diff --git "a/finetune/finetune_faster-rcnn_12k_coco/20221022_163550.log" "b/finetune/finetune_faster-rcnn_12k_coco/20221022_163550.log" new file mode 100644--- /dev/null +++ "b/finetune/finetune_faster-rcnn_12k_coco/20221022_163550.log" @@ -0,0 +1,1237 @@ +2022-10-22 16:35:50,278 - mmdet - INFO - Environment info: +------------------------------------------------------------ +sys.platform: linux +Python: 3.7.3 (default, Jan 22 2021, 20:04:44) [GCC 8.3.0] +CUDA available: True +GPU 0,1,2,3,4,5,6,7: A100-SXM-80GB +CUDA_HOME: /usr/local/cuda +NVCC: Cuda compilation tools, release 11.3, V11.3.109 +GCC: x86_64-linux-gnu-gcc (Debian 8.3.0-6) 8.3.0 +PyTorch: 1.10.0 +PyTorch compiling details: PyTorch built with: + - GCC 7.3 + - C++ Version: 201402 + - Intel(R) Math Kernel Library Version 2020.0.0 Product Build 20191122 for Intel(R) 64 architecture applications + - Intel(R) MKL-DNN v2.2.3 (Git Hash 7336ca9f055cf1bfa13efb658fe15dc9b41f0740) + - OpenMP 201511 (a.k.a. OpenMP 4.5) + - LAPACK is enabled (usually provided by MKL) + - NNPACK is enabled + - CPU capability usage: AVX512 + - CUDA Runtime 11.3 + - NVCC architecture flags: -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 + - CuDNN 8.2 + - Magma 2.5.2 + - Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.3, CUDNN_VERSION=8.2.0, CXX_COMPILER=/opt/rh/devtoolset-7/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-sign-compare -Wno-unused-parameter -Wno-unused-variable -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 -Wno-stringop-overflow, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, TORCH_VERSION=1.10.0, USE_CUDA=ON, USE_CUDNN=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=ON, USE_NNPACK=ON, USE_OPENMP=ON, + +TorchVision: 0.11.1+cu113 +OpenCV: 4.6.0 +MMCV: 1.6.1 +MMCV Compiler: GCC 9.3 +MMCV CUDA Compiler: 11.3 +MMDetection: 2.25.2+a7ef785 +------------------------------------------------------------ + +2022-10-22 16:35:50,589 - mmdet - INFO - Distributed training: True +2022-10-22 16:35:50,857 - mmdet - INFO - Config: +model = dict( + type='MaskRCNN', + backbone=dict( + type='ResNet', + depth=50, + num_stages=4, + out_indices=(0, 1, 2, 3), + frozen_stages=1, + norm_cfg=dict(type='SyncBN', requires_grad=True), + norm_eval=True, + style='pytorch', + init_cfg=dict(type='Pretrained', checkpoint='torchvision://resnet50')), + neck=dict( + type='FPN', + in_channels=[256, 512, 1024, 2048], + out_channels=256, + num_outs=5, + norm_cfg=dict(type='SyncBN', requires_grad=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='Shared4Conv1FCBBoxHead', + 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=None, + mask_head=None), + 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), + dict(type='Resize', img_scale=(1333, 800), keep_ratio=True), + dict(type='RandomFlip', flip_ratio=0.5), + 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']) +] +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=2, + 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), + dict(type='Resize', img_scale=(1333, 800), keep_ratio=True), + dict(type='RandomFlip', flip_ratio=0.5), + 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']) + ]), + 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( + interval=12000, metric='bbox', save_best='auto', gpu_collect=True) +optimizer = dict(type='SGD', lr=0.03, momentum=0.9, weight_decay=5e-05) +optimizer_config = dict(grad_clip=None) +lr_config = dict( + policy='step', + warmup='linear', + warmup_iters=500, + warmup_ratio=0.001, + step=[9000, 11000], + by_epoch=False) +runner = dict(type='IterBasedRunner', max_iters=12000) +checkpoint_config = dict(interval=12000) +log_config = dict(interval=50, hooks=[dict(type='TextLoggerHook')]) +custom_hooks = [ + dict(type='NumClassCheckHook'), + dict( + type='MMDetWandbHook', + init_kwargs=dict(project='I2B', group='semi-coco'), + interval=50, + num_eval_images=0, + log_checkpoint=False) +] +dist_params = dict(backend='nccl') +log_level = 'INFO' +load_from = 'pretrain/selfsup_mask-rcnn_mstrain-soft-teacher_sampler-4096_temp0.5/final_model.pth' +resume_from = None +workflow = [('train', 1)] +opencv_num_threads = 0 +mp_start_method = 'fork' +auto_scale_lr = dict(enable=False, base_batch_size=16) +custom_imports = None +norm_cfg = dict(type='SyncBN', requires_grad=True) +work_dir = 'work_dirs/finetune_faster-rcnn_12k_coco' +auto_resume = False +gpu_ids = range(0, 8) + +2022-10-22 16:35:50,858 - mmdet - INFO - Set random seed to 42, deterministic: False +2022-10-22 16:35:51,212 - mmdet - INFO - initialize ResNet with init_cfg {'type': 'Pretrained', 'checkpoint': 'torchvision://resnet50'} +2022-10-22 16:36:04,134 - mmdet - INFO - initialize FPN with init_cfg {'type': 'Xavier', 'layer': 'Conv2d', 'distribution': 'uniform'} +2022-10-22 16:36:04,180 - mmdet - INFO - initialize RPNHead with init_cfg {'type': 'Normal', 'layer': 'Conv2d', 'std': 0.01} +2022-10-22 16:36:04,185 - mmdet - INFO - initialize Shared4Conv1FCBBoxHead 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.conv1.weight - torch.Size([64, 3, 7, 7]): +PretrainedInit: load from torchvision://resnet50 + +backbone.bn1.weight - torch.Size([64]): +PretrainedInit: load from torchvision://resnet50 + +backbone.bn1.bias - torch.Size([64]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer1.0.conv1.weight - torch.Size([64, 64, 1, 1]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer1.0.bn1.weight - torch.Size([64]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer1.0.bn1.bias - torch.Size([64]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer1.0.conv2.weight - torch.Size([64, 64, 3, 3]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer1.0.bn2.weight - torch.Size([64]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer1.0.bn2.bias - torch.Size([64]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer1.0.conv3.weight - torch.Size([256, 64, 1, 1]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer1.0.bn3.weight - torch.Size([256]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer1.0.bn3.bias - torch.Size([256]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer1.0.downsample.0.weight - torch.Size([256, 64, 1, 1]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer1.0.downsample.1.weight - torch.Size([256]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer1.0.downsample.1.bias - torch.Size([256]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer1.1.conv1.weight - torch.Size([64, 256, 1, 1]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer1.1.bn1.weight - torch.Size([64]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer1.1.bn1.bias - torch.Size([64]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer1.1.conv2.weight - torch.Size([64, 64, 3, 3]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer1.1.bn2.weight - torch.Size([64]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer1.1.bn2.bias - torch.Size([64]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer1.1.conv3.weight - torch.Size([256, 64, 1, 1]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer1.1.bn3.weight - torch.Size([256]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer1.1.bn3.bias - torch.Size([256]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer1.2.conv1.weight - torch.Size([64, 256, 1, 1]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer1.2.bn1.weight - torch.Size([64]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer1.2.bn1.bias - torch.Size([64]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer1.2.conv2.weight - torch.Size([64, 64, 3, 3]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer1.2.bn2.weight - torch.Size([64]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer1.2.bn2.bias - torch.Size([64]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer1.2.conv3.weight - torch.Size([256, 64, 1, 1]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer1.2.bn3.weight - torch.Size([256]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer1.2.bn3.bias - torch.Size([256]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer2.0.conv1.weight - torch.Size([128, 256, 1, 1]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer2.0.bn1.weight - torch.Size([128]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer2.0.bn1.bias - torch.Size([128]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer2.0.conv2.weight - torch.Size([128, 128, 3, 3]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer2.0.bn2.weight - torch.Size([128]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer2.0.bn2.bias - torch.Size([128]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer2.0.conv3.weight - torch.Size([512, 128, 1, 1]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer2.0.bn3.weight - torch.Size([512]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer2.0.bn3.bias - torch.Size([512]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer2.0.downsample.0.weight - torch.Size([512, 256, 1, 1]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer2.0.downsample.1.weight - torch.Size([512]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer2.0.downsample.1.bias - torch.Size([512]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer2.1.conv1.weight - torch.Size([128, 512, 1, 1]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer2.1.bn1.weight - torch.Size([128]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer2.1.bn1.bias - torch.Size([128]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer2.1.conv2.weight - torch.Size([128, 128, 3, 3]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer2.1.bn2.weight - torch.Size([128]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer2.1.bn2.bias - torch.Size([128]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer2.1.conv3.weight - torch.Size([512, 128, 1, 1]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer2.1.bn3.weight - torch.Size([512]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer2.1.bn3.bias - torch.Size([512]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer2.2.conv1.weight - torch.Size([128, 512, 1, 1]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer2.2.bn1.weight - torch.Size([128]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer2.2.bn1.bias - torch.Size([128]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer2.2.conv2.weight - torch.Size([128, 128, 3, 3]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer2.2.bn2.weight - torch.Size([128]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer2.2.bn2.bias - torch.Size([128]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer2.2.conv3.weight - torch.Size([512, 128, 1, 1]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer2.2.bn3.weight - torch.Size([512]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer2.2.bn3.bias - torch.Size([512]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer2.3.conv1.weight - torch.Size([128, 512, 1, 1]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer2.3.bn1.weight - torch.Size([128]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer2.3.bn1.bias - torch.Size([128]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer2.3.conv2.weight - torch.Size([128, 128, 3, 3]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer2.3.bn2.weight - torch.Size([128]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer2.3.bn2.bias - torch.Size([128]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer2.3.conv3.weight - torch.Size([512, 128, 1, 1]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer2.3.bn3.weight - torch.Size([512]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer2.3.bn3.bias - torch.Size([512]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer3.0.conv1.weight - torch.Size([256, 512, 1, 1]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer3.0.bn1.weight - torch.Size([256]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer3.0.bn1.bias - torch.Size([256]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer3.0.conv2.weight - torch.Size([256, 256, 3, 3]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer3.0.bn2.weight - torch.Size([256]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer3.0.bn2.bias - torch.Size([256]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer3.0.conv3.weight - torch.Size([1024, 256, 1, 1]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer3.0.bn3.weight - torch.Size([1024]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer3.0.bn3.bias - torch.Size([1024]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer3.0.downsample.0.weight - torch.Size([1024, 512, 1, 1]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer3.0.downsample.1.weight - torch.Size([1024]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer3.0.downsample.1.bias - torch.Size([1024]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer3.1.conv1.weight - torch.Size([256, 1024, 1, 1]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer3.1.bn1.weight - torch.Size([256]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer3.1.bn1.bias - torch.Size([256]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer3.1.conv2.weight - torch.Size([256, 256, 3, 3]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer3.1.bn2.weight - torch.Size([256]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer3.1.bn2.bias - torch.Size([256]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer3.1.conv3.weight - torch.Size([1024, 256, 1, 1]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer3.1.bn3.weight - torch.Size([1024]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer3.1.bn3.bias - torch.Size([1024]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer3.2.conv1.weight - torch.Size([256, 1024, 1, 1]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer3.2.bn1.weight - torch.Size([256]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer3.2.bn1.bias - torch.Size([256]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer3.2.conv2.weight - torch.Size([256, 256, 3, 3]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer3.2.bn2.weight - torch.Size([256]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer3.2.bn2.bias - torch.Size([256]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer3.2.conv3.weight - torch.Size([1024, 256, 1, 1]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer3.2.bn3.weight - torch.Size([1024]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer3.2.bn3.bias - torch.Size([1024]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer3.3.conv1.weight - torch.Size([256, 1024, 1, 1]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer3.3.bn1.weight - torch.Size([256]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer3.3.bn1.bias - torch.Size([256]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer3.3.conv2.weight - torch.Size([256, 256, 3, 3]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer3.3.bn2.weight - torch.Size([256]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer3.3.bn2.bias - torch.Size([256]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer3.3.conv3.weight - torch.Size([1024, 256, 1, 1]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer3.3.bn3.weight - torch.Size([1024]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer3.3.bn3.bias - torch.Size([1024]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer3.4.conv1.weight - torch.Size([256, 1024, 1, 1]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer3.4.bn1.weight - torch.Size([256]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer3.4.bn1.bias - torch.Size([256]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer3.4.conv2.weight - torch.Size([256, 256, 3, 3]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer3.4.bn2.weight - torch.Size([256]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer3.4.bn2.bias - torch.Size([256]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer3.4.conv3.weight - torch.Size([1024, 256, 1, 1]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer3.4.bn3.weight - torch.Size([1024]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer3.4.bn3.bias - torch.Size([1024]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer3.5.conv1.weight - torch.Size([256, 1024, 1, 1]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer3.5.bn1.weight - torch.Size([256]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer3.5.bn1.bias - torch.Size([256]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer3.5.conv2.weight - torch.Size([256, 256, 3, 3]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer3.5.bn2.weight - torch.Size([256]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer3.5.bn2.bias - torch.Size([256]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer3.5.conv3.weight - torch.Size([1024, 256, 1, 1]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer3.5.bn3.weight - torch.Size([1024]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer3.5.bn3.bias - torch.Size([1024]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer4.0.conv1.weight - torch.Size([512, 1024, 1, 1]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer4.0.bn1.weight - torch.Size([512]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer4.0.bn1.bias - torch.Size([512]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer4.0.conv2.weight - torch.Size([512, 512, 3, 3]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer4.0.bn2.weight - torch.Size([512]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer4.0.bn2.bias - torch.Size([512]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer4.0.conv3.weight - torch.Size([2048, 512, 1, 1]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer4.0.bn3.weight - torch.Size([2048]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer4.0.bn3.bias - torch.Size([2048]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer4.0.downsample.0.weight - torch.Size([2048, 1024, 1, 1]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer4.0.downsample.1.weight - torch.Size([2048]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer4.0.downsample.1.bias - torch.Size([2048]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer4.1.conv1.weight - torch.Size([512, 2048, 1, 1]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer4.1.bn1.weight - torch.Size([512]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer4.1.bn1.bias - torch.Size([512]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer4.1.conv2.weight - torch.Size([512, 512, 3, 3]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer4.1.bn2.weight - torch.Size([512]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer4.1.bn2.bias - torch.Size([512]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer4.1.conv3.weight - torch.Size([2048, 512, 1, 1]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer4.1.bn3.weight - torch.Size([2048]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer4.1.bn3.bias - torch.Size([2048]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer4.2.conv1.weight - torch.Size([512, 2048, 1, 1]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer4.2.bn1.weight - torch.Size([512]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer4.2.bn1.bias - torch.Size([512]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer4.2.conv2.weight - torch.Size([512, 512, 3, 3]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer4.2.bn2.weight - torch.Size([512]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer4.2.bn2.bias - torch.Size([512]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer4.2.conv3.weight - torch.Size([2048, 512, 1, 1]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer4.2.bn3.weight - torch.Size([2048]): +PretrainedInit: load from torchvision://resnet50 + +backbone.layer4.2.bn3.bias - torch.Size([2048]): +PretrainedInit: load from torchvision://resnet50 + +neck.lateral_convs.0.conv.weight - torch.Size([256, 256, 1, 1]): +XavierInit: gain=1, distribution=uniform, bias=0 + +neck.lateral_convs.0.bn.weight - torch.Size([256]): +The value is the same before and after calling `init_weights` of MaskRCNN + +neck.lateral_convs.0.bn.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, 512, 1, 1]): +XavierInit: gain=1, distribution=uniform, bias=0 + +neck.lateral_convs.1.bn.weight - torch.Size([256]): +The value is the same before and after calling `init_weights` of MaskRCNN + +neck.lateral_convs.1.bn.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, 1024, 1, 1]): +XavierInit: gain=1, distribution=uniform, bias=0 + +neck.lateral_convs.2.bn.weight - torch.Size([256]): +The value is the same before and after calling `init_weights` of MaskRCNN + +neck.lateral_convs.2.bn.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, 2048, 1, 1]): +XavierInit: gain=1, distribution=uniform, bias=0 + +neck.lateral_convs.3.bn.weight - torch.Size([256]): +The value is the same before and after calling `init_weights` of MaskRCNN + +neck.lateral_convs.3.bn.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.bn.weight - torch.Size([256]): +The value is the same before and after calling `init_weights` of MaskRCNN + +neck.fpn_convs.0.bn.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.bn.weight - torch.Size([256]): +The value is the same before and after calling `init_weights` of MaskRCNN + +neck.fpn_convs.1.bn.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.bn.weight - torch.Size([256]): +The value is the same before and after calling `init_weights` of MaskRCNN + +neck.fpn_convs.2.bn.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.bn.weight - torch.Size([256]): +The value is the same before and after calling `init_weights` of MaskRCNN + +neck.fpn_convs.3.bn.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_convs.0.conv.weight - torch.Size([256, 256, 3, 3]): +The value is the same before and after calling `init_weights` of MaskRCNN + +roi_head.bbox_head.shared_convs.0.conv.bias - torch.Size([256]): +The value is the same before and after calling `init_weights` of MaskRCNN + +roi_head.bbox_head.shared_convs.1.conv.weight - torch.Size([256, 256, 3, 3]): +The value is the same before and after calling `init_weights` of MaskRCNN + +roi_head.bbox_head.shared_convs.1.conv.bias - torch.Size([256]): +The value is the same before and after calling `init_weights` of MaskRCNN + +roi_head.bbox_head.shared_convs.2.conv.weight - torch.Size([256, 256, 3, 3]): +The value is the same before and after calling `init_weights` of MaskRCNN + +roi_head.bbox_head.shared_convs.2.conv.bias - torch.Size([256]): +The value is the same before and after calling `init_weights` of MaskRCNN + +roi_head.bbox_head.shared_convs.3.conv.weight - torch.Size([256, 256, 3, 3]): +The value is the same before and after calling `init_weights` of MaskRCNN + +roi_head.bbox_head.shared_convs.3.conv.bias - torch.Size([256]): +The value is the same before and after calling `init_weights` of MaskRCNN + +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 +2022-10-22 16:36:18,989 - mmdet - INFO - Automatic scaling of learning rate (LR) has been disabled. +2022-10-22 16:36:20,261 - mmdet - INFO - load checkpoint from local path: pretrain/selfsup_mask-rcnn_mstrain-soft-teacher_sampler-4096_temp0.5/final_model.pth +2022-10-22 16:36:20,412 - mmdet - WARNING - The model and loaded state dict do not match exactly + +unexpected key in source state_dict: neck.lateral_convs.0.conv.bias, neck.lateral_convs.1.conv.bias, neck.lateral_convs.2.conv.bias, neck.lateral_convs.3.conv.bias, neck.fpn_convs.0.conv.bias, neck.fpn_convs.1.conv.bias, neck.fpn_convs.2.conv.bias, neck.fpn_convs.3.conv.bias + +missing keys in source state_dict: neck.lateral_convs.0.bn.weight, neck.lateral_convs.0.bn.bias, neck.lateral_convs.0.bn.running_mean, neck.lateral_convs.0.bn.running_var, neck.lateral_convs.1.bn.weight, neck.lateral_convs.1.bn.bias, neck.lateral_convs.1.bn.running_mean, neck.lateral_convs.1.bn.running_var, neck.lateral_convs.2.bn.weight, neck.lateral_convs.2.bn.bias, neck.lateral_convs.2.bn.running_mean, neck.lateral_convs.2.bn.running_var, neck.lateral_convs.3.bn.weight, neck.lateral_convs.3.bn.bias, neck.lateral_convs.3.bn.running_mean, neck.lateral_convs.3.bn.running_var, neck.fpn_convs.0.bn.weight, neck.fpn_convs.0.bn.bias, neck.fpn_convs.0.bn.running_mean, neck.fpn_convs.0.bn.running_var, neck.fpn_convs.1.bn.weight, neck.fpn_convs.1.bn.bias, neck.fpn_convs.1.bn.running_mean, neck.fpn_convs.1.bn.running_var, neck.fpn_convs.2.bn.weight, neck.fpn_convs.2.bn.bias, neck.fpn_convs.2.bn.running_mean, neck.fpn_convs.2.bn.running_var, neck.fpn_convs.3.bn.weight, neck.fpn_convs.3.bn.bias, neck.fpn_convs.3.bn.running_mean, neck.fpn_convs.3.bn.running_var, rpn_head.rpn_cls.weight, rpn_head.rpn_cls.bias, rpn_head.rpn_reg.weight, rpn_head.rpn_reg.bias, roi_head.bbox_head.fc_cls.weight, roi_head.bbox_head.fc_cls.bias, roi_head.bbox_head.fc_reg.weight, roi_head.bbox_head.fc_reg.bias + +2022-10-22 16:36:20,420 - mmdet - INFO - Start running, host: tiger@n136-145-082, work_dir: /home/tiger/code/mmdet/work_dirs/finetune_faster-rcnn_12k_coco +2022-10-22 16:36:20,420 - mmdet - INFO - Hooks will be executed in the following order: +before_run: +(VERY_HIGH ) StepLrUpdaterHook +(NORMAL ) CheckpointHook +(NORMAL ) MMDetWandbHook +(LOW ) DistEvalHook +(VERY_LOW ) TextLoggerHook + -------------------- +before_train_epoch: +(VERY_HIGH ) StepLrUpdaterHook +(NORMAL ) NumClassCheckHook +(NORMAL ) MMDetWandbHook +(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 +(NORMAL ) MMDetWandbHook +(LOW ) IterTimerHook +(LOW ) DistEvalHook +(VERY_LOW ) TextLoggerHook + -------------------- +after_train_epoch: +(NORMAL ) CheckpointHook +(NORMAL ) MMDetWandbHook +(LOW ) DistEvalHook +(VERY_LOW ) TextLoggerHook + -------------------- +before_val_epoch: +(NORMAL ) NumClassCheckHook +(NORMAL ) MMDetWandbHook +(LOW ) IterTimerHook +(VERY_LOW ) TextLoggerHook + -------------------- +before_val_iter: +(LOW ) IterTimerHook + -------------------- +after_val_iter: +(LOW ) IterTimerHook + -------------------- +after_val_epoch: +(NORMAL ) MMDetWandbHook +(VERY_LOW ) TextLoggerHook + -------------------- +after_run: +(NORMAL ) MMDetWandbHook +(VERY_LOW ) TextLoggerHook + -------------------- +2022-10-22 16:36:20,421 - mmdet - INFO - workflow: [('train', 1)], max: 12000 iters +2022-10-22 16:36:20,421 - mmdet - INFO - Checkpoints will be saved to /home/tiger/code/mmdet/work_dirs/finetune_faster-rcnn_12k_coco by HardDiskBackend. +2022-10-22 16:36:28,778 - mmdet - INFO - Iter [50/12000] lr: 2.967e-03, eta: 0:26:01, time: 0.131, data_time: 0.009, memory: 4029, loss_rpn_cls: 0.5004, loss_rpn_bbox: 0.1032, loss_cls: 1.4508, acc: 83.7205, loss_bbox: 0.0500, loss: 2.1044 +2022-10-22 16:36:35,036 - mmdet - INFO - Iter [100/12000] lr: 5.964e-03, eta: 0:25:22, time: 0.125, data_time: 0.007, memory: 4062, loss_rpn_cls: 0.2272, loss_rpn_bbox: 0.0963, loss_cls: 0.4777, acc: 93.1421, loss_bbox: 0.2376, loss: 1.0388 +2022-10-22 16:36:42,195 - mmdet - INFO - Iter [150/12000] lr: 8.961e-03, eta: 0:26:15, time: 0.143, data_time: 0.007, memory: 4062, loss_rpn_cls: 0.1504, loss_rpn_bbox: 0.0874, loss_cls: 0.4988, acc: 91.9944, loss_bbox: 0.2850, loss: 1.0216 +2022-10-22 16:36:48,394 - mmdet - INFO - Iter [200/12000] lr: 1.196e-02, eta: 0:25:42, time: 0.124, data_time: 0.007, memory: 4062, loss_rpn_cls: 0.0982, loss_rpn_bbox: 0.0864, loss_cls: 0.5849, acc: 89.7361, loss_bbox: 0.3704, loss: 1.1399 +2022-10-22 16:36:54,673 - mmdet - INFO - Iter [250/12000] lr: 1.496e-02, eta: 0:25:23, time: 0.126, data_time: 0.007, memory: 4062, loss_rpn_cls: 0.0943, loss_rpn_bbox: 0.0837, loss_cls: 0.5577, acc: 89.7908, loss_bbox: 0.3555, loss: 1.0912 +2022-10-22 16:37:01,083 - mmdet - INFO - Iter [300/12000] lr: 1.795e-02, eta: 0:25:14, time: 0.128, data_time: 0.007, memory: 4062, loss_rpn_cls: 0.0893, loss_rpn_bbox: 0.0852, loss_cls: 0.5575, acc: 89.9045, loss_bbox: 0.3238, loss: 1.0558 +2022-10-22 16:37:07,356 - mmdet - INFO - Iter [350/12000] lr: 2.095e-02, eta: 0:25:01, time: 0.125, data_time: 0.007, memory: 4062, loss_rpn_cls: 0.0890, loss_rpn_bbox: 0.0834, loss_cls: 0.5248, acc: 90.1399, loss_bbox: 0.3032, loss: 1.0004 +2022-10-22 16:37:13,641 - mmdet - INFO - Iter [400/12000] lr: 2.395e-02, eta: 0:24:50, time: 0.126, data_time: 0.007, memory: 4062, loss_rpn_cls: 0.0887, loss_rpn_bbox: 0.0856, loss_cls: 0.5053, acc: 89.8982, loss_bbox: 0.3057, loss: 0.9854 +2022-10-22 16:37:19,962 - mmdet - INFO - Iter [450/12000] lr: 2.694e-02, eta: 0:24:41, time: 0.126, data_time: 0.007, memory: 4062, loss_rpn_cls: 0.0788, loss_rpn_bbox: 0.0758, loss_cls: 0.4661, acc: 90.5925, loss_bbox: 0.2817, loss: 0.9023 +2022-10-22 16:37:26,241 - mmdet - INFO - Iter [500/12000] lr: 2.994e-02, eta: 0:24:31, time: 0.126, data_time: 0.007, memory: 4062, loss_rpn_cls: 0.0826, loss_rpn_bbox: 0.0836, loss_cls: 0.4688, acc: 90.1523, loss_bbox: 0.2908, loss: 0.9259 +2022-10-22 16:37:32,541 - mmdet - INFO - Iter [550/12000] lr: 3.000e-02, eta: 0:24:23, time: 0.126, data_time: 0.007, memory: 4062, loss_rpn_cls: 0.0790, loss_rpn_bbox: 0.0798, loss_cls: 0.4741, acc: 89.8284, loss_bbox: 0.2920, loss: 0.9250 +2022-10-22 16:37:38,841 - mmdet - INFO - Iter [600/12000] lr: 3.000e-02, eta: 0:24:15, time: 0.126, data_time: 0.007, memory: 4062, loss_rpn_cls: 0.0816, loss_rpn_bbox: 0.0771, loss_cls: 0.4369, acc: 90.5037, loss_bbox: 0.2748, loss: 0.8703 +2022-10-22 16:37:45,073 - mmdet - INFO - Iter [650/12000] lr: 3.000e-02, eta: 0:24:06, time: 0.125, data_time: 0.007, memory: 4062, loss_rpn_cls: 0.0801, loss_rpn_bbox: 0.0821, loss_cls: 0.4659, acc: 89.7993, loss_bbox: 0.2852, loss: 0.9133 +2022-10-22 16:37:51,310 - mmdet - INFO - Iter [700/12000] lr: 3.000e-02, eta: 0:23:57, time: 0.125, data_time: 0.007, memory: 4062, loss_rpn_cls: 0.0801, loss_rpn_bbox: 0.0793, loss_cls: 0.4272, acc: 90.2856, loss_bbox: 0.2815, loss: 0.8681 +2022-10-22 16:37:57,516 - mmdet - INFO - Iter [750/12000] lr: 3.000e-02, eta: 0:23:49, time: 0.124, data_time: 0.007, memory: 4062, loss_rpn_cls: 0.0775, loss_rpn_bbox: 0.0774, loss_cls: 0.4249, acc: 90.2822, loss_bbox: 0.2820, loss: 0.8619 +2022-10-22 16:38:03,747 - mmdet - INFO - Iter [800/12000] lr: 3.000e-02, eta: 0:23:40, time: 0.125, data_time: 0.007, memory: 4062, loss_rpn_cls: 0.0747, loss_rpn_bbox: 0.0783, loss_cls: 0.4182, acc: 90.2380, loss_bbox: 0.2851, loss: 0.8562 +2022-10-22 16:38:09,981 - mmdet - INFO - Iter [850/12000] lr: 3.000e-02, eta: 0:23:33, time: 0.125, data_time: 0.007, memory: 4062, loss_rpn_cls: 0.0773, loss_rpn_bbox: 0.0739, loss_cls: 0.4063, acc: 90.4534, loss_bbox: 0.2724, loss: 0.8299 +2022-10-22 16:38:16,319 - mmdet - INFO - Iter [900/12000] lr: 3.000e-02, eta: 0:23:26, time: 0.127, data_time: 0.007, memory: 4062, loss_rpn_cls: 0.0739, loss_rpn_bbox: 0.0795, loss_cls: 0.4034, acc: 90.3110, loss_bbox: 0.2764, loss: 0.8332 +2022-10-22 16:38:22,693 - mmdet - INFO - Iter [950/12000] lr: 3.000e-02, eta: 0:23:20, time: 0.127, data_time: 0.007, memory: 4062, loss_rpn_cls: 0.0760, loss_rpn_bbox: 0.0801, loss_cls: 0.4050, acc: 90.3713, loss_bbox: 0.2765, loss: 0.8376 +2022-10-22 16:38:29,165 - mmdet - INFO - Exp name: faster_rcnn_fpn_12k_semi-coco.py +2022-10-22 16:38:29,165 - mmdet - INFO - Iter [1000/12000] lr: 3.000e-02, eta: 0:23:16, time: 0.129, data_time: 0.007, memory: 4062, loss_rpn_cls: 0.0721, loss_rpn_bbox: 0.0751, loss_cls: 0.3964, acc: 90.3232, loss_bbox: 0.2763, loss: 0.8199 +2022-10-22 16:38:35,500 - mmdet - INFO - Iter [1050/12000] lr: 3.000e-02, eta: 0:23:09, time: 0.127, data_time: 0.007, memory: 4062, loss_rpn_cls: 0.0773, loss_rpn_bbox: 0.0740, loss_cls: 0.3930, acc: 90.4121, loss_bbox: 0.2758, loss: 0.8200 +2022-10-22 16:38:41,716 - mmdet - INFO - Iter [1100/12000] lr: 3.000e-02, eta: 0:23:01, time: 0.124, data_time: 0.007, memory: 4062, loss_rpn_cls: 0.0721, loss_rpn_bbox: 0.0763, loss_cls: 0.4011, acc: 90.1985, loss_bbox: 0.2806, loss: 0.8301 +2022-10-22 16:38:47,940 - mmdet - INFO - Iter [1150/12000] lr: 3.000e-02, eta: 0:22:54, time: 0.124, data_time: 0.007, memory: 4062, loss_rpn_cls: 0.0720, loss_rpn_bbox: 0.0707, loss_cls: 0.3779, acc: 90.5337, loss_bbox: 0.2776, loss: 0.7982 +2022-10-22 16:38:54,291 - mmdet - INFO - Iter [1200/12000] lr: 3.000e-02, eta: 0:22:48, time: 0.127, data_time: 0.007, memory: 4062, loss_rpn_cls: 0.0731, loss_rpn_bbox: 0.0754, loss_cls: 0.3799, acc: 90.4258, loss_bbox: 0.2698, loss: 0.7983 +2022-10-22 16:39:00,606 - mmdet - INFO - Iter [1250/12000] lr: 3.000e-02, eta: 0:22:41, time: 0.126, data_time: 0.007, memory: 4062, loss_rpn_cls: 0.0689, loss_rpn_bbox: 0.0783, loss_cls: 0.3721, acc: 90.4668, loss_bbox: 0.2731, loss: 0.7924 +2022-10-22 16:39:06,852 - mmdet - INFO - Iter [1300/12000] lr: 3.000e-02, eta: 0:22:34, time: 0.125, data_time: 0.007, memory: 4062, loss_rpn_cls: 0.0660, loss_rpn_bbox: 0.0700, loss_cls: 0.3762, acc: 90.3889, loss_bbox: 0.2762, loss: 0.7884 +2022-10-22 16:39:13,102 - mmdet - INFO - Iter [1350/12000] lr: 3.000e-02, eta: 0:22:27, time: 0.125, data_time: 0.007, memory: 4062, loss_rpn_cls: 0.0723, loss_rpn_bbox: 0.0779, loss_cls: 0.3755, acc: 90.2651, loss_bbox: 0.2840, loss: 0.8096 +2022-10-22 16:39:19,320 - mmdet - INFO - Iter [1400/12000] lr: 3.000e-02, eta: 0:22:20, time: 0.124, data_time: 0.007, memory: 4062, loss_rpn_cls: 0.0732, loss_rpn_bbox: 0.0777, loss_cls: 0.3831, acc: 90.2297, loss_bbox: 0.2844, loss: 0.8185 +2022-10-22 16:39:25,524 - mmdet - INFO - Iter [1450/12000] lr: 3.000e-02, eta: 0:22:13, time: 0.124, data_time: 0.007, memory: 4062, loss_rpn_cls: 0.0746, loss_rpn_bbox: 0.0771, loss_cls: 0.3725, acc: 90.4241, loss_bbox: 0.2774, loss: 0.8017 +2022-10-22 16:39:31,831 - mmdet - INFO - Iter [1500/12000] lr: 3.000e-02, eta: 0:22:07, time: 0.126, data_time: 0.007, memory: 4062, loss_rpn_cls: 0.0701, loss_rpn_bbox: 0.0728, loss_cls: 0.3716, acc: 90.3193, loss_bbox: 0.2795, loss: 0.7940 +2022-10-22 16:39:38,221 - mmdet - INFO - Iter [1550/12000] lr: 3.000e-02, eta: 0:22:01, time: 0.128, data_time: 0.007, memory: 4062, loss_rpn_cls: 0.0702, loss_rpn_bbox: 0.0783, loss_cls: 0.3669, acc: 90.4958, loss_bbox: 0.2715, loss: 0.7869 +2022-10-22 16:39:44,434 - mmdet - INFO - Iter [1600/12000] lr: 3.000e-02, eta: 0:21:54, time: 0.124, data_time: 0.007, memory: 4062, loss_rpn_cls: 0.0648, loss_rpn_bbox: 0.0689, loss_cls: 0.3614, acc: 90.5920, loss_bbox: 0.2736, loss: 0.7688 +2022-10-22 16:39:50,716 - mmdet - INFO - Iter [1650/12000] lr: 3.000e-02, eta: 0:21:47, time: 0.126, data_time: 0.007, memory: 4062, loss_rpn_cls: 0.0656, loss_rpn_bbox: 0.0722, loss_cls: 0.3476, acc: 91.0107, loss_bbox: 0.2594, loss: 0.7448 +2022-10-22 16:39:56,968 - mmdet - INFO - Iter [1700/12000] lr: 3.000e-02, eta: 0:21:40, time: 0.125, data_time: 0.007, memory: 4062, loss_rpn_cls: 0.0669, loss_rpn_bbox: 0.0738, loss_cls: 0.3587, acc: 90.5908, loss_bbox: 0.2720, loss: 0.7714 +2022-10-22 16:40:03,261 - mmdet - INFO - Iter [1750/12000] lr: 3.000e-02, eta: 0:21:34, time: 0.126, data_time: 0.007, memory: 4062, loss_rpn_cls: 0.0697, loss_rpn_bbox: 0.0748, loss_cls: 0.3749, acc: 90.1841, loss_bbox: 0.2905, loss: 0.8098 +2022-10-22 16:40:09,671 - mmdet - INFO - Iter [1800/12000] lr: 3.000e-02, eta: 0:21:28, time: 0.128, data_time: 0.007, memory: 4062, loss_rpn_cls: 0.0651, loss_rpn_bbox: 0.0730, loss_cls: 0.3361, acc: 91.1050, loss_bbox: 0.2574, loss: 0.7316 +2022-10-22 16:40:15,933 - mmdet - INFO - Iter [1850/12000] lr: 3.000e-02, eta: 0:21:22, time: 0.125, data_time: 0.007, memory: 4062, loss_rpn_cls: 0.0628, loss_rpn_bbox: 0.0736, loss_cls: 0.3725, acc: 90.2866, loss_bbox: 0.2797, loss: 0.7885 +2022-10-22 16:40:22,278 - mmdet - INFO - Iter [1900/12000] lr: 3.000e-02, eta: 0:21:15, time: 0.127, data_time: 0.007, memory: 4062, loss_rpn_cls: 0.0756, loss_rpn_bbox: 0.0790, loss_cls: 0.3537, acc: 90.5332, loss_bbox: 0.2741, loss: 0.7824 +2022-10-22 16:40:28,609 - mmdet - INFO - Iter [1950/12000] lr: 3.000e-02, eta: 0:21:09, time: 0.127, data_time: 0.007, memory: 4062, loss_rpn_cls: 0.0691, loss_rpn_bbox: 0.0722, loss_cls: 0.3488, acc: 90.6167, loss_bbox: 0.2729, loss: 0.7631 +2022-10-22 16:40:34,983 - mmdet - INFO - Exp name: faster_rcnn_fpn_12k_semi-coco.py +2022-10-22 16:40:34,984 - mmdet - INFO - Iter [2000/12000] lr: 3.000e-02, eta: 0:21:03, time: 0.127, data_time: 0.007, memory: 4062, loss_rpn_cls: 0.0623, loss_rpn_bbox: 0.0668, loss_cls: 0.3421, acc: 90.9204, loss_bbox: 0.2626, loss: 0.7338 +2022-10-22 16:40:41,482 - mmdet - INFO - Iter [2050/12000] lr: 3.000e-02, eta: 0:20:58, time: 0.130, data_time: 0.007, memory: 4062, loss_rpn_cls: 0.0663, loss_rpn_bbox: 0.0727, loss_cls: 0.3605, acc: 90.2908, loss_bbox: 0.2793, loss: 0.7788 +2022-10-22 16:40:47,896 - mmdet - INFO - Iter [2100/12000] lr: 3.000e-02, eta: 0:20:52, time: 0.128, data_time: 0.007, memory: 4062, loss_rpn_cls: 0.0652, loss_rpn_bbox: 0.0726, loss_cls: 0.3453, acc: 90.6177, loss_bbox: 0.2726, loss: 0.7557 +2022-10-22 16:40:54,239 - mmdet - INFO - Iter [2150/12000] lr: 3.000e-02, eta: 0:20:46, time: 0.127, data_time: 0.007, memory: 4062, loss_rpn_cls: 0.0693, loss_rpn_bbox: 0.0736, loss_cls: 0.3490, acc: 90.7104, loss_bbox: 0.2724, loss: 0.7643 +2022-10-22 16:41:00,714 - mmdet - INFO - Iter [2200/12000] lr: 3.000e-02, eta: 0:20:40, time: 0.130, data_time: 0.007, memory: 4062, loss_rpn_cls: 0.0682, loss_rpn_bbox: 0.0753, loss_cls: 0.3457, acc: 90.6938, loss_bbox: 0.2737, loss: 0.7629 +2022-10-22 16:41:07,084 - mmdet - INFO - Iter [2250/12000] lr: 3.000e-02, eta: 0:20:34, time: 0.127, data_time: 0.006, memory: 4062, loss_rpn_cls: 0.0702, loss_rpn_bbox: 0.0747, loss_cls: 0.3733, acc: 90.1941, loss_bbox: 0.2845, loss: 0.8026 +2022-10-22 16:41:13,437 - mmdet - INFO - Iter [2300/12000] lr: 3.000e-02, eta: 0:20:28, time: 0.127, data_time: 0.007, memory: 4062, loss_rpn_cls: 0.0635, loss_rpn_bbox: 0.0745, loss_cls: 0.3482, acc: 90.5188, loss_bbox: 0.2729, loss: 0.7591 +2022-10-22 16:41:19,732 - mmdet - INFO - Iter [2350/12000] lr: 3.000e-02, eta: 0:20:21, time: 0.126, data_time: 0.006, memory: 4062, loss_rpn_cls: 0.0654, loss_rpn_bbox: 0.0742, loss_cls: 0.3539, acc: 90.6497, loss_bbox: 0.2696, loss: 0.7631 +2022-10-22 16:41:25,993 - mmdet - INFO - Iter [2400/12000] lr: 3.000e-02, eta: 0:20:14, time: 0.125, data_time: 0.007, memory: 4062, loss_rpn_cls: 0.0681, loss_rpn_bbox: 0.0712, loss_cls: 0.3351, acc: 91.0818, loss_bbox: 0.2599, loss: 0.7342 +2022-10-22 16:41:32,349 - mmdet - INFO - Iter [2450/12000] lr: 3.000e-02, eta: 0:20:08, time: 0.127, data_time: 0.008, memory: 4062, loss_rpn_cls: 0.0684, loss_rpn_bbox: 0.0708, loss_cls: 0.3375, acc: 90.9424, loss_bbox: 0.2648, loss: 0.7415 +2022-10-22 16:41:38,621 - mmdet - INFO - Iter [2500/12000] lr: 3.000e-02, eta: 0:20:02, time: 0.125, data_time: 0.007, memory: 4062, loss_rpn_cls: 0.0677, loss_rpn_bbox: 0.0766, loss_cls: 0.3333, acc: 90.9873, loss_bbox: 0.2582, loss: 0.7359 +2022-10-22 16:41:44,868 - mmdet - INFO - Iter [2550/12000] lr: 3.000e-02, eta: 0:19:55, time: 0.125, data_time: 0.007, memory: 4062, loss_rpn_cls: 0.0632, loss_rpn_bbox: 0.0677, loss_cls: 0.3360, acc: 90.7932, loss_bbox: 0.2705, loss: 0.7373 +2022-10-22 16:41:51,221 - mmdet - INFO - Iter [2600/12000] lr: 3.000e-02, eta: 0:19:49, time: 0.127, data_time: 0.007, memory: 4062, loss_rpn_cls: 0.0634, loss_rpn_bbox: 0.0743, loss_cls: 0.3264, acc: 91.0439, loss_bbox: 0.2642, loss: 0.7284 +2022-10-22 16:41:57,514 - mmdet - INFO - Iter [2650/12000] lr: 3.000e-02, eta: 0:19:42, time: 0.126, data_time: 0.007, memory: 4062, loss_rpn_cls: 0.0653, loss_rpn_bbox: 0.0679, loss_cls: 0.3518, acc: 90.4697, loss_bbox: 0.2693, loss: 0.7543 +2022-10-22 16:42:03,825 - mmdet - INFO - Iter [2700/12000] lr: 3.000e-02, eta: 0:19:36, time: 0.126, data_time: 0.007, memory: 4062, loss_rpn_cls: 0.0669, loss_rpn_bbox: 0.0749, loss_cls: 0.3469, acc: 90.5918, loss_bbox: 0.2694, loss: 0.7582 +2022-10-22 16:42:10,052 - mmdet - INFO - Iter [2750/12000] lr: 3.000e-02, eta: 0:19:29, time: 0.125, data_time: 0.007, memory: 4062, loss_rpn_cls: 0.0660, loss_rpn_bbox: 0.0753, loss_cls: 0.3469, acc: 90.4744, loss_bbox: 0.2799, loss: 0.7681 +2022-10-22 16:42:16,435 - mmdet - INFO - Iter [2800/12000] lr: 3.000e-02, eta: 0:19:23, time: 0.128, data_time: 0.007, memory: 4062, loss_rpn_cls: 0.0658, loss_rpn_bbox: 0.0729, loss_cls: 0.3566, acc: 90.3433, loss_bbox: 0.2809, loss: 0.7762 +2022-10-22 16:42:22,650 - mmdet - INFO - Iter [2850/12000] lr: 3.000e-02, eta: 0:19:17, time: 0.124, data_time: 0.007, memory: 4062, loss_rpn_cls: 0.0628, loss_rpn_bbox: 0.0736, loss_cls: 0.3439, acc: 90.5654, loss_bbox: 0.2761, loss: 0.7563 +2022-10-22 16:42:28,892 - mmdet - INFO - Iter [2900/12000] lr: 3.000e-02, eta: 0:19:10, time: 0.125, data_time: 0.007, memory: 4062, loss_rpn_cls: 0.0627, loss_rpn_bbox: 0.0727, loss_cls: 0.3341, acc: 90.8472, loss_bbox: 0.2716, loss: 0.7411 +2022-10-22 16:42:35,157 - mmdet - INFO - Iter [2950/12000] lr: 3.000e-02, eta: 0:19:03, time: 0.125, data_time: 0.007, memory: 4062, loss_rpn_cls: 0.0606, loss_rpn_bbox: 0.0671, loss_cls: 0.3247, acc: 91.1829, loss_bbox: 0.2650, loss: 0.7174 +2022-10-22 16:42:41,411 - mmdet - INFO - Exp name: faster_rcnn_fpn_12k_semi-coco.py +2022-10-22 16:42:41,411 - mmdet - INFO - Iter [3000/12000] lr: 3.000e-02, eta: 0:18:57, time: 0.125, data_time: 0.007, memory: 4062, loss_rpn_cls: 0.0608, loss_rpn_bbox: 0.0673, loss_cls: 0.3356, acc: 90.9160, loss_bbox: 0.2620, loss: 0.7257 +2022-10-22 16:42:47,722 - mmdet - INFO - Iter [3050/12000] lr: 3.000e-02, eta: 0:18:51, time: 0.126, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0598, loss_rpn_bbox: 0.0705, loss_cls: 0.3270, acc: 91.1438, loss_bbox: 0.2630, loss: 0.7203 +2022-10-22 16:42:53,983 - mmdet - INFO - Iter [3100/12000] lr: 3.000e-02, eta: 0:18:44, time: 0.125, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0602, loss_rpn_bbox: 0.0713, loss_cls: 0.3366, acc: 90.6887, loss_bbox: 0.2712, loss: 0.7394 +2022-10-22 16:43:00,348 - mmdet - INFO - Iter [3150/12000] lr: 3.000e-02, eta: 0:18:38, time: 0.127, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0600, loss_rpn_bbox: 0.0672, loss_cls: 0.3037, acc: 91.6899, loss_bbox: 0.2468, loss: 0.6778 +2022-10-22 16:43:06,609 - mmdet - INFO - Iter [3200/12000] lr: 3.000e-02, eta: 0:18:31, time: 0.125, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0649, loss_rpn_bbox: 0.0745, loss_cls: 0.3424, acc: 90.6033, loss_bbox: 0.2703, loss: 0.7521 +2022-10-22 16:43:12,859 - mmdet - INFO - Iter [3250/12000] lr: 3.000e-02, eta: 0:18:25, time: 0.125, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0642, loss_rpn_bbox: 0.0685, loss_cls: 0.3327, acc: 90.8679, loss_bbox: 0.2598, loss: 0.7252 +2022-10-22 16:43:19,172 - mmdet - INFO - Iter [3300/12000] lr: 3.000e-02, eta: 0:18:19, time: 0.126, data_time: 0.006, memory: 4086, loss_rpn_cls: 0.0613, loss_rpn_bbox: 0.0720, loss_cls: 0.3398, acc: 90.7783, loss_bbox: 0.2717, loss: 0.7448 +2022-10-22 16:43:25,455 - mmdet - INFO - Iter [3350/12000] lr: 3.000e-02, eta: 0:18:12, time: 0.126, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0590, loss_rpn_bbox: 0.0663, loss_cls: 0.3289, acc: 90.9084, loss_bbox: 0.2645, loss: 0.7186 +2022-10-22 16:43:31,873 - mmdet - INFO - Iter [3400/12000] lr: 3.000e-02, eta: 0:18:06, time: 0.128, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0603, loss_rpn_bbox: 0.0694, loss_cls: 0.3226, acc: 90.9817, loss_bbox: 0.2617, loss: 0.7140 +2022-10-22 16:43:38,114 - mmdet - INFO - Iter [3450/12000] lr: 3.000e-02, eta: 0:18:00, time: 0.125, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0647, loss_rpn_bbox: 0.0706, loss_cls: 0.3313, acc: 90.8647, loss_bbox: 0.2620, loss: 0.7287 +2022-10-22 16:43:44,404 - mmdet - INFO - Iter [3500/12000] lr: 3.000e-02, eta: 0:17:53, time: 0.126, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0619, loss_rpn_bbox: 0.0668, loss_cls: 0.3132, acc: 91.2651, loss_bbox: 0.2539, loss: 0.6958 +2022-10-22 16:43:50,681 - mmdet - INFO - Iter [3550/12000] lr: 3.000e-02, eta: 0:17:47, time: 0.126, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0606, loss_rpn_bbox: 0.0663, loss_cls: 0.3244, acc: 90.9224, loss_bbox: 0.2644, loss: 0.7157 +2022-10-22 16:43:57,082 - mmdet - INFO - Iter [3600/12000] lr: 3.000e-02, eta: 0:17:41, time: 0.128, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0586, loss_rpn_bbox: 0.0691, loss_cls: 0.3354, acc: 90.6985, loss_bbox: 0.2709, loss: 0.7339 +2022-10-22 16:44:03,292 - mmdet - INFO - Iter [3650/12000] lr: 3.000e-02, eta: 0:17:34, time: 0.124, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0590, loss_rpn_bbox: 0.0710, loss_cls: 0.3220, acc: 90.8740, loss_bbox: 0.2712, loss: 0.7232 +2022-10-22 16:44:09,684 - mmdet - INFO - Iter [3700/12000] lr: 3.000e-02, eta: 0:17:28, time: 0.128, data_time: 0.008, memory: 4086, loss_rpn_cls: 0.0551, loss_rpn_bbox: 0.0703, loss_cls: 0.3321, acc: 90.6555, loss_bbox: 0.2737, loss: 0.7313 +2022-10-22 16:44:15,959 - mmdet - INFO - Iter [3750/12000] lr: 3.000e-02, eta: 0:17:22, time: 0.126, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0577, loss_rpn_bbox: 0.0699, loss_cls: 0.3378, acc: 90.4526, loss_bbox: 0.2827, loss: 0.7480 +2022-10-22 16:44:22,219 - mmdet - INFO - Iter [3800/12000] lr: 3.000e-02, eta: 0:17:15, time: 0.125, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0645, loss_rpn_bbox: 0.0710, loss_cls: 0.3213, acc: 91.1318, loss_bbox: 0.2651, loss: 0.7219 +2022-10-22 16:44:28,439 - mmdet - INFO - Iter [3850/12000] lr: 3.000e-02, eta: 0:17:09, time: 0.124, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0584, loss_rpn_bbox: 0.0694, loss_cls: 0.3249, acc: 90.9062, loss_bbox: 0.2655, loss: 0.7182 +2022-10-22 16:44:34,675 - mmdet - INFO - Iter [3900/12000] lr: 3.000e-02, eta: 0:17:02, time: 0.125, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0645, loss_rpn_bbox: 0.0708, loss_cls: 0.3224, acc: 91.0769, loss_bbox: 0.2583, loss: 0.7161 +2022-10-22 16:44:40,877 - mmdet - INFO - Iter [3950/12000] lr: 3.000e-02, eta: 0:16:56, time: 0.124, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0608, loss_rpn_bbox: 0.0681, loss_cls: 0.3133, acc: 91.1050, loss_bbox: 0.2534, loss: 0.6955 +2022-10-22 16:44:47,300 - mmdet - INFO - Exp name: faster_rcnn_fpn_12k_semi-coco.py +2022-10-22 16:44:47,301 - mmdet - INFO - Iter [4000/12000] lr: 3.000e-02, eta: 0:16:50, time: 0.128, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0565, loss_rpn_bbox: 0.0635, loss_cls: 0.3149, acc: 91.2400, loss_bbox: 0.2526, loss: 0.6875 +2022-10-22 16:44:53,512 - mmdet - INFO - Iter [4050/12000] lr: 3.000e-02, eta: 0:16:43, time: 0.124, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0597, loss_rpn_bbox: 0.0679, loss_cls: 0.3323, acc: 90.7122, loss_bbox: 0.2728, loss: 0.7326 +2022-10-22 16:44:59,696 - mmdet - INFO - Iter [4100/12000] lr: 3.000e-02, eta: 0:16:37, time: 0.124, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0594, loss_rpn_bbox: 0.0678, loss_cls: 0.3197, acc: 90.9490, loss_bbox: 0.2606, loss: 0.7075 +2022-10-22 16:45:05,997 - mmdet - INFO - Iter [4150/12000] lr: 3.000e-02, eta: 0:16:30, time: 0.126, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0605, loss_rpn_bbox: 0.0690, loss_cls: 0.3317, acc: 90.7759, loss_bbox: 0.2682, loss: 0.7294 +2022-10-22 16:45:12,230 - mmdet - INFO - Iter [4200/12000] lr: 3.000e-02, eta: 0:16:24, time: 0.125, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0595, loss_rpn_bbox: 0.0700, loss_cls: 0.3258, acc: 90.7007, loss_bbox: 0.2688, loss: 0.7241 +2022-10-22 16:45:18,507 - mmdet - INFO - Iter [4250/12000] lr: 3.000e-02, eta: 0:16:17, time: 0.126, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0639, loss_rpn_bbox: 0.0711, loss_cls: 0.3207, acc: 90.8489, loss_bbox: 0.2618, loss: 0.7176 +2022-10-22 16:45:24,796 - mmdet - INFO - Iter [4300/12000] lr: 3.000e-02, eta: 0:16:11, time: 0.126, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0598, loss_rpn_bbox: 0.0681, loss_cls: 0.3266, acc: 90.9014, loss_bbox: 0.2628, loss: 0.7173 +2022-10-22 16:45:31,047 - mmdet - INFO - Iter [4350/12000] lr: 3.000e-02, eta: 0:16:05, time: 0.125, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0590, loss_rpn_bbox: 0.0669, loss_cls: 0.3213, acc: 90.8997, loss_bbox: 0.2642, loss: 0.7114 +2022-10-22 16:45:37,385 - mmdet - INFO - Iter [4400/12000] lr: 3.000e-02, eta: 0:15:58, time: 0.127, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0628, loss_rpn_bbox: 0.0706, loss_cls: 0.3124, acc: 91.0066, loss_bbox: 0.2639, loss: 0.7096 +2022-10-22 16:45:43,618 - mmdet - INFO - Iter [4450/12000] lr: 3.000e-02, eta: 0:15:52, time: 0.125, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0521, loss_rpn_bbox: 0.0631, loss_cls: 0.2979, acc: 91.7246, loss_bbox: 0.2433, loss: 0.6563 +2022-10-22 16:45:49,819 - mmdet - INFO - Iter [4500/12000] lr: 3.000e-02, eta: 0:15:45, time: 0.124, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0552, loss_rpn_bbox: 0.0661, loss_cls: 0.3135, acc: 90.9727, loss_bbox: 0.2623, loss: 0.6971 +2022-10-22 16:45:56,216 - mmdet - INFO - Iter [4550/12000] lr: 3.000e-02, eta: 0:15:39, time: 0.128, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0602, loss_rpn_bbox: 0.0714, loss_cls: 0.3156, acc: 91.1604, loss_bbox: 0.2590, loss: 0.7062 +2022-10-22 16:46:02,554 - mmdet - INFO - Iter [4600/12000] lr: 3.000e-02, eta: 0:15:33, time: 0.127, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0552, loss_rpn_bbox: 0.0671, loss_cls: 0.3114, acc: 91.1506, loss_bbox: 0.2606, loss: 0.6943 +2022-10-22 16:46:08,791 - mmdet - INFO - Iter [4650/12000] lr: 3.000e-02, eta: 0:15:27, time: 0.125, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0612, loss_rpn_bbox: 0.0738, loss_cls: 0.3380, acc: 90.3289, loss_bbox: 0.2758, loss: 0.7488 +2022-10-22 16:46:15,047 - mmdet - INFO - Iter [4700/12000] lr: 3.000e-02, eta: 0:15:20, time: 0.125, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0576, loss_rpn_bbox: 0.0684, loss_cls: 0.3276, acc: 90.7415, loss_bbox: 0.2725, loss: 0.7260 +2022-10-22 16:46:21,275 - mmdet - INFO - Iter [4750/12000] lr: 3.000e-02, eta: 0:15:14, time: 0.125, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0589, loss_rpn_bbox: 0.0701, loss_cls: 0.3201, acc: 90.8643, loss_bbox: 0.2697, loss: 0.7188 +2022-10-22 16:46:27,569 - mmdet - INFO - Iter [4800/12000] lr: 3.000e-02, eta: 0:15:07, time: 0.126, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0559, loss_rpn_bbox: 0.0659, loss_cls: 0.3244, acc: 90.7837, loss_bbox: 0.2700, loss: 0.7161 +2022-10-22 16:46:33,745 - mmdet - INFO - Iter [4850/12000] lr: 3.000e-02, eta: 0:15:01, time: 0.124, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0641, loss_rpn_bbox: 0.0707, loss_cls: 0.3166, acc: 91.1899, loss_bbox: 0.2554, loss: 0.7069 +2022-10-22 16:46:40,177 - mmdet - INFO - Iter [4900/12000] lr: 3.000e-02, eta: 0:14:55, time: 0.129, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0531, loss_rpn_bbox: 0.0656, loss_cls: 0.3089, acc: 91.2168, loss_bbox: 0.2595, loss: 0.6871 +2022-10-22 16:46:46,382 - mmdet - INFO - Iter [4950/12000] lr: 3.000e-02, eta: 0:14:48, time: 0.124, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0540, loss_rpn_bbox: 0.0641, loss_cls: 0.2977, acc: 91.2393, loss_bbox: 0.2523, loss: 0.6680 +2022-10-22 16:46:52,607 - mmdet - INFO - Exp name: faster_rcnn_fpn_12k_semi-coco.py +2022-10-22 16:46:52,608 - mmdet - INFO - Iter [5000/12000] lr: 3.000e-02, eta: 0:14:42, time: 0.125, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0630, loss_rpn_bbox: 0.0666, loss_cls: 0.3096, acc: 91.2363, loss_bbox: 0.2588, loss: 0.6980 +2022-10-22 16:46:58,876 - mmdet - INFO - Iter [5050/12000] lr: 3.000e-02, eta: 0:14:36, time: 0.125, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0550, loss_rpn_bbox: 0.0658, loss_cls: 0.3152, acc: 91.0659, loss_bbox: 0.2650, loss: 0.7011 +2022-10-22 16:47:05,097 - mmdet - INFO - Iter [5100/12000] lr: 3.000e-02, eta: 0:14:29, time: 0.124, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0590, loss_rpn_bbox: 0.0655, loss_cls: 0.3170, acc: 91.1177, loss_bbox: 0.2578, loss: 0.6992 +2022-10-22 16:47:11,368 - mmdet - INFO - Iter [5150/12000] lr: 3.000e-02, eta: 0:14:23, time: 0.125, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0603, loss_rpn_bbox: 0.0694, loss_cls: 0.3189, acc: 90.8940, loss_bbox: 0.2660, loss: 0.7146 +2022-10-22 16:47:17,723 - mmdet - INFO - Iter [5200/12000] lr: 3.000e-02, eta: 0:14:17, time: 0.127, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0597, loss_rpn_bbox: 0.0696, loss_cls: 0.3241, acc: 90.7939, loss_bbox: 0.2658, loss: 0.7192 +2022-10-22 16:47:23,945 - mmdet - INFO - Iter [5250/12000] lr: 3.000e-02, eta: 0:14:10, time: 0.124, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0555, loss_rpn_bbox: 0.0666, loss_cls: 0.3133, acc: 91.0063, loss_bbox: 0.2621, loss: 0.6976 +2022-10-22 16:47:30,225 - mmdet - INFO - Iter [5300/12000] lr: 3.000e-02, eta: 0:14:04, time: 0.126, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0559, loss_rpn_bbox: 0.0643, loss_cls: 0.3275, acc: 90.7729, loss_bbox: 0.2684, loss: 0.7160 +2022-10-22 16:47:36,434 - mmdet - INFO - Iter [5350/12000] lr: 3.000e-02, eta: 0:13:57, time: 0.124, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0569, loss_rpn_bbox: 0.0666, loss_cls: 0.3092, acc: 91.2310, loss_bbox: 0.2607, loss: 0.6934 +2022-10-22 16:47:42,660 - mmdet - INFO - Iter [5400/12000] lr: 3.000e-02, eta: 0:13:51, time: 0.125, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0545, loss_rpn_bbox: 0.0659, loss_cls: 0.3028, acc: 91.4395, loss_bbox: 0.2553, loss: 0.6785 +2022-10-22 16:47:49,006 - mmdet - INFO - Iter [5450/12000] lr: 3.000e-02, eta: 0:13:45, time: 0.127, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0570, loss_rpn_bbox: 0.0684, loss_cls: 0.3137, acc: 90.8330, loss_bbox: 0.2694, loss: 0.7085 +2022-10-22 16:47:55,219 - mmdet - INFO - Iter [5500/12000] lr: 3.000e-02, eta: 0:13:38, time: 0.124, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0576, loss_rpn_bbox: 0.0659, loss_cls: 0.3206, acc: 91.0447, loss_bbox: 0.2583, loss: 0.7024 +2022-10-22 16:48:01,478 - mmdet - INFO - Iter [5550/12000] lr: 3.000e-02, eta: 0:13:32, time: 0.125, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0521, loss_rpn_bbox: 0.0667, loss_cls: 0.2992, acc: 91.2329, loss_bbox: 0.2548, loss: 0.6727 +2022-10-22 16:48:07,750 - mmdet - INFO - Iter [5600/12000] lr: 3.000e-02, eta: 0:13:26, time: 0.125, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0580, loss_rpn_bbox: 0.0688, loss_cls: 0.3055, acc: 91.0591, loss_bbox: 0.2638, loss: 0.6961 +2022-10-22 16:48:14,119 - mmdet - INFO - Iter [5650/12000] lr: 3.000e-02, eta: 0:13:20, time: 0.127, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0543, loss_rpn_bbox: 0.0637, loss_cls: 0.2983, acc: 91.4980, loss_bbox: 0.2494, loss: 0.6657 +2022-10-22 16:48:20,339 - mmdet - INFO - Iter [5700/12000] lr: 3.000e-02, eta: 0:13:13, time: 0.124, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0570, loss_rpn_bbox: 0.0685, loss_cls: 0.3136, acc: 90.9600, loss_bbox: 0.2633, loss: 0.7025 +2022-10-22 16:48:26,585 - mmdet - INFO - Iter [5750/12000] lr: 3.000e-02, eta: 0:13:07, time: 0.125, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0546, loss_rpn_bbox: 0.0691, loss_cls: 0.3018, acc: 91.1831, loss_bbox: 0.2618, loss: 0.6874 +2022-10-22 16:48:32,784 - mmdet - INFO - Iter [5800/12000] lr: 3.000e-02, eta: 0:13:00, time: 0.124, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0526, loss_rpn_bbox: 0.0644, loss_cls: 0.2993, acc: 91.4355, loss_bbox: 0.2520, loss: 0.6684 +2022-10-22 16:48:38,974 - mmdet - INFO - Iter [5850/12000] lr: 3.000e-02, eta: 0:12:54, time: 0.124, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0540, loss_rpn_bbox: 0.0644, loss_cls: 0.3068, acc: 91.2966, loss_bbox: 0.2509, loss: 0.6761 +2022-10-22 16:48:45,222 - mmdet - INFO - Iter [5900/12000] lr: 3.000e-02, eta: 0:12:48, time: 0.125, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0574, loss_rpn_bbox: 0.0676, loss_cls: 0.3063, acc: 91.0559, loss_bbox: 0.2626, loss: 0.6939 +2022-10-22 16:48:51,384 - mmdet - INFO - Iter [5950/12000] lr: 3.000e-02, eta: 0:12:41, time: 0.123, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0516, loss_rpn_bbox: 0.0672, loss_cls: 0.3060, acc: 91.0483, loss_bbox: 0.2655, loss: 0.6903 +2022-10-22 16:48:57,593 - mmdet - INFO - Exp name: faster_rcnn_fpn_12k_semi-coco.py +2022-10-22 16:48:57,593 - mmdet - INFO - Iter [6000/12000] lr: 3.000e-02, eta: 0:12:35, time: 0.124, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0561, loss_rpn_bbox: 0.0678, loss_cls: 0.3087, acc: 91.0989, loss_bbox: 0.2662, loss: 0.6988 +2022-10-22 16:49:03,860 - mmdet - INFO - Iter [6050/12000] lr: 3.000e-02, eta: 0:12:28, time: 0.125, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0603, loss_rpn_bbox: 0.0693, loss_cls: 0.2975, acc: 91.2502, loss_bbox: 0.2584, loss: 0.6856 +2022-10-22 16:49:10,084 - mmdet - INFO - Iter [6100/12000] lr: 3.000e-02, eta: 0:12:22, time: 0.124, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0570, loss_rpn_bbox: 0.0703, loss_cls: 0.3063, acc: 91.2590, loss_bbox: 0.2551, loss: 0.6887 +2022-10-22 16:49:16,295 - mmdet - INFO - Iter [6150/12000] lr: 3.000e-02, eta: 0:12:16, time: 0.124, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0532, loss_rpn_bbox: 0.0646, loss_cls: 0.2919, acc: 91.5095, loss_bbox: 0.2513, loss: 0.6610 +2022-10-22 16:49:22,534 - mmdet - INFO - Iter [6200/12000] lr: 3.000e-02, eta: 0:12:09, time: 0.125, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0574, loss_rpn_bbox: 0.0655, loss_cls: 0.3131, acc: 90.9788, loss_bbox: 0.2635, loss: 0.6995 +2022-10-22 16:49:28,703 - mmdet - INFO - Iter [6250/12000] lr: 3.000e-02, eta: 0:12:03, time: 0.123, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0533, loss_rpn_bbox: 0.0667, loss_cls: 0.3248, acc: 90.9150, loss_bbox: 0.2569, loss: 0.7017 +2022-10-22 16:49:34,879 - mmdet - INFO - Iter [6300/12000] lr: 3.000e-02, eta: 0:11:57, time: 0.124, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0608, loss_rpn_bbox: 0.0712, loss_cls: 0.3104, acc: 91.2854, loss_bbox: 0.2538, loss: 0.6962 +2022-10-22 16:49:41,075 - mmdet - INFO - Iter [6350/12000] lr: 3.000e-02, eta: 0:11:50, time: 0.124, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0581, loss_rpn_bbox: 0.0694, loss_cls: 0.3136, acc: 91.1394, loss_bbox: 0.2647, loss: 0.7058 +2022-10-22 16:49:47,390 - mmdet - INFO - Iter [6400/12000] lr: 3.000e-02, eta: 0:11:44, time: 0.126, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0571, loss_rpn_bbox: 0.0646, loss_cls: 0.2928, acc: 91.4709, loss_bbox: 0.2478, loss: 0.6623 +2022-10-22 16:49:53,609 - mmdet - INFO - Iter [6450/12000] lr: 3.000e-02, eta: 0:11:38, time: 0.124, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0521, loss_rpn_bbox: 0.0647, loss_cls: 0.2917, acc: 91.5503, loss_bbox: 0.2471, loss: 0.6556 +2022-10-22 16:50:00,062 - mmdet - INFO - Iter [6500/12000] lr: 3.000e-02, eta: 0:11:31, time: 0.129, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0557, loss_rpn_bbox: 0.0666, loss_cls: 0.3016, acc: 91.2002, loss_bbox: 0.2592, loss: 0.6832 +2022-10-22 16:50:06,306 - mmdet - INFO - Iter [6550/12000] lr: 3.000e-02, eta: 0:11:25, time: 0.125, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0516, loss_rpn_bbox: 0.0653, loss_cls: 0.2923, acc: 91.4944, loss_bbox: 0.2543, loss: 0.6635 +2022-10-22 16:50:12,529 - mmdet - INFO - Iter [6600/12000] lr: 3.000e-02, eta: 0:11:19, time: 0.124, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0563, loss_rpn_bbox: 0.0697, loss_cls: 0.3055, acc: 91.1716, loss_bbox: 0.2592, loss: 0.6908 +2022-10-22 16:50:18,814 - mmdet - INFO - Iter [6650/12000] lr: 3.000e-02, eta: 0:11:13, time: 0.126, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0556, loss_rpn_bbox: 0.0640, loss_cls: 0.2922, acc: 91.6426, loss_bbox: 0.2483, loss: 0.6601 +2022-10-22 16:50:25,136 - mmdet - INFO - Iter [6700/12000] lr: 3.000e-02, eta: 0:11:06, time: 0.126, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0576, loss_rpn_bbox: 0.0709, loss_cls: 0.3171, acc: 90.9021, loss_bbox: 0.2636, loss: 0.7093 +2022-10-22 16:50:31,356 - mmdet - INFO - Iter [6750/12000] lr: 3.000e-02, eta: 0:11:00, time: 0.124, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0604, loss_rpn_bbox: 0.0686, loss_cls: 0.3000, acc: 91.4270, loss_bbox: 0.2543, loss: 0.6834 +2022-10-22 16:50:37,565 - mmdet - INFO - Iter [6800/12000] lr: 3.000e-02, eta: 0:10:54, time: 0.124, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0540, loss_rpn_bbox: 0.0677, loss_cls: 0.3030, acc: 91.1067, loss_bbox: 0.2611, loss: 0.6858 +2022-10-22 16:50:43,757 - mmdet - INFO - Iter [6850/12000] lr: 3.000e-02, eta: 0:10:47, time: 0.124, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0541, loss_rpn_bbox: 0.0649, loss_cls: 0.3116, acc: 91.0359, loss_bbox: 0.2567, loss: 0.6873 +2022-10-22 16:50:50,207 - mmdet - INFO - Iter [6900/12000] lr: 3.000e-02, eta: 0:10:41, time: 0.129, data_time: 0.008, memory: 4086, loss_rpn_cls: 0.0528, loss_rpn_bbox: 0.0671, loss_cls: 0.3072, acc: 91.1514, loss_bbox: 0.2540, loss: 0.6810 +2022-10-22 16:50:56,532 - mmdet - INFO - Iter [6950/12000] lr: 3.000e-02, eta: 0:10:35, time: 0.127, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0558, loss_rpn_bbox: 0.0638, loss_cls: 0.3190, acc: 90.7671, loss_bbox: 0.2678, loss: 0.7063 +2022-10-22 16:51:02,896 - mmdet - INFO - Exp name: faster_rcnn_fpn_12k_semi-coco.py +2022-10-22 16:51:02,896 - mmdet - INFO - Iter [7000/12000] lr: 3.000e-02, eta: 0:10:29, time: 0.127, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0522, loss_rpn_bbox: 0.0655, loss_cls: 0.2861, acc: 91.6497, loss_bbox: 0.2539, loss: 0.6577 +2022-10-22 16:51:09,223 - mmdet - INFO - Iter [7050/12000] lr: 3.000e-02, eta: 0:10:22, time: 0.127, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0515, loss_rpn_bbox: 0.0643, loss_cls: 0.3007, acc: 91.2241, loss_bbox: 0.2549, loss: 0.6714 +2022-10-22 16:51:15,459 - mmdet - INFO - Iter [7100/12000] lr: 3.000e-02, eta: 0:10:16, time: 0.125, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0495, loss_rpn_bbox: 0.0640, loss_cls: 0.2962, acc: 91.2205, loss_bbox: 0.2575, loss: 0.6672 +2022-10-22 16:51:21,700 - mmdet - INFO - Iter [7150/12000] lr: 3.000e-02, eta: 0:10:10, time: 0.125, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0591, loss_rpn_bbox: 0.0712, loss_cls: 0.3019, acc: 90.9880, loss_bbox: 0.2657, loss: 0.6980 +2022-10-22 16:51:28,057 - mmdet - INFO - Iter [7200/12000] lr: 3.000e-02, eta: 0:10:03, time: 0.127, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0597, loss_rpn_bbox: 0.0645, loss_cls: 0.2939, acc: 91.4583, loss_bbox: 0.2468, loss: 0.6650 +2022-10-22 16:51:34,500 - mmdet - INFO - Iter [7250/12000] lr: 3.000e-02, eta: 0:09:57, time: 0.129, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0522, loss_rpn_bbox: 0.0627, loss_cls: 0.3016, acc: 91.2542, loss_bbox: 0.2553, loss: 0.6718 +2022-10-22 16:51:40,811 - mmdet - INFO - Iter [7300/12000] lr: 3.000e-02, eta: 0:09:51, time: 0.126, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0500, loss_rpn_bbox: 0.0654, loss_cls: 0.2954, acc: 91.4331, loss_bbox: 0.2501, loss: 0.6609 +2022-10-22 16:51:47,011 - mmdet - INFO - Iter [7350/12000] lr: 3.000e-02, eta: 0:09:45, time: 0.124, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0562, loss_rpn_bbox: 0.0680, loss_cls: 0.3055, acc: 91.0459, loss_bbox: 0.2685, loss: 0.6982 +2022-10-22 16:51:53,384 - mmdet - INFO - Iter [7400/12000] lr: 3.000e-02, eta: 0:09:38, time: 0.127, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0502, loss_rpn_bbox: 0.0708, loss_cls: 0.2982, acc: 91.2317, loss_bbox: 0.2646, loss: 0.6838 +2022-10-22 16:51:59,617 - mmdet - INFO - Iter [7450/12000] lr: 3.000e-02, eta: 0:09:32, time: 0.125, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0541, loss_rpn_bbox: 0.0665, loss_cls: 0.2960, acc: 91.3059, loss_bbox: 0.2565, loss: 0.6731 +2022-10-22 16:52:05,999 - mmdet - INFO - Iter [7500/12000] lr: 3.000e-02, eta: 0:09:26, time: 0.128, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0529, loss_rpn_bbox: 0.0678, loss_cls: 0.3045, acc: 91.0625, loss_bbox: 0.2640, loss: 0.6892 +2022-10-22 16:52:12,324 - mmdet - INFO - Iter [7550/12000] lr: 3.000e-02, eta: 0:09:19, time: 0.126, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0503, loss_rpn_bbox: 0.0642, loss_cls: 0.2904, acc: 91.5271, loss_bbox: 0.2518, loss: 0.6568 +2022-10-22 16:52:18,518 - mmdet - INFO - Iter [7600/12000] lr: 3.000e-02, eta: 0:09:13, time: 0.124, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0519, loss_rpn_bbox: 0.0634, loss_cls: 0.2876, acc: 91.4692, loss_bbox: 0.2551, loss: 0.6579 +2022-10-22 16:52:24,706 - mmdet - INFO - Iter [7650/12000] lr: 3.000e-02, eta: 0:09:07, time: 0.124, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0510, loss_rpn_bbox: 0.0657, loss_cls: 0.2997, acc: 91.1636, loss_bbox: 0.2628, loss: 0.6792 +2022-10-22 16:52:30,951 - mmdet - INFO - Iter [7700/12000] lr: 3.000e-02, eta: 0:09:00, time: 0.125, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0524, loss_rpn_bbox: 0.0682, loss_cls: 0.2902, acc: 91.3843, loss_bbox: 0.2534, loss: 0.6643 +2022-10-22 16:52:37,143 - mmdet - INFO - Iter [7750/12000] lr: 3.000e-02, eta: 0:08:54, time: 0.124, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0500, loss_rpn_bbox: 0.0634, loss_cls: 0.2887, acc: 91.5381, loss_bbox: 0.2476, loss: 0.6497 +2022-10-22 16:52:43,431 - mmdet - INFO - Iter [7800/12000] lr: 3.000e-02, eta: 0:08:48, time: 0.126, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0515, loss_rpn_bbox: 0.0664, loss_cls: 0.2977, acc: 91.2141, loss_bbox: 0.2615, loss: 0.6771 +2022-10-22 16:52:49,766 - mmdet - INFO - Iter [7850/12000] lr: 3.000e-02, eta: 0:08:42, time: 0.127, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0508, loss_rpn_bbox: 0.0623, loss_cls: 0.2955, acc: 91.4021, loss_bbox: 0.2570, loss: 0.6657 +2022-10-22 16:52:56,059 - mmdet - INFO - Iter [7900/12000] lr: 3.000e-02, eta: 0:08:35, time: 0.126, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0530, loss_rpn_bbox: 0.0671, loss_cls: 0.3027, acc: 91.1396, loss_bbox: 0.2603, loss: 0.6831 +2022-10-22 16:53:02,272 - mmdet - INFO - Iter [7950/12000] lr: 3.000e-02, eta: 0:08:29, time: 0.124, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0492, loss_rpn_bbox: 0.0647, loss_cls: 0.2849, acc: 91.6516, loss_bbox: 0.2451, loss: 0.6439 +2022-10-22 16:53:08,501 - mmdet - INFO - Exp name: faster_rcnn_fpn_12k_semi-coco.py +2022-10-22 16:53:08,502 - mmdet - INFO - Iter [8000/12000] lr: 3.000e-02, eta: 0:08:23, time: 0.125, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0517, loss_rpn_bbox: 0.0626, loss_cls: 0.2963, acc: 91.2466, loss_bbox: 0.2596, loss: 0.6701 +2022-10-22 16:53:14,775 - mmdet - INFO - Iter [8050/12000] lr: 3.000e-02, eta: 0:08:16, time: 0.125, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0566, loss_rpn_bbox: 0.0660, loss_cls: 0.2996, acc: 91.1558, loss_bbox: 0.2528, loss: 0.6751 +2022-10-22 16:53:21,010 - mmdet - INFO - Iter [8100/12000] lr: 3.000e-02, eta: 0:08:10, time: 0.125, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0515, loss_rpn_bbox: 0.0686, loss_cls: 0.2988, acc: 91.1746, loss_bbox: 0.2603, loss: 0.6792 +2022-10-22 16:53:27,227 - mmdet - INFO - Iter [8150/12000] lr: 3.000e-02, eta: 0:08:04, time: 0.124, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0543, loss_rpn_bbox: 0.0656, loss_cls: 0.2907, acc: 91.4248, loss_bbox: 0.2549, loss: 0.6654 +2022-10-22 16:53:33,483 - mmdet - INFO - Iter [8200/12000] lr: 3.000e-02, eta: 0:07:57, time: 0.125, data_time: 0.008, memory: 4086, loss_rpn_cls: 0.0522, loss_rpn_bbox: 0.0644, loss_cls: 0.2924, acc: 91.4417, loss_bbox: 0.2488, loss: 0.6577 +2022-10-22 16:53:39,733 - mmdet - INFO - Iter [8250/12000] lr: 3.000e-02, eta: 0:07:51, time: 0.125, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0566, loss_rpn_bbox: 0.0660, loss_cls: 0.3094, acc: 90.7471, loss_bbox: 0.2721, loss: 0.7042 +2022-10-22 16:53:46,182 - mmdet - INFO - Iter [8300/12000] lr: 3.000e-02, eta: 0:07:45, time: 0.129, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0508, loss_rpn_bbox: 0.0679, loss_cls: 0.2940, acc: 91.3010, loss_bbox: 0.2582, loss: 0.6709 +2022-10-22 16:53:52,391 - mmdet - INFO - Iter [8350/12000] lr: 3.000e-02, eta: 0:07:39, time: 0.124, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0509, loss_rpn_bbox: 0.0677, loss_cls: 0.2964, acc: 91.2080, loss_bbox: 0.2607, loss: 0.6757 +2022-10-22 16:53:58,610 - mmdet - INFO - Iter [8400/12000] lr: 3.000e-02, eta: 0:07:32, time: 0.124, data_time: 0.008, memory: 4086, loss_rpn_cls: 0.0513, loss_rpn_bbox: 0.0644, loss_cls: 0.2924, acc: 91.3198, loss_bbox: 0.2551, loss: 0.6632 +2022-10-22 16:54:04,891 - mmdet - INFO - Iter [8450/12000] lr: 3.000e-02, eta: 0:07:26, time: 0.126, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0506, loss_rpn_bbox: 0.0659, loss_cls: 0.2822, acc: 91.4727, loss_bbox: 0.2572, loss: 0.6558 +2022-10-22 16:54:11,104 - mmdet - INFO - Iter [8500/12000] lr: 3.000e-02, eta: 0:07:20, time: 0.124, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0498, loss_rpn_bbox: 0.0660, loss_cls: 0.2924, acc: 91.4468, loss_bbox: 0.2548, loss: 0.6631 +2022-10-22 16:54:17,393 - mmdet - INFO - Iter [8550/12000] lr: 3.000e-02, eta: 0:07:13, time: 0.126, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0488, loss_rpn_bbox: 0.0612, loss_cls: 0.2881, acc: 91.5671, loss_bbox: 0.2485, loss: 0.6465 +2022-10-22 16:54:23,808 - mmdet - INFO - Iter [8600/12000] lr: 3.000e-02, eta: 0:07:07, time: 0.128, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0574, loss_rpn_bbox: 0.0693, loss_cls: 0.2994, acc: 91.0710, loss_bbox: 0.2609, loss: 0.6869 +2022-10-22 16:54:30,350 - mmdet - INFO - Iter [8650/12000] lr: 3.000e-02, eta: 0:07:01, time: 0.131, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0481, loss_rpn_bbox: 0.0616, loss_cls: 0.2783, acc: 91.6069, loss_bbox: 0.2504, loss: 0.6385 +2022-10-22 16:54:36,559 - mmdet - INFO - Iter [8700/12000] lr: 3.000e-02, eta: 0:06:55, time: 0.124, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0547, loss_rpn_bbox: 0.0653, loss_cls: 0.2918, acc: 91.4026, loss_bbox: 0.2551, loss: 0.6670 +2022-10-22 16:54:42,757 - mmdet - INFO - Iter [8750/12000] lr: 3.000e-02, eta: 0:06:48, time: 0.124, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0492, loss_rpn_bbox: 0.0621, loss_cls: 0.2759, acc: 91.7061, loss_bbox: 0.2450, loss: 0.6322 +2022-10-22 16:54:48,977 - mmdet - INFO - Iter [8800/12000] lr: 3.000e-02, eta: 0:06:42, time: 0.124, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0494, loss_rpn_bbox: 0.0608, loss_cls: 0.2834, acc: 91.6045, loss_bbox: 0.2517, loss: 0.6452 +2022-10-22 16:54:55,302 - mmdet - INFO - Iter [8850/12000] lr: 3.000e-02, eta: 0:06:36, time: 0.126, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0548, loss_rpn_bbox: 0.0659, loss_cls: 0.2987, acc: 90.9878, loss_bbox: 0.2662, loss: 0.6855 +2022-10-22 16:55:01,554 - mmdet - INFO - Iter [8900/12000] lr: 3.000e-02, eta: 0:06:29, time: 0.125, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0507, loss_rpn_bbox: 0.0671, loss_cls: 0.2976, acc: 91.0359, loss_bbox: 0.2610, loss: 0.6764 +2022-10-22 16:55:07,815 - mmdet - INFO - Iter [8950/12000] lr: 3.000e-02, eta: 0:06:23, time: 0.125, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0483, loss_rpn_bbox: 0.0642, loss_cls: 0.2786, acc: 91.6858, loss_bbox: 0.2488, loss: 0.6399 +2022-10-22 16:55:14,172 - mmdet - INFO - Exp name: faster_rcnn_fpn_12k_semi-coco.py +2022-10-22 16:55:14,173 - mmdet - INFO - Iter [9000/12000] lr: 3.000e-02, eta: 0:06:17, time: 0.127, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0529, loss_rpn_bbox: 0.0685, loss_cls: 0.2932, acc: 91.1577, loss_bbox: 0.2626, loss: 0.6773 +2022-10-22 16:55:20,426 - mmdet - INFO - Iter [9050/12000] lr: 3.000e-03, eta: 0:06:10, time: 0.125, data_time: 0.008, memory: 4086, loss_rpn_cls: 0.0473, loss_rpn_bbox: 0.0641, loss_cls: 0.2839, acc: 91.3230, loss_bbox: 0.2576, loss: 0.6529 +2022-10-22 16:55:26,677 - mmdet - INFO - Iter [9100/12000] lr: 3.000e-03, eta: 0:06:04, time: 0.125, data_time: 0.008, memory: 4086, loss_rpn_cls: 0.0462, loss_rpn_bbox: 0.0600, loss_cls: 0.2656, acc: 91.7488, loss_bbox: 0.2475, loss: 0.6194 +2022-10-22 16:55:33,066 - mmdet - INFO - Iter [9150/12000] lr: 3.000e-03, eta: 0:05:58, time: 0.128, data_time: 0.008, memory: 4086, loss_rpn_cls: 0.0486, loss_rpn_bbox: 0.0644, loss_cls: 0.2729, acc: 91.6545, loss_bbox: 0.2480, loss: 0.6338 +2022-10-22 16:55:39,379 - mmdet - INFO - Iter [9200/12000] lr: 3.000e-03, eta: 0:05:52, time: 0.126, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0464, loss_rpn_bbox: 0.0620, loss_cls: 0.2602, acc: 91.8008, loss_bbox: 0.2529, loss: 0.6215 +2022-10-22 16:55:45,799 - mmdet - INFO - Iter [9250/12000] lr: 3.000e-03, eta: 0:05:45, time: 0.128, data_time: 0.008, memory: 4086, loss_rpn_cls: 0.0438, loss_rpn_bbox: 0.0589, loss_cls: 0.2683, acc: 91.5366, loss_bbox: 0.2531, loss: 0.6241 +2022-10-22 16:55:52,172 - mmdet - INFO - Iter [9300/12000] lr: 3.000e-03, eta: 0:05:39, time: 0.127, data_time: 0.008, memory: 4086, loss_rpn_cls: 0.0459, loss_rpn_bbox: 0.0640, loss_cls: 0.2731, acc: 91.4482, loss_bbox: 0.2583, loss: 0.6414 +2022-10-22 16:55:58,492 - mmdet - INFO - Iter [9350/12000] lr: 3.000e-03, eta: 0:05:33, time: 0.126, data_time: 0.008, memory: 4086, loss_rpn_cls: 0.0434, loss_rpn_bbox: 0.0595, loss_cls: 0.2677, acc: 91.7297, loss_bbox: 0.2497, loss: 0.6202 +2022-10-22 16:56:04,870 - mmdet - INFO - Iter [9400/12000] lr: 3.000e-03, eta: 0:05:27, time: 0.128, data_time: 0.008, memory: 4086, loss_rpn_cls: 0.0456, loss_rpn_bbox: 0.0628, loss_cls: 0.2567, acc: 91.9172, loss_bbox: 0.2464, loss: 0.6116 +2022-10-22 16:56:11,135 - mmdet - INFO - Iter [9450/12000] lr: 3.000e-03, eta: 0:05:20, time: 0.125, data_time: 0.008, memory: 4086, loss_rpn_cls: 0.0422, loss_rpn_bbox: 0.0619, loss_cls: 0.2611, acc: 91.8494, loss_bbox: 0.2493, loss: 0.6145 +2022-10-22 16:56:17,408 - mmdet - INFO - Iter [9500/12000] lr: 3.000e-03, eta: 0:05:14, time: 0.125, data_time: 0.008, memory: 4086, loss_rpn_cls: 0.0459, loss_rpn_bbox: 0.0640, loss_cls: 0.2761, acc: 91.4441, loss_bbox: 0.2561, loss: 0.6421 +2022-10-22 16:56:23,755 - mmdet - INFO - Iter [9550/12000] lr: 3.000e-03, eta: 0:05:08, time: 0.127, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0457, loss_rpn_bbox: 0.0604, loss_cls: 0.2617, acc: 91.6775, loss_bbox: 0.2545, loss: 0.6224 +2022-10-22 16:56:30,017 - mmdet - INFO - Iter [9600/12000] lr: 3.000e-03, eta: 0:05:01, time: 0.125, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0425, loss_rpn_bbox: 0.0544, loss_cls: 0.2544, acc: 92.1001, loss_bbox: 0.2378, loss: 0.5892 +2022-10-22 16:56:36,193 - mmdet - INFO - Iter [9650/12000] lr: 3.000e-03, eta: 0:04:55, time: 0.123, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0435, loss_rpn_bbox: 0.0579, loss_cls: 0.2566, acc: 91.8743, loss_bbox: 0.2437, loss: 0.6017 +2022-10-22 16:56:42,440 - mmdet - INFO - Iter [9700/12000] lr: 3.000e-03, eta: 0:04:49, time: 0.125, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0430, loss_rpn_bbox: 0.0607, loss_cls: 0.2533, acc: 91.9861, loss_bbox: 0.2444, loss: 0.6014 +2022-10-22 16:56:48,660 - mmdet - INFO - Iter [9750/12000] lr: 3.000e-03, eta: 0:04:43, time: 0.124, data_time: 0.008, memory: 4086, loss_rpn_cls: 0.0438, loss_rpn_bbox: 0.0602, loss_cls: 0.2545, acc: 91.9121, loss_bbox: 0.2435, loss: 0.6021 +2022-10-22 16:56:54,878 - mmdet - INFO - Iter [9800/12000] lr: 3.000e-03, eta: 0:04:36, time: 0.124, data_time: 0.008, memory: 4086, loss_rpn_cls: 0.0434, loss_rpn_bbox: 0.0611, loss_cls: 0.2626, acc: 91.6379, loss_bbox: 0.2502, loss: 0.6172 +2022-10-22 16:57:01,074 - mmdet - INFO - Iter [9850/12000] lr: 3.000e-03, eta: 0:04:30, time: 0.124, data_time: 0.008, memory: 4086, loss_rpn_cls: 0.0393, loss_rpn_bbox: 0.0586, loss_cls: 0.2424, acc: 92.3071, loss_bbox: 0.2298, loss: 0.5702 +2022-10-22 16:57:07,472 - mmdet - INFO - Iter [9900/12000] lr: 3.000e-03, eta: 0:04:24, time: 0.128, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0428, loss_rpn_bbox: 0.0585, loss_cls: 0.2578, acc: 91.7849, loss_bbox: 0.2466, loss: 0.6057 +2022-10-22 16:57:13,775 - mmdet - INFO - Iter [9950/12000] lr: 3.000e-03, eta: 0:04:17, time: 0.126, data_time: 0.008, memory: 4086, loss_rpn_cls: 0.0400, loss_rpn_bbox: 0.0576, loss_cls: 0.2398, acc: 92.4346, loss_bbox: 0.2340, loss: 0.5714 +2022-10-22 16:57:20,010 - mmdet - INFO - Exp name: faster_rcnn_fpn_12k_semi-coco.py +2022-10-22 16:57:20,011 - mmdet - INFO - Iter [10000/12000] lr: 3.000e-03, eta: 0:04:11, time: 0.125, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0428, loss_rpn_bbox: 0.0596, loss_cls: 0.2594, acc: 91.8596, loss_bbox: 0.2455, loss: 0.6073 +2022-10-22 16:57:26,360 - mmdet - INFO - Iter [10050/12000] lr: 3.000e-03, eta: 0:04:05, time: 0.127, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0433, loss_rpn_bbox: 0.0580, loss_cls: 0.2614, acc: 91.8499, loss_bbox: 0.2524, loss: 0.6150 +2022-10-22 16:57:32,861 - mmdet - INFO - Iter [10100/12000] lr: 3.000e-03, eta: 0:03:59, time: 0.130, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0433, loss_rpn_bbox: 0.0590, loss_cls: 0.2502, acc: 92.0054, loss_bbox: 0.2383, loss: 0.5908 +2022-10-22 16:57:39,119 - mmdet - INFO - Iter [10150/12000] lr: 3.000e-03, eta: 0:03:52, time: 0.125, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0392, loss_rpn_bbox: 0.0556, loss_cls: 0.2491, acc: 92.0425, loss_bbox: 0.2429, loss: 0.5868 +2022-10-22 16:57:45,341 - mmdet - INFO - Iter [10200/12000] lr: 3.000e-03, eta: 0:03:46, time: 0.124, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0401, loss_rpn_bbox: 0.0584, loss_cls: 0.2529, acc: 92.0129, loss_bbox: 0.2428, loss: 0.5941 +2022-10-22 16:57:51,853 - mmdet - INFO - Iter [10250/12000] lr: 3.000e-03, eta: 0:03:40, time: 0.130, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0426, loss_rpn_bbox: 0.0599, loss_cls: 0.2633, acc: 91.7686, loss_bbox: 0.2511, loss: 0.6170 +2022-10-22 16:57:58,161 - mmdet - INFO - Iter [10300/12000] lr: 3.000e-03, eta: 0:03:33, time: 0.126, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0414, loss_rpn_bbox: 0.0583, loss_cls: 0.2553, acc: 91.8328, loss_bbox: 0.2423, loss: 0.5974 +2022-10-22 16:58:04,348 - mmdet - INFO - Iter [10350/12000] lr: 3.000e-03, eta: 0:03:27, time: 0.124, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0430, loss_rpn_bbox: 0.0573, loss_cls: 0.2641, acc: 91.7388, loss_bbox: 0.2471, loss: 0.6116 +2022-10-22 16:58:10,603 - mmdet - INFO - Iter [10400/12000] lr: 3.000e-03, eta: 0:03:21, time: 0.125, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0402, loss_rpn_bbox: 0.0546, loss_cls: 0.2528, acc: 91.9519, loss_bbox: 0.2423, loss: 0.5899 +2022-10-22 16:58:16,835 - mmdet - INFO - Iter [10450/12000] lr: 3.000e-03, eta: 0:03:14, time: 0.125, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0424, loss_rpn_bbox: 0.0583, loss_cls: 0.2505, acc: 92.0305, loss_bbox: 0.2415, loss: 0.5926 +2022-10-22 16:58:23,159 - mmdet - INFO - Iter [10500/12000] lr: 3.000e-03, eta: 0:03:08, time: 0.126, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0398, loss_rpn_bbox: 0.0561, loss_cls: 0.2484, acc: 92.1521, loss_bbox: 0.2408, loss: 0.5851 +2022-10-22 16:58:29,477 - mmdet - INFO - Iter [10550/12000] lr: 3.000e-03, eta: 0:03:02, time: 0.126, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0442, loss_rpn_bbox: 0.0591, loss_cls: 0.2506, acc: 92.1785, loss_bbox: 0.2385, loss: 0.5924 +2022-10-22 16:58:35,791 - mmdet - INFO - Iter [10600/12000] lr: 3.000e-03, eta: 0:02:56, time: 0.126, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0423, loss_rpn_bbox: 0.0581, loss_cls: 0.2457, acc: 92.2214, loss_bbox: 0.2384, loss: 0.5845 +2022-10-22 16:58:42,099 - mmdet - INFO - Iter [10650/12000] lr: 3.000e-03, eta: 0:02:49, time: 0.126, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0445, loss_rpn_bbox: 0.0621, loss_cls: 0.2586, acc: 91.8770, loss_bbox: 0.2425, loss: 0.6077 +2022-10-22 16:58:48,348 - mmdet - INFO - Iter [10700/12000] lr: 3.000e-03, eta: 0:02:43, time: 0.125, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0430, loss_rpn_bbox: 0.0601, loss_cls: 0.2548, acc: 91.9316, loss_bbox: 0.2471, loss: 0.6050 +2022-10-22 16:58:54,628 - mmdet - INFO - Iter [10750/12000] lr: 3.000e-03, eta: 0:02:37, time: 0.126, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0445, loss_rpn_bbox: 0.0612, loss_cls: 0.2706, acc: 91.4897, loss_bbox: 0.2586, loss: 0.6350 +2022-10-22 16:59:00,949 - mmdet - INFO - Iter [10800/12000] lr: 3.000e-03, eta: 0:02:30, time: 0.126, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0418, loss_rpn_bbox: 0.0581, loss_cls: 0.2514, acc: 91.9272, loss_bbox: 0.2502, loss: 0.6015 +2022-10-22 16:59:07,152 - mmdet - INFO - Iter [10850/12000] lr: 3.000e-03, eta: 0:02:24, time: 0.124, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0374, loss_rpn_bbox: 0.0527, loss_cls: 0.2433, acc: 92.3982, loss_bbox: 0.2290, loss: 0.5624 +2022-10-22 16:59:13,407 - mmdet - INFO - Iter [10900/12000] lr: 3.000e-03, eta: 0:02:18, time: 0.125, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0398, loss_rpn_bbox: 0.0593, loss_cls: 0.2516, acc: 92.0269, loss_bbox: 0.2399, loss: 0.5906 +2022-10-22 16:59:19,731 - mmdet - INFO - Iter [10950/12000] lr: 3.000e-03, eta: 0:02:12, time: 0.126, data_time: 0.008, memory: 4086, loss_rpn_cls: 0.0398, loss_rpn_bbox: 0.0625, loss_cls: 0.2573, acc: 91.7578, loss_bbox: 0.2533, loss: 0.6129 +2022-10-22 16:59:26,027 - mmdet - INFO - Exp name: faster_rcnn_fpn_12k_semi-coco.py +2022-10-22 16:59:26,028 - mmdet - INFO - Iter [11000/12000] lr: 3.000e-03, eta: 0:02:05, time: 0.126, data_time: 0.008, memory: 4086, loss_rpn_cls: 0.0421, loss_rpn_bbox: 0.0592, loss_cls: 0.2490, acc: 91.9536, loss_bbox: 0.2440, loss: 0.5943 +2022-10-22 16:59:32,347 - mmdet - INFO - Iter [11050/12000] lr: 3.000e-04, eta: 0:01:59, time: 0.126, data_time: 0.008, memory: 4086, loss_rpn_cls: 0.0410, loss_rpn_bbox: 0.0597, loss_cls: 0.2604, acc: 91.7368, loss_bbox: 0.2507, loss: 0.6117 +2022-10-22 16:59:38,646 - mmdet - INFO - Iter [11100/12000] lr: 3.000e-04, eta: 0:01:53, time: 0.126, data_time: 0.008, memory: 4086, loss_rpn_cls: 0.0405, loss_rpn_bbox: 0.0582, loss_cls: 0.2509, acc: 91.9768, loss_bbox: 0.2427, loss: 0.5924 +2022-10-22 16:59:44,889 - mmdet - INFO - Iter [11150/12000] lr: 3.000e-04, eta: 0:01:46, time: 0.125, data_time: 0.008, memory: 4086, loss_rpn_cls: 0.0415, loss_rpn_bbox: 0.0571, loss_cls: 0.2371, acc: 92.3857, loss_bbox: 0.2286, loss: 0.5643 +2022-10-22 16:59:51,287 - mmdet - INFO - Iter [11200/12000] lr: 3.000e-04, eta: 0:01:40, time: 0.128, data_time: 0.008, memory: 4086, loss_rpn_cls: 0.0407, loss_rpn_bbox: 0.0587, loss_cls: 0.2430, acc: 92.2397, loss_bbox: 0.2360, loss: 0.5784 +2022-10-22 16:59:57,536 - mmdet - INFO - Iter [11250/12000] lr: 3.000e-04, eta: 0:01:34, time: 0.125, data_time: 0.008, memory: 4086, loss_rpn_cls: 0.0401, loss_rpn_bbox: 0.0570, loss_cls: 0.2491, acc: 92.0874, loss_bbox: 0.2425, loss: 0.5888 +2022-10-22 17:00:03,927 - mmdet - INFO - Iter [11300/12000] lr: 3.000e-04, eta: 0:01:28, time: 0.128, data_time: 0.008, memory: 4086, loss_rpn_cls: 0.0404, loss_rpn_bbox: 0.0551, loss_cls: 0.2473, acc: 92.2288, loss_bbox: 0.2379, loss: 0.5806 +2022-10-22 17:00:10,209 - mmdet - INFO - Iter [11350/12000] lr: 3.000e-04, eta: 0:01:21, time: 0.126, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0419, loss_rpn_bbox: 0.0583, loss_cls: 0.2559, acc: 91.9749, loss_bbox: 0.2444, loss: 0.6005 +2022-10-22 17:00:16,459 - mmdet - INFO - Iter [11400/12000] lr: 3.000e-04, eta: 0:01:15, time: 0.125, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0426, loss_rpn_bbox: 0.0612, loss_cls: 0.2611, acc: 91.8323, loss_bbox: 0.2458, loss: 0.6106 +2022-10-22 17:00:22,713 - mmdet - INFO - Iter [11450/12000] lr: 3.000e-04, eta: 0:01:09, time: 0.125, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0397, loss_rpn_bbox: 0.0573, loss_cls: 0.2547, acc: 91.8511, loss_bbox: 0.2494, loss: 0.6010 +2022-10-22 17:00:29,032 - mmdet - INFO - Iter [11500/12000] lr: 3.000e-04, eta: 0:01:02, time: 0.126, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0404, loss_rpn_bbox: 0.0591, loss_cls: 0.2532, acc: 91.8679, loss_bbox: 0.2531, loss: 0.6057 +2022-10-22 17:00:35,378 - mmdet - INFO - Iter [11550/12000] lr: 3.000e-04, eta: 0:00:56, time: 0.127, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0395, loss_rpn_bbox: 0.0569, loss_cls: 0.2493, acc: 92.1882, loss_bbox: 0.2407, loss: 0.5865 +2022-10-22 17:00:41,614 - mmdet - INFO - Iter [11600/12000] lr: 3.000e-04, eta: 0:00:50, time: 0.125, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0428, loss_rpn_bbox: 0.0585, loss_cls: 0.2478, acc: 92.0247, loss_bbox: 0.2471, loss: 0.5961 +2022-10-22 17:00:47,908 - mmdet - INFO - Iter [11650/12000] lr: 3.000e-04, eta: 0:00:44, time: 0.126, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0422, loss_rpn_bbox: 0.0595, loss_cls: 0.2530, acc: 91.9456, loss_bbox: 0.2463, loss: 0.6010 +2022-10-22 17:00:54,138 - mmdet - INFO - Iter [11700/12000] lr: 3.000e-04, eta: 0:00:37, time: 0.125, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0424, loss_rpn_bbox: 0.0594, loss_cls: 0.2570, acc: 91.8096, loss_bbox: 0.2482, loss: 0.6070 +2022-10-22 17:01:00,496 - mmdet - INFO - Iter [11750/12000] lr: 3.000e-04, eta: 0:00:31, time: 0.127, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0435, loss_rpn_bbox: 0.0623, loss_cls: 0.2552, acc: 91.7668, loss_bbox: 0.2519, loss: 0.6128 +2022-10-22 17:01:06,770 - mmdet - INFO - Iter [11800/12000] lr: 3.000e-04, eta: 0:00:25, time: 0.125, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0444, loss_rpn_bbox: 0.0597, loss_cls: 0.2468, acc: 92.0859, loss_bbox: 0.2423, loss: 0.5932 +2022-10-22 17:01:12,989 - mmdet - INFO - Iter [11850/12000] lr: 3.000e-04, eta: 0:00:18, time: 0.124, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0432, loss_rpn_bbox: 0.0566, loss_cls: 0.2581, acc: 91.7993, loss_bbox: 0.2474, loss: 0.6053 +2022-10-22 17:01:19,199 - mmdet - INFO - Iter [11900/12000] lr: 3.000e-04, eta: 0:00:12, time: 0.124, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0400, loss_rpn_bbox: 0.0560, loss_cls: 0.2529, acc: 91.8071, loss_bbox: 0.2463, loss: 0.5953 +2022-10-22 17:01:25,360 - mmdet - INFO - Iter [11950/12000] lr: 3.000e-04, eta: 0:00:06, time: 0.123, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0392, loss_rpn_bbox: 0.0553, loss_cls: 0.2533, acc: 91.9062, loss_bbox: 0.2463, loss: 0.5940 +2022-10-22 17:01:31,560 - mmdet - INFO - Saving checkpoint at 12000 iterations +2022-10-22 17:01:32,262 - mmdet - INFO - Exp name: faster_rcnn_fpn_12k_semi-coco.py +2022-10-22 17:01:32,263 - mmdet - INFO - Iter [12000/12000] lr: 3.000e-04, eta: 0:00:00, time: 0.138, data_time: 0.007, memory: 4086, loss_rpn_cls: 0.0411, loss_rpn_bbox: 0.0583, loss_cls: 0.2511, acc: 92.0078, loss_bbox: 0.2432, loss: 0.5937 +2022-10-22 17:01:56,564 - mmdet - INFO - Evaluating bbox... +2022-10-22 17:02:30,040 - mmdet - INFO - + Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.306 + Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=1000 ] = 0.490 + Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=1000 ] = 0.327 + Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.169 + Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.336 + Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.395 + Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.465 + Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.465 + Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=1000 ] = 0.465 + Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.267 + Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.509 + Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.596 + +2022-10-22 17:02:31,084 - mmdet - INFO - Now best checkpoint is saved as best_bbox_mAP_iter_12000.pth. +2022-10-22 17:02:31,084 - mmdet - INFO - Best bbox_mAP is 0.3060 at 12000 iter. +2022-10-22 17:02:31,085 - mmdet - INFO - Exp name: faster_rcnn_fpn_12k_semi-coco.py +2022-10-22 17:02:31,085 - mmdet - INFO - Iter(val) [625] bbox_mAP: 0.3060, bbox_mAP_50: 0.4900, bbox_mAP_75: 0.3270, bbox_mAP_s: 0.1690, bbox_mAP_m: 0.3360, bbox_mAP_l: 0.3950, bbox_mAP_copypaste: 0.306 0.490 0.327 0.169 0.336 0.395