss_rpn_cls: 0.0211, loss_rpn_bbox: 0.0309, loss_cls: 0.1500, acc: 94.4787, loss_bbox: 0.1986, loss_mask: 0.2158, loss: 0.6165 2023-11-16 02:35:04,308 - mmdet - INFO - Epoch [21][100/1833] lr: 2.000e-04, eta: 9:37:47, time: 1.198, data_time: 0.068, memory: 16000, loss_rpn_cls: 0.0204, loss_rpn_bbox: 0.0302, loss_cls: 0.1507, acc: 94.4365, loss_bbox: 0.1959, loss_mask: 0.2125, loss: 0.6098 2023-11-16 02:36:04,347 - mmdet - INFO - Epoch [21][150/1833] lr: 2.000e-04, eta: 9:36:49, time: 1.201, data_time: 0.072, memory: 16000, loss_rpn_cls: 0.0217, loss_rpn_bbox: 0.0327, loss_cls: 0.1608, acc: 94.0714, loss_bbox: 0.2079, loss_mask: 0.2157, loss: 0.6389 2023-11-16 02:37:04,951 - mmdet - INFO - Epoch [21][200/1833] lr: 2.000e-04, eta: 9:35:50, time: 1.212, data_time: 0.063, memory: 16000, loss_rpn_cls: 0.0212, loss_rpn_bbox: 0.0308, loss_cls: 0.1522, acc: 94.3668, loss_bbox: 0.1976, loss_mask: 0.2135, loss: 0.6153 2023-11-16 02:38:05,649 - mmdet - INFO - Epoch [21][250/1833] lr: 2.000e-04, eta: 9:34:52, time: 1.214, data_time: 0.069, memory: 16000, loss_rpn_cls: 0.0212, loss_rpn_bbox: 0.0313, loss_cls: 0.1537, acc: 94.3444, loss_bbox: 0.1998, loss_mask: 0.2161, loss: 0.6221 2023-11-16 02:39:05,895 - mmdet - INFO - Epoch [21][300/1833] lr: 2.000e-04, eta: 9:33:54, time: 1.205, data_time: 0.065, memory: 16000, loss_rpn_cls: 0.0204, loss_rpn_bbox: 0.0309, loss_cls: 0.1500, acc: 94.4180, loss_bbox: 0.1980, loss_mask: 0.2164, loss: 0.6157 2023-11-16 02:40:05,635 - mmdet - INFO - Epoch [21][350/1833] lr: 2.000e-04, eta: 9:32:55, time: 1.195, data_time: 0.071, memory: 16000, loss_rpn_cls: 0.0212, loss_rpn_bbox: 0.0305, loss_cls: 0.1478, acc: 94.5024, loss_bbox: 0.1948, loss_mask: 0.2136, loss: 0.6079 2023-11-16 02:41:05,970 - mmdet - INFO - Epoch [21][400/1833] lr: 2.000e-04, eta: 9:31:56, time: 1.207, data_time: 0.067, memory: 16000, loss_rpn_cls: 0.0198, loss_rpn_bbox: 0.0300, loss_cls: 0.1523, acc: 94.4344, loss_bbox: 0.1986, loss_mask: 0.2161, loss: 0.6167 2023-11-16 02:42:04,976 - mmdet - INFO - Epoch [21][450/1833] lr: 2.000e-04, eta: 9:30:57, time: 1.180, data_time: 0.062, memory: 16000, loss_rpn_cls: 0.0196, loss_rpn_bbox: 0.0296, loss_cls: 0.1492, acc: 94.4902, loss_bbox: 0.1940, loss_mask: 0.2096, loss: 0.6021 2023-11-16 02:43:05,249 - mmdet - INFO - Epoch [21][500/1833] lr: 2.000e-04, eta: 9:29:58, time: 1.205, data_time: 0.061, memory: 16000, loss_rpn_cls: 0.0221, loss_rpn_bbox: 0.0313, loss_cls: 0.1557, acc: 94.2596, loss_bbox: 0.2020, loss_mask: 0.2168, loss: 0.6280 2023-11-16 02:44:06,396 - mmdet - INFO - Epoch [21][550/1833] lr: 2.000e-04, eta: 9:29:00, time: 1.223, data_time: 0.071, memory: 16000, loss_rpn_cls: 0.0209, loss_rpn_bbox: 0.0306, loss_cls: 0.1480, acc: 94.5794, loss_bbox: 0.1947, loss_mask: 0.2147, loss: 0.6088 2023-11-16 02:45:06,012 - mmdet - INFO - Epoch [21][600/1833] lr: 2.000e-04, eta: 9:28:01, time: 1.192, data_time: 0.062, memory: 16000, loss_rpn_cls: 0.0218, loss_rpn_bbox: 0.0316, loss_cls: 0.1530, acc: 94.3788, loss_bbox: 0.1989, loss_mask: 0.2182, loss: 0.6236 2023-11-16 02:46:06,229 - mmdet - INFO - Epoch [21][650/1833] lr: 2.000e-04, eta: 9:27:02, time: 1.204, data_time: 0.070, memory: 16000, loss_rpn_cls: 0.0206, loss_rpn_bbox: 0.0300, loss_cls: 0.1510, acc: 94.4681, loss_bbox: 0.1944, loss_mask: 0.2138, loss: 0.6097 2023-11-16 02:47:05,175 - mmdet - INFO - Epoch [21][700/1833] lr: 2.000e-04, eta: 9:26:03, time: 1.179, data_time: 0.067, memory: 16000, loss_rpn_cls: 0.0210, loss_rpn_bbox: 0.0299, loss_cls: 0.1507, acc: 94.4799, loss_bbox: 0.1944, loss_mask: 0.2131, loss: 0.6093 2023-11-16 02:48:05,942 - mmdet - INFO - Epoch [21][750/1833] lr: 2.000e-04, eta: 9:25:05, time: 1.215, data_time: 0.065, memory: 16000, loss_rpn_cls: 0.0210, loss_rpn_bbox: 0.0311, loss_cls: 0.1526, acc: 94.3486, loss_bbox: 0.1997, loss_mask: 0.2182, loss: 0.6227 2023-11-16 02:49:05,405 - mmdet - INFO - Epoch [21][800/1833] lr: 2.000e-04, eta: 9:24:05, time: 1.189, data_time: 0.064, memory: 16000, loss_rpn_cls: 0.0207, loss_rpn_bbox: 0.0300, loss_cls: 0.1511, acc: 94.4363, loss_bbox: 0.1946, loss_mask: 0.2124, loss: 0.6089 2023-11-16 02:50:07,045 - mmdet - INFO - Epoch [21][850/1833] lr: 2.000e-04, eta: 9:23:08, time: 1.233, data_time: 0.067, memory: 16000, loss_rpn_cls: 0.0223, loss_rpn_bbox: 0.0315, loss_cls: 0.1538, acc: 94.3719, loss_bbox: 0.1989, loss_mask: 0.2159, loss: 0.6224 2023-11-16 02:51:10,592 - mmdet - INFO - Epoch [21][900/1833] lr: 2.000e-04, eta: 9:22:12, time: 1.271, data_time: 0.078, memory: 16000, loss_rpn_cls: 0.0226, loss_rpn_bbox: 0.0323, loss_cls: 0.1577, acc: 94.2057, loss_bbox: 0.2021, loss_mask: 0.2170, loss: 0.6317 2023-11-16 02:52:13,940 - mmdet - INFO - Epoch [21][950/1833] lr: 2.000e-04, eta: 9:21:15, time: 1.267, data_time: 0.061, memory: 16000, loss_rpn_cls: 0.0207, loss_rpn_bbox: 0.0313, loss_cls: 0.1490, acc: 94.5129, loss_bbox: 0.1940, loss_mask: 0.2137, loss: 0.6087 2023-11-16 02:53:13,612 - mmdet - INFO - Epoch [21][1000/1833] lr: 2.000e-04, eta: 9:20:16, time: 1.193, data_time: 0.070, memory: 16000, loss_rpn_cls: 0.0202, loss_rpn_bbox: 0.0300, loss_cls: 0.1487, acc: 94.5334, loss_bbox: 0.1958, loss_mask: 0.2136, loss: 0.6083 2023-11-16 02:54:12,670 - mmdet - INFO - Epoch [21][1050/1833] lr: 2.000e-04, eta: 9:19:17, time: 1.181, data_time: 0.062, memory: 16000, loss_rpn_cls: 0.0214, loss_rpn_bbox: 0.0305, loss_cls: 0.1538, acc: 94.4100, loss_bbox: 0.1964, loss_mask: 0.2176, loss: 0.6198 2023-11-16 02:55:12,764 - mmdet - INFO - Epoch [21][1100/1833] lr: 2.000e-04, eta: 9:18:18, time: 1.202, data_time: 0.063, memory: 16000, loss_rpn_cls: 0.0217, loss_rpn_bbox: 0.0307, loss_cls: 0.1539, acc: 94.3522, loss_bbox: 0.1987, loss_mask: 0.2163, loss: 0.6212 2023-11-16 02:56:12,816 - mmdet - INFO - Epoch [21][1150/1833] lr: 2.000e-04, eta: 9:17:19, time: 1.201, data_time: 0.066, memory: 16000, loss_rpn_cls: 0.0212, loss_rpn_bbox: 0.0304, loss_cls: 0.1523, acc: 94.4225, loss_bbox: 0.1968, loss_mask: 0.2137, loss: 0.6145 2023-11-16 02:57:13,243 - mmdet - INFO - Epoch [21][1200/1833] lr: 2.000e-04, eta: 9:16:21, time: 1.209, data_time: 0.068, memory: 16000, loss_rpn_cls: 0.0203, loss_rpn_bbox: 0.0306, loss_cls: 0.1507, acc: 94.4814, loss_bbox: 0.1936, loss_mask: 0.2141, loss: 0.6093 2023-11-16 02:58:13,940 - mmdet - INFO - Epoch [21][1250/1833] lr: 2.000e-04, eta: 9:15:22, time: 1.214, data_time: 0.068, memory: 16000, loss_rpn_cls: 0.0217, loss_rpn_bbox: 0.0309, loss_cls: 0.1574, acc: 94.2057, loss_bbox: 0.2027, loss_mask: 0.2174, loss: 0.6302 2023-11-16 02:59:13,471 - mmdet - INFO - Epoch [21][1300/1833] lr: 2.000e-04, eta: 9:14:23, time: 1.191, data_time: 0.063, memory: 16000, loss_rpn_cls: 0.0209, loss_rpn_bbox: 0.0303, loss_cls: 0.1528, acc: 94.3860, loss_bbox: 0.1971, loss_mask: 0.2157, loss: 0.6169 2023-11-16 03:00:12,813 - mmdet - INFO - Epoch [21][1350/1833] lr: 2.000e-04, eta: 9:13:24, time: 1.187, data_time: 0.063, memory: 16000, loss_rpn_cls: 0.0214, loss_rpn_bbox: 0.0315, loss_cls: 0.1576, acc: 94.1938, loss_bbox: 0.2022, loss_mask: 0.2162, loss: 0.6289 2023-11-16 03:01:13,049 - mmdet - INFO - Epoch [21][1400/1833] lr: 2.000e-04, eta: 9:12:25, time: 1.205, data_time: 0.064, memory: 16000, loss_rpn_cls: 0.0211, loss_rpn_bbox: 0.0308, loss_cls: 0.1526, acc: 94.3882, loss_bbox: 0.1996, loss_mask: 0.2149, loss: 0.6191 2023-11-16 03:02:13,672 - mmdet - INFO - Epoch [21][1450/1833] lr: 2.000e-04, eta: 9:11:27, time: 1.212, data_time: 0.064, memory: 16000, loss_rpn_cls: 0.0231, loss_rpn_bbox: 0.0320, loss_cls: 0.1592, acc: 94.1490, loss_bbox: 0.2029, loss_mask: 0.2165, loss: 0.6336 2023-11-16 03:03:14,927 - mmdet - INFO - Epoch [21][1500/1833] lr: 2.000e-04, eta: 9:10:29, time: 1.225, data_time: 0.066, memory: 16000, loss_rpn_cls: 0.0224, loss_rpn_bbox: 0.0314, loss_cls: 0.1521, acc: 94.3648, loss_bbox: 0.2001, loss_mask: 0.2172, loss: 0.6232 2023-11-16 03:04:18,492 - mmdet - INFO - Epoch [21][1550/1833] lr: 2.000e-04, eta: 9:09:32, time: 1.271, data_time: 0.070, memory: 16000, loss_rpn_cls: 0.0224, loss_rpn_bbox: 0.0316, loss_cls: 0.1544, acc: 94.3625, loss_bbox: 0.1972, loss_mask: 0.2165, loss: 0.6220 2023-11-16 03:05:17,966 - mmdet - INFO - Epoch [21][1600/1833] lr: 2.000e-04, eta: 9:08:33, time: 1.189, data_time: 0.064, memory: 16000, loss_rpn_cls: 0.0231, loss_rpn_bbox: 0.0325, loss_cls: 0.1565, acc: 94.2382, loss_bbox: 0.2015, loss_mask: 0.2201, loss: 0.6336 2023-11-16 03:06:18,496 - mmdet - INFO - Epoch [21][1650/1833] lr: 2.000e-04, eta: 9:07:35, time: 1.211, data_time: 0.068, memory: 16000, loss_rpn_cls: 0.0222, loss_rpn_bbox: 0.0318, loss_cls: 0.1560, acc: 94.2305, loss_bbox: 0.2014, loss_mask: 0.2155, loss: 0.6268 2023-11-16 03:07:17,703 - mmdet - INFO - Epoch [21][1700/1833] lr: 2.000e-04, eta: 9:06:35, time: 1.184, data_time: 0.059, memory: 16000, loss_rpn_cls: 0.0210, loss_rpn_bbox: 0.0299, loss_cls: 0.1528, acc: 94.4193, loss_bbox: 0.1953, loss_mask: 0.2142, loss: 0.6133 2023-11-16 03:08:18,459 - mmdet - INFO - Epoch [21][1750/1833] lr: 2.000e-04, eta: 9:05:37, time: 1.215, data_time: 0.066, memory: 16000, loss_rpn_cls: 0.0220, loss_rpn_bbox: 0.0323, loss_cls: 0.1592, acc: 94.1788, loss_bbox: 0.2030, loss_mask: 0.2163, loss: 0.6328 2023-11-16 03:09:18,189 - mmdet - INFO - Epoch [21][1800/1833] lr: 2.000e-04, eta: 9:04:38, time: 1.195, data_time: 0.070, memory: 16000, loss_rpn_cls: 0.0221, loss_rpn_bbox: 0.0313, loss_cls: 0.1557, acc: 94.2737, loss_bbox: 0.2009, loss_mask: 0.2177, loss: 0.6277 2023-11-16 03:09:59,098 - mmdet - INFO - Saving checkpoint at 21 epochs 2023-11-16 03:10:46,319 - mmdet - INFO - Evaluating bbox... 2023-11-16 03:11:13,851 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.480 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.700 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.525 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.320 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 ] = 0.624 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 ] = 0.443 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 ] = 0.756 2023-11-16 03:11:13,853 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.584 | bicycle | 0.379 | car | 0.495 | | motorcycle | 0.480 | airplane | 0.701 | bus | 0.695 | | train | 0.663 | truck | 0.408 | boat | 0.330 | | traffic light | 0.301 | fire hydrant | 0.726 | stop sign | 0.687 | | parking meter | 0.531 | bench | 0.297 | bird | 0.423 | | cat | 0.718 | dog | 0.683 | horse | 0.633 | | sheep | 0.607 | cow | 0.616 | elephant | 0.667 | | bear | 0.724 | zebra | 0.696 | giraffe | 0.703 | | backpack | 0.220 | umbrella | 0.467 | handbag | 0.234 | | tie | 0.394 | suitcase | 0.485 | frisbee | 0.694 | | skis | 0.312 | snowboard | 0.434 | sports ball | 0.481 | | kite | 0.456 | baseball bat | 0.437 | baseball glove | 0.437 | | skateboard | 0.592 | surfboard | 0.450 | tennis racket | 0.572 | | bottle | 0.465 | wine glass | 0.430 | cup | 0.488 | | fork | 0.463 | knife | 0.295 | spoon | 0.320 | | bowl | 0.472 | banana | 0.280 | apple | 0.264 | | sandwich | 0.445 | orange | 0.371 | broccoli | 0.261 | | carrot | 0.278 | hot dog | 0.476 | pizza | 0.539 | | donut | 0.540 | cake | 0.454 | chair | 0.369 | | couch | 0.473 | potted plant | 0.341 | bed | 0.446 | | dining table | 0.310 | toilet | 0.660 | tv | 0.638 | | laptop | 0.684 | mouse | 0.648 | remote | 0.436 | | keyboard | 0.530 | cell phone | 0.463 | microwave | 0.645 | | oven | 0.397 | toaster | 0.443 | sink | 0.427 | | refrigerator | 0.620 | book | 0.202 | clock | 0.535 | | vase | 0.433 | scissors | 0.421 | teddy bear | 0.517 | | hair drier | 0.179 | toothbrush | 0.324 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-16 03:11:13,854 - mmdet - INFO - Evaluating segm... 2023-11-16 03:11:46,412 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.429 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.669 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.462 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.235 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.465 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 ] = 0.550 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 ] = 0.380 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.589 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.704 2023-11-16 03:11:46,414 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.504 | bicycle | 0.230 | car | 0.454 | | motorcycle | 0.402 | airplane | 0.531 | bus | 0.688 | | train | 0.661 | truck | 0.387 | boat | 0.292 | | traffic light | 0.293 | fire hydrant | 0.702 | stop sign | 0.678 | | parking meter | 0.524 | bench | 0.237 | bird | 0.340 | | cat | 0.723 | dog | 0.647 | horse | 0.469 | | sheep | 0.532 | cow | 0.509 | elephant | 0.606 | | bear | 0.708 | zebra | 0.612 | giraffe | 0.555 | | backpack | 0.231 | umbrella | 0.523 | handbag | 0.221 | | tie | 0.363 | suitcase | 0.503 | frisbee | 0.650 | | skis | 0.067 | snowboard | 0.276 | sports ball | 0.466 | | kite | 0.325 | baseball bat | 0.310 | baseball glove | 0.453 | | skateboard | 0.375 | surfboard | 0.355 | tennis racket | 0.603 | | bottle | 0.436 | wine glass | 0.387 | cup | 0.483 | | fork | 0.238 | knife | 0.214 | spoon | 0.220 | | bowl | 0.443 | banana | 0.235 | apple | 0.267 | | sandwich | 0.457 | orange | 0.365 | broccoli | 0.251 | | carrot | 0.238 | hot dog | 0.412 | pizza | 0.521 | | donut | 0.537 | cake | 0.455 | chair | 0.261 | | couch | 0.394 | potted plant | 0.296 | bed | 0.365 | | dining table | 0.188 | toilet | 0.639 | tv | 0.663 | | laptop | 0.673 | mouse | 0.627 | remote | 0.392 | | keyboard | 0.526 | cell phone | 0.423 | microwave | 0.651 | | oven | 0.352 | toaster | 0.485 | sink | 0.396 | | refrigerator | 0.629 | book | 0.150 | clock | 0.528 | | vase | 0.430 | scissors | 0.285 | teddy bear | 0.508 | | hair drier | 0.091 | toothbrush | 0.220 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-16 03:11:46,861 - mmdet - INFO - Exp name: mask_rcnn_flash_internimage_s_fpn_3x_coco_0.4.py 2023-11-16 03:11:46,861 - mmdet - INFO - Epoch(val) [21][625] bbox_mAP: 0.4799, bbox_mAP_50: 0.6996, bbox_mAP_75: 0.5253, bbox_mAP_s: 0.3198, bbox_mAP_m: 0.5216, bbox_mAP_l: 0.6245, bbox_mAP_copypaste: 0.4799 0.6996 0.5253 0.3198 0.5216 0.6245, segm_mAP: 0.4292, segm_mAP_50: 0.6689, segm_mAP_75: 0.4621, segm_mAP_s: 0.2348, segm_mAP_m: 0.4649, segm_mAP_l: 0.6145, segm_mAP_copypaste: 0.4292 0.6689 0.4621 0.2348 0.4649 0.6145 2023-11-16 03:12:50,113 - mmdet - INFO - Epoch [22][50/1833] lr: 2.000e-04, eta: 9:02:34, time: 1.265, data_time: 0.132, memory: 16000, loss_rpn_cls: 0.0206, loss_rpn_bbox: 0.0296, loss_cls: 0.1486, acc: 94.5425, loss_bbox: 0.1947, loss_mask: 0.2138, loss: 0.6073 2023-11-16 03:13:51,208 - mmdet - INFO - Epoch [22][100/1833] lr: 2.000e-04, eta: 9:01:36, time: 1.222, data_time: 0.083, memory: 16000, loss_rpn_cls: 0.0205, loss_rpn_bbox: 0.0310, loss_cls: 0.1551, acc: 94.2995, loss_bbox: 0.1992, loss_mask: 0.2130, loss: 0.6187 2023-11-16 03:14:52,607 - mmdet - INFO - Epoch [22][150/1833] lr: 2.000e-04, eta: 9:00:38, time: 1.228, data_time: 0.077, memory: 16000, loss_rpn_cls: 0.0201, loss_rpn_bbox: 0.0303, loss_cls: 0.1492, acc: 94.5207, loss_bbox: 0.1915, loss_mask: 0.2098, loss: 0.6009 2023-11-16 03:15:52,909 - mmdet - INFO - Epoch [22][200/1833] lr: 2.000e-04, eta: 8:59:40, time: 1.206, data_time: 0.070, memory: 16000, loss_rpn_cls: 0.0211, loss_rpn_bbox: 0.0304, loss_cls: 0.1495, acc: 94.5101, loss_bbox: 0.1960, loss_mask: 0.2163, loss: 0.6131 2023-11-16 03:16:53,793 - mmdet - INFO - Epoch [22][250/1833] lr: 2.000e-04, eta: 8:58:41, time: 1.218, data_time: 0.074, memory: 16000, loss_rpn_cls: 0.0207, loss_rpn_bbox: 0.0304, loss_cls: 0.1515, acc: 94.4229, loss_bbox: 0.1988, loss_mask: 0.2134, loss: 0.6149 2023-11-16 03:17:56,955 - mmdet - INFO - Epoch [22][300/1833] lr: 2.000e-04, eta: 8:57:45, time: 1.263, data_time: 0.075, memory: 16000, loss_rpn_cls: 0.0196, loss_rpn_bbox: 0.0302, loss_cls: 0.1466, acc: 94.5894, loss_bbox: 0.1926, loss_mask: 0.2123, loss: 0.6013 2023-11-16 03:18:57,076 - mmdet - INFO - Epoch [22][350/1833] lr: 2.000e-04, eta: 8:56:46, time: 1.202, data_time: 0.073, memory: 16000, loss_rpn_cls: 0.0221, loss_rpn_bbox: 0.0317, loss_cls: 0.1546, acc: 94.3395, loss_bbox: 0.2005, loss_mask: 0.2140, loss: 0.6230 2023-11-16 03:19:57,007 - mmdet - INFO - Epoch [22][400/1833] lr: 2.000e-04, eta: 8:55:47, time: 1.199, data_time: 0.081, memory: 16000, loss_rpn_cls: 0.0201, loss_rpn_bbox: 0.0298, loss_cls: 0.1496, acc: 94.4542, loss_bbox: 0.1968, loss_mask: 0.2150, loss: 0.6115 2023-11-16 03:20:57,372 - mmdet - INFO - Epoch [22][450/1833] lr: 2.000e-04, eta: 8:54:49, time: 1.207, data_time: 0.071, memory: 16000, loss_rpn_cls: 0.0208, loss_rpn_bbox: 0.0313, loss_cls: 0.1548, acc: 94.2804, loss_bbox: 0.2005, loss_mask: 0.2156, loss: 0.6230 2023-11-16 03:21:56,985 - mmdet - INFO - Epoch [22][500/1833] lr: 2.000e-04, eta: 8:53:49, time: 1.192, data_time: 0.071, memory: 16000, loss_rpn_cls: 0.0227, loss_rpn_bbox: 0.0320, loss_cls: 0.1558, acc: 94.2480, loss_bbox: 0.2008, loss_mask: 0.2146, loss: 0.6260 2023-11-16 03:22:57,049 - mmdet - INFO - Epoch [22][550/1833] lr: 2.000e-04, eta: 8:52:51, time: 1.201, data_time: 0.072, memory: 16000, loss_rpn_cls: 0.0195, loss_rpn_bbox: 0.0300, loss_cls: 0.1487, acc: 94.5482, loss_bbox: 0.1928, loss_mask: 0.2124, loss: 0.6035 2023-11-16 03:23:56,112 - mmdet - INFO - Epoch [22][600/1833] lr: 2.000e-04, eta: 8:51:51, time: 1.181, data_time: 0.079, memory: 16000, loss_rpn_cls: 0.0219, loss_rpn_bbox: 0.0315, loss_cls: 0.1522, acc: 94.3600, loss_bbox: 0.1977, loss_mask: 0.2160, loss: 0.6193 2023-11-16 03:24:55,780 - mmdet - INFO - Epoch [22][650/1833] lr: 2.000e-04, eta: 8:50:52, time: 1.193, data_time: 0.074, memory: 16000, loss_rpn_cls: 0.0213, loss_rpn_bbox: 0.0309, loss_cls: 0.1505, acc: 94.4464, loss_bbox: 0.1978, loss_mask: 0.2141, loss: 0.6146 2023-11-16 03:25:55,539 - mmdet - INFO - Epoch [22][700/1833] lr: 2.000e-04, eta: 8:49:53, time: 1.195, data_time: 0.081, memory: 16000, loss_rpn_cls: 0.0201, loss_rpn_bbox: 0.0305, loss_cls: 0.1491, acc: 94.4995, loss_bbox: 0.1953, loss_mask: 0.2152, loss: 0.6103 2023-11-16 03:26:56,042 - mmdet - INFO - Epoch [22][750/1833] lr: 2.000e-04, eta: 8:48:54, time: 1.210, data_time: 0.073, memory: 16000, loss_rpn_cls: 0.0199, loss_rpn_bbox: 0.0302, loss_cls: 0.1457, acc: 94.6293, loss_bbox: 0.1903, loss_mask: 0.2135, loss: 0.5995 2023-11-16 03:27:56,054 - mmdet - INFO - Epoch [22][800/1833] lr: 2.000e-04, eta: 8:47:56, time: 1.200, data_time: 0.079, memory: 16000, loss_rpn_cls: 0.0203, loss_rpn_bbox: 0.0303, loss_cls: 0.1506, acc: 94.4636, loss_bbox: 0.1959, loss_mask: 0.2141, loss: 0.6112 2023-11-16 03:28:55,829 - mmdet - INFO - Epoch [22][850/1833] lr: 2.000e-04, eta: 8:46:57, time: 1.195, data_time: 0.076, memory: 16000, loss_rpn_cls: 0.0211, loss_rpn_bbox: 0.0300, loss_cls: 0.1490, acc: 94.4970, loss_bbox: 0.1953, loss_mask: 0.2135, loss: 0.6088 2023-11-16 03:29:54,865 - mmdet - INFO - Epoch [22][900/1833] lr: 2.000e-04, eta: 8:45:57, time: 1.181, data_time: 0.071, memory: 16000, loss_rpn_cls: 0.0218, loss_rpn_bbox: 0.0317, loss_cls: 0.1545, acc: 94.2971, loss_bbox: 0.2013, loss_mask: 0.2175, loss: 0.6268 2023-11-16 03:30:55,387 - mmdet - INFO - Epoch [22][950/1833] lr: 2.000e-04, eta: 8:44:58, time: 1.210, data_time: 0.081, memory: 16000, loss_rpn_cls: 0.0210, loss_rpn_bbox: 0.0305, loss_cls: 0.1511, acc: 94.4142, loss_bbox: 0.1968, loss_mask: 0.2138, loss: 0.6133 2023-11-16 03:31:55,296 - mmdet - INFO - Epoch [22][1000/1833] lr: 2.000e-04, eta: 8:44:00, time: 1.198, data_time: 0.070, memory: 16000, loss_rpn_cls: 0.0217, loss_rpn_bbox: 0.0316, loss_cls: 0.1546, acc: 94.3124, loss_bbox: 0.1990, loss_mask: 0.2152, loss: 0.6222 2023-11-16 03:32:54,530 - mmdet - INFO - Epoch [22][1050/1833] lr: 2.000e-04, eta: 8:43:00, time: 1.185, data_time: 0.071, memory: 16000, loss_rpn_cls: 0.0202, loss_rpn_bbox: 0.0304, loss_cls: 0.1490, acc: 94.5303, loss_bbox: 0.1929, loss_mask: 0.2141, loss: 0.6067 2023-11-16 03:33:54,292 - mmdet - INFO - Epoch [22][1100/1833] lr: 2.000e-04, eta: 8:42:01, time: 1.195, data_time: 0.071, memory: 16000, loss_rpn_cls: 0.0227, loss_rpn_bbox: 0.0320, loss_cls: 0.1534, acc: 94.3593, loss_bbox: 0.1981, loss_mask: 0.2162, loss: 0.6224 2023-11-16 03:34:53,744 - mmdet - INFO - Epoch [22][1150/1833] lr: 2.000e-04, eta: 8:41:02, time: 1.189, data_time: 0.079, memory: 16000, loss_rpn_cls: 0.0215, loss_rpn_bbox: 0.0306, loss_cls: 0.1524, acc: 94.3863, loss_bbox: 0.1961, loss_mask: 0.2177, loss: 0.6182 2023-11-16 03:35:55,138 - mmdet - INFO - Epoch [22][1200/1833] lr: 2.000e-04, eta: 8:40:04, time: 1.228, data_time: 0.076, memory: 16000, loss_rpn_cls: 0.0212, loss_rpn_bbox: 0.0315, loss_cls: 0.1537, acc: 94.3349, loss_bbox: 0.1993, loss_mask: 0.2167, loss: 0.6225 2023-11-16 03:36:54,970 - mmdet - INFO - Epoch [22][1250/1833] lr: 2.000e-04, eta: 8:39:05, time: 1.197, data_time: 0.072, memory: 16000, loss_rpn_cls: 0.0216, loss_rpn_bbox: 0.0314, loss_cls: 0.1543, acc: 94.3276, loss_bbox: 0.1978, loss_mask: 0.2185, loss: 0.6237 2023-11-16 03:37:54,448 - mmdet - INFO - Epoch [22][1300/1833] lr: 2.000e-04, eta: 8:38:06, time: 1.190, data_time: 0.073, memory: 16000, loss_rpn_cls: 0.0216, loss_rpn_bbox: 0.0314, loss_cls: 0.1535, acc: 94.3771, loss_bbox: 0.1997, loss_mask: 0.2167, loss: 0.6228 2023-11-16 03:38:55,445 - mmdet - INFO - Epoch [22][1350/1833] lr: 2.000e-04, eta: 8:37:07, time: 1.220, data_time: 0.075, memory: 16000, loss_rpn_cls: 0.0209, loss_rpn_bbox: 0.0314, loss_cls: 0.1553, acc: 94.2774, loss_bbox: 0.2024, loss_mask: 0.2163, loss: 0.6263 2023-11-16 03:39:55,074 - mmdet - INFO - Epoch [22][1400/1833] lr: 2.000e-04, eta: 8:36:08, time: 1.193, data_time: 0.067, memory: 16000, loss_rpn_cls: 0.0221, loss_rpn_bbox: 0.0305, loss_cls: 0.1508, acc: 94.4538, loss_bbox: 0.1957, loss_mask: 0.2140, loss: 0.6130 2023-11-16 03:40:54,132 - mmdet - INFO - Epoch [22][1450/1833] lr: 2.000e-04, eta: 8:35:09, time: 1.181, data_time: 0.067, memory: 16000, loss_rpn_cls: 0.0201, loss_rpn_bbox: 0.0303, loss_cls: 0.1508, acc: 94.4682, loss_bbox: 0.1951, loss_mask: 0.2137, loss: 0.6100 2023-11-16 03:41:54,037 - mmdet - INFO - Epoch [22][1500/1833] lr: 2.000e-04, eta: 8:34:10, time: 1.198, data_time: 0.081, memory: 16000, loss_rpn_cls: 0.0203, loss_rpn_bbox: 0.0299, loss_cls: 0.1543, acc: 94.3640, loss_bbox: 0.1989, loss_mask: 0.2153, loss: 0.6187 2023-11-16 03:42:54,622 - mmdet - INFO - Epoch [22][1550/1833] lr: 2.000e-04, eta: 8:33:11, time: 1.212, data_time: 0.077, memory: 16000, loss_rpn_cls: 0.0216, loss_rpn_bbox: 0.0321, loss_cls: 0.1555, acc: 94.2543, loss_bbox: 0.2011, loss_mask: 0.2182, loss: 0.6285 2023-11-16 03:43:54,638 - mmdet - INFO - Epoch [22][1600/1833] lr: 2.000e-04, eta: 8:32:12, time: 1.200, data_time: 0.080, memory: 16000, loss_rpn_cls: 0.0217, loss_rpn_bbox: 0.0313, loss_cls: 0.1541, acc: 94.3546, loss_bbox: 0.1981, loss_mask: 0.2161, loss: 0.6213 2023-11-16 03:44:54,832 - mmdet - INFO - Epoch [22][1650/1833] lr: 2.000e-04, eta: 8:31:13, time: 1.204, data_time: 0.068, memory: 16000, loss_rpn_cls: 0.0208, loss_rpn_bbox: 0.0312, loss_cls: 0.1537, acc: 94.3549, loss_bbox: 0.1982, loss_mask: 0.2129, loss: 0.6167 2023-11-16 03:45:54,601 - mmdet - INFO - Epoch [22][1700/1833] lr: 2.000e-04, eta: 8:30:14, time: 1.195, data_time: 0.074, memory: 16000, loss_rpn_cls: 0.0209, loss_rpn_bbox: 0.0311, loss_cls: 0.1567, acc: 94.2892, loss_bbox: 0.2022, loss_mask: 0.2134, loss: 0.6242 2023-11-16 03:46:54,219 - mmdet - INFO - Epoch [22][1750/1833] lr: 2.000e-04, eta: 8:29:15, time: 1.192, data_time: 0.065, memory: 16000, loss_rpn_cls: 0.0219, loss_rpn_bbox: 0.0309, loss_cls: 0.1515, acc: 94.4735, loss_bbox: 0.1951, loss_mask: 0.2134, loss: 0.6128 2023-11-16 03:47:54,172 - mmdet - INFO - Epoch [22][1800/1833] lr: 2.000e-04, eta: 8:28:16, time: 1.199, data_time: 0.071, memory: 16000, loss_rpn_cls: 0.0213, loss_rpn_bbox: 0.0303, loss_cls: 0.1519, acc: 94.4116, loss_bbox: 0.1953, loss_mask: 0.2169, loss: 0.6157 2023-11-16 03:48:35,000 - mmdet - INFO - Saving checkpoint at 22 epochs 2023-11-16 03:49:23,070 - mmdet - INFO - Evaluating bbox... 2023-11-16 03:49:51,999 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.483 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.702 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.533 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.322 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.527 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 ] = 0.607 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.607 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.607 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.445 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.644 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.748 2023-11-16 03:49:52,002 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.585 | bicycle | 0.380 | car | 0.495 | | motorcycle | 0.489 | airplane | 0.691 | bus | 0.697 | | train | 0.644 | truck | 0.445 | boat | 0.326 | | traffic light | 0.316 | fire hydrant | 0.712 | stop sign | 0.696 | | parking meter | 0.475 | bench | 0.310 | bird | 0.414 | | cat | 0.726 | dog | 0.688 | horse | 0.644 | | sheep | 0.603 | cow | 0.617 | elephant | 0.705 | | bear | 0.731 | zebra | 0.686 | giraffe | 0.687 | | backpack | 0.233 | umbrella | 0.474 | handbag | 0.231 | | tie | 0.403 | suitcase | 0.474 | frisbee | 0.703 | | skis | 0.304 | snowboard | 0.467 | sports ball | 0.478 | | kite | 0.459 | baseball bat | 0.427 | baseball glove | 0.422 | | skateboard | 0.596 | surfboard | 0.457 | tennis racket | 0.581 | | bottle | 0.458 | wine glass | 0.414 | cup | 0.497 | | fork | 0.492 | knife | 0.290 | spoon | 0.290 | | bowl | 0.475 | banana | 0.293 | apple | 0.288 | | sandwich | 0.436 | orange | 0.350 | broccoli | 0.248 | | carrot | 0.264 | hot dog | 0.495 | pizza | 0.552 | | donut | 0.535 | cake | 0.419 | chair | 0.374 | | couch | 0.494 | potted plant | 0.350 | bed | 0.476 | | dining table | 0.320 | toilet | 0.664 | tv | 0.623 | | laptop | 0.664 | mouse | 0.644 | remote | 0.423 | | keyboard | 0.566 | cell phone | 0.458 | microwave | 0.667 | | oven | 0.405 | toaster | 0.474 | sink | 0.448 | | refrigerator | 0.616 | book | 0.197 | clock | 0.520 | | vase | 0.447 | scissors | 0.438 | teddy bear | 0.559 | | hair drier | 0.230 | toothbrush | 0.343 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-16 03:49:52,002 - mmdet - INFO - Evaluating segm... 2023-11-16 03:50:25,930 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.431 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.672 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.462 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.233 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 ] = 0.548 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.548 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.548 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.373 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 ] = 0.704 2023-11-16 03:50:25,933 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.510 | bicycle | 0.238 | car | 0.449 | | motorcycle | 0.405 | airplane | 0.537 | bus | 0.687 | | train | 0.647 | truck | 0.427 | boat | 0.293 | | traffic light | 0.298 | fire hydrant | 0.698 | stop sign | 0.678 | | parking meter | 0.490 | bench | 0.242 | bird | 0.340 | | cat | 0.720 | dog | 0.645 | horse | 0.467 | | sheep | 0.514 | cow | 0.517 | elephant | 0.630 | | bear | 0.704 | zebra | 0.591 | giraffe | 0.539 | | backpack | 0.236 | umbrella | 0.521 | handbag | 0.215 | | tie | 0.366 | suitcase | 0.485 | frisbee | 0.654 | | skis | 0.059 | snowboard | 0.303 | sports ball | 0.470 | | kite | 0.327 | baseball bat | 0.307 | baseball glove | 0.450 | | skateboard | 0.388 | surfboard | 0.365 | tennis racket | 0.622 | | bottle | 0.429 | wine glass | 0.380 | cup | 0.494 | | fork | 0.244 | knife | 0.199 | spoon | 0.207 | | bowl | 0.437 | banana | 0.237 | apple | 0.277 | | sandwich | 0.466 | orange | 0.346 | broccoli | 0.228 | | carrot | 0.225 | hot dog | 0.411 | pizza | 0.539 | | donut | 0.530 | cake | 0.428 | chair | 0.259 | | couch | 0.425 | potted plant | 0.284 | bed | 0.373 | | dining table | 0.180 | toilet | 0.648 | tv | 0.646 | | laptop | 0.658 | mouse | 0.619 | remote | 0.385 | | keyboard | 0.541 | cell phone | 0.431 | microwave | 0.670 | | oven | 0.374 | toaster | 0.519 | sink | 0.411 | | refrigerator | 0.628 | book | 0.152 | clock | 0.515 | | vase | 0.436 | scissors | 0.292 | teddy bear | 0.530 | | hair drier | 0.174 | toothbrush | 0.226 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-16 03:50:26,326 - mmdet - INFO - Exp name: mask_rcnn_flash_internimage_s_fpn_3x_coco_0.4.py 2023-11-16 03:50:26,326 - mmdet - INFO - Epoch(val) [22][625] bbox_mAP: 0.4833, bbox_mAP_50: 0.7020, bbox_mAP_75: 0.5331, bbox_mAP_s: 0.3220, bbox_mAP_m: 0.5270, bbox_mAP_l: 0.6228, bbox_mAP_copypaste: 0.4833 0.7020 0.5331 0.3220 0.5270 0.6228, segm_mAP: 0.4311, segm_mAP_50: 0.6715, segm_mAP_75: 0.4625, segm_mAP_s: 0.2330, segm_mAP_m: 0.4682, segm_mAP_l: 0.6153, segm_mAP_copypaste: 0.4311 0.6715 0.4625 0.2330 0.4682 0.6153 2023-11-16 03:51:30,003 - mmdet - INFO - Epoch [23][50/1833] lr: 2.000e-04, eta: 8:26:16, time: 1.273, data_time: 0.127, memory: 16000, loss_rpn_cls: 0.0201, loss_rpn_bbox: 0.0310, loss_cls: 0.1489, acc: 94.5272, loss_bbox: 0.1947, loss_mask: 0.2149, loss: 0.6095 2023-11-16 03:52:30,340 - mmdet - INFO - Epoch [23][100/1833] lr: 2.000e-04, eta: 8:25:17, time: 1.207, data_time: 0.086, memory: 16000, loss_rpn_cls: 0.0195, loss_rpn_bbox: 0.0304, loss_cls: 0.1476, acc: 94.5396, loss_bbox: 0.1931, loss_mask: 0.2095, loss: 0.6001 2023-11-16 03:53:31,639 - mmdet - INFO - Epoch [23][150/1833] lr: 2.000e-04, eta: 8:24:19, time: 1.226, data_time: 0.071, memory: 16000, loss_rpn_cls: 0.0199, loss_rpn_bbox: 0.0300, loss_cls: 0.1463, acc: 94.5939, loss_bbox: 0.1941, loss_mask: 0.2137, loss: 0.6040 2023-11-16 03:54:32,732 - mmdet - INFO - Epoch [23][200/1833] lr: 2.000e-04, eta: 8:23:21, time: 1.222, data_time: 0.064, memory: 16000, loss_rpn_cls: 0.0201, loss_rpn_bbox: 0.0303, loss_cls: 0.1482, acc: 94.5466, loss_bbox: 0.1954, loss_mask: 0.2139, loss: 0.6079 2023-11-16 03:55:33,534 - mmdet - INFO - Epoch [23][250/1833] lr: 2.000e-04, eta: 8:22:22, time: 1.216, data_time: 0.066, memory: 16000, loss_rpn_cls: 0.0203, loss_rpn_bbox: 0.0308, loss_cls: 0.1524, acc: 94.3778, loss_bbox: 0.2010, loss_mask: 0.2148, loss: 0.6193 2023-11-16 03:56:33,340 - mmdet - INFO - Epoch [23][300/1833] lr: 2.000e-04, eta: 8:21:23, time: 1.196, data_time: 0.077, memory: 16000, loss_rpn_cls: 0.0207, loss_rpn_bbox: 0.0303, loss_cls: 0.1520, acc: 94.4249, loss_bbox: 0.1952, loss_mask: 0.2115, loss: 0.6096 2023-11-16 03:57:33,702 - mmdet - INFO - Epoch [23][350/1833] lr: 2.000e-04, eta: 8:20:25, time: 1.207, data_time: 0.071, memory: 16000, loss_rpn_cls: 0.0210, loss_rpn_bbox: 0.0314, loss_cls: 0.1488, acc: 94.4961, loss_bbox: 0.1943, loss_mask: 0.2149, loss: 0.6103 2023-11-16 03:58:34,231 - mmdet - INFO - Epoch [23][400/1833] lr: 2.000e-04, eta: 8:19:26, time: 1.210, data_time: 0.082, memory: 16000, loss_rpn_cls: 0.0216, loss_rpn_bbox: 0.0313, loss_cls: 0.1539, acc: 94.3520, loss_bbox: 0.1990, loss_mask: 0.2169, loss: 0.6227 2023-11-16 03:59:34,776 - mmdet - INFO - Epoch [23][450/1833] lr: 2.000e-04, eta: 8:18:28, time: 1.211, data_time: 0.082, memory: 16000, loss_rpn_cls: 0.0213, loss_rpn_bbox: 0.0315, loss_cls: 0.1515, acc: 94.4131, loss_bbox: 0.1974, loss_mask: 0.2142, loss: 0.6159 2023-11-16 04:00:34,740 - mmdet - INFO - Epoch [23][500/1833] lr: 2.000e-04, eta: 8:17:29, time: 1.199, data_time: 0.072, memory: 16000, loss_rpn_cls: 0.0210, loss_rpn_bbox: 0.0308, loss_cls: 0.1522, acc: 94.3902, loss_bbox: 0.1993, loss_mask: 0.2123, loss: 0.6157 2023-11-16 04:01:35,380 - mmdet - INFO - Epoch [23][550/1833] lr: 2.000e-04, eta: 8:16:30, time: 1.213, data_time: 0.075, memory: 16000, loss_rpn_cls: 0.0207, loss_rpn_bbox: 0.0300, loss_cls: 0.1500, acc: 94.4702, loss_bbox: 0.1979, loss_mask: 0.2139, loss: 0.6125 2023-11-16 04:02:34,935 - mmdet - INFO - Epoch [23][600/1833] lr: 2.000e-04, eta: 8:15:31, time: 1.191, data_time: 0.081, memory: 16000, loss_rpn_cls: 0.0206, loss_rpn_bbox: 0.0303, loss_cls: 0.1490, acc: 94.5479, loss_bbox: 0.1951, loss_mask: 0.2121, loss: 0.6072 2023-11-16 04:03:34,184 - mmdet - INFO - Epoch [23][650/1833] lr: 2.000e-04, eta: 8:14:32, time: 1.185, data_time: 0.075, memory: 16000, loss_rpn_cls: 0.0198, loss_rpn_bbox: 0.0300, loss_cls: 0.1491, acc: 94.5176, loss_bbox: 0.1922, loss_mask: 0.2139, loss: 0.6049 2023-11-16 04:04:33,456 - mmdet - INFO - Epoch [23][700/1833] lr: 2.000e-04, eta: 8:13:32, time: 1.185, data_time: 0.079, memory: 16000, loss_rpn_cls: 0.0202, loss_rpn_bbox: 0.0298, loss_cls: 0.1461, acc: 94.5784, loss_bbox: 0.1931, loss_mask: 0.2108, loss: 0.6000 2023-11-16 04:05:34,038 - mmdet - INFO - Epoch [23][750/1833] lr: 2.000e-04, eta: 8:12:34, time: 1.212, data_time: 0.074, memory: 16000, loss_rpn_cls: 0.0208, loss_rpn_bbox: 0.0306, loss_cls: 0.1486, acc: 94.5006, loss_bbox: 0.1944, loss_mask: 0.2123, loss: 0.6067 2023-11-16 04:06:33,984 - mmdet - INFO - Epoch [23][800/1833] lr: 2.000e-04, eta: 8:11:35, time: 1.199, data_time: 0.065, memory: 16000, loss_rpn_cls: 0.0203, loss_rpn_bbox: 0.0306, loss_cls: 0.1538, acc: 94.3523, loss_bbox: 0.1966, loss_mask: 0.2147, loss: 0.6159 2023-11-16 04:07:33,427 - mmdet - INFO - Epoch [23][850/1833] lr: 2.000e-04, eta: 8:10:36, time: 1.189, data_time: 0.065, memory: 16000, loss_rpn_cls: 0.0207, loss_rpn_bbox: 0.0300, loss_cls: 0.1522, acc: 94.4503, loss_bbox: 0.1960, loss_mask: 0.2144, loss: 0.6133 2023-11-16 04:08:33,455 - mmdet - INFO - Epoch [23][900/1833] lr: 2.000e-04, eta: 8:09:37, time: 1.201, data_time: 0.071, memory: 16000, loss_rpn_cls: 0.0212, loss_rpn_bbox: 0.0304, loss_cls: 0.1508, acc: 94.4734, loss_bbox: 0.1963, loss_mask: 0.2159, loss: 0.6146 2023-11-16 04:09:34,618 - mmdet - INFO - Epoch [23][950/1833] lr: 2.000e-04, eta: 8:08:39, time: 1.223, data_time: 0.070, memory: 16000, loss_rpn_cls: 0.0206, loss_rpn_bbox: 0.0298, loss_cls: 0.1473, acc: 94.5775, loss_bbox: 0.1940, loss_mask: 0.2124, loss: 0.6042 2023-11-16 04:10:35,040 - mmdet - INFO - Epoch [23][1000/1833] lr: 2.000e-04, eta: 8:07:40, time: 1.208, data_time: 0.070, memory: 16000, loss_rpn_cls: 0.0206, loss_rpn_bbox: 0.0304, loss_cls: 0.1494, acc: 94.4935, loss_bbox: 0.1940, loss_mask: 0.2161, loss: 0.6106 2023-11-16 04:11:35,655 - mmdet - INFO - Epoch [23][1050/1833] lr: 2.000e-04, eta: 8:06:41, time: 1.212, data_time: 0.074, memory: 16000, loss_rpn_cls: 0.0207, loss_rpn_bbox: 0.0302, loss_cls: 0.1492, acc: 94.5048, loss_bbox: 0.1970, loss_mask: 0.2131, loss: 0.6102 2023-11-16 04:12:35,703 - mmdet - INFO - Epoch [23][1100/1833] lr: 2.000e-04, eta: 8:05:42, time: 1.201, data_time: 0.070, memory: 16000, loss_rpn_cls: 0.0225, loss_rpn_bbox: 0.0320, loss_cls: 0.1560, acc: 94.2608, loss_bbox: 0.2005, loss_mask: 0.2167, loss: 0.6277 2023-11-16 04:13:34,219 - mmdet - INFO - Epoch [23][1150/1833] lr: 2.000e-04, eta: 8:04:43, time: 1.170, data_time: 0.070, memory: 16000, loss_rpn_cls: 0.0197, loss_rpn_bbox: 0.0293, loss_cls: 0.1457, acc: 94.6560, loss_bbox: 0.1888, loss_mask: 0.2107, loss: 0.5943 2023-11-16 04:14:35,168 - mmdet - INFO - Epoch [23][1200/1833] lr: 2.000e-04, eta: 8:03:44, time: 1.219, data_time: 0.079, memory: 16000, loss_rpn_cls: 0.0213, loss_rpn_bbox: 0.0316, loss_cls: 0.1541, acc: 94.3693, loss_bbox: 0.1993, loss_mask: 0.2151, loss: 0.6214 2023-11-16 04:15:35,549 - mmdet - INFO - Epoch [23][1250/1833] lr: 2.000e-04, eta: 8:02:46, time: 1.208, data_time: 0.070, memory: 16000, loss_rpn_cls: 0.0199, loss_rpn_bbox: 0.0293, loss_cls: 0.1506, acc: 94.4996, loss_bbox: 0.1951, loss_mask: 0.2109, loss: 0.6058 2023-11-16 04:16:34,589 - mmdet - INFO - Epoch [23][1300/1833] lr: 2.000e-04, eta: 8:01:46, time: 1.181, data_time: 0.075, memory: 16000, loss_rpn_cls: 0.0212, loss_rpn_bbox: 0.0308, loss_cls: 0.1491, acc: 94.4866, loss_bbox: 0.1956, loss_mask: 0.2157, loss: 0.6124 2023-11-16 04:17:35,848 - mmdet - INFO - Epoch [23][1350/1833] lr: 2.000e-04, eta: 8:00:48, time: 1.225, data_time: 0.085, memory: 16000, loss_rpn_cls: 0.0203, loss_rpn_bbox: 0.0300, loss_cls: 0.1481, acc: 94.5248, loss_bbox: 0.1936, loss_mask: 0.2104, loss: 0.6024 2023-11-16 04:18:34,933 - mmdet - INFO - Epoch [23][1400/1833] lr: 2.000e-04, eta: 7:59:48, time: 1.182, data_time: 0.064, memory: 16000, loss_rpn_cls: 0.0214, loss_rpn_bbox: 0.0306, loss_cls: 0.1518, acc: 94.4423, loss_bbox: 0.1948, loss_mask: 0.2152, loss: 0.6138 2023-11-16 04:19:36,172 - mmdet - INFO - Epoch [23][1450/1833] lr: 2.000e-04, eta: 7:58:50, time: 1.225, data_time: 0.067, memory: 16000, loss_rpn_cls: 0.0220, loss_rpn_bbox: 0.0316, loss_cls: 0.1537, acc: 94.3394, loss_bbox: 0.2008, loss_mask: 0.2159, loss: 0.6240 2023-11-16 04:20:35,128 - mmdet - INFO - Epoch [23][1500/1833] lr: 2.000e-04, eta: 7:57:51, time: 1.179, data_time: 0.063, memory: 16000, loss_rpn_cls: 0.0212, loss_rpn_bbox: 0.0302, loss_cls: 0.1505, acc: 94.4886, loss_bbox: 0.1948, loss_mask: 0.2146, loss: 0.6112 2023-11-16 04:21:35,603 - mmdet - INFO - Epoch [23][1550/1833] lr: 2.000e-04, eta: 7:56:52, time: 1.209, data_time: 0.063, memory: 16000, loss_rpn_cls: 0.0213, loss_rpn_bbox: 0.0310, loss_cls: 0.1491, acc: 94.4915, loss_bbox: 0.1953, loss_mask: 0.2153, loss: 0.6120 2023-11-16 04:22:36,141 - mmdet - INFO - Epoch [23][1600/1833] lr: 2.000e-04, eta: 7:55:53, time: 1.211, data_time: 0.075, memory: 16000, loss_rpn_cls: 0.0210, loss_rpn_bbox: 0.0318, loss_cls: 0.1547, acc: 94.2739, loss_bbox: 0.2010, loss_mask: 0.2168, loss: 0.6254 2023-11-16 04:23:36,613 - mmdet - INFO - Epoch [23][1650/1833] lr: 2.000e-04, eta: 7:54:55, time: 1.209, data_time: 0.065, memory: 16000, loss_rpn_cls: 0.0209, loss_rpn_bbox: 0.0306, loss_cls: 0.1505, acc: 94.4948, loss_bbox: 0.1936, loss_mask: 0.2133, loss: 0.6089 2023-11-16 04:24:37,373 - mmdet - INFO - Epoch [23][1700/1833] lr: 2.000e-04, eta: 7:53:56, time: 1.215, data_time: 0.073, memory: 16000, loss_rpn_cls: 0.0214, loss_rpn_bbox: 0.0313, loss_cls: 0.1539, acc: 94.3461, loss_bbox: 0.1982, loss_mask: 0.2173, loss: 0.6219 2023-11-16 04:25:37,407 - mmdet - INFO - Epoch [23][1750/1833] lr: 2.000e-04, eta: 7:52:57, time: 1.201, data_time: 0.073, memory: 16000, loss_rpn_cls: 0.0213, loss_rpn_bbox: 0.0307, loss_cls: 0.1516, acc: 94.4515, loss_bbox: 0.1949, loss_mask: 0.2134, loss: 0.6121 2023-11-16 04:26:37,269 - mmdet - INFO - Epoch [23][1800/1833] lr: 2.000e-04, eta: 7:51:58, time: 1.197, data_time: 0.069, memory: 16000, loss_rpn_cls: 0.0211, loss_rpn_bbox: 0.0308, loss_cls: 0.1525, acc: 94.4119, loss_bbox: 0.1975, loss_mask: 0.2153, loss: 0.6171 2023-11-16 04:27:17,498 - mmdet - INFO - Saving checkpoint at 23 epochs 2023-11-16 04:28:04,955 - mmdet - INFO - Evaluating bbox... 2023-11-16 04:28:33,191 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.483 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.702 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.533 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.322 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 ] = 0.633 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 ] = 0.447 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 ] = 0.759 2023-11-16 04:28:33,194 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.586 | bicycle | 0.366 | car | 0.489 | | motorcycle | 0.491 | airplane | 0.714 | bus | 0.701 | | train | 0.684 | truck | 0.422 | boat | 0.343 | | traffic light | 0.318 | fire hydrant | 0.746 | stop sign | 0.674 | | parking meter | 0.522 | bench | 0.298 | bird | 0.418 | | cat | 0.732 | dog | 0.698 | horse | 0.644 | | sheep | 0.611 | cow | 0.644 | elephant | 0.673 | | bear | 0.761 | zebra | 0.686 | giraffe | 0.711 | | backpack | 0.211 | umbrella | 0.460 | handbag | 0.246 | | tie | 0.416 | suitcase | 0.489 | frisbee | 0.712 | | skis | 0.321 | snowboard | 0.430 | sports ball | 0.473 | | kite | 0.484 | baseball bat | 0.410 | baseball glove | 0.447 | | skateboard | 0.581 | surfboard | 0.464 | tennis racket | 0.574 | | bottle | 0.453 | wine glass | 0.428 | cup | 0.486 | | fork | 0.479 | knife | 0.302 | spoon | 0.300 | | bowl | 0.481 | banana | 0.272 | apple | 0.250 | | sandwich | 0.437 | orange | 0.353 | broccoli | 0.238 | | carrot | 0.235 | hot dog | 0.463 | pizza | 0.509 | | donut | 0.579 | cake | 0.427 | chair | 0.369 | | couch | 0.483 | potted plant | 0.341 | bed | 0.467 | | dining table | 0.313 | toilet | 0.654 | tv | 0.629 | | laptop | 0.684 | mouse | 0.649 | remote | 0.434 | | keyboard | 0.530 | cell phone | 0.462 | microwave | 0.643 | | oven | 0.407 | toaster | 0.452 | sink | 0.430 | | refrigerator | 0.643 | book | 0.197 | clock | 0.514 | | vase | 0.434 | scissors | 0.440 | teddy bear | 0.548 | | hair drier | 0.213 | toothbrush | 0.361 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-16 04:28:33,194 - mmdet - INFO - Evaluating segm... 2023-11-16 04:29:06,656 - 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 ] = 0.676 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.468 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.240 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.467 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.617 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 ] = 0.596 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.703 2023-11-16 04:29:06,659 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.509 | bicycle | 0.221 | car | 0.450 | | motorcycle | 0.405 | airplane | 0.550 | bus | 0.685 | | train | 0.673 | truck | 0.399 | boat | 0.311 | | traffic light | 0.303 | fire hydrant | 0.708 | stop sign | 0.668 | | parking meter | 0.534 | bench | 0.233 | bird | 0.345 | | cat | 0.715 | dog | 0.655 | horse | 0.489 | | sheep | 0.532 | cow | 0.551 | elephant | 0.608 | | bear | 0.742 | zebra | 0.589 | giraffe | 0.553 | | backpack | 0.215 | umbrella | 0.527 | handbag | 0.216 | | tie | 0.376 | suitcase | 0.502 | frisbee | 0.666 | | skis | 0.071 | snowboard | 0.289 | sports ball | 0.457 | | kite | 0.338 | baseball bat | 0.314 | baseball glove | 0.457 | | skateboard | 0.391 | surfboard | 0.386 | tennis racket | 0.604 | | bottle | 0.431 | wine glass | 0.393 | cup | 0.483 | | fork | 0.236 | knife | 0.195 | spoon | 0.210 | | bowl | 0.446 | banana | 0.231 | apple | 0.251 | | sandwich | 0.449 | orange | 0.348 | broccoli | 0.229 | | carrot | 0.215 | hot dog | 0.396 | pizza | 0.483 | | donut | 0.577 | cake | 0.434 | chair | 0.269 | | couch | 0.404 | potted plant | 0.290 | bed | 0.377 | | dining table | 0.181 | toilet | 0.648 | tv | 0.655 | | laptop | 0.669 | mouse | 0.631 | remote | 0.386 | | keyboard | 0.528 | cell phone | 0.429 | microwave | 0.640 | | oven | 0.365 | toaster | 0.527 | sink | 0.395 | | refrigerator | 0.633 | book | 0.154 | clock | 0.514 | | vase | 0.424 | scissors | 0.318 | teddy bear | 0.536 | | hair drier | 0.177 | toothbrush | 0.268 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-16 04:29:07,105 - mmdet - INFO - Exp name: mask_rcnn_flash_internimage_s_fpn_3x_coco_0.4.py 2023-11-16 04:29:07,105 - mmdet - INFO - Epoch(val) [23][625] bbox_mAP: 0.4829, bbox_mAP_50: 0.7024, bbox_mAP_75: 0.5332, bbox_mAP_s: 0.3216, bbox_mAP_m: 0.5223, bbox_mAP_l: 0.6329, bbox_mAP_copypaste: 0.4829 0.7024 0.5332 0.3216 0.5223 0.6329, segm_mAP: 0.4333, segm_mAP_50: 0.6758, segm_mAP_75: 0.4680, segm_mAP_s: 0.2401, segm_mAP_m: 0.4667, segm_mAP_l: 0.6166, segm_mAP_copypaste: 0.4333 0.6758 0.4680 0.2401 0.4667 0.6166 2023-11-16 04:30:11,131 - mmdet - INFO - Epoch [24][50/1833] lr: 2.000e-04, eta: 7:50:00, time: 1.280, data_time: 0.136, memory: 16000, loss_rpn_cls: 0.0189, loss_rpn_bbox: 0.0290, loss_cls: 0.1410, acc: 94.7693, loss_bbox: 0.1890, loss_mask: 0.2095, loss: 0.5873 2023-11-16 04:31:11,150 - mmdet - INFO - Epoch [24][100/1833] lr: 2.000e-04, eta: 7:49:01, time: 1.200, data_time: 0.081, memory: 16000, loss_rpn_cls: 0.0217, loss_rpn_bbox: 0.0310, loss_cls: 0.1530, acc: 94.4043, loss_bbox: 0.1976, loss_mask: 0.2125, loss: 0.6157 2023-11-16 04:32:11,192 - mmdet - INFO - Epoch [24][150/1833] lr: 2.000e-04, eta: 7:48:02, time: 1.201, data_time: 0.078, memory: 16000, loss_rpn_cls: 0.0191, loss_rpn_bbox: 0.0302, loss_cls: 0.1480, acc: 94.5635, loss_bbox: 0.1936, loss_mask: 0.2135, loss: 0.6045 2023-11-16 04:33:12,237 - mmdet - INFO - Epoch [24][200/1833] lr: 2.000e-04, eta: 7:47:04, time: 1.221, data_time: 0.089, memory: 16000, loss_rpn_cls: 0.0200, loss_rpn_bbox: 0.0304, loss_cls: 0.1508, acc: 94.4526, loss_bbox: 0.1952, loss_mask: 0.2134, loss: 0.6098 2023-11-16 04:34:12,958 - mmdet - INFO - Epoch [24][250/1833] lr: 2.000e-04, eta: 7:46:06, time: 1.214, data_time: 0.073, memory: 16000, loss_rpn_cls: 0.0196, loss_rpn_bbox: 0.0298, loss_cls: 0.1495, acc: 94.4799, loss_bbox: 0.1965, loss_mask: 0.2139, loss: 0.6094 2023-11-16 04:35:14,085 - mmdet - INFO - Epoch [24][300/1833] lr: 2.000e-04, eta: 7:45:07, time: 1.222, data_time: 0.074, memory: 16000, loss_rpn_cls: 0.0214, loss_rpn_bbox: 0.0320, loss_cls: 0.1507, acc: 94.4525, loss_bbox: 0.1969, loss_mask: 0.2146, loss: 0.6156 2023-11-16 04:36:13,986 - mmdet - INFO - Epoch [24][350/1833] lr: 2.000e-04, eta: 7:44:08, time: 1.198, data_time: 0.081, memory: 16000, loss_rpn_cls: 0.0199, loss_rpn_bbox: 0.0296, loss_cls: 0.1450, acc: 94.6514, loss_bbox: 0.1890, loss_mask: 0.2100, loss: 0.5936 2023-11-16 04:37:14,527 - mmdet - INFO - Epoch [24][400/1833] lr: 2.000e-04, eta: 7:43:10, time: 1.211, data_time: 0.074, memory: 16000, loss_rpn_cls: 0.0200, loss_rpn_bbox: 0.0295, loss_cls: 0.1450, acc: 94.6452, loss_bbox: 0.1899, loss_mask: 0.2123, loss: 0.5967 2023-11-16 04:38:14,060 - mmdet - INFO - Epoch [24][450/1833] lr: 2.000e-04, eta: 7:42:10, time: 1.191, data_time: 0.073, memory: 16000, loss_rpn_cls: 0.0201, loss_rpn_bbox: 0.0299, loss_cls: 0.1477, acc: 94.5737, loss_bbox: 0.1947, loss_mask: 0.2143, loss: 0.6068 2023-11-16 04:39:13,229 - mmdet - INFO - Epoch [24][500/1833] lr: 2.000e-04, eta: 7:41:11, time: 1.183, data_time: 0.079, memory: 16000, loss_rpn_cls: 0.0209, loss_rpn_bbox: 0.0309, loss_cls: 0.1494, acc: 94.4474, loss_bbox: 0.1971, loss_mask: 0.2153, loss: 0.6135 2023-11-16 04:40:12,486 - mmdet - INFO - Epoch [24][550/1833] lr: 2.000e-04, eta: 7:40:12, time: 1.185, data_time: 0.068, memory: 16000, loss_rpn_cls: 0.0197, loss_rpn_bbox: 0.0296, loss_cls: 0.1458, acc: 94.5650, loss_bbox: 0.1932, loss_mask: 0.2142, loss: 0.6025 2023-11-16 04:41:11,304 - mmdet - INFO - Epoch [24][600/1833] lr: 2.000e-04, eta: 7:39:12, time: 1.176, data_time: 0.066, memory: 16000, loss_rpn_cls: 0.0210, loss_rpn_bbox: 0.0303, loss_cls: 0.1488, acc: 94.5576, loss_bbox: 0.1952, loss_mask: 0.2148, loss: 0.6101 2023-11-16 04:42:11,892 - mmdet - INFO - Epoch [24][650/1833] lr: 2.000e-04, eta: 7:38:14, time: 1.212, data_time: 0.066, memory: 16000, loss_rpn_cls: 0.0201, loss_rpn_bbox: 0.0299, loss_cls: 0.1465, acc: 94.6186, loss_bbox: 0.1909, loss_mask: 0.2123, loss: 0.5997 2023-11-16 04:43:11,630 - mmdet - INFO - Epoch [24][700/1833] lr: 2.000e-04, eta: 7:37:15, time: 1.195, data_time: 0.070, memory: 16000, loss_rpn_cls: 0.0203, loss_rpn_bbox: 0.0307, loss_cls: 0.1497, acc: 94.4691, loss_bbox: 0.1957, loss_mask: 0.2124, loss: 0.6089 2023-11-16 04:44:12,055 - mmdet - INFO - Epoch [24][750/1833] lr: 2.000e-04, eta: 7:36:16, time: 1.209, data_time: 0.074, memory: 16000, loss_rpn_cls: 0.0213, loss_rpn_bbox: 0.0311, loss_cls: 0.1515, acc: 94.4409, loss_bbox: 0.1969, loss_mask: 0.2145, loss: 0.6153 2023-11-16 04:45:12,252 - mmdet - INFO - Epoch [24][800/1833] lr: 2.000e-04, eta: 7:35:17, time: 1.204, data_time: 0.072, memory: 16000, loss_rpn_cls: 0.0202, loss_rpn_bbox: 0.0301, loss_cls: 0.1482, acc: 94.5485, loss_bbox: 0.1940, loss_mask: 0.2118, loss: 0.6044 2023-11-16 04:46:11,309 - mmdet - INFO - Epoch [24][850/1833] lr: 2.000e-04, eta: 7:34:18, time: 1.181, data_time: 0.072, memory: 16000, loss_rpn_cls: 0.0204, loss_rpn_bbox: 0.0307, loss_cls: 0.1516, acc: 94.4005, loss_bbox: 0.1963, loss_mask: 0.2138, loss: 0.6128 2023-11-16 04:47:11,938 - mmdet - INFO - Epoch [24][900/1833] lr: 2.000e-04, eta: 7:33:19, time: 1.212, data_time: 0.069, memory: 16000, loss_rpn_cls: 0.0205, loss_rpn_bbox: 0.0305, loss_cls: 0.1521, acc: 94.3758, loss_bbox: 0.1978, loss_mask: 0.2134, loss: 0.6143 2023-11-16 04:48:11,171 - mmdet - INFO - Epoch [24][950/1833] lr: 2.000e-04, eta: 7:32:20, time: 1.185, data_time: 0.074, memory: 16000, loss_rpn_cls: 0.0212, loss_rpn_bbox: 0.0312, loss_cls: 0.1502, acc: 94.4556, loss_bbox: 0.1981, loss_mask: 0.2162, loss: 0.6168 2023-11-16 04:49:11,776 - mmdet - INFO - Epoch [24][1000/1833] lr: 2.000e-04, eta: 7:31:21, time: 1.212, data_time: 0.072, memory: 16000, loss_rpn_cls: 0.0204, loss_rpn_bbox: 0.0307, loss_cls: 0.1502, acc: 94.4987, loss_bbox: 0.1955, loss_mask: 0.2154, loss: 0.6121 2023-11-16 04:50:11,958 - mmdet - INFO - Epoch [24][1050/1833] lr: 2.000e-04, eta: 7:30:22, time: 1.204, data_time: 0.070, memory: 16000, loss_rpn_cls: 0.0206, loss_rpn_bbox: 0.0308, loss_cls: 0.1512, acc: 94.3765, loss_bbox: 0.1960, loss_mask: 0.2129, loss: 0.6115 2023-11-16 04:51:11,193 - mmdet - INFO - Epoch [24][1100/1833] lr: 2.000e-04, eta: 7:29:23, time: 1.185, data_time: 0.069, memory: 16000, loss_rpn_cls: 0.0204, loss_rpn_bbox: 0.0310, loss_cls: 0.1509, acc: 94.4288, loss_bbox: 0.1986, loss_mask: 0.2138, loss: 0.6148 2023-11-16 04:52:11,025 - mmdet - INFO - Epoch [24][1150/1833] lr: 2.000e-04, eta: 7:28:24, time: 1.197, data_time: 0.065, memory: 16000, loss_rpn_cls: 0.0205, loss_rpn_bbox: 0.0301, loss_cls: 0.1508, acc: 94.4153, loss_bbox: 0.1963, loss_mask: 0.2148, loss: 0.6124 2023-11-16 04:53:11,318 - mmdet - INFO - Epoch [24][1200/1833] lr: 2.000e-04, eta: 7:27:25, time: 1.206, data_time: 0.080, memory: 16000, loss_rpn_cls: 0.0208, loss_rpn_bbox: 0.0303, loss_cls: 0.1502, acc: 94.5298, loss_bbox: 0.1945, loss_mask: 0.2139, loss: 0.6096 2023-11-16 04:54:12,197 - mmdet - INFO - Epoch [24][1250/1833] lr: 2.000e-04, eta: 7:26:26, time: 1.218, data_time: 0.073, memory: 16000, loss_rpn_cls: 0.0212, loss_rpn_bbox: 0.0305, loss_cls: 0.1492, acc: 94.5340, loss_bbox: 0.1946, loss_mask: 0.2101, loss: 0.6057 2023-11-16 04:55:11,593 - mmdet - INFO - Epoch [24][1300/1833] lr: 2.000e-04, eta: 7:25:27, time: 1.188, data_time: 0.071, memory: 16000, loss_rpn_cls: 0.0199, loss_rpn_bbox: 0.0306, loss_cls: 0.1503, acc: 94.5048, loss_bbox: 0.1940, loss_mask: 0.2160, loss: 0.6109 2023-11-16 04:56:11,610 - mmdet - INFO - Epoch [24][1350/1833] lr: 2.000e-04, eta: 7:24:28, time: 1.200, data_time: 0.077, memory: 16000, loss_rpn_cls: 0.0208, loss_rpn_bbox: 0.0309, loss_cls: 0.1555, acc: 94.3054, loss_bbox: 0.1994, loss_mask: 0.2118, loss: 0.6183 2023-11-16 04:57:11,656 - mmdet - INFO - Epoch [24][1400/1833] lr: 2.000e-04, eta: 7:23:29, time: 1.201, data_time: 0.073, memory: 16000, loss_rpn_cls: 0.0215, loss_rpn_bbox: 0.0307, loss_cls: 0.1556, acc: 94.3346, loss_bbox: 0.2008, loss_mask: 0.2151, loss: 0.6236 2023-11-16 04:58:11,979 - mmdet - INFO - Epoch [24][1450/1833] lr: 2.000e-04, eta: 7:22:30, time: 1.206, data_time: 0.077, memory: 16000, loss_rpn_cls: 0.0221, loss_rpn_bbox: 0.0322, loss_cls: 0.1536, acc: 94.3121, loss_bbox: 0.2005, loss_mask: 0.2177, loss: 0.6261 2023-11-16 04:59:12,603 - mmdet - INFO - Epoch [24][1500/1833] lr: 2.000e-04, eta: 7:21:32, time: 1.212, data_time: 0.070, memory: 16000, loss_rpn_cls: 0.0207, loss_rpn_bbox: 0.0299, loss_cls: 0.1500, acc: 94.5027, loss_bbox: 0.1936, loss_mask: 0.2149, loss: 0.6090 2023-11-16 05:00:11,907 - mmdet - INFO - Epoch [24][1550/1833] lr: 2.000e-04, eta: 7:20:32, time: 1.186, data_time: 0.073, memory: 16000, loss_rpn_cls: 0.0219, loss_rpn_bbox: 0.0305, loss_cls: 0.1502, acc: 94.5227, loss_bbox: 0.1927, loss_mask: 0.2110, loss: 0.6062 2023-11-16 05:01:12,251 - mmdet - INFO - Epoch [24][1600/1833] lr: 2.000e-04, eta: 7:19:34, time: 1.207, data_time: 0.074, memory: 16000, loss_rpn_cls: 0.0204, loss_rpn_bbox: 0.0296, loss_cls: 0.1501, acc: 94.4717, loss_bbox: 0.1935, loss_mask: 0.2125, loss: 0.6062 2023-11-16 05:02:12,548 - mmdet - INFO - Epoch [24][1650/1833] lr: 2.000e-04, eta: 7:18:35, time: 1.206, data_time: 0.066, memory: 16000, loss_rpn_cls: 0.0208, loss_rpn_bbox: 0.0311, loss_cls: 0.1545, acc: 94.2913, loss_bbox: 0.1991, loss_mask: 0.2134, loss: 0.6189 2023-11-16 05:03:11,834 - mmdet - INFO - Epoch [24][1700/1833] lr: 2.000e-04, eta: 7:17:35, time: 1.186, data_time: 0.075, memory: 16000, loss_rpn_cls: 0.0209, loss_rpn_bbox: 0.0303, loss_cls: 0.1517, acc: 94.4321, loss_bbox: 0.1953, loss_mask: 0.2139, loss: 0.6122 2023-11-16 05:04:14,089 - mmdet - INFO - Epoch [24][1750/1833] lr: 2.000e-04, eta: 7:16:38, time: 1.245, data_time: 0.064, memory: 16000, loss_rpn_cls: 0.0210, loss_rpn_bbox: 0.0307, loss_cls: 0.1511, acc: 94.4467, loss_bbox: 0.1950, loss_mask: 0.2123, loss: 0.6101 2023-11-16 05:05:13,811 - mmdet - INFO - Epoch [24][1800/1833] lr: 2.000e-04, eta: 7:15:38, time: 1.195, data_time: 0.069, memory: 16000, loss_rpn_cls: 0.0199, loss_rpn_bbox: 0.0293, loss_cls: 0.1470, acc: 94.6265, loss_bbox: 0.1898, loss_mask: 0.2070, loss: 0.5930 2023-11-16 05:05:53,584 - mmdet - INFO - Saving checkpoint at 24 epochs 2023-11-16 05:06:41,176 - mmdet - INFO - Evaluating bbox... 2023-11-16 05:07:08,690 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.485 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.702 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.533 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.325 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.528 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 ] = 0.612 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.612 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.612 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.438 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.652 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.759 2023-11-16 05:07:08,693 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.592 | bicycle | 0.385 | car | 0.505 | | motorcycle | 0.500 | airplane | 0.708 | bus | 0.706 | | train | 0.691 | truck | 0.400 | boat | 0.338 | | traffic light | 0.320 | fire hydrant | 0.743 | stop sign | 0.675 | | parking meter | 0.520 | bench | 0.302 | bird | 0.433 | | cat | 0.738 | dog | 0.687 | horse | 0.632 | | sheep | 0.600 | cow | 0.631 | elephant | 0.708 | | bear | 0.752 | zebra | 0.690 | giraffe | 0.697 | | backpack | 0.212 | umbrella | 0.476 | handbag | 0.248 | | tie | 0.411 | suitcase | 0.481 | frisbee | 0.721 | | skis | 0.304 | snowboard | 0.436 | sports ball | 0.490 | | kite | 0.483 | baseball bat | 0.406 | baseball glove | 0.447 | | skateboard | 0.588 | surfboard | 0.469 | tennis racket | 0.572 | | bottle | 0.454 | wine glass | 0.416 | cup | 0.498 | | fork | 0.498 | knife | 0.317 | spoon | 0.267 | | bowl | 0.476 | banana | 0.279 | apple | 0.277 | | sandwich | 0.455 | orange | 0.359 | broccoli | 0.270 | | carrot | 0.251 | hot dog | 0.451 | pizza | 0.538 | | donut | 0.563 | cake | 0.431 | chair | 0.375 | | couch | 0.472 | potted plant | 0.347 | bed | 0.462 | | dining table | 0.321 | toilet | 0.649 | tv | 0.626 | | laptop | 0.681 | mouse | 0.648 | remote | 0.434 | | keyboard | 0.539 | cell phone | 0.441 | microwave | 0.671 | | oven | 0.411 | toaster | 0.393 | sink | 0.444 | | refrigerator | 0.657 | book | 0.205 | clock | 0.523 | | vase | 0.437 | scissors | 0.465 | teddy bear | 0.547 | | hair drier | 0.237 | toothbrush | 0.313 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-16 05:07:08,693 - mmdet - INFO - Evaluating segm... 2023-11-16 05:07:39,614 - 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 ] = 0.674 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.468 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.241 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 ] = 0.621 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.553 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.553 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.553 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.379 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.592 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.710 2023-11-16 05:07:39,616 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.514 | bicycle | 0.220 | car | 0.463 | | motorcycle | 0.422 | airplane | 0.526 | bus | 0.682 | | train | 0.685 | truck | 0.387 | boat | 0.305 | | traffic light | 0.304 | fire hydrant | 0.706 | stop sign | 0.661 | | parking meter | 0.518 | bench | 0.233 | bird | 0.358 | | cat | 0.722 | dog | 0.648 | horse | 0.470 | | sheep | 0.529 | cow | 0.531 | elephant | 0.649 | | bear | 0.740 | zebra | 0.603 | giraffe | 0.551 | | backpack | 0.212 | umbrella | 0.537 | handbag | 0.233 | | tie | 0.371 | suitcase | 0.504 | frisbee | 0.658 | | skis | 0.066 | snowboard | 0.284 | sports ball | 0.471 | | kite | 0.334 | baseball bat | 0.323 | baseball glove | 0.463 | | skateboard | 0.396 | surfboard | 0.379 | tennis racket | 0.612 | | bottle | 0.428 | wine glass | 0.371 | cup | 0.492 | | fork | 0.266 | knife | 0.223 | spoon | 0.199 | | bowl | 0.454 | banana | 0.224 | apple | 0.268 | | sandwich | 0.468 | orange | 0.354 | broccoli | 0.250 | | carrot | 0.224 | hot dog | 0.377 | pizza | 0.519 | | donut | 0.565 | cake | 0.445 | chair | 0.264 | | couch | 0.397 | potted plant | 0.285 | bed | 0.381 | | dining table | 0.193 | toilet | 0.643 | tv | 0.649 | | laptop | 0.674 | mouse | 0.627 | remote | 0.400 | | keyboard | 0.520 | cell phone | 0.414 | microwave | 0.668 | | oven | 0.370 | toaster | 0.417 | sink | 0.423 | | refrigerator | 0.649 | book | 0.153 | clock | 0.521 | | vase | 0.428 | scissors | 0.320 | teddy bear | 0.513 | | hair drier | 0.143 | toothbrush | 0.214 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-16 05:07:40,086 - mmdet - INFO - The previous best checkpoint /mnt/petrelfs/lizhiqi/DINO/detection/work_dirs/mask_rcnn_flash_internimage_s_fpn_3x_coco_0.4/best_bbox_mAP_epoch_19.pth was removed 2023-11-16 05:07:42,262 - mmdet - INFO - Now best checkpoint is saved as best_bbox_mAP_epoch_24.pth. 2023-11-16 05:07:42,263 - mmdet - INFO - Best bbox_mAP is 0.4849 at 24 epoch. 2023-11-16 05:07:42,263 - mmdet - INFO - Exp name: mask_rcnn_flash_internimage_s_fpn_3x_coco_0.4.py 2023-11-16 05:07:42,263 - mmdet - INFO - Epoch(val) [24][625] bbox_mAP: 0.4849, bbox_mAP_50: 0.7024, bbox_mAP_75: 0.5329, bbox_mAP_s: 0.3255, bbox_mAP_m: 0.5283, bbox_mAP_l: 0.6244, bbox_mAP_copypaste: 0.4849 0.7024 0.5329 0.3255 0.5283 0.6244, segm_mAP: 0.4334, segm_mAP_50: 0.6738, segm_mAP_75: 0.4682, segm_mAP_s: 0.2414, segm_mAP_m: 0.4679, segm_mAP_l: 0.6211, segm_mAP_copypaste: 0.4334 0.6738 0.4682 0.2414 0.4679 0.6211 2023-11-16 05:08:46,357 - mmdet - INFO - Epoch [25][50/1833] lr: 2.000e-04, eta: 7:13:43, time: 1.281, data_time: 0.129, memory: 16000, loss_rpn_cls: 0.0199, loss_rpn_bbox: 0.0305, loss_cls: 0.1493, acc: 94.4958, loss_bbox: 0.1961, loss_mask: 0.2117, loss: 0.6075 2023-11-16 05:09:46,549 - mmdet - INFO - Epoch [25][100/1833] lr: 2.000e-04, eta: 7:12:44, time: 1.204, data_time: 0.076, memory: 16000, loss_rpn_cls: 0.0196, loss_rpn_bbox: 0.0300, loss_cls: 0.1462, acc: 94.5773, loss_bbox: 0.1935, loss_mask: 0.2124, loss: 0.6017 2023-11-16 05:10:49,542 - mmdet - INFO - Epoch [25][150/1833] lr: 2.000e-04, eta: 7:11:46, time: 1.260, data_time: 0.074, memory: 16000, loss_rpn_cls: 0.0203, loss_rpn_bbox: 0.0306, loss_cls: 0.1475, acc: 94.5516, loss_bbox: 0.1931, loss_mask: 0.2108, loss: 0.6023 2023-11-16 05:11:49,235 - mmdet - INFO - Epoch [25][200/1833] lr: 2.000e-04, eta: 7:10:47, time: 1.194, data_time: 0.074, memory: 16000, loss_rpn_cls: 0.0197, loss_rpn_bbox: 0.0296, loss_cls: 0.1462, acc: 94.6047, loss_bbox: 0.1917, loss_mask: 0.2112, loss: 0.5985 2023-11-16 05:12:49,364 - mmdet - INFO - Epoch [25][250/1833] lr: 2.000e-04, eta: 7:09:48, time: 1.202, data_time: 0.069, memory: 16000, loss_rpn_cls: 0.0208, loss_rpn_bbox: 0.0305, loss_cls: 0.1461, acc: 94.5497, loss_bbox: 0.1924, loss_mask: 0.2122, loss: 0.6020 2023-11-16 05:13:49,498 - mmdet - INFO - Epoch [25][300/1833] lr: 2.000e-04, eta: 7:08:50, time: 1.203, data_time: 0.068, memory: 16000, loss_rpn_cls: 0.0204, loss_rpn_bbox: 0.0306, loss_cls: 0.1488, acc: 94.5040, loss_bbox: 0.1947, loss_mask: 0.2129, loss: 0.6074 2023-11-16 05:14:49,502 - mmdet - INFO - Epoch [25][350/1833] lr: 2.000e-04, eta: 7:07:51, time: 1.200, data_time: 0.075, memory: 16000, loss_rpn_cls: 0.0198, loss_rpn_bbox: 0.0308, loss_cls: 0.1479, acc: 94.5247, loss_bbox: 0.1928, loss_mask: 0.2125, loss: 0.6038 2023-11-16 05:15:49,266 - mmdet - INFO - Epoch [25][400/1833] lr: 2.000e-04, eta: 7:06:52, time: 1.195, data_time: 0.075, memory: 16000, loss_rpn_cls: 0.0192, loss_rpn_bbox: 0.0295, loss_cls: 0.1451, acc: 94.6607, loss_bbox: 0.1895, loss_mask: 0.2120, loss: 0.5953 2023-11-16 05:16:49,007 - mmdet - INFO - Epoch [25][450/1833] lr: 2.000e-04, eta: 7:05:52, time: 1.195, data_time: 0.069, memory: 16000, loss_rpn_cls: 0.0187, loss_rpn_bbox: 0.0296, loss_cls: 0.1483, acc: 94.5522, loss_bbox: 0.1937, loss_mask: 0.2126, loss: 0.6029 2023-11-16 05:17:48,965 - mmdet - INFO - Epoch [25][500/1833] lr: 2.000e-04, eta: 7:04:54, time: 1.199, data_time: 0.071, memory: 16000, loss_rpn_cls: 0.0190, loss_rpn_bbox: 0.0293, loss_cls: 0.1484, acc: 94.4962, loss_bbox: 0.1953, loss_mask: 0.2119, loss: 0.6038 2023-11-16 05:18:48,805 - mmdet - INFO - Epoch [25][550/1833] lr: 2.000e-04, eta: 7:03:54, time: 1.197, data_time: 0.068, memory: 16000, loss_rpn_cls: 0.0193, loss_rpn_bbox: 0.0293, loss_cls: 0.1452, acc: 94.6400, loss_bbox: 0.1919, loss_mask: 0.2119, loss: 0.5976 2023-11-16 05:19:47,889 - mmdet - INFO - Epoch [25][600/1833] lr: 2.000e-04, eta: 7:02:55, time: 1.182, data_time: 0.068, memory: 16000, loss_rpn_cls: 0.0202, loss_rpn_bbox: 0.0296, loss_cls: 0.1484, acc: 94.4860, loss_bbox: 0.1947, loss_mask: 0.2131, loss: 0.6059 2023-11-16 05:20:48,577 - mmdet - INFO - Epoch [25][650/1833] lr: 2.000e-04, eta: 7:01:56, time: 1.214, data_time: 0.073, memory: 16000, loss_rpn_cls: 0.0206, loss_rpn_bbox: 0.0304, loss_cls: 0.1473, acc: 94.5706, loss_bbox: 0.1921, loss_mask: 0.2120, loss: 0.6024 2023-11-16 05:21:49,720 - mmdet - INFO - Epoch [25][700/1833] lr: 2.000e-04, eta: 7:00:58, time: 1.223, data_time: 0.067, memory: 16000, loss_rpn_cls: 0.0199, loss_rpn_bbox: 0.0303, loss_cls: 0.1480, acc: 94.5276, loss_bbox: 0.1944, loss_mask: 0.2129, loss: 0.6055 2023-11-16 05:22:50,529 - mmdet - INFO - Epoch [25][750/1833] lr: 2.000e-04, eta: 6:59:59, time: 1.216, data_time: 0.066, memory: 16000, loss_rpn_cls: 0.0211, loss_rpn_bbox: 0.0312, loss_cls: 0.1513, acc: 94.4489, loss_bbox: 0.1964, loss_mask: 0.2102, loss: 0.6102 2023-11-16 05:23:50,584 - mmdet - INFO - Epoch [25][800/1833] lr: 2.000e-04, eta: 6:59:00, time: 1.201, data_time: 0.060, memory: 16000, loss_rpn_cls: 0.0190, loss_rpn_bbox: 0.0290, loss_cls: 0.1435, acc: 94.7186, loss_bbox: 0.1885, loss_mask: 0.2114, loss: 0.5914 2023-11-16 05:24:50,890 - mmdet - INFO - Epoch [25][850/1833] lr: 2.000e-04, eta: 6:58:02, time: 1.206, data_time: 0.074, memory: 16000, loss_rpn_cls: 0.0196, loss_rpn_bbox: 0.0307, loss_cls: 0.1485, acc: 94.4988, loss_bbox: 0.1938, loss_mask: 0.2111, loss: 0.6037 2023-11-16 05:25:52,873 - mmdet - INFO - Epoch [25][900/1833] lr: 2.000e-04, eta: 6:57:04, time: 1.240, data_time: 0.078, memory: 16000, loss_rpn_cls: 0.0207, loss_rpn_bbox: 0.0302, loss_cls: 0.1495, acc: 94.5219, loss_bbox: 0.1929, loss_mask: 0.2127, loss: 0.6060 2023-11-16 05:26:53,358 - mmdet - INFO - Epoch [25][950/1833] lr: 2.000e-04, eta: 6:56:05, time: 1.210, data_time: 0.075, memory: 16000, loss_rpn_cls: 0.0211, loss_rpn_bbox: 0.0311, loss_cls: 0.1514, acc: 94.4348, loss_bbox: 0.1975, loss_mask: 0.2138, loss: 0.6148 2023-11-16 05:27:53,205 - mmdet - INFO - Epoch [25][1000/1833] lr: 2.000e-04, eta: 6:55:06, time: 1.197, data_time: 0.073, memory: 16000, loss_rpn_cls: 0.0188, loss_rpn_bbox: 0.0290, loss_cls: 0.1464, acc: 94.5688, loss_bbox: 0.1916, loss_mask: 0.2100, loss: 0.5958 2023-11-16 05:28:54,196 - mmdet - INFO - Epoch [25][1050/1833] lr: 2.000e-04, eta: 6:54:07, time: 1.220, data_time: 0.067, memory: 16000, loss_rpn_cls: 0.0214, loss_rpn_bbox: 0.0306, loss_cls: 0.1498, acc: 94.4453, loss_bbox: 0.1969, loss_mask: 0.2119, loss: 0.6105 2023-11-16 05:29:56,075 - mmdet - INFO - Epoch [25][1100/1833] lr: 2.000e-04, eta: 6:53:09, time: 1.238, data_time: 0.068, memory: 16000, loss_rpn_cls: 0.0212, loss_rpn_bbox: 0.0317, loss_cls: 0.1534, acc: 94.3289, loss_bbox: 0.1973, loss_mask: 0.2126, loss: 0.6162 2023-11-16 05:30:56,755 - mmdet - INFO - Epoch [25][1150/1833] lr: 2.000e-04, eta: 6:52:10, time: 1.214, data_time: 0.062, memory: 16000, loss_rpn_cls: 0.0220, loss_rpn_bbox: 0.0324, loss_cls: 0.1580, acc: 94.1887, loss_bbox: 0.2032, loss_mask: 0.2186, loss: 0.6342 2023-11-16 05:31:56,843 - mmdet - INFO - Epoch [25][1200/1833] lr: 2.000e-04, eta: 6:51:11, time: 1.202, data_time: 0.075, memory: 16000, loss_rpn_cls: 0.0206, loss_rpn_bbox: 0.0301, loss_cls: 0.1486, acc: 94.5574, loss_bbox: 0.1917, loss_mask: 0.2120, loss: 0.6029 2023-11-16 05:32:56,113 - mmdet - INFO - Epoch [25][1250/1833] lr: 2.000e-04, eta: 6:50:12, time: 1.185, data_time: 0.078, memory: 16000, loss_rpn_cls: 0.0208, loss_rpn_bbox: 0.0309, loss_cls: 0.1554, acc: 94.2913, loss_bbox: 0.2007, loss_mask: 0.2163, loss: 0.6242 2023-11-16 05:33:56,446 - mmdet - INFO - Epoch [25][1300/1833] lr: 2.000e-04, eta: 6:49:13, time: 1.207, data_time: 0.083, memory: 16000, loss_rpn_cls: 0.0212, loss_rpn_bbox: 0.0314, loss_cls: 0.1519, acc: 94.4286, loss_bbox: 0.1971, loss_mask: 0.2139, loss: 0.6154 2023-11-16 05:34:56,937 - mmdet - INFO - Epoch [25][1350/1833] lr: 2.000e-04, eta: 6:48:14, time: 1.210, data_time: 0.079, memory: 16000, loss_rpn_cls: 0.0209, loss_rpn_bbox: 0.0301, loss_cls: 0.1483, acc: 94.5671, loss_bbox: 0.1930, loss_mask: 0.2112, loss: 0.6034 2023-11-16 05:35:56,825 - mmdet - INFO - Epoch [25][1400/1833] lr: 2.000e-04, eta: 6:47:15, time: 1.198, data_time: 0.087, memory: 16000, loss_rpn_cls: 0.0207, loss_rpn_bbox: 0.0306, loss_cls: 0.1490, acc: 94.4689, loss_bbox: 0.1956, loss_mask: 0.2146, loss: 0.6105 2023-11-16 05:36:56,706 - mmdet - INFO - Epoch [25][1450/1833] lr: 2.000e-04, eta: 6:46:16, time: 1.198, data_time: 0.078, memory: 16000, loss_rpn_cls: 0.0203, loss_rpn_bbox: 0.0310, loss_cls: 0.1482, acc: 94.5860, loss_bbox: 0.1917, loss_mask: 0.2138, loss: 0.6050 2023-11-16 05:37:56,746 - mmdet - INFO - Epoch [25][1500/1833] lr: 2.000e-04, eta: 6:45:17, time: 1.201, data_time: 0.088, memory: 16000, loss_rpn_cls: 0.0207, loss_rpn_bbox: 0.0309, loss_cls: 0.1517, acc: 94.4477, loss_bbox: 0.1978, loss_mask: 0.2149, loss: 0.6160 2023-11-16 05:38:58,374 - mmdet - INFO - Epoch [25][1550/1833] lr: 2.000e-04, eta: 6:44:19, time: 1.233, data_time: 0.076, memory: 16000, loss_rpn_cls: 0.0204, loss_rpn_bbox: 0.0300, loss_cls: 0.1475, acc: 94.5339, loss_bbox: 0.1927, loss_mask: 0.2112, loss: 0.6017 2023-11-16 05:39:57,557 - mmdet - INFO - Epoch [25][1600/1833] lr: 2.000e-04, eta: 6:43:20, time: 1.184, data_time: 0.088, memory: 16000, loss_rpn_cls: 0.0207, loss_rpn_bbox: 0.0311, loss_cls: 0.1550, acc: 94.3491, loss_bbox: 0.1986, loss_mask: 0.2151, loss: 0.6205 2023-11-16 05:40:56,839 - mmdet - INFO - Epoch [25][1650/1833] lr: 2.000e-04, eta: 6:42:20, time: 1.186, data_time: 0.074, memory: 16000, loss_rpn_cls: 0.0201, loss_rpn_bbox: 0.0294, loss_cls: 0.1469, acc: 94.5300, loss_bbox: 0.1926, loss_mask: 0.2103, loss: 0.5994 2023-11-16 05:41:55,346 - mmdet - INFO - Epoch [25][1700/1833] lr: 2.000e-04, eta: 6:41:21, time: 1.170, data_time: 0.072, memory: 16000, loss_rpn_cls: 0.0208, loss_rpn_bbox: 0.0303, loss_cls: 0.1515, acc: 94.4512, loss_bbox: 0.1943, loss_mask: 0.2118, loss: 0.6087 2023-11-16 05:42:56,411 - mmdet - INFO - Epoch [25][1750/1833] lr: 2.000e-04, eta: 6:40:22, time: 1.221, data_time: 0.077, memory: 16000, loss_rpn_cls: 0.0204, loss_rpn_bbox: 0.0303, loss_cls: 0.1503, acc: 94.4131, loss_bbox: 0.1956, loss_mask: 0.2134, loss: 0.6099 2023-11-16 05:43:55,311 - mmdet - INFO - Epoch [25][1800/1833] lr: 2.000e-04, eta: 6:39:23, time: 1.178, data_time: 0.081, memory: 16000, loss_rpn_cls: 0.0207, loss_rpn_bbox: 0.0306, loss_cls: 0.1516, acc: 94.4779, loss_bbox: 0.1948, loss_mask: 0.2136, loss: 0.6112 2023-11-16 05:44:35,668 - mmdet - INFO - Saving checkpoint at 25 epochs 2023-11-16 05:45:22,865 - mmdet - INFO - Evaluating bbox... 2023-11-16 05:45:50,900 - 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 ] = 0.706 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.534 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.324 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 ] = 0.626 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.612 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.612 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.612 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.441 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 ] = 0.757 2023-11-16 05:45:50,903 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.590 | bicycle | 0.393 | car | 0.495 | | motorcycle | 0.500 | airplane | 0.709 | bus | 0.698 | | train | 0.671 | truck | 0.460 | boat | 0.321 | | traffic light | 0.311 | fire hydrant | 0.739 | stop sign | 0.688 | | parking meter | 0.522 | bench | 0.311 | bird | 0.422 | | cat | 0.746 | dog | 0.696 | horse | 0.636 | | sheep | 0.615 | cow | 0.626 | elephant | 0.697 | | bear | 0.755 | zebra | 0.684 | giraffe | 0.708 | | backpack | 0.224 | umbrella | 0.466 | handbag | 0.249 | | tie | 0.397 | suitcase | 0.482 | frisbee | 0.713 | | skis | 0.303 | snowboard | 0.449 | sports ball | 0.469 | | kite | 0.479 | baseball bat | 0.406 | baseball glove | 0.442 | | skateboard | 0.582 | surfboard | 0.471 | tennis racket | 0.572 | | bottle | 0.465 | wine glass | 0.415 | cup | 0.499 | | fork | 0.483 | knife | 0.294 | spoon | 0.321 | | bowl | 0.476 | banana | 0.267 | apple | 0.256 | | sandwich | 0.445 | orange | 0.371 | broccoli | 0.247 | | carrot | 0.272 | hot dog | 0.455 | pizza | 0.554 | | donut | 0.561 | cake | 0.448 | chair | 0.366 | | couch | 0.471 | potted plant | 0.353 | bed | 0.472 | | dining table | 0.329 | toilet | 0.666 | tv | 0.635 | | laptop | 0.683 | mouse | 0.644 | remote | 0.459 | | keyboard | 0.570 | cell phone | 0.431 | microwave | 0.680 | | oven | 0.411 | toaster | 0.478 | sink | 0.432 | | refrigerator | 0.653 | book | 0.209 | clock | 0.514 | | vase | 0.445 | scissors | 0.379 | teddy bear | 0.545 | | hair drier | 0.232 | toothbrush | 0.355 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-16 05:45:50,903 - mmdet - INFO - Evaluating segm... 2023-11-16 05:46:23,013 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.435 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.677 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.467 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.241 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.470 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 ] = 0.554 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.554 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.554 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.379 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 ] = 0.707 2023-11-16 05:46:23,016 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.512 | bicycle | 0.233 | car | 0.456 | | motorcycle | 0.414 | airplane | 0.534 | bus | 0.685 | | train | 0.667 | truck | 0.432 | boat | 0.294 | | traffic light | 0.301 | fire hydrant | 0.710 | stop sign | 0.669 | | parking meter | 0.522 | bench | 0.237 | bird | 0.340 | | cat | 0.723 | dog | 0.641 | horse | 0.474 | | sheep | 0.544 | cow | 0.530 | elephant | 0.643 | | bear | 0.725 | zebra | 0.602 | giraffe | 0.562 | | backpack | 0.222 | umbrella | 0.514 | handbag | 0.223 | | tie | 0.367 | suitcase | 0.497 | frisbee | 0.658 | | skis | 0.072 | snowboard | 0.302 | sports ball | 0.462 | | kite | 0.334 | baseball bat | 0.326 | baseball glove | 0.464 | | skateboard | 0.358 | surfboard | 0.378 | tennis racket | 0.611 | | bottle | 0.439 | wine glass | 0.385 | cup | 0.496 | | fork | 0.244 | knife | 0.199 | spoon | 0.216 | | bowl | 0.435 | banana | 0.220 | apple | 0.242 | | sandwich | 0.457 | orange | 0.371 | broccoli | 0.237 | | carrot | 0.243 | hot dog | 0.364 | pizza | 0.535 | | donut | 0.564 | cake | 0.454 | chair | 0.262 | | couch | 0.413 | potted plant | 0.297 | bed | 0.363 | | dining table | 0.196 | toilet | 0.639 | tv | 0.663 | | laptop | 0.674 | mouse | 0.629 | remote | 0.404 | | keyboard | 0.551 | cell phone | 0.410 | microwave | 0.681 | | oven | 0.371 | toaster | 0.538 | sink | 0.411 | | refrigerator | 0.659 | book | 0.150 | clock | 0.515 | | vase | 0.441 | scissors | 0.268 | teddy bear | 0.511 | | hair drier | 0.199 | toothbrush | 0.230 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-16 05:46:23,482 - mmdet - INFO - The previous best checkpoint /mnt/petrelfs/lizhiqi/DINO/detection/work_dirs/mask_rcnn_flash_internimage_s_fpn_3x_coco_0.4/best_bbox_mAP_epoch_24.pth was removed 2023-11-16 05:46:25,634 - mmdet - INFO - Now best checkpoint is saved as best_bbox_mAP_epoch_25.pth. 2023-11-16 05:46:25,635 - mmdet - INFO - Best bbox_mAP is 0.4867 at 25 epoch. 2023-11-16 05:46:25,635 - mmdet - INFO - Exp name: mask_rcnn_flash_internimage_s_fpn_3x_coco_0.4.py 2023-11-16 05:46:25,635 - mmdet - INFO - Epoch(val) [25][625] bbox_mAP: 0.4867, bbox_mAP_50: 0.7060, bbox_mAP_75: 0.5338, bbox_mAP_s: 0.3242, bbox_mAP_m: 0.5264, bbox_mAP_l: 0.6257, bbox_mAP_copypaste: 0.4867 0.7060 0.5338 0.3242 0.5264 0.6257, segm_mAP: 0.4352, segm_mAP_50: 0.6771, segm_mAP_75: 0.4672, segm_mAP_s: 0.2406, segm_mAP_m: 0.4696, segm_mAP_l: 0.6227, segm_mAP_copypaste: 0.4352 0.6771 0.4672 0.2406 0.4696 0.6227 2023-11-16 05:47:30,044 - mmdet - INFO - Epoch [26][50/1833] lr: 2.000e-04, eta: 6:37:29, time: 1.288, data_time: 0.135, memory: 16000, loss_rpn_cls: 0.0194, loss_rpn_bbox: 0.0302, loss_cls: 0.1457, acc: 94.5929, loss_bbox: 0.1916, loss_mask: 0.2102, loss: 0.5971 2023-11-16 05:48:33,046 - mmdet - INFO - Epoch [26][100/1833] lr: 2.000e-04, eta: 6:36:31, time: 1.260, data_time: 0.081, memory: 16000, loss_rpn_cls: 0.0190, loss_rpn_bbox: 0.0296, loss_cls: 0.1469, acc: 94.5679, loss_bbox: 0.1934, loss_mask: 0.2112, loss: 0.6001 2023-11-16 05:49:33,782 - mmdet - INFO - Epoch [26][150/1833] lr: 2.000e-04, eta: 6:35:33, time: 1.215, data_time: 0.071, memory: 16000, loss_rpn_cls: 0.0210, loss_rpn_bbox: 0.0305, loss_cls: 0.1472, acc: 94.5513, loss_bbox: 0.1947, loss_mask: 0.2127, loss: 0.6062 2023-11-16 05:50:34,613 - mmdet - INFO - Epoch [26][200/1833] lr: 2.000e-04, eta: 6:34:34, time: 1.217, data_time: 0.075, memory: 16000, loss_rpn_cls: 0.0200, loss_rpn_bbox: 0.0305, loss_cls: 0.1460, acc: 94.6133, loss_bbox: 0.1937, loss_mask: 0.2127, loss: 0.6029 2023-11-16 05:51:35,860 - mmdet - INFO - Epoch [26][250/1833] lr: 2.000e-04, eta: 6:33:36, time: 1.225, data_time: 0.074, memory: 16000, loss_rpn_cls: 0.0196, loss_rpn_bbox: 0.0311, loss_cls: 0.1508, acc: 94.4255, loss_bbox: 0.1979, loss_mask: 0.2097, loss: 0.6091 2023-11-16 05:52:37,346 - mmdet - INFO - Epoch [26][300/1833] lr: 2.000e-04, eta: 6:32:37, time: 1.230, data_time: 0.090, memory: 16000, loss_rpn_cls: 0.0201, loss_rpn_bbox: 0.0308, loss_cls: 0.1490, acc: 94.5454, loss_bbox: 0.1948, loss_mask: 0.2118, loss: 0.6065 2023-11-16 05:53:37,903 - mmdet - INFO - Epoch [26][350/1833] lr: 2.000e-04, eta: 6:31:39, time: 1.211, data_time: 0.085, memory: 16000, loss_rpn_cls: 0.0198, loss_rpn_bbox: 0.0299, loss_cls: 0.1429, acc: 94.7136, loss_bbox: 0.1900, loss_mask: 0.2088, loss: 0.5915 2023-11-16 05:54:38,969 - mmdet - INFO - Epoch [26][400/1833] lr: 2.000e-04, eta: 6:30:40, time: 1.221, data_time: 0.082, memory: 16000, loss_rpn_cls: 0.0199, loss_rpn_bbox: 0.0303, loss_cls: 0.1448, acc: 94.7015, loss_bbox: 0.1914, loss_mask: 0.2093, loss: 0.5957 2023-11-16 05:55:40,275 - mmdet - INFO - Epoch [26][450/1833] lr: 2.000e-04, eta: 6:29:42, time: 1.226, data_time: 0.078, memory: 16000, loss_rpn_cls: 0.0202, loss_rpn_bbox: 0.0309, loss_cls: 0.1494, acc: 94.4989, loss_bbox: 0.1955, loss_mask: 0.2112, loss: 0.6073 2023-11-16 05:56:40,351 - mmdet - INFO - Epoch [26][500/1833] lr: 2.000e-04, eta: 6:28:43, time: 1.202, data_time: 0.081, memory: 16000, loss_rpn_cls: 0.0189, loss_rpn_bbox: 0.0287, loss_cls: 0.1442, acc: 94.6381, loss_bbox: 0.1910, loss_mask: 0.2114, loss: 0.5943 2023-11-16 05:57:40,821 - mmdet - INFO - Epoch [26][550/1833] lr: 2.000e-04, eta: 6:27:44, time: 1.209, data_time: 0.085, memory: 16000, loss_rpn_cls: 0.0202, loss_rpn_bbox: 0.0310, loss_cls: 0.1496, acc: 94.4519, loss_bbox: 0.1943, loss_mask: 0.2116, loss: 0.6068 2023-11-16 05:58:39,598 - mmdet - INFO - Epoch [26][600/1833] lr: 2.000e-04, eta: 6:26:44, time: 1.175, data_time: 0.074, memory: 16000, loss_rpn_cls: 0.0201, loss_rpn_bbox: 0.0295, loss_cls: 0.1463, acc: 94.6331, loss_bbox: 0.1891, loss_mask: 0.2088, loss: 0.5938 2023-11-16 05:59:39,595 - mmdet - INFO - Epoch [26][650/1833] lr: 2.000e-04, eta: 6:25:45, time: 1.200, data_time: 0.076, memory: 16000, loss_rpn_cls: 0.0191, loss_rpn_bbox: 0.0292, loss_cls: 0.1423, acc: 94.7376, loss_bbox: 0.1886, loss_mask: 0.2096, loss: 0.5887 2023-11-16 06:00:39,549 - mmdet - INFO - Epoch [26][700/1833] lr: 2.000e-04, eta: 6:24:46, time: 1.199, data_time: 0.073, memory: 16000, loss_rpn_cls: 0.0206, loss_rpn_bbox: 0.0295, loss_cls: 0.1455, acc: 94.6486, loss_bbox: 0.1903, loss_mask: 0.2122, loss: 0.5981 2023-11-16 06:01:40,883 - mmdet - INFO - Epoch [26][750/1833] lr: 2.000e-04, eta: 6:23:48, time: 1.227, data_time: 0.081, memory: 16000, loss_rpn_cls: 0.0197, loss_rpn_bbox: 0.0297, loss_cls: 0.1512, acc: 94.4266, loss_bbox: 0.1959, loss_mask: 0.2115, loss: 0.6081 2023-11-16 06:02:40,496 - mmdet - INFO - Epoch [26][800/1833] lr: 2.000e-04, eta: 6:22:49, time: 1.192, data_time: 0.069, memory: 16000, loss_rpn_cls: 0.0211, loss_rpn_bbox: 0.0298, loss_cls: 0.1471, acc: 94.5353, loss_bbox: 0.1916, loss_mask: 0.2112, loss: 0.6008 2023-11-16 06:03:41,128 - mmdet - INFO - Epoch [26][850/1833] lr: 2.000e-04, eta: 6:21:50, time: 1.213, data_time: 0.077, memory: 16000, loss_rpn_cls: 0.0219, loss_rpn_bbox: 0.0310, loss_cls: 0.1523, acc: 94.3777, loss_bbox: 0.1957, loss_mask: 0.2136, loss: 0.6146 2023-11-16 06:04:40,932 - mmdet - INFO - Epoch [26][900/1833] lr: 2.000e-04, eta: 6:20:51, time: 1.196, data_time: 0.081, memory: 16000, loss_rpn_cls: 0.0201, loss_rpn_bbox: 0.0300, loss_cls: 0.1452, acc: 94.6231, loss_bbox: 0.1925, loss_mask: 0.2087, loss: 0.5965 2023-11-16 06:05:42,222 - mmdet - INFO - Epoch [26][950/1833] lr: 2.000e-04, eta: 6:19:52, time: 1.226, data_time: 0.078, memory: 16000, loss_rpn_cls: 0.0213, loss_rpn_bbox: 0.0313, loss_cls: 0.1540, acc: 94.2800, loss_bbox: 0.2012, loss_mask: 0.2134, loss: 0.6213 2023-11-16 06:06:41,855 - mmdet - INFO - Epoch [26][1000/1833] lr: 2.000e-04, eta: 6:18:53, time: 1.193, data_time: 0.069, memory: 16000, loss_rpn_cls: 0.0197, loss_rpn_bbox: 0.0301, loss_cls: 0.1470, acc: 94.5608, loss_bbox: 0.1934, loss_mask: 0.2084, loss: 0.5985 2023-11-16 06:07:40,994 - mmdet - INFO - Epoch [26][1050/1833] lr: 2.000e-04, eta: 6:17:54, time: 1.183, data_time: 0.081, memory: 16000, loss_rpn_cls: 0.0212, loss_rpn_bbox: 0.0305, loss_cls: 0.1492, acc: 94.4943, loss_bbox: 0.1958, loss_mask: 0.2109, loss: 0.6076 2023-11-16 06:08:41,197 - mmdet - INFO - Epoch [26][1100/1833] lr: 2.000e-04, eta: 6:16:55, time: 1.204, data_time: 0.072, memory: 16000, loss_rpn_cls: 0.0205, loss_rpn_bbox: 0.0309, loss_cls: 0.1512, acc: 94.3809, loss_bbox: 0.1975, loss_mask: 0.2128, loss: 0.6130 2023-11-16 06:09:40,299 - mmdet - INFO - Epoch [26][1150/1833] lr: 2.000e-04, eta: 6:15:55, time: 1.182, data_time: 0.076, memory: 16000, loss_rpn_cls: 0.0211, loss_rpn_bbox: 0.0305, loss_cls: 0.1488, acc: 94.5151, loss_bbox: 0.1933, loss_mask: 0.2126, loss: 0.6063 2023-11-16 06:10:41,389 - mmdet - INFO - Epoch [26][1200/1833] lr: 2.000e-04, eta: 6:14:57, time: 1.222, data_time: 0.076, memory: 16000, loss_rpn_cls: 0.0216, loss_rpn_bbox: 0.0313, loss_cls: 0.1507, acc: 94.4274, loss_bbox: 0.1956, loss_mask: 0.2114, loss: 0.6106 2023-11-16 06:11:40,666 - mmdet - INFO - Epoch [26][1250/1833] lr: 2.000e-04, eta: 6:13:57, time: 1.185, data_time: 0.078, memory: 16000, loss_rpn_cls: 0.0196, loss_rpn_bbox: 0.0305, loss_cls: 0.1464, acc: 94.5944, loss_bbox: 0.1910, loss_mask: 0.2107, loss: 0.5983 2023-11-16 06:12:40,549 - mmdet - INFO - Epoch [26][1300/1833] lr: 2.000e-04, eta: 6:12:58, time: 1.198, data_time: 0.081, memory: 16000, loss_rpn_cls: 0.0204, loss_rpn_bbox: 0.0301, loss_cls: 0.1496, acc: 94.4901, loss_bbox: 0.1946, loss_mask: 0.2127, loss: 0.6073 2023-11-16 06:13:40,384 - mmdet - INFO - Epoch [26][1350/1833] lr: 2.000e-04, eta: 6:11:59, time: 1.197, data_time: 0.080, memory: 16000, loss_rpn_cls: 0.0206, loss_rpn_bbox: 0.0305, loss_cls: 0.1518, acc: 94.4910, loss_bbox: 0.1950, loss_mask: 0.2103, loss: 0.6082 2023-11-16 06:14:39,830 - mmdet - INFO - Epoch [26][1400/1833] lr: 2.000e-04, eta: 6:11:00, time: 1.189, data_time: 0.074, memory: 16000, loss_rpn_cls: 0.0203, loss_rpn_bbox: 0.0293, loss_cls: 0.1463, acc: 94.6353, loss_bbox: 0.1904, loss_mask: 0.2088, loss: 0.5951 2023-11-16 06:15:40,333 - mmdet - INFO - Epoch [26][1450/1833] lr: 2.000e-04, eta: 6:10:01, time: 1.210, data_time: 0.075, memory: 16000, loss_rpn_cls: 0.0201, loss_rpn_bbox: 0.0306, loss_cls: 0.1481, acc: 94.4883, loss_bbox: 0.1972, loss_mask: 0.2125, loss: 0.6086 2023-11-16 06:16:41,237 - mmdet - INFO - Epoch [26][1500/1833] lr: 2.000e-04, eta: 6:09:02, time: 1.218, data_time: 0.081, memory: 16000, loss_rpn_cls: 0.0198, loss_rpn_bbox: 0.0299, loss_cls: 0.1477, acc: 94.5629, loss_bbox: 0.1925, loss_mask: 0.2109, loss: 0.6008 2023-11-16 06:17:41,046 - mmdet - INFO - Epoch [26][1550/1833] lr: 2.000e-04, eta: 6:08:03, time: 1.196, data_time: 0.078, memory: 16000, loss_rpn_cls: 0.0197, loss_rpn_bbox: 0.0299, loss_cls: 0.1452, acc: 94.6473, loss_bbox: 0.1906, loss_mask: 0.2129, loss: 0.5983 2023-11-16 06:18:42,361 - mmdet - INFO - Epoch [26][1600/1833] lr: 2.000e-04, eta: 6:07:05, time: 1.226, data_time: 0.080, memory: 16000, loss_rpn_cls: 0.0212, loss_rpn_bbox: 0.0311, loss_cls: 0.1546, acc: 94.3188, loss_bbox: 0.1985, loss_mask: 0.2150, loss: 0.6204 2023-11-16 06:19:42,412 - mmdet - INFO - Epoch [26][1650/1833] lr: 2.000e-04, eta: 6:06:06, time: 1.201, data_time: 0.076, memory: 16000, loss_rpn_cls: 0.0203, loss_rpn_bbox: 0.0305, loss_cls: 0.1486, acc: 94.4619, loss_bbox: 0.1954, loss_mask: 0.2139, loss: 0.6088 2023-11-16 06:20:41,976 - mmdet - INFO - Epoch [26][1700/1833] lr: 2.000e-04, eta: 6:05:06, time: 1.191, data_time: 0.075, memory: 16000, loss_rpn_cls: 0.0198, loss_rpn_bbox: 0.0293, loss_cls: 0.1485, acc: 94.5683, loss_bbox: 0.1901, loss_mask: 0.2131, loss: 0.6007 2023-11-16 06:21:42,487 - mmdet - INFO - Epoch [26][1750/1833] lr: 2.000e-04, eta: 6:04:07, time: 1.210, data_time: 0.078, memory: 16000, loss_rpn_cls: 0.0200, loss_rpn_bbox: 0.0302, loss_cls: 0.1497, acc: 94.5135, loss_bbox: 0.1919, loss_mask: 0.2098, loss: 0.6015 2023-11-16 06:22:43,005 - mmdet - INFO - Epoch [26][1800/1833] lr: 2.000e-04, eta: 6:03:09, time: 1.210, data_time: 0.078, memory: 16000, loss_rpn_cls: 0.0201, loss_rpn_bbox: 0.0301, loss_cls: 0.1507, acc: 94.4591, loss_bbox: 0.1945, loss_mask: 0.2117, loss: 0.6071 2023-11-16 06:23:23,516 - mmdet - INFO - Saving checkpoint at 26 epochs 2023-11-16 06:24:11,295 - mmdet - INFO - Evaluating bbox... 2023-11-16 06:24:40,603 - 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 ] = 0.704 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.533 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 ] = 0.525 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 ] = 0.613 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 ] = 0.460 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.654 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.750 2023-11-16 06:24:40,606 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.582 | bicycle | 0.389 | car | 0.490 | | motorcycle | 0.494 | airplane | 0.684 | bus | 0.709 | | train | 0.687 | truck | 0.439 | boat | 0.335 | | traffic light | 0.311 | fire hydrant | 0.745 | stop sign | 0.711 | | parking meter | 0.508 | bench | 0.316 | bird | 0.417 | | cat | 0.696 | dog | 0.692 | horse | 0.634 | | sheep | 0.603 | cow | 0.630 | elephant | 0.681 | | bear | 0.709 | zebra | 0.694 | giraffe | 0.704 | | backpack | 0.207 | umbrella | 0.485 | handbag | 0.248 | | tie | 0.408 | suitcase | 0.489 | frisbee | 0.708 | | skis | 0.309 | snowboard | 0.447 | sports ball | 0.463 | | kite | 0.464 | baseball bat | 0.446 | baseball glove | 0.458 | | skateboard | 0.597 | surfboard | 0.460 | tennis racket | 0.578 | | bottle | 0.459 | wine glass | 0.425 | cup | 0.497 | | fork | 0.496 | knife | 0.299 | spoon | 0.308 | | bowl | 0.476 | banana | 0.291 | apple | 0.268 | | sandwich | 0.446 | orange | 0.344 | broccoli | 0.245 | | carrot | 0.253 | hot dog | 0.453 | pizza | 0.567 | | donut | 0.534 | cake | 0.444 | chair | 0.366 | | couch | 0.493 | potted plant | 0.348 | bed | 0.471 | | dining table | 0.316 | toilet | 0.666 | tv | 0.635 | | laptop | 0.658 | mouse | 0.644 | remote | 0.450 | | keyboard | 0.570 | cell phone | 0.434 | microwave | 0.647 | | oven | 0.431 | toaster | 0.467 | sink | 0.441 | | refrigerator | 0.601 | book | 0.199 | clock | 0.494 | | vase | 0.445 | scissors | 0.437 | teddy bear | 0.538 | | hair drier | 0.224 | toothbrush | 0.325 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-16 06:24:40,606 - mmdet - INFO - Evaluating segm... 2023-11-16 06:25:14,691 - 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 ] = 0.467 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.251 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 ] = 0.615 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 ] = 0.388 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.597 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.704 2023-11-16 06:25:14,693 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.507 | bicycle | 0.244 | car | 0.448 | | motorcycle | 0.399 | airplane | 0.534 | bus | 0.697 | | train | 0.666 | truck | 0.430 | boat | 0.306 | | traffic light | 0.299 | fire hydrant | 0.709 | stop sign | 0.690 | | parking meter | 0.515 | bench | 0.244 | bird | 0.345 | | cat | 0.697 | dog | 0.657 | horse | 0.472 | | sheep | 0.536 | cow | 0.524 | elephant | 0.617 | | bear | 0.700 | zebra | 0.597 | giraffe | 0.552 | | backpack | 0.222 | umbrella | 0.531 | handbag | 0.233 | | tie | 0.374 | suitcase | 0.493 | frisbee | 0.674 | | skis | 0.060 | snowboard | 0.273 | sports ball | 0.449 | | kite | 0.323 | baseball bat | 0.323 | baseball glove | 0.456 | | skateboard | 0.379 | surfboard | 0.383 | tennis racket | 0.605 | | bottle | 0.433 | wine glass | 0.387 | cup | 0.490 | | fork | 0.249 | knife | 0.214 | spoon | 0.210 | | bowl | 0.448 | banana | 0.243 | apple | 0.251 | | sandwich | 0.454 | orange | 0.346 | broccoli | 0.227 | | carrot | 0.225 | hot dog | 0.385 | pizza | 0.537 | | donut | 0.529 | cake | 0.451 | chair | 0.262 | | couch | 0.409 | potted plant | 0.291 | bed | 0.386 | | dining table | 0.185 | toilet | 0.650 | tv | 0.664 | | laptop | 0.657 | mouse | 0.634 | remote | 0.396 | | keyboard | 0.553 | cell phone | 0.408 | microwave | 0.661 | | oven | 0.380 | toaster | 0.532 | sink | 0.420 | | refrigerator | 0.608 | book | 0.149 | clock | 0.504 | | vase | 0.434 | scissors | 0.314 | teddy bear | 0.517 | | hair drier | 0.171 | toothbrush | 0.242 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-16 06:25:15,160 - mmdet - INFO - Exp name: mask_rcnn_flash_internimage_s_fpn_3x_coco_0.4.py 2023-11-16 06:25:15,161 - mmdet - INFO - Epoch(val) [26][625] bbox_mAP: 0.4841, bbox_mAP_50: 0.7044, bbox_mAP_75: 0.5334, bbox_mAP_s: 0.3377, bbox_mAP_m: 0.5246, bbox_mAP_l: 0.6194, bbox_mAP_copypaste: 0.4841 0.7044 0.5334 0.3377 0.5246 0.6194, segm_mAP: 0.4333, segm_mAP_50: 0.6754, segm_mAP_75: 0.4670, segm_mAP_s: 0.2513, segm_mAP_m: 0.4657, segm_mAP_l: 0.6155, segm_mAP_copypaste: 0.4333 0.6754 0.4670 0.2513 0.4657 0.6155 2023-11-16 06:26:19,823 - mmdet - INFO - Epoch [27][50/1833] lr: 2.000e-04, eta: 6:01:17, time: 1.293, data_time: 0.136, memory: 16000, loss_rpn_cls: 0.0186, loss_rpn_bbox: 0.0300, loss_cls: 0.1449, acc: 94.6183, loss_bbox: 0.1924, loss_mask: 0.2103, loss: 0.5962 2023-11-16 06:27:20,059 - mmdet - INFO - Epoch [27][100/1833] lr: 2.000e-04, eta: 6:00:18, time: 1.205, data_time: 0.089, memory: 16000, loss_rpn_cls: 0.0189, loss_rpn_bbox: 0.0298, loss_cls: 0.1407, acc: 94.7391, loss_bbox: 0.1881, loss_mask: 0.2087, loss: 0.5862 2023-11-16 06:28:20,119 - mmdet - INFO - Epoch [27][150/1833] lr: 2.000e-04, eta: 5:59:19, time: 1.201, data_time: 0.069, memory: 16000, loss_rpn_cls: 0.0182, loss_rpn_bbox: 0.0294, loss_cls: 0.1450, acc: 94.6210, loss_bbox: 0.1934, loss_mask: 0.2110, loss: 0.5969 2023-11-16 06:29:20,481 - mmdet - INFO - Epoch [27][200/1833] lr: 2.000e-04, eta: 5:58:20, time: 1.207, data_time: 0.073, memory: 16000, loss_rpn_cls: 0.0198, loss_rpn_bbox: 0.0300, loss_cls: 0.1422, acc: 94.6953, loss_bbox: 0.1923, loss_mask: 0.2097, loss: 0.5939 2023-11-16 06:30:20,911 - mmdet - INFO - Epoch [27][250/1833] lr: 2.000e-04, eta: 5:57:21, time: 1.209, data_time: 0.076, memory: 16000, loss_rpn_cls: 0.0208, loss_rpn_bbox: 0.0312, loss_cls: 0.1441, acc: 94.6363, loss_bbox: 0.1919, loss_mask: 0.2097, loss: 0.5976 2023-11-16 06:31:20,841 - mmdet - INFO - Epoch [27][300/1833] lr: 2.000e-04, eta: 5:56:22, time: 1.199, data_time: 0.081, memory: 16000, loss_rpn_cls: 0.0205, loss_rpn_bbox: 0.0310, loss_cls: 0.1520, acc: 94.3492, loss_bbox: 0.1999, loss_mask: 0.2121, loss: 0.6155 2023-11-16 06:32:20,269 - mmdet - INFO - Epoch [27][350/1833] lr: 2.000e-04, eta: 5:55:23, time: 1.189, data_time: 0.076, memory: 16000, loss_rpn_cls: 0.0188, loss_rpn_bbox: 0.0289, loss_cls: 0.1397, acc: 94.7780, loss_bbox: 0.1875, loss_mask: 0.2122, loss: 0.5871 2023-11-16 06:33:21,726 - mmdet - INFO - Epoch [27][400/1833] lr: 2.000e-04, eta: 5:54:25, time: 1.229, data_time: 0.080, memory: 16000, loss_rpn_cls: 0.0201, loss_rpn_bbox: 0.0307, loss_cls: 0.1447, acc: 94.6396, loss_bbox: 0.1924, loss_mask: 0.2113, loss: 0.5992 2023-11-16 06:34:21,416 - mmdet - INFO - Epoch [27][450/1833] lr: 2.000e-04, eta: 5:53:25, time: 1.194, data_time: 0.076, memory: 16000, loss_rpn_cls: 0.0192, loss_rpn_bbox: 0.0296, loss_cls: 0.1443, acc: 94.6384, loss_bbox: 0.1903, loss_mask: 0.2093, loss: 0.5926 2023-11-16 06:35:22,274 - mmdet - INFO - Epoch [27][500/1833] lr: 2.000e-04, eta: 5:52:27, time: 1.217, data_time: 0.074, memory: 16000, loss_rpn_cls: 0.0203, loss_rpn_bbox: 0.0312, loss_cls: 0.1515, acc: 94.4086, loss_bbox: 0.1974, loss_mask: 0.2121, loss: 0.6124 2023-11-16 06:36:22,551 - mmdet - INFO - Epoch [27][550/1833] lr: 2.000e-04, eta: 5:51:28, time: 1.205, data_time: 0.077, memory: 16000, loss_rpn_cls: 0.0185, loss_rpn_bbox: 0.0280, loss_cls: 0.1406, acc: 94.7758, loss_bbox: 0.1873, loss_mask: 0.2076, loss: 0.5820 2023-11-16 06:37:21,611 - mmdet - INFO - Epoch [27][600/1833] lr: 2.000e-04, eta: 5:50:28, time: 1.181, data_time: 0.068, memory: 16000, loss_rpn_cls: 0.0192, loss_rpn_bbox: 0.0291, loss_cls: 0.1472, acc: 94.5694, loss_bbox: 0.1915, loss_mask: 0.2084, loss: 0.5954 2023-11-16 06:38:22,387 - mmdet - INFO - Epoch [27][650/1833] lr: 2.000e-04, eta: 5:49:30, time: 1.216, data_time: 0.067, memory: 16000, loss_rpn_cls: 0.0214, loss_rpn_bbox: 0.0303, loss_cls: 0.1469, acc: 94.5648, loss_bbox: 0.1933, loss_mask: 0.2108, loss: 0.6028 2023-11-16 06:39:22,684 - mmdet - INFO - Epoch [27][700/1833] lr: 2.000e-04, eta: 5:48:31, time: 1.206, data_time: 0.076, memory: 16000, loss_rpn_cls: 0.0205, loss_rpn_bbox: 0.0302, loss_cls: 0.1495, acc: 94.4092, loss_bbox: 0.1967, loss_mask: 0.2119, loss: 0.6088 2023-11-16 06:40:24,208 - mmdet - INFO - Epoch [27][750/1833] lr: 2.000e-04, eta: 5:47:32, time: 1.231, data_time: 0.082, memory: 16000, loss_rpn_cls: 0.0195, loss_rpn_bbox: 0.0301, loss_cls: 0.1458, acc: 94.5785, loss_bbox: 0.1914, loss_mask: 0.2139, loss: 0.6007 2023-11-16 06:41:24,444 - mmdet - INFO - Epoch [27][800/1833] lr: 2.000e-04, eta: 5:46:33, time: 1.205, data_time: 0.071, memory: 16000, loss_rpn_cls: 0.0188, loss_rpn_bbox: 0.0298, loss_cls: 0.1446, acc: 94.6535, loss_bbox: 0.1902, loss_mask: 0.2111, loss: 0.5945 2023-11-16 06:42:24,020 - mmdet - INFO - Epoch [27][850/1833] lr: 2.000e-04, eta: 5:45:34, time: 1.191, data_time: 0.070, memory: 16000, loss_rpn_cls: 0.0205, loss_rpn_bbox: 0.0308, loss_cls: 0.1499, acc: 94.4750, loss_bbox: 0.1950, loss_mask: 0.2144, loss: 0.6105 2023-11-16 06:43:23,218 - mmdet - INFO - Epoch [27][900/1833] lr: 2.000e-04, eta: 5:44:35, time: 1.184, data_time: 0.077, memory: 16000, loss_rpn_cls: 0.0190, loss_rpn_bbox: 0.0299, loss_cls: 0.1457, acc: 94.6166, loss_bbox: 0.1920, loss_mask: 0.2105, loss: 0.5972 2023-11-16 06:44:23,890 - mmdet - INFO - Epoch [27][950/1833] lr: 2.000e-04, eta: 5:43:36, time: 1.213, data_time: 0.069, memory: 16000, loss_rpn_cls: 0.0196, loss_rpn_bbox: 0.0297, loss_cls: 0.1452, acc: 94.6185, loss_bbox: 0.1906, loss_mask: 0.2105, loss: 0.5957 2023-11-16 06:45:24,871 - mmdet - INFO - Epoch [27][1000/1833] lr: 2.000e-04, eta: 5:42:37, time: 1.220, data_time: 0.079, memory: 16000, loss_rpn_cls: 0.0205, loss_rpn_bbox: 0.0309, loss_cls: 0.1473, acc: 94.5392, loss_bbox: 0.1964, loss_mask: 0.2131, loss: 0.6082 2023-11-16 06:46:25,181 - mmdet - INFO - Epoch [27][1050/1833] lr: 2.000e-04, eta: 5:41:38, time: 1.206, data_time: 0.076, memory: 16000, loss_rpn_cls: 0.0192, loss_rpn_bbox: 0.0295, loss_cls: 0.1435, acc: 94.6890, loss_bbox: 0.1890, loss_mask: 0.2118, loss: 0.5930 2023-11-16 06:47:24,539 - mmdet - INFO - Epoch [27][1100/1833] lr: 2.000e-04, eta: 5:40:39, time: 1.187, data_time: 0.073, memory: 16000, loss_rpn_cls: 0.0198, loss_rpn_bbox: 0.0300, loss_cls: 0.1474, acc: 94.6195, loss_bbox: 0.1924, loss_mask: 0.2143, loss: 0.6039 2023-11-16 06:48:24,855 - mmdet - INFO - Epoch [27][1150/1833] lr: 2.000e-04, eta: 5:39:40, time: 1.206, data_time: 0.076, memory: 16000, loss_rpn_cls: 0.0209, loss_rpn_bbox: 0.0307, loss_cls: 0.1490, acc: 94.5115, loss_bbox: 0.1929, loss_mask: 0.2121, loss: 0.6056 2023-11-16 06:49:24,348 - mmdet - INFO - Epoch [27][1200/1833] lr: 2.000e-04, eta: 5:38:41, time: 1.190, data_time: 0.080, memory: 16000, loss_rpn_cls: 0.0199, loss_rpn_bbox: 0.0303, loss_cls: 0.1491, acc: 94.4800, loss_bbox: 0.1942, loss_mask: 0.2120, loss: 0.6055 2023-11-16 06:50:25,525 - mmdet - INFO - Epoch [27][1250/1833] lr: 2.000e-04, eta: 5:37:42, time: 1.223, data_time: 0.072, memory: 16000, loss_rpn_cls: 0.0205, loss_rpn_bbox: 0.0301, loss_cls: 0.1500, acc: 94.4990, loss_bbox: 0.1950, loss_mask: 0.2111, loss: 0.6067 2023-11-16 06:51:25,710 - mmdet - INFO - Epoch [27][1300/1833] lr: 2.000e-04, eta: 5:36:43, time: 1.204, data_time: 0.070, memory: 16000, loss_rpn_cls: 0.0193, loss_rpn_bbox: 0.0296, loss_cls: 0.1454, acc: 94.5883, loss_bbox: 0.1925, loss_mask: 0.2108, loss: 0.5976 2023-11-16 06:52:26,247 - mmdet - INFO - Epoch [27][1350/1833] lr: 2.000e-04, eta: 5:35:44, time: 1.211, data_time: 0.078, memory: 16000, loss_rpn_cls: 0.0188, loss_rpn_bbox: 0.0298, loss_cls: 0.1445, acc: 94.6470, loss_bbox: 0.1899, loss_mask: 0.2113, loss: 0.5942 2023-11-16 06:53:26,047 - mmdet - INFO - Epoch [27][1400/1833] lr: 2.000e-04, eta: 5:34:45, time: 1.196, data_time: 0.075, memory: 16000, loss_rpn_cls: 0.0212, loss_rpn_bbox: 0.0306, loss_cls: 0.1475, acc: 94.6031, loss_bbox: 0.1912, loss_mask: 0.2081, loss: 0.5987 2023-11-16 06:54:25,515 - mmdet - INFO - Epoch [27][1450/1833] lr: 2.000e-04, eta: 5:33:46, time: 1.189, data_time: 0.079, memory: 16000, loss_rpn_cls: 0.0198, loss_rpn_bbox: 0.0294, loss_cls: 0.1474, acc: 94.5516, loss_bbox: 0.1923, loss_mask: 0.2094, loss: 0.5984 2023-11-16 06:55:25,326 - mmdet - INFO - Epoch [27][1500/1833] lr: 2.000e-04, eta: 5:32:47, time: 1.196, data_time: 0.076, memory: 16000, loss_rpn_cls: 0.0209, loss_rpn_bbox: 0.0305, loss_cls: 0.1452, acc: 94.6772, loss_bbox: 0.1913, loss_mask: 0.2116, loss: 0.5996 2023-11-16 06:56:25,780 - mmdet - INFO - Epoch [27][1550/1833] lr: 2.000e-04, eta: 5:31:48, time: 1.209, data_time: 0.078, memory: 16000, loss_rpn_cls: 0.0209, loss_rpn_bbox: 0.0307, loss_cls: 0.1486, acc: 94.5142, loss_bbox: 0.1942, loss_mask: 0.2119, loss: 0.6064 2023-11-16 06:57:26,247 - mmdet - INFO - Epoch [27][1600/1833] lr: 2.000e-04, eta: 5:30:49, time: 1.209, data_time: 0.077, memory: 16000, loss_rpn_cls: 0.0208, loss_rpn_bbox: 0.0308, loss_cls: 0.1513, acc: 94.4651, loss_bbox: 0.1961, loss_mask: 0.2121, loss: 0.6110 2023-11-16 06:58:26,006 - mmdet - INFO - Epoch [27][1650/1833] lr: 2.000e-04, eta: 5:29:49, time: 1.195, data_time: 0.078, memory: 16000, loss_rpn_cls: 0.0202, loss_rpn_bbox: 0.0299, loss_cls: 0.1494, acc: 94.5385, loss_bbox: 0.1914, loss_mask: 0.2142, loss: 0.6052 2023-11-16 06:59:25,962 - mmdet - INFO - Epoch [27][1700/1833] lr: 2.000e-04, eta: 5:28:50, time: 1.199, data_time: 0.070, memory: 16000, loss_rpn_cls: 0.0195, loss_rpn_bbox: 0.0294, loss_cls: 0.1471, acc: 94.5614, loss_bbox: 0.1919, loss_mask: 0.2137, loss: 0.6017 2023-11-16 07:00:26,762 - mmdet - INFO - Epoch [27][1750/1833] lr: 2.000e-04, eta: 5:27:52, time: 1.216, data_time: 0.070, memory: 16000, loss_rpn_cls: 0.0200, loss_rpn_bbox: 0.0289, loss_cls: 0.1498, acc: 94.5045, loss_bbox: 0.1925, loss_mask: 0.2127, loss: 0.6039 2023-11-16 07:01:27,162 - mmdet - INFO - Epoch [27][1800/1833] lr: 2.000e-04, eta: 5:26:53, time: 1.208, data_time: 0.071, memory: 16000, loss_rpn_cls: 0.0198, loss_rpn_bbox: 0.0301, loss_cls: 0.1449, acc: 94.6663, loss_bbox: 0.1911, loss_mask: 0.2108, loss: 0.5967 2023-11-16 07:02:07,032 - mmdet - INFO - Saving checkpoint at 27 epochs 2023-11-16 07:02:54,171 - mmdet - INFO - Evaluating bbox... 2023-11-16 07:03:22,338 - 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 ] = 0.703 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.534 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.320 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 ] = 0.619 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.611 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.611 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.611 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.436 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.650 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.755 2023-11-16 07:03:22,341 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.588 | bicycle | 0.394 | car | 0.508 | | motorcycle | 0.474 | airplane | 0.715 | bus | 0.710 | | train | 0.687 | truck | 0.425 | boat | 0.330 | | traffic light | 0.308 | fire hydrant | 0.726 | stop sign | 0.687 | | parking meter | 0.532 | bench | 0.318 | bird | 0.425 | | cat | 0.729 | dog | 0.675 | horse | 0.633 | | sheep | 0.594 | cow | 0.610 | elephant | 0.685 | | bear | 0.734 | zebra | 0.683 | giraffe | 0.692 | | backpack | 0.221 | umbrella | 0.455 | handbag | 0.236 | | tie | 0.409 | suitcase | 0.489 | frisbee | 0.729 | | skis | 0.302 | snowboard | 0.435 | sports ball | 0.477 | | kite | 0.476 | baseball bat | 0.407 | baseball glove | 0.443 | | skateboard | 0.599 | surfboard | 0.461 | tennis racket | 0.564 | | bottle | 0.459 | wine glass | 0.429 | cup | 0.497 | | fork | 0.481 | knife | 0.291 | spoon | 0.309 | | bowl | 0.481 | banana | 0.262 | apple | 0.256 | | sandwich | 0.450 | orange | 0.335 | broccoli | 0.263 | | carrot | 0.269 | hot dog | 0.452 | pizza | 0.559 | | donut | 0.554 | cake | 0.430 | chair | 0.360 | | couch | 0.496 | potted plant | 0.367 | bed | 0.439 | | dining table | 0.318 | toilet | 0.657 | tv | 0.630 | | laptop | 0.678 | mouse | 0.647 | remote | 0.447 | | keyboard | 0.535 | cell phone | 0.425 | microwave | 0.666 | | oven | 0.414 | toaster | 0.458 | sink | 0.456 | | refrigerator | 0.654 | book | 0.196 | clock | 0.513 | | vase | 0.442 | scissors | 0.417 | teddy bear | 0.529 | | hair drier | 0.262 | toothbrush | 0.344 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-16 07:03:22,341 - mmdet - INFO - Evaluating segm... 2023-11-16 07:03:55,348 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.431 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.675 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.462 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.235 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.467 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 ] = 0.552 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 ] = 0.373 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.592 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.707 2023-11-16 07:03:55,350 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.510 | bicycle | 0.249 | car | 0.463 | | motorcycle | 0.394 | airplane | 0.530 | bus | 0.702 | | train | 0.675 | truck | 0.403 | boat | 0.293 | | traffic light | 0.294 | fire hydrant | 0.692 | stop sign | 0.662 | | parking meter | 0.551 | bench | 0.247 | bird | 0.349 | | cat | 0.726 | dog | 0.659 | horse | 0.469 | | sheep | 0.519 | cow | 0.519 | elephant | 0.618 | | bear | 0.724 | zebra | 0.594 | giraffe | 0.545 | | backpack | 0.220 | umbrella | 0.515 | handbag | 0.219 | | tie | 0.360 | suitcase | 0.506 | frisbee | 0.680 | | skis | 0.059 | snowboard | 0.279 | sports ball | 0.456 | | kite | 0.323 | baseball bat | 0.297 | baseball glove | 0.445 | | skateboard | 0.385 | surfboard | 0.374 | tennis racket | 0.602 | | bottle | 0.433 | wine glass | 0.385 | cup | 0.491 | | fork | 0.234 | knife | 0.193 | spoon | 0.214 | | bowl | 0.445 | banana | 0.213 | apple | 0.252 | | sandwich | 0.478 | orange | 0.346 | broccoli | 0.245 | | carrot | 0.233 | hot dog | 0.387 | pizza | 0.545 | | donut | 0.548 | cake | 0.437 | chair | 0.258 | | couch | 0.427 | potted plant | 0.297 | bed | 0.345 | | dining table | 0.184 | toilet | 0.634 | tv | 0.663 | | laptop | 0.670 | mouse | 0.631 | remote | 0.388 | | keyboard | 0.521 | cell phone | 0.395 | microwave | 0.655 | | oven | 0.372 | toaster | 0.491 | sink | 0.436 | | refrigerator | 0.653 | book | 0.148 | clock | 0.509 | | vase | 0.436 | scissors | 0.314 | teddy bear | 0.513 | | hair drier | 0.114 | toothbrush | 0.259 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-16 07:03:55,789 - mmdet - INFO - Exp name: mask_rcnn_flash_internimage_s_fpn_3x_coco_0.4.py 2023-11-16 07:03:55,789 - mmdet - INFO - Epoch(val) [27][625] bbox_mAP: 0.4836, bbox_mAP_50: 0.7029, bbox_mAP_75: 0.5338, bbox_mAP_s: 0.3203, bbox_mAP_m: 0.5253, bbox_mAP_l: 0.6193, bbox_mAP_copypaste: 0.4836 0.7029 0.5338 0.3203 0.5253 0.6193, segm_mAP: 0.4312, segm_mAP_50: 0.6755, segm_mAP_75: 0.4622, segm_mAP_s: 0.2345, segm_mAP_m: 0.4674, segm_mAP_l: 0.6177, segm_mAP_copypaste: 0.4312 0.6755 0.4622 0.2345 0.4674 0.6177 2023-11-16 07:04:59,372 - mmdet - INFO - Epoch [28][50/1833] lr: 2.000e-05, eta: 5:25:03, time: 1.271, data_time: 0.121, memory: 16000, loss_rpn_cls: 0.0201, loss_rpn_bbox: 0.0297, loss_cls: 0.1430, acc: 94.7192, loss_bbox: 0.1912, loss_mask: 0.2111, loss: 0.5950 2023-11-16 07:05:59,738 - mmdet - INFO - Epoch [28][100/1833] lr: 2.000e-05, eta: 5:24:04, time: 1.207, data_time: 0.065, memory: 16000, loss_rpn_cls: 0.0177, loss_rpn_bbox: 0.0285, loss_cls: 0.1353, acc: 94.9767, loss_bbox: 0.1803, loss_mask: 0.2052, loss: 0.5670 2023-11-16 07:06:59,945 - mmdet - INFO - Epoch [28][150/1833] lr: 2.000e-05, eta: 5:23:05, time: 1.204, data_time: 0.068, memory: 16000, loss_rpn_cls: 0.0173, loss_rpn_bbox: 0.0283, loss_cls: 0.1365, acc: 94.9232, loss_bbox: 0.1843, loss_mask: 0.2048, loss: 0.5713 2023-11-16 07:07:59,921 - mmdet - INFO - Epoch [28][200/1833] lr: 2.000e-05, eta: 5:22:06, time: 1.199, data_time: 0.066, memory: 16000, loss_rpn_cls: 0.0184, loss_rpn_bbox: 0.0289, loss_cls: 0.1391, acc: 94.8325, loss_bbox: 0.1863, loss_mask: 0.2052, loss: 0.5779 2023-11-16 07:09:01,262 - mmdet - INFO - Epoch [28][250/1833] lr: 2.000e-05, eta: 5:21:07, time: 1.227, data_time: 0.076, memory: 16000, loss_rpn_cls: 0.0189, loss_rpn_bbox: 0.0290, loss_cls: 0.1387, acc: 94.8435, loss_bbox: 0.1867, loss_mask: 0.2054, loss: 0.5787 2023-11-16 07:10:01,861 - mmdet - INFO - Epoch [28][300/1833] lr: 2.000e-05, eta: 5:20:08, time: 1.212, data_time: 0.065, memory: 16000, loss_rpn_cls: 0.0183, loss_rpn_bbox: 0.0295, loss_cls: 0.1408, acc: 94.7224, loss_bbox: 0.1912, loss_mask: 0.2057, loss: 0.5855 2023-11-16 07:11:02,407 - mmdet - INFO - Epoch [28][350/1833] lr: 2.000e-05, eta: 5:19:09, time: 1.211, data_time: 0.064, memory: 16000, loss_rpn_cls: 0.0190, loss_rpn_bbox: 0.0298, loss_cls: 0.1400, acc: 94.7286, loss_bbox: 0.1881, loss_mask: 0.2074, loss: 0.5843 2023-11-16 07:12:03,787 - mmdet - INFO - Epoch [28][400/1833] lr: 2.000e-05, eta: 5:18:10, time: 1.227, data_time: 0.073, memory: 16000, loss_rpn_cls: 0.0181, loss_rpn_bbox: 0.0296, loss_cls: 0.1391, acc: 94.8098, loss_bbox: 0.1881, loss_mask: 0.2079, loss: 0.5827 2023-11-16 07:13:04,428 - mmdet - INFO - Epoch [28][450/1833] lr: 2.000e-05, eta: 5:17:12, time: 1.213, data_time: 0.071, memory: 16000, loss_rpn_cls: 0.0185, loss_rpn_bbox: 0.0290, loss_cls: 0.1388, acc: 94.8314, loss_bbox: 0.1876, loss_mask: 0.2040, loss: 0.5779 2023-11-16 07:14:03,884 - mmdet - INFO - Epoch [28][500/1833] lr: 2.000e-05, eta: 5:16:12, time: 1.189, data_time: 0.070, memory: 16000, loss_rpn_cls: 0.0174, loss_rpn_bbox: 0.0275, loss_cls: 0.1349, acc: 94.9653, loss_bbox: 0.1833, loss_mask: 0.2045, loss: 0.5677 2023-11-16 07:15:04,735 - mmdet - INFO - Epoch [28][550/1833] lr: 2.000e-05, eta: 5:15:14, time: 1.217, data_time: 0.071, memory: 16000, loss_rpn_cls: 0.0193, loss_rpn_bbox: 0.0302, loss_cls: 0.1396, acc: 94.7774, loss_bbox: 0.1895, loss_mask: 0.2080, loss: 0.5866 2023-11-16 07:16:05,012 - mmdet - INFO - Epoch [28][600/1833] lr: 2.000e-05, eta: 5:14:15, time: 1.206, data_time: 0.074, memory: 16000, loss_rpn_cls: 0.0196, loss_rpn_bbox: 0.0299, loss_cls: 0.1414, acc: 94.7228, loss_bbox: 0.1880, loss_mask: 0.2075, loss: 0.5865 2023-11-16 07:17:05,110 - mmdet - INFO - Epoch [28][650/1833] lr: 2.000e-05, eta: 5:13:16, time: 1.202, data_time: 0.075, memory: 16000, loss_rpn_cls: 0.0177, loss_rpn_bbox: 0.0281, loss_cls: 0.1371, acc: 94.8730, loss_bbox: 0.1832, loss_mask: 0.2029, loss: 0.5690 2023-11-16 07:18:05,327 - mmdet - INFO - Epoch [28][700/1833] lr: 2.000e-05, eta: 5:12:17, time: 1.204, data_time: 0.065, memory: 16000, loss_rpn_cls: 0.0179, loss_rpn_bbox: 0.0283, loss_cls: 0.1338, acc: 94.9769, loss_bbox: 0.1817, loss_mask: 0.2024, loss: 0.5640 2023-11-16 07:19:06,714 - mmdet - INFO - Epoch [28][750/1833] lr: 2.000e-05, eta: 5:11:18, time: 1.228, data_time: 0.061, memory: 16000, loss_rpn_cls: 0.0175, loss_rpn_bbox: 0.0279, loss_cls: 0.1361, acc: 94.8727, loss_bbox: 0.1822, loss_mask: 0.2050, loss: 0.5688 2023-11-16 07:20:07,132 - mmdet - INFO - Epoch [28][800/1833] lr: 2.000e-05, eta: 5:10:19, time: 1.208, data_time: 0.070, memory: 16000, loss_rpn_cls: 0.0186, loss_rpn_bbox: 0.0294, loss_cls: 0.1381, acc: 94.8315, loss_bbox: 0.1852, loss_mask: 0.2071, loss: 0.5783 2023-11-16 07:21:07,422 - mmdet - INFO - Epoch [28][850/1833] lr: 2.000e-05, eta: 5:09:20, time: 1.206, data_time: 0.067, memory: 16000, loss_rpn_cls: 0.0176, loss_rpn_bbox: 0.0287, loss_cls: 0.1335, acc: 94.9800, loss_bbox: 0.1839, loss_mask: 0.2038, loss: 0.5675 2023-11-16 07:22:07,885 - mmdet - INFO - Epoch [28][900/1833] lr: 2.000e-05, eta: 5:08:21, time: 1.209, data_time: 0.071, memory: 16000, loss_rpn_cls: 0.0174, loss_rpn_bbox: 0.0279, loss_cls: 0.1337, acc: 95.0145, loss_bbox: 0.1797, loss_mask: 0.2018, loss: 0.5604 2023-11-16 07:23:09,092 - mmdet - INFO - Epoch [28][950/1833] lr: 2.000e-05, eta: 5:07:22, time: 1.224, data_time: 0.068, memory: 16000, loss_rpn_cls: 0.0176, loss_rpn_bbox: 0.0286, loss_cls: 0.1339, acc: 95.0052, loss_bbox: 0.1820, loss_mask: 0.2031, loss: 0.5651 2023-11-16 07:24:09,100 - mmdet - INFO - Epoch [28][1000/1833] lr: 2.000e-05, eta: 5:06:23, time: 1.200, data_time: 0.063, memory: 16000, loss_rpn_cls: 0.0181, loss_rpn_bbox: 0.0284, loss_cls: 0.1355, acc: 94.9002, loss_bbox: 0.1847, loss_mask: 0.2020, loss: 0.5686 2023-11-16 07:25:09,388 - mmdet - INFO - Epoch [28][1050/1833] lr: 2.000e-05, eta: 5:05:24, time: 1.206, data_time: 0.076, memory: 16000, loss_rpn_cls: 0.0179, loss_rpn_bbox: 0.0287, loss_cls: 0.1362, acc: 94.8915, loss_bbox: 0.1846, loss_mask: 0.2036, loss: 0.5709 2023-11-16 07:26:08,752 - mmdet - INFO - Epoch [28][1100/1833] lr: 2.000e-05, eta: 5:04:25, time: 1.187, data_time: 0.072, memory: 16000, loss_rpn_cls: 0.0173, loss_rpn_bbox: 0.0281, loss_cls: 0.1343, acc: 94.9812, loss_bbox: 0.1819, loss_mask: 0.2027, loss: 0.5643 2023-11-16 07:27:09,786 - mmdet - INFO - Epoch [28][1150/1833] lr: 2.000e-05, eta: 5:03:26, time: 1.221, data_time: 0.076, memory: 16000, loss_rpn_cls: 0.0185, loss_rpn_bbox: 0.0298, loss_cls: 0.1383, acc: 94.8405, loss_bbox: 0.1869, loss_mask: 0.2057, loss: 0.5792 2023-11-16 07:28:10,438 - mmdet - INFO - Epoch [28][1200/1833] lr: 2.000e-05, eta: 5:02:27, time: 1.213, data_time: 0.071, memory: 16000, loss_rpn_cls: 0.0175, loss_rpn_bbox: 0.0275, loss_cls: 0.1318, acc: 95.0044, loss_bbox: 0.1800, loss_mask: 0.2031, loss: 0.5599 2023-11-16 07:29:10,851 - mmdet - INFO - Epoch [28][1250/1833] lr: 2.000e-05, eta: 5:01:28, time: 1.208, data_time: 0.075, memory: 16000, loss_rpn_cls: 0.0173, loss_rpn_bbox: 0.0281, loss_cls: 0.1351, acc: 94.9325, loss_bbox: 0.1837, loss_mask: 0.2027, loss: 0.5670 2023-11-16 07:30:10,749 - mmdet - INFO - Epoch [28][1300/1833] lr: 2.000e-05, eta: 5:00:29, time: 1.198, data_time: 0.067, memory: 16000, loss_rpn_cls: 0.0168, loss_rpn_bbox: 0.0278, loss_cls: 0.1346, acc: 94.9321, loss_bbox: 0.1811, loss_mask: 0.2025, loss: 0.5628 2023-11-16 07:31:12,431 - mmdet - INFO - Epoch [28][1350/1833] lr: 2.000e-05, eta: 4:59:30, time: 1.234, data_time: 0.072, memory: 16000, loss_rpn_cls: 0.0191, loss_rpn_bbox: 0.0294, loss_cls: 0.1378, acc: 94.8172, loss_bbox: 0.1858, loss_mask: 0.2053, loss: 0.5774 2023-11-16 07:32:13,507 - mmdet - INFO - Epoch [28][1400/1833] lr: 2.000e-05, eta: 4:58:32, time: 1.222, data_time: 0.072, memory: 16000, loss_rpn_cls: 0.0186, loss_rpn_bbox: 0.0287, loss_cls: 0.1365, acc: 94.8633, loss_bbox: 0.1862, loss_mask: 0.2052, loss: 0.5752 2023-11-16 07:33:13,839 - mmdet - INFO - Epoch [28][1450/1833] lr: 2.000e-05, eta: 4:57:33, time: 1.207, data_time: 0.066, memory: 16000, loss_rpn_cls: 0.0171, loss_rpn_bbox: 0.0282, loss_cls: 0.1340, acc: 94.9905, loss_bbox: 0.1828, loss_mask: 0.2016, loss: 0.5636 2023-11-16 07:34:14,662 - mmdet - INFO - Epoch [28][1500/1833] lr: 2.000e-05, eta: 4:56:34, time: 1.217, data_time: 0.060, memory: 16000, loss_rpn_cls: 0.0172, loss_rpn_bbox: 0.0280, loss_cls: 0.1329, acc: 95.0292, loss_bbox: 0.1819, loss_mask: 0.2020, loss: 0.5620 2023-11-16 07:35:14,145 - mmdet - INFO - Epoch [28][1550/1833] lr: 2.000e-05, eta: 4:55:34, time: 1.190, data_time: 0.059, memory: 16000, loss_rpn_cls: 0.0176, loss_rpn_bbox: 0.0275, loss_cls: 0.1318, acc: 95.0914, loss_bbox: 0.1797, loss_mask: 0.2028, loss: 0.5593 2023-11-16 07:36:14,534 - mmdet - INFO - Epoch [28][1600/1833] lr: 2.000e-05, eta: 4:54:35, time: 1.208, data_time: 0.064, memory: 16000, loss_rpn_cls: 0.0158, loss_rpn_bbox: 0.0278, loss_cls: 0.1322, acc: 95.0239, loss_bbox: 0.1818, loss_mask: 0.2011, loss: 0.5588 2023-11-16 07:37:15,624 - mmdet - INFO - Epoch [28][1650/1833] lr: 2.000e-05, eta: 4:53:37, time: 1.222, data_time: 0.065, memory: 16000, loss_rpn_cls: 0.0169, loss_rpn_bbox: 0.0273, loss_cls: 0.1308, acc: 95.0630, loss_bbox: 0.1791, loss_mask: 0.2010, loss: 0.5552 2023-11-16 07:38:14,958 - mmdet - INFO - Epoch [28][1700/1833] lr: 2.000e-05, eta: 4:52:37, time: 1.187, data_time: 0.076, memory: 16000, loss_rpn_cls: 0.0168, loss_rpn_bbox: 0.0271, loss_cls: 0.1295, acc: 95.1656, loss_bbox: 0.1758, loss_mask: 0.2013, loss: 0.5504 2023-11-16 07:39:16,527 - mmdet - INFO - Epoch [28][1750/1833] lr: 2.000e-05, eta: 4:51:39, time: 1.231, data_time: 0.065, memory: 16000, loss_rpn_cls: 0.0181, loss_rpn_bbox: 0.0286, loss_cls: 0.1347, acc: 94.9299, loss_bbox: 0.1832, loss_mask: 0.2026, loss: 0.5671 2023-11-16 07:40:16,670 - mmdet - INFO - Epoch [28][1800/1833] lr: 2.000e-05, eta: 4:50:39, time: 1.203, data_time: 0.067, memory: 16000, loss_rpn_cls: 0.0176, loss_rpn_bbox: 0.0284, loss_cls: 0.1329, acc: 95.0359, loss_bbox: 0.1795, loss_mask: 0.2026, loss: 0.5610 2023-11-16 07:40:57,923 - mmdet - INFO - Saving checkpoint at 28 epochs 2023-11-16 07:41:43,881 - mmdet - INFO - Evaluating bbox... 2023-11-16 07:42:10,012 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.501 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.716 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.547 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.338 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.539 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.641 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 ] = 0.456 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 ] = 0.763 2023-11-16 07:42:10,014 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.598 | bicycle | 0.397 | car | 0.508 | | motorcycle | 0.500 | airplane | 0.716 | bus | 0.729 | | train | 0.709 | truck | 0.452 | boat | 0.341 | | traffic light | 0.319 | fire hydrant | 0.756 | stop sign | 0.709 | | parking meter | 0.536 | bench | 0.331 | bird | 0.429 | | cat | 0.752 | dog | 0.707 | horse | 0.663 | | sheep | 0.623 | cow | 0.629 | elephant | 0.724 | | bear | 0.738 | zebra | 0.696 | giraffe | 0.712 | | backpack | 0.228 | umbrella | 0.480 | handbag | 0.264 | | tie | 0.426 | suitcase | 0.508 | frisbee | 0.732 | | skis | 0.325 | snowboard | 0.459 | sports ball | 0.492 | | kite | 0.475 | baseball bat | 0.413 | baseball glove | 0.461 | | skateboard | 0.613 | surfboard | 0.470 | tennis racket | 0.591 | | bottle | 0.477 | wine glass | 0.438 | cup | 0.511 | | fork | 0.514 | knife | 0.307 | spoon | 0.326 | | bowl | 0.495 | banana | 0.294 | apple | 0.286 | | sandwich | 0.480 | orange | 0.371 | broccoli | 0.256 | | carrot | 0.274 | hot dog | 0.454 | pizza | 0.569 | | donut | 0.572 | cake | 0.450 | chair | 0.378 | | couch | 0.498 | potted plant | 0.371 | bed | 0.476 | | dining table | 0.334 | toilet | 0.676 | tv | 0.645 | | laptop | 0.695 | mouse | 0.664 | remote | 0.455 | | keyboard | 0.565 | cell phone | 0.474 | microwave | 0.697 | | oven | 0.429 | toaster | 0.490 | sink | 0.455 | | refrigerator | 0.677 | book | 0.212 | clock | 0.521 | | vase | 0.459 | scissors | 0.453 | teddy bear | 0.547 | | hair drier | 0.255 | toothbrush | 0.347 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-16 07:42:10,014 - mmdet - INFO - Evaluating segm... 2023-11-16 07:42:40,890 - 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 ] = 0.685 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.475 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 ] = 0.475 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 ] = 0.558 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.558 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.558 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 ] = 0.594 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.715 2023-11-16 07:42:40,892 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.519 | bicycle | 0.250 | car | 0.463 | | motorcycle | 0.416 | airplane | 0.543 | bus | 0.705 | | train | 0.686 | truck | 0.429 | boat | 0.307 | | traffic light | 0.305 | fire hydrant | 0.709 | stop sign | 0.683 | | parking meter | 0.542 | bench | 0.254 | bird | 0.360 | | cat | 0.728 | dog | 0.660 | horse | 0.485 | | sheep | 0.547 | cow | 0.536 | elephant | 0.650 | | bear | 0.729 | zebra | 0.615 | giraffe | 0.555 | | backpack | 0.232 | umbrella | 0.525 | handbag | 0.236 | | tie | 0.381 | suitcase | 0.521 | frisbee | 0.674 | | skis | 0.071 | snowboard | 0.303 | sports ball | 0.471 | | kite | 0.334 | baseball bat | 0.312 | baseball glove | 0.462 | | skateboard | 0.397 | surfboard | 0.386 | tennis racket | 0.613 | | bottle | 0.450 | wine glass | 0.393 | cup | 0.504 | | fork | 0.262 | knife | 0.211 | spoon | 0.233 | | bowl | 0.455 | banana | 0.243 | apple | 0.279 | | sandwich | 0.495 | orange | 0.369 | broccoli | 0.241 | | carrot | 0.239 | hot dog | 0.366 | pizza | 0.551 | | donut | 0.564 | cake | 0.454 | chair | 0.272 | | couch | 0.415 | potted plant | 0.308 | bed | 0.377 | | dining table | 0.195 | toilet | 0.640 | tv | 0.670 | | laptop | 0.675 | mouse | 0.632 | remote | 0.399 | | keyboard | 0.540 | cell phone | 0.435 | microwave | 0.698 | | oven | 0.383 | toaster | 0.529 | sink | 0.428 | | refrigerator | 0.665 | book | 0.158 | clock | 0.510 | | vase | 0.445 | scissors | 0.331 | teddy bear | 0.520 | | hair drier | 0.137 | toothbrush | 0.250 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-16 07:42:41,260 - mmdet - INFO - The previous best checkpoint /mnt/petrelfs/lizhiqi/DINO/detection/work_dirs/mask_rcnn_flash_internimage_s_fpn_3x_coco_0.4/best_bbox_mAP_epoch_25.pth was removed 2023-11-16 07:42:43,419 - mmdet - INFO - Now best checkpoint is saved as best_bbox_mAP_epoch_28.pth. 2023-11-16 07:42:43,419 - mmdet - INFO - Best bbox_mAP is 0.5008 at 28 epoch. 2023-11-16 07:42:43,419 - mmdet - INFO - Exp name: mask_rcnn_flash_internimage_s_fpn_3x_coco_0.4.py 2023-11-16 07:42:43,420 - mmdet - INFO - Epoch(val) [28][625] bbox_mAP: 0.5008, bbox_mAP_50: 0.7163, bbox_mAP_75: 0.5471, bbox_mAP_s: 0.3379, bbox_mAP_m: 0.5388, bbox_mAP_l: 0.6407, bbox_mAP_copypaste: 0.5008 0.7163 0.5471 0.3379 0.5388 0.6407, segm_mAP: 0.4440, segm_mAP_50: 0.6847, segm_mAP_75: 0.4753, segm_mAP_s: 0.2468, segm_mAP_m: 0.4751, segm_mAP_l: 0.6311, segm_mAP_copypaste: 0.4440 0.6847 0.4753 0.2468 0.4751 0.6311 2023-11-16 07:43:47,257 - mmdet - INFO - Epoch [29][50/1833] lr: 2.000e-05, eta: 4:48:51, time: 1.276, data_time: 0.143, memory: 16000, loss_rpn_cls: 0.0171, loss_rpn_bbox: 0.0286, loss_cls: 0.1314, acc: 95.0595, loss_bbox: 0.1795, loss_mask: 0.2031, loss: 0.5596 2023-11-16 07:44:46,160 - mmdet - INFO - Epoch [29][100/1833] lr: 2.000e-05, eta: 4:47:52, time: 1.178, data_time: 0.065, memory: 16000, loss_rpn_cls: 0.0172, loss_rpn_bbox: 0.0275, loss_cls: 0.1303, acc: 95.1116, loss_bbox: 0.1791, loss_mask: 0.2010, loss: 0.5551 2023-11-16 07:45:45,359 - mmdet - INFO - Epoch [29][150/1833] lr: 2.000e-05, eta: 4:46:52, time: 1.184, data_time: 0.071, memory: 16000, loss_rpn_cls: 0.0172, loss_rpn_bbox: 0.0284, loss_cls: 0.1353, acc: 94.8818, loss_bbox: 0.1852, loss_mask: 0.2069, loss: 0.5730 2023-11-16 07:46:45,661 - mmdet - INFO - Epoch [29][200/1833] lr: 2.000e-05, eta: 4:45:53, time: 1.206, data_time: 0.075, memory: 16000, loss_rpn_cls: 0.0175, loss_rpn_bbox: 0.0278, loss_cls: 0.1282, acc: 95.1602, loss_bbox: 0.1757, loss_mask: 0.2000, loss: 0.5492 2023-11-16 07:47:46,111 - mmdet - INFO - Epoch [29][250/1833] lr: 2.000e-05, eta: 4:44:54, time: 1.209, data_time: 0.074, memory: 16000, loss_rpn_cls: 0.0176, loss_rpn_bbox: 0.0285, loss_cls: 0.1331, acc: 94.9753, loss_bbox: 0.1828, loss_mask: 0.2018, loss: 0.5640 2023-11-16 07:48:45,769 - mmdet - INFO - Epoch [29][300/1833] lr: 2.000e-05, eta: 4:43:55, time: 1.193, data_time: 0.077, memory: 16000, loss_rpn_cls: 0.0161, loss_rpn_bbox: 0.0272, loss_cls: 0.1297, acc: 95.1208, loss_bbox: 0.1785, loss_mask: 0.1990, loss: 0.5504 2023-11-16 07:49:45,368 - mmdet - INFO - Epoch [29][350/1833] lr: 2.000e-05, eta: 4:42:56, time: 1.192, data_time: 0.083, memory: 16000, loss_rpn_cls: 0.0171, loss_rpn_bbox: 0.0279, loss_cls: 0.1293, acc: 95.1198, loss_bbox: 0.1776, loss_mask: 0.2016, loss: 0.5535 2023-11-16 07:50:46,212 - mmdet - INFO - Epoch [29][400/1833] lr: 2.000e-05, eta: 4:41:57, time: 1.217, data_time: 0.091, memory: 16000, loss_rpn_cls: 0.0166, loss_rpn_bbox: 0.0280, loss_cls: 0.1329, acc: 95.0363, loss_bbox: 0.1810, loss_mask: 0.2017, loss: 0.5602 2023-11-16 07:51:47,056 - mmdet - INFO - Epoch [29][450/1833] lr: 2.000e-05, eta: 4:40:58, time: 1.217, data_time: 0.089, memory: 16000, loss_rpn_cls: 0.0182, loss_rpn_bbox: 0.0304, loss_cls: 0.1362, acc: 94.8760, loss_bbox: 0.1867, loss_mask: 0.2054, loss: 0.5768 2023-11-16 07:52:47,155 - mmdet - INFO - Epoch [29][500/1833] lr: 2.000e-05, eta: 4:39:59, time: 1.202, data_time: 0.079, memory: 16000, loss_rpn_cls: 0.0179, loss_rpn_bbox: 0.0288, loss_cls: 0.1340, acc: 94.9289, loss_bbox: 0.1822, loss_mask: 0.2031, loss: 0.5660 2023-11-16 07:53:47,012 - mmdet - INFO - Epoch [29][550/1833] lr: 2.000e-05, eta: 4:39:00, time: 1.197, data_time: 0.077, memory: 16000, loss_rpn_cls: 0.0166, loss_rpn_bbox: 0.0283, loss_cls: 0.1329, acc: 94.9712, loss_bbox: 0.1827, loss_mask: 0.2005, loss: 0.5610 2023-11-16 07:54:45,969 - mmdet - INFO - Epoch [29][600/1833] lr: 2.000e-05, eta: 4:38:01, time: 1.179, data_time: 0.089, memory: 16000, loss_rpn_cls: 0.0179, loss_rpn_bbox: 0.0286, loss_cls: 0.1340, acc: 94.9380, loss_bbox: 0.1840, loss_mask: 0.2019, loss: 0.5664 2023-11-16 07:55:44,210 - mmdet - INFO - Epoch [29][650/1833] lr: 2.000e-05, eta: 4:37:01, time: 1.165, data_time: 0.075, memory: 16000, loss_rpn_cls: 0.0174, loss_rpn_bbox: 0.0280, loss_cls: 0.1325, acc: 95.0286, loss_bbox: 0.1814, loss_mask: 0.2002, loss: 0.5595 2023-11-16 07:56:44,789 - mmdet - INFO - Epoch [29][700/1833] lr: 2.000e-05, eta: 4:36:02, time: 1.212, data_time: 0.087, memory: 16000, loss_rpn_cls: 0.0181, loss_rpn_bbox: 0.0286, loss_cls: 0.1338, acc: 94.9573, loss_bbox: 0.1840, loss_mask: 0.2015, loss: 0.5660 2023-11-16 07:57:44,337 - mmdet - INFO - Epoch [29][750/1833] lr: 2.000e-05, eta: 4:35:03, time: 1.191, data_time: 0.074, memory: 16000, loss_rpn_cls: 0.0170, loss_rpn_bbox: 0.0277, loss_cls: 0.1317, acc: 95.0290, loss_bbox: 0.1809, loss_mask: 0.2012, loss: 0.5584 2023-11-16 07:58:45,883 - mmdet - INFO - Epoch [29][800/1833] lr: 2.000e-05, eta: 4:34:04, time: 1.231, data_time: 0.090, memory: 16000, loss_rpn_cls: 0.0174, loss_rpn_bbox: 0.0290, loss_cls: 0.1337, acc: 94.9343, loss_bbox: 0.1835, loss_mask: 0.2026, loss: 0.5663 2023-11-16 07:59:45,696 - mmdet - INFO - Epoch [29][850/1833] lr: 2.000e-05, eta: 4:33:05, time: 1.196, data_time: 0.084, memory: 16000, loss_rpn_cls: 0.0170, loss_rpn_bbox: 0.0280, loss_cls: 0.1325, acc: 95.0369, loss_bbox: 0.1816, loss_mask: 0.2034, loss: 0.5625 2023-11-16 08:00:44,694 - mmdet - INFO - Epoch [29][900/1833] lr: 2.000e-05, eta: 4:32:05, time: 1.180, data_time: 0.076, memory: 16000, loss_rpn_cls: 0.0171, loss_rpn_bbox: 0.0277, loss_cls: 0.1295, acc: 95.1259, loss_bbox: 0.1785, loss_mask: 0.2024, loss: 0.5551 2023-11-16 08:01:44,214 - mmdet - INFO - Epoch [29][950/1833] lr: 2.000e-05, eta: 4:31:06, time: 1.190, data_time: 0.084, memory: 16000, loss_rpn_cls: 0.0171, loss_rpn_bbox: 0.0282, loss_cls: 0.1313, acc: 95.0751, loss_bbox: 0.1791, loss_mask: 0.2005, loss: 0.5562 2023-11-16 08:02:43,137 - mmdet - INFO - Epoch [29][1000/1833] lr: 2.000e-05, eta: 4:30:07, time: 1.178, data_time: 0.082, memory: 16000, loss_rpn_cls: 0.0175, loss_rpn_bbox: 0.0282, loss_cls: 0.1328, acc: 95.0001, loss_bbox: 0.1821, loss_mask: 0.2049, loss: 0.5656 2023-11-16 08:03:42,756 - mmdet - INFO - Epoch [29][1050/1833] lr: 2.000e-05, eta: 4:29:08, time: 1.192, data_time: 0.081, memory: 16000, loss_rpn_cls: 0.0163, loss_rpn_bbox: 0.0270, loss_cls: 0.1300, acc: 95.1243, loss_bbox: 0.1773, loss_mask: 0.2000, loss: 0.5506 2023-11-16 08:04:41,632 - mmdet - INFO - Epoch [29][1100/1833] lr: 2.000e-05, eta: 4:28:08, time: 1.177, data_time: 0.075, memory: 16000, loss_rpn_cls: 0.0171, loss_rpn_bbox: 0.0274, loss_cls: 0.1316, acc: 95.0144, loss_bbox: 0.1802, loss_mask: 0.2018, loss: 0.5582 2023-11-16 08:05:40,923 - mmdet - INFO - Epoch [29][1150/1833] lr: 2.000e-05, eta: 4:27:09, time: 1.186, data_time: 0.078, memory: 16000, loss_rpn_cls: 0.0166, loss_rpn_bbox: 0.0271, loss_cls: 0.1281, acc: 95.1856, loss_bbox: 0.1770, loss_mask: 0.2008, loss: 0.5495 2023-11-16 08:06:41,735 - mmdet - INFO - Epoch [29][1200/1833] lr: 2.000e-05, eta: 4:26:10, time: 1.216, data_time: 0.076, memory: 16000, loss_rpn_cls: 0.0167, loss_rpn_bbox: 0.0278, loss_cls: 0.1324, acc: 95.0000, loss_bbox: 0.1828, loss_mask: 0.2017, loss: 0.5614 2023-11-16 08:07:44,084 - mmdet - INFO - Epoch [29][1250/1833] lr: 2.000e-05, eta: 4:25:11, time: 1.247, data_time: 0.084, memory: 16000, loss_rpn_cls: 0.0165, loss_rpn_bbox: 0.0276, loss_cls: 0.1317, acc: 95.0761, loss_bbox: 0.1824, loss_mask: 0.2014, loss: 0.5596 2023-11-16 08:08:42,862 - mmdet - INFO - Epoch [29][1300/1833] lr: 2.000e-05, eta: 4:24:12, time: 1.176, data_time: 0.081, memory: 16000, loss_rpn_cls: 0.0168, loss_rpn_bbox: 0.0281, loss_cls: 0.1314, acc: 95.0878, loss_bbox: 0.1797, loss_mask: 0.1995, loss: 0.5555 2023-11-16 08:09:42,096 - mmdet - INFO - Epoch [29][1350/1833] lr: 2.000e-05, eta: 4:23:13, time: 1.185, data_time: 0.073, memory: 16000, loss_rpn_cls: 0.0168, loss_rpn_bbox: 0.0276, loss_cls: 0.1317, acc: 95.0837, loss_bbox: 0.1809, loss_mask: 0.2044, loss: 0.5613 2023-11-16 08:10:39,856 - mmdet - INFO - Epoch [29][1400/1833] lr: 2.000e-05, eta: 4:22:13, time: 1.155, data_time: 0.081, memory: 16000, loss_rpn_cls: 0.0167, loss_rpn_bbox: 0.0276, loss_cls: 0.1320, acc: 95.0535, loss_bbox: 0.1785, loss_mask: 0.2008, loss: 0.5555 2023-11-16 08:11:39,373 - mmdet - INFO - Epoch [29][1450/1833] lr: 2.000e-05, eta: 4:21:14, time: 1.190, data_time: 0.080, memory: 16000, loss_rpn_cls: 0.0175, loss_rpn_bbox: 0.0290, loss_cls: 0.1335, acc: 94.9849, loss_bbox: 0.1842, loss_mask: 0.2026, loss: 0.5668 2023-11-16 08:12:38,653 - mmdet - INFO - Epoch [29][1500/1833] lr: 2.000e-05, eta: 4:20:14, time: 1.186, data_time: 0.081, memory: 16000, loss_rpn_cls: 0.0170, loss_rpn_bbox: 0.0287, loss_cls: 0.1323, acc: 95.0314, loss_bbox: 0.1804, loss_mask: 0.2050, loss: 0.5634 2023-11-16 08:13:38,496 - mmdet - INFO - Epoch [29][1550/1833] lr: 2.000e-05, eta: 4:19:15, time: 1.197, data_time: 0.076, memory: 16000, loss_rpn_cls: 0.0177, loss_rpn_bbox: 0.0286, loss_cls: 0.1337, acc: 94.9791, loss_bbox: 0.1817, loss_mask: 0.2014, loss: 0.5631 2023-11-16 08:14:38,373 - mmdet - INFO - Epoch [29][1600/1833] lr: 2.000e-05, eta: 4:18:16, time: 1.198, data_time: 0.080, memory: 16000, loss_rpn_cls: 0.0166, loss_rpn_bbox: 0.0277, loss_cls: 0.1317, acc: 95.0594, loss_bbox: 0.1813, loss_mask: 0.2011, loss: 0.5584 2023-11-16 08:15:39,020 - mmdet - INFO - Epoch [29][1650/1833] lr: 2.000e-05, eta: 4:17:17, time: 1.213, data_time: 0.079, memory: 16000, loss_rpn_cls: 0.0169, loss_rpn_bbox: 0.0285, loss_cls: 0.1311, acc: 95.0573, loss_bbox: 0.1779, loss_mask: 0.2019, loss: 0.5563 2023-11-16 08:16:38,827 - mmdet - INFO - Epoch [29][1700/1833] lr: 2.000e-05, eta: 4:16:18, time: 1.196, data_time: 0.074, memory: 16000, loss_rpn_cls: 0.0163, loss_rpn_bbox: 0.0263, loss_cls: 0.1278, acc: 95.2079, loss_bbox: 0.1782, loss_mask: 0.2012, loss: 0.5497 2023-11-16 08:17:39,189 - mmdet - INFO - Epoch [29][1750/1833] lr: 2.000e-05, eta: 4:15:19, time: 1.207, data_time: 0.085, memory: 16000, loss_rpn_cls: 0.0173, loss_rpn_bbox: 0.0286, loss_cls: 0.1333, acc: 94.9568, loss_bbox: 0.1840, loss_mask: 0.2029, loss: 0.5661 2023-11-16 08:18:37,578 - mmdet - INFO - Epoch [29][1800/1833] lr: 2.000e-05, eta: 4:14:19, time: 1.168, data_time: 0.081, memory: 16000, loss_rpn_cls: 0.0174, loss_rpn_bbox: 0.0275, loss_cls: 0.1298, acc: 95.1160, loss_bbox: 0.1779, loss_mask: 0.2021, loss: 0.5547 2023-11-16 08:19:16,898 - mmdet - INFO - Saving checkpoint at 29 epochs 2023-11-16 08:20:00,604 - mmdet - INFO - Evaluating bbox... 2023-11-16 08:20:29,902 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.502 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.718 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.549 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.343 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.538 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.645 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 ] = 0.456 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 ] = 0.764 2023-11-16 08:20:29,905 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.596 | bicycle | 0.405 | car | 0.503 | | motorcycle | 0.504 | airplane | 0.709 | bus | 0.732 | | train | 0.693 | truck | 0.462 | boat | 0.343 | | traffic light | 0.318 | fire hydrant | 0.749 | stop sign | 0.703 | | parking meter | 0.543 | bench | 0.327 | bird | 0.434 | | cat | 0.733 | dog | 0.722 | horse | 0.656 | | sheep | 0.625 | cow | 0.632 | elephant | 0.724 | | bear | 0.745 | zebra | 0.692 | giraffe | 0.721 | | backpack | 0.234 | umbrella | 0.479 | handbag | 0.263 | | tie | 0.435 | suitcase | 0.503 | frisbee | 0.731 | | skis | 0.327 | snowboard | 0.458 | sports ball | 0.494 | | kite | 0.474 | baseball bat | 0.427 | baseball glove | 0.455 | | skateboard | 0.613 | surfboard | 0.472 | tennis racket | 0.589 | | bottle | 0.478 | wine glass | 0.435 | cup | 0.516 | | fork | 0.512 | knife | 0.309 | spoon | 0.329 | | bowl | 0.495 | banana | 0.294 | apple | 0.282 | | sandwich | 0.483 | orange | 0.365 | broccoli | 0.266 | | carrot | 0.273 | hot dog | 0.447 | pizza | 0.582 | | donut | 0.564 | cake | 0.453 | chair | 0.380 | | couch | 0.495 | potted plant | 0.376 | bed | 0.478 | | dining table | 0.337 | toilet | 0.665 | tv | 0.640 | | laptop | 0.699 | mouse | 0.663 | remote | 0.448 | | keyboard | 0.573 | cell phone | 0.471 | microwave | 0.681 | | oven | 0.437 | toaster | 0.496 | sink | 0.448 | | refrigerator | 0.685 | book | 0.213 | clock | 0.523 | | vase | 0.453 | scissors | 0.484 | teddy bear | 0.572 | | hair drier | 0.241 | toothbrush | 0.370 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-16 08:20:29,905 - mmdet - INFO - Evaluating segm... 2023-11-16 08:20:59,118 - 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 ] = 0.687 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.479 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.250 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 ] = 0.634 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 ] = 0.394 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.596 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.714 2023-11-16 08:20:59,121 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.517 | bicycle | 0.254 | car | 0.463 | | motorcycle | 0.421 | airplane | 0.546 | bus | 0.714 | | train | 0.680 | truck | 0.437 | boat | 0.309 | | traffic light | 0.308 | fire hydrant | 0.708 | stop sign | 0.680 | | parking meter | 0.548 | bench | 0.251 | bird | 0.361 | | cat | 0.725 | dog | 0.677 | horse | 0.484 | | sheep | 0.551 | cow | 0.536 | elephant | 0.653 | | bear | 0.734 | zebra | 0.599 | giraffe | 0.559 | | backpack | 0.232 | umbrella | 0.529 | handbag | 0.238 | | tie | 0.392 | suitcase | 0.517 | frisbee | 0.685 | | skis | 0.076 | snowboard | 0.311 | sports ball | 0.472 | | kite | 0.337 | baseball bat | 0.323 | baseball glove | 0.458 | | skateboard | 0.393 | surfboard | 0.384 | tennis racket | 0.620 | | bottle | 0.448 | wine glass | 0.395 | cup | 0.508 | | fork | 0.272 | knife | 0.215 | spoon | 0.232 | | bowl | 0.456 | banana | 0.237 | apple | 0.275 | | sandwich | 0.491 | orange | 0.359 | broccoli | 0.243 | | carrot | 0.239 | hot dog | 0.358 | pizza | 0.559 | | donut | 0.559 | cake | 0.454 | chair | 0.275 | | couch | 0.414 | potted plant | 0.309 | bed | 0.384 | | dining table | 0.198 | toilet | 0.643 | tv | 0.666 | | laptop | 0.676 | mouse | 0.639 | remote | 0.405 | | keyboard | 0.555 | cell phone | 0.438 | microwave | 0.684 | | oven | 0.390 | toaster | 0.546 | sink | 0.423 | | refrigerator | 0.680 | book | 0.159 | clock | 0.515 | | vase | 0.444 | scissors | 0.338 | teddy bear | 0.536 | | hair drier | 0.173 | toothbrush | 0.257 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-16 08:20:59,580 - mmdet - INFO - The previous best checkpoint /mnt/petrelfs/lizhiqi/DINO/detection/work_dirs/mask_rcnn_flash_internimage_s_fpn_3x_coco_0.4/best_bbox_mAP_epoch_28.pth was removed 2023-11-16 08:21:01,813 - mmdet - INFO - Now best checkpoint is saved as best_bbox_mAP_epoch_29.pth. 2023-11-16 08:21:01,813 - mmdet - INFO - Best bbox_mAP is 0.5017 at 29 epoch. 2023-11-16 08:21:01,814 - mmdet - INFO - Exp name: mask_rcnn_flash_internimage_s_fpn_3x_coco_0.4.py 2023-11-16 08:21:01,814 - mmdet - INFO - Epoch(val) [29][625] bbox_mAP: 0.5017, bbox_mAP_50: 0.7179, bbox_mAP_75: 0.5486, bbox_mAP_s: 0.3429, bbox_mAP_m: 0.5385, bbox_mAP_l: 0.6445, bbox_mAP_copypaste: 0.5017 0.7179 0.5486 0.3429 0.5385 0.6445, segm_mAP: 0.4466, segm_mAP_50: 0.6875, segm_mAP_75: 0.4790, segm_mAP_s: 0.2500, segm_mAP_m: 0.4780, segm_mAP_l: 0.6344, segm_mAP_copypaste: 0.4466 0.6875 0.4790 0.2500 0.4780 0.6344 2023-11-16 08:22:05,461 - mmdet - INFO - Epoch [30][50/1833] lr: 2.000e-05, eta: 4:12:32, time: 1.273, data_time: 0.139, memory: 16000, loss_rpn_cls: 0.0164, loss_rpn_bbox: 0.0265, loss_cls: 0.1259, acc: 95.2709, loss_bbox: 0.1742, loss_mask: 0.1987, loss: 0.5418 2023-11-16 08:23:05,585 - mmdet - INFO - Epoch [30][100/1833] lr: 2.000e-05, eta: 4:11:33, time: 1.202, data_time: 0.085, memory: 16000, loss_rpn_cls: 0.0170, loss_rpn_bbox: 0.0277, loss_cls: 0.1297, acc: 95.0868, loss_bbox: 0.1804, loss_mask: 0.2028, loss: 0.5577 2023-11-16 08:24:05,890 - mmdet - INFO - Epoch [30][150/1833] lr: 2.000e-05, eta: 4:10:34, time: 1.206, data_time: 0.076, memory: 16000, loss_rpn_cls: 0.0172, loss_rpn_bbox: 0.0275, loss_cls: 0.1290, acc: 95.1381, loss_bbox: 0.1768, loss_mask: 0.2014, loss: 0.5519 2023-11-16 08:25:05,760 - mmdet - INFO - Epoch [30][200/1833] lr: 2.000e-05, eta: 4:09:35, time: 1.197, data_time: 0.071, memory: 16000, loss_rpn_cls: 0.0159, loss_rpn_bbox: 0.0267, loss_cls: 0.1279, acc: 95.1857, loss_bbox: 0.1767, loss_mask: 0.1999, loss: 0.5470 2023-11-16 08:26:07,098 - mmdet - INFO - Epoch [30][250/1833] lr: 2.000e-05, eta: 4:08:36, time: 1.227, data_time: 0.081, memory: 16000, loss_rpn_cls: 0.0170, loss_rpn_bbox: 0.0282, loss_cls: 0.1330, acc: 95.0331, loss_bbox: 0.1825, loss_mask: 0.2016, loss: 0.5624 2023-11-16 08:27:08,252 - mmdet - INFO - Epoch [30][300/1833] lr: 2.000e-05, eta: 4:07:38, time: 1.223, data_time: 0.083, memory: 16000, loss_rpn_cls: 0.0174, loss_rpn_bbox: 0.0288, loss_cls: 0.1318, acc: 95.0258, loss_bbox: 0.1810, loss_mask: 0.2027, loss: 0.5617 2023-11-16 08:28:08,193 - mmdet - INFO - Epoch [30][350/1833] lr: 2.000e-05, eta: 4:06:38, time: 1.199, data_time: 0.094, memory: 16000, loss_rpn_cls: 0.0175, loss_rpn_bbox: 0.0282, loss_cls: 0.1315, acc: 95.0372, loss_bbox: 0.1818, loss_mask: 0.2005, loss: 0.5595 2023-11-16 08:29:10,004 - mmdet - INFO - Epoch [30][400/1833] lr: 2.000e-05, eta: 4:05:40, time: 1.236, data_time: 0.090, memory: 16000, loss_rpn_cls: 0.0175, loss_rpn_bbox: 0.0286, loss_cls: 0.1319, acc: 95.0409, loss_bbox: 0.1827, loss_mask: 0.2023, loss: 0.5629 2023-11-16 08:30:10,730 - mmdet - INFO - Epoch [30][450/1833] lr: 2.000e-05, eta: 4:04:41, time: 1.214, data_time: 0.083, memory: 16000, loss_rpn_cls: 0.0169, loss_rpn_bbox: 0.0276, loss_cls: 0.1336, acc: 94.9822, loss_bbox: 0.1823, loss_mask: 0.2021, loss: 0.5625 2023-11-16 08:31:10,241 - mmdet - INFO - Epoch [30][500/1833] lr: 2.000e-05, eta: 4:03:41, time: 1.190, data_time: 0.086, memory: 16000, loss_rpn_cls: 0.0176, loss_rpn_bbox: 0.0286, loss_cls: 0.1339, acc: 94.9602, loss_bbox: 0.1845, loss_mask: 0.2034, loss: 0.5680 2023-11-16 08:32:10,886 - mmdet - INFO - Epoch [30][550/1833] lr: 2.000e-05, eta: 4:02:42, time: 1.213, data_time: 0.081, memory: 16000, loss_rpn_cls: 0.0171, loss_rpn_bbox: 0.0281, loss_cls: 0.1314, acc: 95.0452, loss_bbox: 0.1791, loss_mask: 0.2015, loss: 0.5572 2023-11-16 08:33:10,443 - mmdet - INFO - Epoch [30][600/1833] lr: 2.000e-05, eta: 4:01:43, time: 1.191, data_time: 0.077, memory: 16000, loss_rpn_cls: 0.0173, loss_rpn_bbox: 0.0279, loss_cls: 0.1265, acc: 95.2418, loss_bbox: 0.1745, loss_mask: 0.1989, loss: 0.5451 2023-11-16 08:34:13,554 - mmdet - INFO - Epoch [30][650/1833] lr: 2.000e-05, eta: 4:00:45, time: 1.262, data_time: 0.083, memory: 16000, loss_rpn_cls: 0.0177, loss_rpn_bbox: 0.0288, loss_cls: 0.1339, acc: 94.9375, loss_bbox: 0.1843, loss_mask: 0.2025, loss: 0.5672 2023-11-16 08:35:13,903 - mmdet - INFO - Epoch [30][700/1833] lr: 2.000e-05, eta: 3:59:46, time: 1.207, data_time: 0.083, memory: 16000, loss_rpn_cls: 0.0176, loss_rpn_bbox: 0.0276, loss_cls: 0.1334, acc: 94.9959, loss_bbox: 0.1824, loss_mask: 0.2042, loss: 0.5652 2023-11-16 08:36:15,790 - mmdet - INFO - Epoch [30][750/1833] lr: 2.000e-05, eta: 3:58:47, time: 1.238, data_time: 0.078, memory: 16000, loss_rpn_cls: 0.0165, loss_rpn_bbox: 0.0273, loss_cls: 0.1274, acc: 95.1685, loss_bbox: 0.1789, loss_mask: 0.2010, loss: 0.5512 2023-11-16 08:37:15,790 - mmdet - INFO - Epoch [30][800/1833] lr: 2.000e-05, eta: 3:57:48, time: 1.200, data_time: 0.076, memory: 16000, loss_rpn_cls: 0.0165, loss_rpn_bbox: 0.0279, loss_cls: 0.1277, acc: 95.1817, loss_bbox: 0.1781, loss_mask: 0.2027, loss: 0.5529 2023-11-16 08:38:15,023 - mmdet - INFO - Epoch [30][850/1833] lr: 2.000e-05, eta: 3:56:49, time: 1.185, data_time: 0.079, memory: 16000, loss_rpn_cls: 0.0167, loss_rpn_bbox: 0.0280, loss_cls: 0.1285, acc: 95.1742, loss_bbox: 0.1786, loss_mask: 0.2000, loss: 0.5518 2023-11-16 08:39:14,819 - mmdet - INFO - Epoch [30][900/1833] lr: 2.000e-05, eta: 3:55:49, time: 1.196, data_time: 0.087, memory: 16000, loss_rpn_cls: 0.0164, loss_rpn_bbox: 0.0269, loss_cls: 0.1278, acc: 95.1649, loss_bbox: 0.1753, loss_mask: 0.1995, loss: 0.5459 2023-11-16 08:40:15,066 - mmdet - INFO - Epoch [30][950/1833] lr: 2.000e-05, eta: 3:54:50, time: 1.205, data_time: 0.076, memory: 16000, loss_rpn_cls: 0.0170, loss_rpn_bbox: 0.0272, loss_cls: 0.1294, acc: 95.1443, loss_bbox: 0.1774, loss_mask: 0.2009, loss: 0.5520 2023-11-16 08:41:14,502 - mmdet - INFO - Epoch [30][1000/1833] lr: 2.000e-05, eta: 3:53:51, time: 1.189, data_time: 0.080, memory: 16000, loss_rpn_cls: 0.0168, loss_rpn_bbox: 0.0269, loss_cls: 0.1267, acc: 95.2343, loss_bbox: 0.1743, loss_mask: 0.1989, loss: 0.5436 2023-11-16 08:42:14,227 - mmdet - INFO - Epoch [30][1050/1833] lr: 2.000e-05, eta: 3:52:52, time: 1.195, data_time: 0.074, memory: 16000, loss_rpn_cls: 0.0158, loss_rpn_bbox: 0.0266, loss_cls: 0.1286, acc: 95.1362, loss_bbox: 0.1782, loss_mask: 0.1997, loss: 0.5489 2023-11-16 08:43:13,094 - mmdet - INFO - Epoch [30][1100/1833] lr: 2.000e-05, eta: 3:51:52, time: 1.177, data_time: 0.069, memory: 16000, loss_rpn_cls: 0.0170, loss_rpn_bbox: 0.0275, loss_cls: 0.1288, acc: 95.1251, loss_bbox: 0.1770, loss_mask: 0.2015, loss: 0.5518 2023-11-16 08:44:13,644 - mmdet - INFO - Epoch [30][1150/1833] lr: 2.000e-05, eta: 3:50:53, time: 1.211, data_time: 0.072, memory: 16000, loss_rpn_cls: 0.0167, loss_rpn_bbox: 0.0281, loss_cls: 0.1311, acc: 95.0347, loss_bbox: 0.1804, loss_mask: 0.2009, loss: 0.5572 2023-11-16 08:45:14,581 - mmdet - INFO - Epoch [30][1200/1833] lr: 2.000e-05, eta: 3:49:54, time: 1.219, data_time: 0.086, memory: 16000, loss_rpn_cls: 0.0169, loss_rpn_bbox: 0.0280, loss_cls: 0.1305, acc: 95.0709, loss_bbox: 0.1790, loss_mask: 0.2020, loss: 0.5564 2023-11-16 08:46:15,659 - mmdet - INFO - Epoch [30][1250/1833] lr: 2.000e-05, eta: 3:48:56, time: 1.222, data_time: 0.076, memory: 16000, loss_rpn_cls: 0.0174, loss_rpn_bbox: 0.0285, loss_cls: 0.1298, acc: 95.0840, loss_bbox: 0.1806, loss_mask: 0.2028, loss: 0.5591 2023-11-16 08:47:15,708 - mmdet - INFO - Epoch [30][1300/1833] lr: 2.000e-05, eta: 3:47:56, time: 1.201, data_time: 0.086, memory: 16000, loss_rpn_cls: 0.0179, loss_rpn_bbox: 0.0290, loss_cls: 0.1360, acc: 94.9120, loss_bbox: 0.1844, loss_mask: 0.2042, loss: 0.5714 2023-11-16 08:48:16,097 - mmdet - INFO - Epoch [30][1350/1833] lr: 2.000e-05, eta: 3:46:57, time: 1.208, data_time: 0.080, memory: 16000, loss_rpn_cls: 0.0171, loss_rpn_bbox: 0.0279, loss_cls: 0.1306, acc: 95.0808, loss_bbox: 0.1785, loss_mask: 0.1991, loss: 0.5531 2023-11-16 08:49:16,415 - mmdet - INFO - Epoch [30][1400/1833] lr: 2.000e-05, eta: 3:45:58, time: 1.206, data_time: 0.079, memory: 16000, loss_rpn_cls: 0.0170, loss_rpn_bbox: 0.0278, loss_cls: 0.1298, acc: 95.0897, loss_bbox: 0.1809, loss_mask: 0.2014, loss: 0.5568 2023-11-16 08:50:16,646 - mmdet - INFO - Epoch [30][1450/1833] lr: 2.000e-05, eta: 3:44:59, time: 1.205, data_time: 0.077, memory: 16000, loss_rpn_cls: 0.0168, loss_rpn_bbox: 0.0277, loss_cls: 0.1288, acc: 95.1302, loss_bbox: 0.1793, loss_mask: 0.1996, loss: 0.5522 2023-11-16 08:51:17,046 - mmdet - INFO - Epoch [30][1500/1833] lr: 2.000e-05, eta: 3:44:00, time: 1.208, data_time: 0.081, memory: 16000, loss_rpn_cls: 0.0174, loss_rpn_bbox: 0.0284, loss_cls: 0.1310, acc: 95.0578, loss_bbox: 0.1809, loss_mask: 0.2013, loss: 0.5590 2023-11-16 08:52:16,456 - mmdet - INFO - Epoch [30][1550/1833] lr: 2.000e-05, eta: 3:43:01, time: 1.188, data_time: 0.076, memory: 16000, loss_rpn_cls: 0.0167, loss_rpn_bbox: 0.0274, loss_cls: 0.1301, acc: 95.0886, loss_bbox: 0.1784, loss_mask: 0.1970, loss: 0.5496 2023-11-16 08:53:17,242 - mmdet - INFO - Epoch [30][1600/1833] lr: 2.000e-05, eta: 3:42:02, time: 1.216, data_time: 0.073, memory: 16000, loss_rpn_cls: 0.0163, loss_rpn_bbox: 0.0271, loss_cls: 0.1309, acc: 95.0748, loss_bbox: 0.1777, loss_mask: 0.1997, loss: 0.5517 2023-11-16 08:54:17,073 - mmdet - INFO - Epoch [30][1650/1833] lr: 2.000e-05, eta: 3:41:03, time: 1.197, data_time: 0.083, memory: 16000, loss_rpn_cls: 0.0175, loss_rpn_bbox: 0.0285, loss_cls: 0.1327, acc: 94.9904, loss_bbox: 0.1814, loss_mask: 0.2004, loss: 0.5606 2023-11-16 08:55:17,031 - mmdet - INFO - Epoch [30][1700/1833] lr: 2.000e-05, eta: 3:40:03, time: 1.199, data_time: 0.081, memory: 16000, loss_rpn_cls: 0.0172, loss_rpn_bbox: 0.0281, loss_cls: 0.1294, acc: 95.1521, loss_bbox: 0.1789, loss_mask: 0.2000, loss: 0.5536 2023-11-16 08:56:17,682 - mmdet - INFO - Epoch [30][1750/1833] lr: 2.000e-05, eta: 3:39:04, time: 1.213, data_time: 0.072, memory: 16000, loss_rpn_cls: 0.0168, loss_rpn_bbox: 0.0270, loss_cls: 0.1273, acc: 95.1734, loss_bbox: 0.1763, loss_mask: 0.1988, loss: 0.5463 2023-11-16 08:57:17,464 - mmdet - INFO - Epoch [30][1800/1833] lr: 2.000e-05, eta: 3:38:05, time: 1.196, data_time: 0.078, memory: 16000, loss_rpn_cls: 0.0167, loss_rpn_bbox: 0.0273, loss_cls: 0.1306, acc: 95.0973, loss_bbox: 0.1787, loss_mask: 0.2012, loss: 0.5546 2023-11-16 08:57:58,891 - mmdet - INFO - Saving checkpoint at 30 epochs 2023-11-16 08:58:45,200 - mmdet - INFO - Evaluating bbox... 2023-11-16 08:59:15,095 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.503 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.718 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.550 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.337 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.541 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.645 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 ] = 0.461 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 ] = 0.770 2023-11-16 08:59:15,098 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.600 | bicycle | 0.407 | car | 0.512 | | motorcycle | 0.503 | airplane | 0.713 | bus | 0.736 | | train | 0.700 | truck | 0.452 | boat | 0.338 | | traffic light | 0.318 | fire hydrant | 0.747 | stop sign | 0.706 | | parking meter | 0.545 | bench | 0.329 | bird | 0.431 | | cat | 0.744 | dog | 0.717 | horse | 0.653 | | sheep | 0.623 | cow | 0.634 | elephant | 0.718 | | bear | 0.747 | zebra | 0.701 | giraffe | 0.720 | | backpack | 0.232 | umbrella | 0.480 | handbag | 0.267 | | tie | 0.430 | suitcase | 0.507 | frisbee | 0.734 | | skis | 0.324 | snowboard | 0.464 | sports ball | 0.491 | | kite | 0.480 | baseball bat | 0.427 | baseball glove | 0.458 | | skateboard | 0.610 | surfboard | 0.474 | tennis racket | 0.585 | | bottle | 0.479 | wine glass | 0.434 | cup | 0.514 | | fork | 0.512 | knife | 0.315 | spoon | 0.335 | | bowl | 0.494 | banana | 0.287 | apple | 0.285 | | sandwich | 0.475 | orange | 0.352 | broccoli | 0.255 | | carrot | 0.275 | hot dog | 0.465 | pizza | 0.579 | | donut | 0.568 | cake | 0.454 | chair | 0.381 | | couch | 0.498 | potted plant | 0.372 | bed | 0.481 | | dining table | 0.332 | toilet | 0.669 | tv | 0.644 | | laptop | 0.711 | mouse | 0.671 | remote | 0.449 | | keyboard | 0.577 | cell phone | 0.471 | microwave | 0.690 | | oven | 0.442 | toaster | 0.512 | sink | 0.448 | | refrigerator | 0.689 | book | 0.214 | clock | 0.525 | | vase | 0.450 | scissors | 0.485 | teddy bear | 0.567 | | hair drier | 0.225 | toothbrush | 0.358 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-16 08:59:15,098 - mmdet - INFO - Evaluating segm... 2023-11-16 08:59:44,311 - 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 ] = 0.689 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.481 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.250 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.477 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 ] = 0.560 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 ] = 0.398 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.596 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.715 2023-11-16 08:59:44,314 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.520 | bicycle | 0.256 | car | 0.469 | | motorcycle | 0.417 | airplane | 0.544 | bus | 0.709 | | train | 0.681 | truck | 0.424 | boat | 0.311 | | traffic light | 0.304 | fire hydrant | 0.705 | stop sign | 0.681 | | parking meter | 0.551 | bench | 0.252 | bird | 0.361 | | cat | 0.728 | dog | 0.671 | horse | 0.490 | | sheep | 0.549 | cow | 0.539 | elephant | 0.649 | | bear | 0.734 | zebra | 0.611 | giraffe | 0.560 | | backpack | 0.236 | umbrella | 0.528 | handbag | 0.235 | | tie | 0.387 | suitcase | 0.526 | frisbee | 0.679 | | skis | 0.073 | snowboard | 0.300 | sports ball | 0.470 | | kite | 0.339 | baseball bat | 0.316 | baseball glove | 0.463 | | skateboard | 0.396 | surfboard | 0.383 | tennis racket | 0.615 | | bottle | 0.451 | wine glass | 0.391 | cup | 0.509 | | fork | 0.269 | knife | 0.220 | spoon | 0.237 | | bowl | 0.454 | banana | 0.234 | apple | 0.275 | | sandwich | 0.486 | orange | 0.350 | broccoli | 0.237 | | carrot | 0.238 | hot dog | 0.382 | pizza | 0.556 | | donut | 0.563 | cake | 0.458 | chair | 0.276 | | couch | 0.416 | potted plant | 0.307 | bed | 0.381 | | dining table | 0.195 | toilet | 0.641 | tv | 0.673 | | laptop | 0.681 | mouse | 0.642 | remote | 0.403 | | keyboard | 0.565 | cell phone | 0.435 | microwave | 0.688 | | oven | 0.396 | toaster | 0.554 | sink | 0.427 | | refrigerator | 0.676 | book | 0.158 | clock | 0.515 | | vase | 0.446 | scissors | 0.344 | teddy bear | 0.536 | | hair drier | 0.174 | toothbrush | 0.255 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-16 08:59:44,815 - mmdet - INFO - The previous best checkpoint /mnt/petrelfs/lizhiqi/DINO/detection/work_dirs/mask_rcnn_flash_internimage_s_fpn_3x_coco_0.4/best_bbox_mAP_epoch_29.pth was removed 2023-11-16 08:59:47,039 - mmdet - INFO - Now best checkpoint is saved as best_bbox_mAP_epoch_30.pth. 2023-11-16 08:59:47,040 - mmdet - INFO - Best bbox_mAP is 0.5025 at 30 epoch. 2023-11-16 08:59:47,040 - mmdet - INFO - Exp name: mask_rcnn_flash_internimage_s_fpn_3x_coco_0.4.py 2023-11-16 08:59:47,040 - mmdet - INFO - Epoch(val) [30][625] bbox_mAP: 0.5025, bbox_mAP_50: 0.7183, bbox_mAP_75: 0.5501, bbox_mAP_s: 0.3374, bbox_mAP_m: 0.5410, bbox_mAP_l: 0.6447, bbox_mAP_copypaste: 0.5025 0.7183 0.5501 0.3374 0.5410 0.6447, segm_mAP: 0.4469, segm_mAP_50: 0.6888, segm_mAP_75: 0.4813, segm_mAP_s: 0.2497, segm_mAP_m: 0.4772, segm_mAP_l: 0.6342, segm_mAP_copypaste: 0.4469 0.6888 0.4813 0.2497 0.4772 0.6342 2023-11-16 09:00:50,042 - mmdet - INFO - Epoch [31][50/1833] lr: 2.000e-05, eta: 3:36:20, time: 1.260, data_time: 0.144, memory: 16000, loss_rpn_cls: 0.0165, loss_rpn_bbox: 0.0271, loss_cls: 0.1261, acc: 95.2753, loss_bbox: 0.1755, loss_mask: 0.2001, loss: 0.5453 2023-11-16 09:01:49,378 - mmdet - INFO - Epoch [31][100/1833] lr: 2.000e-05, eta: 3:35:20, time: 1.187, data_time: 0.076, memory: 16000, loss_rpn_cls: 0.0161, loss_rpn_bbox: 0.0270, loss_cls: 0.1253, acc: 95.2749, loss_bbox: 0.1751, loss_mask: 0.2006, loss: 0.5442 2023-11-16 09:02:50,299 - mmdet - INFO - Epoch [31][150/1833] lr: 2.000e-05, eta: 3:34:21, time: 1.218, data_time: 0.077, memory: 16000, loss_rpn_cls: 0.0167, loss_rpn_bbox: 0.0271, loss_cls: 0.1300, acc: 95.0939, loss_bbox: 0.1799, loss_mask: 0.2016, loss: 0.5553 2023-11-16 09:03:50,306 - mmdet - INFO - Epoch [31][200/1833] lr: 2.000e-05, eta: 3:33:22, time: 1.200, data_time: 0.090, memory: 16000, loss_rpn_cls: 0.0169, loss_rpn_bbox: 0.0278, loss_cls: 0.1291, acc: 95.1679, loss_bbox: 0.1785, loss_mask: 0.2002, loss: 0.5525 2023-11-16 09:04:51,493 - mmdet - INFO - Epoch [31][250/1833] lr: 2.000e-05, eta: 3:32:23, time: 1.224, data_time: 0.078, memory: 16000, loss_rpn_cls: 0.0174, loss_rpn_bbox: 0.0284, loss_cls: 0.1308, acc: 95.0878, loss_bbox: 0.1807, loss_mask: 0.2022, loss: 0.5594 2023-11-16 09:05:51,099 - mmdet - INFO - Epoch [31][300/1833] lr: 2.000e-05, eta: 3:31:24, time: 1.192, data_time: 0.078, memory: 16000, loss_rpn_cls: 0.0169, loss_rpn_bbox: 0.0282, loss_cls: 0.1289, acc: 95.1549, loss_bbox: 0.1785, loss_mask: 0.2003, loss: 0.5528 2023-11-16 09:06:51,098 - mmdet - INFO - Epoch [31][350/1833] lr: 2.000e-05, eta: 3:30:25, time: 1.200, data_time: 0.084, memory: 16000, loss_rpn_cls: 0.0165, loss_rpn_bbox: 0.0274, loss_cls: 0.1290, acc: 95.1440, loss_bbox: 0.1783, loss_mask: 0.1995, loss: 0.5507 2023-11-16 09:07:51,505 - mmdet - INFO - Epoch [31][400/1833] lr: 2.000e-05, eta: 3:29:26, time: 1.208, data_time: 0.079, memory: 16000, loss_rpn_cls: 0.0173, loss_rpn_bbox: 0.0276, loss_cls: 0.1294, acc: 95.1190, loss_bbox: 0.1800, loss_mask: 0.2004, loss: 0.5547 2023-11-16 09:08:51,509 - mmdet - INFO - Epoch [31][450/1833] lr: 2.000e-05, eta: 3:28:27, time: 1.200, data_time: 0.078, memory: 16000, loss_rpn_cls: 0.0153, loss_rpn_bbox: 0.0265, loss_cls: 0.1273, acc: 95.2055, loss_bbox: 0.1759, loss_mask: 0.1978, loss: 0.5428 2023-11-16 09:09:50,660 - mmdet - INFO - Epoch [31][500/1833] lr: 2.000e-05, eta: 3:27:27, time: 1.183, data_time: 0.076, memory: 16000, loss_rpn_cls: 0.0176, loss_rpn_bbox: 0.0280, loss_cls: 0.1315, acc: 95.0699, loss_bbox: 0.1812, loss_mask: 0.2002, loss: 0.5585 2023-11-16 09:10:51,040 - mmdet - INFO - Epoch [31][550/1833] lr: 2.000e-05, eta: 3:26:28, time: 1.208, data_time: 0.074, memory: 16000, loss_rpn_cls: 0.0167, loss_rpn_bbox: 0.0277, loss_cls: 0.1290, acc: 95.0960, loss_bbox: 0.1812, loss_mask: 0.2007, loss: 0.5554 2023-11-16 09:11:50,884 - mmdet - INFO - Epoch [31][600/1833] lr: 2.000e-05, eta: 3:25:29, time: 1.197, data_time: 0.081, memory: 16000, loss_rpn_cls: 0.0167, loss_rpn_bbox: 0.0282, loss_cls: 0.1295, acc: 95.0646, loss_bbox: 0.1805, loss_mask: 0.2017, loss: 0.5567 2023-11-16 09:12:50,862 - mmdet - INFO - Epoch [31][650/1833] lr: 2.000e-05, eta: 3:24:30, time: 1.200, data_time: 0.079, memory: 16000, loss_rpn_cls: 0.0173, loss_rpn_bbox: 0.0288, loss_cls: 0.1317, acc: 94.9924, loss_bbox: 0.1827, loss_mask: 0.2032, loss: 0.5636 2023-11-16 09:13:50,243 - mmdet - INFO - Epoch [31][700/1833] lr: 2.000e-05, eta: 3:23:31, time: 1.188, data_time: 0.077, memory: 16000, loss_rpn_cls: 0.0171, loss_rpn_bbox: 0.0283, loss_cls: 0.1317, acc: 95.0201, loss_bbox: 0.1816, loss_mask: 0.2010, loss: 0.5597 2023-11-16 09:14:50,308 - mmdet - INFO - Epoch [31][750/1833] lr: 2.000e-05, eta: 3:22:32, time: 1.201, data_time: 0.073, memory: 16000, loss_rpn_cls: 0.0168, loss_rpn_bbox: 0.0280, loss_cls: 0.1315, acc: 95.0673, loss_bbox: 0.1807, loss_mask: 0.2019, loss: 0.5589 2023-11-16 09:15:51,030 - mmdet - INFO - Epoch [31][800/1833] lr: 2.000e-05, eta: 3:21:33, time: 1.215, data_time: 0.078, memory: 16000, loss_rpn_cls: 0.0165, loss_rpn_bbox: 0.0273, loss_cls: 0.1264, acc: 95.2064, loss_bbox: 0.1760, loss_mask: 0.1993, loss: 0.5455 2023-11-16 09:16:51,407 - mmdet - INFO - Epoch [31][850/1833] lr: 2.000e-05, eta: 3:20:33, time: 1.207, data_time: 0.077, memory: 16000, loss_rpn_cls: 0.0174, loss_rpn_bbox: 0.0281, loss_cls: 0.1302, acc: 95.1064, loss_bbox: 0.1782, loss_mask: 0.2006, loss: 0.5545 2023-11-16 09:17:50,769 - mmdet - INFO - Epoch [31][900/1833] lr: 2.000e-05, eta: 3:19:34, time: 1.187, data_time: 0.086, memory: 16000, loss_rpn_cls: 0.0162, loss_rpn_bbox: 0.0274, loss_cls: 0.1271, acc: 95.2095, loss_bbox: 0.1778, loss_mask: 0.2006, loss: 0.5490 2023-11-16 09:18:51,851 - mmdet - INFO - Epoch [31][950/1833] lr: 2.000e-05, eta: 3:18:35, time: 1.222, data_time: 0.083, memory: 16000, loss_rpn_cls: 0.0167, loss_rpn_bbox: 0.0285, loss_cls: 0.1307, acc: 95.0703, loss_bbox: 0.1780, loss_mask: 0.2034, loss: 0.5574 2023-11-16 09:19:51,086 - mmdet - INFO - Epoch [31][1000/1833] lr: 2.000e-05, eta: 3:17:36, time: 1.185, data_time: 0.082, memory: 16000, loss_rpn_cls: 0.0171, loss_rpn_bbox: 0.0279, loss_cls: 0.1295, acc: 95.0773, loss_bbox: 0.1810, loss_mask: 0.1991, loss: 0.5546 2023-11-16 09:20:51,279 - mmdet - INFO - Epoch [31][1050/1833] lr: 2.000e-05, eta: 3:16:37, time: 1.204, data_time: 0.067, memory: 16000, loss_rpn_cls: 0.0174, loss_rpn_bbox: 0.0277, loss_cls: 0.1286, acc: 95.1531, loss_bbox: 0.1765, loss_mask: 0.2017, loss: 0.5519 2023-11-16 09:21:51,048 - mmdet - INFO - Epoch [31][1100/1833] lr: 2.000e-05, eta: 3:15:38, time: 1.195, data_time: 0.077, memory: 16000, loss_rpn_cls: 0.0161, loss_rpn_bbox: 0.0277, loss_cls: 0.1285, acc: 95.1607, loss_bbox: 0.1787, loss_mask: 0.1998, loss: 0.5508 2023-11-16 09:22:51,559 - mmdet - INFO - Epoch [31][1150/1833] lr: 2.000e-05, eta: 3:14:38, time: 1.210, data_time: 0.080, memory: 16000, loss_rpn_cls: 0.0167, loss_rpn_bbox: 0.0273, loss_cls: 0.1294, acc: 95.1443, loss_bbox: 0.1778, loss_mask: 0.2006, loss: 0.5519 2023-11-16 09:23:51,946 - mmdet - INFO - Epoch [31][1200/1833] lr: 2.000e-05, eta: 3:13:39, time: 1.208, data_time: 0.085, memory: 16000, loss_rpn_cls: 0.0179, loss_rpn_bbox: 0.0288, loss_cls: 0.1307, acc: 95.1040, loss_bbox: 0.1790, loss_mask: 0.2007, loss: 0.5570 2023-11-16 09:24:52,674 - mmdet - INFO - Epoch [31][1250/1833] lr: 2.000e-05, eta: 3:12:40, time: 1.215, data_time: 0.078, memory: 16000, loss_rpn_cls: 0.0170, loss_rpn_bbox: 0.0279, loss_cls: 0.1310, acc: 95.0719, loss_bbox: 0.1794, loss_mask: 0.2013, loss: 0.5566 2023-11-16 09:25:51,743 - mmdet - INFO - Epoch [31][1300/1833] lr: 2.000e-05, eta: 3:11:41, time: 1.181, data_time: 0.081, memory: 16000, loss_rpn_cls: 0.0157, loss_rpn_bbox: 0.0275, loss_cls: 0.1261, acc: 95.2654, loss_bbox: 0.1766, loss_mask: 0.2010, loss: 0.5468 2023-11-16 09:26:52,067 - mmdet - INFO - Epoch [31][1350/1833] lr: 2.000e-05, eta: 3:10:42, time: 1.207, data_time: 0.078, memory: 16000, loss_rpn_cls: 0.0172, loss_rpn_bbox: 0.0279, loss_cls: 0.1302, acc: 95.1199, loss_bbox: 0.1792, loss_mask: 0.1989, loss: 0.5533 2023-11-16 09:27:50,836 - mmdet - INFO - Epoch [31][1400/1833] lr: 2.000e-05, eta: 3:09:42, time: 1.175, data_time: 0.074, memory: 16000, loss_rpn_cls: 0.0161, loss_rpn_bbox: 0.0278, loss_cls: 0.1283, acc: 95.1451, loss_bbox: 0.1781, loss_mask: 0.2009, loss: 0.5512 2023-11-16 09:28:50,587 - mmdet - INFO - Epoch [31][1450/1833] lr: 2.000e-05, eta: 3:08:43, time: 1.195, data_time: 0.082, memory: 16000, loss_rpn_cls: 0.0170, loss_rpn_bbox: 0.0274, loss_cls: 0.1296, acc: 95.1187, loss_bbox: 0.1778, loss_mask: 0.2007, loss: 0.5525 2023-11-16 09:29:50,219 - mmdet - INFO - Epoch [31][1500/1833] lr: 2.000e-05, eta: 3:07:44, time: 1.193, data_time: 0.073, memory: 16000, loss_rpn_cls: 0.0162, loss_rpn_bbox: 0.0266, loss_cls: 0.1281, acc: 95.1802, loss_bbox: 0.1773, loss_mask: 0.2017, loss: 0.5500 2023-11-16 09:30:48,984 - mmdet - INFO - Epoch [31][1550/1833] lr: 2.000e-05, eta: 3:06:45, time: 1.175, data_time: 0.078, memory: 16000, loss_rpn_cls: 0.0160, loss_rpn_bbox: 0.0268, loss_cls: 0.1266, acc: 95.2293, loss_bbox: 0.1760, loss_mask: 0.1976, loss: 0.5430 2023-11-16 09:31:50,708 - mmdet - INFO - Epoch [31][1600/1833] lr: 2.000e-05, eta: 3:05:46, time: 1.234, data_time: 0.080, memory: 16000, loss_rpn_cls: 0.0171, loss_rpn_bbox: 0.0285, loss_cls: 0.1288, acc: 95.1062, loss_bbox: 0.1799, loss_mask: 0.2013, loss: 0.5556 2023-11-16 09:32:51,070 - mmdet - INFO - Epoch [31][1650/1833] lr: 2.000e-05, eta: 3:04:47, time: 1.207, data_time: 0.076, memory: 16000, loss_rpn_cls: 0.0162, loss_rpn_bbox: 0.0266, loss_cls: 0.1279, acc: 95.1355, loss_bbox: 0.1771, loss_mask: 0.1977, loss: 0.5455 2023-11-16 09:33:50,283 - mmdet - INFO - Epoch [31][1700/1833] lr: 2.000e-05, eta: 3:03:47, time: 1.184, data_time: 0.076, memory: 16000, loss_rpn_cls: 0.0162, loss_rpn_bbox: 0.0274, loss_cls: 0.1266, acc: 95.2148, loss_bbox: 0.1766, loss_mask: 0.1987, loss: 0.5456 2023-11-16 09:34:50,849 - mmdet - INFO - Epoch [31][1750/1833] lr: 2.000e-05, eta: 3:02:48, time: 1.211, data_time: 0.076, memory: 16000, loss_rpn_cls: 0.0163, loss_rpn_bbox: 0.0272, loss_cls: 0.1263, acc: 95.2304, loss_bbox: 0.1759, loss_mask: 0.1984, loss: 0.5441 2023-11-16 09:35:51,171 - mmdet - INFO - Epoch [31][1800/1833] lr: 2.000e-05, eta: 3:01:49, time: 1.206, data_time: 0.073, memory: 16000, loss_rpn_cls: 0.0167, loss_rpn_bbox: 0.0281, loss_cls: 0.1302, acc: 95.1189, loss_bbox: 0.1772, loss_mask: 0.2013, loss: 0.5535 2023-11-16 09:36:31,814 - mmdet - INFO - Saving checkpoint at 31 epochs 2023-11-16 09:37:17,295 - mmdet - INFO - Evaluating bbox... 2023-11-16 09:37:44,167 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.503 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.718 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.550 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.345 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.541 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 ] = 0.459 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 ] = 0.769 2023-11-16 09:37:44,170 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.599 | bicycle | 0.407 | car | 0.505 | | motorcycle | 0.506 | airplane | 0.720 | bus | 0.739 | | train | 0.705 | truck | 0.458 | boat | 0.344 | | traffic light | 0.314 | fire hydrant | 0.756 | stop sign | 0.696 | | parking meter | 0.545 | bench | 0.330 | bird | 0.432 | | cat | 0.739 | dog | 0.709 | horse | 0.659 | | sheep | 0.623 | cow | 0.640 | elephant | 0.723 | | bear | 0.760 | zebra | 0.686 | giraffe | 0.725 | | backpack | 0.234 | umbrella | 0.479 | handbag | 0.265 | | tie | 0.424 | suitcase | 0.499 | frisbee | 0.736 | | skis | 0.322 | snowboard | 0.464 | sports ball | 0.494 | | kite | 0.486 | baseball bat | 0.428 | baseball glove | 0.454 | | skateboard | 0.616 | surfboard | 0.477 | tennis racket | 0.582 | | bottle | 0.479 | wine glass | 0.430 | cup | 0.516 | | fork | 0.508 | knife | 0.311 | spoon | 0.337 | | bowl | 0.494 | banana | 0.283 | apple | 0.283 | | sandwich | 0.478 | orange | 0.360 | broccoli | 0.256 | | carrot | 0.275 | hot dog | 0.461 | pizza | 0.577 | | donut | 0.565 | cake | 0.454 | chair | 0.384 | | couch | 0.507 | potted plant | 0.378 | bed | 0.468 | | dining table | 0.333 | toilet | 0.678 | tv | 0.646 | | laptop | 0.704 | mouse | 0.668 | remote | 0.456 | | keyboard | 0.570 | cell phone | 0.477 | microwave | 0.693 | | oven | 0.436 | toaster | 0.499 | sink | 0.458 | | refrigerator | 0.689 | book | 0.215 | clock | 0.521 | | vase | 0.449 | scissors | 0.475 | teddy bear | 0.563 | | hair drier | 0.264 | toothbrush | 0.361 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-16 09:37:44,170 - mmdet - INFO - Evaluating segm... 2023-11-16 09:38:15,486 - 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 ] = 0.688 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.483 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 ] = 0.478 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 ] = 0.558 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.558 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.558 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 ] = 0.594 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.715 2023-11-16 09:38:15,489 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.520 | bicycle | 0.256 | car | 0.464 | | motorcycle | 0.422 | airplane | 0.540 | bus | 0.709 | | train | 0.684 | truck | 0.432 | boat | 0.317 | | traffic light | 0.302 | fire hydrant | 0.719 | stop sign | 0.678 | | parking meter | 0.550 | bench | 0.251 | bird | 0.362 | | cat | 0.730 | dog | 0.670 | horse | 0.487 | | sheep | 0.553 | cow | 0.540 | elephant | 0.648 | | bear | 0.738 | zebra | 0.603 | giraffe | 0.563 | | backpack | 0.227 | umbrella | 0.530 | handbag | 0.236 | | tie | 0.393 | suitcase | 0.517 | frisbee | 0.681 | | skis | 0.073 | snowboard | 0.307 | sports ball | 0.475 | | kite | 0.340 | baseball bat | 0.315 | baseball glove | 0.462 | | skateboard | 0.393 | surfboard | 0.389 | tennis racket | 0.616 | | bottle | 0.452 | wine glass | 0.395 | cup | 0.509 | | fork | 0.264 | knife | 0.213 | spoon | 0.240 | | bowl | 0.456 | banana | 0.226 | apple | 0.279 | | sandwich | 0.494 | orange | 0.358 | broccoli | 0.237 | | carrot | 0.240 | hot dog | 0.387 | pizza | 0.553 | | donut | 0.563 | cake | 0.459 | chair | 0.274 | | couch | 0.428 | potted plant | 0.309 | bed | 0.377 | | dining table | 0.200 | toilet | 0.646 | tv | 0.665 | | laptop | 0.683 | mouse | 0.641 | remote | 0.407 | | keyboard | 0.550 | cell phone | 0.442 | microwave | 0.685 | | oven | 0.390 | toaster | 0.539 | sink | 0.423 | | refrigerator | 0.679 | book | 0.157 | clock | 0.515 | | vase | 0.443 | scissors | 0.337 | teddy bear | 0.533 | | hair drier | 0.183 | toothbrush | 0.269 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-16 09:38:15,984 - mmdet - INFO - The previous best checkpoint /mnt/petrelfs/lizhiqi/DINO/detection/work_dirs/mask_rcnn_flash_internimage_s_fpn_3x_coco_0.4/best_bbox_mAP_epoch_30.pth was removed 2023-11-16 09:38:17,990 - mmdet - INFO - Now best checkpoint is saved as best_bbox_mAP_epoch_31.pth. 2023-11-16 09:38:17,991 - mmdet - INFO - Best bbox_mAP is 0.5030 at 31 epoch. 2023-11-16 09:38:17,991 - mmdet - INFO - Exp name: mask_rcnn_flash_internimage_s_fpn_3x_coco_0.4.py 2023-11-16 09:38:17,991 - mmdet - INFO - Epoch(val) [31][625] bbox_mAP: 0.5030, bbox_mAP_50: 0.7183, bbox_mAP_75: 0.5497, bbox_mAP_s: 0.3454, bbox_mAP_m: 0.5408, bbox_mAP_l: 0.6473, bbox_mAP_copypaste: 0.5030 0.7183 0.5497 0.3454 0.5408 0.6473, segm_mAP: 0.4474, segm_mAP_50: 0.6881, segm_mAP_75: 0.4832, segm_mAP_s: 0.2608, segm_mAP_m: 0.4785, segm_mAP_l: 0.6336, segm_mAP_copypaste: 0.4474 0.6881 0.4832 0.2608 0.4785 0.6336 2023-11-16 09:39:21,760 - mmdet - INFO - Epoch [32][50/1833] lr: 2.000e-05, eta: 3:00:05, time: 1.275, data_time: 0.126, memory: 16000, loss_rpn_cls: 0.0166, loss_rpn_bbox: 0.0278, loss_cls: 0.1272, acc: 95.1971, loss_bbox: 0.1769, loss_mask: 0.1974, loss: 0.5459 2023-11-16 09:40:21,528 - mmdet - INFO - Epoch [32][100/1833] lr: 2.000e-05, eta: 2:59:06, time: 1.195, data_time: 0.071, memory: 16000, loss_rpn_cls: 0.0176, loss_rpn_bbox: 0.0279, loss_cls: 0.1270, acc: 95.2000, loss_bbox: 0.1769, loss_mask: 0.2000, loss: 0.5494 2023-11-16 09:41:22,006 - mmdet - INFO - Epoch [32][150/1833] lr: 2.000e-05, eta: 2:58:07, time: 1.210, data_time: 0.067, memory: 16000, loss_rpn_cls: 0.0166, loss_rpn_bbox: 0.0273, loss_cls: 0.1261, acc: 95.2350, loss_bbox: 0.1747, loss_mask: 0.1993, loss: 0.5440 2023-11-16 09:42:23,008 - mmdet - INFO - Epoch [32][200/1833] lr: 2.000e-05, eta: 2:57:08, time: 1.220, data_time: 0.060, memory: 16000, loss_rpn_cls: 0.0163, loss_rpn_bbox: 0.0265, loss_cls: 0.1261, acc: 95.2173, loss_bbox: 0.1758, loss_mask: 0.1991, loss: 0.5439 2023-11-16 09:43:24,133 - mmdet - INFO - Epoch [32][250/1833] lr: 2.000e-05, eta: 2:56:09, time: 1.222, data_time: 0.070, memory: 16000, loss_rpn_cls: 0.0166, loss_rpn_bbox: 0.0278, loss_cls: 0.1301, acc: 95.0993, loss_bbox: 0.1780, loss_mask: 0.1984, loss: 0.5510 2023-11-16 09:44:25,662 - mmdet - INFO - Epoch [32][300/1833] lr: 2.000e-05, eta: 2:55:10, time: 1.231, data_time: 0.073, memory: 16000, loss_rpn_cls: 0.0170, loss_rpn_bbox: 0.0277, loss_cls: 0.1291, acc: 95.1372, loss_bbox: 0.1790, loss_mask: 0.1999, loss: 0.5526 2023-11-16 09:45:25,931 - mmdet - INFO - Epoch [32][350/1833] lr: 2.000e-05, eta: 2:54:11, time: 1.205, data_time: 0.069, memory: 16000, loss_rpn_cls: 0.0160, loss_rpn_bbox: 0.0266, loss_cls: 0.1263, acc: 95.1922, loss_bbox: 0.1764, loss_mask: 0.1983, loss: 0.5436 2023-11-16 09:46:26,338 - mmdet - INFO - Epoch [32][400/1833] lr: 2.000e-05, eta: 2:53:12, time: 1.208, data_time: 0.074, memory: 16000, loss_rpn_cls: 0.0165, loss_rpn_bbox: 0.0274, loss_cls: 0.1278, acc: 95.2099, loss_bbox: 0.1766, loss_mask: 0.1999, loss: 0.5482 2023-11-16 09:47:28,170 - mmdet - INFO - Epoch [32][450/1833] lr: 2.000e-05, eta: 2:52:13, time: 1.237, data_time: 0.078, memory: 16000, loss_rpn_cls: 0.0166, loss_rpn_bbox: 0.0280, loss_cls: 0.1292, acc: 95.1111, loss_bbox: 0.1809, loss_mask: 0.1994, loss: 0.5541 2023-11-16 09:48:27,793 - mmdet - INFO - Epoch [32][500/1833] lr: 2.000e-05, eta: 2:51:13, time: 1.193, data_time: 0.065, memory: 16000, loss_rpn_cls: 0.0165, loss_rpn_bbox: 0.0280, loss_cls: 0.1284, acc: 95.1675, loss_bbox: 0.1774, loss_mask: 0.2014, loss: 0.5517 2023-11-16 09:49:27,584 - mmdet - INFO - Epoch [32][550/1833] lr: 2.000e-05, eta: 2:50:14, time: 1.196, data_time: 0.069, memory: 16000, loss_rpn_cls: 0.0163, loss_rpn_bbox: 0.0274, loss_cls: 0.1268, acc: 95.2294, loss_bbox: 0.1764, loss_mask: 0.1997, loss: 0.5466 2023-11-16 09:50:27,755 - mmdet - INFO - Epoch [32][600/1833] lr: 2.000e-05, eta: 2:49:15, time: 1.203, data_time: 0.072, memory: 16000, loss_rpn_cls: 0.0183, loss_rpn_bbox: 0.0274, loss_cls: 0.1282, acc: 95.1830, loss_bbox: 0.1774, loss_mask: 0.1999, loss: 0.5512 2023-11-16 09:51:27,193 - mmdet - INFO - Epoch [32][650/1833] lr: 2.000e-05, eta: 2:48:16, time: 1.189, data_time: 0.072, memory: 16000, loss_rpn_cls: 0.0161, loss_rpn_bbox: 0.0270, loss_cls: 0.1252, acc: 95.2554, loss_bbox: 0.1749, loss_mask: 0.1999, loss: 0.5431 2023-11-16 09:52:28,505 - mmdet - INFO - Epoch [32][700/1833] lr: 2.000e-05, eta: 2:47:17, time: 1.226, data_time: 0.067, memory: 16000, loss_rpn_cls: 0.0155, loss_rpn_bbox: 0.0268, loss_cls: 0.1256, acc: 95.2501, loss_bbox: 0.1766, loss_mask: 0.1982, loss: 0.5427 2023-11-16 09:53:28,471 - mmdet - INFO - Epoch [32][750/1833] lr: 2.000e-05, eta: 2:46:18, time: 1.199, data_time: 0.063, memory: 16000, loss_rpn_cls: 0.0160, loss_rpn_bbox: 0.0272, loss_cls: 0.1253, acc: 95.2592, loss_bbox: 0.1776, loss_mask: 0.2009, loss: 0.5471 2023-11-16 09:54:28,253 - mmdet - INFO - Epoch [32][800/1833] lr: 2.000e-05, eta: 2:45:18, time: 1.196, data_time: 0.067, memory: 16000, loss_rpn_cls: 0.0158, loss_rpn_bbox: 0.0269, loss_cls: 0.1263, acc: 95.2282, loss_bbox: 0.1728, loss_mask: 0.1957, loss: 0.5375 2023-11-16 09:55:28,928 - mmdet - INFO - Epoch [32][850/1833] lr: 2.000e-05, eta: 2:44:19, time: 1.213, data_time: 0.069, memory: 16000, loss_rpn_cls: 0.0157, loss_rpn_bbox: 0.0270, loss_cls: 0.1275, acc: 95.1932, loss_bbox: 0.1758, loss_mask: 0.1998, loss: 0.5458 2023-11-16 09:56:28,851 - mmdet - INFO - Epoch [32][900/1833] lr: 2.000e-05, eta: 2:43:20, time: 1.198, data_time: 0.070, memory: 16000, loss_rpn_cls: 0.0166, loss_rpn_bbox: 0.0279, loss_cls: 0.1288, acc: 95.1102, loss_bbox: 0.1805, loss_mask: 0.1995, loss: 0.5534 2023-11-16 09:57:29,178 - mmdet - INFO - Epoch [32][950/1833] lr: 2.000e-05, eta: 2:42:21, time: 1.206, data_time: 0.076, memory: 16000, loss_rpn_cls: 0.0171, loss_rpn_bbox: 0.0280, loss_cls: 0.1295, acc: 95.0998, loss_bbox: 0.1797, loss_mask: 0.2011, loss: 0.5553 2023-11-16 09:58:29,301 - mmdet - INFO - Epoch [32][1000/1833] lr: 2.000e-05, eta: 2:41:22, time: 1.202, data_time: 0.067, memory: 16000, loss_rpn_cls: 0.0168, loss_rpn_bbox: 0.0274, loss_cls: 0.1262, acc: 95.2772, loss_bbox: 0.1754, loss_mask: 0.1982, loss: 0.5441 2023-11-16 09:59:30,256 - mmdet - INFO - Epoch [32][1050/1833] lr: 2.000e-05, eta: 2:40:23, time: 1.219, data_time: 0.062, memory: 16000, loss_rpn_cls: 0.0160, loss_rpn_bbox: 0.0274, loss_cls: 0.1270, acc: 95.1780, loss_bbox: 0.1768, loss_mask: 0.1997, loss: 0.5469 2023-11-16 10:00:30,428 - mmdet - INFO - Epoch [32][1100/1833] lr: 2.000e-05, eta: 2:39:24, time: 1.203, data_time: 0.068, memory: 16000, loss_rpn_cls: 0.0162, loss_rpn_bbox: 0.0274, loss_cls: 0.1275, acc: 95.1737, loss_bbox: 0.1777, loss_mask: 0.1999, loss: 0.5487 2023-11-16 10:01:31,769 - mmdet - INFO - Epoch [32][1150/1833] lr: 2.000e-05, eta: 2:38:25, time: 1.227, data_time: 0.063, memory: 16000, loss_rpn_cls: 0.0162, loss_rpn_bbox: 0.0275, loss_cls: 0.1276, acc: 95.1515, loss_bbox: 0.1778, loss_mask: 0.2006, loss: 0.5497 2023-11-16 10:02:32,032 - mmdet - INFO - Epoch [32][1200/1833] lr: 2.000e-05, eta: 2:37:25, time: 1.205, data_time: 0.067, memory: 16000, loss_rpn_cls: 0.0173, loss_rpn_bbox: 0.0284, loss_cls: 0.1305, acc: 95.0877, loss_bbox: 0.1810, loss_mask: 0.2022, loss: 0.5594 2023-11-16 10:03:34,608 - mmdet - INFO - Epoch [32][1250/1833] lr: 2.000e-05, eta: 2:36:27, time: 1.251, data_time: 0.079, memory: 16000, loss_rpn_cls: 0.0166, loss_rpn_bbox: 0.0286, loss_cls: 0.1315, acc: 95.0103, loss_bbox: 0.1833, loss_mask: 0.2019, loss: 0.5619 2023-11-16 10:04:36,854 - mmdet - INFO - Epoch [32][1300/1833] lr: 2.000e-05, eta: 2:35:28, time: 1.245, data_time: 0.079, memory: 16000, loss_rpn_cls: 0.0175, loss_rpn_bbox: 0.0291, loss_cls: 0.1302, acc: 95.0367, loss_bbox: 0.1801, loss_mask: 0.2014, loss: 0.5582 2023-11-16 10:05:37,449 - mmdet - INFO - Epoch [32][1350/1833] lr: 2.000e-05, eta: 2:34:29, time: 1.212, data_time: 0.069, memory: 16000, loss_rpn_cls: 0.0154, loss_rpn_bbox: 0.0268, loss_cls: 0.1259, acc: 95.2652, loss_bbox: 0.1748, loss_mask: 0.1980, loss: 0.5409 2023-11-16 10:06:37,641 - mmdet - INFO - Epoch [32][1400/1833] lr: 2.000e-05, eta: 2:33:29, time: 1.204, data_time: 0.062, memory: 16000, loss_rpn_cls: 0.0164, loss_rpn_bbox: 0.0278, loss_cls: 0.1274, acc: 95.2151, loss_bbox: 0.1774, loss_mask: 0.1991, loss: 0.5480 2023-11-16 10:07:37,329 - mmdet - INFO - Epoch [32][1450/1833] lr: 2.000e-05, eta: 2:32:30, time: 1.194, data_time: 0.070, memory: 16000, loss_rpn_cls: 0.0173, loss_rpn_bbox: 0.0277, loss_cls: 0.1268, acc: 95.2521, loss_bbox: 0.1738, loss_mask: 0.1982, loss: 0.5437 2023-11-16 10:08:37,343 - mmdet - INFO - Epoch [32][1500/1833] lr: 2.000e-05, eta: 2:31:31, time: 1.200, data_time: 0.062, memory: 16000, loss_rpn_cls: 0.0166, loss_rpn_bbox: 0.0274, loss_cls: 0.1293, acc: 95.1757, loss_bbox: 0.1798, loss_mask: 0.2029, loss: 0.5561 2023-11-16 10:09:37,801 - mmdet - INFO - Epoch [32][1550/1833] lr: 2.000e-05, eta: 2:30:32, time: 1.209, data_time: 0.066, memory: 16000, loss_rpn_cls: 0.0172, loss_rpn_bbox: 0.0279, loss_cls: 0.1321, acc: 95.0976, loss_bbox: 0.1794, loss_mask: 0.1995, loss: 0.5561 2023-11-16 10:10:41,924 - mmdet - INFO - Epoch [32][1600/1833] lr: 2.000e-05, eta: 2:29:33, time: 1.282, data_time: 0.071, memory: 16000, loss_rpn_cls: 0.0163, loss_rpn_bbox: 0.0275, loss_cls: 0.1263, acc: 95.2283, loss_bbox: 0.1760, loss_mask: 0.1978, loss: 0.5439 2023-11-16 10:11:42,402 - mmdet - INFO - Epoch [32][1650/1833] lr: 2.000e-05, eta: 2:28:34, time: 1.210, data_time: 0.072, memory: 16000, loss_rpn_cls: 0.0174, loss_rpn_bbox: 0.0285, loss_cls: 0.1324, acc: 95.0225, loss_bbox: 0.1799, loss_mask: 0.2005, loss: 0.5587 2023-11-16 10:12:41,429 - mmdet - INFO - Epoch [32][1700/1833] lr: 2.000e-05, eta: 2:27:35, time: 1.181, data_time: 0.069, memory: 16000, loss_rpn_cls: 0.0166, loss_rpn_bbox: 0.0276, loss_cls: 0.1272, acc: 95.1874, loss_bbox: 0.1796, loss_mask: 0.1990, loss: 0.5500 2023-11-16 10:13:41,962 - mmdet - INFO - Epoch [32][1750/1833] lr: 2.000e-05, eta: 2:26:35, time: 1.211, data_time: 0.070, memory: 16000, loss_rpn_cls: 0.0169, loss_rpn_bbox: 0.0274, loss_cls: 0.1281, acc: 95.2189, loss_bbox: 0.1764, loss_mask: 0.2003, loss: 0.5490 2023-11-16 10:14:41,989 - mmdet - INFO - Epoch [32][1800/1833] lr: 2.000e-05, eta: 2:25:36, time: 1.201, data_time: 0.059, memory: 16000, loss_rpn_cls: 0.0158, loss_rpn_bbox: 0.0270, loss_cls: 0.1277, acc: 95.2056, loss_bbox: 0.1748, loss_mask: 0.1984, loss: 0.5437 2023-11-16 10:15:22,021 - mmdet - INFO - Saving checkpoint at 32 epochs 2023-11-16 10:16:05,247 - mmdet - INFO - Evaluating bbox... 2023-11-16 10:16:32,836 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.503 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.719 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.551 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.342 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.542 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.645 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 ] = 0.460 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 ] = 0.768 2023-11-16 10:16:32,839 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.601 | bicycle | 0.399 | car | 0.507 | | motorcycle | 0.504 | airplane | 0.720 | bus | 0.744 | | train | 0.695 | truck | 0.459 | boat | 0.345 | | traffic light | 0.319 | fire hydrant | 0.750 | stop sign | 0.705 | | parking meter | 0.542 | bench | 0.332 | bird | 0.436 | | cat | 0.741 | dog | 0.712 | horse | 0.658 | | sheep | 0.624 | cow | 0.631 | elephant | 0.726 | | bear | 0.758 | zebra | 0.690 | giraffe | 0.729 | | backpack | 0.231 | umbrella | 0.478 | handbag | 0.266 | | tie | 0.439 | suitcase | 0.501 | frisbee | 0.730 | | skis | 0.326 | snowboard | 0.477 | sports ball | 0.493 | | kite | 0.487 | baseball bat | 0.427 | baseball glove | 0.456 | | skateboard | 0.617 | surfboard | 0.475 | tennis racket | 0.584 | | bottle | 0.477 | wine glass | 0.437 | cup | 0.517 | | fork | 0.511 | knife | 0.320 | spoon | 0.334 | | bowl | 0.495 | banana | 0.287 | apple | 0.291 | | sandwich | 0.484 | orange | 0.357 | broccoli | 0.244 | | carrot | 0.270 | hot dog | 0.467 | pizza | 0.576 | | donut | 0.564 | cake | 0.448 | chair | 0.378 | | couch | 0.514 | potted plant | 0.379 | bed | 0.479 | | dining table | 0.334 | toilet | 0.674 | tv | 0.639 | | laptop | 0.716 | mouse | 0.665 | remote | 0.450 | | keyboard | 0.577 | cell phone | 0.475 | microwave | 0.688 | | oven | 0.423 | toaster | 0.460 | sink | 0.458 | | refrigerator | 0.698 | book | 0.214 | clock | 0.515 | | vase | 0.447 | scissors | 0.480 | teddy bear | 0.564 | | hair drier | 0.257 | toothbrush | 0.365 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-16 10:16:32,839 - mmdet - INFO - Evaluating segm... 2023-11-16 10:17:00,728 - 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 ] = 0.688 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.481 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.254 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 ] = 0.635 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 ] = 0.394 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.597 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.715 2023-11-16 10:17:00,730 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.521 | bicycle | 0.252 | car | 0.467 | | motorcycle | 0.420 | airplane | 0.544 | bus | 0.717 | | train | 0.686 | truck | 0.437 | boat | 0.306 | | traffic light | 0.305 | fire hydrant | 0.717 | stop sign | 0.680 | | parking meter | 0.544 | bench | 0.253 | bird | 0.366 | | cat | 0.733 | dog | 0.668 | horse | 0.490 | | sheep | 0.549 | cow | 0.534 | elephant | 0.655 | | bear | 0.740 | zebra | 0.600 | giraffe | 0.562 | | backpack | 0.231 | umbrella | 0.527 | handbag | 0.237 | | tie | 0.396 | suitcase | 0.516 | frisbee | 0.682 | | skis | 0.075 | snowboard | 0.309 | sports ball | 0.476 | | kite | 0.345 | baseball bat | 0.314 | baseball glove | 0.459 | | skateboard | 0.397 | surfboard | 0.386 | tennis racket | 0.617 | | bottle | 0.449 | wine glass | 0.393 | cup | 0.512 | | fork | 0.266 | knife | 0.222 | spoon | 0.239 | | bowl | 0.455 | banana | 0.237 | apple | 0.282 | | sandwich | 0.503 | orange | 0.355 | broccoli | 0.229 | | carrot | 0.237 | hot dog | 0.383 | pizza | 0.556 | | donut | 0.559 | cake | 0.453 | chair | 0.271 | | couch | 0.439 | potted plant | 0.307 | bed | 0.381 | | dining table | 0.199 | toilet | 0.649 | tv | 0.667 | | laptop | 0.685 | mouse | 0.641 | remote | 0.405 | | keyboard | 0.557 | cell phone | 0.439 | microwave | 0.694 | | oven | 0.392 | toaster | 0.513 | sink | 0.424 | | refrigerator | 0.685 | book | 0.159 | clock | 0.512 | | vase | 0.440 | scissors | 0.337 | teddy bear | 0.526 | | hair drier | 0.185 | toothbrush | 0.243 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-16 10:17:01,078 - mmdet - INFO - Exp name: mask_rcnn_flash_internimage_s_fpn_3x_coco_0.4.py 2023-11-16 10:17:01,078 - mmdet - INFO - Epoch(val) [32][625] bbox_mAP: 0.5030, bbox_mAP_50: 0.7195, bbox_mAP_75: 0.5505, bbox_mAP_s: 0.3420, bbox_mAP_m: 0.5418, bbox_mAP_l: 0.6448, bbox_mAP_copypaste: 0.5030 0.7195 0.5505 0.3420 0.5418 0.6448, segm_mAP: 0.4474, segm_mAP_50: 0.6878, segm_mAP_75: 0.4812, segm_mAP_s: 0.2537, segm_mAP_m: 0.4797, segm_mAP_l: 0.6354, segm_mAP_copypaste: 0.4474 0.6878 0.4812 0.2537 0.4797 0.6354 2023-11-16 10:18:06,223 - mmdet - INFO - Epoch [33][50/1833] lr: 2.000e-05, eta: 2:23:54, time: 1.302, data_time: 0.143, memory: 16000, loss_rpn_cls: 0.0161, loss_rpn_bbox: 0.0269, loss_cls: 0.1289, acc: 95.1373, loss_bbox: 0.1795, loss_mask: 0.2003, loss: 0.5516 2023-11-16 10:19:07,051 - mmdet - INFO - Epoch [33][100/1833] lr: 2.000e-05, eta: 2:22:54, time: 1.217, data_time: 0.072, memory: 16000, loss_rpn_cls: 0.0157, loss_rpn_bbox: 0.0270, loss_cls: 0.1282, acc: 95.1616, loss_bbox: 0.1784, loss_mask: 0.2001, loss: 0.5495 2023-11-16 10:20:07,581 - mmdet - INFO - Epoch [33][150/1833] lr: 2.000e-05, eta: 2:21:55, time: 1.210, data_time: 0.083, memory: 16000, loss_rpn_cls: 0.0169, loss_rpn_bbox: 0.0279, loss_cls: 0.1283, acc: 95.1564, loss_bbox: 0.1756, loss_mask: 0.1981, loss: 0.5468 2023-11-16 10:21:08,819 - mmdet - INFO - Epoch [33][200/1833] lr: 2.000e-05, eta: 2:20:56, time: 1.225, data_time: 0.083, memory: 16000, loss_rpn_cls: 0.0175, loss_rpn_bbox: 0.0288, loss_cls: 0.1315, acc: 95.0513, loss_bbox: 0.1820, loss_mask: 0.2018, loss: 0.5615 2023-11-16 10:22:08,870 - mmdet - INFO - Epoch [33][250/1833] lr: 2.000e-05, eta: 2:19:57, time: 1.201, data_time: 0.074, memory: 16000, loss_rpn_cls: 0.0151, loss_rpn_bbox: 0.0261, loss_cls: 0.1251, acc: 95.3218, loss_bbox: 0.1734, loss_mask: 0.1984, loss: 0.5381 2023-11-16 10:23:09,993 - mmdet - INFO - Epoch [33][300/1833] lr: 2.000e-05, eta: 2:18:58, time: 1.222, data_time: 0.079, memory: 16000, loss_rpn_cls: 0.0165, loss_rpn_bbox: 0.0272, loss_cls: 0.1263, acc: 95.2342, loss_bbox: 0.1762, loss_mask: 0.1986, loss: 0.5447 2023-11-16 10:24:10,370 - mmdet - INFO - Epoch [33][350/1833] lr: 2.000e-05, eta: 2:17:59, time: 1.208, data_time: 0.079, memory: 16000, loss_rpn_cls: 0.0159, loss_rpn_bbox: 0.0275, loss_cls: 0.1260, acc: 95.2407, loss_bbox: 0.1763, loss_mask: 0.2013, loss: 0.5470 2023-11-16 10:25:09,898 - mmdet - INFO - Epoch [33][400/1833] lr: 2.000e-05, eta: 2:17:00, time: 1.190, data_time: 0.083, memory: 16000, loss_rpn_cls: 0.0169, loss_rpn_bbox: 0.0277, loss_cls: 0.1287, acc: 95.1356, loss_bbox: 0.1788, loss_mask: 0.1996, loss: 0.5516 2023-11-16 10:26:09,346 - mmdet - INFO - Epoch [33][450/1833] lr: 2.000e-05, eta: 2:16:00, time: 1.189, data_time: 0.076, memory: 16000, loss_rpn_cls: 0.0160, loss_rpn_bbox: 0.0267, loss_cls: 0.1273, acc: 95.2051, loss_bbox: 0.1767, loss_mask: 0.2000, loss: 0.5467 2023-11-16 10:27:08,415 - mmdet - INFO - Epoch [33][500/1833] lr: 2.000e-05, eta: 2:15:01, time: 1.181, data_time: 0.088, memory: 16000, loss_rpn_cls: 0.0161, loss_rpn_bbox: 0.0273, loss_cls: 0.1257, acc: 95.2619, loss_bbox: 0.1755, loss_mask: 0.2000, loss: 0.5447 2023-11-16 10:28:09,014 - mmdet - INFO - Epoch [33][550/1833] lr: 2.000e-05, eta: 2:14:02, time: 1.212, data_time: 0.073, memory: 16000, loss_rpn_cls: 0.0171, loss_rpn_bbox: 0.0280, loss_cls: 0.1275, acc: 95.1495, loss_bbox: 0.1808, loss_mask: 0.2014, loss: 0.5548 2023-11-16 10:29:07,154 - mmdet - INFO - Epoch [33][600/1833] lr: 2.000e-05, eta: 2:13:02, time: 1.163, data_time: 0.079, memory: 16000, loss_rpn_cls: 0.0166, loss_rpn_bbox: 0.0264, loss_cls: 0.1262, acc: 95.2961, loss_bbox: 0.1746, loss_mask: 0.1961, loss: 0.5399 2023-11-16 10:30:06,604 - mmdet - INFO - Epoch [33][650/1833] lr: 2.000e-05, eta: 2:12:03, time: 1.189, data_time: 0.087, memory: 16000, loss_rpn_cls: 0.0163, loss_rpn_bbox: 0.0280, loss_cls: 0.1298, acc: 95.1055, loss_bbox: 0.1793, loss_mask: 0.2012, loss: 0.5547 2023-11-16 10:31:07,626 - mmdet - INFO - Epoch [33][700/1833] lr: 2.000e-05, eta: 2:11:04, time: 1.220, data_time: 0.080, memory: 16000, loss_rpn_cls: 0.0158, loss_rpn_bbox: 0.0274, loss_cls: 0.1293, acc: 95.1171, loss_bbox: 0.1785, loss_mask: 0.1996, loss: 0.5506 2023-11-16 10:32:08,070 - mmdet - INFO - Epoch [33][750/1833] lr: 2.000e-05, eta: 2:10:05, time: 1.209, data_time: 0.087, memory: 16000, loss_rpn_cls: 0.0165, loss_rpn_bbox: 0.0277, loss_cls: 0.1289, acc: 95.1038, loss_bbox: 0.1778, loss_mask: 0.2003, loss: 0.5512 2023-11-16 10:33:08,627 - mmdet - INFO - Epoch [33][800/1833] lr: 2.000e-05, eta: 2:09:06, time: 1.211, data_time: 0.080, memory: 16000, loss_rpn_cls: 0.0164, loss_rpn_bbox: 0.0279, loss_cls: 0.1301, acc: 95.0920, loss_bbox: 0.1791, loss_mask: 0.2007, loss: 0.5541 2023-11-16 10:34:08,224 - mmdet - INFO - Epoch [33][850/1833] lr: 2.000e-05, eta: 2:08:07, time: 1.192, data_time: 0.075, memory: 16000, loss_rpn_cls: 0.0162, loss_rpn_bbox: 0.0276, loss_cls: 0.1294, acc: 95.1219, loss_bbox: 0.1780, loss_mask: 0.1988, loss: 0.5500 2023-11-16 10:35:08,569 - mmdet - INFO - Epoch [33][900/1833] lr: 2.000e-05, eta: 2:07:07, time: 1.207, data_time: 0.076, memory: 16000, loss_rpn_cls: 0.0158, loss_rpn_bbox: 0.0263, loss_cls: 0.1266, acc: 95.1701, loss_bbox: 0.1764, loss_mask: 0.1985, loss: 0.5436 2023-11-16 10:36:09,187 - mmdet - INFO - Epoch [33][950/1833] lr: 2.000e-05, eta: 2:06:08, time: 1.212, data_time: 0.082, memory: 16000, loss_rpn_cls: 0.0161, loss_rpn_bbox: 0.0284, loss_cls: 0.1281, acc: 95.1759, loss_bbox: 0.1796, loss_mask: 0.1993, loss: 0.5516 2023-11-16 10:37:11,250 - mmdet - INFO - Epoch [33][1000/1833] lr: 2.000e-05, eta: 2:05:09, time: 1.241, data_time: 0.085, memory: 16000, loss_rpn_cls: 0.0163, loss_rpn_bbox: 0.0280, loss_cls: 0.1304, acc: 95.0793, loss_bbox: 0.1808, loss_mask: 0.2046, loss: 0.5600 2023-11-16 10:38:10,047 - mmdet - INFO - Epoch [33][1050/1833] lr: 2.000e-05, eta: 2:04:10, time: 1.176, data_time: 0.078, memory: 16000, loss_rpn_cls: 0.0161, loss_rpn_bbox: 0.0282, loss_cls: 0.1273, acc: 95.2010, loss_bbox: 0.1756, loss_mask: 0.1989, loss: 0.5461 2023-11-16 10:39:10,511 - mmdet - INFO - Epoch [33][1100/1833] lr: 2.000e-05, eta: 2:03:11, time: 1.209, data_time: 0.079, memory: 16000, loss_rpn_cls: 0.0157, loss_rpn_bbox: 0.0264, loss_cls: 0.1242, acc: 95.2917, loss_bbox: 0.1748, loss_mask: 0.1982, loss: 0.5394 2023-11-16 10:40:10,413 - mmdet - INFO - Epoch [33][1150/1833] lr: 2.000e-05, eta: 2:02:11, time: 1.198, data_time: 0.085, memory: 16000, loss_rpn_cls: 0.0156, loss_rpn_bbox: 0.0270, loss_cls: 0.1247, acc: 95.2853, loss_bbox: 0.1732, loss_mask: 0.1960, loss: 0.5364 2023-11-16 10:41:10,719 - mmdet - INFO - Epoch [33][1200/1833] lr: 2.000e-05, eta: 2:01:12, time: 1.206, data_time: 0.077, memory: 16000, loss_rpn_cls: 0.0163, loss_rpn_bbox: 0.0274, loss_cls: 0.1259, acc: 95.2358, loss_bbox: 0.1777, loss_mask: 0.2014, loss: 0.5488 2023-11-16 10:42:10,485 - mmdet - INFO - Epoch [33][1250/1833] lr: 2.000e-05, eta: 2:00:13, time: 1.195, data_time: 0.083, memory: 16000, loss_rpn_cls: 0.0156, loss_rpn_bbox: 0.0264, loss_cls: 0.1231, acc: 95.3363, loss_bbox: 0.1736, loss_mask: 0.1975, loss: 0.5363 2023-11-16 10:43:09,827 - mmdet - INFO - Epoch [33][1300/1833] lr: 2.000e-05, eta: 1:59:14, time: 1.187, data_time: 0.078, memory: 16000, loss_rpn_cls: 0.0166, loss_rpn_bbox: 0.0281, loss_cls: 0.1290, acc: 95.1499, loss_bbox: 0.1783, loss_mask: 0.1975, loss: 0.5496 2023-11-16 10:44:10,302 - mmdet - INFO - Epoch [33][1350/1833] lr: 2.000e-05, eta: 1:58:14, time: 1.209, data_time: 0.076, memory: 16000, loss_rpn_cls: 0.0161, loss_rpn_bbox: 0.0274, loss_cls: 0.1279, acc: 95.1455, loss_bbox: 0.1780, loss_mask: 0.1977, loss: 0.5471 2023-11-16 10:45:10,451 - mmdet - INFO - Epoch [33][1400/1833] lr: 2.000e-05, eta: 1:57:15, time: 1.203, data_time: 0.075, memory: 16000, loss_rpn_cls: 0.0167, loss_rpn_bbox: 0.0280, loss_cls: 0.1280, acc: 95.1636, loss_bbox: 0.1775, loss_mask: 0.1995, loss: 0.5496 2023-11-16 10:46:12,885 - mmdet - INFO - Epoch [33][1450/1833] lr: 2.000e-05, eta: 1:56:16, time: 1.249, data_time: 0.089, memory: 16000, loss_rpn_cls: 0.0159, loss_rpn_bbox: 0.0267, loss_cls: 0.1255, acc: 95.2640, loss_bbox: 0.1748, loss_mask: 0.1997, loss: 0.5427 2023-11-16 10:47:12,641 - mmdet - INFO - Epoch [33][1500/1833] lr: 2.000e-05, eta: 1:55:17, time: 1.195, data_time: 0.082, memory: 16000, loss_rpn_cls: 0.0169, loss_rpn_bbox: 0.0280, loss_cls: 0.1302, acc: 95.0776, loss_bbox: 0.1803, loss_mask: 0.2009, loss: 0.5562 2023-11-16 10:48:11,818 - mmdet - INFO - Epoch [33][1550/1833] lr: 2.000e-05, eta: 1:54:18, time: 1.184, data_time: 0.082, memory: 16000, loss_rpn_cls: 0.0148, loss_rpn_bbox: 0.0268, loss_cls: 0.1224, acc: 95.3657, loss_bbox: 0.1713, loss_mask: 0.1974, loss: 0.5327 2023-11-16 10:49:12,308 - mmdet - INFO - Epoch [33][1600/1833] lr: 2.000e-05, eta: 1:53:18, time: 1.210, data_time: 0.078, memory: 16000, loss_rpn_cls: 0.0171, loss_rpn_bbox: 0.0282, loss_cls: 0.1300, acc: 95.0803, loss_bbox: 0.1798, loss_mask: 0.1991, loss: 0.5542 2023-11-16 10:50:11,136 - mmdet - INFO - Epoch [33][1650/1833] lr: 2.000e-05, eta: 1:52:19, time: 1.177, data_time: 0.080, memory: 16000, loss_rpn_cls: 0.0159, loss_rpn_bbox: 0.0264, loss_cls: 0.1239, acc: 95.3010, loss_bbox: 0.1747, loss_mask: 0.1994, loss: 0.5403 2023-11-16 10:51:10,585 - mmdet - INFO - Epoch [33][1700/1833] lr: 2.000e-05, eta: 1:51:20, time: 1.189, data_time: 0.076, memory: 16000, loss_rpn_cls: 0.0168, loss_rpn_bbox: 0.0277, loss_cls: 0.1256, acc: 95.2333, loss_bbox: 0.1760, loss_mask: 0.2008, loss: 0.5470 2023-11-16 10:52:10,179 - mmdet - INFO - Epoch [33][1750/1833] lr: 2.000e-05, eta: 1:50:21, time: 1.192, data_time: 0.088, memory: 16000, loss_rpn_cls: 0.0172, loss_rpn_bbox: 0.0278, loss_cls: 0.1262, acc: 95.1978, loss_bbox: 0.1775, loss_mask: 0.1999, loss: 0.5485 2023-11-16 10:53:10,149 - mmdet - INFO - Epoch [33][1800/1833] lr: 2.000e-05, eta: 1:49:21, time: 1.199, data_time: 0.082, memory: 16000, loss_rpn_cls: 0.0169, loss_rpn_bbox: 0.0273, loss_cls: 0.1280, acc: 95.2227, loss_bbox: 0.1767, loss_mask: 0.1976, loss: 0.5466 2023-11-16 10:53:50,701 - mmdet - INFO - Saving checkpoint at 33 epochs 2023-11-16 10:54:35,500 - mmdet - INFO - Evaluating bbox... 2023-11-16 10:55:04,477 - 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 ] = 0.719 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.550 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 ] = 0.542 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.644 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 ] = 0.459 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 ] = 0.769 2023-11-16 10:55:04,480 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.599 | bicycle | 0.406 | car | 0.506 | | motorcycle | 0.494 | airplane | 0.708 | bus | 0.734 | | train | 0.701 | truck | 0.458 | boat | 0.343 | | traffic light | 0.317 | fire hydrant | 0.753 | stop sign | 0.711 | | parking meter | 0.541 | bench | 0.332 | bird | 0.434 | | cat | 0.738 | dog | 0.701 | horse | 0.655 | | sheep | 0.624 | cow | 0.642 | elephant | 0.719 | | bear | 0.771 | zebra | 0.689 | giraffe | 0.727 | | backpack | 0.241 | umbrella | 0.477 | handbag | 0.266 | | tie | 0.438 | suitcase | 0.499 | frisbee | 0.729 | | skis | 0.315 | snowboard | 0.467 | sports ball | 0.490 | | kite | 0.492 | baseball bat | 0.419 | baseball glove | 0.460 | | skateboard | 0.614 | surfboard | 0.474 | tennis racket | 0.589 | | bottle | 0.477 | wine glass | 0.431 | cup | 0.517 | | fork | 0.508 | knife | 0.305 | spoon | 0.344 | | bowl | 0.500 | banana | 0.288 | apple | 0.294 | | sandwich | 0.478 | orange | 0.365 | broccoli | 0.259 | | carrot | 0.267 | hot dog | 0.471 | pizza | 0.576 | | donut | 0.572 | cake | 0.457 | chair | 0.386 | | couch | 0.500 | potted plant | 0.381 | bed | 0.470 | | dining table | 0.337 | toilet | 0.667 | tv | 0.643 | | laptop | 0.707 | mouse | 0.665 | remote | 0.454 | | keyboard | 0.574 | cell phone | 0.476 | microwave | 0.685 | | oven | 0.435 | toaster | 0.511 | sink | 0.462 | | refrigerator | 0.701 | book | 0.215 | clock | 0.513 | | vase | 0.451 | scissors | 0.470 | teddy bear | 0.559 | | hair drier | 0.282 | toothbrush | 0.358 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-16 10:55:04,480 - mmdet - INFO - Evaluating segm... 2023-11-16 10:55:35,764 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.448 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.689 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.483 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 ] = 0.481 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 ] = 0.560 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 ] = 0.396 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.596 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.711 2023-11-16 10:55:35,766 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.520 | bicycle | 0.255 | car | 0.464 | | motorcycle | 0.418 | airplane | 0.542 | bus | 0.713 | | train | 0.694 | truck | 0.433 | boat | 0.311 | | traffic light | 0.305 | fire hydrant | 0.711 | stop sign | 0.681 | | parking meter | 0.539 | bench | 0.254 | bird | 0.365 | | cat | 0.732 | dog | 0.662 | horse | 0.486 | | sheep | 0.552 | cow | 0.547 | elephant | 0.645 | | bear | 0.737 | zebra | 0.602 | giraffe | 0.564 | | backpack | 0.236 | umbrella | 0.531 | handbag | 0.236 | | tie | 0.392 | suitcase | 0.515 | frisbee | 0.678 | | skis | 0.076 | snowboard | 0.308 | sports ball | 0.476 | | kite | 0.351 | baseball bat | 0.315 | baseball glove | 0.461 | | skateboard | 0.396 | surfboard | 0.384 | tennis racket | 0.612 | | bottle | 0.452 | wine glass | 0.393 | cup | 0.509 | | fork | 0.266 | knife | 0.211 | spoon | 0.250 | | bowl | 0.459 | banana | 0.239 | apple | 0.284 | | sandwich | 0.497 | orange | 0.365 | broccoli | 0.235 | | carrot | 0.235 | hot dog | 0.385 | pizza | 0.558 | | donut | 0.567 | cake | 0.459 | chair | 0.278 | | couch | 0.421 | potted plant | 0.313 | bed | 0.388 | | dining table | 0.199 | toilet | 0.637 | tv | 0.668 | | laptop | 0.688 | mouse | 0.644 | remote | 0.401 | | keyboard | 0.539 | cell phone | 0.440 | microwave | 0.689 | | oven | 0.391 | toaster | 0.537 | sink | 0.424 | | refrigerator | 0.690 | book | 0.160 | clock | 0.508 | | vase | 0.440 | scissors | 0.334 | teddy bear | 0.532 | | hair drier | 0.199 | toothbrush | 0.238 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-16 10:55:36,142 - mmdet - INFO - The previous best checkpoint /mnt/petrelfs/lizhiqi/DINO/detection/work_dirs/mask_rcnn_flash_internimage_s_fpn_3x_coco_0.4/best_bbox_mAP_epoch_31.pth was removed 2023-11-16 10:55:38,361 - mmdet - INFO - Now best checkpoint is saved as best_bbox_mAP_epoch_33.pth. 2023-11-16 10:55:38,362 - mmdet - INFO - Best bbox_mAP is 0.5035 at 33 epoch. 2023-11-16 10:55:38,362 - mmdet - INFO - Exp name: mask_rcnn_flash_internimage_s_fpn_3x_coco_0.4.py 2023-11-16 10:55:38,362 - mmdet - INFO - Epoch(val) [33][625] bbox_mAP: 0.5035, bbox_mAP_50: 0.7192, bbox_mAP_75: 0.5505, bbox_mAP_s: 0.3362, bbox_mAP_m: 0.5423, bbox_mAP_l: 0.6442, bbox_mAP_copypaste: 0.5035 0.7192 0.5505 0.3362 0.5423 0.6442, segm_mAP: 0.4478, segm_mAP_50: 0.6887, segm_mAP_75: 0.4829, segm_mAP_s: 0.2498, segm_mAP_m: 0.4810, segm_mAP_l: 0.6283, segm_mAP_copypaste: 0.4478 0.6887 0.4829 0.2498 0.4810 0.6283 2023-11-16 10:56:42,384 - mmdet - INFO - Epoch [34][50/1833] lr: 2.000e-06, eta: 1:47:40, time: 1.280, data_time: 0.132, memory: 16000, loss_rpn_cls: 0.0158, loss_rpn_bbox: 0.0269, loss_cls: 0.1247, acc: 95.3019, loss_bbox: 0.1762, loss_mask: 0.1971, loss: 0.5408 2023-11-16 10:57:43,242 - mmdet - INFO - Epoch [34][100/1833] lr: 2.000e-06, eta: 1:46:41, time: 1.217, data_time: 0.070, memory: 16000, loss_rpn_cls: 0.0164, loss_rpn_bbox: 0.0264, loss_cls: 0.1239, acc: 95.2834, loss_bbox: 0.1730, loss_mask: 0.1966, loss: 0.5363 2023-11-16 10:58:44,683 - mmdet - INFO - Epoch [34][150/1833] lr: 2.000e-06, eta: 1:45:42, time: 1.229, data_time: 0.074, memory: 16000, loss_rpn_cls: 0.0163, loss_rpn_bbox: 0.0272, loss_cls: 0.1259, acc: 95.2725, loss_bbox: 0.1754, loss_mask: 0.1974, loss: 0.5421 2023-11-16 10:59:48,021 - mmdet - INFO - Epoch [34][200/1833] lr: 2.000e-06, eta: 1:44:43, time: 1.267, data_time: 0.074, memory: 16000, loss_rpn_cls: 0.0166, loss_rpn_bbox: 0.0264, loss_cls: 0.1248, acc: 95.2797, loss_bbox: 0.1725, loss_mask: 0.1974, loss: 0.5376 2023-11-16 11:00:48,970 - mmdet - INFO - Epoch [34][250/1833] lr: 2.000e-06, eta: 1:43:43, time: 1.219, data_time: 0.077, memory: 16000, loss_rpn_cls: 0.0165, loss_rpn_bbox: 0.0285, loss_cls: 0.1295, acc: 95.0626, loss_bbox: 0.1805, loss_mask: 0.2010, loss: 0.5560 2023-11-16 11:01:49,786 - mmdet - INFO - Epoch [34][300/1833] lr: 2.000e-06, eta: 1:42:44, time: 1.216, data_time: 0.077, memory: 16000, loss_rpn_cls: 0.0162, loss_rpn_bbox: 0.0281, loss_cls: 0.1268, acc: 95.2212, loss_bbox: 0.1780, loss_mask: 0.2024, loss: 0.5515 2023-11-16 11:02:49,906 - mmdet - INFO - Epoch [34][350/1833] lr: 2.000e-06, eta: 1:41:45, time: 1.202, data_time: 0.072, memory: 16000, loss_rpn_cls: 0.0165, loss_rpn_bbox: 0.0272, loss_cls: 0.1275, acc: 95.1772, loss_bbox: 0.1752, loss_mask: 0.1990, loss: 0.5454 2023-11-16 11:03:49,866 - mmdet - INFO - Epoch [34][400/1833] lr: 2.000e-06, eta: 1:40:46, time: 1.199, data_time: 0.077, memory: 16000, loss_rpn_cls: 0.0152, loss_rpn_bbox: 0.0263, loss_cls: 0.1218, acc: 95.3691, loss_bbox: 0.1718, loss_mask: 0.1974, loss: 0.5325 2023-11-16 11:04:50,113 - mmdet - INFO - Epoch [34][450/1833] lr: 2.000e-06, eta: 1:39:47, time: 1.205, data_time: 0.081, memory: 16000, loss_rpn_cls: 0.0156, loss_rpn_bbox: 0.0266, loss_cls: 0.1226, acc: 95.3490, loss_bbox: 0.1737, loss_mask: 0.1977, loss: 0.5361 2023-11-16 11:05:49,610 - mmdet - INFO - Epoch [34][500/1833] lr: 2.000e-06, eta: 1:38:47, time: 1.190, data_time: 0.079, memory: 16000, loss_rpn_cls: 0.0161, loss_rpn_bbox: 0.0271, loss_cls: 0.1227, acc: 95.3651, loss_bbox: 0.1734, loss_mask: 0.1972, loss: 0.5364 2023-11-16 11:06:50,162 - mmdet - INFO - Epoch [34][550/1833] lr: 2.000e-06, eta: 1:37:48, time: 1.211, data_time: 0.079, memory: 16000, loss_rpn_cls: 0.0158, loss_rpn_bbox: 0.0276, loss_cls: 0.1252, acc: 95.2790, loss_bbox: 0.1772, loss_mask: 0.1976, loss: 0.5434 2023-11-16 11:07:49,606 - mmdet - INFO - Epoch [34][600/1833] lr: 2.000e-06, eta: 1:36:49, time: 1.189, data_time: 0.076, memory: 16000, loss_rpn_cls: 0.0168, loss_rpn_bbox: 0.0276, loss_cls: 0.1267, acc: 95.2183, loss_bbox: 0.1788, loss_mask: 0.1997, loss: 0.5496 2023-11-16 11:08:49,748 - mmdet - INFO - Epoch [34][650/1833] lr: 2.000e-06, eta: 1:35:50, time: 1.203, data_time: 0.080, memory: 16000, loss_rpn_cls: 0.0158, loss_rpn_bbox: 0.0270, loss_cls: 0.1258, acc: 95.2393, loss_bbox: 0.1785, loss_mask: 0.1995, loss: 0.5467 2023-11-16 11:09:50,544 - mmdet - INFO - Epoch [34][700/1833] lr: 2.000e-06, eta: 1:34:51, time: 1.216, data_time: 0.085, memory: 16000, loss_rpn_cls: 0.0163, loss_rpn_bbox: 0.0279, loss_cls: 0.1274, acc: 95.1597, loss_bbox: 0.1771, loss_mask: 0.2000, loss: 0.5486 2023-11-16 11:10:51,031 - mmdet - INFO - Epoch [34][750/1833] lr: 2.000e-06, eta: 1:33:51, time: 1.210, data_time: 0.071, memory: 16000, loss_rpn_cls: 0.0157, loss_rpn_bbox: 0.0265, loss_cls: 0.1216, acc: 95.4116, loss_bbox: 0.1718, loss_mask: 0.1958, loss: 0.5314 2023-11-16 11:11:50,567 - mmdet - INFO - Epoch [34][800/1833] lr: 2.000e-06, eta: 1:32:52, time: 1.191, data_time: 0.077, memory: 16000, loss_rpn_cls: 0.0162, loss_rpn_bbox: 0.0274, loss_cls: 0.1246, acc: 95.2674, loss_bbox: 0.1743, loss_mask: 0.1968, loss: 0.5394 2023-11-16 11:12:50,280 - mmdet - INFO - Epoch [34][850/1833] lr: 2.000e-06, eta: 1:31:53, time: 1.194, data_time: 0.084, memory: 16000, loss_rpn_cls: 0.0161, loss_rpn_bbox: 0.0271, loss_cls: 0.1257, acc: 95.2574, loss_bbox: 0.1755, loss_mask: 0.1979, loss: 0.5424 2023-11-16 11:13:51,725 - mmdet - INFO - Epoch [34][900/1833] lr: 2.000e-06, eta: 1:30:54, time: 1.229, data_time: 0.084, memory: 16000, loss_rpn_cls: 0.0164, loss_rpn_bbox: 0.0272, loss_cls: 0.1272, acc: 95.1890, loss_bbox: 0.1774, loss_mask: 0.1977, loss: 0.5459 2023-11-16 11:14:52,127 - mmdet - INFO - Epoch [34][950/1833] lr: 2.000e-06, eta: 1:29:54, time: 1.208, data_time: 0.078, memory: 16000, loss_rpn_cls: 0.0149, loss_rpn_bbox: 0.0267, loss_cls: 0.1242, acc: 95.3370, loss_bbox: 0.1741, loss_mask: 0.1974, loss: 0.5373 2023-11-16 11:15:51,947 - mmdet - INFO - Epoch [34][1000/1833] lr: 2.000e-06, eta: 1:28:55, time: 1.196, data_time: 0.072, memory: 16000, loss_rpn_cls: 0.0159, loss_rpn_bbox: 0.0264, loss_cls: 0.1229, acc: 95.3748, loss_bbox: 0.1706, loss_mask: 0.1946, loss: 0.5305 2023-11-16 11:16:52,058 - mmdet - INFO - Epoch [34][1050/1833] lr: 2.000e-06, eta: 1:27:56, time: 1.202, data_time: 0.074, memory: 16000, loss_rpn_cls: 0.0156, loss_rpn_bbox: 0.0269, loss_cls: 0.1246, acc: 95.2866, loss_bbox: 0.1753, loss_mask: 0.1980, loss: 0.5404 2023-11-16 11:17:52,583 - mmdet - INFO - Epoch [34][1100/1833] lr: 2.000e-06, eta: 1:26:57, time: 1.210, data_time: 0.078, memory: 16000, loss_rpn_cls: 0.0167, loss_rpn_bbox: 0.0275, loss_cls: 0.1270, acc: 95.2253, loss_bbox: 0.1774, loss_mask: 0.1994, loss: 0.5481 2023-11-16 11:18:53,381 - mmdet - INFO - Epoch [34][1150/1833] lr: 2.000e-06, eta: 1:25:58, time: 1.216, data_time: 0.084, memory: 16000, loss_rpn_cls: 0.0170, loss_rpn_bbox: 0.0277, loss_cls: 0.1245, acc: 95.2802, loss_bbox: 0.1740, loss_mask: 0.1967, loss: 0.5400 2023-11-16 11:19:53,137 - mmdet - INFO - Epoch [34][1200/1833] lr: 2.000e-06, eta: 1:24:58, time: 1.195, data_time: 0.072, memory: 16000, loss_rpn_cls: 0.0164, loss_rpn_bbox: 0.0274, loss_cls: 0.1255, acc: 95.2589, loss_bbox: 0.1759, loss_mask: 0.1966, loss: 0.5418 2023-11-16 11:20:53,137 - mmdet - INFO - Epoch [34][1250/1833] lr: 2.000e-06, eta: 1:23:59, time: 1.200, data_time: 0.082, memory: 16000, loss_rpn_cls: 0.0165, loss_rpn_bbox: 0.0269, loss_cls: 0.1262, acc: 95.2559, loss_bbox: 0.1757, loss_mask: 0.2000, loss: 0.5453 2023-11-16 11:21:53,061 - mmdet - INFO - Epoch [34][1300/1833] lr: 2.000e-06, eta: 1:23:00, time: 1.199, data_time: 0.083, memory: 16000, loss_rpn_cls: 0.0153, loss_rpn_bbox: 0.0261, loss_cls: 0.1236, acc: 95.3273, loss_bbox: 0.1716, loss_mask: 0.1966, loss: 0.5333 2023-11-16 11:22:53,678 - mmdet - INFO - Epoch [34][1350/1833] lr: 2.000e-06, eta: 1:22:01, time: 1.212, data_time: 0.076, memory: 16000, loss_rpn_cls: 0.0163, loss_rpn_bbox: 0.0273, loss_cls: 0.1257, acc: 95.2327, loss_bbox: 0.1771, loss_mask: 0.1987, loss: 0.5450 2023-11-16 11:23:55,196 - mmdet - INFO - Epoch [34][1400/1833] lr: 2.000e-06, eta: 1:21:01, time: 1.230, data_time: 0.078, memory: 16000, loss_rpn_cls: 0.0165, loss_rpn_bbox: 0.0275, loss_cls: 0.1268, acc: 95.1816, loss_bbox: 0.1779, loss_mask: 0.1978, loss: 0.5466 2023-11-16 11:24:55,927 - mmdet - INFO - Epoch [34][1450/1833] lr: 2.000e-06, eta: 1:20:02, time: 1.215, data_time: 0.071, memory: 16000, loss_rpn_cls: 0.0167, loss_rpn_bbox: 0.0273, loss_cls: 0.1246, acc: 95.2582, loss_bbox: 0.1737, loss_mask: 0.1984, loss: 0.5406 2023-11-16 11:25:57,624 - mmdet - INFO - Epoch [34][1500/1833] lr: 2.000e-06, eta: 1:19:03, time: 1.234, data_time: 0.077, memory: 16000, loss_rpn_cls: 0.0172, loss_rpn_bbox: 0.0280, loss_cls: 0.1275, acc: 95.1808, loss_bbox: 0.1764, loss_mask: 0.1987, loss: 0.5478 2023-11-16 11:26:59,355 - mmdet - INFO - Epoch [34][1550/1833] lr: 2.000e-06, eta: 1:18:04, time: 1.235, data_time: 0.084, memory: 16000, loss_rpn_cls: 0.0164, loss_rpn_bbox: 0.0276, loss_cls: 0.1257, acc: 95.2510, loss_bbox: 0.1778, loss_mask: 0.1988, loss: 0.5464 2023-11-16 11:28:01,715 - mmdet - INFO - Epoch [34][1600/1833] lr: 2.000e-06, eta: 1:17:05, time: 1.247, data_time: 0.082, memory: 16000, loss_rpn_cls: 0.0166, loss_rpn_bbox: 0.0280, loss_cls: 0.1288, acc: 95.1310, loss_bbox: 0.1806, loss_mask: 0.1994, loss: 0.5534 2023-11-16 11:29:01,769 - mmdet - INFO - Epoch [34][1650/1833] lr: 2.000e-06, eta: 1:16:05, time: 1.201, data_time: 0.080, memory: 16000, loss_rpn_cls: 0.0158, loss_rpn_bbox: 0.0269, loss_cls: 0.1240, acc: 95.3206, loss_bbox: 0.1736, loss_mask: 0.1956, loss: 0.5360 2023-11-16 11:30:03,103 - mmdet - INFO - Epoch [34][1700/1833] lr: 2.000e-06, eta: 1:15:06, time: 1.227, data_time: 0.073, memory: 16000, loss_rpn_cls: 0.0174, loss_rpn_bbox: 0.0283, loss_cls: 0.1294, acc: 95.0852, loss_bbox: 0.1801, loss_mask: 0.2014, loss: 0.5566 2023-11-16 11:31:04,333 - mmdet - INFO - Epoch [34][1750/1833] lr: 2.000e-06, eta: 1:14:07, time: 1.225, data_time: 0.077, memory: 16000, loss_rpn_cls: 0.0165, loss_rpn_bbox: 0.0273, loss_cls: 0.1278, acc: 95.1290, loss_bbox: 0.1778, loss_mask: 0.2002, loss: 0.5497 2023-11-16 11:32:04,969 - mmdet - INFO - Epoch [34][1800/1833] lr: 2.000e-06, eta: 1:13:08, time: 1.213, data_time: 0.077, memory: 16000, loss_rpn_cls: 0.0169, loss_rpn_bbox: 0.0283, loss_cls: 0.1282, acc: 95.1304, loss_bbox: 0.1793, loss_mask: 0.1994, loss: 0.5521 2023-11-16 11:32:45,231 - mmdet - INFO - Saving checkpoint at 34 epochs 2023-11-16 11:33:28,448 - mmdet - INFO - Evaluating bbox... 2023-11-16 11:33:57,616 - 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 ] = 0.719 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.551 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.338 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.543 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.644 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 ] = 0.463 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 ] = 0.769 2023-11-16 11:33:57,618 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.599 | bicycle | 0.411 | car | 0.507 | | motorcycle | 0.504 | airplane | 0.713 | bus | 0.734 | | train | 0.704 | truck | 0.457 | boat | 0.342 | | traffic light | 0.315 | fire hydrant | 0.758 | stop sign | 0.706 | | parking meter | 0.543 | bench | 0.335 | bird | 0.436 | | cat | 0.739 | dog | 0.711 | horse | 0.652 | | sheep | 0.621 | cow | 0.631 | elephant | 0.726 | | bear | 0.752 | zebra | 0.695 | giraffe | 0.724 | | backpack | 0.237 | umbrella | 0.479 | handbag | 0.263 | | tie | 0.442 | suitcase | 0.496 | frisbee | 0.731 | | skis | 0.321 | snowboard | 0.481 | sports ball | 0.494 | | kite | 0.490 | baseball bat | 0.416 | baseball glove | 0.453 | | skateboard | 0.620 | surfboard | 0.472 | tennis racket | 0.585 | | bottle | 0.477 | wine glass | 0.435 | cup | 0.518 | | fork | 0.516 | knife | 0.314 | spoon | 0.342 | | bowl | 0.502 | banana | 0.288 | apple | 0.292 | | sandwich | 0.483 | orange | 0.365 | broccoli | 0.257 | | carrot | 0.272 | hot dog | 0.475 | pizza | 0.574 | | donut | 0.577 | cake | 0.452 | chair | 0.385 | | couch | 0.507 | potted plant | 0.378 | bed | 0.478 | | dining table | 0.339 | toilet | 0.674 | tv | 0.646 | | laptop | 0.711 | mouse | 0.673 | remote | 0.455 | | keyboard | 0.575 | cell phone | 0.481 | microwave | 0.691 | | oven | 0.434 | toaster | 0.499 | sink | 0.457 | | refrigerator | 0.699 | book | 0.214 | clock | 0.519 | | vase | 0.451 | scissors | 0.458 | teddy bear | 0.565 | | hair drier | 0.249 | toothbrush | 0.357 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-16 11:33:57,618 - mmdet - INFO - Evaluating segm... 2023-11-16 11:34:26,370 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.448 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.689 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.483 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 ] = 0.480 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 ] = 0.561 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 ] = 0.398 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.596 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.716 2023-11-16 11:34:26,372 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.521 | bicycle | 0.258 | car | 0.466 | | motorcycle | 0.419 | airplane | 0.544 | bus | 0.715 | | train | 0.687 | truck | 0.429 | boat | 0.308 | | traffic light | 0.306 | fire hydrant | 0.718 | stop sign | 0.682 | | parking meter | 0.543 | bench | 0.254 | bird | 0.366 | | cat | 0.732 | dog | 0.665 | horse | 0.485 | | sheep | 0.550 | cow | 0.540 | elephant | 0.654 | | bear | 0.736 | zebra | 0.603 | giraffe | 0.567 | | backpack | 0.238 | umbrella | 0.531 | handbag | 0.238 | | tie | 0.395 | suitcase | 0.517 | frisbee | 0.677 | | skis | 0.076 | snowboard | 0.308 | sports ball | 0.476 | | kite | 0.344 | baseball bat | 0.317 | baseball glove | 0.461 | | skateboard | 0.398 | surfboard | 0.386 | tennis racket | 0.614 | | bottle | 0.450 | wine glass | 0.394 | cup | 0.509 | | fork | 0.268 | knife | 0.216 | spoon | 0.245 | | bowl | 0.460 | banana | 0.239 | apple | 0.283 | | sandwich | 0.500 | orange | 0.363 | broccoli | 0.233 | | carrot | 0.236 | hot dog | 0.386 | pizza | 0.553 | | donut | 0.569 | cake | 0.458 | chair | 0.276 | | couch | 0.424 | potted plant | 0.312 | bed | 0.393 | | dining table | 0.200 | toilet | 0.646 | tv | 0.668 | | laptop | 0.685 | mouse | 0.645 | remote | 0.404 | | keyboard | 0.551 | cell phone | 0.441 | microwave | 0.696 | | oven | 0.393 | toaster | 0.533 | sink | 0.426 | | refrigerator | 0.691 | book | 0.159 | clock | 0.513 | | vase | 0.441 | scissors | 0.336 | teddy bear | 0.537 | | hair drier | 0.173 | toothbrush | 0.244 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-16 11:34:26,810 - mmdet - INFO - The previous best checkpoint /mnt/petrelfs/lizhiqi/DINO/detection/work_dirs/mask_rcnn_flash_internimage_s_fpn_3x_coco_0.4/best_bbox_mAP_epoch_33.pth was removed 2023-11-16 11:34:29,032 - mmdet - INFO - Now best checkpoint is saved as best_bbox_mAP_epoch_34.pth. 2023-11-16 11:34:29,033 - mmdet - INFO - Best bbox_mAP is 0.5042 at 34 epoch. 2023-11-16 11:34:29,033 - mmdet - INFO - Exp name: mask_rcnn_flash_internimage_s_fpn_3x_coco_0.4.py 2023-11-16 11:34:29,033 - mmdet - INFO - Epoch(val) [34][625] bbox_mAP: 0.5042, bbox_mAP_50: 0.7194, bbox_mAP_75: 0.5509, bbox_mAP_s: 0.3379, bbox_mAP_m: 0.5432, bbox_mAP_l: 0.6440, bbox_mAP_copypaste: 0.5042 0.7194 0.5509 0.3379 0.5432 0.6440, segm_mAP: 0.4484, segm_mAP_50: 0.6892, segm_mAP_75: 0.4832, segm_mAP_s: 0.2516, segm_mAP_m: 0.4798, segm_mAP_l: 0.6337, segm_mAP_copypaste: 0.4484 0.6892 0.4832 0.2516 0.4798 0.6337 2023-11-16 11:35:33,271 - mmdet - INFO - Epoch [35][50/1833] lr: 2.000e-06, eta: 1:11:27, time: 1.284, data_time: 0.134, memory: 16000, loss_rpn_cls: 0.0161, loss_rpn_bbox: 0.0281, loss_cls: 0.1263, acc: 95.1946, loss_bbox: 0.1766, loss_mask: 0.1988, loss: 0.5459 2023-11-16 11:36:33,873 - mmdet - INFO - Epoch [35][100/1833] lr: 2.000e-06, eta: 1:10:28, time: 1.212, data_time: 0.078, memory: 16000, loss_rpn_cls: 0.0163, loss_rpn_bbox: 0.0275, loss_cls: 0.1258, acc: 95.2537, loss_bbox: 0.1739, loss_mask: 0.1984, loss: 0.5420 2023-11-16 11:37:35,125 - mmdet - INFO - Epoch [35][150/1833] lr: 2.000e-06, eta: 1:09:29, time: 1.225, data_time: 0.072, memory: 16000, loss_rpn_cls: 0.0159, loss_rpn_bbox: 0.0265, loss_cls: 0.1227, acc: 95.3845, loss_bbox: 0.1737, loss_mask: 0.1990, loss: 0.5378 2023-11-16 11:38:36,506 - mmdet - INFO - Epoch [35][200/1833] lr: 2.000e-06, eta: 1:08:30, time: 1.228, data_time: 0.074, memory: 16000, loss_rpn_cls: 0.0162, loss_rpn_bbox: 0.0274, loss_cls: 0.1255, acc: 95.2966, loss_bbox: 0.1753, loss_mask: 0.1987, loss: 0.5431 2023-11-16 11:39:37,517 - mmdet - INFO - Epoch [35][250/1833] lr: 2.000e-06, eta: 1:07:31, time: 1.220, data_time: 0.069, memory: 16000, loss_rpn_cls: 0.0172, loss_rpn_bbox: 0.0275, loss_cls: 0.1278, acc: 95.1664, loss_bbox: 0.1774, loss_mask: 0.1994, loss: 0.5495 2023-11-16 11:40:37,422 - mmdet - INFO - Epoch [35][300/1833] lr: 2.000e-06, eta: 1:06:31, time: 1.198, data_time: 0.074, memory: 16000, loss_rpn_cls: 0.0160, loss_rpn_bbox: 0.0271, loss_cls: 0.1249, acc: 95.2732, loss_bbox: 0.1756, loss_mask: 0.1989, loss: 0.5425 2023-11-16 11:41:36,942 - mmdet - INFO - Epoch [35][350/1833] lr: 2.000e-06, eta: 1:05:32, time: 1.190, data_time: 0.070, memory: 16000, loss_rpn_cls: 0.0162, loss_rpn_bbox: 0.0268, loss_cls: 0.1236, acc: 95.3126, loss_bbox: 0.1732, loss_mask: 0.1954, loss: 0.5353 2023-11-16 11:42:36,906 - mmdet - INFO - Epoch [35][400/1833] lr: 2.000e-06, eta: 1:04:33, time: 1.199, data_time: 0.069, memory: 16000, loss_rpn_cls: 0.0160, loss_rpn_bbox: 0.0272, loss_cls: 0.1255, acc: 95.2502, loss_bbox: 0.1774, loss_mask: 0.1986, loss: 0.5447 2023-11-16 11:43:36,022 - mmdet - INFO - Epoch [35][450/1833] lr: 2.000e-06, eta: 1:03:33, time: 1.182, data_time: 0.071, memory: 16000, loss_rpn_cls: 0.0153, loss_rpn_bbox: 0.0265, loss_cls: 0.1220, acc: 95.3558, loss_bbox: 0.1705, loss_mask: 0.1956, loss: 0.5300 2023-11-16 11:44:35,497 - mmdet - INFO - Epoch [35][500/1833] lr: 2.000e-06, eta: 1:02:34, time: 1.190, data_time: 0.077, memory: 16000, loss_rpn_cls: 0.0151, loss_rpn_bbox: 0.0258, loss_cls: 0.1210, acc: 95.4388, loss_bbox: 0.1723, loss_mask: 0.1948, loss: 0.5290 2023-11-16 11:45:35,337 - mmdet - INFO - Epoch [35][550/1833] lr: 2.000e-06, eta: 1:01:35, time: 1.197, data_time: 0.064, memory: 16000, loss_rpn_cls: 0.0160, loss_rpn_bbox: 0.0271, loss_cls: 0.1278, acc: 95.1852, loss_bbox: 0.1772, loss_mask: 0.1998, loss: 0.5480 2023-11-16 11:46:34,387 - mmdet - INFO - Epoch [35][600/1833] lr: 2.000e-06, eta: 1:00:36, time: 1.181, data_time: 0.066, memory: 16000, loss_rpn_cls: 0.0172, loss_rpn_bbox: 0.0282, loss_cls: 0.1283, acc: 95.1623, loss_bbox: 0.1783, loss_mask: 0.2008, loss: 0.5529 2023-11-16 11:47:33,898 - mmdet - INFO - Epoch [35][650/1833] lr: 2.000e-06, eta: 0:59:36, time: 1.190, data_time: 0.063, memory: 16000, loss_rpn_cls: 0.0158, loss_rpn_bbox: 0.0279, loss_cls: 0.1267, acc: 95.2150, loss_bbox: 0.1771, loss_mask: 0.1993, loss: 0.5469 2023-11-16 11:48:33,470 - mmdet - INFO - Epoch [35][700/1833] lr: 2.000e-06, eta: 0:58:37, time: 1.191, data_time: 0.075, memory: 16000, loss_rpn_cls: 0.0161, loss_rpn_bbox: 0.0273, loss_cls: 0.1257, acc: 95.2314, loss_bbox: 0.1755, loss_mask: 0.1980, loss: 0.5426 2023-11-16 11:49:34,066 - mmdet - INFO - Epoch [35][750/1833] lr: 2.000e-06, eta: 0:57:38, time: 1.212, data_time: 0.068, memory: 16000, loss_rpn_cls: 0.0161, loss_rpn_bbox: 0.0270, loss_cls: 0.1264, acc: 95.2138, loss_bbox: 0.1767, loss_mask: 0.1988, loss: 0.5450 2023-11-16 11:50:33,417 - mmdet - INFO - Epoch [35][800/1833] lr: 2.000e-06, eta: 0:56:39, time: 1.187, data_time: 0.077, memory: 16000, loss_rpn_cls: 0.0153, loss_rpn_bbox: 0.0267, loss_cls: 0.1250, acc: 95.2834, loss_bbox: 0.1760, loss_mask: 0.1953, loss: 0.5384 2023-11-16 11:51:32,576 - mmdet - INFO - Epoch [35][850/1833] lr: 2.000e-06, eta: 0:55:39, time: 1.183, data_time: 0.069, memory: 16000, loss_rpn_cls: 0.0161, loss_rpn_bbox: 0.0275, loss_cls: 0.1260, acc: 95.2311, loss_bbox: 0.1748, loss_mask: 0.1995, loss: 0.5439 2023-11-16 11:52:32,448 - mmdet - INFO - Epoch [35][900/1833] lr: 2.000e-06, eta: 0:54:40, time: 1.197, data_time: 0.068, memory: 16000, loss_rpn_cls: 0.0158, loss_rpn_bbox: 0.0269, loss_cls: 0.1244, acc: 95.3015, loss_bbox: 0.1753, loss_mask: 0.1993, loss: 0.5417 2023-11-16 11:53:32,894 - mmdet - INFO - Epoch [35][950/1833] lr: 2.000e-06, eta: 0:53:41, time: 1.209, data_time: 0.066, memory: 16000, loss_rpn_cls: 0.0163, loss_rpn_bbox: 0.0274, loss_cls: 0.1250, acc: 95.2911, loss_bbox: 0.1752, loss_mask: 0.1971, loss: 0.5411 2023-11-16 11:54:33,355 - mmdet - INFO - Epoch [35][1000/1833] lr: 2.000e-06, eta: 0:52:41, time: 1.209, data_time: 0.079, memory: 16000, loss_rpn_cls: 0.0162, loss_rpn_bbox: 0.0275, loss_cls: 0.1252, acc: 95.2589, loss_bbox: 0.1757, loss_mask: 0.1985, loss: 0.5431 2023-11-16 11:55:32,701 - mmdet - INFO - Epoch [35][1050/1833] lr: 2.000e-06, eta: 0:51:42, time: 1.187, data_time: 0.071, memory: 16000, loss_rpn_cls: 0.0145, loss_rpn_bbox: 0.0257, loss_cls: 0.1224, acc: 95.3333, loss_bbox: 0.1721, loss_mask: 0.1945, loss: 0.5292 2023-11-16 11:56:31,324 - mmdet - INFO - Epoch [35][1100/1833] lr: 2.000e-06, eta: 0:50:43, time: 1.172, data_time: 0.062, memory: 16000, loss_rpn_cls: 0.0170, loss_rpn_bbox: 0.0276, loss_cls: 0.1272, acc: 95.2184, loss_bbox: 0.1761, loss_mask: 0.1986, loss: 0.5465 2023-11-16 11:57:30,169 - mmdet - INFO - Epoch [35][1150/1833] lr: 2.000e-06, eta: 0:49:43, time: 1.177, data_time: 0.069, memory: 16000, loss_rpn_cls: 0.0159, loss_rpn_bbox: 0.0270, loss_cls: 0.1258, acc: 95.2278, loss_bbox: 0.1774, loss_mask: 0.1980, loss: 0.5441 2023-11-16 11:58:29,317 - mmdet - INFO - Epoch [35][1200/1833] lr: 2.000e-06, eta: 0:48:44, time: 1.183, data_time: 0.068, memory: 16000, loss_rpn_cls: 0.0159, loss_rpn_bbox: 0.0273, loss_cls: 0.1258, acc: 95.1979, loss_bbox: 0.1755, loss_mask: 0.1985, loss: 0.5430 2023-11-16 11:59:29,742 - mmdet - INFO - Epoch [35][1250/1833] lr: 2.000e-06, eta: 0:47:45, time: 1.208, data_time: 0.067, memory: 16000, loss_rpn_cls: 0.0158, loss_rpn_bbox: 0.0277, loss_cls: 0.1271, acc: 95.1484, loss_bbox: 0.1789, loss_mask: 0.1997, loss: 0.5491 2023-11-16 12:00:28,820 - mmdet - INFO - Epoch [35][1300/1833] lr: 2.000e-06, eta: 0:46:46, time: 1.182, data_time: 0.069, memory: 16000, loss_rpn_cls: 0.0166, loss_rpn_bbox: 0.0278, loss_cls: 0.1275, acc: 95.1920, loss_bbox: 0.1793, loss_mask: 0.2020, loss: 0.5532 2023-11-16 12:01:28,809 - mmdet - INFO - Epoch [35][1350/1833] lr: 2.000e-06, eta: 0:45:46, time: 1.200, data_time: 0.070, memory: 16000, loss_rpn_cls: 0.0162, loss_rpn_bbox: 0.0274, loss_cls: 0.1254, acc: 95.2775, loss_bbox: 0.1762, loss_mask: 0.1970, loss: 0.5422 2023-11-16 12:02:27,713 - mmdet - INFO - Epoch [35][1400/1833] lr: 2.000e-06, eta: 0:44:47, time: 1.178, data_time: 0.059, memory: 16000, loss_rpn_cls: 0.0155, loss_rpn_bbox: 0.0269, loss_cls: 0.1232, acc: 95.3195, loss_bbox: 0.1737, loss_mask: 0.1971, loss: 0.5363 2023-11-16 12:03:26,094 - mmdet - INFO - Epoch [35][1450/1833] lr: 2.000e-06, eta: 0:43:48, time: 1.168, data_time: 0.080, memory: 16000, loss_rpn_cls: 0.0158, loss_rpn_bbox: 0.0266, loss_cls: 0.1227, acc: 95.3721, loss_bbox: 0.1707, loss_mask: 0.1957, loss: 0.5315 2023-11-16 12:04:26,034 - mmdet - INFO - Epoch [35][1500/1833] lr: 2.000e-06, eta: 0:42:48, time: 1.199, data_time: 0.069, memory: 16000, loss_rpn_cls: 0.0165, loss_rpn_bbox: 0.0276, loss_cls: 0.1253, acc: 95.2518, loss_bbox: 0.1765, loss_mask: 0.1967, loss: 0.5425 2023-11-16 12:05:25,580 - mmdet - INFO - Epoch [35][1550/1833] lr: 2.000e-06, eta: 0:41:49, time: 1.191, data_time: 0.070, memory: 16000, loss_rpn_cls: 0.0164, loss_rpn_bbox: 0.0266, loss_cls: 0.1251, acc: 95.3331, loss_bbox: 0.1738, loss_mask: 0.1975, loss: 0.5395 2023-11-16 12:06:25,156 - mmdet - INFO - Epoch [35][1600/1833] lr: 2.000e-06, eta: 0:40:50, time: 1.192, data_time: 0.073, memory: 16000, loss_rpn_cls: 0.0161, loss_rpn_bbox: 0.0263, loss_cls: 0.1228, acc: 95.3499, loss_bbox: 0.1716, loss_mask: 0.1961, loss: 0.5330 2023-11-16 12:07:24,020 - mmdet - INFO - Epoch [35][1650/1833] lr: 2.000e-06, eta: 0:39:51, time: 1.177, data_time: 0.066, memory: 16000, loss_rpn_cls: 0.0155, loss_rpn_bbox: 0.0270, loss_cls: 0.1225, acc: 95.3596, loss_bbox: 0.1750, loss_mask: 0.1969, loss: 0.5368 2023-11-16 12:08:22,733 - mmdet - INFO - Epoch [35][1700/1833] lr: 2.000e-06, eta: 0:38:51, time: 1.174, data_time: 0.060, memory: 16000, loss_rpn_cls: 0.0161, loss_rpn_bbox: 0.0277, loss_cls: 0.1236, acc: 95.3069, loss_bbox: 0.1741, loss_mask: 0.1978, loss: 0.5393 2023-11-16 12:09:22,929 - mmdet - INFO - Epoch [35][1750/1833] lr: 2.000e-06, eta: 0:37:52, time: 1.204, data_time: 0.071, memory: 16000, loss_rpn_cls: 0.0163, loss_rpn_bbox: 0.0272, loss_cls: 0.1257, acc: 95.2292, loss_bbox: 0.1772, loss_mask: 0.1981, loss: 0.5445 2023-11-16 12:10:23,056 - mmdet - INFO - Epoch [35][1800/1833] lr: 2.000e-06, eta: 0:36:53, time: 1.203, data_time: 0.074, memory: 16000, loss_rpn_cls: 0.0156, loss_rpn_bbox: 0.0266, loss_cls: 0.1238, acc: 95.3058, loss_bbox: 0.1729, loss_mask: 0.1969, loss: 0.5359 2023-11-16 12:11:02,996 - mmdet - INFO - Saving checkpoint at 35 epochs 2023-11-16 12:11:48,450 - mmdet - INFO - Evaluating bbox... 2023-11-16 12:12:15,704 - 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 ] = 0.720 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.552 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.341 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.545 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 ] = 0.623 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 ] = 0.461 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 ] = 0.769 2023-11-16 12:12:15,706 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.600 | bicycle | 0.409 | car | 0.507 | | motorcycle | 0.504 | airplane | 0.716 | bus | 0.736 | | train | 0.700 | truck | 0.458 | boat | 0.343 | | traffic light | 0.316 | fire hydrant | 0.754 | stop sign | 0.703 | | parking meter | 0.546 | bench | 0.333 | bird | 0.438 | | cat | 0.738 | dog | 0.715 | horse | 0.655 | | sheep | 0.623 | cow | 0.633 | elephant | 0.722 | | bear | 0.760 | zebra | 0.691 | giraffe | 0.726 | | backpack | 0.235 | umbrella | 0.481 | handbag | 0.267 | | tie | 0.444 | suitcase | 0.491 | frisbee | 0.735 | | skis | 0.325 | snowboard | 0.476 | sports ball | 0.493 | | kite | 0.489 | baseball bat | 0.418 | baseball glove | 0.454 | | skateboard | 0.617 | surfboard | 0.475 | tennis racket | 0.585 | | bottle | 0.477 | wine glass | 0.433 | cup | 0.519 | | fork | 0.520 | knife | 0.317 | spoon | 0.345 | | bowl | 0.504 | banana | 0.288 | apple | 0.290 | | sandwich | 0.487 | orange | 0.362 | broccoli | 0.255 | | carrot | 0.273 | hot dog | 0.472 | pizza | 0.577 | | donut | 0.580 | cake | 0.451 | chair | 0.385 | | couch | 0.506 | potted plant | 0.377 | bed | 0.477 | | dining table | 0.340 | toilet | 0.681 | tv | 0.649 | | laptop | 0.714 | mouse | 0.674 | remote | 0.459 | | keyboard | 0.576 | cell phone | 0.479 | microwave | 0.687 | | oven | 0.429 | toaster | 0.511 | sink | 0.466 | | refrigerator | 0.699 | book | 0.216 | clock | 0.517 | | vase | 0.453 | scissors | 0.461 | teddy bear | 0.570 | | hair drier | 0.260 | toothbrush | 0.354 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-16 12:12:15,707 - mmdet - INFO - Evaluating segm... 2023-11-16 12:12:43,562 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.449 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.690 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.484 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.252 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 ] = 0.635 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 ] = 0.396 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.596 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.715 2023-11-16 12:12:43,564 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.521 | bicycle | 0.254 | car | 0.466 | | motorcycle | 0.421 | airplane | 0.541 | bus | 0.716 | | train | 0.691 | truck | 0.429 | boat | 0.309 | | traffic light | 0.305 | fire hydrant | 0.718 | stop sign | 0.683 | | parking meter | 0.542 | bench | 0.252 | bird | 0.366 | | cat | 0.735 | dog | 0.674 | horse | 0.488 | | sheep | 0.550 | cow | 0.537 | elephant | 0.649 | | bear | 0.735 | zebra | 0.604 | giraffe | 0.566 | | backpack | 0.236 | umbrella | 0.530 | handbag | 0.237 | | tie | 0.398 | suitcase | 0.510 | frisbee | 0.681 | | skis | 0.077 | snowboard | 0.307 | sports ball | 0.475 | | kite | 0.347 | baseball bat | 0.318 | baseball glove | 0.459 | | skateboard | 0.400 | surfboard | 0.388 | tennis racket | 0.612 | | bottle | 0.449 | wine glass | 0.393 | cup | 0.510 | | fork | 0.271 | knife | 0.218 | spoon | 0.245 | | bowl | 0.460 | banana | 0.238 | apple | 0.284 | | sandwich | 0.500 | orange | 0.360 | broccoli | 0.233 | | carrot | 0.238 | hot dog | 0.384 | pizza | 0.556 | | donut | 0.572 | cake | 0.455 | chair | 0.276 | | couch | 0.422 | potted plant | 0.312 | bed | 0.386 | | dining table | 0.202 | toilet | 0.654 | tv | 0.669 | | laptop | 0.685 | mouse | 0.645 | remote | 0.411 | | keyboard | 0.554 | cell phone | 0.443 | microwave | 0.682 | | oven | 0.392 | toaster | 0.554 | sink | 0.429 | | refrigerator | 0.690 | book | 0.159 | clock | 0.515 | | vase | 0.441 | scissors | 0.343 | teddy bear | 0.541 | | hair drier | 0.167 | toothbrush | 0.247 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-16 12:12:43,964 - mmdet - INFO - The previous best checkpoint /mnt/petrelfs/lizhiqi/DINO/detection/work_dirs/mask_rcnn_flash_internimage_s_fpn_3x_coco_0.4/best_bbox_mAP_epoch_34.pth was removed 2023-11-16 12:12:46,049 - mmdet - INFO - Now best checkpoint is saved as best_bbox_mAP_epoch_35.pth. 2023-11-16 12:12:46,049 - mmdet - INFO - Best bbox_mAP is 0.5050 at 35 epoch. 2023-11-16 12:12:46,050 - mmdet - INFO - Exp name: mask_rcnn_flash_internimage_s_fpn_3x_coco_0.4.py 2023-11-16 12:12:46,050 - mmdet - INFO - Epoch(val) [35][625] bbox_mAP: 0.5050, bbox_mAP_50: 0.7197, bbox_mAP_75: 0.5522, bbox_mAP_s: 0.3411, bbox_mAP_m: 0.5447, bbox_mAP_l: 0.6466, bbox_mAP_copypaste: 0.5050 0.7197 0.5522 0.3411 0.5447 0.6466, segm_mAP: 0.4489, segm_mAP_50: 0.6898, segm_mAP_75: 0.4840, segm_mAP_s: 0.2521, segm_mAP_m: 0.4795, segm_mAP_l: 0.6346, segm_mAP_copypaste: 0.4489 0.6898 0.4840 0.2521 0.4795 0.6346 2023-11-16 12:13:51,018 - mmdet - INFO - Epoch [36][50/1833] lr: 2.000e-06, eta: 0:35:13, time: 1.299, data_time: 0.132, memory: 16000, loss_rpn_cls: 0.0155, loss_rpn_bbox: 0.0278, loss_cls: 0.1229, acc: 95.3376, loss_bbox: 0.1744, loss_mask: 0.1955, loss: 0.5361 2023-11-16 12:14:51,365 - mmdet - INFO - Epoch [36][100/1833] lr: 2.000e-06, eta: 0:34:14, time: 1.207, data_time: 0.068, memory: 16000, loss_rpn_cls: 0.0174, loss_rpn_bbox: 0.0280, loss_cls: 0.1281, acc: 95.1673, loss_bbox: 0.1771, loss_mask: 0.1989, loss: 0.5495 2023-11-16 12:15:52,298 - mmdet - INFO - Epoch [36][150/1833] lr: 2.000e-06, eta: 0:33:15, time: 1.219, data_time: 0.067, memory: 16000, loss_rpn_cls: 0.0168, loss_rpn_bbox: 0.0274, loss_cls: 0.1266, acc: 95.1998, loss_bbox: 0.1768, loss_mask: 0.2000, loss: 0.5475 2023-11-16 12:16:52,722 - mmdet - INFO - Epoch [36][200/1833] lr: 2.000e-06, eta: 0:32:16, time: 1.208, data_time: 0.069, memory: 16000, loss_rpn_cls: 0.0159, loss_rpn_bbox: 0.0257, loss_cls: 0.1223, acc: 95.3730, loss_bbox: 0.1727, loss_mask: 0.1944, loss: 0.5310 2023-11-16 12:17:53,585 - mmdet - INFO - Epoch [36][250/1833] lr: 2.000e-06, eta: 0:31:16, time: 1.217, data_time: 0.066, memory: 16000, loss_rpn_cls: 0.0168, loss_rpn_bbox: 0.0283, loss_cls: 0.1281, acc: 95.1431, loss_bbox: 0.1772, loss_mask: 0.1998, loss: 0.5502 2023-11-16 12:18:53,823 - mmdet - INFO - Epoch [36][300/1833] lr: 2.000e-06, eta: 0:30:17, time: 1.205, data_time: 0.071, memory: 16000, loss_rpn_cls: 0.0156, loss_rpn_bbox: 0.0267, loss_cls: 0.1234, acc: 95.3408, loss_bbox: 0.1734, loss_mask: 0.1960, loss: 0.5351 2023-11-16 12:19:54,207 - mmdet - INFO - Epoch [36][350/1833] lr: 2.000e-06, eta: 0:29:18, time: 1.208, data_time: 0.068, memory: 16000, loss_rpn_cls: 0.0164, loss_rpn_bbox: 0.0270, loss_cls: 0.1258, acc: 95.2651, loss_bbox: 0.1756, loss_mask: 0.1967, loss: 0.5414 2023-11-16 12:20:54,186 - mmdet - INFO - Epoch [36][400/1833] lr: 2.000e-06, eta: 0:28:19, time: 1.200, data_time: 0.075, memory: 16000, loss_rpn_cls: 0.0159, loss_rpn_bbox: 0.0274, loss_cls: 0.1248, acc: 95.2635, loss_bbox: 0.1769, loss_mask: 0.1987, loss: 0.5438 2023-11-16 12:21:54,234 - mmdet - INFO - Epoch [36][450/1833] lr: 2.000e-06, eta: 0:27:19, time: 1.201, data_time: 0.068, memory: 16000, loss_rpn_cls: 0.0155, loss_rpn_bbox: 0.0270, loss_cls: 0.1242, acc: 95.3472, loss_bbox: 0.1739, loss_mask: 0.1977, loss: 0.5383 2023-11-16 12:22:55,074 - mmdet - INFO - Epoch [36][500/1833] lr: 2.000e-06, eta: 0:26:20, time: 1.217, data_time: 0.070, memory: 16000, loss_rpn_cls: 0.0161, loss_rpn_bbox: 0.0272, loss_cls: 0.1222, acc: 95.3602, loss_bbox: 0.1730, loss_mask: 0.1969, loss: 0.5354 2023-11-16 12:23:56,613 - mmdet - INFO - Epoch [36][550/1833] lr: 2.000e-06, eta: 0:25:21, time: 1.231, data_time: 0.073, memory: 16000, loss_rpn_cls: 0.0166, loss_rpn_bbox: 0.0278, loss_cls: 0.1270, acc: 95.1670, loss_bbox: 0.1773, loss_mask: 0.1999, loss: 0.5486 2023-11-16 12:24:56,032 - mmdet - INFO - Epoch [36][600/1833] lr: 2.000e-06, eta: 0:24:21, time: 1.188, data_time: 0.066, memory: 16000, loss_rpn_cls: 0.0161, loss_rpn_bbox: 0.0275, loss_cls: 0.1260, acc: 95.2084, loss_bbox: 0.1781, loss_mask: 0.1979, loss: 0.5457 2023-11-16 12:25:56,412 - mmdet - INFO - Epoch [36][650/1833] lr: 2.000e-06, eta: 0:23:22, time: 1.208, data_time: 0.071, memory: 16000, loss_rpn_cls: 0.0168, loss_rpn_bbox: 0.0267, loss_cls: 0.1250, acc: 95.2851, loss_bbox: 0.1745, loss_mask: 0.1973, loss: 0.5402 2023-11-16 12:26:58,062 - mmdet - INFO - Epoch [36][700/1833] lr: 2.000e-06, eta: 0:22:23, time: 1.233, data_time: 0.070, memory: 16000, loss_rpn_cls: 0.0176, loss_rpn_bbox: 0.0286, loss_cls: 0.1286, acc: 95.1200, loss_bbox: 0.1806, loss_mask: 0.2003, loss: 0.5557 2023-11-16 12:27:58,579 - mmdet - INFO - Epoch [36][750/1833] lr: 2.000e-06, eta: 0:21:24, time: 1.210, data_time: 0.064, memory: 16000, loss_rpn_cls: 0.0171, loss_rpn_bbox: 0.0277, loss_cls: 0.1259, acc: 95.2277, loss_bbox: 0.1755, loss_mask: 0.2006, loss: 0.5467 2023-11-16 12:28:58,417 - mmdet - INFO - Epoch [36][800/1833] lr: 2.000e-06, eta: 0:20:24, time: 1.197, data_time: 0.063, memory: 16000, loss_rpn_cls: 0.0159, loss_rpn_bbox: 0.0274, loss_cls: 0.1240, acc: 95.2779, loss_bbox: 0.1739, loss_mask: 0.1985, loss: 0.5396 2023-11-16 12:29:58,290 - mmdet - INFO - Epoch [36][850/1833] lr: 2.000e-06, eta: 0:19:25, time: 1.197, data_time: 0.071, memory: 16000, loss_rpn_cls: 0.0157, loss_rpn_bbox: 0.0263, loss_cls: 0.1237, acc: 95.3481, loss_bbox: 0.1724, loss_mask: 0.1961, loss: 0.5342 2023-11-16 12:30:58,325 - mmdet - INFO - Epoch [36][900/1833] lr: 2.000e-06, eta: 0:18:26, time: 1.201, data_time: 0.072, memory: 16000, loss_rpn_cls: 0.0149, loss_rpn_bbox: 0.0267, loss_cls: 0.1219, acc: 95.3646, loss_bbox: 0.1705, loss_mask: 0.1963, loss: 0.5303 2023-11-16 12:31:59,264 - mmdet - INFO - Epoch [36][950/1833] lr: 2.000e-06, eta: 0:17:27, time: 1.219, data_time: 0.074, memory: 16000, loss_rpn_cls: 0.0159, loss_rpn_bbox: 0.0269, loss_cls: 0.1219, acc: 95.3782, loss_bbox: 0.1708, loss_mask: 0.1951, loss: 0.5305 2023-11-16 12:32:58,312 - mmdet - INFO - Epoch [36][1000/1833] lr: 2.000e-06, eta: 0:16:27, time: 1.181, data_time: 0.068, memory: 16000, loss_rpn_cls: 0.0158, loss_rpn_bbox: 0.0264, loss_cls: 0.1246, acc: 95.3301, loss_bbox: 0.1740, loss_mask: 0.1968, loss: 0.5376 2023-11-16 12:33:58,945 - mmdet - INFO - Epoch [36][1050/1833] lr: 2.000e-06, eta: 0:15:28, time: 1.213, data_time: 0.074, memory: 16000, loss_rpn_cls: 0.0168, loss_rpn_bbox: 0.0279, loss_cls: 0.1274, acc: 95.2127, loss_bbox: 0.1792, loss_mask: 0.1993, loss: 0.5506 2023-11-16 12:34:58,696 - mmdet - INFO - Epoch [36][1100/1833] lr: 2.000e-06, eta: 0:14:29, time: 1.195, data_time: 0.073, memory: 16000, loss_rpn_cls: 0.0164, loss_rpn_bbox: 0.0276, loss_cls: 0.1261, acc: 95.2361, loss_bbox: 0.1779, loss_mask: 0.1978, loss: 0.5458 2023-11-16 12:35:58,641 - mmdet - INFO - Epoch [36][1150/1833] lr: 2.000e-06, eta: 0:13:29, time: 1.199, data_time: 0.071, memory: 16000, loss_rpn_cls: 0.0164, loss_rpn_bbox: 0.0278, loss_cls: 0.1265, acc: 95.1755, loss_bbox: 0.1777, loss_mask: 0.1973, loss: 0.5456 2023-11-16 12:37:00,985 - mmdet - INFO - Epoch [36][1200/1833] lr: 2.000e-06, eta: 0:12:30, time: 1.247, data_time: 0.074, memory: 16000, loss_rpn_cls: 0.0173, loss_rpn_bbox: 0.0279, loss_cls: 0.1271, acc: 95.2211, loss_bbox: 0.1767, loss_mask: 0.1980, loss: 0.5470 2023-11-16 12:38:00,680 - mmdet - INFO - Epoch [36][1250/1833] lr: 2.000e-06, eta: 0:11:31, time: 1.194, data_time: 0.072, memory: 16000, loss_rpn_cls: 0.0160, loss_rpn_bbox: 0.0269, loss_cls: 0.1219, acc: 95.3842, loss_bbox: 0.1713, loss_mask: 0.1982, loss: 0.5343 2023-11-16 12:38:59,859 - mmdet - INFO - Epoch [36][1300/1833] lr: 2.000e-06, eta: 0:10:32, time: 1.183, data_time: 0.069, memory: 16000, loss_rpn_cls: 0.0153, loss_rpn_bbox: 0.0274, loss_cls: 0.1236, acc: 95.2925, loss_bbox: 0.1755, loss_mask: 0.1998, loss: 0.5416 2023-11-16 12:40:08,547 - mmdet - INFO - Epoch [36][1350/1833] lr: 2.000e-06, eta: 0:09:32, time: 1.374, data_time: 0.152, memory: 16000, loss_rpn_cls: 0.0152, loss_rpn_bbox: 0.0266, loss_cls: 0.1240, acc: 95.2935, loss_bbox: 0.1736, loss_mask: 0.1974, loss: 0.5368 2023-11-16 12:41:12,661 - mmdet - INFO - Epoch [36][1400/1833] lr: 2.000e-06, eta: 0:08:33, time: 1.282, data_time: 0.134, memory: 16000, loss_rpn_cls: 0.0160, loss_rpn_bbox: 0.0271, loss_cls: 0.1254, acc: 95.2596, loss_bbox: 0.1755, loss_mask: 0.1986, loss: 0.5426 2023-11-16 12:42:12,526 - mmdet - INFO - Epoch [36][1450/1833] lr: 2.000e-06, eta: 0:07:34, time: 1.197, data_time: 0.066, memory: 16000, loss_rpn_cls: 0.0165, loss_rpn_bbox: 0.0275, loss_cls: 0.1262, acc: 95.2464, loss_bbox: 0.1755, loss_mask: 0.1986, loss: 0.5444 2023-11-16 12:43:12,162 - mmdet - INFO - Epoch [36][1500/1833] lr: 2.000e-06, eta: 0:06:34, time: 1.193, data_time: 0.067, memory: 16000, loss_rpn_cls: 0.0159, loss_rpn_bbox: 0.0267, loss_cls: 0.1238, acc: 95.3025, loss_bbox: 0.1739, loss_mask: 0.1970, loss: 0.5374 2023-11-16 12:44:11,694 - mmdet - INFO - Epoch [36][1550/1833] lr: 2.000e-06, eta: 0:05:35, time: 1.191, data_time: 0.067, memory: 16000, loss_rpn_cls: 0.0162, loss_rpn_bbox: 0.0278, loss_cls: 0.1256, acc: 95.2247, loss_bbox: 0.1746, loss_mask: 0.1982, loss: 0.5424 2023-11-16 12:45:11,641 - mmdet - INFO - Epoch [36][1600/1833] lr: 2.000e-06, eta: 0:04:36, time: 1.199, data_time: 0.067, memory: 16000, loss_rpn_cls: 0.0160, loss_rpn_bbox: 0.0278, loss_cls: 0.1265, acc: 95.2067, loss_bbox: 0.1767, loss_mask: 0.2002, loss: 0.5472 2023-11-16 12:46:11,167 - mmdet - INFO - Epoch [36][1650/1833] lr: 2.000e-06, eta: 0:03:37, time: 1.191, data_time: 0.066, memory: 16000, loss_rpn_cls: 0.0167, loss_rpn_bbox: 0.0271, loss_cls: 0.1268, acc: 95.1655, loss_bbox: 0.1776, loss_mask: 0.1982, loss: 0.5465 2023-11-16 12:47:10,097 - mmdet - INFO - Epoch [36][1700/1833] lr: 2.000e-06, eta: 0:02:37, time: 1.179, data_time: 0.066, memory: 16000, loss_rpn_cls: 0.0150, loss_rpn_bbox: 0.0263, loss_cls: 0.1219, acc: 95.3943, loss_bbox: 0.1711, loss_mask: 0.1983, loss: 0.5326 2023-11-16 12:48:09,955 - mmdet - INFO - Epoch [36][1750/1833] lr: 2.000e-06, eta: 0:01:38, time: 1.197, data_time: 0.067, memory: 16000, loss_rpn_cls: 0.0155, loss_rpn_bbox: 0.0264, loss_cls: 0.1228, acc: 95.3760, loss_bbox: 0.1726, loss_mask: 0.1964, loss: 0.5336 2023-11-16 12:49:08,889 - mmdet - INFO - Epoch [36][1800/1833] lr: 2.000e-06, eta: 0:00:39, time: 1.179, data_time: 0.076, memory: 16000, loss_rpn_cls: 0.0164, loss_rpn_bbox: 0.0269, loss_cls: 0.1253, acc: 95.2574, loss_bbox: 0.1735, loss_mask: 0.1967, loss: 0.5388 2023-11-16 12:49:49,359 - mmdet - INFO - Saving checkpoint at 36 epochs 2023-11-16 12:50:34,733 - mmdet - INFO - Evaluating bbox... 2023-11-16 12:51:00,083 - 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 ] = 0.720 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.552 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.339 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.543 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 ] = 0.623 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 ] = 0.459 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 ] = 0.772 2023-11-16 12:51:00,085 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.600 | bicycle | 0.407 | car | 0.506 | | motorcycle | 0.505 | airplane | 0.709 | bus | 0.736 | | train | 0.709 | truck | 0.458 | boat | 0.341 | | traffic light | 0.317 | fire hydrant | 0.765 | stop sign | 0.705 | | parking meter | 0.542 | bench | 0.334 | bird | 0.436 | | cat | 0.740 | dog | 0.717 | horse | 0.657 | | sheep | 0.624 | cow | 0.633 | elephant | 0.725 | | bear | 0.770 | zebra | 0.691 | giraffe | 0.728 | | backpack | 0.236 | umbrella | 0.480 | handbag | 0.266 | | tie | 0.442 | suitcase | 0.496 | frisbee | 0.735 | | skis | 0.323 | snowboard | 0.479 | sports ball | 0.496 | | kite | 0.492 | baseball bat | 0.417 | baseball glove | 0.453 | | skateboard | 0.617 | surfboard | 0.470 | tennis racket | 0.589 | | bottle | 0.479 | wine glass | 0.434 | cup | 0.520 | | fork | 0.515 | knife | 0.320 | spoon | 0.340 | | bowl | 0.503 | banana | 0.290 | apple | 0.291 | | sandwich | 0.478 | orange | 0.364 | broccoli | 0.254 | | carrot | 0.273 | hot dog | 0.468 | pizza | 0.577 | | donut | 0.580 | cake | 0.450 | chair | 0.386 | | couch | 0.508 | potted plant | 0.380 | bed | 0.479 | | dining table | 0.338 | toilet | 0.684 | tv | 0.649 | | laptop | 0.712 | mouse | 0.676 | remote | 0.464 | | keyboard | 0.572 | cell phone | 0.475 | microwave | 0.690 | | oven | 0.432 | toaster | 0.503 | sink | 0.461 | | refrigerator | 0.692 | book | 0.214 | clock | 0.517 | | vase | 0.452 | scissors | 0.464 | teddy bear | 0.567 | | hair drier | 0.254 | toothbrush | 0.355 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-16 12:51:00,085 - mmdet - INFO - Evaluating segm... 2023-11-16 12:51:30,605 - mmdet - INFO - Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.449 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.690 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.484 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.251 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 ] = 0.633 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 ] = 0.394 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 ] = 0.716 2023-11-16 12:51:30,608 - mmdet - INFO - +---------------+-------+--------------+-------+----------------+-------+ | category | AP | category | AP | category | AP | +---------------+-------+--------------+-------+----------------+-------+ | person | 0.521 | bicycle | 0.257 | car | 0.465 | | motorcycle | 0.421 | airplane | 0.535 | bus | 0.714 | | train | 0.691 | truck | 0.430 | boat | 0.308 | | traffic light | 0.307 | fire hydrant | 0.719 | stop sign | 0.682 | | parking meter | 0.545 | bench | 0.253 | bird | 0.364 | | cat | 0.730 | dog | 0.668 | horse | 0.488 | | sheep | 0.551 | cow | 0.536 | elephant | 0.651 | | bear | 0.740 | zebra | 0.601 | giraffe | 0.568 | | backpack | 0.235 | umbrella | 0.532 | handbag | 0.240 | | tie | 0.395 | suitcase | 0.515 | frisbee | 0.682 | | skis | 0.076 | snowboard | 0.306 | sports ball | 0.478 | | kite | 0.345 | baseball bat | 0.316 | baseball glove | 0.462 | | skateboard | 0.400 | surfboard | 0.388 | tennis racket | 0.615 | | bottle | 0.450 | wine glass | 0.394 | cup | 0.512 | | fork | 0.269 | knife | 0.219 | spoon | 0.243 | | bowl | 0.461 | banana | 0.242 | apple | 0.282 | | sandwich | 0.498 | orange | 0.361 | broccoli | 0.233 | | carrot | 0.238 | hot dog | 0.390 | pizza | 0.558 | | donut | 0.573 | cake | 0.455 | chair | 0.275 | | couch | 0.422 | potted plant | 0.314 | bed | 0.387 | | dining table | 0.203 | toilet | 0.653 | tv | 0.667 | | laptop | 0.687 | mouse | 0.641 | remote | 0.412 | | keyboard | 0.555 | cell phone | 0.441 | microwave | 0.683 | | oven | 0.388 | toaster | 0.534 | sink | 0.426 | | refrigerator | 0.680 | book | 0.159 | clock | 0.512 | | vase | 0.443 | scissors | 0.340 | teddy bear | 0.541 | | hair drier | 0.165 | toothbrush | 0.249 | None | None | +---------------+-------+--------------+-------+----------------+-------+ 2023-11-16 12:51:30,988 - mmdet - INFO - Exp name: mask_rcnn_flash_internimage_s_fpn_3x_coco_0.4.py 2023-11-16 12:51:30,989 - mmdet - INFO - Epoch(val) [36][625] bbox_mAP: 0.5050, bbox_mAP_50: 0.7198, bbox_mAP_75: 0.5525, bbox_mAP_s: 0.3394, bbox_mAP_m: 0.5433, bbox_mAP_l: 0.6469, bbox_mAP_copypaste: 0.5050 0.7198 0.5525 0.3394 0.5433 0.6469, segm_mAP: 0.4486, segm_mAP_50: 0.6899, segm_mAP_75: 0.4839, segm_mAP_s: 0.2513, segm_mAP_m: 0.4800, segm_mAP_l: 0.6332, segm_mAP_copypaste: 0.4486 0.6899 0.4839 0.2513 0.4800 0.6332