2022/09/13 12:04:16 - mmengine - INFO - ------------------------------------------------------------ System environment: sys.platform: linux Python: 3.7.13 (default, Mar 29 2022, 02:18:16) [GCC 7.5.0] CUDA available: True numpy_random_seed: 799856970 GPU 0,1,2,3,4,5,6,7: NVIDIA A100-SXM4-80GB CUDA_HOME: /mnt/lustre/share/cuda-11.1 NVCC: Cuda compilation tools, release 11.1, V11.1.74 GCC: gcc (GCC) 5.4.0 PyTorch: 1.9.0+cu111 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 v2.1.2 (Git Hash 98be7e8afa711dc9b66c8ff3504129cb82013cdb) - OpenMP 201511 (a.k.a. OpenMP 4.5) - NNPACK is enabled - CPU capability usage: AVX2 - CUDA Runtime 11.1 - NVCC architecture flags: -gencode;arch=compute_37,code=sm_37;-gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_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 8.0.5 - Magma 2.5.2 - Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.1, CUDNN_VERSION=8.0.5, 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 -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=1.9.0, 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: 0.10.0+cu111 OpenCV: 4.6.0 MMEngine: 0.1.0 Runtime environment: cudnn_benchmark: False mp_cfg: {'mp_start_method': 'fork', 'opencv_num_threads': 0} dist_cfg: {'backend': 'nccl'} seed: None Distributed launcher: slurm Distributed training: True GPU number: 8 ------------------------------------------------------------ 2022/09/13 12:04:18 - mmengine - INFO - Config: default_scope = 'mmpose' default_hooks = dict( timer=dict(type='IterTimerHook'), logger=dict(type='LoggerHook', interval=50), param_scheduler=dict(type='ParamSchedulerHook'), checkpoint=dict( type='CheckpointHook', interval=1, save_best='coco/AP', rule='greater', max_keep_ckpts=1), sampler_seed=dict(type='DistSamplerSeedHook'), visualization=dict(type='PoseVisualizationHook', enable=False)) custom_hooks = [dict(type='SyncBuffersHook')] env_cfg = dict( cudnn_benchmark=False, mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0), dist_cfg=dict(backend='nccl')) vis_backends = [dict(type='LocalVisBackend')] visualizer = dict( type='PoseLocalVisualizer', vis_backends=[dict(type='LocalVisBackend')], name='visualizer') log_processor = dict( type='LogProcessor', window_size=50, by_epoch=True, num_digits=6) log_level = 'INFO' load_from = None resume = False file_client_args = dict( backend='petrel', path_mapping=dict({ './data/': 's3://openmmlab/datasets/detection/', 'data/': 's3://openmmlab/datasets/detection/' })) train_cfg = dict(by_epoch=True, max_epochs=210, val_interval=10) val_cfg = dict() test_cfg = dict() optim_wrapper = dict(optimizer=dict(type='Adam', lr=0.0005)) param_scheduler = [ dict( type='LinearLR', begin=0, end=500, start_factor=0.001, by_epoch=False), dict( type='MultiStepLR', begin=0, end=210, milestones=[170, 200], gamma=0.1, by_epoch=True) ] auto_scale_lr = dict(base_batch_size=512) codec = dict( type='MSRAHeatmap', input_size=(192, 256), heatmap_size=(48, 64), sigma=2, unbiased=True) model = dict( type='TopdownPoseEstimator', data_preprocessor=dict( type='PoseDataPreprocessor', mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], bgr_to_rgb=True), backbone=dict( type='HRNet', in_channels=3, extra=dict( stage1=dict( num_modules=1, num_branches=1, block='BOTTLENECK', num_blocks=(4, ), num_channels=(64, )), stage2=dict( num_modules=1, num_branches=2, block='BASIC', num_blocks=(4, 4), num_channels=(32, 64)), stage3=dict( num_modules=4, num_branches=3, block='BASIC', num_blocks=(4, 4, 4), num_channels=(32, 64, 128)), stage4=dict( num_modules=3, num_branches=4, block='BASIC', num_blocks=(4, 4, 4, 4), num_channels=(32, 64, 128, 256))), init_cfg=dict( type='Pretrained', checkpoint= 'https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth' )), head=dict( type='HeatmapHead', in_channels=32, out_channels=17, deconv_out_channels=None, loss=dict(type='KeypointMSELoss', use_target_weight=True), decoder=dict( type='MSRAHeatmap', input_size=(192, 256), heatmap_size=(48, 64), sigma=2, unbiased=True)), test_cfg=dict(flip_test=True, flip_mode='heatmap', shift_heatmap=True)) dataset_type = 'CocoDataset' data_mode = 'topdown' data_root = 'data/coco/' train_pipeline = [ dict( type='LoadImage', file_client_args=dict( backend='petrel', path_mapping=dict({ './data/': 's3://openmmlab/datasets/detection/', 'data/': 's3://openmmlab/datasets/detection/' }))), dict(type='GetBBoxCenterScale'), dict(type='RandomFlip', direction='horizontal'), dict(type='RandomHalfBody'), dict(type='RandomBBoxTransform'), dict(type='TopdownAffine', input_size=(192, 256)), dict( type='GenerateTarget', target_type='heatmap', encoder=dict( type='MSRAHeatmap', input_size=(192, 256), heatmap_size=(48, 64), sigma=2, unbiased=True)), dict(type='PackPoseInputs') ] test_pipeline = [ dict( type='LoadImage', file_client_args=dict( backend='petrel', path_mapping=dict({ './data/': 's3://openmmlab/datasets/detection/', 'data/': 's3://openmmlab/datasets/detection/' }))), dict(type='GetBBoxCenterScale'), dict(type='TopdownAffine', input_size=(192, 256)), dict(type='PackPoseInputs') ] train_dataloader = dict( batch_size=64, num_workers=2, persistent_workers=True, sampler=dict(type='DefaultSampler', shuffle=True), dataset=dict( type='CocoDataset', data_root='data/coco/', data_mode='topdown', ann_file='annotations/person_keypoints_train2017.json', data_prefix=dict(img='train2017/'), pipeline=[ dict( type='LoadImage', file_client_args=dict( backend='petrel', path_mapping=dict({ './data/': 's3://openmmlab/datasets/detection/', 'data/': 's3://openmmlab/datasets/detection/' }))), dict(type='GetBBoxCenterScale'), dict(type='RandomFlip', direction='horizontal'), dict(type='RandomHalfBody'), dict(type='RandomBBoxTransform'), dict(type='TopdownAffine', input_size=(192, 256)), dict( type='GenerateTarget', target_type='heatmap', encoder=dict( type='MSRAHeatmap', input_size=(192, 256), heatmap_size=(48, 64), sigma=2, unbiased=True)), dict(type='PackPoseInputs') ])) val_dataloader = dict( batch_size=32, num_workers=2, persistent_workers=True, drop_last=False, sampler=dict(type='DefaultSampler', shuffle=False, round_up=False), dataset=dict( type='CocoDataset', data_root='data/coco/', data_mode='topdown', ann_file='annotations/person_keypoints_val2017.json', bbox_file= 'data/coco/person_detection_results/COCO_val2017_detections_AP_H_56_person.json', data_prefix=dict(img='val2017/'), test_mode=True, pipeline=[ dict( type='LoadImage', file_client_args=dict( backend='petrel', path_mapping=dict({ './data/': 's3://openmmlab/datasets/detection/', 'data/': 's3://openmmlab/datasets/detection/' }))), dict(type='GetBBoxCenterScale'), dict(type='TopdownAffine', input_size=(192, 256)), dict(type='PackPoseInputs') ])) test_dataloader = dict( batch_size=32, num_workers=2, persistent_workers=True, drop_last=False, sampler=dict(type='DefaultSampler', shuffle=False, round_up=False), dataset=dict( type='CocoDataset', data_root='data/coco/', data_mode='topdown', ann_file='annotations/person_keypoints_val2017.json', bbox_file= 'data/coco/person_detection_results/COCO_val2017_detections_AP_H_56_person.json', data_prefix=dict(img='val2017/'), test_mode=True, pipeline=[ dict( type='LoadImage', file_client_args=dict( backend='petrel', path_mapping=dict({ './data/': 's3://openmmlab/datasets/detection/', 'data/': 's3://openmmlab/datasets/detection/' }))), dict(type='GetBBoxCenterScale'), dict(type='TopdownAffine', input_size=(192, 256)), dict(type='PackPoseInputs') ])) val_evaluator = dict( type='CocoMetric', ann_file='data/coco/annotations/person_keypoints_val2017.json') test_evaluator = dict( type='CocoMetric', ann_file='data/coco/annotations/person_keypoints_val2017.json') launcher = 'slurm' work_dir = '/mnt/lustre/liqikai/work_dirs/20220913/dark_w32_256_v1/' 2022/09/13 12:05:02 - mmengine - WARNING - Failed to search registry with scope "mmpose" in the "data sampler" registry tree. As a workaround, the current "data sampler" registry in "mmengine" is used to build instance. This may cause unexpected failure when running the built modules. Please check whether "mmpose" is a correct scope, or whether the registry is initialized. 2022/09/13 12:05:02 - mmengine - WARNING - Failed to search registry with scope "mmpose" in the "optimizer wrapper constructor" registry tree. As a workaround, the current "optimizer wrapper constructor" registry in "mmengine" is used to build instance. This may cause unexpected failure when running the built modules. Please check whether "mmpose" is a correct scope, or whether the registry is initialized. 2022/09/13 12:05:02 - mmengine - WARNING - Failed to search registry with scope "mmpose" in the "optimizer" registry tree. As a workaround, the current "optimizer" registry in "mmengine" is used to build instance. This may cause unexpected failure when running the built modules. Please check whether "mmpose" is a correct scope, or whether the registry is initialized. 2022/09/13 12:05:02 - mmengine - WARNING - Failed to search registry with scope "mmpose" in the "optim_wrapper" registry tree. As a workaround, the current "optim_wrapper" registry in "mmengine" is used to build instance. This may cause unexpected failure when running the built modules. Please check whether "mmpose" is a correct scope, or whether the registry is initialized. 2022/09/13 12:05:02 - mmengine - WARNING - Failed to search registry with scope "mmpose" in the "parameter scheduler" registry tree. As a workaround, the current "parameter scheduler" registry in "mmengine" is used to build instance. This may cause unexpected failure when running the built modules. Please check whether "mmpose" is a correct scope, or whether the registry is initialized. 2022/09/13 12:05:02 - mmengine - WARNING - Failed to search registry with scope "mmpose" in the "parameter scheduler" registry tree. As a workaround, the current "parameter scheduler" registry in "mmengine" is used to build instance. This may cause unexpected failure when running the built modules. Please check whether "mmpose" is a correct scope, or whether the registry is initialized. 2022/09/13 12:05:02 - mmengine - WARNING - Failed to search registry with scope "mmpose" in the "parameter scheduler" registry tree. As a workaround, the current "parameter scheduler" registry in "mmengine" is used to build instance. This may cause unexpected failure when running the built modules. Please check whether "mmpose" is a correct scope, or whether the registry is initialized. 2022/09/13 12:05:02 - mmengine - WARNING - Failed to search registry with scope "mmpose" in the "parameter scheduler" registry tree. As a workaround, the current "parameter scheduler" registry in "mmengine" is used to build instance. This may cause unexpected failure when running the built modules. Please check whether "mmpose" is a correct scope, or whether the registry is initialized. 2022/09/13 12:05:06 - mmengine - WARNING - Failed to search registry with scope "mmpose" in the "data sampler" registry tree. As a workaround, the current "data sampler" registry in "mmengine" is used to build instance. This may cause unexpected failure when running the built modules. Please check whether "mmpose" is a correct scope, or whether the registry is initialized. 2022/09/13 12:05:08 - mmengine - WARNING - Failed to search registry with scope "mmpose" in the "weight initializer" registry tree. As a workaround, the current "weight initializer" registry in "mmengine" is used to build instance. This may cause unexpected failure when running the built modules. Please check whether "mmpose" is a correct scope, or whether the registry is initialized. 2022/09/13 12:05:09 - mmengine - WARNING - Failed to search registry with scope "mmpose" in the "weight initializer" registry tree. As a workaround, the current "weight initializer" registry in "mmengine" is used to build instance. This may cause unexpected failure when running the built modules. Please check whether "mmpose" is a correct scope, or whether the registry is initialized. 2022/09/13 12:05:09 - mmengine - WARNING - Failed to search registry with scope "mmpose" in the "weight initializer" registry tree. As a workaround, the current "weight initializer" registry in "mmengine" is used to build instance. This may cause unexpected failure when running the built modules. Please check whether "mmpose" is a correct scope, or whether the registry is initialized. Name of parameter - Initialization information backbone.conv1.weight - torch.Size([64, 3, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.bn1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.bn1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.bn2.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.bn2.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.layer1.0.conv1.weight - torch.Size([64, 64, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.layer1.0.bn1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.layer1.0.bn1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.layer1.0.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.layer1.0.bn2.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.layer1.0.bn2.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.layer1.0.conv3.weight - torch.Size([256, 64, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.layer1.0.bn3.weight - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.layer1.0.bn3.bias - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.layer1.0.downsample.0.weight - torch.Size([256, 64, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.layer1.0.downsample.1.weight - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.layer1.0.downsample.1.bias - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.layer1.1.conv1.weight - torch.Size([64, 256, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.layer1.1.bn1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.layer1.1.bn1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.layer1.1.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.layer1.1.bn2.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.layer1.1.bn2.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.layer1.1.conv3.weight - torch.Size([256, 64, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.layer1.1.bn3.weight - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.layer1.1.bn3.bias - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.layer1.2.conv1.weight - torch.Size([64, 256, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.layer1.2.bn1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.layer1.2.bn1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.layer1.2.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.layer1.2.bn2.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.layer1.2.bn2.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.layer1.2.conv3.weight - torch.Size([256, 64, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.layer1.2.bn3.weight - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.layer1.2.bn3.bias - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.layer1.3.conv1.weight - torch.Size([64, 256, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.layer1.3.bn1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.layer1.3.bn1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.layer1.3.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.layer1.3.bn2.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.layer1.3.bn2.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.layer1.3.conv3.weight - torch.Size([256, 64, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.layer1.3.bn3.weight - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.layer1.3.bn3.bias - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.transition1.0.0.weight - torch.Size([32, 256, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.transition1.0.1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.transition1.0.1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.transition1.1.0.0.weight - torch.Size([64, 256, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.transition1.1.0.1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.transition1.1.0.1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.branches.0.0.conv1.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.branches.0.0.bn1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.branches.0.0.bn1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.branches.0.0.conv2.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.branches.0.0.bn2.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.branches.0.0.bn2.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.branches.0.1.conv1.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.branches.0.1.bn1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.branches.0.1.bn1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.branches.0.1.conv2.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.branches.0.1.bn2.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.branches.0.1.bn2.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.branches.0.2.conv1.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.branches.0.2.bn1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.branches.0.2.bn1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.branches.0.2.conv2.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.branches.0.2.bn2.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.branches.0.2.bn2.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.branches.0.3.conv1.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.branches.0.3.bn1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.branches.0.3.bn1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.branches.0.3.conv2.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.branches.0.3.bn2.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.branches.0.3.bn2.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.branches.1.0.conv1.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.branches.1.0.bn1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.branches.1.0.bn1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.branches.1.0.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.branches.1.0.bn2.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.branches.1.0.bn2.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.branches.1.1.conv1.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.branches.1.1.bn1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.branches.1.1.bn1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.branches.1.1.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.branches.1.1.bn2.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.branches.1.1.bn2.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.branches.1.2.conv1.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.branches.1.2.bn1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.branches.1.2.bn1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.branches.1.2.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.branches.1.2.bn2.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.branches.1.2.bn2.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.branches.1.3.conv1.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.branches.1.3.bn1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.branches.1.3.bn1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.branches.1.3.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.branches.1.3.bn2.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.branches.1.3.bn2.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.fuse_layers.0.1.0.weight - torch.Size([32, 64, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.fuse_layers.0.1.1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.fuse_layers.0.1.1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.fuse_layers.1.0.0.0.weight - torch.Size([64, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.fuse_layers.1.0.0.1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage2.0.fuse_layers.1.0.0.1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.transition2.2.0.0.weight - torch.Size([128, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.transition2.2.0.1.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.transition2.2.0.1.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.0.0.conv1.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.0.0.bn1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.0.0.bn1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.0.0.conv2.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.0.0.bn2.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.0.0.bn2.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.0.1.conv1.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.0.1.bn1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.0.1.bn1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.0.1.conv2.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.0.1.bn2.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.0.1.bn2.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.0.2.conv1.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.0.2.bn1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.0.2.bn1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.0.2.conv2.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.0.2.bn2.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.0.2.bn2.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.0.3.conv1.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.0.3.bn1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.0.3.bn1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.0.3.conv2.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.0.3.bn2.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.0.3.bn2.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.1.0.conv1.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.1.0.bn1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.1.0.bn1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.1.0.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.1.0.bn2.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.1.0.bn2.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.1.1.conv1.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.1.1.bn1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.1.1.bn1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.1.1.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.1.1.bn2.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.1.1.bn2.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.1.2.conv1.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.1.2.bn1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.1.2.bn1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.1.2.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.1.2.bn2.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.1.2.bn2.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.1.3.conv1.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.1.3.bn1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.1.3.bn1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.1.3.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.1.3.bn2.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.1.3.bn2.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.2.0.conv1.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.2.0.bn1.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.2.0.bn1.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.2.0.conv2.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.2.0.bn2.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.2.0.bn2.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.2.1.conv1.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.2.1.bn1.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.2.1.bn1.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.2.1.conv2.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.2.1.bn2.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.2.1.bn2.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.2.2.conv1.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.2.2.bn1.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.2.2.bn1.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.2.2.conv2.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.2.2.bn2.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.2.2.bn2.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.2.3.conv1.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.2.3.bn1.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.2.3.bn1.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.2.3.conv2.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.2.3.bn2.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.branches.2.3.bn2.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.fuse_layers.0.1.0.weight - torch.Size([32, 64, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.fuse_layers.0.1.1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.fuse_layers.0.1.1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.fuse_layers.0.2.0.weight - torch.Size([32, 128, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.fuse_layers.0.2.1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.fuse_layers.0.2.1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.fuse_layers.1.0.0.0.weight - torch.Size([64, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.fuse_layers.1.0.0.1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.fuse_layers.1.0.0.1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.fuse_layers.1.2.0.weight - torch.Size([64, 128, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.fuse_layers.1.2.1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.fuse_layers.1.2.1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.fuse_layers.2.0.0.0.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.fuse_layers.2.0.0.1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.fuse_layers.2.0.0.1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.fuse_layers.2.0.1.0.weight - torch.Size([128, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.fuse_layers.2.0.1.1.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.fuse_layers.2.0.1.1.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.fuse_layers.2.1.0.0.weight - torch.Size([128, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.fuse_layers.2.1.0.1.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.0.fuse_layers.2.1.0.1.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.0.0.conv1.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.0.0.bn1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.0.0.bn1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.0.0.conv2.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.0.0.bn2.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.0.0.bn2.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.0.1.conv1.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.0.1.bn1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.0.1.bn1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.0.1.conv2.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.0.1.bn2.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.0.1.bn2.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.0.2.conv1.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.0.2.bn1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.0.2.bn1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.0.2.conv2.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.0.2.bn2.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.0.2.bn2.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.0.3.conv1.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.0.3.bn1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.0.3.bn1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.0.3.conv2.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.0.3.bn2.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.0.3.bn2.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.1.0.conv1.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.1.0.bn1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.1.0.bn1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.1.0.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.1.0.bn2.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.1.0.bn2.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.1.1.conv1.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.1.1.bn1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.1.1.bn1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.1.1.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.1.1.bn2.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.1.1.bn2.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.1.2.conv1.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.1.2.bn1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.1.2.bn1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.1.2.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.1.2.bn2.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.1.2.bn2.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.1.3.conv1.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.1.3.bn1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.1.3.bn1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.1.3.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.1.3.bn2.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.1.3.bn2.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.2.0.conv1.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.2.0.bn1.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.2.0.bn1.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.2.0.conv2.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.2.0.bn2.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.2.0.bn2.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.2.1.conv1.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.2.1.bn1.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.2.1.bn1.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.2.1.conv2.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.2.1.bn2.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.2.1.bn2.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.2.2.conv1.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.2.2.bn1.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.2.2.bn1.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.2.2.conv2.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.2.2.bn2.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.2.2.bn2.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.2.3.conv1.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.2.3.bn1.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.2.3.bn1.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.2.3.conv2.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.2.3.bn2.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.branches.2.3.bn2.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.fuse_layers.0.1.0.weight - torch.Size([32, 64, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.fuse_layers.0.1.1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.fuse_layers.0.1.1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.fuse_layers.0.2.0.weight - torch.Size([32, 128, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.fuse_layers.0.2.1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.fuse_layers.0.2.1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.fuse_layers.1.0.0.0.weight - torch.Size([64, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.fuse_layers.1.0.0.1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.fuse_layers.1.0.0.1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.fuse_layers.1.2.0.weight - torch.Size([64, 128, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.fuse_layers.1.2.1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.fuse_layers.1.2.1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.fuse_layers.2.0.0.0.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.fuse_layers.2.0.0.1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.fuse_layers.2.0.0.1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.fuse_layers.2.0.1.0.weight - torch.Size([128, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.fuse_layers.2.0.1.1.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.fuse_layers.2.0.1.1.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.fuse_layers.2.1.0.0.weight - torch.Size([128, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.fuse_layers.2.1.0.1.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.1.fuse_layers.2.1.0.1.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.0.0.conv1.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.0.0.bn1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.0.0.bn1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.0.0.conv2.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.0.0.bn2.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.0.0.bn2.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.0.1.conv1.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.0.1.bn1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.0.1.bn1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.0.1.conv2.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.0.1.bn2.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.0.1.bn2.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.0.2.conv1.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.0.2.bn1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.0.2.bn1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.0.2.conv2.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.0.2.bn2.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.0.2.bn2.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.0.3.conv1.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.0.3.bn1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.0.3.bn1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.0.3.conv2.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.0.3.bn2.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.0.3.bn2.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.1.0.conv1.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.1.0.bn1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.1.0.bn1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.1.0.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.1.0.bn2.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.1.0.bn2.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.1.1.conv1.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.1.1.bn1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.1.1.bn1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.1.1.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.1.1.bn2.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.1.1.bn2.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.1.2.conv1.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.1.2.bn1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.1.2.bn1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.1.2.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.1.2.bn2.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.1.2.bn2.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.1.3.conv1.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.1.3.bn1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.1.3.bn1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.1.3.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.1.3.bn2.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.1.3.bn2.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.2.0.conv1.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.2.0.bn1.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.2.0.bn1.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.2.0.conv2.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.2.0.bn2.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.2.0.bn2.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.2.1.conv1.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.2.1.bn1.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.2.1.bn1.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.2.1.conv2.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.2.1.bn2.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.2.1.bn2.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.2.2.conv1.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.2.2.bn1.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.2.2.bn1.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.2.2.conv2.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.2.2.bn2.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.2.2.bn2.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.2.3.conv1.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.2.3.bn1.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.2.3.bn1.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.2.3.conv2.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.2.3.bn2.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.branches.2.3.bn2.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.fuse_layers.0.1.0.weight - torch.Size([32, 64, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.fuse_layers.0.1.1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.fuse_layers.0.1.1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.fuse_layers.0.2.0.weight - torch.Size([32, 128, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.fuse_layers.0.2.1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.fuse_layers.0.2.1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.fuse_layers.1.0.0.0.weight - torch.Size([64, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.fuse_layers.1.0.0.1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.fuse_layers.1.0.0.1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.fuse_layers.1.2.0.weight - torch.Size([64, 128, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.fuse_layers.1.2.1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.fuse_layers.1.2.1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.fuse_layers.2.0.0.0.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.fuse_layers.2.0.0.1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.fuse_layers.2.0.0.1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.fuse_layers.2.0.1.0.weight - torch.Size([128, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.fuse_layers.2.0.1.1.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.fuse_layers.2.0.1.1.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.fuse_layers.2.1.0.0.weight - torch.Size([128, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.fuse_layers.2.1.0.1.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.2.fuse_layers.2.1.0.1.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.0.0.conv1.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.0.0.bn1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.0.0.bn1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.0.0.conv2.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.0.0.bn2.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.0.0.bn2.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.0.1.conv1.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.0.1.bn1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.0.1.bn1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.0.1.conv2.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.0.1.bn2.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.0.1.bn2.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.0.2.conv1.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.0.2.bn1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.0.2.bn1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.0.2.conv2.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.0.2.bn2.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.0.2.bn2.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.0.3.conv1.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.0.3.bn1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.0.3.bn1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.0.3.conv2.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.0.3.bn2.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.0.3.bn2.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.1.0.conv1.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.1.0.bn1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.1.0.bn1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.1.0.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.1.0.bn2.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.1.0.bn2.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.1.1.conv1.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.1.1.bn1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.1.1.bn1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.1.1.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.1.1.bn2.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.1.1.bn2.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.1.2.conv1.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.1.2.bn1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.1.2.bn1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.1.2.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.1.2.bn2.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.1.2.bn2.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.1.3.conv1.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.1.3.bn1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.1.3.bn1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.1.3.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.1.3.bn2.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.1.3.bn2.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.2.0.conv1.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.2.0.bn1.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.2.0.bn1.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.2.0.conv2.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.2.0.bn2.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.2.0.bn2.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.2.1.conv1.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.2.1.bn1.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.2.1.bn1.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.2.1.conv2.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.2.1.bn2.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.2.1.bn2.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.2.2.conv1.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.2.2.bn1.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.2.2.bn1.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.2.2.conv2.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.2.2.bn2.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.2.2.bn2.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.2.3.conv1.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.2.3.bn1.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.2.3.bn1.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.2.3.conv2.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.2.3.bn2.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.branches.2.3.bn2.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.fuse_layers.0.1.0.weight - torch.Size([32, 64, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.fuse_layers.0.1.1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.fuse_layers.0.1.1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.fuse_layers.0.2.0.weight - torch.Size([32, 128, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.fuse_layers.0.2.1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.fuse_layers.0.2.1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.fuse_layers.1.0.0.0.weight - torch.Size([64, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.fuse_layers.1.0.0.1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.fuse_layers.1.0.0.1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.fuse_layers.1.2.0.weight - torch.Size([64, 128, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.fuse_layers.1.2.1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.fuse_layers.1.2.1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.fuse_layers.2.0.0.0.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.fuse_layers.2.0.0.1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.fuse_layers.2.0.0.1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.fuse_layers.2.0.1.0.weight - torch.Size([128, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.fuse_layers.2.0.1.1.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.fuse_layers.2.0.1.1.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.fuse_layers.2.1.0.0.weight - torch.Size([128, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.fuse_layers.2.1.0.1.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage3.3.fuse_layers.2.1.0.1.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.transition3.3.0.0.weight - torch.Size([256, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.transition3.3.0.1.weight - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.transition3.3.0.1.bias - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.0.0.conv1.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.0.0.bn1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.0.0.bn1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.0.0.conv2.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.0.0.bn2.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.0.0.bn2.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.0.1.conv1.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.0.1.bn1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.0.1.bn1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.0.1.conv2.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.0.1.bn2.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.0.1.bn2.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.0.2.conv1.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.0.2.bn1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.0.2.bn1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.0.2.conv2.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.0.2.bn2.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.0.2.bn2.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.0.3.conv1.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.0.3.bn1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.0.3.bn1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.0.3.conv2.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.0.3.bn2.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.0.3.bn2.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.1.0.conv1.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.1.0.bn1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.1.0.bn1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.1.0.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.1.0.bn2.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.1.0.bn2.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.1.1.conv1.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.1.1.bn1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.1.1.bn1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.1.1.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.1.1.bn2.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.1.1.bn2.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.1.2.conv1.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.1.2.bn1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.1.2.bn1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.1.2.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.1.2.bn2.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.1.2.bn2.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.1.3.conv1.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.1.3.bn1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.1.3.bn1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.1.3.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.1.3.bn2.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.1.3.bn2.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.2.0.conv1.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.2.0.bn1.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.2.0.bn1.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.2.0.conv2.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.2.0.bn2.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.2.0.bn2.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.2.1.conv1.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.2.1.bn1.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.2.1.bn1.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.2.1.conv2.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.2.1.bn2.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.2.1.bn2.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.2.2.conv1.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.2.2.bn1.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.2.2.bn1.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.2.2.conv2.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.2.2.bn2.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.2.2.bn2.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.2.3.conv1.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.2.3.bn1.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.2.3.bn1.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.2.3.conv2.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.2.3.bn2.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.2.3.bn2.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.3.0.conv1.weight - torch.Size([256, 256, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.3.0.bn1.weight - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.3.0.bn1.bias - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.3.0.conv2.weight - torch.Size([256, 256, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.3.0.bn2.weight - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.3.0.bn2.bias - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.3.1.conv1.weight - torch.Size([256, 256, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.3.1.bn1.weight - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.3.1.bn1.bias - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.3.1.conv2.weight - torch.Size([256, 256, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.3.1.bn2.weight - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.3.1.bn2.bias - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.3.2.conv1.weight - torch.Size([256, 256, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.3.2.bn1.weight - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.3.2.bn1.bias - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.3.2.conv2.weight - torch.Size([256, 256, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.3.2.bn2.weight - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.3.2.bn2.bias - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.3.3.conv1.weight - torch.Size([256, 256, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.3.3.bn1.weight - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.3.3.bn1.bias - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.3.3.conv2.weight - torch.Size([256, 256, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.3.3.bn2.weight - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.branches.3.3.bn2.bias - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.fuse_layers.0.1.0.weight - torch.Size([32, 64, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.fuse_layers.0.1.1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.fuse_layers.0.1.1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.fuse_layers.0.2.0.weight - torch.Size([32, 128, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.fuse_layers.0.2.1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.fuse_layers.0.2.1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.fuse_layers.0.3.0.weight - torch.Size([32, 256, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.fuse_layers.0.3.1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.fuse_layers.0.3.1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.fuse_layers.1.0.0.0.weight - torch.Size([64, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.fuse_layers.1.0.0.1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.fuse_layers.1.0.0.1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.fuse_layers.1.2.0.weight - torch.Size([64, 128, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.fuse_layers.1.2.1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.fuse_layers.1.2.1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.fuse_layers.1.3.0.weight - torch.Size([64, 256, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.fuse_layers.1.3.1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.fuse_layers.1.3.1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.fuse_layers.2.0.0.0.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.fuse_layers.2.0.0.1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.fuse_layers.2.0.0.1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.fuse_layers.2.0.1.0.weight - torch.Size([128, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.fuse_layers.2.0.1.1.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.fuse_layers.2.0.1.1.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.fuse_layers.2.1.0.0.weight - torch.Size([128, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.fuse_layers.2.1.0.1.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.fuse_layers.2.1.0.1.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.fuse_layers.2.3.0.weight - torch.Size([128, 256, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.fuse_layers.2.3.1.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.fuse_layers.2.3.1.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.fuse_layers.3.0.0.0.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.fuse_layers.3.0.0.1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.fuse_layers.3.0.0.1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.fuse_layers.3.0.1.0.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.fuse_layers.3.0.1.1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.fuse_layers.3.0.1.1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.fuse_layers.3.0.2.0.weight - torch.Size([256, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.fuse_layers.3.0.2.1.weight - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.fuse_layers.3.0.2.1.bias - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.fuse_layers.3.1.0.0.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.fuse_layers.3.1.0.1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.fuse_layers.3.1.0.1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.fuse_layers.3.1.1.0.weight - torch.Size([256, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.fuse_layers.3.1.1.1.weight - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.fuse_layers.3.1.1.1.bias - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.fuse_layers.3.2.0.0.weight - torch.Size([256, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.fuse_layers.3.2.0.1.weight - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.0.fuse_layers.3.2.0.1.bias - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.0.0.conv1.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.0.0.bn1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.0.0.bn1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.0.0.conv2.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.0.0.bn2.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.0.0.bn2.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.0.1.conv1.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.0.1.bn1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.0.1.bn1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.0.1.conv2.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.0.1.bn2.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.0.1.bn2.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.0.2.conv1.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.0.2.bn1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.0.2.bn1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.0.2.conv2.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.0.2.bn2.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.0.2.bn2.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.0.3.conv1.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.0.3.bn1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.0.3.bn1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.0.3.conv2.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.0.3.bn2.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.0.3.bn2.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.1.0.conv1.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.1.0.bn1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.1.0.bn1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.1.0.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.1.0.bn2.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.1.0.bn2.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.1.1.conv1.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.1.1.bn1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.1.1.bn1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.1.1.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.1.1.bn2.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.1.1.bn2.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.1.2.conv1.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.1.2.bn1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.1.2.bn1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.1.2.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.1.2.bn2.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.1.2.bn2.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.1.3.conv1.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.1.3.bn1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.1.3.bn1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.1.3.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.1.3.bn2.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.1.3.bn2.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.2.0.conv1.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.2.0.bn1.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.2.0.bn1.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.2.0.conv2.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.2.0.bn2.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.2.0.bn2.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.2.1.conv1.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.2.1.bn1.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.2.1.bn1.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.2.1.conv2.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.2.1.bn2.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.2.1.bn2.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.2.2.conv1.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.2.2.bn1.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.2.2.bn1.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.2.2.conv2.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.2.2.bn2.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.2.2.bn2.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.2.3.conv1.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.2.3.bn1.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.2.3.bn1.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.2.3.conv2.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.2.3.bn2.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.2.3.bn2.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.3.0.conv1.weight - torch.Size([256, 256, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.3.0.bn1.weight - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.3.0.bn1.bias - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.3.0.conv2.weight - torch.Size([256, 256, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.3.0.bn2.weight - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.3.0.bn2.bias - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.3.1.conv1.weight - torch.Size([256, 256, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.3.1.bn1.weight - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.3.1.bn1.bias - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.3.1.conv2.weight - torch.Size([256, 256, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.3.1.bn2.weight - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.3.1.bn2.bias - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.3.2.conv1.weight - torch.Size([256, 256, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.3.2.bn1.weight - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.3.2.bn1.bias - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.3.2.conv2.weight - torch.Size([256, 256, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.3.2.bn2.weight - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.3.2.bn2.bias - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.3.3.conv1.weight - torch.Size([256, 256, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.3.3.bn1.weight - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.3.3.bn1.bias - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.3.3.conv2.weight - torch.Size([256, 256, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.3.3.bn2.weight - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.branches.3.3.bn2.bias - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.fuse_layers.0.1.0.weight - torch.Size([32, 64, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.fuse_layers.0.1.1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.fuse_layers.0.1.1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.fuse_layers.0.2.0.weight - torch.Size([32, 128, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.fuse_layers.0.2.1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.fuse_layers.0.2.1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.fuse_layers.0.3.0.weight - torch.Size([32, 256, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.fuse_layers.0.3.1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.fuse_layers.0.3.1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.fuse_layers.1.0.0.0.weight - torch.Size([64, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.fuse_layers.1.0.0.1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.fuse_layers.1.0.0.1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.fuse_layers.1.2.0.weight - torch.Size([64, 128, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.fuse_layers.1.2.1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.fuse_layers.1.2.1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.fuse_layers.1.3.0.weight - torch.Size([64, 256, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.fuse_layers.1.3.1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.fuse_layers.1.3.1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.fuse_layers.2.0.0.0.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.fuse_layers.2.0.0.1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.fuse_layers.2.0.0.1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.fuse_layers.2.0.1.0.weight - torch.Size([128, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.fuse_layers.2.0.1.1.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.fuse_layers.2.0.1.1.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.fuse_layers.2.1.0.0.weight - torch.Size([128, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.fuse_layers.2.1.0.1.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.fuse_layers.2.1.0.1.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.fuse_layers.2.3.0.weight - torch.Size([128, 256, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.fuse_layers.2.3.1.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.fuse_layers.2.3.1.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.fuse_layers.3.0.0.0.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.fuse_layers.3.0.0.1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.fuse_layers.3.0.0.1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.fuse_layers.3.0.1.0.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.fuse_layers.3.0.1.1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.fuse_layers.3.0.1.1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.fuse_layers.3.0.2.0.weight - torch.Size([256, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.fuse_layers.3.0.2.1.weight - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.fuse_layers.3.0.2.1.bias - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.fuse_layers.3.1.0.0.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.fuse_layers.3.1.0.1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.fuse_layers.3.1.0.1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.fuse_layers.3.1.1.0.weight - torch.Size([256, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.fuse_layers.3.1.1.1.weight - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.fuse_layers.3.1.1.1.bias - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.fuse_layers.3.2.0.0.weight - torch.Size([256, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.fuse_layers.3.2.0.1.weight - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.1.fuse_layers.3.2.0.1.bias - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.0.0.conv1.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.0.0.bn1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.0.0.bn1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.0.0.conv2.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.0.0.bn2.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.0.0.bn2.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.0.1.conv1.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.0.1.bn1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.0.1.bn1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.0.1.conv2.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.0.1.bn2.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.0.1.bn2.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.0.2.conv1.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.0.2.bn1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.0.2.bn1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.0.2.conv2.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.0.2.bn2.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.0.2.bn2.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.0.3.conv1.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.0.3.bn1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.0.3.bn1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.0.3.conv2.weight - torch.Size([32, 32, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.0.3.bn2.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.0.3.bn2.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.1.0.conv1.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.1.0.bn1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.1.0.bn1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.1.0.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.1.0.bn2.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.1.0.bn2.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.1.1.conv1.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.1.1.bn1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.1.1.bn1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.1.1.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.1.1.bn2.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.1.1.bn2.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.1.2.conv1.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.1.2.bn1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.1.2.bn1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.1.2.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.1.2.bn2.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.1.2.bn2.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.1.3.conv1.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.1.3.bn1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.1.3.bn1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.1.3.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.1.3.bn2.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.1.3.bn2.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.2.0.conv1.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.2.0.bn1.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.2.0.bn1.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.2.0.conv2.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.2.0.bn2.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.2.0.bn2.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.2.1.conv1.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.2.1.bn1.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.2.1.bn1.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.2.1.conv2.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.2.1.bn2.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.2.1.bn2.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.2.2.conv1.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.2.2.bn1.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.2.2.bn1.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.2.2.conv2.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.2.2.bn2.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.2.2.bn2.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.2.3.conv1.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.2.3.bn1.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.2.3.bn1.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.2.3.conv2.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.2.3.bn2.weight - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.2.3.bn2.bias - torch.Size([128]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.3.0.conv1.weight - torch.Size([256, 256, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.3.0.bn1.weight - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.3.0.bn1.bias - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.3.0.conv2.weight - torch.Size([256, 256, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.3.0.bn2.weight - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.3.0.bn2.bias - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.3.1.conv1.weight - torch.Size([256, 256, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.3.1.bn1.weight - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.3.1.bn1.bias - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.3.1.conv2.weight - torch.Size([256, 256, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.3.1.bn2.weight - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.3.1.bn2.bias - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.3.2.conv1.weight - torch.Size([256, 256, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.3.2.bn1.weight - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.3.2.bn1.bias - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.3.2.conv2.weight - torch.Size([256, 256, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.3.2.bn2.weight - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.3.2.bn2.bias - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.3.3.conv1.weight - torch.Size([256, 256, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.3.3.bn1.weight - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.3.3.bn1.bias - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.3.3.conv2.weight - torch.Size([256, 256, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.3.3.bn2.weight - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.branches.3.3.bn2.bias - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.fuse_layers.0.1.0.weight - torch.Size([32, 64, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.fuse_layers.0.1.1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.fuse_layers.0.1.1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.fuse_layers.0.2.0.weight - torch.Size([32, 128, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.fuse_layers.0.2.1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.fuse_layers.0.2.1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.fuse_layers.0.3.0.weight - torch.Size([32, 256, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.fuse_layers.0.3.1.weight - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth backbone.stage4.2.fuse_layers.0.3.1.bias - torch.Size([32]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth head.final_layer.weight - torch.Size([17, 32, 1, 1]): NormalInit: mean=0, std=0.001, bias=0 head.final_layer.bias - torch.Size([17]): NormalInit: mean=0, std=0.001, bias=0 2022/09/13 12:05:24 - mmengine - INFO - Checkpoints will be saved to /mnt/lustre/liqikai/work_dirs/20220913/dark_w32_256_v1 by HardDiskBackend. 2022/09/13 12:06:22 - mmengine - INFO - Epoch(train) [1][50/293] lr: 4.954910e-05 eta: 19:48:41 time: 1.160075 data_time: 0.275636 memory: 9871 loss_kpt: 0.002193 acc_pose: 0.114498 loss: 0.002193 2022/09/13 12:07:00 - mmengine - INFO - Epoch(train) [1][100/293] lr: 9.959920e-05 eta: 16:14:48 time: 0.744151 data_time: 0.125580 memory: 9871 loss_kpt: 0.001900 acc_pose: 0.404942 loss: 0.001900 2022/09/13 12:07:31 - mmengine - INFO - Epoch(train) [1][150/293] lr: 1.496493e-04 eta: 14:24:41 time: 0.631524 data_time: 0.102240 memory: 9871 loss_kpt: 0.001612 acc_pose: 0.442139 loss: 0.001612 2022/09/13 12:08:05 - mmengine - INFO - Epoch(train) [1][200/293] lr: 1.996994e-04 eta: 13:38:49 time: 0.668553 data_time: 0.083253 memory: 9871 loss_kpt: 0.001436 acc_pose: 0.530283 loss: 0.001436 2022/09/13 12:08:37 - mmengine - INFO - Epoch(train) [1][250/293] lr: 2.497495e-04 eta: 13:07:41 time: 0.651896 data_time: 0.122110 memory: 9871 loss_kpt: 0.001302 acc_pose: 0.519524 loss: 0.001302 2022/09/13 12:09:02 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 12:09:02 - mmengine - INFO - Saving checkpoint at 1 epochs 2022/09/13 12:09:33 - mmengine - INFO - Epoch(train) [2][50/293] lr: 3.428427e-04 eta: 10:51:32 time: 0.526647 data_time: 0.088490 memory: 9871 loss_kpt: 0.001188 acc_pose: 0.620478 loss: 0.001188 2022/09/13 12:09:57 - mmengine - INFO - Epoch(train) [2][100/293] lr: 3.928928e-04 eta: 10:32:19 time: 0.494810 data_time: 0.074721 memory: 9871 loss_kpt: 0.001146 acc_pose: 0.588084 loss: 0.001146 2022/09/13 12:10:23 - mmengine - INFO - Epoch(train) [2][150/293] lr: 4.429429e-04 eta: 10:19:07 time: 0.510198 data_time: 0.070358 memory: 9871 loss_kpt: 0.001099 acc_pose: 0.599006 loss: 0.001099 2022/09/13 12:10:48 - mmengine - INFO - Epoch(train) [2][200/293] lr: 4.929930e-04 eta: 10:07:08 time: 0.496788 data_time: 0.076836 memory: 9871 loss_kpt: 0.001075 acc_pose: 0.602138 loss: 0.001075 2022/09/13 12:11:13 - mmengine - INFO - Epoch(train) [2][250/293] lr: 5.000000e-04 eta: 9:57:43 time: 0.501616 data_time: 0.069860 memory: 9871 loss_kpt: 0.001075 acc_pose: 0.641862 loss: 0.001075 2022/09/13 12:11:35 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 12:11:35 - mmengine - INFO - Saving checkpoint at 2 epochs 2022/09/13 12:12:05 - mmengine - INFO - Epoch(train) [3][50/293] lr: 5.000000e-04 eta: 9:09:46 time: 0.504277 data_time: 0.080483 memory: 9871 loss_kpt: 0.001009 acc_pose: 0.668976 loss: 0.001009 2022/09/13 12:12:29 - mmengine - INFO - Epoch(train) [3][100/293] lr: 5.000000e-04 eta: 9:04:59 time: 0.482999 data_time: 0.071153 memory: 9871 loss_kpt: 0.001021 acc_pose: 0.626402 loss: 0.001021 2022/09/13 12:12:54 - mmengine - INFO - Epoch(train) [3][150/293] lr: 5.000000e-04 eta: 9:02:35 time: 0.509149 data_time: 0.074377 memory: 9871 loss_kpt: 0.001018 acc_pose: 0.623138 loss: 0.001018 2022/09/13 12:13:20 - mmengine - INFO - Epoch(train) [3][200/293] lr: 5.000000e-04 eta: 9:00:08 time: 0.504306 data_time: 0.072364 memory: 9871 loss_kpt: 0.000980 acc_pose: 0.597643 loss: 0.000980 2022/09/13 12:13:44 - mmengine - INFO - Epoch(train) [3][250/293] lr: 5.000000e-04 eta: 8:57:34 time: 0.498357 data_time: 0.073743 memory: 9871 loss_kpt: 0.000967 acc_pose: 0.704507 loss: 0.000967 2022/09/13 12:14:06 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 12:14:06 - mmengine - INFO - Saving checkpoint at 3 epochs 2022/09/13 12:14:36 - mmengine - INFO - Epoch(train) [4][50/293] lr: 5.000000e-04 eta: 8:30:42 time: 0.509634 data_time: 0.082757 memory: 9871 loss_kpt: 0.000965 acc_pose: 0.677894 loss: 0.000965 2022/09/13 12:15:01 - mmengine - INFO - Epoch(train) [4][100/293] lr: 5.000000e-04 eta: 8:29:50 time: 0.496734 data_time: 0.073025 memory: 9871 loss_kpt: 0.000958 acc_pose: 0.629605 loss: 0.000958 2022/09/13 12:15:11 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 12:15:26 - mmengine - INFO - Epoch(train) [4][150/293] lr: 5.000000e-04 eta: 8:29:22 time: 0.504401 data_time: 0.069768 memory: 9871 loss_kpt: 0.000929 acc_pose: 0.626394 loss: 0.000929 2022/09/13 12:15:50 - mmengine - INFO - Epoch(train) [4][200/293] lr: 5.000000e-04 eta: 8:28:13 time: 0.489699 data_time: 0.069205 memory: 9871 loss_kpt: 0.000929 acc_pose: 0.740006 loss: 0.000929 2022/09/13 12:16:16 - mmengine - INFO - Epoch(train) [4][250/293] lr: 5.000000e-04 eta: 8:27:58 time: 0.508191 data_time: 0.071303 memory: 9871 loss_kpt: 0.000917 acc_pose: 0.724453 loss: 0.000917 2022/09/13 12:16:38 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 12:16:38 - mmengine - INFO - Saving checkpoint at 4 epochs 2022/09/13 12:17:08 - mmengine - INFO - Epoch(train) [5][50/293] lr: 5.000000e-04 eta: 8:09:45 time: 0.514562 data_time: 0.085123 memory: 9871 loss_kpt: 0.000911 acc_pose: 0.705635 loss: 0.000911 2022/09/13 12:17:34 - mmengine - INFO - Epoch(train) [5][100/293] lr: 5.000000e-04 eta: 8:10:28 time: 0.515498 data_time: 0.073746 memory: 9871 loss_kpt: 0.000910 acc_pose: 0.662928 loss: 0.000910 2022/09/13 12:17:58 - mmengine - INFO - Epoch(train) [5][150/293] lr: 5.000000e-04 eta: 8:10:11 time: 0.491615 data_time: 0.072842 memory: 9871 loss_kpt: 0.000901 acc_pose: 0.719508 loss: 0.000901 2022/09/13 12:18:23 - mmengine - INFO - Epoch(train) [5][200/293] lr: 5.000000e-04 eta: 8:10:08 time: 0.498472 data_time: 0.074366 memory: 9871 loss_kpt: 0.000883 acc_pose: 0.700821 loss: 0.000883 2022/09/13 12:18:48 - mmengine - INFO - Epoch(train) [5][250/293] lr: 5.000000e-04 eta: 8:10:10 time: 0.501145 data_time: 0.077817 memory: 9871 loss_kpt: 0.000891 acc_pose: 0.695600 loss: 0.000891 2022/09/13 12:19:10 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 12:19:10 - mmengine - INFO - Saving checkpoint at 5 epochs 2022/09/13 12:19:40 - mmengine - INFO - Epoch(train) [6][50/293] lr: 5.000000e-04 eta: 7:56:15 time: 0.511557 data_time: 0.087068 memory: 9871 loss_kpt: 0.000883 acc_pose: 0.717377 loss: 0.000883 2022/09/13 12:20:06 - mmengine - INFO - Epoch(train) [6][100/293] lr: 5.000000e-04 eta: 7:57:16 time: 0.520796 data_time: 0.081790 memory: 9871 loss_kpt: 0.000898 acc_pose: 0.686032 loss: 0.000898 2022/09/13 12:20:30 - mmengine - INFO - Epoch(train) [6][150/293] lr: 5.000000e-04 eta: 7:57:22 time: 0.493536 data_time: 0.069305 memory: 9871 loss_kpt: 0.000881 acc_pose: 0.759391 loss: 0.000881 2022/09/13 12:20:55 - mmengine - INFO - Epoch(train) [6][200/293] lr: 5.000000e-04 eta: 7:57:43 time: 0.502730 data_time: 0.074243 memory: 9871 loss_kpt: 0.000873 acc_pose: 0.740493 loss: 0.000873 2022/09/13 12:21:21 - mmengine - INFO - Epoch(train) [6][250/293] lr: 5.000000e-04 eta: 7:58:12 time: 0.509085 data_time: 0.077517 memory: 9871 loss_kpt: 0.000873 acc_pose: 0.723817 loss: 0.000873 2022/09/13 12:21:42 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 12:21:42 - mmengine - INFO - Saving checkpoint at 6 epochs 2022/09/13 12:22:12 - mmengine - INFO - Epoch(train) [7][50/293] lr: 5.000000e-04 eta: 7:47:00 time: 0.512919 data_time: 0.081177 memory: 9871 loss_kpt: 0.000842 acc_pose: 0.724526 loss: 0.000842 2022/09/13 12:22:37 - mmengine - INFO - Epoch(train) [7][100/293] lr: 5.000000e-04 eta: 7:47:23 time: 0.497801 data_time: 0.074204 memory: 9871 loss_kpt: 0.000845 acc_pose: 0.721313 loss: 0.000845 2022/09/13 12:23:03 - mmengine - INFO - Epoch(train) [7][150/293] lr: 5.000000e-04 eta: 7:47:57 time: 0.506948 data_time: 0.077735 memory: 9871 loss_kpt: 0.000855 acc_pose: 0.708199 loss: 0.000855 2022/09/13 12:23:29 - mmengine - INFO - Epoch(train) [7][200/293] lr: 5.000000e-04 eta: 7:48:46 time: 0.518753 data_time: 0.074485 memory: 9871 loss_kpt: 0.000853 acc_pose: 0.764481 loss: 0.000853 2022/09/13 12:23:49 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 12:23:53 - mmengine - INFO - Epoch(train) [7][250/293] lr: 5.000000e-04 eta: 7:48:51 time: 0.491264 data_time: 0.070046 memory: 9871 loss_kpt: 0.000847 acc_pose: 0.739633 loss: 0.000847 2022/09/13 12:24:15 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 12:24:15 - mmengine - INFO - Saving checkpoint at 7 epochs 2022/09/13 12:24:44 - mmengine - INFO - Epoch(train) [8][50/293] lr: 5.000000e-04 eta: 7:39:24 time: 0.508917 data_time: 0.082405 memory: 9871 loss_kpt: 0.000842 acc_pose: 0.724405 loss: 0.000842 2022/09/13 12:25:09 - mmengine - INFO - Epoch(train) [8][100/293] lr: 5.000000e-04 eta: 7:39:46 time: 0.496426 data_time: 0.077063 memory: 9871 loss_kpt: 0.000828 acc_pose: 0.722816 loss: 0.000828 2022/09/13 12:25:35 - mmengine - INFO - Epoch(train) [8][150/293] lr: 5.000000e-04 eta: 7:40:35 time: 0.518516 data_time: 0.075199 memory: 9871 loss_kpt: 0.000841 acc_pose: 0.722129 loss: 0.000841 2022/09/13 12:26:00 - mmengine - INFO - Epoch(train) [8][200/293] lr: 5.000000e-04 eta: 7:40:40 time: 0.487255 data_time: 0.073452 memory: 9871 loss_kpt: 0.000841 acc_pose: 0.673349 loss: 0.000841 2022/09/13 12:26:24 - mmengine - INFO - Epoch(train) [8][250/293] lr: 5.000000e-04 eta: 7:40:51 time: 0.493127 data_time: 0.074657 memory: 9871 loss_kpt: 0.000821 acc_pose: 0.770891 loss: 0.000821 2022/09/13 12:26:45 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 12:26:45 - mmengine - INFO - Saving checkpoint at 8 epochs 2022/09/13 12:27:15 - mmengine - INFO - Epoch(train) [9][50/293] lr: 5.000000e-04 eta: 7:32:50 time: 0.513512 data_time: 0.084232 memory: 9871 loss_kpt: 0.000807 acc_pose: 0.708209 loss: 0.000807 2022/09/13 12:27:40 - mmengine - INFO - Epoch(train) [9][100/293] lr: 5.000000e-04 eta: 7:33:06 time: 0.492102 data_time: 0.079031 memory: 9871 loss_kpt: 0.000824 acc_pose: 0.703728 loss: 0.000824 2022/09/13 12:28:05 - mmengine - INFO - Epoch(train) [9][150/293] lr: 5.000000e-04 eta: 7:33:29 time: 0.499405 data_time: 0.074230 memory: 9871 loss_kpt: 0.000826 acc_pose: 0.750778 loss: 0.000826 2022/09/13 12:28:30 - mmengine - INFO - Epoch(train) [9][200/293] lr: 5.000000e-04 eta: 7:33:55 time: 0.502948 data_time: 0.079694 memory: 9871 loss_kpt: 0.000801 acc_pose: 0.739777 loss: 0.000801 2022/09/13 12:28:55 - mmengine - INFO - Epoch(train) [9][250/293] lr: 5.000000e-04 eta: 7:34:13 time: 0.497369 data_time: 0.069988 memory: 9871 loss_kpt: 0.000810 acc_pose: 0.767537 loss: 0.000810 2022/09/13 12:29:15 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 12:29:15 - mmengine - INFO - Saving checkpoint at 9 epochs 2022/09/13 12:29:45 - mmengine - INFO - Epoch(train) [10][50/293] lr: 5.000000e-04 eta: 7:27:07 time: 0.511112 data_time: 0.086689 memory: 9871 loss_kpt: 0.000828 acc_pose: 0.744730 loss: 0.000828 2022/09/13 12:30:11 - mmengine - INFO - Epoch(train) [10][100/293] lr: 5.000000e-04 eta: 7:27:43 time: 0.510257 data_time: 0.069890 memory: 9871 loss_kpt: 0.000812 acc_pose: 0.761475 loss: 0.000812 2022/09/13 12:30:36 - mmengine - INFO - Epoch(train) [10][150/293] lr: 5.000000e-04 eta: 7:28:10 time: 0.504560 data_time: 0.082574 memory: 9871 loss_kpt: 0.000794 acc_pose: 0.733268 loss: 0.000794 2022/09/13 12:31:00 - mmengine - INFO - Epoch(train) [10][200/293] lr: 5.000000e-04 eta: 7:28:22 time: 0.490660 data_time: 0.070519 memory: 9871 loss_kpt: 0.000807 acc_pose: 0.807836 loss: 0.000807 2022/09/13 12:31:25 - mmengine - INFO - Epoch(train) [10][250/293] lr: 5.000000e-04 eta: 7:28:27 time: 0.486402 data_time: 0.074837 memory: 9871 loss_kpt: 0.000826 acc_pose: 0.711238 loss: 0.000826 2022/09/13 12:31:46 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 12:31:46 - mmengine - INFO - Saving checkpoint at 10 epochs 2022/09/13 12:32:03 - mmengine - INFO - Epoch(val) [10][50/407] eta: 0:01:15 time: 0.211096 data_time: 0.056038 memory: 9871 2022/09/13 12:32:12 - mmengine - INFO - Epoch(val) [10][100/407] eta: 0:00:55 time: 0.181538 data_time: 0.027330 memory: 920 2022/09/13 12:32:21 - mmengine - INFO - Epoch(val) [10][150/407] eta: 0:00:48 time: 0.187706 data_time: 0.032298 memory: 920 2022/09/13 12:32:30 - mmengine - INFO - Epoch(val) [10][200/407] eta: 0:00:35 time: 0.172837 data_time: 0.015747 memory: 920 2022/09/13 12:32:38 - mmengine - INFO - Epoch(val) [10][250/407] eta: 0:00:25 time: 0.165151 data_time: 0.008354 memory: 920 2022/09/13 12:32:47 - mmengine - INFO - Epoch(val) [10][300/407] eta: 0:00:18 time: 0.169206 data_time: 0.013965 memory: 920 2022/09/13 12:32:56 - mmengine - INFO - Epoch(val) [10][350/407] eta: 0:00:10 time: 0.180088 data_time: 0.026058 memory: 920 2022/09/13 12:33:05 - mmengine - INFO - Epoch(val) [10][400/407] eta: 0:00:01 time: 0.177564 data_time: 0.024968 memory: 920 2022/09/13 12:33:42 - mmengine - INFO - Evaluating CocoMetric... 2022/09/13 12:33:57 - mmengine - INFO - Epoch(val) [10][407/407] coco/AP: 0.662713 coco/AP .5: 0.870693 coco/AP .75: 0.734877 coco/AP (M): 0.627331 coco/AP (L): 0.724755 coco/AR: 0.721568 coco/AR .5: 0.911209 coco/AR .75: 0.789830 coco/AR (M): 0.679213 coco/AR (L): 0.782051 2022/09/13 12:34:00 - mmengine - INFO - The best checkpoint with 0.6627 coco/AP at 10 epoch is saved to best_coco/AP_epoch_10.pth. 2022/09/13 12:34:26 - mmengine - INFO - Epoch(train) [11][50/293] lr: 5.000000e-04 eta: 7:22:13 time: 0.516509 data_time: 0.079240 memory: 9871 loss_kpt: 0.000810 acc_pose: 0.746294 loss: 0.000810 2022/09/13 12:34:35 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 12:34:50 - mmengine - INFO - Epoch(train) [11][100/293] lr: 5.000000e-04 eta: 7:22:30 time: 0.494063 data_time: 0.080987 memory: 9871 loss_kpt: 0.000800 acc_pose: 0.719203 loss: 0.000800 2022/09/13 12:35:15 - mmengine - INFO - Epoch(train) [11][150/293] lr: 5.000000e-04 eta: 7:22:52 time: 0.500854 data_time: 0.076307 memory: 9871 loss_kpt: 0.000801 acc_pose: 0.771857 loss: 0.000801 2022/09/13 12:35:40 - mmengine - INFO - Epoch(train) [11][200/293] lr: 5.000000e-04 eta: 7:23:07 time: 0.495299 data_time: 0.076102 memory: 9871 loss_kpt: 0.000797 acc_pose: 0.732351 loss: 0.000797 2022/09/13 12:36:05 - mmengine - INFO - Epoch(train) [11][250/293] lr: 5.000000e-04 eta: 7:23:21 time: 0.495209 data_time: 0.079350 memory: 9871 loss_kpt: 0.000780 acc_pose: 0.751530 loss: 0.000780 2022/09/13 12:36:26 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 12:36:26 - mmengine - INFO - Saving checkpoint at 11 epochs 2022/09/13 12:36:56 - mmengine - INFO - Epoch(train) [12][50/293] lr: 5.000000e-04 eta: 7:17:31 time: 0.502587 data_time: 0.085115 memory: 9871 loss_kpt: 0.000779 acc_pose: 0.748097 loss: 0.000779 2022/09/13 12:37:20 - mmengine - INFO - Epoch(train) [12][100/293] lr: 5.000000e-04 eta: 7:17:45 time: 0.491537 data_time: 0.071982 memory: 9871 loss_kpt: 0.000791 acc_pose: 0.745973 loss: 0.000791 2022/09/13 12:37:46 - mmengine - INFO - Epoch(train) [12][150/293] lr: 5.000000e-04 eta: 7:18:10 time: 0.506475 data_time: 0.080800 memory: 9871 loss_kpt: 0.000795 acc_pose: 0.810618 loss: 0.000795 2022/09/13 12:38:11 - mmengine - INFO - Epoch(train) [12][200/293] lr: 5.000000e-04 eta: 7:18:30 time: 0.501922 data_time: 0.077093 memory: 9871 loss_kpt: 0.000770 acc_pose: 0.723638 loss: 0.000770 2022/09/13 12:38:36 - mmengine - INFO - Epoch(train) [12][250/293] lr: 5.000000e-04 eta: 7:18:52 time: 0.506985 data_time: 0.082571 memory: 9871 loss_kpt: 0.000780 acc_pose: 0.743206 loss: 0.000780 2022/09/13 12:38:57 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 12:38:57 - mmengine - INFO - Saving checkpoint at 12 epochs 2022/09/13 12:39:28 - mmengine - INFO - Epoch(train) [13][50/293] lr: 5.000000e-04 eta: 7:13:43 time: 0.514596 data_time: 0.080470 memory: 9871 loss_kpt: 0.000785 acc_pose: 0.744982 loss: 0.000785 2022/09/13 12:39:52 - mmengine - INFO - Epoch(train) [13][100/293] lr: 5.000000e-04 eta: 7:13:54 time: 0.491713 data_time: 0.071863 memory: 9871 loss_kpt: 0.000777 acc_pose: 0.803671 loss: 0.000777 2022/09/13 12:40:17 - mmengine - INFO - Epoch(train) [13][150/293] lr: 5.000000e-04 eta: 7:14:12 time: 0.500376 data_time: 0.071701 memory: 9871 loss_kpt: 0.000750 acc_pose: 0.698781 loss: 0.000750 2022/09/13 12:40:42 - mmengine - INFO - Epoch(train) [13][200/293] lr: 5.000000e-04 eta: 7:14:27 time: 0.498020 data_time: 0.076999 memory: 9871 loss_kpt: 0.000772 acc_pose: 0.784424 loss: 0.000772 2022/09/13 12:41:07 - mmengine - INFO - Epoch(train) [13][250/293] lr: 5.000000e-04 eta: 7:14:39 time: 0.496351 data_time: 0.072212 memory: 9871 loss_kpt: 0.000767 acc_pose: 0.771374 loss: 0.000767 2022/09/13 12:41:28 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 12:41:28 - mmengine - INFO - Saving checkpoint at 13 epochs 2022/09/13 12:41:59 - mmengine - INFO - Epoch(train) [14][50/293] lr: 5.000000e-04 eta: 7:09:49 time: 0.507617 data_time: 0.082325 memory: 9871 loss_kpt: 0.000774 acc_pose: 0.745440 loss: 0.000774 2022/09/13 12:42:24 - mmengine - INFO - Epoch(train) [14][100/293] lr: 5.000000e-04 eta: 7:10:04 time: 0.498454 data_time: 0.074832 memory: 9871 loss_kpt: 0.000765 acc_pose: 0.753167 loss: 0.000765 2022/09/13 12:42:48 - mmengine - INFO - Epoch(train) [14][150/293] lr: 5.000000e-04 eta: 7:10:11 time: 0.488280 data_time: 0.075765 memory: 9871 loss_kpt: 0.000768 acc_pose: 0.763339 loss: 0.000768 2022/09/13 12:43:08 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 12:43:13 - mmengine - INFO - Epoch(train) [14][200/293] lr: 5.000000e-04 eta: 7:10:21 time: 0.492955 data_time: 0.077063 memory: 9871 loss_kpt: 0.000759 acc_pose: 0.754722 loss: 0.000759 2022/09/13 12:43:38 - mmengine - INFO - Epoch(train) [14][250/293] lr: 5.000000e-04 eta: 7:10:44 time: 0.513069 data_time: 0.085431 memory: 9871 loss_kpt: 0.000762 acc_pose: 0.796783 loss: 0.000762 2022/09/13 12:43:59 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 12:43:59 - mmengine - INFO - Saving checkpoint at 14 epochs 2022/09/13 12:44:29 - mmengine - INFO - Epoch(train) [15][50/293] lr: 5.000000e-04 eta: 7:06:14 time: 0.506496 data_time: 0.083511 memory: 9871 loss_kpt: 0.000765 acc_pose: 0.778834 loss: 0.000765 2022/09/13 12:44:54 - mmengine - INFO - Epoch(train) [15][100/293] lr: 5.000000e-04 eta: 7:06:33 time: 0.505565 data_time: 0.076823 memory: 9871 loss_kpt: 0.000753 acc_pose: 0.782763 loss: 0.000753 2022/09/13 12:45:19 - mmengine - INFO - Epoch(train) [15][150/293] lr: 5.000000e-04 eta: 7:06:41 time: 0.491827 data_time: 0.072883 memory: 9871 loss_kpt: 0.000761 acc_pose: 0.785421 loss: 0.000761 2022/09/13 12:45:43 - mmengine - INFO - Epoch(train) [15][200/293] lr: 5.000000e-04 eta: 7:06:50 time: 0.494334 data_time: 0.079131 memory: 9871 loss_kpt: 0.000759 acc_pose: 0.772144 loss: 0.000759 2022/09/13 12:46:08 - mmengine - INFO - Epoch(train) [15][250/293] lr: 5.000000e-04 eta: 7:06:59 time: 0.495073 data_time: 0.071927 memory: 9871 loss_kpt: 0.000751 acc_pose: 0.812624 loss: 0.000751 2022/09/13 12:46:30 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 12:46:30 - mmengine - INFO - Saving checkpoint at 15 epochs 2022/09/13 12:47:02 - mmengine - INFO - Epoch(train) [16][50/293] lr: 5.000000e-04 eta: 7:02:51 time: 0.512249 data_time: 0.084549 memory: 9871 loss_kpt: 0.000756 acc_pose: 0.788989 loss: 0.000756 2022/09/13 12:47:27 - mmengine - INFO - Epoch(train) [16][100/293] lr: 5.000000e-04 eta: 7:03:05 time: 0.501545 data_time: 0.074199 memory: 9871 loss_kpt: 0.000766 acc_pose: 0.778089 loss: 0.000766 2022/09/13 12:47:52 - mmengine - INFO - Epoch(train) [16][150/293] lr: 5.000000e-04 eta: 7:03:17 time: 0.499219 data_time: 0.080994 memory: 9871 loss_kpt: 0.000749 acc_pose: 0.764749 loss: 0.000749 2022/09/13 12:48:17 - mmengine - INFO - Epoch(train) [16][200/293] lr: 5.000000e-04 eta: 7:03:27 time: 0.497768 data_time: 0.082689 memory: 9871 loss_kpt: 0.000763 acc_pose: 0.800629 loss: 0.000763 2022/09/13 12:48:42 - mmengine - INFO - Epoch(train) [16][250/293] lr: 5.000000e-04 eta: 7:03:41 time: 0.506269 data_time: 0.075248 memory: 9871 loss_kpt: 0.000765 acc_pose: 0.800381 loss: 0.000765 2022/09/13 12:49:03 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 12:49:03 - mmengine - INFO - Saving checkpoint at 16 epochs 2022/09/13 12:49:34 - mmengine - INFO - Epoch(train) [17][50/293] lr: 5.000000e-04 eta: 6:59:52 time: 0.519055 data_time: 0.082276 memory: 9871 loss_kpt: 0.000751 acc_pose: 0.719045 loss: 0.000751 2022/09/13 12:49:58 - mmengine - INFO - Epoch(train) [17][100/293] lr: 5.000000e-04 eta: 7:00:01 time: 0.495965 data_time: 0.074796 memory: 9871 loss_kpt: 0.000754 acc_pose: 0.795785 loss: 0.000754 2022/09/13 12:50:24 - mmengine - INFO - Epoch(train) [17][150/293] lr: 5.000000e-04 eta: 7:00:19 time: 0.511655 data_time: 0.084235 memory: 9871 loss_kpt: 0.000752 acc_pose: 0.769707 loss: 0.000752 2022/09/13 12:50:49 - mmengine - INFO - Epoch(train) [17][200/293] lr: 5.000000e-04 eta: 7:00:26 time: 0.496400 data_time: 0.074307 memory: 9871 loss_kpt: 0.000732 acc_pose: 0.797105 loss: 0.000732 2022/09/13 12:51:13 - mmengine - INFO - Epoch(train) [17][250/293] lr: 5.000000e-04 eta: 7:00:32 time: 0.494044 data_time: 0.072975 memory: 9871 loss_kpt: 0.000766 acc_pose: 0.760105 loss: 0.000766 2022/09/13 12:51:35 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 12:51:35 - mmengine - INFO - Saving checkpoint at 17 epochs 2022/09/13 12:51:49 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 12:52:05 - mmengine - INFO - Epoch(train) [18][50/293] lr: 5.000000e-04 eta: 6:56:56 time: 0.518186 data_time: 0.082592 memory: 9871 loss_kpt: 0.000744 acc_pose: 0.811565 loss: 0.000744 2022/09/13 12:52:30 - mmengine - INFO - Epoch(train) [18][100/293] lr: 5.000000e-04 eta: 6:57:03 time: 0.495021 data_time: 0.080835 memory: 9871 loss_kpt: 0.000748 acc_pose: 0.725290 loss: 0.000748 2022/09/13 12:52:55 - mmengine - INFO - Epoch(train) [18][150/293] lr: 5.000000e-04 eta: 6:57:14 time: 0.505075 data_time: 0.076832 memory: 9871 loss_kpt: 0.000739 acc_pose: 0.786378 loss: 0.000739 2022/09/13 12:53:20 - mmengine - INFO - Epoch(train) [18][200/293] lr: 5.000000e-04 eta: 6:57:19 time: 0.492359 data_time: 0.076176 memory: 9871 loss_kpt: 0.000742 acc_pose: 0.773993 loss: 0.000742 2022/09/13 12:53:45 - mmengine - INFO - Epoch(train) [18][250/293] lr: 5.000000e-04 eta: 6:57:26 time: 0.498824 data_time: 0.076424 memory: 9871 loss_kpt: 0.000753 acc_pose: 0.811065 loss: 0.000753 2022/09/13 12:54:05 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 12:54:05 - mmengine - INFO - Saving checkpoint at 18 epochs 2022/09/13 12:54:36 - mmengine - INFO - Epoch(train) [19][50/293] lr: 5.000000e-04 eta: 6:53:59 time: 0.515305 data_time: 0.086845 memory: 9871 loss_kpt: 0.000741 acc_pose: 0.778874 loss: 0.000741 2022/09/13 12:55:02 - mmengine - INFO - Epoch(train) [19][100/293] lr: 5.000000e-04 eta: 6:54:14 time: 0.511118 data_time: 0.076452 memory: 9871 loss_kpt: 0.000725 acc_pose: 0.784678 loss: 0.000725 2022/09/13 12:55:27 - mmengine - INFO - Epoch(train) [19][150/293] lr: 5.000000e-04 eta: 6:54:18 time: 0.494188 data_time: 0.082521 memory: 9871 loss_kpt: 0.000745 acc_pose: 0.765558 loss: 0.000745 2022/09/13 12:55:51 - mmengine - INFO - Epoch(train) [19][200/293] lr: 5.000000e-04 eta: 6:54:22 time: 0.493999 data_time: 0.077310 memory: 9871 loss_kpt: 0.000739 acc_pose: 0.718199 loss: 0.000739 2022/09/13 12:56:16 - mmengine - INFO - Epoch(train) [19][250/293] lr: 5.000000e-04 eta: 6:54:26 time: 0.495152 data_time: 0.084184 memory: 9871 loss_kpt: 0.000746 acc_pose: 0.788122 loss: 0.000746 2022/09/13 12:56:38 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 12:56:38 - mmengine - INFO - Saving checkpoint at 19 epochs 2022/09/13 12:57:08 - mmengine - INFO - Epoch(train) [20][50/293] lr: 5.000000e-04 eta: 6:51:09 time: 0.513736 data_time: 0.089342 memory: 9871 loss_kpt: 0.000718 acc_pose: 0.742495 loss: 0.000718 2022/09/13 12:57:34 - mmengine - INFO - Epoch(train) [20][100/293] lr: 5.000000e-04 eta: 6:51:25 time: 0.516940 data_time: 0.092823 memory: 9871 loss_kpt: 0.000738 acc_pose: 0.795704 loss: 0.000738 2022/09/13 12:57:58 - mmengine - INFO - Epoch(train) [20][150/293] lr: 5.000000e-04 eta: 6:51:30 time: 0.497242 data_time: 0.076164 memory: 9871 loss_kpt: 0.000713 acc_pose: 0.777307 loss: 0.000713 2022/09/13 12:58:24 - mmengine - INFO - Epoch(train) [20][200/293] lr: 5.000000e-04 eta: 6:51:36 time: 0.502350 data_time: 0.078627 memory: 9871 loss_kpt: 0.000730 acc_pose: 0.765815 loss: 0.000730 2022/09/13 12:58:48 - mmengine - INFO - Epoch(train) [20][250/293] lr: 5.000000e-04 eta: 6:51:39 time: 0.494538 data_time: 0.082458 memory: 9871 loss_kpt: 0.000710 acc_pose: 0.797569 loss: 0.000710 2022/09/13 12:59:10 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 12:59:10 - mmengine - INFO - Saving checkpoint at 20 epochs 2022/09/13 12:59:23 - mmengine - INFO - Epoch(val) [20][50/407] eta: 0:00:59 time: 0.166401 data_time: 0.012645 memory: 9871 2022/09/13 12:59:31 - mmengine - INFO - Epoch(val) [20][100/407] eta: 0:00:48 time: 0.159288 data_time: 0.007916 memory: 920 2022/09/13 12:59:39 - mmengine - INFO - Epoch(val) [20][150/407] eta: 0:00:40 time: 0.157688 data_time: 0.007676 memory: 920 2022/09/13 12:59:47 - mmengine - INFO - Epoch(val) [20][200/407] eta: 0:00:33 time: 0.163207 data_time: 0.012305 memory: 920 2022/09/13 12:59:55 - mmengine - INFO - Epoch(val) [20][250/407] eta: 0:00:24 time: 0.157901 data_time: 0.007326 memory: 920 2022/09/13 13:00:03 - mmengine - INFO - Epoch(val) [20][300/407] eta: 0:00:17 time: 0.159444 data_time: 0.007620 memory: 920 2022/09/13 13:00:11 - mmengine - INFO - Epoch(val) [20][350/407] eta: 0:00:09 time: 0.159179 data_time: 0.008230 memory: 920 2022/09/13 13:00:19 - mmengine - INFO - Epoch(val) [20][400/407] eta: 0:00:01 time: 0.157450 data_time: 0.007796 memory: 920 2022/09/13 13:00:55 - mmengine - INFO - Evaluating CocoMetric... 2022/09/13 13:01:09 - mmengine - INFO - Epoch(val) [20][407/407] coco/AP: 0.691124 coco/AP .5: 0.879417 coco/AP .75: 0.764264 coco/AP (M): 0.655518 coco/AP (L): 0.756686 coco/AR: 0.748095 coco/AR .5: 0.920183 coco/AR .75: 0.815334 coco/AR (M): 0.705518 coco/AR (L): 0.809550 2022/09/13 13:01:09 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220913/dark_w32_256_v1/best_coco/AP_epoch_10.pth is removed 2022/09/13 13:01:12 - mmengine - INFO - The best checkpoint with 0.6911 coco/AP at 20 epoch is saved to best_coco/AP_epoch_20.pth. 2022/09/13 13:01:37 - mmengine - INFO - Epoch(train) [21][50/293] lr: 5.000000e-04 eta: 6:48:26 time: 0.502552 data_time: 0.085390 memory: 9871 loss_kpt: 0.000734 acc_pose: 0.780696 loss: 0.000734 2022/09/13 13:02:02 - mmengine - INFO - Epoch(train) [21][100/293] lr: 5.000000e-04 eta: 6:48:32 time: 0.500691 data_time: 0.081890 memory: 9871 loss_kpt: 0.000726 acc_pose: 0.760655 loss: 0.000726 2022/09/13 13:02:22 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 13:02:27 - mmengine - INFO - Epoch(train) [21][150/293] lr: 5.000000e-04 eta: 6:48:35 time: 0.495165 data_time: 0.070788 memory: 9871 loss_kpt: 0.000713 acc_pose: 0.747323 loss: 0.000713 2022/09/13 13:02:52 - mmengine - INFO - Epoch(train) [21][200/293] lr: 5.000000e-04 eta: 6:48:36 time: 0.491917 data_time: 0.074433 memory: 9871 loss_kpt: 0.000732 acc_pose: 0.753620 loss: 0.000732 2022/09/13 13:03:17 - mmengine - INFO - Epoch(train) [21][250/293] lr: 5.000000e-04 eta: 6:48:41 time: 0.501768 data_time: 0.078774 memory: 9871 loss_kpt: 0.000721 acc_pose: 0.730337 loss: 0.000721 2022/09/13 13:03:38 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 13:03:38 - mmengine - INFO - Saving checkpoint at 21 epochs 2022/09/13 13:04:08 - mmengine - INFO - Epoch(train) [22][50/293] lr: 5.000000e-04 eta: 6:45:41 time: 0.511027 data_time: 0.090320 memory: 9871 loss_kpt: 0.000726 acc_pose: 0.855617 loss: 0.000726 2022/09/13 13:04:33 - mmengine - INFO - Epoch(train) [22][100/293] lr: 5.000000e-04 eta: 6:45:43 time: 0.493926 data_time: 0.073587 memory: 9871 loss_kpt: 0.000726 acc_pose: 0.723976 loss: 0.000726 2022/09/13 13:04:58 - mmengine - INFO - Epoch(train) [22][150/293] lr: 5.000000e-04 eta: 6:45:44 time: 0.494284 data_time: 0.073207 memory: 9871 loss_kpt: 0.000731 acc_pose: 0.773930 loss: 0.000731 2022/09/13 13:05:23 - mmengine - INFO - Epoch(train) [22][200/293] lr: 5.000000e-04 eta: 6:45:52 time: 0.508297 data_time: 0.074271 memory: 9871 loss_kpt: 0.000724 acc_pose: 0.793898 loss: 0.000724 2022/09/13 13:05:48 - mmengine - INFO - Epoch(train) [22][250/293] lr: 5.000000e-04 eta: 6:45:55 time: 0.501540 data_time: 0.077274 memory: 9871 loss_kpt: 0.000728 acc_pose: 0.821544 loss: 0.000728 2022/09/13 13:06:09 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 13:06:09 - mmengine - INFO - Saving checkpoint at 22 epochs 2022/09/13 13:06:40 - mmengine - INFO - Epoch(train) [23][50/293] lr: 5.000000e-04 eta: 6:43:02 time: 0.509035 data_time: 0.082760 memory: 9871 loss_kpt: 0.000720 acc_pose: 0.765110 loss: 0.000720 2022/09/13 13:07:05 - mmengine - INFO - Epoch(train) [23][100/293] lr: 5.000000e-04 eta: 6:43:06 time: 0.502531 data_time: 0.078372 memory: 9871 loss_kpt: 0.000713 acc_pose: 0.800821 loss: 0.000713 2022/09/13 13:07:30 - mmengine - INFO - Epoch(train) [23][150/293] lr: 5.000000e-04 eta: 6:43:08 time: 0.497127 data_time: 0.077879 memory: 9871 loss_kpt: 0.000722 acc_pose: 0.741587 loss: 0.000722 2022/09/13 13:07:54 - mmengine - INFO - Epoch(train) [23][200/293] lr: 5.000000e-04 eta: 6:43:09 time: 0.495205 data_time: 0.073636 memory: 9871 loss_kpt: 0.000712 acc_pose: 0.806128 loss: 0.000712 2022/09/13 13:08:19 - mmengine - INFO - Epoch(train) [23][250/293] lr: 5.000000e-04 eta: 6:43:09 time: 0.495618 data_time: 0.072305 memory: 9871 loss_kpt: 0.000728 acc_pose: 0.750935 loss: 0.000728 2022/09/13 13:08:40 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 13:08:40 - mmengine - INFO - Saving checkpoint at 23 epochs 2022/09/13 13:09:10 - mmengine - INFO - Epoch(train) [24][50/293] lr: 5.000000e-04 eta: 6:40:18 time: 0.497072 data_time: 0.085590 memory: 9871 loss_kpt: 0.000711 acc_pose: 0.782214 loss: 0.000711 2022/09/13 13:09:35 - mmengine - INFO - Epoch(train) [24][100/293] lr: 5.000000e-04 eta: 6:40:22 time: 0.503978 data_time: 0.081383 memory: 9871 loss_kpt: 0.000713 acc_pose: 0.794011 loss: 0.000713 2022/09/13 13:10:00 - mmengine - INFO - Epoch(train) [24][150/293] lr: 5.000000e-04 eta: 6:40:22 time: 0.495371 data_time: 0.075704 memory: 9871 loss_kpt: 0.000723 acc_pose: 0.733529 loss: 0.000723 2022/09/13 13:10:24 - mmengine - INFO - Epoch(train) [24][200/293] lr: 5.000000e-04 eta: 6:40:21 time: 0.492393 data_time: 0.071929 memory: 9871 loss_kpt: 0.000730 acc_pose: 0.776572 loss: 0.000730 2022/09/13 13:10:49 - mmengine - INFO - Epoch(train) [24][250/293] lr: 5.000000e-04 eta: 6:40:21 time: 0.495504 data_time: 0.076927 memory: 9871 loss_kpt: 0.000718 acc_pose: 0.784749 loss: 0.000718 2022/09/13 13:10:55 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 13:11:10 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 13:11:10 - mmengine - INFO - Saving checkpoint at 24 epochs 2022/09/13 13:11:40 - mmengine - INFO - Epoch(train) [25][50/293] lr: 5.000000e-04 eta: 6:37:42 time: 0.513359 data_time: 0.090298 memory: 9871 loss_kpt: 0.000711 acc_pose: 0.745385 loss: 0.000711 2022/09/13 13:12:05 - mmengine - INFO - Epoch(train) [25][100/293] lr: 5.000000e-04 eta: 6:37:46 time: 0.506458 data_time: 0.078450 memory: 9871 loss_kpt: 0.000697 acc_pose: 0.797092 loss: 0.000697 2022/09/13 13:12:30 - mmengine - INFO - Epoch(train) [25][150/293] lr: 5.000000e-04 eta: 6:37:44 time: 0.489798 data_time: 0.076020 memory: 9871 loss_kpt: 0.000724 acc_pose: 0.787398 loss: 0.000724 2022/09/13 13:12:55 - mmengine - INFO - Epoch(train) [25][200/293] lr: 5.000000e-04 eta: 6:37:46 time: 0.505104 data_time: 0.076138 memory: 9871 loss_kpt: 0.000719 acc_pose: 0.738869 loss: 0.000719 2022/09/13 13:13:20 - mmengine - INFO - Epoch(train) [25][250/293] lr: 5.000000e-04 eta: 6:37:46 time: 0.496066 data_time: 0.076372 memory: 9871 loss_kpt: 0.000702 acc_pose: 0.743968 loss: 0.000702 2022/09/13 13:13:41 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 13:13:41 - mmengine - INFO - Saving checkpoint at 25 epochs 2022/09/13 13:14:11 - mmengine - INFO - Epoch(train) [26][50/293] lr: 5.000000e-04 eta: 6:35:12 time: 0.512656 data_time: 0.079382 memory: 9871 loss_kpt: 0.000717 acc_pose: 0.815686 loss: 0.000717 2022/09/13 13:14:37 - mmengine - INFO - Epoch(train) [26][100/293] lr: 5.000000e-04 eta: 6:35:16 time: 0.508083 data_time: 0.076460 memory: 9871 loss_kpt: 0.000705 acc_pose: 0.728638 loss: 0.000705 2022/09/13 13:15:01 - mmengine - INFO - Epoch(train) [26][150/293] lr: 5.000000e-04 eta: 6:35:11 time: 0.485025 data_time: 0.071194 memory: 9871 loss_kpt: 0.000701 acc_pose: 0.779771 loss: 0.000701 2022/09/13 13:15:26 - mmengine - INFO - Epoch(train) [26][200/293] lr: 5.000000e-04 eta: 6:35:12 time: 0.501626 data_time: 0.074652 memory: 9871 loss_kpt: 0.000694 acc_pose: 0.764835 loss: 0.000694 2022/09/13 13:15:50 - mmengine - INFO - Epoch(train) [26][250/293] lr: 5.000000e-04 eta: 6:35:08 time: 0.491341 data_time: 0.078973 memory: 9871 loss_kpt: 0.000707 acc_pose: 0.792133 loss: 0.000707 2022/09/13 13:16:12 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 13:16:12 - mmengine - INFO - Saving checkpoint at 26 epochs 2022/09/13 13:16:42 - mmengine - INFO - Epoch(train) [27][50/293] lr: 5.000000e-04 eta: 6:32:39 time: 0.508974 data_time: 0.083120 memory: 9871 loss_kpt: 0.000691 acc_pose: 0.810840 loss: 0.000691 2022/09/13 13:17:07 - mmengine - INFO - Epoch(train) [27][100/293] lr: 5.000000e-04 eta: 6:32:42 time: 0.509287 data_time: 0.077397 memory: 9871 loss_kpt: 0.000707 acc_pose: 0.762396 loss: 0.000707 2022/09/13 13:17:32 - mmengine - INFO - Epoch(train) [27][150/293] lr: 5.000000e-04 eta: 6:32:41 time: 0.497846 data_time: 0.075574 memory: 9871 loss_kpt: 0.000708 acc_pose: 0.785105 loss: 0.000708 2022/09/13 13:17:57 - mmengine - INFO - Epoch(train) [27][200/293] lr: 5.000000e-04 eta: 6:32:41 time: 0.501064 data_time: 0.084587 memory: 9871 loss_kpt: 0.000688 acc_pose: 0.801069 loss: 0.000688 2022/09/13 13:18:22 - mmengine - INFO - Epoch(train) [27][250/293] lr: 5.000000e-04 eta: 6:32:41 time: 0.501655 data_time: 0.077362 memory: 9871 loss_kpt: 0.000706 acc_pose: 0.768938 loss: 0.000706 2022/09/13 13:18:43 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 13:18:43 - mmengine - INFO - Saving checkpoint at 27 epochs 2022/09/13 13:19:13 - mmengine - INFO - Epoch(train) [28][50/293] lr: 5.000000e-04 eta: 6:30:14 time: 0.503835 data_time: 0.085180 memory: 9871 loss_kpt: 0.000698 acc_pose: 0.728443 loss: 0.000698 2022/09/13 13:19:32 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 13:19:38 - mmengine - INFO - Epoch(train) [28][100/293] lr: 5.000000e-04 eta: 6:30:15 time: 0.503222 data_time: 0.078746 memory: 9871 loss_kpt: 0.000703 acc_pose: 0.797132 loss: 0.000703 2022/09/13 13:20:04 - mmengine - INFO - Epoch(train) [28][150/293] lr: 5.000000e-04 eta: 6:30:15 time: 0.505121 data_time: 0.075795 memory: 9871 loss_kpt: 0.000700 acc_pose: 0.785540 loss: 0.000700 2022/09/13 13:20:29 - mmengine - INFO - Epoch(train) [28][200/293] lr: 5.000000e-04 eta: 6:30:14 time: 0.500761 data_time: 0.078475 memory: 9871 loss_kpt: 0.000711 acc_pose: 0.795660 loss: 0.000711 2022/09/13 13:20:53 - mmengine - INFO - Epoch(train) [28][250/293] lr: 5.000000e-04 eta: 6:30:11 time: 0.497188 data_time: 0.077557 memory: 9871 loss_kpt: 0.000699 acc_pose: 0.839983 loss: 0.000699 2022/09/13 13:21:14 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 13:21:14 - mmengine - INFO - Saving checkpoint at 28 epochs 2022/09/13 13:21:46 - mmengine - INFO - Epoch(train) [29][50/293] lr: 5.000000e-04 eta: 6:27:54 time: 0.517686 data_time: 0.090892 memory: 9871 loss_kpt: 0.000696 acc_pose: 0.796279 loss: 0.000696 2022/09/13 13:22:11 - mmengine - INFO - Epoch(train) [29][100/293] lr: 5.000000e-04 eta: 6:27:53 time: 0.500159 data_time: 0.076454 memory: 9871 loss_kpt: 0.000703 acc_pose: 0.816012 loss: 0.000703 2022/09/13 13:22:36 - mmengine - INFO - Epoch(train) [29][150/293] lr: 5.000000e-04 eta: 6:27:53 time: 0.506556 data_time: 0.077566 memory: 9871 loss_kpt: 0.000716 acc_pose: 0.792053 loss: 0.000716 2022/09/13 13:23:01 - mmengine - INFO - Epoch(train) [29][200/293] lr: 5.000000e-04 eta: 6:27:50 time: 0.496136 data_time: 0.072610 memory: 9871 loss_kpt: 0.000705 acc_pose: 0.772065 loss: 0.000705 2022/09/13 13:23:26 - mmengine - INFO - Epoch(train) [29][250/293] lr: 5.000000e-04 eta: 6:27:48 time: 0.504210 data_time: 0.078194 memory: 9871 loss_kpt: 0.000695 acc_pose: 0.775066 loss: 0.000695 2022/09/13 13:23:47 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 13:23:47 - mmengine - INFO - Saving checkpoint at 29 epochs 2022/09/13 13:24:18 - mmengine - INFO - Epoch(train) [30][50/293] lr: 5.000000e-04 eta: 6:25:35 time: 0.515122 data_time: 0.080468 memory: 9871 loss_kpt: 0.000714 acc_pose: 0.718554 loss: 0.000714 2022/09/13 13:24:43 - mmengine - INFO - Epoch(train) [30][100/293] lr: 5.000000e-04 eta: 6:25:36 time: 0.513769 data_time: 0.081564 memory: 9871 loss_kpt: 0.000704 acc_pose: 0.762949 loss: 0.000704 2022/09/13 13:25:08 - mmengine - INFO - Epoch(train) [30][150/293] lr: 5.000000e-04 eta: 6:25:32 time: 0.495048 data_time: 0.077116 memory: 9871 loss_kpt: 0.000697 acc_pose: 0.797484 loss: 0.000697 2022/09/13 13:25:33 - mmengine - INFO - Epoch(train) [30][200/293] lr: 5.000000e-04 eta: 6:25:27 time: 0.490640 data_time: 0.073513 memory: 9871 loss_kpt: 0.000687 acc_pose: 0.786879 loss: 0.000687 2022/09/13 13:25:58 - mmengine - INFO - Epoch(train) [30][250/293] lr: 5.000000e-04 eta: 6:25:22 time: 0.496281 data_time: 0.079408 memory: 9871 loss_kpt: 0.000693 acc_pose: 0.826042 loss: 0.000693 2022/09/13 13:26:19 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 13:26:19 - mmengine - INFO - Saving checkpoint at 30 epochs 2022/09/13 13:26:32 - mmengine - INFO - Epoch(val) [30][50/407] eta: 0:00:59 time: 0.165565 data_time: 0.012759 memory: 9871 2022/09/13 13:26:40 - mmengine - INFO - Epoch(val) [30][100/407] eta: 0:00:48 time: 0.159401 data_time: 0.008004 memory: 920 2022/09/13 13:26:48 - mmengine - INFO - Epoch(val) [30][150/407] eta: 0:00:40 time: 0.158282 data_time: 0.008049 memory: 920 2022/09/13 13:26:56 - mmengine - INFO - Epoch(val) [30][200/407] eta: 0:00:33 time: 0.163869 data_time: 0.007635 memory: 920 2022/09/13 13:27:04 - mmengine - INFO - Epoch(val) [30][250/407] eta: 0:00:24 time: 0.158802 data_time: 0.007422 memory: 920 2022/09/13 13:27:12 - mmengine - INFO - Epoch(val) [30][300/407] eta: 0:00:16 time: 0.157589 data_time: 0.007968 memory: 920 2022/09/13 13:27:20 - mmengine - INFO - Epoch(val) [30][350/407] eta: 0:00:09 time: 0.158203 data_time: 0.007832 memory: 920 2022/09/13 13:27:27 - mmengine - INFO - Epoch(val) [30][400/407] eta: 0:00:01 time: 0.156259 data_time: 0.007974 memory: 920 2022/09/13 13:28:04 - mmengine - INFO - Evaluating CocoMetric... 2022/09/13 13:28:18 - mmengine - INFO - Epoch(val) [30][407/407] coco/AP: 0.707035 coco/AP .5: 0.886295 coco/AP .75: 0.779669 coco/AP (M): 0.673348 coco/AP (L): 0.768984 coco/AR: 0.761776 coco/AR .5: 0.926008 coco/AR .75: 0.827928 coco/AR (M): 0.721524 coco/AR (L): 0.819398 2022/09/13 13:28:18 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220913/dark_w32_256_v1/best_coco/AP_epoch_20.pth is removed 2022/09/13 13:28:21 - mmengine - INFO - The best checkpoint with 0.7070 coco/AP at 30 epoch is saved to best_coco/AP_epoch_30.pth. 2022/09/13 13:28:47 - mmengine - INFO - Epoch(train) [31][50/293] lr: 5.000000e-04 eta: 6:23:13 time: 0.517976 data_time: 0.081813 memory: 9871 loss_kpt: 0.000688 acc_pose: 0.834298 loss: 0.000688 2022/09/13 13:29:12 - mmengine - INFO - Epoch(train) [31][100/293] lr: 5.000000e-04 eta: 6:23:13 time: 0.510465 data_time: 0.088824 memory: 9871 loss_kpt: 0.000699 acc_pose: 0.801996 loss: 0.000699 2022/09/13 13:29:37 - mmengine - INFO - Epoch(train) [31][150/293] lr: 5.000000e-04 eta: 6:23:10 time: 0.500613 data_time: 0.082392 memory: 9871 loss_kpt: 0.000695 acc_pose: 0.788297 loss: 0.000695 2022/09/13 13:30:02 - mmengine - INFO - Epoch(train) [31][200/293] lr: 5.000000e-04 eta: 6:23:06 time: 0.498968 data_time: 0.072165 memory: 9871 loss_kpt: 0.000695 acc_pose: 0.763087 loss: 0.000695 2022/09/13 13:30:07 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 13:30:27 - mmengine - INFO - Epoch(train) [31][250/293] lr: 5.000000e-04 eta: 6:23:03 time: 0.502006 data_time: 0.074801 memory: 9871 loss_kpt: 0.000699 acc_pose: 0.800964 loss: 0.000699 2022/09/13 13:30:48 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 13:30:49 - mmengine - INFO - Saving checkpoint at 31 epochs 2022/09/13 13:31:19 - mmengine - INFO - Epoch(train) [32][50/293] lr: 5.000000e-04 eta: 6:20:56 time: 0.511632 data_time: 0.085002 memory: 9871 loss_kpt: 0.000683 acc_pose: 0.800376 loss: 0.000683 2022/09/13 13:31:44 - mmengine - INFO - Epoch(train) [32][100/293] lr: 5.000000e-04 eta: 6:20:56 time: 0.512160 data_time: 0.075269 memory: 9871 loss_kpt: 0.000691 acc_pose: 0.838725 loss: 0.000691 2022/09/13 13:32:09 - mmengine - INFO - Epoch(train) [32][150/293] lr: 5.000000e-04 eta: 6:20:50 time: 0.494668 data_time: 0.071577 memory: 9871 loss_kpt: 0.000691 acc_pose: 0.769311 loss: 0.000691 2022/09/13 13:32:34 - mmengine - INFO - Epoch(train) [32][200/293] lr: 5.000000e-04 eta: 6:20:48 time: 0.508005 data_time: 0.086725 memory: 9871 loss_kpt: 0.000695 acc_pose: 0.725379 loss: 0.000695 2022/09/13 13:32:59 - mmengine - INFO - Epoch(train) [32][250/293] lr: 5.000000e-04 eta: 6:20:45 time: 0.503651 data_time: 0.080396 memory: 9871 loss_kpt: 0.000690 acc_pose: 0.776092 loss: 0.000690 2022/09/13 13:33:21 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 13:33:21 - mmengine - INFO - Saving checkpoint at 32 epochs 2022/09/13 13:33:51 - mmengine - INFO - Epoch(train) [33][50/293] lr: 5.000000e-04 eta: 6:18:42 time: 0.515883 data_time: 0.088426 memory: 9871 loss_kpt: 0.000693 acc_pose: 0.826659 loss: 0.000693 2022/09/13 13:34:17 - mmengine - INFO - Epoch(train) [33][100/293] lr: 5.000000e-04 eta: 6:18:41 time: 0.511540 data_time: 0.077879 memory: 9871 loss_kpt: 0.000697 acc_pose: 0.811716 loss: 0.000697 2022/09/13 13:34:41 - mmengine - INFO - Epoch(train) [33][150/293] lr: 5.000000e-04 eta: 6:18:36 time: 0.497900 data_time: 0.076505 memory: 9871 loss_kpt: 0.000686 acc_pose: 0.797551 loss: 0.000686 2022/09/13 13:35:06 - mmengine - INFO - Epoch(train) [33][200/293] lr: 5.000000e-04 eta: 6:18:31 time: 0.498877 data_time: 0.084453 memory: 9871 loss_kpt: 0.000690 acc_pose: 0.802366 loss: 0.000690 2022/09/13 13:35:31 - mmengine - INFO - Epoch(train) [33][250/293] lr: 5.000000e-04 eta: 6:18:26 time: 0.501694 data_time: 0.081031 memory: 9871 loss_kpt: 0.000684 acc_pose: 0.798772 loss: 0.000684 2022/09/13 13:35:53 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 13:35:53 - mmengine - INFO - Saving checkpoint at 33 epochs 2022/09/13 13:36:23 - mmengine - INFO - Epoch(train) [34][50/293] lr: 5.000000e-04 eta: 6:16:26 time: 0.514002 data_time: 0.081579 memory: 9871 loss_kpt: 0.000682 acc_pose: 0.819335 loss: 0.000682 2022/09/13 13:36:48 - mmengine - INFO - Epoch(train) [34][100/293] lr: 5.000000e-04 eta: 6:16:22 time: 0.504562 data_time: 0.078997 memory: 9871 loss_kpt: 0.000679 acc_pose: 0.745163 loss: 0.000679 2022/09/13 13:37:13 - mmengine - INFO - Epoch(train) [34][150/293] lr: 5.000000e-04 eta: 6:16:16 time: 0.496191 data_time: 0.082360 memory: 9871 loss_kpt: 0.000673 acc_pose: 0.809968 loss: 0.000673 2022/09/13 13:37:37 - mmengine - INFO - Epoch(train) [34][200/293] lr: 5.000000e-04 eta: 6:16:08 time: 0.489574 data_time: 0.072677 memory: 9871 loss_kpt: 0.000699 acc_pose: 0.787292 loss: 0.000699 2022/09/13 13:38:02 - mmengine - INFO - Epoch(train) [34][250/293] lr: 5.000000e-04 eta: 6:16:03 time: 0.499929 data_time: 0.077334 memory: 9871 loss_kpt: 0.000684 acc_pose: 0.780688 loss: 0.000684 2022/09/13 13:38:25 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 13:38:25 - mmengine - INFO - Saving checkpoint at 34 epochs 2022/09/13 13:38:48 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 13:38:54 - mmengine - INFO - Epoch(train) [35][50/293] lr: 5.000000e-04 eta: 6:14:04 time: 0.510384 data_time: 0.084396 memory: 9871 loss_kpt: 0.000687 acc_pose: 0.828466 loss: 0.000687 2022/09/13 13:39:19 - mmengine - INFO - Epoch(train) [35][100/293] lr: 5.000000e-04 eta: 6:13:59 time: 0.499560 data_time: 0.076539 memory: 9871 loss_kpt: 0.000678 acc_pose: 0.825066 loss: 0.000678 2022/09/13 13:39:44 - mmengine - INFO - Epoch(train) [35][150/293] lr: 5.000000e-04 eta: 6:13:53 time: 0.500542 data_time: 0.080900 memory: 9871 loss_kpt: 0.000679 acc_pose: 0.810968 loss: 0.000679 2022/09/13 13:40:10 - mmengine - INFO - Epoch(train) [35][200/293] lr: 5.000000e-04 eta: 6:13:49 time: 0.506629 data_time: 0.081297 memory: 9871 loss_kpt: 0.000678 acc_pose: 0.755342 loss: 0.000678 2022/09/13 13:40:35 - mmengine - INFO - Epoch(train) [35][250/293] lr: 5.000000e-04 eta: 6:13:46 time: 0.511182 data_time: 0.077510 memory: 9871 loss_kpt: 0.000675 acc_pose: 0.809641 loss: 0.000675 2022/09/13 13:40:56 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 13:40:56 - mmengine - INFO - Saving checkpoint at 35 epochs 2022/09/13 13:41:27 - mmengine - INFO - Epoch(train) [36][50/293] lr: 5.000000e-04 eta: 6:11:52 time: 0.516477 data_time: 0.086765 memory: 9871 loss_kpt: 0.000694 acc_pose: 0.736588 loss: 0.000694 2022/09/13 13:41:52 - mmengine - INFO - Epoch(train) [36][100/293] lr: 5.000000e-04 eta: 6:11:46 time: 0.500585 data_time: 0.080065 memory: 9871 loss_kpt: 0.000673 acc_pose: 0.829854 loss: 0.000673 2022/09/13 13:42:16 - mmengine - INFO - Epoch(train) [36][150/293] lr: 5.000000e-04 eta: 6:11:38 time: 0.491021 data_time: 0.077881 memory: 9871 loss_kpt: 0.000682 acc_pose: 0.810753 loss: 0.000682 2022/09/13 13:42:41 - mmengine - INFO - Epoch(train) [36][200/293] lr: 5.000000e-04 eta: 6:11:31 time: 0.497148 data_time: 0.075987 memory: 9871 loss_kpt: 0.000676 acc_pose: 0.778089 loss: 0.000676 2022/09/13 13:43:06 - mmengine - INFO - Epoch(train) [36][250/293] lr: 5.000000e-04 eta: 6:11:22 time: 0.490666 data_time: 0.074758 memory: 9871 loss_kpt: 0.000680 acc_pose: 0.760646 loss: 0.000680 2022/09/13 13:43:27 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 13:43:27 - mmengine - INFO - Saving checkpoint at 36 epochs 2022/09/13 13:43:58 - mmengine - INFO - Epoch(train) [37][50/293] lr: 5.000000e-04 eta: 6:09:32 time: 0.521897 data_time: 0.084282 memory: 9871 loss_kpt: 0.000678 acc_pose: 0.798707 loss: 0.000678 2022/09/13 13:44:23 - mmengine - INFO - Epoch(train) [37][100/293] lr: 5.000000e-04 eta: 6:09:25 time: 0.497734 data_time: 0.076843 memory: 9871 loss_kpt: 0.000681 acc_pose: 0.817383 loss: 0.000681 2022/09/13 13:44:47 - mmengine - INFO - Epoch(train) [37][150/293] lr: 5.000000e-04 eta: 6:09:15 time: 0.486672 data_time: 0.071676 memory: 9871 loss_kpt: 0.000681 acc_pose: 0.795838 loss: 0.000681 2022/09/13 13:45:12 - mmengine - INFO - Epoch(train) [37][200/293] lr: 5.000000e-04 eta: 6:09:07 time: 0.491858 data_time: 0.084583 memory: 9871 loss_kpt: 0.000675 acc_pose: 0.844331 loss: 0.000675 2022/09/13 13:45:37 - mmengine - INFO - Epoch(train) [37][250/293] lr: 5.000000e-04 eta: 6:09:00 time: 0.500558 data_time: 0.074332 memory: 9871 loss_kpt: 0.000678 acc_pose: 0.809034 loss: 0.000678 2022/09/13 13:45:58 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 13:45:58 - mmengine - INFO - Saving checkpoint at 37 epochs 2022/09/13 13:46:28 - mmengine - INFO - Epoch(train) [38][50/293] lr: 5.000000e-04 eta: 6:07:08 time: 0.503500 data_time: 0.079729 memory: 9871 loss_kpt: 0.000657 acc_pose: 0.812768 loss: 0.000657 2022/09/13 13:46:52 - mmengine - INFO - Epoch(train) [38][100/293] lr: 5.000000e-04 eta: 6:06:59 time: 0.490131 data_time: 0.081475 memory: 9871 loss_kpt: 0.000686 acc_pose: 0.841664 loss: 0.000686 2022/09/13 13:47:17 - mmengine - INFO - Epoch(train) [38][150/293] lr: 5.000000e-04 eta: 6:06:54 time: 0.507128 data_time: 0.075961 memory: 9871 loss_kpt: 0.000682 acc_pose: 0.719101 loss: 0.000682 2022/09/13 13:47:22 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 13:47:42 - mmengine - INFO - Epoch(train) [38][200/293] lr: 5.000000e-04 eta: 6:06:47 time: 0.500495 data_time: 0.077352 memory: 9871 loss_kpt: 0.000666 acc_pose: 0.807394 loss: 0.000666 2022/09/13 13:48:08 - mmengine - INFO - Epoch(train) [38][250/293] lr: 5.000000e-04 eta: 6:06:43 time: 0.516299 data_time: 0.076358 memory: 9871 loss_kpt: 0.000666 acc_pose: 0.813677 loss: 0.000666 2022/09/13 13:48:29 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 13:48:29 - mmengine - INFO - Saving checkpoint at 38 epochs 2022/09/13 13:49:00 - mmengine - INFO - Epoch(train) [39][50/293] lr: 5.000000e-04 eta: 6:04:57 time: 0.519504 data_time: 0.093362 memory: 9871 loss_kpt: 0.000665 acc_pose: 0.836852 loss: 0.000665 2022/09/13 13:49:25 - mmengine - INFO - Epoch(train) [39][100/293] lr: 5.000000e-04 eta: 6:04:51 time: 0.504887 data_time: 0.074283 memory: 9871 loss_kpt: 0.000684 acc_pose: 0.781866 loss: 0.000684 2022/09/13 13:49:50 - mmengine - INFO - Epoch(train) [39][150/293] lr: 5.000000e-04 eta: 6:04:43 time: 0.496644 data_time: 0.078166 memory: 9871 loss_kpt: 0.000670 acc_pose: 0.839508 loss: 0.000670 2022/09/13 13:50:15 - mmengine - INFO - Epoch(train) [39][200/293] lr: 5.000000e-04 eta: 6:04:35 time: 0.498736 data_time: 0.078500 memory: 9871 loss_kpt: 0.000666 acc_pose: 0.834571 loss: 0.000666 2022/09/13 13:50:39 - mmengine - INFO - Epoch(train) [39][250/293] lr: 5.000000e-04 eta: 6:04:25 time: 0.488209 data_time: 0.077281 memory: 9871 loss_kpt: 0.000671 acc_pose: 0.835953 loss: 0.000671 2022/09/13 13:51:01 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 13:51:01 - mmengine - INFO - Saving checkpoint at 39 epochs 2022/09/13 13:51:31 - mmengine - INFO - Epoch(train) [40][50/293] lr: 5.000000e-04 eta: 6:02:37 time: 0.505297 data_time: 0.084608 memory: 9871 loss_kpt: 0.000670 acc_pose: 0.824646 loss: 0.000670 2022/09/13 13:51:56 - mmengine - INFO - Epoch(train) [40][100/293] lr: 5.000000e-04 eta: 6:02:29 time: 0.497772 data_time: 0.072392 memory: 9871 loss_kpt: 0.000678 acc_pose: 0.716305 loss: 0.000678 2022/09/13 13:52:21 - mmengine - INFO - Epoch(train) [40][150/293] lr: 5.000000e-04 eta: 6:02:21 time: 0.496702 data_time: 0.076752 memory: 9871 loss_kpt: 0.000668 acc_pose: 0.776727 loss: 0.000668 2022/09/13 13:52:45 - mmengine - INFO - Epoch(train) [40][200/293] lr: 5.000000e-04 eta: 6:02:13 time: 0.498846 data_time: 0.075504 memory: 9871 loss_kpt: 0.000664 acc_pose: 0.791046 loss: 0.000664 2022/09/13 13:53:11 - mmengine - INFO - Epoch(train) [40][250/293] lr: 5.000000e-04 eta: 6:02:06 time: 0.505295 data_time: 0.088587 memory: 9871 loss_kpt: 0.000684 acc_pose: 0.760991 loss: 0.000684 2022/09/13 13:53:32 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 13:53:32 - mmengine - INFO - Saving checkpoint at 40 epochs 2022/09/13 13:53:45 - mmengine - INFO - Epoch(val) [40][50/407] eta: 0:00:59 time: 0.167638 data_time: 0.012952 memory: 9871 2022/09/13 13:53:53 - mmengine - INFO - Epoch(val) [40][100/407] eta: 0:00:50 time: 0.164336 data_time: 0.008116 memory: 920 2022/09/13 13:54:01 - mmengine - INFO - Epoch(val) [40][150/407] eta: 0:00:41 time: 0.160053 data_time: 0.008305 memory: 920 2022/09/13 13:54:09 - mmengine - INFO - Epoch(val) [40][200/407] eta: 0:00:33 time: 0.160362 data_time: 0.007987 memory: 920 2022/09/13 13:54:17 - mmengine - INFO - Epoch(val) [40][250/407] eta: 0:00:24 time: 0.158165 data_time: 0.007707 memory: 920 2022/09/13 13:54:25 - mmengine - INFO - Epoch(val) [40][300/407] eta: 0:00:16 time: 0.157680 data_time: 0.007674 memory: 920 2022/09/13 13:54:33 - mmengine - INFO - Epoch(val) [40][350/407] eta: 0:00:09 time: 0.158961 data_time: 0.007774 memory: 920 2022/09/13 13:54:41 - mmengine - INFO - Epoch(val) [40][400/407] eta: 0:00:01 time: 0.155491 data_time: 0.007386 memory: 920 2022/09/13 13:55:17 - mmengine - INFO - Evaluating CocoMetric... 2022/09/13 13:55:30 - mmengine - INFO - Epoch(val) [40][407/407] coco/AP: 0.716462 coco/AP .5: 0.889920 coco/AP .75: 0.788248 coco/AP (M): 0.679354 coco/AP (L): 0.784901 coco/AR: 0.772355 coco/AR .5: 0.930888 coco/AR .75: 0.838004 coco/AR (M): 0.728216 coco/AR (L): 0.835637 2022/09/13 13:55:31 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220913/dark_w32_256_v1/best_coco/AP_epoch_30.pth is removed 2022/09/13 13:55:34 - mmengine - INFO - The best checkpoint with 0.7165 coco/AP at 40 epoch is saved to best_coco/AP_epoch_40.pth. 2022/09/13 13:56:00 - mmengine - INFO - Epoch(train) [41][50/293] lr: 5.000000e-04 eta: 6:00:23 time: 0.514502 data_time: 0.082828 memory: 9871 loss_kpt: 0.000677 acc_pose: 0.749613 loss: 0.000677 2022/09/13 13:56:24 - mmengine - INFO - Epoch(train) [41][100/293] lr: 5.000000e-04 eta: 6:00:13 time: 0.489860 data_time: 0.077098 memory: 9871 loss_kpt: 0.000678 acc_pose: 0.755530 loss: 0.000678 2022/09/13 13:56:49 - mmengine - INFO - Epoch(train) [41][150/293] lr: 5.000000e-04 eta: 6:00:04 time: 0.497190 data_time: 0.075689 memory: 9871 loss_kpt: 0.000671 acc_pose: 0.799819 loss: 0.000671 2022/09/13 13:57:14 - mmengine - INFO - Epoch(train) [41][200/293] lr: 5.000000e-04 eta: 5:59:57 time: 0.503953 data_time: 0.076193 memory: 9871 loss_kpt: 0.000685 acc_pose: 0.777989 loss: 0.000685 2022/09/13 13:57:39 - mmengine - INFO - Epoch(train) [41][250/293] lr: 5.000000e-04 eta: 5:59:46 time: 0.488048 data_time: 0.076392 memory: 9871 loss_kpt: 0.000680 acc_pose: 0.822267 loss: 0.000680 2022/09/13 13:57:54 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 13:58:00 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 13:58:00 - mmengine - INFO - Saving checkpoint at 41 epochs 2022/09/13 13:58:30 - mmengine - INFO - Epoch(train) [42][50/293] lr: 5.000000e-04 eta: 5:58:03 time: 0.506579 data_time: 0.088291 memory: 9871 loss_kpt: 0.000656 acc_pose: 0.817644 loss: 0.000656 2022/09/13 13:58:55 - mmengine - INFO - Epoch(train) [42][100/293] lr: 5.000000e-04 eta: 5:57:54 time: 0.494811 data_time: 0.077148 memory: 9871 loss_kpt: 0.000671 acc_pose: 0.817219 loss: 0.000671 2022/09/13 13:59:20 - mmengine - INFO - Epoch(train) [42][150/293] lr: 5.000000e-04 eta: 5:57:45 time: 0.497287 data_time: 0.077840 memory: 9871 loss_kpt: 0.000661 acc_pose: 0.779042 loss: 0.000661 2022/09/13 13:59:45 - mmengine - INFO - Epoch(train) [42][200/293] lr: 5.000000e-04 eta: 5:57:38 time: 0.510201 data_time: 0.081591 memory: 9871 loss_kpt: 0.000678 acc_pose: 0.817504 loss: 0.000678 2022/09/13 14:00:10 - mmengine - INFO - Epoch(train) [42][250/293] lr: 5.000000e-04 eta: 5:57:30 time: 0.501397 data_time: 0.077051 memory: 9871 loss_kpt: 0.000668 acc_pose: 0.788007 loss: 0.000668 2022/09/13 14:00:31 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 14:00:31 - mmengine - INFO - Saving checkpoint at 42 epochs 2022/09/13 14:01:01 - mmengine - INFO - Epoch(train) [43][50/293] lr: 5.000000e-04 eta: 5:55:48 time: 0.502703 data_time: 0.084710 memory: 9871 loss_kpt: 0.000657 acc_pose: 0.757845 loss: 0.000657 2022/09/13 14:01:26 - mmengine - INFO - Epoch(train) [43][100/293] lr: 5.000000e-04 eta: 5:55:40 time: 0.501126 data_time: 0.076769 memory: 9871 loss_kpt: 0.000672 acc_pose: 0.791194 loss: 0.000672 2022/09/13 14:01:51 - mmengine - INFO - Epoch(train) [43][150/293] lr: 5.000000e-04 eta: 5:55:31 time: 0.499827 data_time: 0.076928 memory: 9871 loss_kpt: 0.000679 acc_pose: 0.781144 loss: 0.000679 2022/09/13 14:02:15 - mmengine - INFO - Epoch(train) [43][200/293] lr: 5.000000e-04 eta: 5:55:20 time: 0.489628 data_time: 0.076465 memory: 9871 loss_kpt: 0.000661 acc_pose: 0.762721 loss: 0.000661 2022/09/13 14:02:40 - mmengine - INFO - Epoch(train) [43][250/293] lr: 5.000000e-04 eta: 5:55:11 time: 0.502350 data_time: 0.080172 memory: 9871 loss_kpt: 0.000663 acc_pose: 0.813778 loss: 0.000663 2022/09/13 14:03:02 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 14:03:02 - mmengine - INFO - Saving checkpoint at 43 epochs 2022/09/13 14:03:32 - mmengine - INFO - Epoch(train) [44][50/293] lr: 5.000000e-04 eta: 5:53:34 time: 0.515287 data_time: 0.081561 memory: 9871 loss_kpt: 0.000659 acc_pose: 0.864191 loss: 0.000659 2022/09/13 14:03:57 - mmengine - INFO - Epoch(train) [44][100/293] lr: 5.000000e-04 eta: 5:53:24 time: 0.493372 data_time: 0.074286 memory: 9871 loss_kpt: 0.000672 acc_pose: 0.794921 loss: 0.000672 2022/09/13 14:04:22 - mmengine - INFO - Epoch(train) [44][150/293] lr: 5.000000e-04 eta: 5:53:15 time: 0.501200 data_time: 0.071703 memory: 9871 loss_kpt: 0.000677 acc_pose: 0.812316 loss: 0.000677 2022/09/13 14:04:47 - mmengine - INFO - Epoch(train) [44][200/293] lr: 5.000000e-04 eta: 5:53:05 time: 0.497545 data_time: 0.083030 memory: 9871 loss_kpt: 0.000653 acc_pose: 0.835090 loss: 0.000653 2022/09/13 14:05:12 - mmengine - INFO - Epoch(train) [44][250/293] lr: 5.000000e-04 eta: 5:52:55 time: 0.498340 data_time: 0.075513 memory: 9871 loss_kpt: 0.000663 acc_pose: 0.783703 loss: 0.000663 2022/09/13 14:05:33 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 14:05:33 - mmengine - INFO - Saving checkpoint at 44 epochs 2022/09/13 14:06:03 - mmengine - INFO - Epoch(train) [45][50/293] lr: 5.000000e-04 eta: 5:51:19 time: 0.513558 data_time: 0.086356 memory: 9871 loss_kpt: 0.000641 acc_pose: 0.796133 loss: 0.000641 2022/09/13 14:06:28 - mmengine - INFO - Epoch(train) [45][100/293] lr: 5.000000e-04 eta: 5:51:10 time: 0.498787 data_time: 0.072721 memory: 9871 loss_kpt: 0.000660 acc_pose: 0.846431 loss: 0.000660 2022/09/13 14:06:32 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 14:06:53 - mmengine - INFO - Epoch(train) [45][150/293] lr: 5.000000e-04 eta: 5:51:00 time: 0.498754 data_time: 0.074139 memory: 9871 loss_kpt: 0.000656 acc_pose: 0.807341 loss: 0.000656 2022/09/13 14:07:18 - mmengine - INFO - Epoch(train) [45][200/293] lr: 5.000000e-04 eta: 5:50:51 time: 0.499637 data_time: 0.076295 memory: 9871 loss_kpt: 0.000670 acc_pose: 0.793645 loss: 0.000670 2022/09/13 14:07:43 - mmengine - INFO - Epoch(train) [45][250/293] lr: 5.000000e-04 eta: 5:50:42 time: 0.505045 data_time: 0.075431 memory: 9871 loss_kpt: 0.000688 acc_pose: 0.785620 loss: 0.000688 2022/09/13 14:08:04 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 14:08:04 - mmengine - INFO - Saving checkpoint at 45 epochs 2022/09/13 14:08:34 - mmengine - INFO - Epoch(train) [46][50/293] lr: 5.000000e-04 eta: 5:49:08 time: 0.514493 data_time: 0.086146 memory: 9871 loss_kpt: 0.000670 acc_pose: 0.804479 loss: 0.000670 2022/09/13 14:08:59 - mmengine - INFO - Epoch(train) [46][100/293] lr: 5.000000e-04 eta: 5:48:57 time: 0.494663 data_time: 0.072144 memory: 9871 loss_kpt: 0.000646 acc_pose: 0.792284 loss: 0.000646 2022/09/13 14:09:24 - mmengine - INFO - Epoch(train) [46][150/293] lr: 5.000000e-04 eta: 5:48:47 time: 0.498858 data_time: 0.080173 memory: 9871 loss_kpt: 0.000666 acc_pose: 0.809254 loss: 0.000666 2022/09/13 14:09:48 - mmengine - INFO - Epoch(train) [46][200/293] lr: 5.000000e-04 eta: 5:48:36 time: 0.495800 data_time: 0.078085 memory: 9871 loss_kpt: 0.000652 acc_pose: 0.798374 loss: 0.000652 2022/09/13 14:10:13 - mmengine - INFO - Epoch(train) [46][250/293] lr: 5.000000e-04 eta: 5:48:26 time: 0.498220 data_time: 0.081099 memory: 9871 loss_kpt: 0.000664 acc_pose: 0.803738 loss: 0.000664 2022/09/13 14:10:34 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 14:10:34 - mmengine - INFO - Saving checkpoint at 46 epochs 2022/09/13 14:11:04 - mmengine - INFO - Epoch(train) [47][50/293] lr: 5.000000e-04 eta: 5:46:53 time: 0.510738 data_time: 0.083052 memory: 9871 loss_kpt: 0.000663 acc_pose: 0.814654 loss: 0.000663 2022/09/13 14:11:30 - mmengine - INFO - Epoch(train) [47][100/293] lr: 5.000000e-04 eta: 5:46:44 time: 0.505957 data_time: 0.082473 memory: 9871 loss_kpt: 0.000643 acc_pose: 0.793487 loss: 0.000643 2022/09/13 14:11:55 - mmengine - INFO - Epoch(train) [47][150/293] lr: 5.000000e-04 eta: 5:46:36 time: 0.509401 data_time: 0.077283 memory: 9871 loss_kpt: 0.000642 acc_pose: 0.772335 loss: 0.000642 2022/09/13 14:12:21 - mmengine - INFO - Epoch(train) [47][200/293] lr: 5.000000e-04 eta: 5:46:28 time: 0.515405 data_time: 0.078623 memory: 9871 loss_kpt: 0.000658 acc_pose: 0.771567 loss: 0.000658 2022/09/13 14:12:46 - mmengine - INFO - Epoch(train) [47][250/293] lr: 5.000000e-04 eta: 5:46:17 time: 0.495562 data_time: 0.077196 memory: 9871 loss_kpt: 0.000655 acc_pose: 0.800819 loss: 0.000655 2022/09/13 14:13:07 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 14:13:07 - mmengine - INFO - Saving checkpoint at 47 epochs 2022/09/13 14:13:36 - mmengine - INFO - Epoch(train) [48][50/293] lr: 5.000000e-04 eta: 5:44:44 time: 0.506563 data_time: 0.082538 memory: 9871 loss_kpt: 0.000668 acc_pose: 0.841505 loss: 0.000668 2022/09/13 14:14:01 - mmengine - INFO - Epoch(train) [48][100/293] lr: 5.000000e-04 eta: 5:44:35 time: 0.503800 data_time: 0.081968 memory: 9871 loss_kpt: 0.000657 acc_pose: 0.792205 loss: 0.000657 2022/09/13 14:14:27 - mmengine - INFO - Epoch(train) [48][150/293] lr: 5.000000e-04 eta: 5:44:26 time: 0.507627 data_time: 0.077062 memory: 9871 loss_kpt: 0.000653 acc_pose: 0.819369 loss: 0.000653 2022/09/13 14:14:51 - mmengine - INFO - Epoch(train) [48][200/293] lr: 5.000000e-04 eta: 5:44:14 time: 0.490364 data_time: 0.078707 memory: 9871 loss_kpt: 0.000663 acc_pose: 0.864363 loss: 0.000663 2022/09/13 14:15:06 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 14:15:17 - mmengine - INFO - Epoch(train) [48][250/293] lr: 5.000000e-04 eta: 5:44:05 time: 0.509034 data_time: 0.072329 memory: 9871 loss_kpt: 0.000664 acc_pose: 0.824381 loss: 0.000664 2022/09/13 14:15:38 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 14:15:38 - mmengine - INFO - Saving checkpoint at 48 epochs 2022/09/13 14:16:08 - mmengine - INFO - Epoch(train) [49][50/293] lr: 5.000000e-04 eta: 5:42:33 time: 0.504556 data_time: 0.087897 memory: 9871 loss_kpt: 0.000651 acc_pose: 0.834945 loss: 0.000651 2022/09/13 14:16:33 - mmengine - INFO - Epoch(train) [49][100/293] lr: 5.000000e-04 eta: 5:42:23 time: 0.501226 data_time: 0.076203 memory: 9871 loss_kpt: 0.000660 acc_pose: 0.787850 loss: 0.000660 2022/09/13 14:16:58 - mmengine - INFO - Epoch(train) [49][150/293] lr: 5.000000e-04 eta: 5:42:12 time: 0.498228 data_time: 0.070998 memory: 9871 loss_kpt: 0.000664 acc_pose: 0.844780 loss: 0.000664 2022/09/13 14:17:24 - mmengine - INFO - Epoch(train) [49][200/293] lr: 5.000000e-04 eta: 5:42:03 time: 0.510556 data_time: 0.079482 memory: 9871 loss_kpt: 0.000656 acc_pose: 0.779991 loss: 0.000656 2022/09/13 14:17:48 - mmengine - INFO - Epoch(train) [49][250/293] lr: 5.000000e-04 eta: 5:41:51 time: 0.494551 data_time: 0.077868 memory: 9871 loss_kpt: 0.000641 acc_pose: 0.802027 loss: 0.000641 2022/09/13 14:18:10 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 14:18:10 - mmengine - INFO - Saving checkpoint at 49 epochs 2022/09/13 14:18:40 - mmengine - INFO - Epoch(train) [50][50/293] lr: 5.000000e-04 eta: 5:40:20 time: 0.500577 data_time: 0.081459 memory: 9871 loss_kpt: 0.000661 acc_pose: 0.822007 loss: 0.000661 2022/09/13 14:19:05 - mmengine - INFO - Epoch(train) [50][100/293] lr: 5.000000e-04 eta: 5:40:12 time: 0.513643 data_time: 0.076949 memory: 9871 loss_kpt: 0.000640 acc_pose: 0.774776 loss: 0.000640 2022/09/13 14:19:30 - mmengine - INFO - Epoch(train) [50][150/293] lr: 5.000000e-04 eta: 5:40:01 time: 0.499779 data_time: 0.080695 memory: 9871 loss_kpt: 0.000652 acc_pose: 0.815972 loss: 0.000652 2022/09/13 14:19:55 - mmengine - INFO - Epoch(train) [50][200/293] lr: 5.000000e-04 eta: 5:39:50 time: 0.501173 data_time: 0.074036 memory: 9871 loss_kpt: 0.000629 acc_pose: 0.823265 loss: 0.000629 2022/09/13 14:20:20 - mmengine - INFO - Epoch(train) [50][250/293] lr: 5.000000e-04 eta: 5:39:39 time: 0.501304 data_time: 0.086210 memory: 9871 loss_kpt: 0.000646 acc_pose: 0.817263 loss: 0.000646 2022/09/13 14:20:41 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 14:20:41 - mmengine - INFO - Saving checkpoint at 50 epochs 2022/09/13 14:20:53 - mmengine - INFO - Epoch(val) [50][50/407] eta: 0:00:58 time: 0.164710 data_time: 0.012791 memory: 9871 2022/09/13 14:21:01 - mmengine - INFO - Epoch(val) [50][100/407] eta: 0:00:48 time: 0.158777 data_time: 0.007321 memory: 920 2022/09/13 14:21:10 - mmengine - INFO - Epoch(val) [50][150/407] eta: 0:00:41 time: 0.161815 data_time: 0.011532 memory: 920 2022/09/13 14:21:17 - mmengine - INFO - Epoch(val) [50][200/407] eta: 0:00:32 time: 0.156912 data_time: 0.007247 memory: 920 2022/09/13 14:21:25 - mmengine - INFO - Epoch(val) [50][250/407] eta: 0:00:24 time: 0.158590 data_time: 0.007411 memory: 920 2022/09/13 14:21:33 - mmengine - INFO - Epoch(val) [50][300/407] eta: 0:00:16 time: 0.158257 data_time: 0.007739 memory: 920 2022/09/13 14:21:41 - mmengine - INFO - Epoch(val) [50][350/407] eta: 0:00:09 time: 0.164283 data_time: 0.012736 memory: 920 2022/09/13 14:21:49 - mmengine - INFO - Epoch(val) [50][400/407] eta: 0:00:01 time: 0.156269 data_time: 0.007194 memory: 920 2022/09/13 14:22:25 - mmengine - INFO - Evaluating CocoMetric... 2022/09/13 14:22:39 - mmengine - INFO - Epoch(val) [50][407/407] coco/AP: 0.721261 coco/AP .5: 0.892512 coco/AP .75: 0.790242 coco/AP (M): 0.684619 coco/AP (L): 0.790005 coco/AR: 0.775819 coco/AR .5: 0.931203 coco/AR .75: 0.839736 coco/AR (M): 0.732259 coco/AR (L): 0.838239 2022/09/13 14:22:39 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220913/dark_w32_256_v1/best_coco/AP_epoch_40.pth is removed 2022/09/13 14:22:42 - mmengine - INFO - The best checkpoint with 0.7213 coco/AP at 50 epoch is saved to best_coco/AP_epoch_50.pth. 2022/09/13 14:23:07 - mmengine - INFO - Epoch(train) [51][50/293] lr: 5.000000e-04 eta: 5:38:09 time: 0.497863 data_time: 0.083372 memory: 9871 loss_kpt: 0.000653 acc_pose: 0.811346 loss: 0.000653 2022/09/13 14:23:32 - mmengine - INFO - Epoch(train) [51][100/293] lr: 5.000000e-04 eta: 5:37:59 time: 0.504263 data_time: 0.076223 memory: 9871 loss_kpt: 0.000660 acc_pose: 0.800176 loss: 0.000660 2022/09/13 14:23:57 - mmengine - INFO - Epoch(train) [51][150/293] lr: 5.000000e-04 eta: 5:37:47 time: 0.493597 data_time: 0.082192 memory: 9871 loss_kpt: 0.000639 acc_pose: 0.804331 loss: 0.000639 2022/09/13 14:24:22 - mmengine - INFO - Epoch(train) [51][200/293] lr: 5.000000e-04 eta: 5:37:36 time: 0.503381 data_time: 0.081232 memory: 9871 loss_kpt: 0.000652 acc_pose: 0.803303 loss: 0.000652 2022/09/13 14:24:47 - mmengine - INFO - Epoch(train) [51][250/293] lr: 5.000000e-04 eta: 5:37:24 time: 0.496052 data_time: 0.071723 memory: 9871 loss_kpt: 0.000643 acc_pose: 0.812654 loss: 0.000643 2022/09/13 14:25:08 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 14:25:08 - mmengine - INFO - Saving checkpoint at 51 epochs 2022/09/13 14:25:39 - mmengine - INFO - Epoch(train) [52][50/293] lr: 5.000000e-04 eta: 5:35:58 time: 0.510809 data_time: 0.084078 memory: 9871 loss_kpt: 0.000652 acc_pose: 0.801480 loss: 0.000652 2022/09/13 14:25:43 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 14:26:04 - mmengine - INFO - Epoch(train) [52][100/293] lr: 5.000000e-04 eta: 5:35:46 time: 0.498722 data_time: 0.078095 memory: 9871 loss_kpt: 0.000660 acc_pose: 0.806636 loss: 0.000660 2022/09/13 14:26:29 - mmengine - INFO - Epoch(train) [52][150/293] lr: 5.000000e-04 eta: 5:35:35 time: 0.502935 data_time: 0.081980 memory: 9871 loss_kpt: 0.000637 acc_pose: 0.864142 loss: 0.000637 2022/09/13 14:26:54 - mmengine - INFO - Epoch(train) [52][200/293] lr: 5.000000e-04 eta: 5:35:23 time: 0.498506 data_time: 0.076065 memory: 9871 loss_kpt: 0.000650 acc_pose: 0.784207 loss: 0.000650 2022/09/13 14:27:19 - mmengine - INFO - Epoch(train) [52][250/293] lr: 5.000000e-04 eta: 5:35:11 time: 0.496891 data_time: 0.082185 memory: 9871 loss_kpt: 0.000665 acc_pose: 0.826405 loss: 0.000665 2022/09/13 14:27:40 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 14:27:40 - mmengine - INFO - Saving checkpoint at 52 epochs 2022/09/13 14:28:10 - mmengine - INFO - Epoch(train) [53][50/293] lr: 5.000000e-04 eta: 5:33:45 time: 0.505946 data_time: 0.083920 memory: 9871 loss_kpt: 0.000634 acc_pose: 0.820039 loss: 0.000634 2022/09/13 14:28:35 - mmengine - INFO - Epoch(train) [53][100/293] lr: 5.000000e-04 eta: 5:33:33 time: 0.497941 data_time: 0.069474 memory: 9871 loss_kpt: 0.000642 acc_pose: 0.800236 loss: 0.000642 2022/09/13 14:29:00 - mmengine - INFO - Epoch(train) [53][150/293] lr: 5.000000e-04 eta: 5:33:21 time: 0.497658 data_time: 0.071467 memory: 9871 loss_kpt: 0.000640 acc_pose: 0.860317 loss: 0.000640 2022/09/13 14:29:25 - mmengine - INFO - Epoch(train) [53][200/293] lr: 5.000000e-04 eta: 5:33:10 time: 0.503326 data_time: 0.075986 memory: 9871 loss_kpt: 0.000658 acc_pose: 0.808425 loss: 0.000658 2022/09/13 14:29:50 - mmengine - INFO - Epoch(train) [53][250/293] lr: 5.000000e-04 eta: 5:32:58 time: 0.500258 data_time: 0.076892 memory: 9871 loss_kpt: 0.000644 acc_pose: 0.831219 loss: 0.000644 2022/09/13 14:30:11 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 14:30:11 - mmengine - INFO - Saving checkpoint at 53 epochs 2022/09/13 14:30:42 - mmengine - INFO - Epoch(train) [54][50/293] lr: 5.000000e-04 eta: 5:31:36 time: 0.523810 data_time: 0.085085 memory: 9871 loss_kpt: 0.000642 acc_pose: 0.824556 loss: 0.000642 2022/09/13 14:31:07 - mmengine - INFO - Epoch(train) [54][100/293] lr: 5.000000e-04 eta: 5:31:25 time: 0.501476 data_time: 0.073254 memory: 9871 loss_kpt: 0.000647 acc_pose: 0.779993 loss: 0.000647 2022/09/13 14:31:32 - mmengine - INFO - Epoch(train) [54][150/293] lr: 5.000000e-04 eta: 5:31:13 time: 0.498463 data_time: 0.081281 memory: 9871 loss_kpt: 0.000655 acc_pose: 0.815057 loss: 0.000655 2022/09/13 14:31:57 - mmengine - INFO - Epoch(train) [54][200/293] lr: 5.000000e-04 eta: 5:31:00 time: 0.497226 data_time: 0.080681 memory: 9871 loss_kpt: 0.000634 acc_pose: 0.844185 loss: 0.000634 2022/09/13 14:32:22 - mmengine - INFO - Epoch(train) [54][250/293] lr: 5.000000e-04 eta: 5:30:48 time: 0.495754 data_time: 0.072261 memory: 9871 loss_kpt: 0.000650 acc_pose: 0.832167 loss: 0.000650 2022/09/13 14:32:42 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 14:32:42 - mmengine - INFO - Saving checkpoint at 54 epochs 2022/09/13 14:33:14 - mmengine - INFO - Epoch(train) [55][50/293] lr: 5.000000e-04 eta: 5:29:28 time: 0.536286 data_time: 0.084056 memory: 9871 loss_kpt: 0.000637 acc_pose: 0.807935 loss: 0.000637 2022/09/13 14:33:38 - mmengine - INFO - Epoch(train) [55][100/293] lr: 5.000000e-04 eta: 5:29:16 time: 0.499035 data_time: 0.081572 memory: 9871 loss_kpt: 0.000637 acc_pose: 0.779246 loss: 0.000637 2022/09/13 14:34:03 - mmengine - INFO - Epoch(train) [55][150/293] lr: 5.000000e-04 eta: 5:29:04 time: 0.497494 data_time: 0.077502 memory: 9871 loss_kpt: 0.000645 acc_pose: 0.840301 loss: 0.000645 2022/09/13 14:34:17 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 14:34:29 - mmengine - INFO - Epoch(train) [55][200/293] lr: 5.000000e-04 eta: 5:28:53 time: 0.508313 data_time: 0.077990 memory: 9871 loss_kpt: 0.000639 acc_pose: 0.797727 loss: 0.000639 2022/09/13 14:34:53 - mmengine - INFO - Epoch(train) [55][250/293] lr: 5.000000e-04 eta: 5:28:39 time: 0.490832 data_time: 0.073751 memory: 9871 loss_kpt: 0.000663 acc_pose: 0.802194 loss: 0.000663 2022/09/13 14:35:15 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 14:35:15 - mmengine - INFO - Saving checkpoint at 55 epochs 2022/09/13 14:35:45 - mmengine - INFO - Epoch(train) [56][50/293] lr: 5.000000e-04 eta: 5:27:16 time: 0.502967 data_time: 0.080813 memory: 9871 loss_kpt: 0.000649 acc_pose: 0.822037 loss: 0.000649 2022/09/13 14:36:10 - mmengine - INFO - Epoch(train) [56][100/293] lr: 5.000000e-04 eta: 5:27:04 time: 0.503320 data_time: 0.081034 memory: 9871 loss_kpt: 0.000644 acc_pose: 0.757634 loss: 0.000644 2022/09/13 14:36:35 - mmengine - INFO - Epoch(train) [56][150/293] lr: 5.000000e-04 eta: 5:26:52 time: 0.503903 data_time: 0.076536 memory: 9871 loss_kpt: 0.000643 acc_pose: 0.847488 loss: 0.000643 2022/09/13 14:37:00 - mmengine - INFO - Epoch(train) [56][200/293] lr: 5.000000e-04 eta: 5:26:40 time: 0.496606 data_time: 0.074052 memory: 9871 loss_kpt: 0.000656 acc_pose: 0.794417 loss: 0.000656 2022/09/13 14:37:25 - mmengine - INFO - Epoch(train) [56][250/293] lr: 5.000000e-04 eta: 5:26:27 time: 0.501496 data_time: 0.083134 memory: 9871 loss_kpt: 0.000652 acc_pose: 0.767812 loss: 0.000652 2022/09/13 14:37:46 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 14:37:46 - mmengine - INFO - Saving checkpoint at 56 epochs 2022/09/13 14:38:16 - mmengine - INFO - Epoch(train) [57][50/293] lr: 5.000000e-04 eta: 5:25:07 time: 0.512617 data_time: 0.092056 memory: 9871 loss_kpt: 0.000650 acc_pose: 0.819521 loss: 0.000650 2022/09/13 14:38:42 - mmengine - INFO - Epoch(train) [57][100/293] lr: 5.000000e-04 eta: 5:24:55 time: 0.506942 data_time: 0.078595 memory: 9871 loss_kpt: 0.000656 acc_pose: 0.793104 loss: 0.000656 2022/09/13 14:39:07 - mmengine - INFO - Epoch(train) [57][150/293] lr: 5.000000e-04 eta: 5:24:44 time: 0.510056 data_time: 0.082534 memory: 9871 loss_kpt: 0.000643 acc_pose: 0.739832 loss: 0.000643 2022/09/13 14:39:32 - mmengine - INFO - Epoch(train) [57][200/293] lr: 5.000000e-04 eta: 5:24:31 time: 0.498551 data_time: 0.077441 memory: 9871 loss_kpt: 0.000650 acc_pose: 0.827073 loss: 0.000650 2022/09/13 14:39:57 - mmengine - INFO - Epoch(train) [57][250/293] lr: 5.000000e-04 eta: 5:24:18 time: 0.494953 data_time: 0.076784 memory: 9871 loss_kpt: 0.000645 acc_pose: 0.780269 loss: 0.000645 2022/09/13 14:40:18 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 14:40:18 - mmengine - INFO - Saving checkpoint at 57 epochs 2022/09/13 14:40:48 - mmengine - INFO - Epoch(train) [58][50/293] lr: 5.000000e-04 eta: 5:22:58 time: 0.509438 data_time: 0.083185 memory: 9871 loss_kpt: 0.000655 acc_pose: 0.803559 loss: 0.000655 2022/09/13 14:41:14 - mmengine - INFO - Epoch(train) [58][100/293] lr: 5.000000e-04 eta: 5:22:46 time: 0.504520 data_time: 0.074144 memory: 9871 loss_kpt: 0.000649 acc_pose: 0.828010 loss: 0.000649 2022/09/13 14:41:38 - mmengine - INFO - Epoch(train) [58][150/293] lr: 5.000000e-04 eta: 5:22:32 time: 0.497582 data_time: 0.081315 memory: 9871 loss_kpt: 0.000636 acc_pose: 0.772844 loss: 0.000636 2022/09/13 14:42:04 - mmengine - INFO - Epoch(train) [58][200/293] lr: 5.000000e-04 eta: 5:22:21 time: 0.508006 data_time: 0.080737 memory: 9871 loss_kpt: 0.000630 acc_pose: 0.829299 loss: 0.000630 2022/09/13 14:42:29 - mmengine - INFO - Epoch(train) [58][250/293] lr: 5.000000e-04 eta: 5:22:08 time: 0.503779 data_time: 0.080902 memory: 9871 loss_kpt: 0.000631 acc_pose: 0.817733 loss: 0.000631 2022/09/13 14:42:51 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 14:42:51 - mmengine - INFO - Saving checkpoint at 58 epochs 2022/09/13 14:42:59 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 14:43:21 - mmengine - INFO - Epoch(train) [59][50/293] lr: 5.000000e-04 eta: 5:20:49 time: 0.504808 data_time: 0.085481 memory: 9871 loss_kpt: 0.000642 acc_pose: 0.837691 loss: 0.000642 2022/09/13 14:43:46 - mmengine - INFO - Epoch(train) [59][100/293] lr: 5.000000e-04 eta: 5:20:37 time: 0.508805 data_time: 0.083438 memory: 9871 loss_kpt: 0.000646 acc_pose: 0.802670 loss: 0.000646 2022/09/13 14:44:11 - mmengine - INFO - Epoch(train) [59][150/293] lr: 5.000000e-04 eta: 5:20:25 time: 0.506897 data_time: 0.077882 memory: 9871 loss_kpt: 0.000658 acc_pose: 0.798910 loss: 0.000658 2022/09/13 14:44:36 - mmengine - INFO - Epoch(train) [59][200/293] lr: 5.000000e-04 eta: 5:20:11 time: 0.494385 data_time: 0.075720 memory: 9871 loss_kpt: 0.000638 acc_pose: 0.777516 loss: 0.000638 2022/09/13 14:45:01 - mmengine - INFO - Epoch(train) [59][250/293] lr: 5.000000e-04 eta: 5:19:59 time: 0.505982 data_time: 0.077548 memory: 9871 loss_kpt: 0.000641 acc_pose: 0.819112 loss: 0.000641 2022/09/13 14:45:22 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 14:45:23 - mmengine - INFO - Saving checkpoint at 59 epochs 2022/09/13 14:45:52 - mmengine - INFO - Epoch(train) [60][50/293] lr: 5.000000e-04 eta: 5:18:40 time: 0.504161 data_time: 0.085211 memory: 9871 loss_kpt: 0.000646 acc_pose: 0.801551 loss: 0.000646 2022/09/13 14:46:18 - mmengine - INFO - Epoch(train) [60][100/293] lr: 5.000000e-04 eta: 5:18:28 time: 0.507312 data_time: 0.082288 memory: 9871 loss_kpt: 0.000635 acc_pose: 0.816503 loss: 0.000635 2022/09/13 14:46:42 - mmengine - INFO - Epoch(train) [60][150/293] lr: 5.000000e-04 eta: 5:18:14 time: 0.495521 data_time: 0.079770 memory: 9871 loss_kpt: 0.000658 acc_pose: 0.793195 loss: 0.000658 2022/09/13 14:47:08 - mmengine - INFO - Epoch(train) [60][200/293] lr: 5.000000e-04 eta: 5:18:02 time: 0.506417 data_time: 0.073375 memory: 9871 loss_kpt: 0.000638 acc_pose: 0.831694 loss: 0.000638 2022/09/13 14:47:33 - mmengine - INFO - Epoch(train) [60][250/293] lr: 5.000000e-04 eta: 5:17:48 time: 0.498385 data_time: 0.076747 memory: 9871 loss_kpt: 0.000639 acc_pose: 0.794683 loss: 0.000639 2022/09/13 14:47:54 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 14:47:54 - mmengine - INFO - Saving checkpoint at 60 epochs 2022/09/13 14:48:07 - mmengine - INFO - Epoch(val) [60][50/407] eta: 0:00:58 time: 0.165172 data_time: 0.012596 memory: 9871 2022/09/13 14:48:15 - mmengine - INFO - Epoch(val) [60][100/407] eta: 0:00:50 time: 0.162899 data_time: 0.010746 memory: 920 2022/09/13 14:48:23 - mmengine - INFO - Epoch(val) [60][150/407] eta: 0:00:43 time: 0.167598 data_time: 0.015596 memory: 920 2022/09/13 14:48:31 - mmengine - INFO - Epoch(val) [60][200/407] eta: 0:00:32 time: 0.158556 data_time: 0.008160 memory: 920 2022/09/13 14:48:39 - mmengine - INFO - Epoch(val) [60][250/407] eta: 0:00:24 time: 0.157764 data_time: 0.007834 memory: 920 2022/09/13 14:48:47 - mmengine - INFO - Epoch(val) [60][300/407] eta: 0:00:17 time: 0.163282 data_time: 0.012216 memory: 920 2022/09/13 14:48:55 - mmengine - INFO - Epoch(val) [60][350/407] eta: 0:00:09 time: 0.159880 data_time: 0.007990 memory: 920 2022/09/13 14:49:03 - mmengine - INFO - Epoch(val) [60][400/407] eta: 0:00:01 time: 0.156433 data_time: 0.007045 memory: 920 2022/09/13 14:49:40 - mmengine - INFO - Evaluating CocoMetric... 2022/09/13 14:49:53 - mmengine - INFO - Epoch(val) [60][407/407] coco/AP: 0.724758 coco/AP .5: 0.893100 coco/AP .75: 0.795013 coco/AP (M): 0.690984 coco/AP (L): 0.789297 coco/AR: 0.780195 coco/AR .5: 0.933407 coco/AR .75: 0.844616 coco/AR (M): 0.739907 coco/AR (L): 0.838536 2022/09/13 14:49:53 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220913/dark_w32_256_v1/best_coco/AP_epoch_50.pth is removed 2022/09/13 14:49:57 - mmengine - INFO - The best checkpoint with 0.7248 coco/AP at 60 epoch is saved to best_coco/AP_epoch_60.pth. 2022/09/13 14:50:22 - mmengine - INFO - Epoch(train) [61][50/293] lr: 5.000000e-04 eta: 5:16:31 time: 0.512886 data_time: 0.085955 memory: 9871 loss_kpt: 0.000626 acc_pose: 0.802436 loss: 0.000626 2022/09/13 14:50:47 - mmengine - INFO - Epoch(train) [61][100/293] lr: 5.000000e-04 eta: 5:16:17 time: 0.491644 data_time: 0.075200 memory: 9871 loss_kpt: 0.000628 acc_pose: 0.793279 loss: 0.000628 2022/09/13 14:51:13 - mmengine - INFO - Epoch(train) [61][150/293] lr: 5.000000e-04 eta: 5:16:05 time: 0.514045 data_time: 0.076831 memory: 9871 loss_kpt: 0.000648 acc_pose: 0.807438 loss: 0.000648 2022/09/13 14:51:37 - mmengine - INFO - Epoch(train) [61][200/293] lr: 5.000000e-04 eta: 5:15:51 time: 0.492340 data_time: 0.074453 memory: 9871 loss_kpt: 0.000637 acc_pose: 0.818826 loss: 0.000637 2022/09/13 14:52:03 - mmengine - INFO - Epoch(train) [61][250/293] lr: 5.000000e-04 eta: 5:15:39 time: 0.508490 data_time: 0.080047 memory: 9871 loss_kpt: 0.000660 acc_pose: 0.792141 loss: 0.000660 2022/09/13 14:52:24 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 14:52:24 - mmengine - INFO - Saving checkpoint at 61 epochs 2022/09/13 14:52:53 - mmengine - INFO - Epoch(train) [62][50/293] lr: 5.000000e-04 eta: 5:14:21 time: 0.497902 data_time: 0.082158 memory: 9871 loss_kpt: 0.000641 acc_pose: 0.844294 loss: 0.000641 2022/09/13 14:53:18 - mmengine - INFO - Epoch(train) [62][100/293] lr: 5.000000e-04 eta: 5:14:08 time: 0.502699 data_time: 0.072959 memory: 9871 loss_kpt: 0.000646 acc_pose: 0.793876 loss: 0.000646 2022/09/13 14:53:32 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 14:53:44 - mmengine - INFO - Epoch(train) [62][150/293] lr: 5.000000e-04 eta: 5:13:55 time: 0.510256 data_time: 0.080233 memory: 9871 loss_kpt: 0.000637 acc_pose: 0.829067 loss: 0.000637 2022/09/13 14:54:09 - mmengine - INFO - Epoch(train) [62][200/293] lr: 5.000000e-04 eta: 5:13:42 time: 0.505965 data_time: 0.086841 memory: 9871 loss_kpt: 0.000636 acc_pose: 0.828048 loss: 0.000636 2022/09/13 14:54:34 - mmengine - INFO - Epoch(train) [62][250/293] lr: 5.000000e-04 eta: 5:13:28 time: 0.493916 data_time: 0.074040 memory: 9871 loss_kpt: 0.000634 acc_pose: 0.802096 loss: 0.000634 2022/09/13 14:54:55 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 14:54:55 - mmengine - INFO - Saving checkpoint at 62 epochs 2022/09/13 14:55:25 - mmengine - INFO - Epoch(train) [63][50/293] lr: 5.000000e-04 eta: 5:12:13 time: 0.512483 data_time: 0.086746 memory: 9871 loss_kpt: 0.000620 acc_pose: 0.853813 loss: 0.000620 2022/09/13 14:55:49 - mmengine - INFO - Epoch(train) [63][100/293] lr: 5.000000e-04 eta: 5:11:58 time: 0.490314 data_time: 0.077602 memory: 9871 loss_kpt: 0.000656 acc_pose: 0.843708 loss: 0.000656 2022/09/13 14:56:14 - mmengine - INFO - Epoch(train) [63][150/293] lr: 5.000000e-04 eta: 5:11:44 time: 0.500123 data_time: 0.075397 memory: 9871 loss_kpt: 0.000642 acc_pose: 0.812529 loss: 0.000642 2022/09/13 14:56:39 - mmengine - INFO - Epoch(train) [63][200/293] lr: 5.000000e-04 eta: 5:11:31 time: 0.503175 data_time: 0.081354 memory: 9871 loss_kpt: 0.000646 acc_pose: 0.808690 loss: 0.000646 2022/09/13 14:57:04 - mmengine - INFO - Epoch(train) [63][250/293] lr: 5.000000e-04 eta: 5:11:17 time: 0.501366 data_time: 0.077026 memory: 9871 loss_kpt: 0.000632 acc_pose: 0.801499 loss: 0.000632 2022/09/13 14:57:26 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 14:57:26 - mmengine - INFO - Saving checkpoint at 63 epochs 2022/09/13 14:57:55 - mmengine - INFO - Epoch(train) [64][50/293] lr: 5.000000e-04 eta: 5:10:02 time: 0.499992 data_time: 0.086218 memory: 9871 loss_kpt: 0.000639 acc_pose: 0.857711 loss: 0.000639 2022/09/13 14:58:20 - mmengine - INFO - Epoch(train) [64][100/293] lr: 5.000000e-04 eta: 5:09:48 time: 0.503581 data_time: 0.079868 memory: 9871 loss_kpt: 0.000621 acc_pose: 0.833996 loss: 0.000621 2022/09/13 14:58:45 - mmengine - INFO - Epoch(train) [64][150/293] lr: 5.000000e-04 eta: 5:09:35 time: 0.504811 data_time: 0.079094 memory: 9871 loss_kpt: 0.000639 acc_pose: 0.841982 loss: 0.000639 2022/09/13 14:59:10 - mmengine - INFO - Epoch(train) [64][200/293] lr: 5.000000e-04 eta: 5:09:21 time: 0.495656 data_time: 0.081063 memory: 9871 loss_kpt: 0.000629 acc_pose: 0.794794 loss: 0.000629 2022/09/13 14:59:35 - mmengine - INFO - Epoch(train) [64][250/293] lr: 5.000000e-04 eta: 5:09:05 time: 0.490208 data_time: 0.073545 memory: 9871 loss_kpt: 0.000637 acc_pose: 0.774061 loss: 0.000637 2022/09/13 14:59:56 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 14:59:56 - mmengine - INFO - Saving checkpoint at 64 epochs 2022/09/13 15:00:26 - mmengine - INFO - Epoch(train) [65][50/293] lr: 5.000000e-04 eta: 5:07:52 time: 0.516198 data_time: 0.082432 memory: 9871 loss_kpt: 0.000644 acc_pose: 0.805734 loss: 0.000644 2022/09/13 15:00:51 - mmengine - INFO - Epoch(train) [65][100/293] lr: 5.000000e-04 eta: 5:07:38 time: 0.499044 data_time: 0.077708 memory: 9871 loss_kpt: 0.000638 acc_pose: 0.786649 loss: 0.000638 2022/09/13 15:01:17 - mmengine - INFO - Epoch(train) [65][150/293] lr: 5.000000e-04 eta: 5:07:25 time: 0.507038 data_time: 0.080484 memory: 9871 loss_kpt: 0.000625 acc_pose: 0.842167 loss: 0.000625 2022/09/13 15:01:42 - mmengine - INFO - Epoch(train) [65][200/293] lr: 5.000000e-04 eta: 5:07:11 time: 0.499720 data_time: 0.082489 memory: 9871 loss_kpt: 0.000637 acc_pose: 0.806881 loss: 0.000637 2022/09/13 15:02:05 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 15:02:06 - mmengine - INFO - Epoch(train) [65][250/293] lr: 5.000000e-04 eta: 5:06:56 time: 0.493458 data_time: 0.072204 memory: 9871 loss_kpt: 0.000649 acc_pose: 0.858423 loss: 0.000649 2022/09/13 15:02:28 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 15:02:28 - mmengine - INFO - Saving checkpoint at 65 epochs 2022/09/13 15:02:59 - mmengine - INFO - Epoch(train) [66][50/293] lr: 5.000000e-04 eta: 5:05:44 time: 0.519561 data_time: 0.086990 memory: 9871 loss_kpt: 0.000634 acc_pose: 0.833257 loss: 0.000634 2022/09/13 15:03:24 - mmengine - INFO - Epoch(train) [66][100/293] lr: 5.000000e-04 eta: 5:05:31 time: 0.509926 data_time: 0.075079 memory: 9871 loss_kpt: 0.000619 acc_pose: 0.799805 loss: 0.000619 2022/09/13 15:03:49 - mmengine - INFO - Epoch(train) [66][150/293] lr: 5.000000e-04 eta: 5:05:16 time: 0.492959 data_time: 0.072038 memory: 9871 loss_kpt: 0.000620 acc_pose: 0.837527 loss: 0.000620 2022/09/13 15:04:14 - mmengine - INFO - Epoch(train) [66][200/293] lr: 5.000000e-04 eta: 5:05:01 time: 0.497699 data_time: 0.084421 memory: 9871 loss_kpt: 0.000639 acc_pose: 0.843153 loss: 0.000639 2022/09/13 15:04:38 - mmengine - INFO - Epoch(train) [66][250/293] lr: 5.000000e-04 eta: 5:04:46 time: 0.493500 data_time: 0.077174 memory: 9871 loss_kpt: 0.000624 acc_pose: 0.802946 loss: 0.000624 2022/09/13 15:05:00 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 15:05:00 - mmengine - INFO - Saving checkpoint at 66 epochs 2022/09/13 15:05:30 - mmengine - INFO - Epoch(train) [67][50/293] lr: 5.000000e-04 eta: 5:03:34 time: 0.507849 data_time: 0.089086 memory: 9871 loss_kpt: 0.000634 acc_pose: 0.810347 loss: 0.000634 2022/09/13 15:05:54 - mmengine - INFO - Epoch(train) [67][100/293] lr: 5.000000e-04 eta: 5:03:19 time: 0.493094 data_time: 0.079077 memory: 9871 loss_kpt: 0.000643 acc_pose: 0.794072 loss: 0.000643 2022/09/13 15:06:19 - mmengine - INFO - Epoch(train) [67][150/293] lr: 5.000000e-04 eta: 5:03:04 time: 0.499252 data_time: 0.079138 memory: 9871 loss_kpt: 0.000641 acc_pose: 0.790388 loss: 0.000641 2022/09/13 15:06:45 - mmengine - INFO - Epoch(train) [67][200/293] lr: 5.000000e-04 eta: 5:02:51 time: 0.511123 data_time: 0.074553 memory: 9871 loss_kpt: 0.000626 acc_pose: 0.798169 loss: 0.000626 2022/09/13 15:07:10 - mmengine - INFO - Epoch(train) [67][250/293] lr: 5.000000e-04 eta: 5:02:37 time: 0.505392 data_time: 0.082236 memory: 9871 loss_kpt: 0.000633 acc_pose: 0.841724 loss: 0.000633 2022/09/13 15:07:32 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 15:07:32 - mmengine - INFO - Saving checkpoint at 67 epochs 2022/09/13 15:08:02 - mmengine - INFO - Epoch(train) [68][50/293] lr: 5.000000e-04 eta: 5:01:24 time: 0.495307 data_time: 0.083768 memory: 9871 loss_kpt: 0.000634 acc_pose: 0.841929 loss: 0.000634 2022/09/13 15:08:27 - mmengine - INFO - Epoch(train) [68][100/293] lr: 5.000000e-04 eta: 5:01:09 time: 0.492559 data_time: 0.073521 memory: 9871 loss_kpt: 0.000638 acc_pose: 0.839456 loss: 0.000638 2022/09/13 15:08:53 - mmengine - INFO - Epoch(train) [68][150/293] lr: 5.000000e-04 eta: 5:00:56 time: 0.513042 data_time: 0.079855 memory: 9871 loss_kpt: 0.000622 acc_pose: 0.856335 loss: 0.000622 2022/09/13 15:09:18 - mmengine - INFO - Epoch(train) [68][200/293] lr: 5.000000e-04 eta: 5:00:42 time: 0.509122 data_time: 0.082434 memory: 9871 loss_kpt: 0.000623 acc_pose: 0.865080 loss: 0.000623 2022/09/13 15:09:43 - mmengine - INFO - Epoch(train) [68][250/293] lr: 5.000000e-04 eta: 5:00:28 time: 0.500052 data_time: 0.080911 memory: 9871 loss_kpt: 0.000637 acc_pose: 0.768855 loss: 0.000637 2022/09/13 15:10:04 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 15:10:04 - mmengine - INFO - Saving checkpoint at 68 epochs 2022/09/13 15:10:34 - mmengine - INFO - Epoch(train) [69][50/293] lr: 5.000000e-04 eta: 4:59:16 time: 0.502077 data_time: 0.087154 memory: 9871 loss_kpt: 0.000631 acc_pose: 0.819424 loss: 0.000631 2022/09/13 15:10:46 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 15:10:59 - mmengine - INFO - Epoch(train) [69][100/293] lr: 5.000000e-04 eta: 4:59:02 time: 0.501724 data_time: 0.072402 memory: 9871 loss_kpt: 0.000623 acc_pose: 0.803067 loss: 0.000623 2022/09/13 15:11:24 - mmengine - INFO - Epoch(train) [69][150/293] lr: 5.000000e-04 eta: 4:58:47 time: 0.501720 data_time: 0.077567 memory: 9871 loss_kpt: 0.000633 acc_pose: 0.812318 loss: 0.000633 2022/09/13 15:11:49 - mmengine - INFO - Epoch(train) [69][200/293] lr: 5.000000e-04 eta: 4:58:32 time: 0.494103 data_time: 0.086389 memory: 9871 loss_kpt: 0.000619 acc_pose: 0.762212 loss: 0.000619 2022/09/13 15:12:14 - mmengine - INFO - Epoch(train) [69][250/293] lr: 5.000000e-04 eta: 4:58:17 time: 0.497912 data_time: 0.077057 memory: 9871 loss_kpt: 0.000637 acc_pose: 0.812244 loss: 0.000637 2022/09/13 15:12:35 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 15:12:35 - mmengine - INFO - Saving checkpoint at 69 epochs 2022/09/13 15:13:05 - mmengine - INFO - Epoch(train) [70][50/293] lr: 5.000000e-04 eta: 4:57:07 time: 0.512330 data_time: 0.082379 memory: 9871 loss_kpt: 0.000626 acc_pose: 0.855664 loss: 0.000626 2022/09/13 15:13:30 - mmengine - INFO - Epoch(train) [70][100/293] lr: 5.000000e-04 eta: 4:56:52 time: 0.502999 data_time: 0.075866 memory: 9871 loss_kpt: 0.000628 acc_pose: 0.837925 loss: 0.000628 2022/09/13 15:13:55 - mmengine - INFO - Epoch(train) [70][150/293] lr: 5.000000e-04 eta: 4:56:38 time: 0.499025 data_time: 0.078911 memory: 9871 loss_kpt: 0.000624 acc_pose: 0.846161 loss: 0.000624 2022/09/13 15:14:20 - mmengine - INFO - Epoch(train) [70][200/293] lr: 5.000000e-04 eta: 4:56:23 time: 0.502581 data_time: 0.078238 memory: 9871 loss_kpt: 0.000638 acc_pose: 0.780286 loss: 0.000638 2022/09/13 15:14:45 - mmengine - INFO - Epoch(train) [70][250/293] lr: 5.000000e-04 eta: 4:56:07 time: 0.492721 data_time: 0.078189 memory: 9871 loss_kpt: 0.000627 acc_pose: 0.775193 loss: 0.000627 2022/09/13 15:15:06 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 15:15:06 - mmengine - INFO - Saving checkpoint at 70 epochs 2022/09/13 15:15:19 - mmengine - INFO - Epoch(val) [70][50/407] eta: 0:01:00 time: 0.168562 data_time: 0.013260 memory: 9871 2022/09/13 15:15:27 - mmengine - INFO - Epoch(val) [70][100/407] eta: 0:00:49 time: 0.160802 data_time: 0.008011 memory: 920 2022/09/13 15:15:35 - mmengine - INFO - Epoch(val) [70][150/407] eta: 0:00:41 time: 0.159681 data_time: 0.008104 memory: 920 2022/09/13 15:15:43 - mmengine - INFO - Epoch(val) [70][200/407] eta: 0:00:32 time: 0.156753 data_time: 0.008195 memory: 920 2022/09/13 15:15:51 - mmengine - INFO - Epoch(val) [70][250/407] eta: 0:00:25 time: 0.163680 data_time: 0.008027 memory: 920 2022/09/13 15:15:59 - mmengine - INFO - Epoch(val) [70][300/407] eta: 0:00:16 time: 0.157395 data_time: 0.008179 memory: 920 2022/09/13 15:16:07 - mmengine - INFO - Epoch(val) [70][350/407] eta: 0:00:09 time: 0.162788 data_time: 0.009158 memory: 920 2022/09/13 15:16:15 - mmengine - INFO - Epoch(val) [70][400/407] eta: 0:00:01 time: 0.154448 data_time: 0.007343 memory: 920 2022/09/13 15:16:51 - mmengine - INFO - Evaluating CocoMetric... 2022/09/13 15:17:04 - mmengine - INFO - Epoch(val) [70][407/407] coco/AP: 0.727744 coco/AP .5: 0.893727 coco/AP .75: 0.797834 coco/AP (M): 0.691904 coco/AP (L): 0.795533 coco/AR: 0.781596 coco/AR .5: 0.933722 coco/AR .75: 0.844931 coco/AR (M): 0.739361 coco/AR (L): 0.842735 2022/09/13 15:17:05 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220913/dark_w32_256_v1/best_coco/AP_epoch_60.pth is removed 2022/09/13 15:17:07 - mmengine - INFO - The best checkpoint with 0.7277 coco/AP at 70 epoch is saved to best_coco/AP_epoch_70.pth. 2022/09/13 15:17:33 - mmengine - INFO - Epoch(train) [71][50/293] lr: 5.000000e-04 eta: 4:54:58 time: 0.513227 data_time: 0.090199 memory: 9871 loss_kpt: 0.000628 acc_pose: 0.844923 loss: 0.000628 2022/09/13 15:17:58 - mmengine - INFO - Epoch(train) [71][100/293] lr: 5.000000e-04 eta: 4:54:43 time: 0.495437 data_time: 0.070475 memory: 9871 loss_kpt: 0.000618 acc_pose: 0.828335 loss: 0.000618 2022/09/13 15:18:22 - mmengine - INFO - Epoch(train) [71][150/293] lr: 5.000000e-04 eta: 4:54:27 time: 0.491528 data_time: 0.076947 memory: 9871 loss_kpt: 0.000619 acc_pose: 0.837248 loss: 0.000619 2022/09/13 15:18:47 - mmengine - INFO - Epoch(train) [71][200/293] lr: 5.000000e-04 eta: 4:54:12 time: 0.493967 data_time: 0.076332 memory: 9871 loss_kpt: 0.000625 acc_pose: 0.816693 loss: 0.000625 2022/09/13 15:19:12 - mmengine - INFO - Epoch(train) [71][250/293] lr: 5.000000e-04 eta: 4:53:56 time: 0.494595 data_time: 0.075504 memory: 9871 loss_kpt: 0.000626 acc_pose: 0.809056 loss: 0.000626 2022/09/13 15:19:33 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 15:19:33 - mmengine - INFO - Saving checkpoint at 71 epochs 2022/09/13 15:20:03 - mmengine - INFO - Epoch(train) [72][50/293] lr: 5.000000e-04 eta: 4:52:47 time: 0.513009 data_time: 0.077289 memory: 9871 loss_kpt: 0.000624 acc_pose: 0.841369 loss: 0.000624 2022/09/13 15:20:29 - mmengine - INFO - Epoch(train) [72][100/293] lr: 5.000000e-04 eta: 4:52:33 time: 0.506588 data_time: 0.074099 memory: 9871 loss_kpt: 0.000619 acc_pose: 0.808836 loss: 0.000619 2022/09/13 15:20:53 - mmengine - INFO - Epoch(train) [72][150/293] lr: 5.000000e-04 eta: 4:52:17 time: 0.493412 data_time: 0.070106 memory: 9871 loss_kpt: 0.000620 acc_pose: 0.819066 loss: 0.000620 2022/09/13 15:21:17 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 15:21:18 - mmengine - INFO - Epoch(train) [72][200/293] lr: 5.000000e-04 eta: 4:52:02 time: 0.497871 data_time: 0.075058 memory: 9871 loss_kpt: 0.000625 acc_pose: 0.844646 loss: 0.000625 2022/09/13 15:21:43 - mmengine - INFO - Epoch(train) [72][250/293] lr: 5.000000e-04 eta: 4:51:46 time: 0.493543 data_time: 0.075864 memory: 9871 loss_kpt: 0.000647 acc_pose: 0.817338 loss: 0.000647 2022/09/13 15:22:04 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 15:22:04 - mmengine - INFO - Saving checkpoint at 72 epochs 2022/09/13 15:22:35 - mmengine - INFO - Epoch(train) [73][50/293] lr: 5.000000e-04 eta: 4:50:39 time: 0.524370 data_time: 0.079719 memory: 9871 loss_kpt: 0.000603 acc_pose: 0.848421 loss: 0.000603 2022/09/13 15:23:00 - mmengine - INFO - Epoch(train) [73][100/293] lr: 5.000000e-04 eta: 4:50:24 time: 0.495483 data_time: 0.075614 memory: 9871 loss_kpt: 0.000619 acc_pose: 0.825475 loss: 0.000619 2022/09/13 15:23:24 - mmengine - INFO - Epoch(train) [73][150/293] lr: 5.000000e-04 eta: 4:50:08 time: 0.490036 data_time: 0.075646 memory: 9871 loss_kpt: 0.000611 acc_pose: 0.834757 loss: 0.000611 2022/09/13 15:23:49 - mmengine - INFO - Epoch(train) [73][200/293] lr: 5.000000e-04 eta: 4:49:52 time: 0.490206 data_time: 0.074857 memory: 9871 loss_kpt: 0.000640 acc_pose: 0.775571 loss: 0.000640 2022/09/13 15:24:14 - mmengine - INFO - Epoch(train) [73][250/293] lr: 5.000000e-04 eta: 4:49:37 time: 0.504830 data_time: 0.080098 memory: 9871 loss_kpt: 0.000631 acc_pose: 0.832086 loss: 0.000631 2022/09/13 15:24:36 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 15:24:36 - mmengine - INFO - Saving checkpoint at 73 epochs 2022/09/13 15:25:06 - mmengine - INFO - Epoch(train) [74][50/293] lr: 5.000000e-04 eta: 4:48:29 time: 0.511587 data_time: 0.083512 memory: 9871 loss_kpt: 0.000614 acc_pose: 0.824280 loss: 0.000614 2022/09/13 15:25:31 - mmengine - INFO - Epoch(train) [74][100/293] lr: 5.000000e-04 eta: 4:48:15 time: 0.510435 data_time: 0.077774 memory: 9871 loss_kpt: 0.000630 acc_pose: 0.785974 loss: 0.000630 2022/09/13 15:25:56 - mmengine - INFO - Epoch(train) [74][150/293] lr: 5.000000e-04 eta: 4:48:00 time: 0.503241 data_time: 0.075537 memory: 9871 loss_kpt: 0.000616 acc_pose: 0.825199 loss: 0.000616 2022/09/13 15:26:21 - mmengine - INFO - Epoch(train) [74][200/293] lr: 5.000000e-04 eta: 4:47:44 time: 0.488511 data_time: 0.076816 memory: 9871 loss_kpt: 0.000617 acc_pose: 0.802235 loss: 0.000617 2022/09/13 15:26:45 - mmengine - INFO - Epoch(train) [74][250/293] lr: 5.000000e-04 eta: 4:47:28 time: 0.493320 data_time: 0.073159 memory: 9871 loss_kpt: 0.000609 acc_pose: 0.800828 loss: 0.000609 2022/09/13 15:27:07 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 15:27:07 - mmengine - INFO - Saving checkpoint at 74 epochs 2022/09/13 15:27:37 - mmengine - INFO - Epoch(train) [75][50/293] lr: 5.000000e-04 eta: 4:46:21 time: 0.510153 data_time: 0.077699 memory: 9871 loss_kpt: 0.000629 acc_pose: 0.848295 loss: 0.000629 2022/09/13 15:28:02 - mmengine - INFO - Epoch(train) [75][100/293] lr: 5.000000e-04 eta: 4:46:06 time: 0.504735 data_time: 0.077346 memory: 9871 loss_kpt: 0.000631 acc_pose: 0.853375 loss: 0.000631 2022/09/13 15:28:27 - mmengine - INFO - Epoch(train) [75][150/293] lr: 5.000000e-04 eta: 4:45:51 time: 0.502960 data_time: 0.073953 memory: 9871 loss_kpt: 0.000613 acc_pose: 0.797551 loss: 0.000613 2022/09/13 15:28:52 - mmengine - INFO - Epoch(train) [75][200/293] lr: 5.000000e-04 eta: 4:45:34 time: 0.490169 data_time: 0.076312 memory: 9871 loss_kpt: 0.000626 acc_pose: 0.811268 loss: 0.000626 2022/09/13 15:29:16 - mmengine - INFO - Epoch(train) [75][250/293] lr: 5.000000e-04 eta: 4:45:18 time: 0.486915 data_time: 0.069981 memory: 9871 loss_kpt: 0.000607 acc_pose: 0.810662 loss: 0.000607 2022/09/13 15:29:39 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 15:29:39 - mmengine - INFO - Saving checkpoint at 75 epochs 2022/09/13 15:29:56 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 15:30:08 - mmengine - INFO - Epoch(train) [76][50/293] lr: 5.000000e-04 eta: 4:44:11 time: 0.508313 data_time: 0.080722 memory: 9871 loss_kpt: 0.000641 acc_pose: 0.846172 loss: 0.000641 2022/09/13 15:30:33 - mmengine - INFO - Epoch(train) [76][100/293] lr: 5.000000e-04 eta: 4:43:55 time: 0.500521 data_time: 0.075171 memory: 9871 loss_kpt: 0.000623 acc_pose: 0.807066 loss: 0.000623 2022/09/13 15:30:59 - mmengine - INFO - Epoch(train) [76][150/293] lr: 5.000000e-04 eta: 4:43:41 time: 0.508116 data_time: 0.078940 memory: 9871 loss_kpt: 0.000624 acc_pose: 0.801116 loss: 0.000624 2022/09/13 15:31:23 - mmengine - INFO - Epoch(train) [76][200/293] lr: 5.000000e-04 eta: 4:43:25 time: 0.495024 data_time: 0.076808 memory: 9871 loss_kpt: 0.000623 acc_pose: 0.787465 loss: 0.000623 2022/09/13 15:31:49 - mmengine - INFO - Epoch(train) [76][250/293] lr: 5.000000e-04 eta: 4:43:09 time: 0.503171 data_time: 0.075208 memory: 9871 loss_kpt: 0.000627 acc_pose: 0.802536 loss: 0.000627 2022/09/13 15:32:10 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 15:32:10 - mmengine - INFO - Saving checkpoint at 76 epochs 2022/09/13 15:32:40 - mmengine - INFO - Epoch(train) [77][50/293] lr: 5.000000e-04 eta: 4:42:04 time: 0.514277 data_time: 0.079838 memory: 9871 loss_kpt: 0.000617 acc_pose: 0.800312 loss: 0.000617 2022/09/13 15:33:06 - mmengine - INFO - Epoch(train) [77][100/293] lr: 5.000000e-04 eta: 4:41:49 time: 0.511846 data_time: 0.079044 memory: 9871 loss_kpt: 0.000613 acc_pose: 0.851904 loss: 0.000613 2022/09/13 15:33:30 - mmengine - INFO - Epoch(train) [77][150/293] lr: 5.000000e-04 eta: 4:41:33 time: 0.490691 data_time: 0.075225 memory: 9871 loss_kpt: 0.000614 acc_pose: 0.851251 loss: 0.000614 2022/09/13 15:33:56 - mmengine - INFO - Epoch(train) [77][200/293] lr: 5.000000e-04 eta: 4:41:18 time: 0.512317 data_time: 0.078442 memory: 9871 loss_kpt: 0.000616 acc_pose: 0.847766 loss: 0.000616 2022/09/13 15:34:21 - mmengine - INFO - Epoch(train) [77][250/293] lr: 5.000000e-04 eta: 4:41:03 time: 0.505946 data_time: 0.072359 memory: 9871 loss_kpt: 0.000632 acc_pose: 0.844534 loss: 0.000632 2022/09/13 15:34:43 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 15:34:43 - mmengine - INFO - Saving checkpoint at 77 epochs 2022/09/13 15:35:15 - mmengine - INFO - Epoch(train) [78][50/293] lr: 5.000000e-04 eta: 4:39:58 time: 0.520704 data_time: 0.080951 memory: 9871 loss_kpt: 0.000616 acc_pose: 0.791410 loss: 0.000616 2022/09/13 15:35:41 - mmengine - INFO - Epoch(train) [78][100/293] lr: 5.000000e-04 eta: 4:39:43 time: 0.506638 data_time: 0.083131 memory: 9871 loss_kpt: 0.000617 acc_pose: 0.831506 loss: 0.000617 2022/09/13 15:36:05 - mmengine - INFO - Epoch(train) [78][150/293] lr: 5.000000e-04 eta: 4:39:26 time: 0.489399 data_time: 0.075149 memory: 9871 loss_kpt: 0.000606 acc_pose: 0.775801 loss: 0.000606 2022/09/13 15:36:30 - mmengine - INFO - Epoch(train) [78][200/293] lr: 5.000000e-04 eta: 4:39:10 time: 0.494265 data_time: 0.078664 memory: 9871 loss_kpt: 0.000612 acc_pose: 0.847204 loss: 0.000612 2022/09/13 15:36:55 - mmengine - INFO - Epoch(train) [78][250/293] lr: 5.000000e-04 eta: 4:38:54 time: 0.498270 data_time: 0.070757 memory: 9871 loss_kpt: 0.000615 acc_pose: 0.820554 loss: 0.000615 2022/09/13 15:37:16 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 15:37:16 - mmengine - INFO - Saving checkpoint at 78 epochs 2022/09/13 15:37:46 - mmengine - INFO - Epoch(train) [79][50/293] lr: 5.000000e-04 eta: 4:37:49 time: 0.510007 data_time: 0.086740 memory: 9871 loss_kpt: 0.000609 acc_pose: 0.842701 loss: 0.000609 2022/09/13 15:38:12 - mmengine - INFO - Epoch(train) [79][100/293] lr: 5.000000e-04 eta: 4:37:34 time: 0.511738 data_time: 0.074928 memory: 9871 loss_kpt: 0.000611 acc_pose: 0.818607 loss: 0.000611 2022/09/13 15:38:35 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 15:38:37 - mmengine - INFO - Epoch(train) [79][150/293] lr: 5.000000e-04 eta: 4:37:19 time: 0.505659 data_time: 0.074172 memory: 9871 loss_kpt: 0.000615 acc_pose: 0.815173 loss: 0.000615 2022/09/13 15:39:02 - mmengine - INFO - Epoch(train) [79][200/293] lr: 5.000000e-04 eta: 4:37:03 time: 0.497276 data_time: 0.079956 memory: 9871 loss_kpt: 0.000630 acc_pose: 0.856065 loss: 0.000630 2022/09/13 15:39:27 - mmengine - INFO - Epoch(train) [79][250/293] lr: 5.000000e-04 eta: 4:36:46 time: 0.494359 data_time: 0.071663 memory: 9871 loss_kpt: 0.000613 acc_pose: 0.772944 loss: 0.000613 2022/09/13 15:39:48 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 15:39:48 - mmengine - INFO - Saving checkpoint at 79 epochs 2022/09/13 15:40:18 - mmengine - INFO - Epoch(train) [80][50/293] lr: 5.000000e-04 eta: 4:35:42 time: 0.508263 data_time: 0.078735 memory: 9871 loss_kpt: 0.000627 acc_pose: 0.871223 loss: 0.000627 2022/09/13 15:40:43 - mmengine - INFO - Epoch(train) [80][100/293] lr: 5.000000e-04 eta: 4:35:26 time: 0.499825 data_time: 0.076452 memory: 9871 loss_kpt: 0.000615 acc_pose: 0.833875 loss: 0.000615 2022/09/13 15:41:07 - mmengine - INFO - Epoch(train) [80][150/293] lr: 5.000000e-04 eta: 4:35:09 time: 0.492661 data_time: 0.073007 memory: 9871 loss_kpt: 0.000610 acc_pose: 0.794287 loss: 0.000610 2022/09/13 15:41:33 - mmengine - INFO - Epoch(train) [80][200/293] lr: 5.000000e-04 eta: 4:34:53 time: 0.503237 data_time: 0.074963 memory: 9871 loss_kpt: 0.000611 acc_pose: 0.786606 loss: 0.000611 2022/09/13 15:41:57 - mmengine - INFO - Epoch(train) [80][250/293] lr: 5.000000e-04 eta: 4:34:37 time: 0.494742 data_time: 0.074784 memory: 9871 loss_kpt: 0.000622 acc_pose: 0.818029 loss: 0.000622 2022/09/13 15:42:18 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 15:42:18 - mmengine - INFO - Saving checkpoint at 80 epochs 2022/09/13 15:42:32 - mmengine - INFO - Epoch(val) [80][50/407] eta: 0:01:00 time: 0.168745 data_time: 0.012765 memory: 9871 2022/09/13 15:42:40 - mmengine - INFO - Epoch(val) [80][100/407] eta: 0:00:49 time: 0.161179 data_time: 0.008115 memory: 920 2022/09/13 15:42:48 - mmengine - INFO - Epoch(val) [80][150/407] eta: 0:00:40 time: 0.159012 data_time: 0.008441 memory: 920 2022/09/13 15:42:56 - mmengine - INFO - Epoch(val) [80][200/407] eta: 0:00:34 time: 0.165140 data_time: 0.011682 memory: 920 2022/09/13 15:43:04 - mmengine - INFO - Epoch(val) [80][250/407] eta: 0:00:25 time: 0.161043 data_time: 0.008765 memory: 920 2022/09/13 15:43:12 - mmengine - INFO - Epoch(val) [80][300/407] eta: 0:00:17 time: 0.159760 data_time: 0.009125 memory: 920 2022/09/13 15:43:20 - mmengine - INFO - Epoch(val) [80][350/407] eta: 0:00:09 time: 0.159023 data_time: 0.007973 memory: 920 2022/09/13 15:43:28 - mmengine - INFO - Epoch(val) [80][400/407] eta: 0:00:01 time: 0.156283 data_time: 0.007587 memory: 920 2022/09/13 15:44:03 - mmengine - INFO - Evaluating CocoMetric... 2022/09/13 15:44:17 - mmengine - INFO - Epoch(val) [80][407/407] coco/AP: 0.736539 coco/AP .5: 0.898476 coco/AP .75: 0.803013 coco/AP (M): 0.701501 coco/AP (L): 0.802190 coco/AR: 0.788854 coco/AR .5: 0.937657 coco/AR .75: 0.849811 coco/AR (M): 0.747446 coco/AR (L): 0.848941 2022/09/13 15:44:17 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220913/dark_w32_256_v1/best_coco/AP_epoch_70.pth is removed 2022/09/13 15:44:21 - mmengine - INFO - The best checkpoint with 0.7365 coco/AP at 80 epoch is saved to best_coco/AP_epoch_80.pth. 2022/09/13 15:44:46 - mmengine - INFO - Epoch(train) [81][50/293] lr: 5.000000e-04 eta: 4:33:33 time: 0.508079 data_time: 0.078847 memory: 9871 loss_kpt: 0.000615 acc_pose: 0.795638 loss: 0.000615 2022/09/13 15:45:11 - mmengine - INFO - Epoch(train) [81][100/293] lr: 5.000000e-04 eta: 4:33:17 time: 0.500149 data_time: 0.079684 memory: 9871 loss_kpt: 0.000615 acc_pose: 0.820495 loss: 0.000615 2022/09/13 15:45:37 - mmengine - INFO - Epoch(train) [81][150/293] lr: 5.000000e-04 eta: 4:33:01 time: 0.508136 data_time: 0.074661 memory: 9871 loss_kpt: 0.000621 acc_pose: 0.844486 loss: 0.000621 2022/09/13 15:46:01 - mmengine - INFO - Epoch(train) [81][200/293] lr: 5.000000e-04 eta: 4:32:45 time: 0.495242 data_time: 0.070922 memory: 9871 loss_kpt: 0.000631 acc_pose: 0.802698 loss: 0.000631 2022/09/13 15:46:26 - mmengine - INFO - Epoch(train) [81][250/293] lr: 5.000000e-04 eta: 4:32:28 time: 0.497346 data_time: 0.072987 memory: 9871 loss_kpt: 0.000617 acc_pose: 0.815066 loss: 0.000617 2022/09/13 15:46:47 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 15:46:47 - mmengine - INFO - Saving checkpoint at 81 epochs 2022/09/13 15:47:18 - mmengine - INFO - Epoch(train) [82][50/293] lr: 5.000000e-04 eta: 4:31:24 time: 0.496269 data_time: 0.078314 memory: 9871 loss_kpt: 0.000600 acc_pose: 0.852908 loss: 0.000600 2022/09/13 15:47:44 - mmengine - INFO - Epoch(train) [82][100/293] lr: 5.000000e-04 eta: 4:31:09 time: 0.517796 data_time: 0.073385 memory: 9871 loss_kpt: 0.000611 acc_pose: 0.887256 loss: 0.000611 2022/09/13 15:48:09 - mmengine - INFO - Epoch(train) [82][150/293] lr: 5.000000e-04 eta: 4:30:53 time: 0.504986 data_time: 0.076506 memory: 9871 loss_kpt: 0.000622 acc_pose: 0.790940 loss: 0.000622 2022/09/13 15:48:34 - mmengine - INFO - Epoch(train) [82][200/293] lr: 5.000000e-04 eta: 4:30:37 time: 0.491835 data_time: 0.076795 memory: 9871 loss_kpt: 0.000609 acc_pose: 0.857958 loss: 0.000609 2022/09/13 15:48:58 - mmengine - INFO - Epoch(train) [82][250/293] lr: 5.000000e-04 eta: 4:30:20 time: 0.491602 data_time: 0.071180 memory: 9871 loss_kpt: 0.000622 acc_pose: 0.837573 loss: 0.000622 2022/09/13 15:49:06 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 15:49:19 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 15:49:19 - mmengine - INFO - Saving checkpoint at 82 epochs 2022/09/13 15:49:50 - mmengine - INFO - Epoch(train) [83][50/293] lr: 5.000000e-04 eta: 4:29:17 time: 0.518635 data_time: 0.080215 memory: 9871 loss_kpt: 0.000612 acc_pose: 0.835669 loss: 0.000612 2022/09/13 15:50:15 - mmengine - INFO - Epoch(train) [83][100/293] lr: 5.000000e-04 eta: 4:29:02 time: 0.510080 data_time: 0.080489 memory: 9871 loss_kpt: 0.000610 acc_pose: 0.788183 loss: 0.000610 2022/09/13 15:50:40 - mmengine - INFO - Epoch(train) [83][150/293] lr: 5.000000e-04 eta: 4:28:45 time: 0.494246 data_time: 0.076264 memory: 9871 loss_kpt: 0.000620 acc_pose: 0.773217 loss: 0.000620 2022/09/13 15:51:04 - mmengine - INFO - Epoch(train) [83][200/293] lr: 5.000000e-04 eta: 4:28:28 time: 0.485712 data_time: 0.071620 memory: 9871 loss_kpt: 0.000615 acc_pose: 0.850999 loss: 0.000615 2022/09/13 15:51:29 - mmengine - INFO - Epoch(train) [83][250/293] lr: 5.000000e-04 eta: 4:28:11 time: 0.492456 data_time: 0.079404 memory: 9871 loss_kpt: 0.000608 acc_pose: 0.843665 loss: 0.000608 2022/09/13 15:51:50 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 15:51:50 - mmengine - INFO - Saving checkpoint at 83 epochs 2022/09/13 15:52:21 - mmengine - INFO - Epoch(train) [84][50/293] lr: 5.000000e-04 eta: 4:27:09 time: 0.526344 data_time: 0.088173 memory: 9871 loss_kpt: 0.000623 acc_pose: 0.845832 loss: 0.000623 2022/09/13 15:52:46 - mmengine - INFO - Epoch(train) [84][100/293] lr: 5.000000e-04 eta: 4:26:54 time: 0.508656 data_time: 0.080750 memory: 9871 loss_kpt: 0.000621 acc_pose: 0.846982 loss: 0.000621 2022/09/13 15:53:11 - mmengine - INFO - Epoch(train) [84][150/293] lr: 5.000000e-04 eta: 4:26:37 time: 0.493909 data_time: 0.071515 memory: 9871 loss_kpt: 0.000608 acc_pose: 0.810104 loss: 0.000608 2022/09/13 15:53:36 - mmengine - INFO - Epoch(train) [84][200/293] lr: 5.000000e-04 eta: 4:26:20 time: 0.491063 data_time: 0.074303 memory: 9871 loss_kpt: 0.000605 acc_pose: 0.836778 loss: 0.000605 2022/09/13 15:54:01 - mmengine - INFO - Epoch(train) [84][250/293] lr: 5.000000e-04 eta: 4:26:04 time: 0.503448 data_time: 0.071604 memory: 9871 loss_kpt: 0.000615 acc_pose: 0.774050 loss: 0.000615 2022/09/13 15:54:22 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 15:54:22 - mmengine - INFO - Saving checkpoint at 84 epochs 2022/09/13 15:54:52 - mmengine - INFO - Epoch(train) [85][50/293] lr: 5.000000e-04 eta: 4:25:02 time: 0.513615 data_time: 0.083746 memory: 9871 loss_kpt: 0.000600 acc_pose: 0.780937 loss: 0.000600 2022/09/13 15:55:17 - mmengine - INFO - Epoch(train) [85][100/293] lr: 5.000000e-04 eta: 4:24:45 time: 0.491914 data_time: 0.071356 memory: 9871 loss_kpt: 0.000611 acc_pose: 0.778036 loss: 0.000611 2022/09/13 15:55:42 - mmengine - INFO - Epoch(train) [85][150/293] lr: 5.000000e-04 eta: 4:24:28 time: 0.499117 data_time: 0.079492 memory: 9871 loss_kpt: 0.000596 acc_pose: 0.838065 loss: 0.000596 2022/09/13 15:56:06 - mmengine - INFO - Epoch(train) [85][200/293] lr: 5.000000e-04 eta: 4:24:11 time: 0.493321 data_time: 0.071575 memory: 9871 loss_kpt: 0.000622 acc_pose: 0.785992 loss: 0.000622 2022/09/13 15:56:32 - mmengine - INFO - Epoch(train) [85][250/293] lr: 5.000000e-04 eta: 4:23:55 time: 0.506795 data_time: 0.075429 memory: 9871 loss_kpt: 0.000623 acc_pose: 0.795206 loss: 0.000623 2022/09/13 15:56:53 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 15:56:53 - mmengine - INFO - Saving checkpoint at 85 epochs 2022/09/13 15:57:23 - mmengine - INFO - Epoch(train) [86][50/293] lr: 5.000000e-04 eta: 4:22:53 time: 0.504574 data_time: 0.084449 memory: 9871 loss_kpt: 0.000606 acc_pose: 0.827070 loss: 0.000606 2022/09/13 15:57:45 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 15:57:48 - mmengine - INFO - Epoch(train) [86][100/293] lr: 5.000000e-04 eta: 4:22:36 time: 0.493324 data_time: 0.079697 memory: 9871 loss_kpt: 0.000612 acc_pose: 0.838982 loss: 0.000612 2022/09/13 15:58:13 - mmengine - INFO - Epoch(train) [86][150/293] lr: 5.000000e-04 eta: 4:22:19 time: 0.500160 data_time: 0.071311 memory: 9871 loss_kpt: 0.000610 acc_pose: 0.842665 loss: 0.000610 2022/09/13 15:58:38 - mmengine - INFO - Epoch(train) [86][200/293] lr: 5.000000e-04 eta: 4:22:03 time: 0.501971 data_time: 0.077465 memory: 9871 loss_kpt: 0.000610 acc_pose: 0.822982 loss: 0.000610 2022/09/13 15:59:03 - mmengine - INFO - Epoch(train) [86][250/293] lr: 5.000000e-04 eta: 4:21:47 time: 0.504221 data_time: 0.078019 memory: 9871 loss_kpt: 0.000609 acc_pose: 0.861211 loss: 0.000609 2022/09/13 15:59:24 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 15:59:24 - mmengine - INFO - Saving checkpoint at 86 epochs 2022/09/13 15:59:54 - mmengine - INFO - Epoch(train) [87][50/293] lr: 5.000000e-04 eta: 4:20:45 time: 0.504772 data_time: 0.083324 memory: 9871 loss_kpt: 0.000603 acc_pose: 0.797400 loss: 0.000603 2022/09/13 16:00:19 - mmengine - INFO - Epoch(train) [87][100/293] lr: 5.000000e-04 eta: 4:20:29 time: 0.505485 data_time: 0.076310 memory: 9871 loss_kpt: 0.000611 acc_pose: 0.781685 loss: 0.000611 2022/09/13 16:00:44 - mmengine - INFO - Epoch(train) [87][150/293] lr: 5.000000e-04 eta: 4:20:12 time: 0.500535 data_time: 0.076353 memory: 9871 loss_kpt: 0.000612 acc_pose: 0.838494 loss: 0.000612 2022/09/13 16:01:10 - mmengine - INFO - Epoch(train) [87][200/293] lr: 5.000000e-04 eta: 4:19:56 time: 0.507221 data_time: 0.081110 memory: 9871 loss_kpt: 0.000619 acc_pose: 0.856067 loss: 0.000619 2022/09/13 16:01:34 - mmengine - INFO - Epoch(train) [87][250/293] lr: 5.000000e-04 eta: 4:19:38 time: 0.489556 data_time: 0.071775 memory: 9871 loss_kpt: 0.000609 acc_pose: 0.823376 loss: 0.000609 2022/09/13 16:01:56 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 16:01:56 - mmengine - INFO - Saving checkpoint at 87 epochs 2022/09/13 16:02:25 - mmengine - INFO - Epoch(train) [88][50/293] lr: 5.000000e-04 eta: 4:18:37 time: 0.506827 data_time: 0.091397 memory: 9871 loss_kpt: 0.000600 acc_pose: 0.847543 loss: 0.000600 2022/09/13 16:02:50 - mmengine - INFO - Epoch(train) [88][100/293] lr: 5.000000e-04 eta: 4:18:21 time: 0.505775 data_time: 0.071027 memory: 9871 loss_kpt: 0.000617 acc_pose: 0.829113 loss: 0.000617 2022/09/13 16:03:16 - mmengine - INFO - Epoch(train) [88][150/293] lr: 5.000000e-04 eta: 4:18:05 time: 0.505519 data_time: 0.077688 memory: 9871 loss_kpt: 0.000614 acc_pose: 0.823516 loss: 0.000614 2022/09/13 16:03:41 - mmengine - INFO - Epoch(train) [88][200/293] lr: 5.000000e-04 eta: 4:17:49 time: 0.508009 data_time: 0.079850 memory: 9871 loss_kpt: 0.000613 acc_pose: 0.850107 loss: 0.000613 2022/09/13 16:04:06 - mmengine - INFO - Epoch(train) [88][250/293] lr: 5.000000e-04 eta: 4:17:31 time: 0.492353 data_time: 0.072680 memory: 9871 loss_kpt: 0.000611 acc_pose: 0.819461 loss: 0.000611 2022/09/13 16:04:27 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 16:04:27 - mmengine - INFO - Saving checkpoint at 88 epochs 2022/09/13 16:04:56 - mmengine - INFO - Epoch(train) [89][50/293] lr: 5.000000e-04 eta: 4:16:31 time: 0.509212 data_time: 0.079920 memory: 9871 loss_kpt: 0.000614 acc_pose: 0.816922 loss: 0.000614 2022/09/13 16:05:21 - mmengine - INFO - Epoch(train) [89][100/293] lr: 5.000000e-04 eta: 4:16:14 time: 0.495646 data_time: 0.070327 memory: 9871 loss_kpt: 0.000606 acc_pose: 0.825649 loss: 0.000606 2022/09/13 16:05:46 - mmengine - INFO - Epoch(train) [89][150/293] lr: 5.000000e-04 eta: 4:15:56 time: 0.495702 data_time: 0.076285 memory: 9871 loss_kpt: 0.000620 acc_pose: 0.817555 loss: 0.000620 2022/09/13 16:06:11 - mmengine - INFO - Epoch(train) [89][200/293] lr: 5.000000e-04 eta: 4:15:40 time: 0.506594 data_time: 0.075033 memory: 9871 loss_kpt: 0.000598 acc_pose: 0.817124 loss: 0.000598 2022/09/13 16:06:19 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 16:06:35 - mmengine - INFO - Epoch(train) [89][250/293] lr: 5.000000e-04 eta: 4:15:22 time: 0.481120 data_time: 0.072859 memory: 9871 loss_kpt: 0.000617 acc_pose: 0.840004 loss: 0.000617 2022/09/13 16:06:56 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 16:06:56 - mmengine - INFO - Saving checkpoint at 89 epochs 2022/09/13 16:07:26 - mmengine - INFO - Epoch(train) [90][50/293] lr: 5.000000e-04 eta: 4:14:22 time: 0.509405 data_time: 0.084426 memory: 9871 loss_kpt: 0.000613 acc_pose: 0.787446 loss: 0.000613 2022/09/13 16:07:52 - mmengine - INFO - Epoch(train) [90][100/293] lr: 5.000000e-04 eta: 4:14:05 time: 0.509168 data_time: 0.074199 memory: 9871 loss_kpt: 0.000615 acc_pose: 0.784413 loss: 0.000615 2022/09/13 16:08:17 - mmengine - INFO - Epoch(train) [90][150/293] lr: 5.000000e-04 eta: 4:13:49 time: 0.501011 data_time: 0.071300 memory: 9871 loss_kpt: 0.000605 acc_pose: 0.814447 loss: 0.000605 2022/09/13 16:08:42 - mmengine - INFO - Epoch(train) [90][200/293] lr: 5.000000e-04 eta: 4:13:31 time: 0.496100 data_time: 0.070980 memory: 9871 loss_kpt: 0.000626 acc_pose: 0.765282 loss: 0.000626 2022/09/13 16:09:06 - mmengine - INFO - Epoch(train) [90][250/293] lr: 5.000000e-04 eta: 4:13:14 time: 0.494298 data_time: 0.076985 memory: 9871 loss_kpt: 0.000600 acc_pose: 0.829661 loss: 0.000600 2022/09/13 16:09:27 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 16:09:27 - mmengine - INFO - Saving checkpoint at 90 epochs 2022/09/13 16:09:40 - mmengine - INFO - Epoch(val) [90][50/407] eta: 0:00:59 time: 0.165872 data_time: 0.013166 memory: 9871 2022/09/13 16:09:48 - mmengine - INFO - Epoch(val) [90][100/407] eta: 0:00:48 time: 0.159074 data_time: 0.008515 memory: 920 2022/09/13 16:09:56 - mmengine - INFO - Epoch(val) [90][150/407] eta: 0:00:40 time: 0.158576 data_time: 0.008135 memory: 920 2022/09/13 16:10:04 - mmengine - INFO - Epoch(val) [90][200/407] eta: 0:00:34 time: 0.167076 data_time: 0.012216 memory: 920 2022/09/13 16:10:12 - mmengine - INFO - Epoch(val) [90][250/407] eta: 0:00:25 time: 0.160153 data_time: 0.008126 memory: 920 2022/09/13 16:10:20 - mmengine - INFO - Epoch(val) [90][300/407] eta: 0:00:17 time: 0.159630 data_time: 0.008204 memory: 920 2022/09/13 16:10:28 - mmengine - INFO - Epoch(val) [90][350/407] eta: 0:00:08 time: 0.157810 data_time: 0.008057 memory: 920 2022/09/13 16:10:36 - mmengine - INFO - Epoch(val) [90][400/407] eta: 0:00:01 time: 0.155318 data_time: 0.007486 memory: 920 2022/09/13 16:11:12 - mmengine - INFO - Evaluating CocoMetric... 2022/09/13 16:11:26 - mmengine - INFO - Epoch(val) [90][407/407] coco/AP: 0.737096 coco/AP .5: 0.898387 coco/AP .75: 0.808796 coco/AP (M): 0.701112 coco/AP (L): 0.803054 coco/AR: 0.790098 coco/AR .5: 0.938602 coco/AR .75: 0.855479 coco/AR (M): 0.749741 coco/AR (L): 0.848718 2022/09/13 16:11:26 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220913/dark_w32_256_v1/best_coco/AP_epoch_80.pth is removed 2022/09/13 16:11:29 - mmengine - INFO - The best checkpoint with 0.7371 coco/AP at 90 epoch is saved to best_coco/AP_epoch_90.pth. 2022/09/13 16:11:54 - mmengine - INFO - Epoch(train) [91][50/293] lr: 5.000000e-04 eta: 4:12:14 time: 0.507608 data_time: 0.084255 memory: 9871 loss_kpt: 0.000599 acc_pose: 0.808782 loss: 0.000599 2022/09/13 16:12:20 - mmengine - INFO - Epoch(train) [91][100/293] lr: 5.000000e-04 eta: 4:11:58 time: 0.509062 data_time: 0.079637 memory: 9871 loss_kpt: 0.000621 acc_pose: 0.844908 loss: 0.000621 2022/09/13 16:12:45 - mmengine - INFO - Epoch(train) [91][150/293] lr: 5.000000e-04 eta: 4:11:41 time: 0.505357 data_time: 0.075147 memory: 9871 loss_kpt: 0.000617 acc_pose: 0.825274 loss: 0.000617 2022/09/13 16:13:10 - mmengine - INFO - Epoch(train) [91][200/293] lr: 5.000000e-04 eta: 4:11:24 time: 0.492534 data_time: 0.074464 memory: 9871 loss_kpt: 0.000610 acc_pose: 0.841981 loss: 0.000610 2022/09/13 16:13:34 - mmengine - INFO - Epoch(train) [91][250/293] lr: 5.000000e-04 eta: 4:11:06 time: 0.496305 data_time: 0.071930 memory: 9871 loss_kpt: 0.000620 acc_pose: 0.785770 loss: 0.000620 2022/09/13 16:13:56 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 16:13:56 - mmengine - INFO - Saving checkpoint at 91 epochs 2022/09/13 16:14:26 - mmengine - INFO - Epoch(train) [92][50/293] lr: 5.000000e-04 eta: 4:10:07 time: 0.512337 data_time: 0.081891 memory: 9871 loss_kpt: 0.000596 acc_pose: 0.789396 loss: 0.000596 2022/09/13 16:14:51 - mmengine - INFO - Epoch(train) [92][100/293] lr: 5.000000e-04 eta: 4:09:50 time: 0.496609 data_time: 0.079925 memory: 9871 loss_kpt: 0.000607 acc_pose: 0.837136 loss: 0.000607 2022/09/13 16:15:16 - mmengine - INFO - Epoch(train) [92][150/293] lr: 5.000000e-04 eta: 4:09:33 time: 0.505573 data_time: 0.079766 memory: 9871 loss_kpt: 0.000615 acc_pose: 0.842266 loss: 0.000615 2022/09/13 16:15:41 - mmengine - INFO - Epoch(train) [92][200/293] lr: 5.000000e-04 eta: 4:09:16 time: 0.498788 data_time: 0.075210 memory: 9871 loss_kpt: 0.000619 acc_pose: 0.817662 loss: 0.000619 2022/09/13 16:16:06 - mmengine - INFO - Epoch(train) [92][250/293] lr: 5.000000e-04 eta: 4:08:59 time: 0.502479 data_time: 0.072059 memory: 9871 loss_kpt: 0.000605 acc_pose: 0.877941 loss: 0.000605 2022/09/13 16:16:27 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 16:16:27 - mmengine - INFO - Saving checkpoint at 92 epochs 2022/09/13 16:16:54 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 16:16:56 - mmengine - INFO - Epoch(train) [93][50/293] lr: 5.000000e-04 eta: 4:08:00 time: 0.499466 data_time: 0.084748 memory: 9871 loss_kpt: 0.000597 acc_pose: 0.852769 loss: 0.000597 2022/09/13 16:17:22 - mmengine - INFO - Epoch(train) [93][100/293] lr: 5.000000e-04 eta: 4:07:43 time: 0.507800 data_time: 0.071480 memory: 9871 loss_kpt: 0.000599 acc_pose: 0.813172 loss: 0.000599 2022/09/13 16:17:47 - mmengine - INFO - Epoch(train) [93][150/293] lr: 5.000000e-04 eta: 4:07:26 time: 0.500453 data_time: 0.081927 memory: 9871 loss_kpt: 0.000607 acc_pose: 0.763026 loss: 0.000607 2022/09/13 16:18:12 - mmengine - INFO - Epoch(train) [93][200/293] lr: 5.000000e-04 eta: 4:07:09 time: 0.503355 data_time: 0.075106 memory: 9871 loss_kpt: 0.000597 acc_pose: 0.817665 loss: 0.000597 2022/09/13 16:18:37 - mmengine - INFO - Epoch(train) [93][250/293] lr: 5.000000e-04 eta: 4:06:52 time: 0.504267 data_time: 0.082091 memory: 9871 loss_kpt: 0.000605 acc_pose: 0.857464 loss: 0.000605 2022/09/13 16:18:58 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 16:18:58 - mmengine - INFO - Saving checkpoint at 93 epochs 2022/09/13 16:19:29 - mmengine - INFO - Epoch(train) [94][50/293] lr: 5.000000e-04 eta: 4:05:54 time: 0.515930 data_time: 0.087583 memory: 9871 loss_kpt: 0.000600 acc_pose: 0.801598 loss: 0.000600 2022/09/13 16:19:54 - mmengine - INFO - Epoch(train) [94][100/293] lr: 5.000000e-04 eta: 4:05:36 time: 0.499311 data_time: 0.076693 memory: 9871 loss_kpt: 0.000607 acc_pose: 0.830767 loss: 0.000607 2022/09/13 16:20:19 - mmengine - INFO - Epoch(train) [94][150/293] lr: 5.000000e-04 eta: 4:05:19 time: 0.503116 data_time: 0.074255 memory: 9871 loss_kpt: 0.000612 acc_pose: 0.848497 loss: 0.000612 2022/09/13 16:20:44 - mmengine - INFO - Epoch(train) [94][200/293] lr: 5.000000e-04 eta: 4:05:03 time: 0.509534 data_time: 0.075427 memory: 9871 loss_kpt: 0.000600 acc_pose: 0.811164 loss: 0.000600 2022/09/13 16:21:09 - mmengine - INFO - Epoch(train) [94][250/293] lr: 5.000000e-04 eta: 4:04:45 time: 0.501634 data_time: 0.080081 memory: 9871 loss_kpt: 0.000596 acc_pose: 0.827604 loss: 0.000596 2022/09/13 16:21:31 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 16:21:31 - mmengine - INFO - Saving checkpoint at 94 epochs 2022/09/13 16:22:01 - mmengine - INFO - Epoch(train) [95][50/293] lr: 5.000000e-04 eta: 4:03:47 time: 0.510843 data_time: 0.091968 memory: 9871 loss_kpt: 0.000596 acc_pose: 0.813554 loss: 0.000596 2022/09/13 16:22:26 - mmengine - INFO - Epoch(train) [95][100/293] lr: 5.000000e-04 eta: 4:03:30 time: 0.494829 data_time: 0.075674 memory: 9871 loss_kpt: 0.000601 acc_pose: 0.797818 loss: 0.000601 2022/09/13 16:22:50 - mmengine - INFO - Epoch(train) [95][150/293] lr: 5.000000e-04 eta: 4:03:12 time: 0.496491 data_time: 0.072488 memory: 9871 loss_kpt: 0.000612 acc_pose: 0.843538 loss: 0.000612 2022/09/13 16:23:16 - mmengine - INFO - Epoch(train) [95][200/293] lr: 5.000000e-04 eta: 4:02:55 time: 0.503744 data_time: 0.075717 memory: 9871 loss_kpt: 0.000619 acc_pose: 0.854683 loss: 0.000619 2022/09/13 16:23:41 - mmengine - INFO - Epoch(train) [95][250/293] lr: 5.000000e-04 eta: 4:02:38 time: 0.506052 data_time: 0.076302 memory: 9871 loss_kpt: 0.000601 acc_pose: 0.825634 loss: 0.000601 2022/09/13 16:24:03 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 16:24:03 - mmengine - INFO - Saving checkpoint at 95 epochs 2022/09/13 16:24:33 - mmengine - INFO - Epoch(train) [96][50/293] lr: 5.000000e-04 eta: 4:01:40 time: 0.509781 data_time: 0.081005 memory: 9871 loss_kpt: 0.000605 acc_pose: 0.826471 loss: 0.000605 2022/09/13 16:24:58 - mmengine - INFO - Epoch(train) [96][100/293] lr: 5.000000e-04 eta: 4:01:22 time: 0.497186 data_time: 0.073050 memory: 9871 loss_kpt: 0.000597 acc_pose: 0.855013 loss: 0.000597 2022/09/13 16:25:23 - mmengine - INFO - Epoch(train) [96][150/293] lr: 5.000000e-04 eta: 4:01:05 time: 0.492712 data_time: 0.070119 memory: 9871 loss_kpt: 0.000602 acc_pose: 0.838355 loss: 0.000602 2022/09/13 16:25:30 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 16:25:48 - mmengine - INFO - Epoch(train) [96][200/293] lr: 5.000000e-04 eta: 4:00:47 time: 0.501457 data_time: 0.070310 memory: 9871 loss_kpt: 0.000607 acc_pose: 0.798654 loss: 0.000607 2022/09/13 16:26:13 - mmengine - INFO - Epoch(train) [96][250/293] lr: 5.000000e-04 eta: 4:00:30 time: 0.506202 data_time: 0.079665 memory: 9871 loss_kpt: 0.000611 acc_pose: 0.747319 loss: 0.000611 2022/09/13 16:26:35 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 16:26:35 - mmengine - INFO - Saving checkpoint at 96 epochs 2022/09/13 16:27:05 - mmengine - INFO - Epoch(train) [97][50/293] lr: 5.000000e-04 eta: 3:59:33 time: 0.517413 data_time: 0.086313 memory: 9871 loss_kpt: 0.000607 acc_pose: 0.843808 loss: 0.000607 2022/09/13 16:27:30 - mmengine - INFO - Epoch(train) [97][100/293] lr: 5.000000e-04 eta: 3:59:16 time: 0.504289 data_time: 0.077016 memory: 9871 loss_kpt: 0.000593 acc_pose: 0.781351 loss: 0.000593 2022/09/13 16:27:55 - mmengine - INFO - Epoch(train) [97][150/293] lr: 5.000000e-04 eta: 3:58:58 time: 0.496603 data_time: 0.076118 memory: 9871 loss_kpt: 0.000595 acc_pose: 0.834444 loss: 0.000595 2022/09/13 16:28:20 - mmengine - INFO - Epoch(train) [97][200/293] lr: 5.000000e-04 eta: 3:58:41 time: 0.500638 data_time: 0.078149 memory: 9871 loss_kpt: 0.000612 acc_pose: 0.827599 loss: 0.000612 2022/09/13 16:28:45 - mmengine - INFO - Epoch(train) [97][250/293] lr: 5.000000e-04 eta: 3:58:23 time: 0.499972 data_time: 0.077716 memory: 9871 loss_kpt: 0.000624 acc_pose: 0.831876 loss: 0.000624 2022/09/13 16:29:07 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 16:29:07 - mmengine - INFO - Saving checkpoint at 97 epochs 2022/09/13 16:29:36 - mmengine - INFO - Epoch(train) [98][50/293] lr: 5.000000e-04 eta: 3:57:26 time: 0.507439 data_time: 0.084417 memory: 9871 loss_kpt: 0.000593 acc_pose: 0.808773 loss: 0.000593 2022/09/13 16:30:01 - mmengine - INFO - Epoch(train) [98][100/293] lr: 5.000000e-04 eta: 3:57:08 time: 0.496475 data_time: 0.075206 memory: 9871 loss_kpt: 0.000600 acc_pose: 0.885016 loss: 0.000600 2022/09/13 16:30:26 - mmengine - INFO - Epoch(train) [98][150/293] lr: 5.000000e-04 eta: 3:56:50 time: 0.494407 data_time: 0.078263 memory: 9871 loss_kpt: 0.000600 acc_pose: 0.849984 loss: 0.000600 2022/09/13 16:30:51 - mmengine - INFO - Epoch(train) [98][200/293] lr: 5.000000e-04 eta: 3:56:33 time: 0.499303 data_time: 0.075689 memory: 9871 loss_kpt: 0.000603 acc_pose: 0.839564 loss: 0.000603 2022/09/13 16:31:16 - mmengine - INFO - Epoch(train) [98][250/293] lr: 5.000000e-04 eta: 3:56:15 time: 0.508125 data_time: 0.075401 memory: 9871 loss_kpt: 0.000598 acc_pose: 0.863587 loss: 0.000598 2022/09/13 16:31:38 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 16:31:38 - mmengine - INFO - Saving checkpoint at 98 epochs 2022/09/13 16:32:09 - mmengine - INFO - Epoch(train) [99][50/293] lr: 5.000000e-04 eta: 3:55:20 time: 0.525320 data_time: 0.091947 memory: 9871 loss_kpt: 0.000592 acc_pose: 0.844597 loss: 0.000592 2022/09/13 16:32:34 - mmengine - INFO - Epoch(train) [99][100/293] lr: 5.000000e-04 eta: 3:55:02 time: 0.498976 data_time: 0.081569 memory: 9871 loss_kpt: 0.000598 acc_pose: 0.808276 loss: 0.000598 2022/09/13 16:32:59 - mmengine - INFO - Epoch(train) [99][150/293] lr: 5.000000e-04 eta: 3:54:44 time: 0.504096 data_time: 0.075794 memory: 9871 loss_kpt: 0.000603 acc_pose: 0.807035 loss: 0.000603 2022/09/13 16:33:24 - mmengine - INFO - Epoch(train) [99][200/293] lr: 5.000000e-04 eta: 3:54:27 time: 0.499546 data_time: 0.074176 memory: 9871 loss_kpt: 0.000593 acc_pose: 0.857982 loss: 0.000593 2022/09/13 16:33:49 - mmengine - INFO - Epoch(train) [99][250/293] lr: 5.000000e-04 eta: 3:54:09 time: 0.494966 data_time: 0.080770 memory: 9871 loss_kpt: 0.000595 acc_pose: 0.792666 loss: 0.000595 2022/09/13 16:34:07 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 16:34:10 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 16:34:10 - mmengine - INFO - Saving checkpoint at 99 epochs 2022/09/13 16:34:40 - mmengine - INFO - Epoch(train) [100][50/293] lr: 5.000000e-04 eta: 3:53:13 time: 0.514638 data_time: 0.084200 memory: 9871 loss_kpt: 0.000597 acc_pose: 0.845818 loss: 0.000597 2022/09/13 16:35:05 - mmengine - INFO - Epoch(train) [100][100/293] lr: 5.000000e-04 eta: 3:52:54 time: 0.491091 data_time: 0.076778 memory: 9871 loss_kpt: 0.000604 acc_pose: 0.849111 loss: 0.000604 2022/09/13 16:35:30 - mmengine - INFO - Epoch(train) [100][150/293] lr: 5.000000e-04 eta: 3:52:37 time: 0.503576 data_time: 0.078623 memory: 9871 loss_kpt: 0.000603 acc_pose: 0.836324 loss: 0.000603 2022/09/13 16:35:56 - mmengine - INFO - Epoch(train) [100][200/293] lr: 5.000000e-04 eta: 3:52:20 time: 0.510389 data_time: 0.083411 memory: 9871 loss_kpt: 0.000611 acc_pose: 0.773726 loss: 0.000611 2022/09/13 16:36:21 - mmengine - INFO - Epoch(train) [100][250/293] lr: 5.000000e-04 eta: 3:52:02 time: 0.499621 data_time: 0.072224 memory: 9871 loss_kpt: 0.000593 acc_pose: 0.837349 loss: 0.000593 2022/09/13 16:36:42 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 16:36:42 - mmengine - INFO - Saving checkpoint at 100 epochs 2022/09/13 16:36:55 - mmengine - INFO - Epoch(val) [100][50/407] eta: 0:01:00 time: 0.168932 data_time: 0.013013 memory: 9871 2022/09/13 16:37:03 - mmengine - INFO - Epoch(val) [100][100/407] eta: 0:00:49 time: 0.162609 data_time: 0.008866 memory: 920 2022/09/13 16:37:12 - mmengine - INFO - Epoch(val) [100][150/407] eta: 0:00:42 time: 0.165012 data_time: 0.011760 memory: 920 2022/09/13 16:37:20 - mmengine - INFO - Epoch(val) [100][200/407] eta: 0:00:33 time: 0.160937 data_time: 0.008418 memory: 920 2022/09/13 16:37:28 - mmengine - INFO - Epoch(val) [100][250/407] eta: 0:00:25 time: 0.164198 data_time: 0.009707 memory: 920 2022/09/13 16:37:36 - mmengine - INFO - Epoch(val) [100][300/407] eta: 0:00:17 time: 0.162232 data_time: 0.008086 memory: 920 2022/09/13 16:37:44 - mmengine - INFO - Epoch(val) [100][350/407] eta: 0:00:09 time: 0.168562 data_time: 0.012780 memory: 920 2022/09/13 16:37:52 - mmengine - INFO - Epoch(val) [100][400/407] eta: 0:00:01 time: 0.155698 data_time: 0.007224 memory: 920 2022/09/13 16:38:29 - mmengine - INFO - Evaluating CocoMetric... 2022/09/13 16:38:43 - mmengine - INFO - Epoch(val) [100][407/407] coco/AP: 0.733678 coco/AP .5: 0.895582 coco/AP .75: 0.805084 coco/AP (M): 0.697256 coco/AP (L): 0.802692 coco/AR: 0.787421 coco/AR .5: 0.936555 coco/AR .75: 0.852802 coco/AR (M): 0.744824 coco/AR (L): 0.848904 2022/09/13 16:39:09 - mmengine - INFO - Epoch(train) [101][50/293] lr: 5.000000e-04 eta: 3:51:06 time: 0.517252 data_time: 0.079979 memory: 9871 loss_kpt: 0.000591 acc_pose: 0.829174 loss: 0.000591 2022/09/13 16:39:35 - mmengine - INFO - Epoch(train) [101][100/293] lr: 5.000000e-04 eta: 3:50:49 time: 0.508000 data_time: 0.075993 memory: 9871 loss_kpt: 0.000600 acc_pose: 0.854292 loss: 0.000600 2022/09/13 16:40:00 - mmengine - INFO - Epoch(train) [101][150/293] lr: 5.000000e-04 eta: 3:50:31 time: 0.501341 data_time: 0.083957 memory: 9871 loss_kpt: 0.000600 acc_pose: 0.813926 loss: 0.000600 2022/09/13 16:40:25 - mmengine - INFO - Epoch(train) [101][200/293] lr: 5.000000e-04 eta: 3:50:14 time: 0.507092 data_time: 0.072494 memory: 9871 loss_kpt: 0.000600 acc_pose: 0.847589 loss: 0.000600 2022/09/13 16:40:50 - mmengine - INFO - Epoch(train) [101][250/293] lr: 5.000000e-04 eta: 3:49:56 time: 0.496015 data_time: 0.081693 memory: 9871 loss_kpt: 0.000606 acc_pose: 0.864323 loss: 0.000606 2022/09/13 16:41:11 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 16:41:11 - mmengine - INFO - Saving checkpoint at 101 epochs 2022/09/13 16:41:42 - mmengine - INFO - Epoch(train) [102][50/293] lr: 5.000000e-04 eta: 3:49:00 time: 0.508127 data_time: 0.078881 memory: 9871 loss_kpt: 0.000603 acc_pose: 0.820380 loss: 0.000603 2022/09/13 16:42:07 - mmengine - INFO - Epoch(train) [102][100/293] lr: 5.000000e-04 eta: 3:48:42 time: 0.507484 data_time: 0.084073 memory: 9871 loss_kpt: 0.000592 acc_pose: 0.834253 loss: 0.000592 2022/09/13 16:42:32 - mmengine - INFO - Epoch(train) [102][150/293] lr: 5.000000e-04 eta: 3:48:24 time: 0.492516 data_time: 0.075314 memory: 9871 loss_kpt: 0.000591 acc_pose: 0.837313 loss: 0.000591 2022/09/13 16:42:57 - mmengine - INFO - Epoch(train) [102][200/293] lr: 5.000000e-04 eta: 3:48:06 time: 0.504860 data_time: 0.077752 memory: 9871 loss_kpt: 0.000601 acc_pose: 0.816147 loss: 0.000601 2022/09/13 16:43:22 - mmengine - INFO - Epoch(train) [102][250/293] lr: 5.000000e-04 eta: 3:47:49 time: 0.508778 data_time: 0.077604 memory: 9871 loss_kpt: 0.000597 acc_pose: 0.871474 loss: 0.000597 2022/09/13 16:43:44 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 16:43:44 - mmengine - INFO - Saving checkpoint at 102 epochs 2022/09/13 16:44:14 - mmengine - INFO - Epoch(train) [103][50/293] lr: 5.000000e-04 eta: 3:46:53 time: 0.512609 data_time: 0.084821 memory: 9871 loss_kpt: 0.000607 acc_pose: 0.899273 loss: 0.000607 2022/09/13 16:44:39 - mmengine - INFO - Epoch(train) [103][100/293] lr: 5.000000e-04 eta: 3:46:36 time: 0.501712 data_time: 0.077058 memory: 9871 loss_kpt: 0.000612 acc_pose: 0.799808 loss: 0.000612 2022/09/13 16:44:46 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 16:45:04 - mmengine - INFO - Epoch(train) [103][150/293] lr: 5.000000e-04 eta: 3:46:18 time: 0.501619 data_time: 0.077500 memory: 9871 loss_kpt: 0.000604 acc_pose: 0.826534 loss: 0.000604 2022/09/13 16:45:30 - mmengine - INFO - Epoch(train) [103][200/293] lr: 5.000000e-04 eta: 3:46:00 time: 0.505605 data_time: 0.077710 memory: 9871 loss_kpt: 0.000599 acc_pose: 0.824581 loss: 0.000599 2022/09/13 16:45:55 - mmengine - INFO - Epoch(train) [103][250/293] lr: 5.000000e-04 eta: 3:45:42 time: 0.495759 data_time: 0.076834 memory: 9871 loss_kpt: 0.000598 acc_pose: 0.858436 loss: 0.000598 2022/09/13 16:46:16 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 16:46:16 - mmengine - INFO - Saving checkpoint at 103 epochs 2022/09/13 16:46:46 - mmengine - INFO - Epoch(train) [104][50/293] lr: 5.000000e-04 eta: 3:44:47 time: 0.509853 data_time: 0.084397 memory: 9871 loss_kpt: 0.000599 acc_pose: 0.796114 loss: 0.000599 2022/09/13 16:47:10 - mmengine - INFO - Epoch(train) [104][100/293] lr: 5.000000e-04 eta: 3:44:28 time: 0.490194 data_time: 0.077417 memory: 9871 loss_kpt: 0.000590 acc_pose: 0.820806 loss: 0.000590 2022/09/13 16:47:36 - mmengine - INFO - Epoch(train) [104][150/293] lr: 5.000000e-04 eta: 3:44:11 time: 0.509992 data_time: 0.084113 memory: 9871 loss_kpt: 0.000611 acc_pose: 0.854078 loss: 0.000611 2022/09/13 16:48:01 - mmengine - INFO - Epoch(train) [104][200/293] lr: 5.000000e-04 eta: 3:43:52 time: 0.493550 data_time: 0.077671 memory: 9871 loss_kpt: 0.000586 acc_pose: 0.837736 loss: 0.000586 2022/09/13 16:48:25 - mmengine - INFO - Epoch(train) [104][250/293] lr: 5.000000e-04 eta: 3:43:34 time: 0.498158 data_time: 0.077727 memory: 9871 loss_kpt: 0.000601 acc_pose: 0.838659 loss: 0.000601 2022/09/13 16:48:47 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 16:48:47 - mmengine - INFO - Saving checkpoint at 104 epochs 2022/09/13 16:49:17 - mmengine - INFO - Epoch(train) [105][50/293] lr: 5.000000e-04 eta: 3:42:39 time: 0.508156 data_time: 0.090788 memory: 9871 loss_kpt: 0.000608 acc_pose: 0.794839 loss: 0.000608 2022/09/13 16:49:42 - mmengine - INFO - Epoch(train) [105][100/293] lr: 5.000000e-04 eta: 3:42:21 time: 0.498502 data_time: 0.079611 memory: 9871 loss_kpt: 0.000593 acc_pose: 0.846107 loss: 0.000593 2022/09/13 16:50:07 - mmengine - INFO - Epoch(train) [105][150/293] lr: 5.000000e-04 eta: 3:42:04 time: 0.512651 data_time: 0.076290 memory: 9871 loss_kpt: 0.000600 acc_pose: 0.856249 loss: 0.000600 2022/09/13 16:50:32 - mmengine - INFO - Epoch(train) [105][200/293] lr: 5.000000e-04 eta: 3:41:45 time: 0.499387 data_time: 0.074764 memory: 9871 loss_kpt: 0.000591 acc_pose: 0.856306 loss: 0.000591 2022/09/13 16:50:58 - mmengine - INFO - Epoch(train) [105][250/293] lr: 5.000000e-04 eta: 3:41:28 time: 0.505528 data_time: 0.075693 memory: 9871 loss_kpt: 0.000606 acc_pose: 0.807268 loss: 0.000606 2022/09/13 16:51:19 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 16:51:19 - mmengine - INFO - Saving checkpoint at 105 epochs 2022/09/13 16:51:49 - mmengine - INFO - Epoch(train) [106][50/293] lr: 5.000000e-04 eta: 3:40:33 time: 0.509716 data_time: 0.083024 memory: 9871 loss_kpt: 0.000595 acc_pose: 0.818116 loss: 0.000595 2022/09/13 16:52:14 - mmengine - INFO - Epoch(train) [106][100/293] lr: 5.000000e-04 eta: 3:40:15 time: 0.503097 data_time: 0.074443 memory: 9871 loss_kpt: 0.000591 acc_pose: 0.760617 loss: 0.000591 2022/09/13 16:52:39 - mmengine - INFO - Epoch(train) [106][150/293] lr: 5.000000e-04 eta: 3:39:57 time: 0.503402 data_time: 0.071333 memory: 9871 loss_kpt: 0.000593 acc_pose: 0.878660 loss: 0.000593 2022/09/13 16:53:05 - mmengine - INFO - Epoch(train) [106][200/293] lr: 5.000000e-04 eta: 3:39:39 time: 0.511446 data_time: 0.083379 memory: 9871 loss_kpt: 0.000591 acc_pose: 0.853099 loss: 0.000591 2022/09/13 16:53:22 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 16:53:29 - mmengine - INFO - Epoch(train) [106][250/293] lr: 5.000000e-04 eta: 3:39:21 time: 0.489759 data_time: 0.073962 memory: 9871 loss_kpt: 0.000590 acc_pose: 0.806937 loss: 0.000590 2022/09/13 16:53:51 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 16:53:51 - mmengine - INFO - Saving checkpoint at 106 epochs 2022/09/13 16:54:20 - mmengine - INFO - Epoch(train) [107][50/293] lr: 5.000000e-04 eta: 3:38:26 time: 0.509012 data_time: 0.080782 memory: 9871 loss_kpt: 0.000597 acc_pose: 0.851509 loss: 0.000597 2022/09/13 16:54:45 - mmengine - INFO - Epoch(train) [107][100/293] lr: 5.000000e-04 eta: 3:38:08 time: 0.491155 data_time: 0.073975 memory: 9871 loss_kpt: 0.000603 acc_pose: 0.870256 loss: 0.000603 2022/09/13 16:55:10 - mmengine - INFO - Epoch(train) [107][150/293] lr: 5.000000e-04 eta: 3:37:50 time: 0.511509 data_time: 0.074162 memory: 9871 loss_kpt: 0.000615 acc_pose: 0.809694 loss: 0.000615 2022/09/13 16:55:35 - mmengine - INFO - Epoch(train) [107][200/293] lr: 5.000000e-04 eta: 3:37:31 time: 0.492267 data_time: 0.072706 memory: 9871 loss_kpt: 0.000583 acc_pose: 0.841099 loss: 0.000583 2022/09/13 16:56:00 - mmengine - INFO - Epoch(train) [107][250/293] lr: 5.000000e-04 eta: 3:37:13 time: 0.504281 data_time: 0.086028 memory: 9871 loss_kpt: 0.000587 acc_pose: 0.840374 loss: 0.000587 2022/09/13 16:56:21 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 16:56:21 - mmengine - INFO - Saving checkpoint at 107 epochs 2022/09/13 16:56:51 - mmengine - INFO - Epoch(train) [108][50/293] lr: 5.000000e-04 eta: 3:36:19 time: 0.503011 data_time: 0.088605 memory: 9871 loss_kpt: 0.000602 acc_pose: 0.812647 loss: 0.000602 2022/09/13 16:57:16 - mmengine - INFO - Epoch(train) [108][100/293] lr: 5.000000e-04 eta: 3:36:01 time: 0.498491 data_time: 0.076955 memory: 9871 loss_kpt: 0.000596 acc_pose: 0.809904 loss: 0.000596 2022/09/13 16:57:41 - mmengine - INFO - Epoch(train) [108][150/293] lr: 5.000000e-04 eta: 3:35:43 time: 0.506955 data_time: 0.071818 memory: 9871 loss_kpt: 0.000594 acc_pose: 0.788925 loss: 0.000594 2022/09/13 16:58:06 - mmengine - INFO - Epoch(train) [108][200/293] lr: 5.000000e-04 eta: 3:35:25 time: 0.501880 data_time: 0.077407 memory: 9871 loss_kpt: 0.000604 acc_pose: 0.823228 loss: 0.000604 2022/09/13 16:58:30 - mmengine - INFO - Epoch(train) [108][250/293] lr: 5.000000e-04 eta: 3:35:06 time: 0.487910 data_time: 0.073768 memory: 9871 loss_kpt: 0.000592 acc_pose: 0.843893 loss: 0.000592 2022/09/13 16:58:52 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 16:58:52 - mmengine - INFO - Saving checkpoint at 108 epochs 2022/09/13 16:59:23 - mmengine - INFO - Epoch(train) [109][50/293] lr: 5.000000e-04 eta: 3:34:12 time: 0.508333 data_time: 0.082601 memory: 9871 loss_kpt: 0.000595 acc_pose: 0.854480 loss: 0.000595 2022/09/13 16:59:47 - mmengine - INFO - Epoch(train) [109][100/293] lr: 5.000000e-04 eta: 3:33:53 time: 0.499854 data_time: 0.074615 memory: 9871 loss_kpt: 0.000586 acc_pose: 0.812519 loss: 0.000586 2022/09/13 17:00:13 - mmengine - INFO - Epoch(train) [109][150/293] lr: 5.000000e-04 eta: 3:33:35 time: 0.501427 data_time: 0.068417 memory: 9871 loss_kpt: 0.000590 acc_pose: 0.850118 loss: 0.000590 2022/09/13 17:00:38 - mmengine - INFO - Epoch(train) [109][200/293] lr: 5.000000e-04 eta: 3:33:17 time: 0.501697 data_time: 0.077083 memory: 9871 loss_kpt: 0.000593 acc_pose: 0.817477 loss: 0.000593 2022/09/13 17:01:02 - mmengine - INFO - Epoch(train) [109][250/293] lr: 5.000000e-04 eta: 3:32:58 time: 0.495838 data_time: 0.074077 memory: 9871 loss_kpt: 0.000582 acc_pose: 0.860806 loss: 0.000582 2022/09/13 17:01:24 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 17:01:24 - mmengine - INFO - Saving checkpoint at 109 epochs 2022/09/13 17:01:53 - mmengine - INFO - Epoch(train) [110][50/293] lr: 5.000000e-04 eta: 3:32:04 time: 0.501958 data_time: 0.080712 memory: 9871 loss_kpt: 0.000589 acc_pose: 0.832084 loss: 0.000589 2022/09/13 17:01:59 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 17:02:19 - mmengine - INFO - Epoch(train) [110][100/293] lr: 5.000000e-04 eta: 3:31:47 time: 0.512010 data_time: 0.076767 memory: 9871 loss_kpt: 0.000601 acc_pose: 0.818043 loss: 0.000601 2022/09/13 17:02:44 - mmengine - INFO - Epoch(train) [110][150/293] lr: 5.000000e-04 eta: 3:31:29 time: 0.505138 data_time: 0.082931 memory: 9871 loss_kpt: 0.000593 acc_pose: 0.825656 loss: 0.000593 2022/09/13 17:03:09 - mmengine - INFO - Epoch(train) [110][200/293] lr: 5.000000e-04 eta: 3:31:10 time: 0.497683 data_time: 0.074832 memory: 9871 loss_kpt: 0.000593 acc_pose: 0.805189 loss: 0.000593 2022/09/13 17:03:34 - mmengine - INFO - Epoch(train) [110][250/293] lr: 5.000000e-04 eta: 3:30:51 time: 0.496460 data_time: 0.074968 memory: 9871 loss_kpt: 0.000599 acc_pose: 0.841407 loss: 0.000599 2022/09/13 17:03:55 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 17:03:55 - mmengine - INFO - Saving checkpoint at 110 epochs 2022/09/13 17:04:08 - mmengine - INFO - Epoch(val) [110][50/407] eta: 0:00:58 time: 0.163336 data_time: 0.012622 memory: 9871 2022/09/13 17:04:16 - mmengine - INFO - Epoch(val) [110][100/407] eta: 0:00:48 time: 0.158328 data_time: 0.007712 memory: 920 2022/09/13 17:04:24 - mmengine - INFO - Epoch(val) [110][150/407] eta: 0:00:40 time: 0.158001 data_time: 0.008227 memory: 920 2022/09/13 17:04:32 - mmengine - INFO - Epoch(val) [110][200/407] eta: 0:00:32 time: 0.158819 data_time: 0.007901 memory: 920 2022/09/13 17:04:40 - mmengine - INFO - Epoch(val) [110][250/407] eta: 0:00:25 time: 0.159488 data_time: 0.007830 memory: 920 2022/09/13 17:04:47 - mmengine - INFO - Epoch(val) [110][300/407] eta: 0:00:16 time: 0.158093 data_time: 0.007836 memory: 920 2022/09/13 17:04:56 - mmengine - INFO - Epoch(val) [110][350/407] eta: 0:00:09 time: 0.164619 data_time: 0.008260 memory: 920 2022/09/13 17:05:04 - mmengine - INFO - Epoch(val) [110][400/407] eta: 0:00:01 time: 0.157457 data_time: 0.008631 memory: 920 2022/09/13 17:05:39 - mmengine - INFO - Evaluating CocoMetric... 2022/09/13 17:05:53 - mmengine - INFO - Epoch(val) [110][407/407] coco/AP: 0.739307 coco/AP .5: 0.898736 coco/AP .75: 0.807358 coco/AP (M): 0.702195 coco/AP (L): 0.807412 coco/AR: 0.791026 coco/AR .5: 0.937500 coco/AR .75: 0.852173 coco/AR (M): 0.748375 coco/AR (L): 0.853066 2022/09/13 17:05:53 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220913/dark_w32_256_v1/best_coco/AP_epoch_90.pth is removed 2022/09/13 17:05:56 - mmengine - INFO - The best checkpoint with 0.7393 coco/AP at 110 epoch is saved to best_coco/AP_epoch_110.pth. 2022/09/13 17:06:22 - mmengine - INFO - Epoch(train) [111][50/293] lr: 5.000000e-04 eta: 3:29:58 time: 0.514336 data_time: 0.077187 memory: 9871 loss_kpt: 0.000600 acc_pose: 0.855144 loss: 0.000600 2022/09/13 17:06:47 - mmengine - INFO - Epoch(train) [111][100/293] lr: 5.000000e-04 eta: 3:29:40 time: 0.499096 data_time: 0.080589 memory: 9871 loss_kpt: 0.000591 acc_pose: 0.818206 loss: 0.000591 2022/09/13 17:07:12 - mmengine - INFO - Epoch(train) [111][150/293] lr: 5.000000e-04 eta: 3:29:21 time: 0.499849 data_time: 0.069848 memory: 9871 loss_kpt: 0.000594 acc_pose: 0.791556 loss: 0.000594 2022/09/13 17:07:37 - mmengine - INFO - Epoch(train) [111][200/293] lr: 5.000000e-04 eta: 3:29:03 time: 0.497699 data_time: 0.074572 memory: 9871 loss_kpt: 0.000608 acc_pose: 0.820296 loss: 0.000608 2022/09/13 17:08:02 - mmengine - INFO - Epoch(train) [111][250/293] lr: 5.000000e-04 eta: 3:28:44 time: 0.497932 data_time: 0.080312 memory: 9871 loss_kpt: 0.000605 acc_pose: 0.855740 loss: 0.000605 2022/09/13 17:08:23 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 17:08:23 - mmengine - INFO - Saving checkpoint at 111 epochs 2022/09/13 17:08:55 - mmengine - INFO - Epoch(train) [112][50/293] lr: 5.000000e-04 eta: 3:27:51 time: 0.514065 data_time: 0.089317 memory: 9871 loss_kpt: 0.000594 acc_pose: 0.820834 loss: 0.000594 2022/09/13 17:09:20 - mmengine - INFO - Epoch(train) [112][100/293] lr: 5.000000e-04 eta: 3:27:33 time: 0.497593 data_time: 0.077734 memory: 9871 loss_kpt: 0.000595 acc_pose: 0.820519 loss: 0.000595 2022/09/13 17:09:46 - mmengine - INFO - Epoch(train) [112][150/293] lr: 5.000000e-04 eta: 3:27:15 time: 0.507283 data_time: 0.077854 memory: 9871 loss_kpt: 0.000590 acc_pose: 0.825092 loss: 0.000590 2022/09/13 17:10:10 - mmengine - INFO - Epoch(train) [112][200/293] lr: 5.000000e-04 eta: 3:26:56 time: 0.496428 data_time: 0.073224 memory: 9871 loss_kpt: 0.000594 acc_pose: 0.797065 loss: 0.000594 2022/09/13 17:10:35 - mmengine - INFO - Epoch(train) [112][250/293] lr: 5.000000e-04 eta: 3:26:37 time: 0.492684 data_time: 0.077731 memory: 9871 loss_kpt: 0.000605 acc_pose: 0.806338 loss: 0.000605 2022/09/13 17:10:56 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 17:10:56 - mmengine - INFO - Saving checkpoint at 112 epochs 2022/09/13 17:11:26 - mmengine - INFO - Epoch(train) [113][50/293] lr: 5.000000e-04 eta: 3:25:45 time: 0.522439 data_time: 0.088130 memory: 9871 loss_kpt: 0.000589 acc_pose: 0.846791 loss: 0.000589 2022/09/13 17:11:51 - mmengine - INFO - Epoch(train) [113][100/293] lr: 5.000000e-04 eta: 3:25:26 time: 0.496571 data_time: 0.076147 memory: 9871 loss_kpt: 0.000583 acc_pose: 0.824580 loss: 0.000583 2022/09/13 17:12:16 - mmengine - INFO - Epoch(train) [113][150/293] lr: 5.000000e-04 eta: 3:25:08 time: 0.497967 data_time: 0.075625 memory: 9871 loss_kpt: 0.000584 acc_pose: 0.862963 loss: 0.000584 2022/09/13 17:12:33 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 17:12:41 - mmengine - INFO - Epoch(train) [113][200/293] lr: 5.000000e-04 eta: 3:24:49 time: 0.502792 data_time: 0.075719 memory: 9871 loss_kpt: 0.000596 acc_pose: 0.823024 loss: 0.000596 2022/09/13 17:13:07 - mmengine - INFO - Epoch(train) [113][250/293] lr: 5.000000e-04 eta: 3:24:31 time: 0.504314 data_time: 0.079643 memory: 9871 loss_kpt: 0.000592 acc_pose: 0.813692 loss: 0.000592 2022/09/13 17:13:28 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 17:13:28 - mmengine - INFO - Saving checkpoint at 113 epochs 2022/09/13 17:13:58 - mmengine - INFO - Epoch(train) [114][50/293] lr: 5.000000e-04 eta: 3:23:38 time: 0.509875 data_time: 0.086675 memory: 9871 loss_kpt: 0.000603 acc_pose: 0.809427 loss: 0.000603 2022/09/13 17:14:23 - mmengine - INFO - Epoch(train) [114][100/293] lr: 5.000000e-04 eta: 3:23:20 time: 0.497598 data_time: 0.075249 memory: 9871 loss_kpt: 0.000592 acc_pose: 0.834426 loss: 0.000592 2022/09/13 17:14:48 - mmengine - INFO - Epoch(train) [114][150/293] lr: 5.000000e-04 eta: 3:23:01 time: 0.495539 data_time: 0.076554 memory: 9871 loss_kpt: 0.000598 acc_pose: 0.841749 loss: 0.000598 2022/09/13 17:15:12 - mmengine - INFO - Epoch(train) [114][200/293] lr: 5.000000e-04 eta: 3:22:42 time: 0.492123 data_time: 0.075027 memory: 9871 loss_kpt: 0.000588 acc_pose: 0.805926 loss: 0.000588 2022/09/13 17:15:37 - mmengine - INFO - Epoch(train) [114][250/293] lr: 5.000000e-04 eta: 3:22:23 time: 0.493153 data_time: 0.080325 memory: 9871 loss_kpt: 0.000582 acc_pose: 0.837242 loss: 0.000582 2022/09/13 17:15:58 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 17:15:58 - mmengine - INFO - Saving checkpoint at 114 epochs 2022/09/13 17:16:29 - mmengine - INFO - Epoch(train) [115][50/293] lr: 5.000000e-04 eta: 3:21:31 time: 0.518862 data_time: 0.086996 memory: 9871 loss_kpt: 0.000587 acc_pose: 0.868006 loss: 0.000587 2022/09/13 17:16:54 - mmengine - INFO - Epoch(train) [115][100/293] lr: 5.000000e-04 eta: 3:21:12 time: 0.498369 data_time: 0.073708 memory: 9871 loss_kpt: 0.000588 acc_pose: 0.812011 loss: 0.000588 2022/09/13 17:17:19 - mmengine - INFO - Epoch(train) [115][150/293] lr: 5.000000e-04 eta: 3:20:54 time: 0.500676 data_time: 0.071806 memory: 9871 loss_kpt: 0.000588 acc_pose: 0.819070 loss: 0.000588 2022/09/13 17:17:43 - mmengine - INFO - Epoch(train) [115][200/293] lr: 5.000000e-04 eta: 3:20:35 time: 0.491753 data_time: 0.076566 memory: 9871 loss_kpt: 0.000591 acc_pose: 0.823896 loss: 0.000591 2022/09/13 17:18:09 - mmengine - INFO - Epoch(train) [115][250/293] lr: 5.000000e-04 eta: 3:20:16 time: 0.512769 data_time: 0.077346 memory: 9871 loss_kpt: 0.000612 acc_pose: 0.827886 loss: 0.000612 2022/09/13 17:18:31 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 17:18:31 - mmengine - INFO - Saving checkpoint at 115 epochs 2022/09/13 17:19:01 - mmengine - INFO - Epoch(train) [116][50/293] lr: 5.000000e-04 eta: 3:19:24 time: 0.507927 data_time: 0.082377 memory: 9871 loss_kpt: 0.000596 acc_pose: 0.822741 loss: 0.000596 2022/09/13 17:19:26 - mmengine - INFO - Epoch(train) [116][100/293] lr: 5.000000e-04 eta: 3:19:06 time: 0.502761 data_time: 0.073342 memory: 9871 loss_kpt: 0.000586 acc_pose: 0.823417 loss: 0.000586 2022/09/13 17:19:51 - mmengine - INFO - Epoch(train) [116][150/293] lr: 5.000000e-04 eta: 3:18:47 time: 0.498823 data_time: 0.075569 memory: 9871 loss_kpt: 0.000587 acc_pose: 0.847791 loss: 0.000587 2022/09/13 17:20:16 - mmengine - INFO - Epoch(train) [116][200/293] lr: 5.000000e-04 eta: 3:18:28 time: 0.503451 data_time: 0.076603 memory: 9871 loss_kpt: 0.000605 acc_pose: 0.849030 loss: 0.000605 2022/09/13 17:20:41 - mmengine - INFO - Epoch(train) [116][250/293] lr: 5.000000e-04 eta: 3:18:09 time: 0.492298 data_time: 0.070872 memory: 9871 loss_kpt: 0.000601 acc_pose: 0.835827 loss: 0.000601 2022/09/13 17:21:02 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 17:21:02 - mmengine - INFO - Saving checkpoint at 116 epochs 2022/09/13 17:21:13 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 17:21:32 - mmengine - INFO - Epoch(train) [117][50/293] lr: 5.000000e-04 eta: 3:17:18 time: 0.514749 data_time: 0.078535 memory: 9871 loss_kpt: 0.000592 acc_pose: 0.785066 loss: 0.000592 2022/09/13 17:21:57 - mmengine - INFO - Epoch(train) [117][100/293] lr: 5.000000e-04 eta: 3:16:59 time: 0.504876 data_time: 0.078205 memory: 9871 loss_kpt: 0.000592 acc_pose: 0.843691 loss: 0.000592 2022/09/13 17:22:22 - mmengine - INFO - Epoch(train) [117][150/293] lr: 5.000000e-04 eta: 3:16:40 time: 0.495322 data_time: 0.070390 memory: 9871 loss_kpt: 0.000590 acc_pose: 0.813131 loss: 0.000590 2022/09/13 17:22:47 - mmengine - INFO - Epoch(train) [117][200/293] lr: 5.000000e-04 eta: 3:16:22 time: 0.508977 data_time: 0.075121 memory: 9871 loss_kpt: 0.000588 acc_pose: 0.853940 loss: 0.000588 2022/09/13 17:23:12 - mmengine - INFO - Epoch(train) [117][250/293] lr: 5.000000e-04 eta: 3:16:03 time: 0.496592 data_time: 0.080493 memory: 9871 loss_kpt: 0.000597 acc_pose: 0.817211 loss: 0.000597 2022/09/13 17:23:34 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 17:23:34 - mmengine - INFO - Saving checkpoint at 117 epochs 2022/09/13 17:24:04 - mmengine - INFO - Epoch(train) [118][50/293] lr: 5.000000e-04 eta: 3:15:11 time: 0.518153 data_time: 0.089112 memory: 9871 loss_kpt: 0.000592 acc_pose: 0.802739 loss: 0.000592 2022/09/13 17:24:29 - mmengine - INFO - Epoch(train) [118][100/293] lr: 5.000000e-04 eta: 3:14:53 time: 0.503153 data_time: 0.071352 memory: 9871 loss_kpt: 0.000590 acc_pose: 0.835098 loss: 0.000590 2022/09/13 17:24:54 - mmengine - INFO - Epoch(train) [118][150/293] lr: 5.000000e-04 eta: 3:14:34 time: 0.493259 data_time: 0.072059 memory: 9871 loss_kpt: 0.000585 acc_pose: 0.840814 loss: 0.000585 2022/09/13 17:25:19 - mmengine - INFO - Epoch(train) [118][200/293] lr: 5.000000e-04 eta: 3:14:15 time: 0.497018 data_time: 0.077854 memory: 9871 loss_kpt: 0.000598 acc_pose: 0.811676 loss: 0.000598 2022/09/13 17:25:44 - mmengine - INFO - Epoch(train) [118][250/293] lr: 5.000000e-04 eta: 3:13:56 time: 0.494668 data_time: 0.074516 memory: 9871 loss_kpt: 0.000587 acc_pose: 0.791019 loss: 0.000587 2022/09/13 17:26:06 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 17:26:06 - mmengine - INFO - Saving checkpoint at 118 epochs 2022/09/13 17:26:37 - mmengine - INFO - Epoch(train) [119][50/293] lr: 5.000000e-04 eta: 3:13:05 time: 0.516108 data_time: 0.084944 memory: 9871 loss_kpt: 0.000583 acc_pose: 0.838482 loss: 0.000583 2022/09/13 17:27:02 - mmengine - INFO - Epoch(train) [119][100/293] lr: 5.000000e-04 eta: 3:12:46 time: 0.497691 data_time: 0.074128 memory: 9871 loss_kpt: 0.000590 acc_pose: 0.847712 loss: 0.000590 2022/09/13 17:27:27 - mmengine - INFO - Epoch(train) [119][150/293] lr: 5.000000e-04 eta: 3:12:27 time: 0.497133 data_time: 0.080803 memory: 9871 loss_kpt: 0.000589 acc_pose: 0.797373 loss: 0.000589 2022/09/13 17:27:51 - mmengine - INFO - Epoch(train) [119][200/293] lr: 5.000000e-04 eta: 3:12:07 time: 0.492350 data_time: 0.079447 memory: 9871 loss_kpt: 0.000588 acc_pose: 0.782552 loss: 0.000588 2022/09/13 17:28:17 - mmengine - INFO - Epoch(train) [119][250/293] lr: 5.000000e-04 eta: 3:11:49 time: 0.515312 data_time: 0.076186 memory: 9871 loss_kpt: 0.000604 acc_pose: 0.760770 loss: 0.000604 2022/09/13 17:28:39 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 17:28:39 - mmengine - INFO - Saving checkpoint at 119 epochs 2022/09/13 17:29:09 - mmengine - INFO - Epoch(train) [120][50/293] lr: 5.000000e-04 eta: 3:10:58 time: 0.508655 data_time: 0.080575 memory: 9871 loss_kpt: 0.000587 acc_pose: 0.816492 loss: 0.000587 2022/09/13 17:29:34 - mmengine - INFO - Epoch(train) [120][100/293] lr: 5.000000e-04 eta: 3:10:39 time: 0.497941 data_time: 0.072314 memory: 9871 loss_kpt: 0.000587 acc_pose: 0.784136 loss: 0.000587 2022/09/13 17:29:51 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 17:29:59 - mmengine - INFO - Epoch(train) [120][150/293] lr: 5.000000e-04 eta: 3:10:20 time: 0.498640 data_time: 0.076403 memory: 9871 loss_kpt: 0.000585 acc_pose: 0.842909 loss: 0.000585 2022/09/13 17:30:25 - mmengine - INFO - Epoch(train) [120][200/293] lr: 5.000000e-04 eta: 3:10:02 time: 0.511402 data_time: 0.074251 memory: 9871 loss_kpt: 0.000596 acc_pose: 0.815371 loss: 0.000596 2022/09/13 17:30:50 - mmengine - INFO - Epoch(train) [120][250/293] lr: 5.000000e-04 eta: 3:09:43 time: 0.505121 data_time: 0.070561 memory: 9871 loss_kpt: 0.000591 acc_pose: 0.804343 loss: 0.000591 2022/09/13 17:31:11 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 17:31:11 - mmengine - INFO - Saving checkpoint at 120 epochs 2022/09/13 17:31:24 - mmengine - INFO - Epoch(val) [120][50/407] eta: 0:00:58 time: 0.163018 data_time: 0.012672 memory: 9871 2022/09/13 17:31:32 - mmengine - INFO - Epoch(val) [120][100/407] eta: 0:00:48 time: 0.158968 data_time: 0.007514 memory: 920 2022/09/13 17:31:40 - mmengine - INFO - Epoch(val) [120][150/407] eta: 0:00:40 time: 0.156559 data_time: 0.007329 memory: 920 2022/09/13 17:31:48 - mmengine - INFO - Epoch(val) [120][200/407] eta: 0:00:32 time: 0.157868 data_time: 0.007515 memory: 920 2022/09/13 17:31:56 - mmengine - INFO - Epoch(val) [120][250/407] eta: 0:00:24 time: 0.156870 data_time: 0.007560 memory: 920 2022/09/13 17:32:04 - mmengine - INFO - Epoch(val) [120][300/407] eta: 0:00:17 time: 0.159841 data_time: 0.007640 memory: 920 2022/09/13 17:32:11 - mmengine - INFO - Epoch(val) [120][350/407] eta: 0:00:08 time: 0.156664 data_time: 0.007469 memory: 920 2022/09/13 17:32:19 - mmengine - INFO - Epoch(val) [120][400/407] eta: 0:00:01 time: 0.159650 data_time: 0.010583 memory: 920 2022/09/13 17:32:55 - mmengine - INFO - Evaluating CocoMetric... 2022/09/13 17:33:08 - mmengine - INFO - Epoch(val) [120][407/407] coco/AP: 0.740366 coco/AP .5: 0.899134 coco/AP .75: 0.809026 coco/AP (M): 0.704520 coco/AP (L): 0.807346 coco/AR: 0.792302 coco/AR .5: 0.937657 coco/AR .75: 0.855006 coco/AR (M): 0.749795 coco/AR (L): 0.853846 2022/09/13 17:33:08 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220913/dark_w32_256_v1/best_coco/AP_epoch_110.pth is removed 2022/09/13 17:33:11 - mmengine - INFO - The best checkpoint with 0.7404 coco/AP at 120 epoch is saved to best_coco/AP_epoch_120.pth. 2022/09/13 17:33:37 - mmengine - INFO - Epoch(train) [121][50/293] lr: 5.000000e-04 eta: 3:08:52 time: 0.524360 data_time: 0.083469 memory: 9871 loss_kpt: 0.000577 acc_pose: 0.835887 loss: 0.000577 2022/09/13 17:34:02 - mmengine - INFO - Epoch(train) [121][100/293] lr: 5.000000e-04 eta: 3:08:33 time: 0.499554 data_time: 0.074485 memory: 9871 loss_kpt: 0.000584 acc_pose: 0.846032 loss: 0.000584 2022/09/13 17:34:27 - mmengine - INFO - Epoch(train) [121][150/293] lr: 5.000000e-04 eta: 3:08:14 time: 0.493689 data_time: 0.072970 memory: 9871 loss_kpt: 0.000584 acc_pose: 0.799812 loss: 0.000584 2022/09/13 17:34:52 - mmengine - INFO - Epoch(train) [121][200/293] lr: 5.000000e-04 eta: 3:07:55 time: 0.500984 data_time: 0.080473 memory: 9871 loss_kpt: 0.000586 acc_pose: 0.842704 loss: 0.000586 2022/09/13 17:35:17 - mmengine - INFO - Epoch(train) [121][250/293] lr: 5.000000e-04 eta: 3:07:36 time: 0.503512 data_time: 0.080993 memory: 9871 loss_kpt: 0.000583 acc_pose: 0.863208 loss: 0.000583 2022/09/13 17:35:39 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 17:35:39 - mmengine - INFO - Saving checkpoint at 121 epochs 2022/09/13 17:36:10 - mmengine - INFO - Epoch(train) [122][50/293] lr: 5.000000e-04 eta: 3:06:46 time: 0.517087 data_time: 0.088664 memory: 9871 loss_kpt: 0.000590 acc_pose: 0.834524 loss: 0.000590 2022/09/13 17:36:34 - mmengine - INFO - Epoch(train) [122][100/293] lr: 5.000000e-04 eta: 3:06:27 time: 0.492229 data_time: 0.074928 memory: 9871 loss_kpt: 0.000592 acc_pose: 0.836761 loss: 0.000592 2022/09/13 17:36:59 - mmengine - INFO - Epoch(train) [122][150/293] lr: 5.000000e-04 eta: 3:06:07 time: 0.493192 data_time: 0.074021 memory: 9871 loss_kpt: 0.000581 acc_pose: 0.848076 loss: 0.000581 2022/09/13 17:37:24 - mmengine - INFO - Epoch(train) [122][200/293] lr: 5.000000e-04 eta: 3:05:48 time: 0.500166 data_time: 0.071122 memory: 9871 loss_kpt: 0.000595 acc_pose: 0.774324 loss: 0.000595 2022/09/13 17:37:49 - mmengine - INFO - Epoch(train) [122][250/293] lr: 5.000000e-04 eta: 3:05:30 time: 0.507607 data_time: 0.078346 memory: 9871 loss_kpt: 0.000583 acc_pose: 0.857293 loss: 0.000583 2022/09/13 17:38:11 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 17:38:11 - mmengine - INFO - Saving checkpoint at 122 epochs 2022/09/13 17:38:40 - mmengine - INFO - Epoch(train) [123][50/293] lr: 5.000000e-04 eta: 3:04:39 time: 0.511306 data_time: 0.082517 memory: 9871 loss_kpt: 0.000589 acc_pose: 0.827938 loss: 0.000589 2022/09/13 17:39:06 - mmengine - INFO - Epoch(train) [123][100/293] lr: 5.000000e-04 eta: 3:04:20 time: 0.506828 data_time: 0.074599 memory: 9871 loss_kpt: 0.000583 acc_pose: 0.837137 loss: 0.000583 2022/09/13 17:39:31 - mmengine - INFO - Epoch(train) [123][150/293] lr: 5.000000e-04 eta: 3:04:02 time: 0.508781 data_time: 0.081190 memory: 9871 loss_kpt: 0.000593 acc_pose: 0.805438 loss: 0.000593 2022/09/13 17:39:56 - mmengine - INFO - Epoch(train) [123][200/293] lr: 5.000000e-04 eta: 3:03:42 time: 0.500719 data_time: 0.074496 memory: 9871 loss_kpt: 0.000587 acc_pose: 0.834320 loss: 0.000587 2022/09/13 17:40:21 - mmengine - INFO - Epoch(train) [123][250/293] lr: 5.000000e-04 eta: 3:03:23 time: 0.491896 data_time: 0.074335 memory: 9871 loss_kpt: 0.000578 acc_pose: 0.864102 loss: 0.000578 2022/09/13 17:40:23 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 17:40:42 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 17:40:42 - mmengine - INFO - Saving checkpoint at 123 epochs 2022/09/13 17:41:11 - mmengine - INFO - Epoch(train) [124][50/293] lr: 5.000000e-04 eta: 3:02:32 time: 0.502696 data_time: 0.082793 memory: 9871 loss_kpt: 0.000585 acc_pose: 0.839889 loss: 0.000585 2022/09/13 17:41:36 - mmengine - INFO - Epoch(train) [124][100/293] lr: 5.000000e-04 eta: 3:02:13 time: 0.499725 data_time: 0.075548 memory: 9871 loss_kpt: 0.000596 acc_pose: 0.797757 loss: 0.000596 2022/09/13 17:42:01 - mmengine - INFO - Epoch(train) [124][150/293] lr: 5.000000e-04 eta: 3:01:54 time: 0.494643 data_time: 0.070508 memory: 9871 loss_kpt: 0.000595 acc_pose: 0.835020 loss: 0.000595 2022/09/13 17:42:26 - mmengine - INFO - Epoch(train) [124][200/293] lr: 5.000000e-04 eta: 3:01:35 time: 0.506657 data_time: 0.078083 memory: 9871 loss_kpt: 0.000585 acc_pose: 0.837547 loss: 0.000585 2022/09/13 17:42:51 - mmengine - INFO - Epoch(train) [124][250/293] lr: 5.000000e-04 eta: 3:01:16 time: 0.494509 data_time: 0.071146 memory: 9871 loss_kpt: 0.000585 acc_pose: 0.834532 loss: 0.000585 2022/09/13 17:43:13 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 17:43:13 - mmengine - INFO - Saving checkpoint at 124 epochs 2022/09/13 17:43:43 - mmengine - INFO - Epoch(train) [125][50/293] lr: 5.000000e-04 eta: 3:00:26 time: 0.518342 data_time: 0.094963 memory: 9871 loss_kpt: 0.000590 acc_pose: 0.830588 loss: 0.000590 2022/09/13 17:44:08 - mmengine - INFO - Epoch(train) [125][100/293] lr: 5.000000e-04 eta: 3:00:07 time: 0.493808 data_time: 0.078414 memory: 9871 loss_kpt: 0.000590 acc_pose: 0.817420 loss: 0.000590 2022/09/13 17:44:33 - mmengine - INFO - Epoch(train) [125][150/293] lr: 5.000000e-04 eta: 2:59:48 time: 0.501749 data_time: 0.082299 memory: 9871 loss_kpt: 0.000586 acc_pose: 0.853258 loss: 0.000586 2022/09/13 17:44:57 - mmengine - INFO - Epoch(train) [125][200/293] lr: 5.000000e-04 eta: 2:59:28 time: 0.488988 data_time: 0.076452 memory: 9871 loss_kpt: 0.000595 acc_pose: 0.824886 loss: 0.000595 2022/09/13 17:45:23 - mmengine - INFO - Epoch(train) [125][250/293] lr: 5.000000e-04 eta: 2:59:10 time: 0.521994 data_time: 0.077022 memory: 9871 loss_kpt: 0.000586 acc_pose: 0.827770 loss: 0.000586 2022/09/13 17:45:45 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 17:45:45 - mmengine - INFO - Saving checkpoint at 125 epochs 2022/09/13 17:46:15 - mmengine - INFO - Epoch(train) [126][50/293] lr: 5.000000e-04 eta: 2:58:20 time: 0.515933 data_time: 0.086624 memory: 9871 loss_kpt: 0.000566 acc_pose: 0.808747 loss: 0.000566 2022/09/13 17:46:40 - mmengine - INFO - Epoch(train) [126][100/293] lr: 5.000000e-04 eta: 2:58:01 time: 0.501142 data_time: 0.075980 memory: 9871 loss_kpt: 0.000589 acc_pose: 0.822199 loss: 0.000589 2022/09/13 17:47:05 - mmengine - INFO - Epoch(train) [126][150/293] lr: 5.000000e-04 eta: 2:57:41 time: 0.497613 data_time: 0.076571 memory: 9871 loss_kpt: 0.000573 acc_pose: 0.850858 loss: 0.000573 2022/09/13 17:47:31 - mmengine - INFO - Epoch(train) [126][200/293] lr: 5.000000e-04 eta: 2:57:22 time: 0.505663 data_time: 0.079759 memory: 9871 loss_kpt: 0.000576 acc_pose: 0.825488 loss: 0.000576 2022/09/13 17:47:55 - mmengine - INFO - Epoch(train) [126][250/293] lr: 5.000000e-04 eta: 2:57:03 time: 0.494734 data_time: 0.079806 memory: 9871 loss_kpt: 0.000578 acc_pose: 0.839041 loss: 0.000578 2022/09/13 17:48:16 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 17:48:16 - mmengine - INFO - Saving checkpoint at 126 epochs 2022/09/13 17:48:48 - mmengine - INFO - Epoch(train) [127][50/293] lr: 5.000000e-04 eta: 2:56:13 time: 0.506850 data_time: 0.083286 memory: 9871 loss_kpt: 0.000586 acc_pose: 0.855608 loss: 0.000586 2022/09/13 17:49:04 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 17:49:13 - mmengine - INFO - Epoch(train) [127][100/293] lr: 5.000000e-04 eta: 2:55:54 time: 0.497998 data_time: 0.080850 memory: 9871 loss_kpt: 0.000589 acc_pose: 0.892981 loss: 0.000589 2022/09/13 17:49:38 - mmengine - INFO - Epoch(train) [127][150/293] lr: 5.000000e-04 eta: 2:55:35 time: 0.496431 data_time: 0.076806 memory: 9871 loss_kpt: 0.000583 acc_pose: 0.844937 loss: 0.000583 2022/09/13 17:50:03 - mmengine - INFO - Epoch(train) [127][200/293] lr: 5.000000e-04 eta: 2:55:15 time: 0.497466 data_time: 0.073581 memory: 9871 loss_kpt: 0.000573 acc_pose: 0.815732 loss: 0.000573 2022/09/13 17:50:27 - mmengine - INFO - Epoch(train) [127][250/293] lr: 5.000000e-04 eta: 2:54:56 time: 0.492623 data_time: 0.076877 memory: 9871 loss_kpt: 0.000587 acc_pose: 0.794853 loss: 0.000587 2022/09/13 17:50:49 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 17:50:49 - mmengine - INFO - Saving checkpoint at 127 epochs 2022/09/13 17:51:19 - mmengine - INFO - Epoch(train) [128][50/293] lr: 5.000000e-04 eta: 2:54:06 time: 0.510897 data_time: 0.083694 memory: 9871 loss_kpt: 0.000577 acc_pose: 0.839594 loss: 0.000577 2022/09/13 17:51:44 - mmengine - INFO - Epoch(train) [128][100/293] lr: 5.000000e-04 eta: 2:53:47 time: 0.502761 data_time: 0.078857 memory: 9871 loss_kpt: 0.000579 acc_pose: 0.845508 loss: 0.000579 2022/09/13 17:52:10 - mmengine - INFO - Epoch(train) [128][150/293] lr: 5.000000e-04 eta: 2:53:28 time: 0.502846 data_time: 0.073446 memory: 9871 loss_kpt: 0.000564 acc_pose: 0.832563 loss: 0.000564 2022/09/13 17:52:34 - mmengine - INFO - Epoch(train) [128][200/293] lr: 5.000000e-04 eta: 2:53:08 time: 0.499300 data_time: 0.076656 memory: 9871 loss_kpt: 0.000588 acc_pose: 0.825289 loss: 0.000588 2022/09/13 17:52:59 - mmengine - INFO - Epoch(train) [128][250/293] lr: 5.000000e-04 eta: 2:52:49 time: 0.496711 data_time: 0.085686 memory: 9871 loss_kpt: 0.000583 acc_pose: 0.841714 loss: 0.000583 2022/09/13 17:53:21 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 17:53:21 - mmengine - INFO - Saving checkpoint at 128 epochs 2022/09/13 17:53:51 - mmengine - INFO - Epoch(train) [129][50/293] lr: 5.000000e-04 eta: 2:52:00 time: 0.511681 data_time: 0.088384 memory: 9871 loss_kpt: 0.000581 acc_pose: 0.847517 loss: 0.000581 2022/09/13 17:54:16 - mmengine - INFO - Epoch(train) [129][100/293] lr: 5.000000e-04 eta: 2:51:40 time: 0.496237 data_time: 0.073126 memory: 9871 loss_kpt: 0.000586 acc_pose: 0.840140 loss: 0.000586 2022/09/13 17:54:40 - mmengine - INFO - Epoch(train) [129][150/293] lr: 5.000000e-04 eta: 2:51:21 time: 0.497627 data_time: 0.076089 memory: 9871 loss_kpt: 0.000586 acc_pose: 0.826990 loss: 0.000586 2022/09/13 17:55:05 - mmengine - INFO - Epoch(train) [129][200/293] lr: 5.000000e-04 eta: 2:51:01 time: 0.493180 data_time: 0.076267 memory: 9871 loss_kpt: 0.000591 acc_pose: 0.881094 loss: 0.000591 2022/09/13 17:55:31 - mmengine - INFO - Epoch(train) [129][250/293] lr: 5.000000e-04 eta: 2:50:43 time: 0.518299 data_time: 0.074862 memory: 9871 loss_kpt: 0.000575 acc_pose: 0.857452 loss: 0.000575 2022/09/13 17:55:53 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 17:55:53 - mmengine - INFO - Saving checkpoint at 129 epochs 2022/09/13 17:56:23 - mmengine - INFO - Epoch(train) [130][50/293] lr: 5.000000e-04 eta: 2:49:53 time: 0.511485 data_time: 0.088711 memory: 9871 loss_kpt: 0.000575 acc_pose: 0.837932 loss: 0.000575 2022/09/13 17:56:48 - mmengine - INFO - Epoch(train) [130][100/293] lr: 5.000000e-04 eta: 2:49:34 time: 0.498719 data_time: 0.073103 memory: 9871 loss_kpt: 0.000569 acc_pose: 0.827497 loss: 0.000569 2022/09/13 17:57:13 - mmengine - INFO - Epoch(train) [130][150/293] lr: 5.000000e-04 eta: 2:49:14 time: 0.491594 data_time: 0.077615 memory: 9871 loss_kpt: 0.000581 acc_pose: 0.808353 loss: 0.000581 2022/09/13 17:57:38 - mmengine - INFO - Epoch(train) [130][200/293] lr: 5.000000e-04 eta: 2:48:55 time: 0.503478 data_time: 0.084669 memory: 9871 loss_kpt: 0.000591 acc_pose: 0.805966 loss: 0.000591 2022/09/13 17:57:40 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 17:58:04 - mmengine - INFO - Epoch(train) [130][250/293] lr: 5.000000e-04 eta: 2:48:36 time: 0.512279 data_time: 0.073345 memory: 9871 loss_kpt: 0.000581 acc_pose: 0.842811 loss: 0.000581 2022/09/13 17:58:25 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 17:58:25 - mmengine - INFO - Saving checkpoint at 130 epochs 2022/09/13 17:58:37 - mmengine - INFO - Epoch(val) [130][50/407] eta: 0:00:59 time: 0.166178 data_time: 0.012614 memory: 9871 2022/09/13 17:58:45 - mmengine - INFO - Epoch(val) [130][100/407] eta: 0:00:48 time: 0.159125 data_time: 0.007695 memory: 920 2022/09/13 17:58:53 - mmengine - INFO - Epoch(val) [130][150/407] eta: 0:00:42 time: 0.164560 data_time: 0.009023 memory: 920 2022/09/13 17:59:01 - mmengine - INFO - Epoch(val) [130][200/407] eta: 0:00:33 time: 0.160807 data_time: 0.008160 memory: 920 2022/09/13 17:59:09 - mmengine - INFO - Epoch(val) [130][250/407] eta: 0:00:24 time: 0.157656 data_time: 0.007460 memory: 920 2022/09/13 17:59:17 - mmengine - INFO - Epoch(val) [130][300/407] eta: 0:00:16 time: 0.158380 data_time: 0.007809 memory: 920 2022/09/13 17:59:25 - mmengine - INFO - Epoch(val) [130][350/407] eta: 0:00:09 time: 0.160697 data_time: 0.007779 memory: 920 2022/09/13 17:59:33 - mmengine - INFO - Epoch(val) [130][400/407] eta: 0:00:01 time: 0.154209 data_time: 0.006909 memory: 920 2022/09/13 18:00:10 - mmengine - INFO - Evaluating CocoMetric... 2022/09/13 18:00:23 - mmengine - INFO - Epoch(val) [130][407/407] coco/AP: 0.743887 coco/AP .5: 0.903508 coco/AP .75: 0.811926 coco/AP (M): 0.708059 coco/AP (L): 0.810838 coco/AR: 0.796269 coco/AR .5: 0.941278 coco/AR .75: 0.858627 coco/AR (M): 0.754876 coco/AR (L): 0.856633 2022/09/13 18:00:23 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220913/dark_w32_256_v1/best_coco/AP_epoch_120.pth is removed 2022/09/13 18:00:27 - mmengine - INFO - The best checkpoint with 0.7439 coco/AP at 130 epoch is saved to best_coco/AP_epoch_130.pth. 2022/09/13 18:00:52 - mmengine - INFO - Epoch(train) [131][50/293] lr: 5.000000e-04 eta: 2:47:47 time: 0.500509 data_time: 0.079869 memory: 9871 loss_kpt: 0.000569 acc_pose: 0.818464 loss: 0.000569 2022/09/13 18:01:17 - mmengine - INFO - Epoch(train) [131][100/293] lr: 5.000000e-04 eta: 2:47:28 time: 0.502761 data_time: 0.074226 memory: 9871 loss_kpt: 0.000579 acc_pose: 0.840557 loss: 0.000579 2022/09/13 18:01:42 - mmengine - INFO - Epoch(train) [131][150/293] lr: 5.000000e-04 eta: 2:47:08 time: 0.497727 data_time: 0.078751 memory: 9871 loss_kpt: 0.000581 acc_pose: 0.793968 loss: 0.000581 2022/09/13 18:02:07 - mmengine - INFO - Epoch(train) [131][200/293] lr: 5.000000e-04 eta: 2:46:49 time: 0.507186 data_time: 0.071592 memory: 9871 loss_kpt: 0.000594 acc_pose: 0.820617 loss: 0.000594 2022/09/13 18:02:32 - mmengine - INFO - Epoch(train) [131][250/293] lr: 5.000000e-04 eta: 2:46:30 time: 0.504850 data_time: 0.076011 memory: 9871 loss_kpt: 0.000592 acc_pose: 0.847753 loss: 0.000592 2022/09/13 18:02:53 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 18:02:53 - mmengine - INFO - Saving checkpoint at 131 epochs 2022/09/13 18:03:24 - mmengine - INFO - Epoch(train) [132][50/293] lr: 5.000000e-04 eta: 2:45:41 time: 0.520544 data_time: 0.088556 memory: 9871 loss_kpt: 0.000586 acc_pose: 0.803709 loss: 0.000586 2022/09/13 18:03:49 - mmengine - INFO - Epoch(train) [132][100/293] lr: 5.000000e-04 eta: 2:45:22 time: 0.501192 data_time: 0.076265 memory: 9871 loss_kpt: 0.000587 acc_pose: 0.851907 loss: 0.000587 2022/09/13 18:04:14 - mmengine - INFO - Epoch(train) [132][150/293] lr: 5.000000e-04 eta: 2:45:02 time: 0.501512 data_time: 0.082511 memory: 9871 loss_kpt: 0.000590 acc_pose: 0.790210 loss: 0.000590 2022/09/13 18:04:39 - mmengine - INFO - Epoch(train) [132][200/293] lr: 5.000000e-04 eta: 2:44:43 time: 0.504017 data_time: 0.076480 memory: 9871 loss_kpt: 0.000573 acc_pose: 0.799592 loss: 0.000573 2022/09/13 18:05:04 - mmengine - INFO - Epoch(train) [132][250/293] lr: 5.000000e-04 eta: 2:44:23 time: 0.496461 data_time: 0.076697 memory: 9871 loss_kpt: 0.000584 acc_pose: 0.818479 loss: 0.000584 2022/09/13 18:05:25 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 18:05:25 - mmengine - INFO - Saving checkpoint at 132 epochs 2022/09/13 18:05:56 - mmengine - INFO - Epoch(train) [133][50/293] lr: 5.000000e-04 eta: 2:43:35 time: 0.519610 data_time: 0.087068 memory: 9871 loss_kpt: 0.000565 acc_pose: 0.851831 loss: 0.000565 2022/09/13 18:06:21 - mmengine - INFO - Epoch(train) [133][100/293] lr: 5.000000e-04 eta: 2:43:15 time: 0.496193 data_time: 0.083013 memory: 9871 loss_kpt: 0.000582 acc_pose: 0.869947 loss: 0.000582 2022/09/13 18:06:46 - mmengine - INFO - Epoch(train) [133][150/293] lr: 5.000000e-04 eta: 2:42:56 time: 0.500165 data_time: 0.077441 memory: 9871 loss_kpt: 0.000583 acc_pose: 0.800558 loss: 0.000583 2022/09/13 18:07:11 - mmengine - INFO - Epoch(train) [133][200/293] lr: 5.000000e-04 eta: 2:42:37 time: 0.507967 data_time: 0.083096 memory: 9871 loss_kpt: 0.000584 acc_pose: 0.830366 loss: 0.000584 2022/09/13 18:07:36 - mmengine - INFO - Epoch(train) [133][250/293] lr: 5.000000e-04 eta: 2:42:17 time: 0.498119 data_time: 0.073208 memory: 9871 loss_kpt: 0.000581 acc_pose: 0.838366 loss: 0.000581 2022/09/13 18:07:57 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 18:07:57 - mmengine - INFO - Saving checkpoint at 133 epochs 2022/09/13 18:08:19 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 18:08:28 - mmengine - INFO - Epoch(train) [134][50/293] lr: 5.000000e-04 eta: 2:41:29 time: 0.520482 data_time: 0.091554 memory: 9871 loss_kpt: 0.000569 acc_pose: 0.836908 loss: 0.000569 2022/09/13 18:08:53 - mmengine - INFO - Epoch(train) [134][100/293] lr: 5.000000e-04 eta: 2:41:10 time: 0.505916 data_time: 0.072754 memory: 9871 loss_kpt: 0.000577 acc_pose: 0.821836 loss: 0.000577 2022/09/13 18:09:18 - mmengine - INFO - Epoch(train) [134][150/293] lr: 5.000000e-04 eta: 2:40:50 time: 0.500147 data_time: 0.077799 memory: 9871 loss_kpt: 0.000581 acc_pose: 0.846226 loss: 0.000581 2022/09/13 18:09:43 - mmengine - INFO - Epoch(train) [134][200/293] lr: 5.000000e-04 eta: 2:40:30 time: 0.500108 data_time: 0.073696 memory: 9871 loss_kpt: 0.000566 acc_pose: 0.807430 loss: 0.000566 2022/09/13 18:10:08 - mmengine - INFO - Epoch(train) [134][250/293] lr: 5.000000e-04 eta: 2:40:11 time: 0.487430 data_time: 0.072644 memory: 9871 loss_kpt: 0.000583 acc_pose: 0.877638 loss: 0.000583 2022/09/13 18:10:29 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 18:10:29 - mmengine - INFO - Saving checkpoint at 134 epochs 2022/09/13 18:10:59 - mmengine - INFO - Epoch(train) [135][50/293] lr: 5.000000e-04 eta: 2:39:22 time: 0.509977 data_time: 0.083517 memory: 9871 loss_kpt: 0.000580 acc_pose: 0.779960 loss: 0.000580 2022/09/13 18:11:24 - mmengine - INFO - Epoch(train) [135][100/293] lr: 5.000000e-04 eta: 2:39:02 time: 0.489682 data_time: 0.072927 memory: 9871 loss_kpt: 0.000580 acc_pose: 0.824311 loss: 0.000580 2022/09/13 18:11:49 - mmengine - INFO - Epoch(train) [135][150/293] lr: 5.000000e-04 eta: 2:38:43 time: 0.511947 data_time: 0.083097 memory: 9871 loss_kpt: 0.000594 acc_pose: 0.827213 loss: 0.000594 2022/09/13 18:12:14 - mmengine - INFO - Epoch(train) [135][200/293] lr: 5.000000e-04 eta: 2:38:24 time: 0.498883 data_time: 0.077172 memory: 9871 loss_kpt: 0.000600 acc_pose: 0.807787 loss: 0.000600 2022/09/13 18:12:40 - mmengine - INFO - Epoch(train) [135][250/293] lr: 5.000000e-04 eta: 2:38:04 time: 0.508583 data_time: 0.076790 memory: 9871 loss_kpt: 0.000585 acc_pose: 0.835999 loss: 0.000585 2022/09/13 18:13:01 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 18:13:01 - mmengine - INFO - Saving checkpoint at 135 epochs 2022/09/13 18:13:31 - mmengine - INFO - Epoch(train) [136][50/293] lr: 5.000000e-04 eta: 2:37:16 time: 0.514985 data_time: 0.085996 memory: 9871 loss_kpt: 0.000570 acc_pose: 0.791779 loss: 0.000570 2022/09/13 18:13:57 - mmengine - INFO - Epoch(train) [136][100/293] lr: 5.000000e-04 eta: 2:36:57 time: 0.505151 data_time: 0.083056 memory: 9871 loss_kpt: 0.000592 acc_pose: 0.790225 loss: 0.000592 2022/09/13 18:14:22 - mmengine - INFO - Epoch(train) [136][150/293] lr: 5.000000e-04 eta: 2:36:37 time: 0.511882 data_time: 0.074017 memory: 9871 loss_kpt: 0.000572 acc_pose: 0.856072 loss: 0.000572 2022/09/13 18:14:47 - mmengine - INFO - Epoch(train) [136][200/293] lr: 5.000000e-04 eta: 2:36:18 time: 0.504538 data_time: 0.082774 memory: 9871 loss_kpt: 0.000572 acc_pose: 0.804596 loss: 0.000572 2022/09/13 18:15:12 - mmengine - INFO - Epoch(train) [136][250/293] lr: 5.000000e-04 eta: 2:35:58 time: 0.490574 data_time: 0.074001 memory: 9871 loss_kpt: 0.000575 acc_pose: 0.829088 loss: 0.000575 2022/09/13 18:15:33 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 18:15:33 - mmengine - INFO - Saving checkpoint at 136 epochs 2022/09/13 18:16:03 - mmengine - INFO - Epoch(train) [137][50/293] lr: 5.000000e-04 eta: 2:35:10 time: 0.508861 data_time: 0.084328 memory: 9871 loss_kpt: 0.000567 acc_pose: 0.886530 loss: 0.000567 2022/09/13 18:16:28 - mmengine - INFO - Epoch(train) [137][100/293] lr: 5.000000e-04 eta: 2:34:50 time: 0.497478 data_time: 0.075932 memory: 9871 loss_kpt: 0.000573 acc_pose: 0.854161 loss: 0.000573 2022/09/13 18:16:53 - mmengine - INFO - Epoch(train) [137][150/293] lr: 5.000000e-04 eta: 2:34:31 time: 0.504625 data_time: 0.083323 memory: 9871 loss_kpt: 0.000589 acc_pose: 0.795035 loss: 0.000589 2022/09/13 18:16:54 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 18:17:19 - mmengine - INFO - Epoch(train) [137][200/293] lr: 5.000000e-04 eta: 2:34:11 time: 0.503063 data_time: 0.074865 memory: 9871 loss_kpt: 0.000581 acc_pose: 0.848805 loss: 0.000581 2022/09/13 18:17:43 - mmengine - INFO - Epoch(train) [137][250/293] lr: 5.000000e-04 eta: 2:33:51 time: 0.490623 data_time: 0.076428 memory: 9871 loss_kpt: 0.000584 acc_pose: 0.817595 loss: 0.000584 2022/09/13 18:18:04 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 18:18:04 - mmengine - INFO - Saving checkpoint at 137 epochs 2022/09/13 18:18:35 - mmengine - INFO - Epoch(train) [138][50/293] lr: 5.000000e-04 eta: 2:33:04 time: 0.514495 data_time: 0.086394 memory: 9871 loss_kpt: 0.000568 acc_pose: 0.842602 loss: 0.000568 2022/09/13 18:18:59 - mmengine - INFO - Epoch(train) [138][100/293] lr: 5.000000e-04 eta: 2:32:44 time: 0.489928 data_time: 0.077305 memory: 9871 loss_kpt: 0.000564 acc_pose: 0.822183 loss: 0.000564 2022/09/13 18:19:24 - mmengine - INFO - Epoch(train) [138][150/293] lr: 5.000000e-04 eta: 2:32:24 time: 0.505659 data_time: 0.078087 memory: 9871 loss_kpt: 0.000574 acc_pose: 0.814317 loss: 0.000574 2022/09/13 18:19:50 - mmengine - INFO - Epoch(train) [138][200/293] lr: 5.000000e-04 eta: 2:32:05 time: 0.506391 data_time: 0.075725 memory: 9871 loss_kpt: 0.000585 acc_pose: 0.861419 loss: 0.000585 2022/09/13 18:20:15 - mmengine - INFO - Epoch(train) [138][250/293] lr: 5.000000e-04 eta: 2:31:45 time: 0.500968 data_time: 0.077321 memory: 9871 loss_kpt: 0.000573 acc_pose: 0.865860 loss: 0.000573 2022/09/13 18:20:36 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 18:20:36 - mmengine - INFO - Saving checkpoint at 138 epochs 2022/09/13 18:21:06 - mmengine - INFO - Epoch(train) [139][50/293] lr: 5.000000e-04 eta: 2:30:57 time: 0.511006 data_time: 0.088854 memory: 9871 loss_kpt: 0.000585 acc_pose: 0.798718 loss: 0.000585 2022/09/13 18:21:31 - mmengine - INFO - Epoch(train) [139][100/293] lr: 5.000000e-04 eta: 2:30:38 time: 0.501069 data_time: 0.073455 memory: 9871 loss_kpt: 0.000581 acc_pose: 0.817992 loss: 0.000581 2022/09/13 18:21:56 - mmengine - INFO - Epoch(train) [139][150/293] lr: 5.000000e-04 eta: 2:30:18 time: 0.498481 data_time: 0.077641 memory: 9871 loss_kpt: 0.000568 acc_pose: 0.831566 loss: 0.000568 2022/09/13 18:22:21 - mmengine - INFO - Epoch(train) [139][200/293] lr: 5.000000e-04 eta: 2:29:58 time: 0.503714 data_time: 0.079102 memory: 9871 loss_kpt: 0.000574 acc_pose: 0.873848 loss: 0.000574 2022/09/13 18:22:46 - mmengine - INFO - Epoch(train) [139][250/293] lr: 5.000000e-04 eta: 2:29:39 time: 0.506711 data_time: 0.074949 memory: 9871 loss_kpt: 0.000577 acc_pose: 0.870543 loss: 0.000577 2022/09/13 18:23:08 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 18:23:08 - mmengine - INFO - Saving checkpoint at 139 epochs 2022/09/13 18:23:37 - mmengine - INFO - Epoch(train) [140][50/293] lr: 5.000000e-04 eta: 2:28:51 time: 0.514071 data_time: 0.087478 memory: 9871 loss_kpt: 0.000578 acc_pose: 0.805874 loss: 0.000578 2022/09/13 18:24:02 - mmengine - INFO - Epoch(train) [140][100/293] lr: 5.000000e-04 eta: 2:28:31 time: 0.497449 data_time: 0.077537 memory: 9871 loss_kpt: 0.000584 acc_pose: 0.826157 loss: 0.000584 2022/09/13 18:24:27 - mmengine - INFO - Epoch(train) [140][150/293] lr: 5.000000e-04 eta: 2:28:12 time: 0.499160 data_time: 0.075725 memory: 9871 loss_kpt: 0.000581 acc_pose: 0.797700 loss: 0.000581 2022/09/13 18:24:53 - mmengine - INFO - Epoch(train) [140][200/293] lr: 5.000000e-04 eta: 2:27:52 time: 0.504990 data_time: 0.076220 memory: 9871 loss_kpt: 0.000584 acc_pose: 0.846070 loss: 0.000584 2022/09/13 18:25:18 - mmengine - INFO - Epoch(train) [140][250/293] lr: 5.000000e-04 eta: 2:27:32 time: 0.505394 data_time: 0.081090 memory: 9871 loss_kpt: 0.000576 acc_pose: 0.846334 loss: 0.000576 2022/09/13 18:25:29 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 18:25:39 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 18:25:39 - mmengine - INFO - Saving checkpoint at 140 epochs 2022/09/13 18:25:52 - mmengine - INFO - Epoch(val) [140][50/407] eta: 0:00:58 time: 0.163811 data_time: 0.011974 memory: 9871 2022/09/13 18:26:00 - mmengine - INFO - Epoch(val) [140][100/407] eta: 0:00:49 time: 0.160415 data_time: 0.011092 memory: 920 2022/09/13 18:26:08 - mmengine - INFO - Epoch(val) [140][150/407] eta: 0:00:40 time: 0.157942 data_time: 0.007584 memory: 920 2022/09/13 18:26:16 - mmengine - INFO - Epoch(val) [140][200/407] eta: 0:00:32 time: 0.156968 data_time: 0.007665 memory: 920 2022/09/13 18:26:24 - mmengine - INFO - Epoch(val) [140][250/407] eta: 0:00:24 time: 0.159007 data_time: 0.007672 memory: 920 2022/09/13 18:26:32 - mmengine - INFO - Epoch(val) [140][300/407] eta: 0:00:16 time: 0.157759 data_time: 0.007518 memory: 920 2022/09/13 18:26:40 - mmengine - INFO - Epoch(val) [140][350/407] eta: 0:00:08 time: 0.156935 data_time: 0.007761 memory: 920 2022/09/13 18:26:48 - mmengine - INFO - Epoch(val) [140][400/407] eta: 0:00:01 time: 0.158637 data_time: 0.007637 memory: 920 2022/09/13 18:27:24 - mmengine - INFO - Evaluating CocoMetric... 2022/09/13 18:27:38 - mmengine - INFO - Epoch(val) [140][407/407] coco/AP: 0.745165 coco/AP .5: 0.900477 coco/AP .75: 0.813128 coco/AP (M): 0.708961 coco/AP (L): 0.812720 coco/AR: 0.796599 coco/AR .5: 0.938287 coco/AR .75: 0.857997 coco/AR (M): 0.755094 coco/AR (L): 0.856931 2022/09/13 18:27:38 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220913/dark_w32_256_v1/best_coco/AP_epoch_130.pth is removed 2022/09/13 18:27:41 - mmengine - INFO - The best checkpoint with 0.7452 coco/AP at 140 epoch is saved to best_coco/AP_epoch_140.pth. 2022/09/13 18:28:06 - mmengine - INFO - Epoch(train) [141][50/293] lr: 5.000000e-04 eta: 2:26:45 time: 0.511493 data_time: 0.079222 memory: 9871 loss_kpt: 0.000571 acc_pose: 0.825885 loss: 0.000571 2022/09/13 18:28:32 - mmengine - INFO - Epoch(train) [141][100/293] lr: 5.000000e-04 eta: 2:26:25 time: 0.508665 data_time: 0.072934 memory: 9871 loss_kpt: 0.000579 acc_pose: 0.810685 loss: 0.000579 2022/09/13 18:28:57 - mmengine - INFO - Epoch(train) [141][150/293] lr: 5.000000e-04 eta: 2:26:06 time: 0.506859 data_time: 0.082778 memory: 9871 loss_kpt: 0.000568 acc_pose: 0.824985 loss: 0.000568 2022/09/13 18:29:22 - mmengine - INFO - Epoch(train) [141][200/293] lr: 5.000000e-04 eta: 2:25:46 time: 0.503225 data_time: 0.069840 memory: 9871 loss_kpt: 0.000596 acc_pose: 0.808353 loss: 0.000596 2022/09/13 18:29:47 - mmengine - INFO - Epoch(train) [141][250/293] lr: 5.000000e-04 eta: 2:25:26 time: 0.497870 data_time: 0.072167 memory: 9871 loss_kpt: 0.000573 acc_pose: 0.850608 loss: 0.000573 2022/09/13 18:30:09 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 18:30:09 - mmengine - INFO - Saving checkpoint at 141 epochs 2022/09/13 18:30:39 - mmengine - INFO - Epoch(train) [142][50/293] lr: 5.000000e-04 eta: 2:24:39 time: 0.516776 data_time: 0.083279 memory: 9871 loss_kpt: 0.000582 acc_pose: 0.852969 loss: 0.000582 2022/09/13 18:31:05 - mmengine - INFO - Epoch(train) [142][100/293] lr: 5.000000e-04 eta: 2:24:20 time: 0.512197 data_time: 0.078315 memory: 9871 loss_kpt: 0.000565 acc_pose: 0.848776 loss: 0.000565 2022/09/13 18:31:30 - mmengine - INFO - Epoch(train) [142][150/293] lr: 5.000000e-04 eta: 2:24:00 time: 0.501725 data_time: 0.076725 memory: 9871 loss_kpt: 0.000579 acc_pose: 0.851365 loss: 0.000579 2022/09/13 18:31:55 - mmengine - INFO - Epoch(train) [142][200/293] lr: 5.000000e-04 eta: 2:23:40 time: 0.506830 data_time: 0.079829 memory: 9871 loss_kpt: 0.000574 acc_pose: 0.801523 loss: 0.000574 2022/09/13 18:32:20 - mmengine - INFO - Epoch(train) [142][250/293] lr: 5.000000e-04 eta: 2:23:20 time: 0.495581 data_time: 0.075458 memory: 9871 loss_kpt: 0.000579 acc_pose: 0.773729 loss: 0.000579 2022/09/13 18:32:41 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 18:32:41 - mmengine - INFO - Saving checkpoint at 142 epochs 2022/09/13 18:33:11 - mmengine - INFO - Epoch(train) [143][50/293] lr: 5.000000e-04 eta: 2:22:33 time: 0.508555 data_time: 0.080940 memory: 9871 loss_kpt: 0.000570 acc_pose: 0.766490 loss: 0.000570 2022/09/13 18:33:36 - mmengine - INFO - Epoch(train) [143][100/293] lr: 5.000000e-04 eta: 2:22:13 time: 0.496996 data_time: 0.075980 memory: 9871 loss_kpt: 0.000580 acc_pose: 0.811166 loss: 0.000580 2022/09/13 18:34:01 - mmengine - INFO - Epoch(train) [143][150/293] lr: 5.000000e-04 eta: 2:21:54 time: 0.506273 data_time: 0.084008 memory: 9871 loss_kpt: 0.000563 acc_pose: 0.849605 loss: 0.000563 2022/09/13 18:34:26 - mmengine - INFO - Epoch(train) [143][200/293] lr: 5.000000e-04 eta: 2:21:34 time: 0.498197 data_time: 0.076463 memory: 9871 loss_kpt: 0.000565 acc_pose: 0.830495 loss: 0.000565 2022/09/13 18:34:50 - mmengine - INFO - Epoch(train) [143][250/293] lr: 5.000000e-04 eta: 2:21:13 time: 0.488714 data_time: 0.076408 memory: 9871 loss_kpt: 0.000578 acc_pose: 0.833696 loss: 0.000578 2022/09/13 18:35:12 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 18:35:12 - mmengine - INFO - Saving checkpoint at 143 epochs 2022/09/13 18:35:43 - mmengine - INFO - Epoch(train) [144][50/293] lr: 5.000000e-04 eta: 2:20:26 time: 0.502922 data_time: 0.085467 memory: 9871 loss_kpt: 0.000572 acc_pose: 0.873886 loss: 0.000572 2022/09/13 18:36:08 - mmengine - INFO - Epoch(train) [144][100/293] lr: 5.000000e-04 eta: 2:20:07 time: 0.503060 data_time: 0.083521 memory: 9871 loss_kpt: 0.000561 acc_pose: 0.851403 loss: 0.000561 2022/09/13 18:36:08 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 18:36:33 - mmengine - INFO - Epoch(train) [144][150/293] lr: 5.000000e-04 eta: 2:19:47 time: 0.508530 data_time: 0.081559 memory: 9871 loss_kpt: 0.000581 acc_pose: 0.848064 loss: 0.000581 2022/09/13 18:36:58 - mmengine - INFO - Epoch(train) [144][200/293] lr: 5.000000e-04 eta: 2:19:27 time: 0.496911 data_time: 0.077535 memory: 9871 loss_kpt: 0.000583 acc_pose: 0.839325 loss: 0.000583 2022/09/13 18:37:23 - mmengine - INFO - Epoch(train) [144][250/293] lr: 5.000000e-04 eta: 2:19:07 time: 0.492322 data_time: 0.072994 memory: 9871 loss_kpt: 0.000568 acc_pose: 0.828558 loss: 0.000568 2022/09/13 18:37:44 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 18:37:44 - mmengine - INFO - Saving checkpoint at 144 epochs 2022/09/13 18:38:14 - mmengine - INFO - Epoch(train) [145][50/293] lr: 5.000000e-04 eta: 2:18:20 time: 0.509075 data_time: 0.086715 memory: 9871 loss_kpt: 0.000574 acc_pose: 0.860491 loss: 0.000574 2022/09/13 18:38:39 - mmengine - INFO - Epoch(train) [145][100/293] lr: 5.000000e-04 eta: 2:18:00 time: 0.504064 data_time: 0.078816 memory: 9871 loss_kpt: 0.000583 acc_pose: 0.823003 loss: 0.000583 2022/09/13 18:39:04 - mmengine - INFO - Epoch(train) [145][150/293] lr: 5.000000e-04 eta: 2:17:40 time: 0.509104 data_time: 0.074762 memory: 9871 loss_kpt: 0.000564 acc_pose: 0.826286 loss: 0.000564 2022/09/13 18:39:29 - mmengine - INFO - Epoch(train) [145][200/293] lr: 5.000000e-04 eta: 2:17:20 time: 0.491606 data_time: 0.071217 memory: 9871 loss_kpt: 0.000561 acc_pose: 0.832056 loss: 0.000561 2022/09/13 18:39:54 - mmengine - INFO - Epoch(train) [145][250/293] lr: 5.000000e-04 eta: 2:17:00 time: 0.502937 data_time: 0.076089 memory: 9871 loss_kpt: 0.000592 acc_pose: 0.849200 loss: 0.000592 2022/09/13 18:40:15 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 18:40:15 - mmengine - INFO - Saving checkpoint at 145 epochs 2022/09/13 18:40:45 - mmengine - INFO - Epoch(train) [146][50/293] lr: 5.000000e-04 eta: 2:16:14 time: 0.517864 data_time: 0.079970 memory: 9871 loss_kpt: 0.000575 acc_pose: 0.812641 loss: 0.000575 2022/09/13 18:41:11 - mmengine - INFO - Epoch(train) [146][100/293] lr: 5.000000e-04 eta: 2:15:54 time: 0.506609 data_time: 0.079666 memory: 9871 loss_kpt: 0.000578 acc_pose: 0.807211 loss: 0.000578 2022/09/13 18:41:35 - mmengine - INFO - Epoch(train) [146][150/293] lr: 5.000000e-04 eta: 2:15:34 time: 0.493217 data_time: 0.071803 memory: 9871 loss_kpt: 0.000575 acc_pose: 0.816899 loss: 0.000575 2022/09/13 18:42:00 - mmengine - INFO - Epoch(train) [146][200/293] lr: 5.000000e-04 eta: 2:15:14 time: 0.493200 data_time: 0.077543 memory: 9871 loss_kpt: 0.000573 acc_pose: 0.856015 loss: 0.000573 2022/09/13 18:42:25 - mmengine - INFO - Epoch(train) [146][250/293] lr: 5.000000e-04 eta: 2:14:54 time: 0.499343 data_time: 0.077603 memory: 9871 loss_kpt: 0.000566 acc_pose: 0.811270 loss: 0.000566 2022/09/13 18:42:47 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 18:42:47 - mmengine - INFO - Saving checkpoint at 146 epochs 2022/09/13 18:43:18 - mmengine - INFO - Epoch(train) [147][50/293] lr: 5.000000e-04 eta: 2:14:08 time: 0.524169 data_time: 0.089193 memory: 9871 loss_kpt: 0.000552 acc_pose: 0.794705 loss: 0.000552 2022/09/13 18:43:43 - mmengine - INFO - Epoch(train) [147][100/293] lr: 5.000000e-04 eta: 2:13:48 time: 0.506062 data_time: 0.073379 memory: 9871 loss_kpt: 0.000566 acc_pose: 0.784202 loss: 0.000566 2022/09/13 18:44:09 - mmengine - INFO - Epoch(train) [147][150/293] lr: 5.000000e-04 eta: 2:13:28 time: 0.515149 data_time: 0.078411 memory: 9871 loss_kpt: 0.000570 acc_pose: 0.839950 loss: 0.000570 2022/09/13 18:44:33 - mmengine - INFO - Epoch(train) [147][200/293] lr: 5.000000e-04 eta: 2:13:08 time: 0.486312 data_time: 0.073170 memory: 9871 loss_kpt: 0.000574 acc_pose: 0.832506 loss: 0.000574 2022/09/13 18:44:44 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 18:44:58 - mmengine - INFO - Epoch(train) [147][250/293] lr: 5.000000e-04 eta: 2:12:48 time: 0.498890 data_time: 0.071412 memory: 9871 loss_kpt: 0.000580 acc_pose: 0.816939 loss: 0.000580 2022/09/13 18:45:20 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 18:45:20 - mmengine - INFO - Saving checkpoint at 147 epochs 2022/09/13 18:45:50 - mmengine - INFO - Epoch(train) [148][50/293] lr: 5.000000e-04 eta: 2:12:02 time: 0.515466 data_time: 0.083188 memory: 9871 loss_kpt: 0.000581 acc_pose: 0.839309 loss: 0.000581 2022/09/13 18:46:15 - mmengine - INFO - Epoch(train) [148][100/293] lr: 5.000000e-04 eta: 2:11:42 time: 0.500659 data_time: 0.076906 memory: 9871 loss_kpt: 0.000567 acc_pose: 0.843398 loss: 0.000567 2022/09/13 18:46:40 - mmengine - INFO - Epoch(train) [148][150/293] lr: 5.000000e-04 eta: 2:11:22 time: 0.496740 data_time: 0.076231 memory: 9871 loss_kpt: 0.000582 acc_pose: 0.852016 loss: 0.000582 2022/09/13 18:47:05 - mmengine - INFO - Epoch(train) [148][200/293] lr: 5.000000e-04 eta: 2:11:02 time: 0.502687 data_time: 0.075617 memory: 9871 loss_kpt: 0.000574 acc_pose: 0.858145 loss: 0.000574 2022/09/13 18:47:30 - mmengine - INFO - Epoch(train) [148][250/293] lr: 5.000000e-04 eta: 2:10:41 time: 0.492222 data_time: 0.083567 memory: 9871 loss_kpt: 0.000572 acc_pose: 0.841351 loss: 0.000572 2022/09/13 18:47:51 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 18:47:51 - mmengine - INFO - Saving checkpoint at 148 epochs 2022/09/13 18:48:21 - mmengine - INFO - Epoch(train) [149][50/293] lr: 5.000000e-04 eta: 2:09:55 time: 0.513801 data_time: 0.089593 memory: 9871 loss_kpt: 0.000587 acc_pose: 0.816795 loss: 0.000587 2022/09/13 18:48:47 - mmengine - INFO - Epoch(train) [149][100/293] lr: 5.000000e-04 eta: 2:09:35 time: 0.511618 data_time: 0.079747 memory: 9871 loss_kpt: 0.000577 acc_pose: 0.820071 loss: 0.000577 2022/09/13 18:49:12 - mmengine - INFO - Epoch(train) [149][150/293] lr: 5.000000e-04 eta: 2:09:15 time: 0.498026 data_time: 0.075765 memory: 9871 loss_kpt: 0.000571 acc_pose: 0.866327 loss: 0.000571 2022/09/13 18:49:37 - mmengine - INFO - Epoch(train) [149][200/293] lr: 5.000000e-04 eta: 2:08:55 time: 0.493490 data_time: 0.071345 memory: 9871 loss_kpt: 0.000578 acc_pose: 0.857899 loss: 0.000578 2022/09/13 18:50:02 - mmengine - INFO - Epoch(train) [149][250/293] lr: 5.000000e-04 eta: 2:08:35 time: 0.499035 data_time: 0.080081 memory: 9871 loss_kpt: 0.000580 acc_pose: 0.867152 loss: 0.000580 2022/09/13 18:50:23 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 18:50:23 - mmengine - INFO - Saving checkpoint at 149 epochs 2022/09/13 18:50:53 - mmengine - INFO - Epoch(train) [150][50/293] lr: 5.000000e-04 eta: 2:07:49 time: 0.506674 data_time: 0.086613 memory: 9871 loss_kpt: 0.000587 acc_pose: 0.824344 loss: 0.000587 2022/09/13 18:51:18 - mmengine - INFO - Epoch(train) [150][100/293] lr: 5.000000e-04 eta: 2:07:29 time: 0.499695 data_time: 0.070834 memory: 9871 loss_kpt: 0.000569 acc_pose: 0.824241 loss: 0.000569 2022/09/13 18:51:42 - mmengine - INFO - Epoch(train) [150][150/293] lr: 5.000000e-04 eta: 2:07:09 time: 0.491816 data_time: 0.076200 memory: 9871 loss_kpt: 0.000569 acc_pose: 0.802641 loss: 0.000569 2022/09/13 18:52:07 - mmengine - INFO - Epoch(train) [150][200/293] lr: 5.000000e-04 eta: 2:06:48 time: 0.496957 data_time: 0.075827 memory: 9871 loss_kpt: 0.000580 acc_pose: 0.807693 loss: 0.000580 2022/09/13 18:52:32 - mmengine - INFO - Epoch(train) [150][250/293] lr: 5.000000e-04 eta: 2:06:28 time: 0.501747 data_time: 0.078941 memory: 9871 loss_kpt: 0.000572 acc_pose: 0.811232 loss: 0.000572 2022/09/13 18:52:54 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 18:52:54 - mmengine - INFO - Saving checkpoint at 150 epochs 2022/09/13 18:53:06 - mmengine - INFO - Epoch(val) [150][50/407] eta: 0:00:59 time: 0.165462 data_time: 0.014155 memory: 9871 2022/09/13 18:53:14 - mmengine - INFO - Epoch(val) [150][100/407] eta: 0:00:48 time: 0.157639 data_time: 0.007422 memory: 920 2022/09/13 18:53:22 - mmengine - INFO - Epoch(val) [150][150/407] eta: 0:00:40 time: 0.158579 data_time: 0.007384 memory: 920 2022/09/13 18:53:30 - mmengine - INFO - Epoch(val) [150][200/407] eta: 0:00:32 time: 0.158182 data_time: 0.007970 memory: 920 2022/09/13 18:53:38 - mmengine - INFO - Epoch(val) [150][250/407] eta: 0:00:24 time: 0.157081 data_time: 0.007310 memory: 920 2022/09/13 18:53:46 - mmengine - INFO - Epoch(val) [150][300/407] eta: 0:00:16 time: 0.157873 data_time: 0.008198 memory: 920 2022/09/13 18:53:54 - mmengine - INFO - Epoch(val) [150][350/407] eta: 0:00:09 time: 0.159606 data_time: 0.009189 memory: 920 2022/09/13 18:54:02 - mmengine - INFO - Epoch(val) [150][400/407] eta: 0:00:01 time: 0.156876 data_time: 0.007418 memory: 920 2022/09/13 18:54:37 - mmengine - INFO - Evaluating CocoMetric... 2022/09/13 18:54:51 - mmengine - INFO - Epoch(val) [150][407/407] coco/AP: 0.744527 coco/AP .5: 0.899263 coco/AP .75: 0.811905 coco/AP (M): 0.708253 coco/AP (L): 0.811973 coco/AR: 0.796332 coco/AR .5: 0.938759 coco/AR .75: 0.857997 coco/AR (M): 0.754657 coco/AR (L): 0.856485 2022/09/13 18:55:18 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 18:55:18 - mmengine - INFO - Epoch(train) [151][50/293] lr: 5.000000e-04 eta: 2:05:43 time: 0.526346 data_time: 0.086636 memory: 9871 loss_kpt: 0.000572 acc_pose: 0.830457 loss: 0.000572 2022/09/13 18:55:43 - mmengine - INFO - Epoch(train) [151][100/293] lr: 5.000000e-04 eta: 2:05:23 time: 0.504549 data_time: 0.075287 memory: 9871 loss_kpt: 0.000573 acc_pose: 0.855788 loss: 0.000573 2022/09/13 18:56:08 - mmengine - INFO - Epoch(train) [151][150/293] lr: 5.000000e-04 eta: 2:05:03 time: 0.500619 data_time: 0.078503 memory: 9871 loss_kpt: 0.000567 acc_pose: 0.836261 loss: 0.000567 2022/09/13 18:56:33 - mmengine - INFO - Epoch(train) [151][200/293] lr: 5.000000e-04 eta: 2:04:42 time: 0.494929 data_time: 0.076177 memory: 9871 loss_kpt: 0.000580 acc_pose: 0.834747 loss: 0.000580 2022/09/13 18:56:58 - mmengine - INFO - Epoch(train) [151][250/293] lr: 5.000000e-04 eta: 2:04:22 time: 0.501364 data_time: 0.072101 memory: 9871 loss_kpt: 0.000581 acc_pose: 0.785518 loss: 0.000581 2022/09/13 18:57:20 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 18:57:20 - mmengine - INFO - Saving checkpoint at 151 epochs 2022/09/13 18:57:49 - mmengine - INFO - Epoch(train) [152][50/293] lr: 5.000000e-04 eta: 2:03:36 time: 0.508310 data_time: 0.083978 memory: 9871 loss_kpt: 0.000575 acc_pose: 0.815993 loss: 0.000575 2022/09/13 18:58:15 - mmengine - INFO - Epoch(train) [152][100/293] lr: 5.000000e-04 eta: 2:03:16 time: 0.506006 data_time: 0.082025 memory: 9871 loss_kpt: 0.000571 acc_pose: 0.847428 loss: 0.000571 2022/09/13 18:58:40 - mmengine - INFO - Epoch(train) [152][150/293] lr: 5.000000e-04 eta: 2:02:56 time: 0.501034 data_time: 0.075990 memory: 9871 loss_kpt: 0.000566 acc_pose: 0.834629 loss: 0.000566 2022/09/13 18:59:05 - mmengine - INFO - Epoch(train) [152][200/293] lr: 5.000000e-04 eta: 2:02:36 time: 0.494444 data_time: 0.075934 memory: 9871 loss_kpt: 0.000582 acc_pose: 0.784545 loss: 0.000582 2022/09/13 18:59:30 - mmengine - INFO - Epoch(train) [152][250/293] lr: 5.000000e-04 eta: 2:02:16 time: 0.502624 data_time: 0.074490 memory: 9871 loss_kpt: 0.000563 acc_pose: 0.824453 loss: 0.000563 2022/09/13 18:59:51 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 18:59:51 - mmengine - INFO - Saving checkpoint at 152 epochs 2022/09/13 19:00:21 - mmengine - INFO - Epoch(train) [153][50/293] lr: 5.000000e-04 eta: 2:01:30 time: 0.521426 data_time: 0.096660 memory: 9871 loss_kpt: 0.000565 acc_pose: 0.820769 loss: 0.000565 2022/09/13 19:00:47 - mmengine - INFO - Epoch(train) [153][100/293] lr: 5.000000e-04 eta: 2:01:11 time: 0.514673 data_time: 0.075404 memory: 9871 loss_kpt: 0.000575 acc_pose: 0.875060 loss: 0.000575 2022/09/13 19:01:12 - mmengine - INFO - Epoch(train) [153][150/293] lr: 5.000000e-04 eta: 2:00:50 time: 0.501077 data_time: 0.076605 memory: 9871 loss_kpt: 0.000583 acc_pose: 0.823299 loss: 0.000583 2022/09/13 19:01:37 - mmengine - INFO - Epoch(train) [153][200/293] lr: 5.000000e-04 eta: 2:00:30 time: 0.499684 data_time: 0.083780 memory: 9871 loss_kpt: 0.000578 acc_pose: 0.833610 loss: 0.000578 2022/09/13 19:02:02 - mmengine - INFO - Epoch(train) [153][250/293] lr: 5.000000e-04 eta: 2:00:10 time: 0.499277 data_time: 0.078656 memory: 9871 loss_kpt: 0.000567 acc_pose: 0.861596 loss: 0.000567 2022/09/13 19:02:24 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 19:02:24 - mmengine - INFO - Saving checkpoint at 153 epochs 2022/09/13 19:02:54 - mmengine - INFO - Epoch(train) [154][50/293] lr: 5.000000e-04 eta: 1:59:24 time: 0.510854 data_time: 0.084374 memory: 9871 loss_kpt: 0.000567 acc_pose: 0.839474 loss: 0.000567 2022/09/13 19:03:19 - mmengine - INFO - Epoch(train) [154][100/293] lr: 5.000000e-04 eta: 1:59:04 time: 0.497689 data_time: 0.077427 memory: 9871 loss_kpt: 0.000570 acc_pose: 0.860621 loss: 0.000570 2022/09/13 19:03:44 - mmengine - INFO - Epoch(train) [154][150/293] lr: 5.000000e-04 eta: 1:58:44 time: 0.498895 data_time: 0.076189 memory: 9871 loss_kpt: 0.000575 acc_pose: 0.844764 loss: 0.000575 2022/09/13 19:03:54 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 19:04:09 - mmengine - INFO - Epoch(train) [154][200/293] lr: 5.000000e-04 eta: 1:58:24 time: 0.498027 data_time: 0.075742 memory: 9871 loss_kpt: 0.000575 acc_pose: 0.867952 loss: 0.000575 2022/09/13 19:04:33 - mmengine - INFO - Epoch(train) [154][250/293] lr: 5.000000e-04 eta: 1:58:03 time: 0.497445 data_time: 0.070654 memory: 9871 loss_kpt: 0.000573 acc_pose: 0.823907 loss: 0.000573 2022/09/13 19:04:55 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 19:04:55 - mmengine - INFO - Saving checkpoint at 154 epochs 2022/09/13 19:05:27 - mmengine - INFO - Epoch(train) [155][50/293] lr: 5.000000e-04 eta: 1:57:18 time: 0.518295 data_time: 0.086209 memory: 9871 loss_kpt: 0.000574 acc_pose: 0.855862 loss: 0.000574 2022/09/13 19:05:52 - mmengine - INFO - Epoch(train) [155][100/293] lr: 5.000000e-04 eta: 1:56:58 time: 0.501411 data_time: 0.076081 memory: 9871 loss_kpt: 0.000574 acc_pose: 0.848674 loss: 0.000574 2022/09/13 19:06:17 - mmengine - INFO - Epoch(train) [155][150/293] lr: 5.000000e-04 eta: 1:56:38 time: 0.490881 data_time: 0.080361 memory: 9871 loss_kpt: 0.000570 acc_pose: 0.836622 loss: 0.000570 2022/09/13 19:06:42 - mmengine - INFO - Epoch(train) [155][200/293] lr: 5.000000e-04 eta: 1:56:17 time: 0.498368 data_time: 0.074703 memory: 9871 loss_kpt: 0.000576 acc_pose: 0.809626 loss: 0.000576 2022/09/13 19:07:06 - mmengine - INFO - Epoch(train) [155][250/293] lr: 5.000000e-04 eta: 1:55:57 time: 0.492501 data_time: 0.074923 memory: 9871 loss_kpt: 0.000577 acc_pose: 0.816519 loss: 0.000577 2022/09/13 19:07:28 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 19:07:28 - mmengine - INFO - Saving checkpoint at 155 epochs 2022/09/13 19:07:57 - mmengine - INFO - Epoch(train) [156][50/293] lr: 5.000000e-04 eta: 1:55:12 time: 0.506105 data_time: 0.079452 memory: 9871 loss_kpt: 0.000562 acc_pose: 0.813732 loss: 0.000562 2022/09/13 19:08:22 - mmengine - INFO - Epoch(train) [156][100/293] lr: 5.000000e-04 eta: 1:54:51 time: 0.495376 data_time: 0.079575 memory: 9871 loss_kpt: 0.000575 acc_pose: 0.867831 loss: 0.000575 2022/09/13 19:08:47 - mmengine - INFO - Epoch(train) [156][150/293] lr: 5.000000e-04 eta: 1:54:31 time: 0.506654 data_time: 0.083415 memory: 9871 loss_kpt: 0.000579 acc_pose: 0.862871 loss: 0.000579 2022/09/13 19:09:12 - mmengine - INFO - Epoch(train) [156][200/293] lr: 5.000000e-04 eta: 1:54:11 time: 0.497063 data_time: 0.076121 memory: 9871 loss_kpt: 0.000571 acc_pose: 0.882218 loss: 0.000571 2022/09/13 19:09:38 - mmengine - INFO - Epoch(train) [156][250/293] lr: 5.000000e-04 eta: 1:53:50 time: 0.506803 data_time: 0.075240 memory: 9871 loss_kpt: 0.000566 acc_pose: 0.877913 loss: 0.000566 2022/09/13 19:09:59 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 19:09:59 - mmengine - INFO - Saving checkpoint at 156 epochs 2022/09/13 19:10:28 - mmengine - INFO - Epoch(train) [157][50/293] lr: 5.000000e-04 eta: 1:53:05 time: 0.499293 data_time: 0.079478 memory: 9871 loss_kpt: 0.000572 acc_pose: 0.812702 loss: 0.000572 2022/09/13 19:10:54 - mmengine - INFO - Epoch(train) [157][100/293] lr: 5.000000e-04 eta: 1:52:45 time: 0.505096 data_time: 0.074543 memory: 9871 loss_kpt: 0.000573 acc_pose: 0.778359 loss: 0.000573 2022/09/13 19:11:18 - mmengine - INFO - Epoch(train) [157][150/293] lr: 5.000000e-04 eta: 1:52:25 time: 0.496630 data_time: 0.072102 memory: 9871 loss_kpt: 0.000576 acc_pose: 0.896911 loss: 0.000576 2022/09/13 19:11:43 - mmengine - INFO - Epoch(train) [157][200/293] lr: 5.000000e-04 eta: 1:52:04 time: 0.500339 data_time: 0.076988 memory: 9871 loss_kpt: 0.000560 acc_pose: 0.856668 loss: 0.000560 2022/09/13 19:12:08 - mmengine - INFO - Epoch(train) [157][250/293] lr: 5.000000e-04 eta: 1:51:44 time: 0.496853 data_time: 0.071700 memory: 9871 loss_kpt: 0.000557 acc_pose: 0.846207 loss: 0.000557 2022/09/13 19:12:29 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 19:12:29 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 19:12:29 - mmengine - INFO - Saving checkpoint at 157 epochs 2022/09/13 19:12:59 - mmengine - INFO - Epoch(train) [158][50/293] lr: 5.000000e-04 eta: 1:50:59 time: 0.516185 data_time: 0.079402 memory: 9871 loss_kpt: 0.000562 acc_pose: 0.837108 loss: 0.000562 2022/09/13 19:13:24 - mmengine - INFO - Epoch(train) [158][100/293] lr: 5.000000e-04 eta: 1:50:39 time: 0.499045 data_time: 0.078754 memory: 9871 loss_kpt: 0.000565 acc_pose: 0.883496 loss: 0.000565 2022/09/13 19:13:50 - mmengine - INFO - Epoch(train) [158][150/293] lr: 5.000000e-04 eta: 1:50:18 time: 0.502093 data_time: 0.086538 memory: 9871 loss_kpt: 0.000563 acc_pose: 0.846443 loss: 0.000563 2022/09/13 19:14:14 - mmengine - INFO - Epoch(train) [158][200/293] lr: 5.000000e-04 eta: 1:49:58 time: 0.491528 data_time: 0.072437 memory: 9871 loss_kpt: 0.000574 acc_pose: 0.816271 loss: 0.000574 2022/09/13 19:14:39 - mmengine - INFO - Epoch(train) [158][250/293] lr: 5.000000e-04 eta: 1:49:37 time: 0.497716 data_time: 0.077144 memory: 9871 loss_kpt: 0.000569 acc_pose: 0.852654 loss: 0.000569 2022/09/13 19:15:00 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 19:15:00 - mmengine - INFO - Saving checkpoint at 158 epochs 2022/09/13 19:15:31 - mmengine - INFO - Epoch(train) [159][50/293] lr: 5.000000e-04 eta: 1:48:53 time: 0.523670 data_time: 0.085023 memory: 9871 loss_kpt: 0.000564 acc_pose: 0.820085 loss: 0.000564 2022/09/13 19:15:56 - mmengine - INFO - Epoch(train) [159][100/293] lr: 5.000000e-04 eta: 1:48:33 time: 0.502946 data_time: 0.082039 memory: 9871 loss_kpt: 0.000559 acc_pose: 0.806907 loss: 0.000559 2022/09/13 19:16:21 - mmengine - INFO - Epoch(train) [159][150/293] lr: 5.000000e-04 eta: 1:48:12 time: 0.501877 data_time: 0.078063 memory: 9871 loss_kpt: 0.000561 acc_pose: 0.848267 loss: 0.000561 2022/09/13 19:16:46 - mmengine - INFO - Epoch(train) [159][200/293] lr: 5.000000e-04 eta: 1:47:52 time: 0.496181 data_time: 0.077292 memory: 9871 loss_kpt: 0.000558 acc_pose: 0.829064 loss: 0.000558 2022/09/13 19:17:12 - mmengine - INFO - Epoch(train) [159][250/293] lr: 5.000000e-04 eta: 1:47:32 time: 0.512167 data_time: 0.082278 memory: 9871 loss_kpt: 0.000569 acc_pose: 0.804706 loss: 0.000569 2022/09/13 19:17:34 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 19:17:34 - mmengine - INFO - Saving checkpoint at 159 epochs 2022/09/13 19:18:04 - mmengine - INFO - Epoch(train) [160][50/293] lr: 5.000000e-04 eta: 1:46:47 time: 0.514693 data_time: 0.090122 memory: 9871 loss_kpt: 0.000563 acc_pose: 0.883144 loss: 0.000563 2022/09/13 19:18:29 - mmengine - INFO - Epoch(train) [160][100/293] lr: 5.000000e-04 eta: 1:46:27 time: 0.501053 data_time: 0.081033 memory: 9871 loss_kpt: 0.000578 acc_pose: 0.842265 loss: 0.000578 2022/09/13 19:18:53 - mmengine - INFO - Epoch(train) [160][150/293] lr: 5.000000e-04 eta: 1:46:06 time: 0.495192 data_time: 0.076949 memory: 9871 loss_kpt: 0.000563 acc_pose: 0.857193 loss: 0.000563 2022/09/13 19:19:18 - mmengine - INFO - Epoch(train) [160][200/293] lr: 5.000000e-04 eta: 1:45:46 time: 0.499632 data_time: 0.073342 memory: 9871 loss_kpt: 0.000585 acc_pose: 0.824957 loss: 0.000585 2022/09/13 19:19:43 - mmengine - INFO - Epoch(train) [160][250/293] lr: 5.000000e-04 eta: 1:45:25 time: 0.495257 data_time: 0.076419 memory: 9871 loss_kpt: 0.000582 acc_pose: 0.818476 loss: 0.000582 2022/09/13 19:20:05 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 19:20:05 - mmengine - INFO - Saving checkpoint at 160 epochs 2022/09/13 19:20:18 - mmengine - INFO - Epoch(val) [160][50/407] eta: 0:00:59 time: 0.166349 data_time: 0.011874 memory: 9871 2022/09/13 19:20:26 - mmengine - INFO - Epoch(val) [160][100/407] eta: 0:00:48 time: 0.156698 data_time: 0.008480 memory: 920 2022/09/13 19:20:34 - mmengine - INFO - Epoch(val) [160][150/407] eta: 0:00:40 time: 0.158682 data_time: 0.008556 memory: 920 2022/09/13 19:20:41 - mmengine - INFO - Epoch(val) [160][200/407] eta: 0:00:32 time: 0.157606 data_time: 0.007732 memory: 920 2022/09/13 19:20:49 - mmengine - INFO - Epoch(val) [160][250/407] eta: 0:00:24 time: 0.158184 data_time: 0.008077 memory: 920 2022/09/13 19:20:57 - mmengine - INFO - Epoch(val) [160][300/407] eta: 0:00:16 time: 0.157651 data_time: 0.007614 memory: 920 2022/09/13 19:21:05 - mmengine - INFO - Epoch(val) [160][350/407] eta: 0:00:09 time: 0.160980 data_time: 0.007756 memory: 920 2022/09/13 19:21:13 - mmengine - INFO - Epoch(val) [160][400/407] eta: 0:00:01 time: 0.155573 data_time: 0.007133 memory: 920 2022/09/13 19:21:49 - mmengine - INFO - Evaluating CocoMetric... 2022/09/13 19:22:02 - mmengine - INFO - Epoch(val) [160][407/407] coco/AP: 0.748847 coco/AP .5: 0.903739 coco/AP .75: 0.819291 coco/AP (M): 0.710075 coco/AP (L): 0.819041 coco/AR: 0.798977 coco/AR .5: 0.940334 coco/AR .75: 0.861618 coco/AR (M): 0.754630 coco/AR (L): 0.862802 2022/09/13 19:22:02 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220913/dark_w32_256_v1/best_coco/AP_epoch_140.pth is removed 2022/09/13 19:22:05 - mmengine - INFO - The best checkpoint with 0.7488 coco/AP at 160 epoch is saved to best_coco/AP_epoch_160.pth. 2022/09/13 19:22:31 - mmengine - INFO - Epoch(train) [161][50/293] lr: 5.000000e-04 eta: 1:44:40 time: 0.503594 data_time: 0.088077 memory: 9871 loss_kpt: 0.000563 acc_pose: 0.833235 loss: 0.000563 2022/09/13 19:22:56 - mmengine - INFO - Epoch(train) [161][100/293] lr: 5.000000e-04 eta: 1:44:20 time: 0.500925 data_time: 0.075853 memory: 9871 loss_kpt: 0.000574 acc_pose: 0.839122 loss: 0.000574 2022/09/13 19:23:06 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 19:23:21 - mmengine - INFO - Epoch(train) [161][150/293] lr: 5.000000e-04 eta: 1:44:00 time: 0.502416 data_time: 0.073618 memory: 9871 loss_kpt: 0.000569 acc_pose: 0.853044 loss: 0.000569 2022/09/13 19:23:46 - mmengine - INFO - Epoch(train) [161][200/293] lr: 5.000000e-04 eta: 1:43:39 time: 0.509446 data_time: 0.070709 memory: 9871 loss_kpt: 0.000565 acc_pose: 0.835302 loss: 0.000565 2022/09/13 19:24:11 - mmengine - INFO - Epoch(train) [161][250/293] lr: 5.000000e-04 eta: 1:43:19 time: 0.498124 data_time: 0.080640 memory: 9871 loss_kpt: 0.000563 acc_pose: 0.824761 loss: 0.000563 2022/09/13 19:24:33 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 19:24:33 - mmengine - INFO - Saving checkpoint at 161 epochs 2022/09/13 19:25:03 - mmengine - INFO - Epoch(train) [162][50/293] lr: 5.000000e-04 eta: 1:42:35 time: 0.519729 data_time: 0.094453 memory: 9871 loss_kpt: 0.000575 acc_pose: 0.824405 loss: 0.000575 2022/09/13 19:25:28 - mmengine - INFO - Epoch(train) [162][100/293] lr: 5.000000e-04 eta: 1:42:14 time: 0.497719 data_time: 0.070590 memory: 9871 loss_kpt: 0.000574 acc_pose: 0.813264 loss: 0.000574 2022/09/13 19:25:53 - mmengine - INFO - Epoch(train) [162][150/293] lr: 5.000000e-04 eta: 1:41:54 time: 0.501154 data_time: 0.068494 memory: 9871 loss_kpt: 0.000578 acc_pose: 0.852956 loss: 0.000578 2022/09/13 19:26:18 - mmengine - INFO - Epoch(train) [162][200/293] lr: 5.000000e-04 eta: 1:41:33 time: 0.491324 data_time: 0.070279 memory: 9871 loss_kpt: 0.000562 acc_pose: 0.756812 loss: 0.000562 2022/09/13 19:26:43 - mmengine - INFO - Epoch(train) [162][250/293] lr: 5.000000e-04 eta: 1:41:13 time: 0.509042 data_time: 0.076955 memory: 9871 loss_kpt: 0.000565 acc_pose: 0.882866 loss: 0.000565 2022/09/13 19:27:04 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 19:27:04 - mmengine - INFO - Saving checkpoint at 162 epochs 2022/09/13 19:27:34 - mmengine - INFO - Epoch(train) [163][50/293] lr: 5.000000e-04 eta: 1:40:28 time: 0.509262 data_time: 0.084960 memory: 9871 loss_kpt: 0.000561 acc_pose: 0.865527 loss: 0.000561 2022/09/13 19:28:00 - mmengine - INFO - Epoch(train) [163][100/293] lr: 5.000000e-04 eta: 1:40:08 time: 0.506288 data_time: 0.074452 memory: 9871 loss_kpt: 0.000571 acc_pose: 0.851851 loss: 0.000571 2022/09/13 19:28:24 - mmengine - INFO - Epoch(train) [163][150/293] lr: 5.000000e-04 eta: 1:39:47 time: 0.492292 data_time: 0.075545 memory: 9871 loss_kpt: 0.000564 acc_pose: 0.827882 loss: 0.000564 2022/09/13 19:28:49 - mmengine - INFO - Epoch(train) [163][200/293] lr: 5.000000e-04 eta: 1:39:27 time: 0.499098 data_time: 0.074967 memory: 9871 loss_kpt: 0.000566 acc_pose: 0.849625 loss: 0.000566 2022/09/13 19:29:15 - mmengine - INFO - Epoch(train) [163][250/293] lr: 5.000000e-04 eta: 1:39:06 time: 0.506440 data_time: 0.079210 memory: 9871 loss_kpt: 0.000564 acc_pose: 0.823403 loss: 0.000564 2022/09/13 19:29:35 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 19:29:35 - mmengine - INFO - Saving checkpoint at 163 epochs 2022/09/13 19:30:06 - mmengine - INFO - Epoch(train) [164][50/293] lr: 5.000000e-04 eta: 1:38:22 time: 0.527317 data_time: 0.089829 memory: 9871 loss_kpt: 0.000545 acc_pose: 0.851076 loss: 0.000545 2022/09/13 19:30:30 - mmengine - INFO - Epoch(train) [164][100/293] lr: 5.000000e-04 eta: 1:38:02 time: 0.492159 data_time: 0.079611 memory: 9871 loss_kpt: 0.000556 acc_pose: 0.843892 loss: 0.000556 2022/09/13 19:30:56 - mmengine - INFO - Epoch(train) [164][150/293] lr: 5.000000e-04 eta: 1:37:41 time: 0.505468 data_time: 0.075622 memory: 9871 loss_kpt: 0.000564 acc_pose: 0.852494 loss: 0.000564 2022/09/13 19:31:20 - mmengine - INFO - Epoch(train) [164][200/293] lr: 5.000000e-04 eta: 1:37:21 time: 0.489159 data_time: 0.081815 memory: 9871 loss_kpt: 0.000569 acc_pose: 0.860670 loss: 0.000569 2022/09/13 19:31:41 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 19:31:46 - mmengine - INFO - Epoch(train) [164][250/293] lr: 5.000000e-04 eta: 1:37:00 time: 0.509164 data_time: 0.072118 memory: 9871 loss_kpt: 0.000577 acc_pose: 0.830773 loss: 0.000577 2022/09/13 19:32:07 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 19:32:07 - mmengine - INFO - Saving checkpoint at 164 epochs 2022/09/13 19:32:37 - mmengine - INFO - Epoch(train) [165][50/293] lr: 5.000000e-04 eta: 1:36:16 time: 0.499705 data_time: 0.082852 memory: 9871 loss_kpt: 0.000560 acc_pose: 0.848355 loss: 0.000560 2022/09/13 19:33:02 - mmengine - INFO - Epoch(train) [165][100/293] lr: 5.000000e-04 eta: 1:35:56 time: 0.508538 data_time: 0.078078 memory: 9871 loss_kpt: 0.000554 acc_pose: 0.818054 loss: 0.000554 2022/09/13 19:33:27 - mmengine - INFO - Epoch(train) [165][150/293] lr: 5.000000e-04 eta: 1:35:35 time: 0.500945 data_time: 0.080236 memory: 9871 loss_kpt: 0.000582 acc_pose: 0.855603 loss: 0.000582 2022/09/13 19:33:52 - mmengine - INFO - Epoch(train) [165][200/293] lr: 5.000000e-04 eta: 1:35:14 time: 0.500616 data_time: 0.080381 memory: 9871 loss_kpt: 0.000558 acc_pose: 0.838253 loss: 0.000558 2022/09/13 19:34:17 - mmengine - INFO - Epoch(train) [165][250/293] lr: 5.000000e-04 eta: 1:34:54 time: 0.494216 data_time: 0.075678 memory: 9871 loss_kpt: 0.000587 acc_pose: 0.880871 loss: 0.000587 2022/09/13 19:34:39 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 19:34:39 - mmengine - INFO - Saving checkpoint at 165 epochs 2022/09/13 19:35:10 - mmengine - INFO - Epoch(train) [166][50/293] lr: 5.000000e-04 eta: 1:34:10 time: 0.505600 data_time: 0.084414 memory: 9871 loss_kpt: 0.000562 acc_pose: 0.880318 loss: 0.000562 2022/09/13 19:35:35 - mmengine - INFO - Epoch(train) [166][100/293] lr: 5.000000e-04 eta: 1:33:49 time: 0.503618 data_time: 0.077539 memory: 9871 loss_kpt: 0.000573 acc_pose: 0.833272 loss: 0.000573 2022/09/13 19:36:00 - mmengine - INFO - Epoch(train) [166][150/293] lr: 5.000000e-04 eta: 1:33:29 time: 0.492608 data_time: 0.072264 memory: 9871 loss_kpt: 0.000560 acc_pose: 0.860919 loss: 0.000560 2022/09/13 19:36:25 - mmengine - INFO - Epoch(train) [166][200/293] lr: 5.000000e-04 eta: 1:33:08 time: 0.500574 data_time: 0.080803 memory: 9871 loss_kpt: 0.000576 acc_pose: 0.883776 loss: 0.000576 2022/09/13 19:36:49 - mmengine - INFO - Epoch(train) [166][250/293] lr: 5.000000e-04 eta: 1:32:47 time: 0.496363 data_time: 0.082185 memory: 9871 loss_kpt: 0.000575 acc_pose: 0.837787 loss: 0.000575 2022/09/13 19:37:11 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 19:37:11 - mmengine - INFO - Saving checkpoint at 166 epochs 2022/09/13 19:37:41 - mmengine - INFO - Epoch(train) [167][50/293] lr: 5.000000e-04 eta: 1:32:04 time: 0.511679 data_time: 0.084635 memory: 9871 loss_kpt: 0.000560 acc_pose: 0.860071 loss: 0.000560 2022/09/13 19:38:06 - mmengine - INFO - Epoch(train) [167][100/293] lr: 5.000000e-04 eta: 1:31:43 time: 0.507783 data_time: 0.081885 memory: 9871 loss_kpt: 0.000568 acc_pose: 0.877987 loss: 0.000568 2022/09/13 19:38:31 - mmengine - INFO - Epoch(train) [167][150/293] lr: 5.000000e-04 eta: 1:31:22 time: 0.498650 data_time: 0.071689 memory: 9871 loss_kpt: 0.000562 acc_pose: 0.814316 loss: 0.000562 2022/09/13 19:38:57 - mmengine - INFO - Epoch(train) [167][200/293] lr: 5.000000e-04 eta: 1:31:02 time: 0.511276 data_time: 0.079252 memory: 9871 loss_kpt: 0.000559 acc_pose: 0.874656 loss: 0.000559 2022/09/13 19:39:22 - mmengine - INFO - Epoch(train) [167][250/293] lr: 5.000000e-04 eta: 1:30:41 time: 0.508567 data_time: 0.074212 memory: 9871 loss_kpt: 0.000575 acc_pose: 0.864016 loss: 0.000575 2022/09/13 19:39:44 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 19:39:44 - mmengine - INFO - Saving checkpoint at 167 epochs 2022/09/13 19:40:15 - mmengine - INFO - Epoch(train) [168][50/293] lr: 5.000000e-04 eta: 1:29:58 time: 0.528007 data_time: 0.084324 memory: 9871 loss_kpt: 0.000560 acc_pose: 0.850900 loss: 0.000560 2022/09/13 19:40:24 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 19:40:40 - mmengine - INFO - Epoch(train) [168][100/293] lr: 5.000000e-04 eta: 1:29:37 time: 0.500574 data_time: 0.078977 memory: 9871 loss_kpt: 0.000563 acc_pose: 0.863836 loss: 0.000563 2022/09/13 19:41:04 - mmengine - INFO - Epoch(train) [168][150/293] lr: 5.000000e-04 eta: 1:29:17 time: 0.492356 data_time: 0.079984 memory: 9871 loss_kpt: 0.000568 acc_pose: 0.821187 loss: 0.000568 2022/09/13 19:41:29 - mmengine - INFO - Epoch(train) [168][200/293] lr: 5.000000e-04 eta: 1:28:56 time: 0.501166 data_time: 0.079928 memory: 9871 loss_kpt: 0.000577 acc_pose: 0.857701 loss: 0.000577 2022/09/13 19:41:54 - mmengine - INFO - Epoch(train) [168][250/293] lr: 5.000000e-04 eta: 1:28:35 time: 0.498956 data_time: 0.071222 memory: 9871 loss_kpt: 0.000587 acc_pose: 0.828357 loss: 0.000587 2022/09/13 19:42:15 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 19:42:15 - mmengine - INFO - Saving checkpoint at 168 epochs 2022/09/13 19:42:46 - mmengine - INFO - Epoch(train) [169][50/293] lr: 5.000000e-04 eta: 1:27:52 time: 0.525496 data_time: 0.084358 memory: 9871 loss_kpt: 0.000558 acc_pose: 0.878839 loss: 0.000558 2022/09/13 19:43:11 - mmengine - INFO - Epoch(train) [169][100/293] lr: 5.000000e-04 eta: 1:27:31 time: 0.500444 data_time: 0.080184 memory: 9871 loss_kpt: 0.000564 acc_pose: 0.839844 loss: 0.000564 2022/09/13 19:43:36 - mmengine - INFO - Epoch(train) [169][150/293] lr: 5.000000e-04 eta: 1:27:11 time: 0.504738 data_time: 0.076380 memory: 9871 loss_kpt: 0.000574 acc_pose: 0.844484 loss: 0.000574 2022/09/13 19:44:01 - mmengine - INFO - Epoch(train) [169][200/293] lr: 5.000000e-04 eta: 1:26:50 time: 0.493483 data_time: 0.081874 memory: 9871 loss_kpt: 0.000558 acc_pose: 0.891139 loss: 0.000558 2022/09/13 19:44:26 - mmengine - INFO - Epoch(train) [169][250/293] lr: 5.000000e-04 eta: 1:26:29 time: 0.507837 data_time: 0.079411 memory: 9871 loss_kpt: 0.000565 acc_pose: 0.864149 loss: 0.000565 2022/09/13 19:44:48 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 19:44:48 - mmengine - INFO - Saving checkpoint at 169 epochs 2022/09/13 19:45:17 - mmengine - INFO - Epoch(train) [170][50/293] lr: 5.000000e-04 eta: 1:25:46 time: 0.509230 data_time: 0.080831 memory: 9871 loss_kpt: 0.000567 acc_pose: 0.817564 loss: 0.000567 2022/09/13 19:45:42 - mmengine - INFO - Epoch(train) [170][100/293] lr: 5.000000e-04 eta: 1:25:25 time: 0.497148 data_time: 0.077916 memory: 9871 loss_kpt: 0.000550 acc_pose: 0.842044 loss: 0.000550 2022/09/13 19:46:08 - mmengine - INFO - Epoch(train) [170][150/293] lr: 5.000000e-04 eta: 1:25:05 time: 0.515446 data_time: 0.080764 memory: 9871 loss_kpt: 0.000565 acc_pose: 0.863878 loss: 0.000565 2022/09/13 19:46:33 - mmengine - INFO - Epoch(train) [170][200/293] lr: 5.000000e-04 eta: 1:24:44 time: 0.492290 data_time: 0.074189 memory: 9871 loss_kpt: 0.000572 acc_pose: 0.839367 loss: 0.000572 2022/09/13 19:46:58 - mmengine - INFO - Epoch(train) [170][250/293] lr: 5.000000e-04 eta: 1:24:23 time: 0.495762 data_time: 0.076252 memory: 9871 loss_kpt: 0.000557 acc_pose: 0.839784 loss: 0.000557 2022/09/13 19:47:19 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 19:47:19 - mmengine - INFO - Saving checkpoint at 170 epochs 2022/09/13 19:47:32 - mmengine - INFO - Epoch(val) [170][50/407] eta: 0:00:59 time: 0.167741 data_time: 0.013491 memory: 9871 2022/09/13 19:47:41 - mmengine - INFO - Epoch(val) [170][100/407] eta: 0:00:52 time: 0.169850 data_time: 0.013390 memory: 920 2022/09/13 19:47:49 - mmengine - INFO - Epoch(val) [170][150/407] eta: 0:00:41 time: 0.160967 data_time: 0.008093 memory: 920 2022/09/13 19:47:57 - mmengine - INFO - Epoch(val) [170][200/407] eta: 0:00:33 time: 0.160691 data_time: 0.008557 memory: 920 2022/09/13 19:48:05 - mmengine - INFO - Epoch(val) [170][250/407] eta: 0:00:25 time: 0.159257 data_time: 0.007925 memory: 920 2022/09/13 19:48:13 - mmengine - INFO - Epoch(val) [170][300/407] eta: 0:00:17 time: 0.159289 data_time: 0.008088 memory: 920 2022/09/13 19:48:21 - mmengine - INFO - Epoch(val) [170][350/407] eta: 0:00:09 time: 0.161556 data_time: 0.008045 memory: 920 2022/09/13 19:48:29 - mmengine - INFO - Epoch(val) [170][400/407] eta: 0:00:01 time: 0.155269 data_time: 0.007420 memory: 920 2022/09/13 19:49:06 - mmengine - INFO - Evaluating CocoMetric... 2022/09/13 19:49:20 - mmengine - INFO - Epoch(val) [170][407/407] coco/AP: 0.745557 coco/AP .5: 0.902441 coco/AP .75: 0.812441 coco/AP (M): 0.711057 coco/AP (L): 0.812853 coco/AR: 0.798315 coco/AR .5: 0.941121 coco/AR .75: 0.859099 coco/AR (M): 0.756214 coco/AR (L): 0.859012 2022/09/13 19:49:46 - mmengine - INFO - Epoch(train) [171][50/293] lr: 5.000000e-05 eta: 1:23:40 time: 0.519668 data_time: 0.080912 memory: 9871 loss_kpt: 0.000547 acc_pose: 0.850566 loss: 0.000547 2022/09/13 19:50:11 - mmengine - INFO - Epoch(train) [171][100/293] lr: 5.000000e-05 eta: 1:23:19 time: 0.499318 data_time: 0.075719 memory: 9871 loss_kpt: 0.000552 acc_pose: 0.850931 loss: 0.000552 2022/09/13 19:50:36 - mmengine - INFO - Epoch(train) [171][150/293] lr: 5.000000e-05 eta: 1:22:58 time: 0.501987 data_time: 0.072457 memory: 9871 loss_kpt: 0.000555 acc_pose: 0.850658 loss: 0.000555 2022/09/13 19:50:56 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 19:51:01 - mmengine - INFO - Epoch(train) [171][200/293] lr: 5.000000e-05 eta: 1:22:38 time: 0.492178 data_time: 0.073114 memory: 9871 loss_kpt: 0.000550 acc_pose: 0.833171 loss: 0.000550 2022/09/13 19:51:26 - mmengine - INFO - Epoch(train) [171][250/293] lr: 5.000000e-05 eta: 1:22:17 time: 0.497575 data_time: 0.076818 memory: 9871 loss_kpt: 0.000565 acc_pose: 0.858132 loss: 0.000565 2022/09/13 19:51:47 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 19:51:47 - mmengine - INFO - Saving checkpoint at 171 epochs 2022/09/13 19:52:17 - mmengine - INFO - Epoch(train) [172][50/293] lr: 5.000000e-05 eta: 1:21:33 time: 0.510412 data_time: 0.082951 memory: 9871 loss_kpt: 0.000545 acc_pose: 0.887219 loss: 0.000545 2022/09/13 19:52:42 - mmengine - INFO - Epoch(train) [172][100/293] lr: 5.000000e-05 eta: 1:21:13 time: 0.497740 data_time: 0.071643 memory: 9871 loss_kpt: 0.000547 acc_pose: 0.823187 loss: 0.000547 2022/09/13 19:53:07 - mmengine - INFO - Epoch(train) [172][150/293] lr: 5.000000e-05 eta: 1:20:52 time: 0.493749 data_time: 0.072665 memory: 9871 loss_kpt: 0.000544 acc_pose: 0.837151 loss: 0.000544 2022/09/13 19:53:32 - mmengine - INFO - Epoch(train) [172][200/293] lr: 5.000000e-05 eta: 1:20:31 time: 0.501486 data_time: 0.072758 memory: 9871 loss_kpt: 0.000542 acc_pose: 0.824649 loss: 0.000542 2022/09/13 19:53:56 - mmengine - INFO - Epoch(train) [172][250/293] lr: 5.000000e-05 eta: 1:20:10 time: 0.490917 data_time: 0.072081 memory: 9871 loss_kpt: 0.000542 acc_pose: 0.845444 loss: 0.000542 2022/09/13 19:54:18 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 19:54:18 - mmengine - INFO - Saving checkpoint at 172 epochs 2022/09/13 19:54:49 - mmengine - INFO - Epoch(train) [173][50/293] lr: 5.000000e-05 eta: 1:19:27 time: 0.520607 data_time: 0.088955 memory: 9871 loss_kpt: 0.000544 acc_pose: 0.871878 loss: 0.000544 2022/09/13 19:55:14 - mmengine - INFO - Epoch(train) [173][100/293] lr: 5.000000e-05 eta: 1:19:06 time: 0.500445 data_time: 0.071446 memory: 9871 loss_kpt: 0.000554 acc_pose: 0.838578 loss: 0.000554 2022/09/13 19:55:38 - mmengine - INFO - Epoch(train) [173][150/293] lr: 5.000000e-05 eta: 1:18:46 time: 0.492764 data_time: 0.074864 memory: 9871 loss_kpt: 0.000544 acc_pose: 0.872487 loss: 0.000544 2022/09/13 19:56:03 - mmengine - INFO - Epoch(train) [173][200/293] lr: 5.000000e-05 eta: 1:18:25 time: 0.497647 data_time: 0.076542 memory: 9871 loss_kpt: 0.000543 acc_pose: 0.821067 loss: 0.000543 2022/09/13 19:56:28 - mmengine - INFO - Epoch(train) [173][250/293] lr: 5.000000e-05 eta: 1:18:04 time: 0.503051 data_time: 0.073137 memory: 9871 loss_kpt: 0.000542 acc_pose: 0.836733 loss: 0.000542 2022/09/13 19:56:50 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 19:56:50 - mmengine - INFO - Saving checkpoint at 173 epochs 2022/09/13 19:57:19 - mmengine - INFO - Epoch(train) [174][50/293] lr: 5.000000e-05 eta: 1:17:21 time: 0.503106 data_time: 0.085882 memory: 9871 loss_kpt: 0.000547 acc_pose: 0.885785 loss: 0.000547 2022/09/13 19:57:45 - mmengine - INFO - Epoch(train) [174][100/293] lr: 5.000000e-05 eta: 1:17:00 time: 0.514242 data_time: 0.073702 memory: 9871 loss_kpt: 0.000540 acc_pose: 0.832254 loss: 0.000540 2022/09/13 19:58:10 - mmengine - INFO - Epoch(train) [174][150/293] lr: 5.000000e-05 eta: 1:16:40 time: 0.500189 data_time: 0.077957 memory: 9871 loss_kpt: 0.000530 acc_pose: 0.873000 loss: 0.000530 2022/09/13 19:58:35 - mmengine - INFO - Epoch(train) [174][200/293] lr: 5.000000e-05 eta: 1:16:19 time: 0.504020 data_time: 0.079985 memory: 9871 loss_kpt: 0.000558 acc_pose: 0.814971 loss: 0.000558 2022/09/13 19:59:00 - mmengine - INFO - Epoch(train) [174][250/293] lr: 5.000000e-05 eta: 1:15:58 time: 0.504021 data_time: 0.080802 memory: 9871 loss_kpt: 0.000553 acc_pose: 0.818576 loss: 0.000553 2022/09/13 19:59:22 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 19:59:22 - mmengine - INFO - Saving checkpoint at 174 epochs 2022/09/13 19:59:36 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 19:59:52 - mmengine - INFO - Epoch(train) [175][50/293] lr: 5.000000e-05 eta: 1:15:15 time: 0.515333 data_time: 0.084665 memory: 9871 loss_kpt: 0.000540 acc_pose: 0.851790 loss: 0.000540 2022/09/13 20:00:17 - mmengine - INFO - Epoch(train) [175][100/293] lr: 5.000000e-05 eta: 1:14:54 time: 0.507184 data_time: 0.076687 memory: 9871 loss_kpt: 0.000536 acc_pose: 0.871967 loss: 0.000536 2022/09/13 20:00:43 - mmengine - INFO - Epoch(train) [175][150/293] lr: 5.000000e-05 eta: 1:14:34 time: 0.509304 data_time: 0.074465 memory: 9871 loss_kpt: 0.000535 acc_pose: 0.869903 loss: 0.000535 2022/09/13 20:01:07 - mmengine - INFO - Epoch(train) [175][200/293] lr: 5.000000e-05 eta: 1:14:13 time: 0.494767 data_time: 0.073173 memory: 9871 loss_kpt: 0.000525 acc_pose: 0.875702 loss: 0.000525 2022/09/13 20:01:32 - mmengine - INFO - Epoch(train) [175][250/293] lr: 5.000000e-05 eta: 1:13:52 time: 0.490848 data_time: 0.073715 memory: 9871 loss_kpt: 0.000538 acc_pose: 0.844477 loss: 0.000538 2022/09/13 20:01:54 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 20:01:54 - mmengine - INFO - Saving checkpoint at 175 epochs 2022/09/13 20:02:24 - mmengine - INFO - Epoch(train) [176][50/293] lr: 5.000000e-05 eta: 1:13:09 time: 0.519558 data_time: 0.090857 memory: 9871 loss_kpt: 0.000528 acc_pose: 0.854562 loss: 0.000528 2022/09/13 20:02:49 - mmengine - INFO - Epoch(train) [176][100/293] lr: 5.000000e-05 eta: 1:12:48 time: 0.506542 data_time: 0.081348 memory: 9871 loss_kpt: 0.000535 acc_pose: 0.820866 loss: 0.000535 2022/09/13 20:03:15 - mmengine - INFO - Epoch(train) [176][150/293] lr: 5.000000e-05 eta: 1:12:28 time: 0.502320 data_time: 0.078625 memory: 9871 loss_kpt: 0.000531 acc_pose: 0.853620 loss: 0.000531 2022/09/13 20:03:39 - mmengine - INFO - Epoch(train) [176][200/293] lr: 5.000000e-05 eta: 1:12:07 time: 0.493213 data_time: 0.072986 memory: 9871 loss_kpt: 0.000524 acc_pose: 0.857923 loss: 0.000524 2022/09/13 20:04:04 - mmengine - INFO - Epoch(train) [176][250/293] lr: 5.000000e-05 eta: 1:11:46 time: 0.494567 data_time: 0.079469 memory: 9871 loss_kpt: 0.000533 acc_pose: 0.864211 loss: 0.000533 2022/09/13 20:04:25 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 20:04:25 - mmengine - INFO - Saving checkpoint at 176 epochs 2022/09/13 20:04:55 - mmengine - INFO - Epoch(train) [177][50/293] lr: 5.000000e-05 eta: 1:11:03 time: 0.503562 data_time: 0.085765 memory: 9871 loss_kpt: 0.000540 acc_pose: 0.837713 loss: 0.000540 2022/09/13 20:05:20 - mmengine - INFO - Epoch(train) [177][100/293] lr: 5.000000e-05 eta: 1:10:42 time: 0.494181 data_time: 0.079338 memory: 9871 loss_kpt: 0.000533 acc_pose: 0.848663 loss: 0.000533 2022/09/13 20:05:45 - mmengine - INFO - Epoch(train) [177][150/293] lr: 5.000000e-05 eta: 1:10:21 time: 0.510888 data_time: 0.081800 memory: 9871 loss_kpt: 0.000542 acc_pose: 0.864325 loss: 0.000542 2022/09/13 20:06:10 - mmengine - INFO - Epoch(train) [177][200/293] lr: 5.000000e-05 eta: 1:10:00 time: 0.499474 data_time: 0.076268 memory: 9871 loss_kpt: 0.000538 acc_pose: 0.871193 loss: 0.000538 2022/09/13 20:06:35 - mmengine - INFO - Epoch(train) [177][250/293] lr: 5.000000e-05 eta: 1:09:39 time: 0.491272 data_time: 0.078377 memory: 9871 loss_kpt: 0.000526 acc_pose: 0.837890 loss: 0.000526 2022/09/13 20:06:56 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 20:06:56 - mmengine - INFO - Saving checkpoint at 177 epochs 2022/09/13 20:07:26 - mmengine - INFO - Epoch(train) [178][50/293] lr: 5.000000e-05 eta: 1:08:57 time: 0.510112 data_time: 0.083082 memory: 9871 loss_kpt: 0.000534 acc_pose: 0.846982 loss: 0.000534 2022/09/13 20:07:52 - mmengine - INFO - Epoch(train) [178][100/293] lr: 5.000000e-05 eta: 1:08:36 time: 0.509237 data_time: 0.078511 memory: 9871 loss_kpt: 0.000537 acc_pose: 0.827087 loss: 0.000537 2022/09/13 20:08:11 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 20:08:16 - mmengine - INFO - Epoch(train) [178][150/293] lr: 5.000000e-05 eta: 1:08:15 time: 0.491832 data_time: 0.074439 memory: 9871 loss_kpt: 0.000527 acc_pose: 0.872998 loss: 0.000527 2022/09/13 20:08:41 - mmengine - INFO - Epoch(train) [178][200/293] lr: 5.000000e-05 eta: 1:07:54 time: 0.501981 data_time: 0.082299 memory: 9871 loss_kpt: 0.000533 acc_pose: 0.851653 loss: 0.000533 2022/09/13 20:09:06 - mmengine - INFO - Epoch(train) [178][250/293] lr: 5.000000e-05 eta: 1:07:33 time: 0.496045 data_time: 0.083220 memory: 9871 loss_kpt: 0.000533 acc_pose: 0.790412 loss: 0.000533 2022/09/13 20:09:27 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 20:09:27 - mmengine - INFO - Saving checkpoint at 178 epochs 2022/09/13 20:09:58 - mmengine - INFO - Epoch(train) [179][50/293] lr: 5.000000e-05 eta: 1:06:51 time: 0.524477 data_time: 0.092594 memory: 9871 loss_kpt: 0.000520 acc_pose: 0.871571 loss: 0.000520 2022/09/13 20:10:23 - mmengine - INFO - Epoch(train) [179][100/293] lr: 5.000000e-05 eta: 1:06:30 time: 0.491995 data_time: 0.077602 memory: 9871 loss_kpt: 0.000536 acc_pose: 0.880141 loss: 0.000536 2022/09/13 20:10:48 - mmengine - INFO - Epoch(train) [179][150/293] lr: 5.000000e-05 eta: 1:06:09 time: 0.501545 data_time: 0.079577 memory: 9871 loss_kpt: 0.000535 acc_pose: 0.849704 loss: 0.000535 2022/09/13 20:11:12 - mmengine - INFO - Epoch(train) [179][200/293] lr: 5.000000e-05 eta: 1:05:48 time: 0.493780 data_time: 0.072440 memory: 9871 loss_kpt: 0.000539 acc_pose: 0.802449 loss: 0.000539 2022/09/13 20:11:37 - mmengine - INFO - Epoch(train) [179][250/293] lr: 5.000000e-05 eta: 1:05:27 time: 0.490679 data_time: 0.076066 memory: 9871 loss_kpt: 0.000532 acc_pose: 0.856511 loss: 0.000532 2022/09/13 20:12:00 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 20:12:00 - mmengine - INFO - Saving checkpoint at 179 epochs 2022/09/13 20:12:30 - mmengine - INFO - Epoch(train) [180][50/293] lr: 5.000000e-05 eta: 1:04:44 time: 0.498765 data_time: 0.086815 memory: 9871 loss_kpt: 0.000531 acc_pose: 0.880525 loss: 0.000531 2022/09/13 20:12:55 - mmengine - INFO - Epoch(train) [180][100/293] lr: 5.000000e-05 eta: 1:04:23 time: 0.496159 data_time: 0.075438 memory: 9871 loss_kpt: 0.000523 acc_pose: 0.896568 loss: 0.000523 2022/09/13 20:13:20 - mmengine - INFO - Epoch(train) [180][150/293] lr: 5.000000e-05 eta: 1:04:02 time: 0.493493 data_time: 0.082475 memory: 9871 loss_kpt: 0.000531 acc_pose: 0.820905 loss: 0.000531 2022/09/13 20:13:45 - mmengine - INFO - Epoch(train) [180][200/293] lr: 5.000000e-05 eta: 1:03:42 time: 0.508390 data_time: 0.072957 memory: 9871 loss_kpt: 0.000533 acc_pose: 0.875867 loss: 0.000533 2022/09/13 20:14:11 - mmengine - INFO - Epoch(train) [180][250/293] lr: 5.000000e-05 eta: 1:03:21 time: 0.515355 data_time: 0.077497 memory: 9871 loss_kpt: 0.000539 acc_pose: 0.861959 loss: 0.000539 2022/09/13 20:14:32 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 20:14:32 - mmengine - INFO - Saving checkpoint at 180 epochs 2022/09/13 20:14:45 - mmengine - INFO - Epoch(val) [180][50/407] eta: 0:00:59 time: 0.165584 data_time: 0.013046 memory: 9871 2022/09/13 20:14:53 - mmengine - INFO - Epoch(val) [180][100/407] eta: 0:00:49 time: 0.159933 data_time: 0.008405 memory: 920 2022/09/13 20:15:01 - mmengine - INFO - Epoch(val) [180][150/407] eta: 0:00:41 time: 0.163166 data_time: 0.012333 memory: 920 2022/09/13 20:15:09 - mmengine - INFO - Epoch(val) [180][200/407] eta: 0:00:32 time: 0.157296 data_time: 0.007267 memory: 920 2022/09/13 20:15:17 - mmengine - INFO - Epoch(val) [180][250/407] eta: 0:00:24 time: 0.158639 data_time: 0.007688 memory: 920 2022/09/13 20:15:25 - mmengine - INFO - Epoch(val) [180][300/407] eta: 0:00:17 time: 0.161237 data_time: 0.010217 memory: 920 2022/09/13 20:15:33 - mmengine - INFO - Epoch(val) [180][350/407] eta: 0:00:09 time: 0.158315 data_time: 0.007596 memory: 920 2022/09/13 20:15:41 - mmengine - INFO - Epoch(val) [180][400/407] eta: 0:00:01 time: 0.155489 data_time: 0.008176 memory: 920 2022/09/13 20:16:17 - mmengine - INFO - Evaluating CocoMetric... 2022/09/13 20:16:31 - mmengine - INFO - Epoch(val) [180][407/407] coco/AP: 0.755169 coco/AP .5: 0.905446 coco/AP .75: 0.823108 coco/AP (M): 0.719297 coco/AP (L): 0.822591 coco/AR: 0.805337 coco/AR .5: 0.942065 coco/AR .75: 0.866184 coco/AR (M): 0.762879 coco/AR (L): 0.867001 2022/09/13 20:16:31 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220913/dark_w32_256_v1/best_coco/AP_epoch_160.pth is removed 2022/09/13 20:16:35 - mmengine - INFO - The best checkpoint with 0.7552 coco/AP at 180 epoch is saved to best_coco/AP_epoch_180.pth. 2022/09/13 20:17:00 - mmengine - INFO - Epoch(train) [181][50/293] lr: 5.000000e-05 eta: 1:02:38 time: 0.502747 data_time: 0.082037 memory: 9871 loss_kpt: 0.000528 acc_pose: 0.881215 loss: 0.000528 2022/09/13 20:17:25 - mmengine - INFO - Epoch(train) [181][100/293] lr: 5.000000e-05 eta: 1:02:17 time: 0.502465 data_time: 0.074518 memory: 9871 loss_kpt: 0.000530 acc_pose: 0.815444 loss: 0.000530 2022/09/13 20:17:50 - mmengine - INFO - Epoch(train) [181][150/293] lr: 5.000000e-05 eta: 1:01:56 time: 0.495214 data_time: 0.076354 memory: 9871 loss_kpt: 0.000534 acc_pose: 0.881958 loss: 0.000534 2022/09/13 20:18:15 - mmengine - INFO - Epoch(train) [181][200/293] lr: 5.000000e-05 eta: 1:01:35 time: 0.507036 data_time: 0.083205 memory: 9871 loss_kpt: 0.000530 acc_pose: 0.859454 loss: 0.000530 2022/09/13 20:18:41 - mmengine - INFO - Epoch(train) [181][250/293] lr: 5.000000e-05 eta: 1:01:15 time: 0.506012 data_time: 0.076525 memory: 9871 loss_kpt: 0.000530 acc_pose: 0.875036 loss: 0.000530 2022/09/13 20:18:46 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 20:19:02 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 20:19:02 - mmengine - INFO - Saving checkpoint at 181 epochs 2022/09/13 20:19:32 - mmengine - INFO - Epoch(train) [182][50/293] lr: 5.000000e-05 eta: 1:00:32 time: 0.506356 data_time: 0.086897 memory: 9871 loss_kpt: 0.000519 acc_pose: 0.836958 loss: 0.000519 2022/09/13 20:19:57 - mmengine - INFO - Epoch(train) [182][100/293] lr: 5.000000e-05 eta: 1:00:11 time: 0.508768 data_time: 0.074173 memory: 9871 loss_kpt: 0.000532 acc_pose: 0.828692 loss: 0.000532 2022/09/13 20:20:22 - mmengine - INFO - Epoch(train) [182][150/293] lr: 5.000000e-05 eta: 0:59:50 time: 0.494252 data_time: 0.079645 memory: 9871 loss_kpt: 0.000527 acc_pose: 0.836917 loss: 0.000527 2022/09/13 20:20:47 - mmengine - INFO - Epoch(train) [182][200/293] lr: 5.000000e-05 eta: 0:59:29 time: 0.506275 data_time: 0.072799 memory: 9871 loss_kpt: 0.000522 acc_pose: 0.824754 loss: 0.000522 2022/09/13 20:21:12 - mmengine - INFO - Epoch(train) [182][250/293] lr: 5.000000e-05 eta: 0:59:08 time: 0.498056 data_time: 0.082868 memory: 9871 loss_kpt: 0.000521 acc_pose: 0.799663 loss: 0.000521 2022/09/13 20:21:34 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 20:21:34 - mmengine - INFO - Saving checkpoint at 182 epochs 2022/09/13 20:22:06 - mmengine - INFO - Epoch(train) [183][50/293] lr: 5.000000e-05 eta: 0:58:26 time: 0.517923 data_time: 0.083969 memory: 9871 loss_kpt: 0.000530 acc_pose: 0.867030 loss: 0.000530 2022/09/13 20:22:31 - mmengine - INFO - Epoch(train) [183][100/293] lr: 5.000000e-05 eta: 0:58:05 time: 0.501185 data_time: 0.072682 memory: 9871 loss_kpt: 0.000528 acc_pose: 0.836394 loss: 0.000528 2022/09/13 20:22:56 - mmengine - INFO - Epoch(train) [183][150/293] lr: 5.000000e-05 eta: 0:57:44 time: 0.495602 data_time: 0.075347 memory: 9871 loss_kpt: 0.000523 acc_pose: 0.859833 loss: 0.000523 2022/09/13 20:23:22 - mmengine - INFO - Epoch(train) [183][200/293] lr: 5.000000e-05 eta: 0:57:23 time: 0.508257 data_time: 0.079333 memory: 9871 loss_kpt: 0.000537 acc_pose: 0.809531 loss: 0.000537 2022/09/13 20:23:47 - mmengine - INFO - Epoch(train) [183][250/293] lr: 5.000000e-05 eta: 0:57:02 time: 0.507072 data_time: 0.082149 memory: 9871 loss_kpt: 0.000518 acc_pose: 0.818048 loss: 0.000518 2022/09/13 20:24:09 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 20:24:09 - mmengine - INFO - Saving checkpoint at 183 epochs 2022/09/13 20:24:39 - mmengine - INFO - Epoch(train) [184][50/293] lr: 5.000000e-05 eta: 0:56:20 time: 0.518896 data_time: 0.082785 memory: 9871 loss_kpt: 0.000535 acc_pose: 0.847681 loss: 0.000535 2022/09/13 20:25:04 - mmengine - INFO - Epoch(train) [184][100/293] lr: 5.000000e-05 eta: 0:55:59 time: 0.499165 data_time: 0.083868 memory: 9871 loss_kpt: 0.000529 acc_pose: 0.875488 loss: 0.000529 2022/09/13 20:25:29 - mmengine - INFO - Epoch(train) [184][150/293] lr: 5.000000e-05 eta: 0:55:38 time: 0.493415 data_time: 0.082092 memory: 9871 loss_kpt: 0.000521 acc_pose: 0.870668 loss: 0.000521 2022/09/13 20:25:54 - mmengine - INFO - Epoch(train) [184][200/293] lr: 5.000000e-05 eta: 0:55:17 time: 0.501069 data_time: 0.078173 memory: 9871 loss_kpt: 0.000525 acc_pose: 0.838155 loss: 0.000525 2022/09/13 20:26:19 - mmengine - INFO - Epoch(train) [184][250/293] lr: 5.000000e-05 eta: 0:54:56 time: 0.511125 data_time: 0.079117 memory: 9871 loss_kpt: 0.000540 acc_pose: 0.839882 loss: 0.000540 2022/09/13 20:26:41 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 20:26:41 - mmengine - INFO - Saving checkpoint at 184 epochs 2022/09/13 20:27:11 - mmengine - INFO - Epoch(train) [185][50/293] lr: 5.000000e-05 eta: 0:54:14 time: 0.516282 data_time: 0.085034 memory: 9871 loss_kpt: 0.000529 acc_pose: 0.882623 loss: 0.000529 2022/09/13 20:27:30 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 20:27:36 - mmengine - INFO - Epoch(train) [185][100/293] lr: 5.000000e-05 eta: 0:53:53 time: 0.500096 data_time: 0.077373 memory: 9871 loss_kpt: 0.000527 acc_pose: 0.866949 loss: 0.000527 2022/09/13 20:28:01 - mmengine - INFO - Epoch(train) [185][150/293] lr: 5.000000e-05 eta: 0:53:32 time: 0.501780 data_time: 0.079763 memory: 9871 loss_kpt: 0.000524 acc_pose: 0.883642 loss: 0.000524 2022/09/13 20:28:27 - mmengine - INFO - Epoch(train) [185][200/293] lr: 5.000000e-05 eta: 0:53:11 time: 0.505059 data_time: 0.081419 memory: 9871 loss_kpt: 0.000528 acc_pose: 0.866753 loss: 0.000528 2022/09/13 20:28:52 - mmengine - INFO - Epoch(train) [185][250/293] lr: 5.000000e-05 eta: 0:52:50 time: 0.497473 data_time: 0.073620 memory: 9871 loss_kpt: 0.000527 acc_pose: 0.880273 loss: 0.000527 2022/09/13 20:29:13 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 20:29:13 - mmengine - INFO - Saving checkpoint at 185 epochs 2022/09/13 20:29:43 - mmengine - INFO - Epoch(train) [186][50/293] lr: 5.000000e-05 eta: 0:52:08 time: 0.519327 data_time: 0.090147 memory: 9871 loss_kpt: 0.000538 acc_pose: 0.884331 loss: 0.000538 2022/09/13 20:30:09 - mmengine - INFO - Epoch(train) [186][100/293] lr: 5.000000e-05 eta: 0:51:47 time: 0.505020 data_time: 0.083215 memory: 9871 loss_kpt: 0.000523 acc_pose: 0.822906 loss: 0.000523 2022/09/13 20:30:33 - mmengine - INFO - Epoch(train) [186][150/293] lr: 5.000000e-05 eta: 0:51:26 time: 0.496176 data_time: 0.076794 memory: 9871 loss_kpt: 0.000529 acc_pose: 0.829060 loss: 0.000529 2022/09/13 20:30:58 - mmengine - INFO - Epoch(train) [186][200/293] lr: 5.000000e-05 eta: 0:51:05 time: 0.495917 data_time: 0.077269 memory: 9871 loss_kpt: 0.000517 acc_pose: 0.850384 loss: 0.000517 2022/09/13 20:31:23 - mmengine - INFO - Epoch(train) [186][250/293] lr: 5.000000e-05 eta: 0:50:44 time: 0.494966 data_time: 0.073120 memory: 9871 loss_kpt: 0.000524 acc_pose: 0.872908 loss: 0.000524 2022/09/13 20:31:45 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 20:31:45 - mmengine - INFO - Saving checkpoint at 186 epochs 2022/09/13 20:32:15 - mmengine - INFO - Epoch(train) [187][50/293] lr: 5.000000e-05 eta: 0:50:02 time: 0.514578 data_time: 0.083930 memory: 9871 loss_kpt: 0.000516 acc_pose: 0.890027 loss: 0.000516 2022/09/13 20:32:39 - mmengine - INFO - Epoch(train) [187][100/293] lr: 5.000000e-05 eta: 0:49:41 time: 0.487587 data_time: 0.077515 memory: 9871 loss_kpt: 0.000523 acc_pose: 0.857042 loss: 0.000523 2022/09/13 20:33:05 - mmengine - INFO - Epoch(train) [187][150/293] lr: 5.000000e-05 eta: 0:49:20 time: 0.510817 data_time: 0.078481 memory: 9871 loss_kpt: 0.000525 acc_pose: 0.838272 loss: 0.000525 2022/09/13 20:33:29 - mmengine - INFO - Epoch(train) [187][200/293] lr: 5.000000e-05 eta: 0:48:59 time: 0.493069 data_time: 0.075389 memory: 9871 loss_kpt: 0.000532 acc_pose: 0.840262 loss: 0.000532 2022/09/13 20:33:55 - mmengine - INFO - Epoch(train) [187][250/293] lr: 5.000000e-05 eta: 0:48:38 time: 0.514761 data_time: 0.078469 memory: 9871 loss_kpt: 0.000541 acc_pose: 0.841130 loss: 0.000541 2022/09/13 20:34:17 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 20:34:17 - mmengine - INFO - Saving checkpoint at 187 epochs 2022/09/13 20:34:46 - mmengine - INFO - Epoch(train) [188][50/293] lr: 5.000000e-05 eta: 0:47:56 time: 0.507881 data_time: 0.086092 memory: 9871 loss_kpt: 0.000514 acc_pose: 0.831655 loss: 0.000514 2022/09/13 20:35:13 - mmengine - INFO - Epoch(train) [188][100/293] lr: 5.000000e-05 eta: 0:47:35 time: 0.525920 data_time: 0.077644 memory: 9871 loss_kpt: 0.000524 acc_pose: 0.826566 loss: 0.000524 2022/09/13 20:35:39 - mmengine - INFO - Epoch(train) [188][150/293] lr: 5.000000e-05 eta: 0:47:14 time: 0.519208 data_time: 0.091397 memory: 9871 loss_kpt: 0.000525 acc_pose: 0.859430 loss: 0.000525 2022/09/13 20:36:04 - mmengine - INFO - Epoch(train) [188][200/293] lr: 5.000000e-05 eta: 0:46:53 time: 0.500926 data_time: 0.078302 memory: 9871 loss_kpt: 0.000530 acc_pose: 0.840853 loss: 0.000530 2022/09/13 20:36:08 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 20:36:28 - mmengine - INFO - Epoch(train) [188][250/293] lr: 5.000000e-05 eta: 0:46:32 time: 0.494281 data_time: 0.077090 memory: 9871 loss_kpt: 0.000522 acc_pose: 0.876718 loss: 0.000522 2022/09/13 20:36:50 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 20:36:50 - mmengine - INFO - Saving checkpoint at 188 epochs 2022/09/13 20:37:21 - mmengine - INFO - Epoch(train) [189][50/293] lr: 5.000000e-05 eta: 0:45:50 time: 0.521098 data_time: 0.089340 memory: 9871 loss_kpt: 0.000531 acc_pose: 0.826144 loss: 0.000531 2022/09/13 20:37:47 - mmengine - INFO - Epoch(train) [189][100/293] lr: 5.000000e-05 eta: 0:45:29 time: 0.513387 data_time: 0.079782 memory: 9871 loss_kpt: 0.000520 acc_pose: 0.833611 loss: 0.000520 2022/09/13 20:38:11 - mmengine - INFO - Epoch(train) [189][150/293] lr: 5.000000e-05 eta: 0:45:08 time: 0.495301 data_time: 0.078642 memory: 9871 loss_kpt: 0.000534 acc_pose: 0.864331 loss: 0.000534 2022/09/13 20:38:37 - mmengine - INFO - Epoch(train) [189][200/293] lr: 5.000000e-05 eta: 0:44:47 time: 0.509105 data_time: 0.075936 memory: 9871 loss_kpt: 0.000534 acc_pose: 0.839348 loss: 0.000534 2022/09/13 20:39:02 - mmengine - INFO - Epoch(train) [189][250/293] lr: 5.000000e-05 eta: 0:44:26 time: 0.505780 data_time: 0.074976 memory: 9871 loss_kpt: 0.000532 acc_pose: 0.883571 loss: 0.000532 2022/09/13 20:39:24 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 20:39:24 - mmengine - INFO - Saving checkpoint at 189 epochs 2022/09/13 20:39:54 - mmengine - INFO - Epoch(train) [190][50/293] lr: 5.000000e-05 eta: 0:43:44 time: 0.513416 data_time: 0.085589 memory: 9871 loss_kpt: 0.000524 acc_pose: 0.896717 loss: 0.000524 2022/09/13 20:40:19 - mmengine - INFO - Epoch(train) [190][100/293] lr: 5.000000e-05 eta: 0:43:23 time: 0.512657 data_time: 0.079243 memory: 9871 loss_kpt: 0.000529 acc_pose: 0.858442 loss: 0.000529 2022/09/13 20:40:45 - mmengine - INFO - Epoch(train) [190][150/293] lr: 5.000000e-05 eta: 0:43:02 time: 0.512005 data_time: 0.074965 memory: 9871 loss_kpt: 0.000531 acc_pose: 0.819452 loss: 0.000531 2022/09/13 20:41:10 - mmengine - INFO - Epoch(train) [190][200/293] lr: 5.000000e-05 eta: 0:42:41 time: 0.500138 data_time: 0.076457 memory: 9871 loss_kpt: 0.000526 acc_pose: 0.838649 loss: 0.000526 2022/09/13 20:41:35 - mmengine - INFO - Epoch(train) [190][250/293] lr: 5.000000e-05 eta: 0:42:20 time: 0.495219 data_time: 0.086806 memory: 9871 loss_kpt: 0.000528 acc_pose: 0.861178 loss: 0.000528 2022/09/13 20:41:57 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 20:41:57 - mmengine - INFO - Saving checkpoint at 190 epochs 2022/09/13 20:42:10 - mmengine - INFO - Epoch(val) [190][50/407] eta: 0:01:00 time: 0.169788 data_time: 0.016191 memory: 9871 2022/09/13 20:42:18 - mmengine - INFO - Epoch(val) [190][100/407] eta: 0:00:50 time: 0.163041 data_time: 0.011120 memory: 920 2022/09/13 20:42:26 - mmengine - INFO - Epoch(val) [190][150/407] eta: 0:00:40 time: 0.157293 data_time: 0.007755 memory: 920 2022/09/13 20:42:34 - mmengine - INFO - Epoch(val) [190][200/407] eta: 0:00:32 time: 0.158810 data_time: 0.008744 memory: 920 2022/09/13 20:42:42 - mmengine - INFO - Epoch(val) [190][250/407] eta: 0:00:25 time: 0.160337 data_time: 0.007406 memory: 920 2022/09/13 20:42:50 - mmengine - INFO - Epoch(val) [190][300/407] eta: 0:00:16 time: 0.158317 data_time: 0.008078 memory: 920 2022/09/13 20:42:58 - mmengine - INFO - Epoch(val) [190][350/407] eta: 0:00:09 time: 0.160556 data_time: 0.007596 memory: 920 2022/09/13 20:43:05 - mmengine - INFO - Epoch(val) [190][400/407] eta: 0:00:01 time: 0.156108 data_time: 0.007616 memory: 920 2022/09/13 20:43:41 - mmengine - INFO - Evaluating CocoMetric... 2022/09/13 20:43:55 - mmengine - INFO - Epoch(val) [190][407/407] coco/AP: 0.756403 coco/AP .5: 0.906076 coco/AP .75: 0.823429 coco/AP (M): 0.719199 coco/AP (L): 0.824926 coco/AR: 0.806486 coco/AR .5: 0.942853 coco/AR .75: 0.867916 coco/AR (M): 0.763507 coco/AR (L): 0.868636 2022/09/13 20:43:55 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220913/dark_w32_256_v1/best_coco/AP_epoch_180.pth is removed 2022/09/13 20:43:58 - mmengine - INFO - The best checkpoint with 0.7564 coco/AP at 190 epoch is saved to best_coco/AP_epoch_190.pth. 2022/09/13 20:44:24 - mmengine - INFO - Epoch(train) [191][50/293] lr: 5.000000e-05 eta: 0:41:39 time: 0.525467 data_time: 0.085513 memory: 9871 loss_kpt: 0.000524 acc_pose: 0.833089 loss: 0.000524 2022/09/13 20:44:49 - mmengine - INFO - Epoch(train) [191][100/293] lr: 5.000000e-05 eta: 0:41:17 time: 0.501248 data_time: 0.078100 memory: 9871 loss_kpt: 0.000521 acc_pose: 0.852824 loss: 0.000521 2022/09/13 20:45:15 - mmengine - INFO - Epoch(train) [191][150/293] lr: 5.000000e-05 eta: 0:40:56 time: 0.511171 data_time: 0.077616 memory: 9871 loss_kpt: 0.000517 acc_pose: 0.841561 loss: 0.000517 2022/09/13 20:45:41 - mmengine - INFO - Epoch(train) [191][200/293] lr: 5.000000e-05 eta: 0:40:35 time: 0.523975 data_time: 0.082385 memory: 9871 loss_kpt: 0.000529 acc_pose: 0.897072 loss: 0.000529 2022/09/13 20:46:06 - mmengine - INFO - Epoch(train) [191][250/293] lr: 5.000000e-05 eta: 0:40:14 time: 0.494088 data_time: 0.076580 memory: 9871 loss_kpt: 0.000524 acc_pose: 0.880883 loss: 0.000524 2022/09/13 20:46:27 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 20:46:27 - mmengine - INFO - Saving checkpoint at 191 epochs 2022/09/13 20:46:50 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 20:46:57 - mmengine - INFO - Epoch(train) [192][50/293] lr: 5.000000e-05 eta: 0:39:33 time: 0.502135 data_time: 0.080429 memory: 9871 loss_kpt: 0.000522 acc_pose: 0.879939 loss: 0.000522 2022/09/13 20:47:22 - mmengine - INFO - Epoch(train) [192][100/293] lr: 5.000000e-05 eta: 0:39:11 time: 0.497037 data_time: 0.076770 memory: 9871 loss_kpt: 0.000531 acc_pose: 0.877408 loss: 0.000531 2022/09/13 20:47:47 - mmengine - INFO - Epoch(train) [192][150/293] lr: 5.000000e-05 eta: 0:38:50 time: 0.507685 data_time: 0.076586 memory: 9871 loss_kpt: 0.000516 acc_pose: 0.830067 loss: 0.000516 2022/09/13 20:48:12 - mmengine - INFO - Epoch(train) [192][200/293] lr: 5.000000e-05 eta: 0:38:29 time: 0.499401 data_time: 0.085306 memory: 9871 loss_kpt: 0.000525 acc_pose: 0.871756 loss: 0.000525 2022/09/13 20:48:38 - mmengine - INFO - Epoch(train) [192][250/293] lr: 5.000000e-05 eta: 0:38:08 time: 0.509794 data_time: 0.069486 memory: 9871 loss_kpt: 0.000529 acc_pose: 0.856408 loss: 0.000529 2022/09/13 20:48:59 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 20:48:59 - mmengine - INFO - Saving checkpoint at 192 epochs 2022/09/13 20:49:29 - mmengine - INFO - Epoch(train) [193][50/293] lr: 5.000000e-05 eta: 0:37:27 time: 0.518519 data_time: 0.079887 memory: 9871 loss_kpt: 0.000524 acc_pose: 0.832610 loss: 0.000524 2022/09/13 20:49:54 - mmengine - INFO - Epoch(train) [193][100/293] lr: 5.000000e-05 eta: 0:37:05 time: 0.499269 data_time: 0.071540 memory: 9871 loss_kpt: 0.000530 acc_pose: 0.878325 loss: 0.000530 2022/09/13 20:50:19 - mmengine - INFO - Epoch(train) [193][150/293] lr: 5.000000e-05 eta: 0:36:44 time: 0.504756 data_time: 0.076073 memory: 9871 loss_kpt: 0.000520 acc_pose: 0.830468 loss: 0.000520 2022/09/13 20:50:44 - mmengine - INFO - Epoch(train) [193][200/293] lr: 5.000000e-05 eta: 0:36:23 time: 0.503389 data_time: 0.083623 memory: 9871 loss_kpt: 0.000534 acc_pose: 0.865176 loss: 0.000534 2022/09/13 20:51:10 - mmengine - INFO - Epoch(train) [193][250/293] lr: 5.000000e-05 eta: 0:36:02 time: 0.503051 data_time: 0.079325 memory: 9871 loss_kpt: 0.000531 acc_pose: 0.856254 loss: 0.000531 2022/09/13 20:51:31 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 20:51:31 - mmengine - INFO - Saving checkpoint at 193 epochs 2022/09/13 20:52:01 - mmengine - INFO - Epoch(train) [194][50/293] lr: 5.000000e-05 eta: 0:35:21 time: 0.507989 data_time: 0.079276 memory: 9871 loss_kpt: 0.000522 acc_pose: 0.850000 loss: 0.000522 2022/09/13 20:52:26 - mmengine - INFO - Epoch(train) [194][100/293] lr: 5.000000e-05 eta: 0:34:59 time: 0.508797 data_time: 0.087054 memory: 9871 loss_kpt: 0.000521 acc_pose: 0.866637 loss: 0.000521 2022/09/13 20:52:51 - mmengine - INFO - Epoch(train) [194][150/293] lr: 5.000000e-05 eta: 0:34:38 time: 0.508947 data_time: 0.077113 memory: 9871 loss_kpt: 0.000533 acc_pose: 0.889048 loss: 0.000533 2022/09/13 20:53:16 - mmengine - INFO - Epoch(train) [194][200/293] lr: 5.000000e-05 eta: 0:34:17 time: 0.496697 data_time: 0.077027 memory: 9871 loss_kpt: 0.000522 acc_pose: 0.837908 loss: 0.000522 2022/09/13 20:53:42 - mmengine - INFO - Epoch(train) [194][250/293] lr: 5.000000e-05 eta: 0:33:56 time: 0.510939 data_time: 0.077324 memory: 9871 loss_kpt: 0.000529 acc_pose: 0.840538 loss: 0.000529 2022/09/13 20:54:04 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 20:54:04 - mmengine - INFO - Saving checkpoint at 194 epochs 2022/09/13 20:54:34 - mmengine - INFO - Epoch(train) [195][50/293] lr: 5.000000e-05 eta: 0:33:15 time: 0.518161 data_time: 0.087037 memory: 9871 loss_kpt: 0.000525 acc_pose: 0.867944 loss: 0.000525 2022/09/13 20:54:59 - mmengine - INFO - Epoch(train) [195][100/293] lr: 5.000000e-05 eta: 0:32:53 time: 0.507932 data_time: 0.076844 memory: 9871 loss_kpt: 0.000521 acc_pose: 0.888959 loss: 0.000521 2022/09/13 20:55:24 - mmengine - INFO - Epoch(train) [195][150/293] lr: 5.000000e-05 eta: 0:32:32 time: 0.497507 data_time: 0.073430 memory: 9871 loss_kpt: 0.000507 acc_pose: 0.831310 loss: 0.000507 2022/09/13 20:55:28 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 20:55:49 - mmengine - INFO - Epoch(train) [195][200/293] lr: 5.000000e-05 eta: 0:32:11 time: 0.491540 data_time: 0.073234 memory: 9871 loss_kpt: 0.000524 acc_pose: 0.856240 loss: 0.000524 2022/09/13 20:56:14 - mmengine - INFO - Epoch(train) [195][250/293] lr: 5.000000e-05 eta: 0:31:50 time: 0.506867 data_time: 0.072673 memory: 9871 loss_kpt: 0.000535 acc_pose: 0.889839 loss: 0.000535 2022/09/13 20:56:35 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 20:56:35 - mmengine - INFO - Saving checkpoint at 195 epochs 2022/09/13 20:57:07 - mmengine - INFO - Epoch(train) [196][50/293] lr: 5.000000e-05 eta: 0:31:09 time: 0.514175 data_time: 0.092511 memory: 9871 loss_kpt: 0.000527 acc_pose: 0.885184 loss: 0.000527 2022/09/13 20:57:32 - mmengine - INFO - Epoch(train) [196][100/293] lr: 5.000000e-05 eta: 0:30:47 time: 0.504571 data_time: 0.077684 memory: 9871 loss_kpt: 0.000528 acc_pose: 0.876690 loss: 0.000528 2022/09/13 20:57:57 - mmengine - INFO - Epoch(train) [196][150/293] lr: 5.000000e-05 eta: 0:30:26 time: 0.499041 data_time: 0.074059 memory: 9871 loss_kpt: 0.000520 acc_pose: 0.815931 loss: 0.000520 2022/09/13 20:58:21 - mmengine - INFO - Epoch(train) [196][200/293] lr: 5.000000e-05 eta: 0:30:05 time: 0.489186 data_time: 0.078281 memory: 9871 loss_kpt: 0.000522 acc_pose: 0.833881 loss: 0.000522 2022/09/13 20:58:47 - mmengine - INFO - Epoch(train) [196][250/293] lr: 5.000000e-05 eta: 0:29:44 time: 0.514159 data_time: 0.082568 memory: 9871 loss_kpt: 0.000528 acc_pose: 0.855004 loss: 0.000528 2022/09/13 20:59:08 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 20:59:08 - mmengine - INFO - Saving checkpoint at 196 epochs 2022/09/13 20:59:38 - mmengine - INFO - Epoch(train) [197][50/293] lr: 5.000000e-05 eta: 0:29:03 time: 0.515248 data_time: 0.082084 memory: 9871 loss_kpt: 0.000528 acc_pose: 0.855640 loss: 0.000528 2022/09/13 21:00:03 - mmengine - INFO - Epoch(train) [197][100/293] lr: 5.000000e-05 eta: 0:28:41 time: 0.499884 data_time: 0.072733 memory: 9871 loss_kpt: 0.000527 acc_pose: 0.892281 loss: 0.000527 2022/09/13 21:00:28 - mmengine - INFO - Epoch(train) [197][150/293] lr: 5.000000e-05 eta: 0:28:20 time: 0.503602 data_time: 0.072930 memory: 9871 loss_kpt: 0.000518 acc_pose: 0.864830 loss: 0.000518 2022/09/13 21:00:53 - mmengine - INFO - Epoch(train) [197][200/293] lr: 5.000000e-05 eta: 0:27:59 time: 0.501083 data_time: 0.076956 memory: 9871 loss_kpt: 0.000518 acc_pose: 0.882665 loss: 0.000518 2022/09/13 21:01:19 - mmengine - INFO - Epoch(train) [197][250/293] lr: 5.000000e-05 eta: 0:27:37 time: 0.501068 data_time: 0.076734 memory: 9871 loss_kpt: 0.000519 acc_pose: 0.868554 loss: 0.000519 2022/09/13 21:01:40 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 21:01:40 - mmengine - INFO - Saving checkpoint at 197 epochs 2022/09/13 21:02:10 - mmengine - INFO - Epoch(train) [198][50/293] lr: 5.000000e-05 eta: 0:26:57 time: 0.513060 data_time: 0.079918 memory: 9871 loss_kpt: 0.000527 acc_pose: 0.859697 loss: 0.000527 2022/09/13 21:02:36 - mmengine - INFO - Epoch(train) [198][100/293] lr: 5.000000e-05 eta: 0:26:35 time: 0.502920 data_time: 0.080015 memory: 9871 loss_kpt: 0.000526 acc_pose: 0.846141 loss: 0.000526 2022/09/13 21:03:01 - mmengine - INFO - Epoch(train) [198][150/293] lr: 5.000000e-05 eta: 0:26:14 time: 0.510068 data_time: 0.079515 memory: 9871 loss_kpt: 0.000517 acc_pose: 0.871730 loss: 0.000517 2022/09/13 21:03:26 - mmengine - INFO - Epoch(train) [198][200/293] lr: 5.000000e-05 eta: 0:25:53 time: 0.499221 data_time: 0.077803 memory: 9871 loss_kpt: 0.000530 acc_pose: 0.855487 loss: 0.000530 2022/09/13 21:03:51 - mmengine - INFO - Epoch(train) [198][250/293] lr: 5.000000e-05 eta: 0:25:31 time: 0.503941 data_time: 0.078095 memory: 9871 loss_kpt: 0.000528 acc_pose: 0.851788 loss: 0.000528 2022/09/13 21:04:06 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 21:04:13 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 21:04:13 - mmengine - INFO - Saving checkpoint at 198 epochs 2022/09/13 21:04:43 - mmengine - INFO - Epoch(train) [199][50/293] lr: 5.000000e-05 eta: 0:24:51 time: 0.511961 data_time: 0.081769 memory: 9871 loss_kpt: 0.000529 acc_pose: 0.839909 loss: 0.000529 2022/09/13 21:05:09 - mmengine - INFO - Epoch(train) [199][100/293] lr: 5.000000e-05 eta: 0:24:29 time: 0.507494 data_time: 0.077315 memory: 9871 loss_kpt: 0.000523 acc_pose: 0.872111 loss: 0.000523 2022/09/13 21:05:34 - mmengine - INFO - Epoch(train) [199][150/293] lr: 5.000000e-05 eta: 0:24:08 time: 0.507737 data_time: 0.077090 memory: 9871 loss_kpt: 0.000520 acc_pose: 0.884316 loss: 0.000520 2022/09/13 21:05:59 - mmengine - INFO - Epoch(train) [199][200/293] lr: 5.000000e-05 eta: 0:23:47 time: 0.502666 data_time: 0.074625 memory: 9871 loss_kpt: 0.000515 acc_pose: 0.851581 loss: 0.000515 2022/09/13 21:06:24 - mmengine - INFO - Epoch(train) [199][250/293] lr: 5.000000e-05 eta: 0:23:25 time: 0.495533 data_time: 0.072174 memory: 9871 loss_kpt: 0.000514 acc_pose: 0.873757 loss: 0.000514 2022/09/13 21:06:45 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 21:06:45 - mmengine - INFO - Saving checkpoint at 199 epochs 2022/09/13 21:07:15 - mmengine - INFO - Epoch(train) [200][50/293] lr: 5.000000e-05 eta: 0:22:44 time: 0.513069 data_time: 0.091427 memory: 9871 loss_kpt: 0.000529 acc_pose: 0.892608 loss: 0.000529 2022/09/13 21:07:40 - mmengine - INFO - Epoch(train) [200][100/293] lr: 5.000000e-05 eta: 0:22:23 time: 0.505199 data_time: 0.080972 memory: 9871 loss_kpt: 0.000522 acc_pose: 0.803145 loss: 0.000522 2022/09/13 21:08:05 - mmengine - INFO - Epoch(train) [200][150/293] lr: 5.000000e-05 eta: 0:22:02 time: 0.495319 data_time: 0.077536 memory: 9871 loss_kpt: 0.000542 acc_pose: 0.856123 loss: 0.000542 2022/09/13 21:08:31 - mmengine - INFO - Epoch(train) [200][200/293] lr: 5.000000e-05 eta: 0:21:41 time: 0.511229 data_time: 0.078582 memory: 9871 loss_kpt: 0.000518 acc_pose: 0.880545 loss: 0.000518 2022/09/13 21:08:55 - mmengine - INFO - Epoch(train) [200][250/293] lr: 5.000000e-05 eta: 0:21:19 time: 0.495891 data_time: 0.077061 memory: 9871 loss_kpt: 0.000523 acc_pose: 0.818422 loss: 0.000523 2022/09/13 21:09:17 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 21:09:17 - mmengine - INFO - Saving checkpoint at 200 epochs 2022/09/13 21:09:30 - mmengine - INFO - Epoch(val) [200][50/407] eta: 0:00:58 time: 0.163907 data_time: 0.012993 memory: 9871 2022/09/13 21:09:38 - mmengine - INFO - Epoch(val) [200][100/407] eta: 0:00:48 time: 0.157929 data_time: 0.007643 memory: 920 2022/09/13 21:09:46 - mmengine - INFO - Epoch(val) [200][150/407] eta: 0:00:40 time: 0.157002 data_time: 0.007581 memory: 920 2022/09/13 21:09:54 - mmengine - INFO - Epoch(val) [200][200/407] eta: 0:00:33 time: 0.160253 data_time: 0.010722 memory: 920 2022/09/13 21:10:02 - mmengine - INFO - Epoch(val) [200][250/407] eta: 0:00:25 time: 0.162388 data_time: 0.010546 memory: 920 2022/09/13 21:10:10 - mmengine - INFO - Epoch(val) [200][300/407] eta: 0:00:17 time: 0.159074 data_time: 0.008439 memory: 920 2022/09/13 21:10:18 - mmengine - INFO - Epoch(val) [200][350/407] eta: 0:00:09 time: 0.159502 data_time: 0.007531 memory: 920 2022/09/13 21:10:26 - mmengine - INFO - Epoch(val) [200][400/407] eta: 0:00:01 time: 0.155374 data_time: 0.007084 memory: 920 2022/09/13 21:11:01 - mmengine - INFO - Evaluating CocoMetric... 2022/09/13 21:11:15 - mmengine - INFO - Epoch(val) [200][407/407] coco/AP: 0.756559 coco/AP .5: 0.906109 coco/AP .75: 0.824442 coco/AP (M): 0.719994 coco/AP (L): 0.823785 coco/AR: 0.806250 coco/AR .5: 0.942380 coco/AR .75: 0.868545 coco/AR (M): 0.764818 coco/AR (L): 0.866778 2022/09/13 21:11:15 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220913/dark_w32_256_v1/best_coco/AP_epoch_190.pth is removed 2022/09/13 21:11:18 - mmengine - INFO - The best checkpoint with 0.7566 coco/AP at 200 epoch is saved to best_coco/AP_epoch_200.pth. 2022/09/13 21:11:44 - mmengine - INFO - Epoch(train) [201][50/293] lr: 5.000000e-06 eta: 0:20:38 time: 0.520476 data_time: 0.087307 memory: 9871 loss_kpt: 0.000538 acc_pose: 0.844143 loss: 0.000538 2022/09/13 21:12:09 - mmengine - INFO - Epoch(train) [201][100/293] lr: 5.000000e-06 eta: 0:20:17 time: 0.491720 data_time: 0.072650 memory: 9871 loss_kpt: 0.000503 acc_pose: 0.808986 loss: 0.000503 2022/09/13 21:12:33 - mmengine - INFO - Epoch(train) [201][150/293] lr: 5.000000e-06 eta: 0:19:56 time: 0.490577 data_time: 0.078390 memory: 9871 loss_kpt: 0.000527 acc_pose: 0.883410 loss: 0.000527 2022/09/13 21:12:58 - mmengine - INFO - Epoch(train) [201][200/293] lr: 5.000000e-06 eta: 0:19:34 time: 0.493270 data_time: 0.072992 memory: 9871 loss_kpt: 0.000515 acc_pose: 0.865669 loss: 0.000515 2022/09/13 21:13:23 - mmengine - INFO - Epoch(train) [201][250/293] lr: 5.000000e-06 eta: 0:19:13 time: 0.508422 data_time: 0.084469 memory: 9871 loss_kpt: 0.000511 acc_pose: 0.831378 loss: 0.000511 2022/09/13 21:13:45 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 21:13:45 - mmengine - INFO - Saving checkpoint at 201 epochs 2022/09/13 21:14:16 - mmengine - INFO - Epoch(train) [202][50/293] lr: 5.000000e-06 eta: 0:18:32 time: 0.520530 data_time: 0.088419 memory: 9871 loss_kpt: 0.000521 acc_pose: 0.821099 loss: 0.000521 2022/09/13 21:14:40 - mmengine - INFO - Epoch(train) [202][100/293] lr: 5.000000e-06 eta: 0:18:11 time: 0.490612 data_time: 0.076165 memory: 9871 loss_kpt: 0.000510 acc_pose: 0.855815 loss: 0.000510 2022/09/13 21:14:44 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 21:15:05 - mmengine - INFO - Epoch(train) [202][150/293] lr: 5.000000e-06 eta: 0:17:50 time: 0.491495 data_time: 0.070902 memory: 9871 loss_kpt: 0.000522 acc_pose: 0.856383 loss: 0.000522 2022/09/13 21:15:30 - mmengine - INFO - Epoch(train) [202][200/293] lr: 5.000000e-06 eta: 0:17:28 time: 0.510205 data_time: 0.080199 memory: 9871 loss_kpt: 0.000506 acc_pose: 0.836797 loss: 0.000506 2022/09/13 21:15:56 - mmengine - INFO - Epoch(train) [202][250/293] lr: 5.000000e-06 eta: 0:17:07 time: 0.516544 data_time: 0.078665 memory: 9871 loss_kpt: 0.000514 acc_pose: 0.882363 loss: 0.000514 2022/09/13 21:16:17 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 21:16:17 - mmengine - INFO - Saving checkpoint at 202 epochs 2022/09/13 21:16:47 - mmengine - INFO - Epoch(train) [203][50/293] lr: 5.000000e-06 eta: 0:16:26 time: 0.507424 data_time: 0.087813 memory: 9871 loss_kpt: 0.000513 acc_pose: 0.860225 loss: 0.000513 2022/09/13 21:17:13 - mmengine - INFO - Epoch(train) [203][100/293] lr: 5.000000e-06 eta: 0:16:05 time: 0.507361 data_time: 0.072881 memory: 9871 loss_kpt: 0.000518 acc_pose: 0.840705 loss: 0.000518 2022/09/13 21:17:37 - mmengine - INFO - Epoch(train) [203][150/293] lr: 5.000000e-06 eta: 0:15:44 time: 0.494999 data_time: 0.077852 memory: 9871 loss_kpt: 0.000525 acc_pose: 0.850751 loss: 0.000525 2022/09/13 21:18:03 - mmengine - INFO - Epoch(train) [203][200/293] lr: 5.000000e-06 eta: 0:15:22 time: 0.508775 data_time: 0.080914 memory: 9871 loss_kpt: 0.000507 acc_pose: 0.823822 loss: 0.000507 2022/09/13 21:18:28 - mmengine - INFO - Epoch(train) [203][250/293] lr: 5.000000e-06 eta: 0:15:01 time: 0.506023 data_time: 0.078202 memory: 9871 loss_kpt: 0.000527 acc_pose: 0.886876 loss: 0.000527 2022/09/13 21:18:50 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 21:18:50 - mmengine - INFO - Saving checkpoint at 203 epochs 2022/09/13 21:19:22 - mmengine - INFO - Epoch(train) [204][50/293] lr: 5.000000e-06 eta: 0:14:20 time: 0.527188 data_time: 0.081755 memory: 9871 loss_kpt: 0.000523 acc_pose: 0.777297 loss: 0.000523 2022/09/13 21:19:47 - mmengine - INFO - Epoch(train) [204][100/293] lr: 5.000000e-06 eta: 0:13:59 time: 0.500680 data_time: 0.082289 memory: 9871 loss_kpt: 0.000524 acc_pose: 0.840699 loss: 0.000524 2022/09/13 21:20:12 - mmengine - INFO - Epoch(train) [204][150/293] lr: 5.000000e-06 eta: 0:13:38 time: 0.497724 data_time: 0.081384 memory: 9871 loss_kpt: 0.000524 acc_pose: 0.827776 loss: 0.000524 2022/09/13 21:20:37 - mmengine - INFO - Epoch(train) [204][200/293] lr: 5.000000e-06 eta: 0:13:16 time: 0.502707 data_time: 0.074178 memory: 9871 loss_kpt: 0.000509 acc_pose: 0.834805 loss: 0.000509 2022/09/13 21:21:02 - mmengine - INFO - Epoch(train) [204][250/293] lr: 5.000000e-06 eta: 0:12:55 time: 0.498527 data_time: 0.076963 memory: 9871 loss_kpt: 0.000521 acc_pose: 0.808320 loss: 0.000521 2022/09/13 21:21:23 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 21:21:23 - mmengine - INFO - Saving checkpoint at 204 epochs 2022/09/13 21:21:54 - mmengine - INFO - Epoch(train) [205][50/293] lr: 5.000000e-06 eta: 0:12:14 time: 0.520906 data_time: 0.087530 memory: 9871 loss_kpt: 0.000524 acc_pose: 0.888395 loss: 0.000524 2022/09/13 21:22:18 - mmengine - INFO - Epoch(train) [205][100/293] lr: 5.000000e-06 eta: 0:11:53 time: 0.489184 data_time: 0.073246 memory: 9871 loss_kpt: 0.000520 acc_pose: 0.881605 loss: 0.000520 2022/09/13 21:22:44 - mmengine - INFO - Epoch(train) [205][150/293] lr: 5.000000e-06 eta: 0:11:31 time: 0.500655 data_time: 0.072432 memory: 9871 loss_kpt: 0.000520 acc_pose: 0.886245 loss: 0.000520 2022/09/13 21:23:09 - mmengine - INFO - Epoch(train) [205][200/293] lr: 5.000000e-06 eta: 0:11:10 time: 0.509599 data_time: 0.077928 memory: 9871 loss_kpt: 0.000525 acc_pose: 0.811668 loss: 0.000525 2022/09/13 21:23:23 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 21:23:34 - mmengine - INFO - Epoch(train) [205][250/293] lr: 5.000000e-06 eta: 0:10:49 time: 0.503992 data_time: 0.073049 memory: 9871 loss_kpt: 0.000509 acc_pose: 0.893090 loss: 0.000509 2022/09/13 21:23:56 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 21:23:56 - mmengine - INFO - Saving checkpoint at 205 epochs 2022/09/13 21:24:26 - mmengine - INFO - Epoch(train) [206][50/293] lr: 5.000000e-06 eta: 0:10:08 time: 0.518408 data_time: 0.085807 memory: 9871 loss_kpt: 0.000527 acc_pose: 0.849874 loss: 0.000527 2022/09/13 21:24:51 - mmengine - INFO - Epoch(train) [206][100/293] lr: 5.000000e-06 eta: 0:09:47 time: 0.507388 data_time: 0.074408 memory: 9871 loss_kpt: 0.000512 acc_pose: 0.838029 loss: 0.000512 2022/09/13 21:25:16 - mmengine - INFO - Epoch(train) [206][150/293] lr: 5.000000e-06 eta: 0:09:25 time: 0.502593 data_time: 0.079981 memory: 9871 loss_kpt: 0.000526 acc_pose: 0.819480 loss: 0.000526 2022/09/13 21:25:42 - mmengine - INFO - Epoch(train) [206][200/293] lr: 5.000000e-06 eta: 0:09:04 time: 0.510707 data_time: 0.073163 memory: 9871 loss_kpt: 0.000525 acc_pose: 0.829972 loss: 0.000525 2022/09/13 21:26:07 - mmengine - INFO - Epoch(train) [206][250/293] lr: 5.000000e-06 eta: 0:08:42 time: 0.496783 data_time: 0.074227 memory: 9871 loss_kpt: 0.000513 acc_pose: 0.867736 loss: 0.000513 2022/09/13 21:26:28 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 21:26:28 - mmengine - INFO - Saving checkpoint at 206 epochs 2022/09/13 21:26:59 - mmengine - INFO - Epoch(train) [207][50/293] lr: 5.000000e-06 eta: 0:08:02 time: 0.521572 data_time: 0.083367 memory: 9871 loss_kpt: 0.000529 acc_pose: 0.874888 loss: 0.000529 2022/09/13 21:27:24 - mmengine - INFO - Epoch(train) [207][100/293] lr: 5.000000e-06 eta: 0:07:41 time: 0.505527 data_time: 0.078882 memory: 9871 loss_kpt: 0.000517 acc_pose: 0.850159 loss: 0.000517 2022/09/13 21:27:49 - mmengine - INFO - Epoch(train) [207][150/293] lr: 5.000000e-06 eta: 0:07:19 time: 0.494625 data_time: 0.075526 memory: 9871 loss_kpt: 0.000527 acc_pose: 0.877968 loss: 0.000527 2022/09/13 21:28:14 - mmengine - INFO - Epoch(train) [207][200/293] lr: 5.000000e-06 eta: 0:06:58 time: 0.504594 data_time: 0.078147 memory: 9871 loss_kpt: 0.000534 acc_pose: 0.843834 loss: 0.000534 2022/09/13 21:28:39 - mmengine - INFO - Epoch(train) [207][250/293] lr: 5.000000e-06 eta: 0:06:36 time: 0.506110 data_time: 0.074468 memory: 9871 loss_kpt: 0.000514 acc_pose: 0.839226 loss: 0.000514 2022/09/13 21:29:01 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 21:29:01 - mmengine - INFO - Saving checkpoint at 207 epochs 2022/09/13 21:29:31 - mmengine - INFO - Epoch(train) [208][50/293] lr: 5.000000e-06 eta: 0:05:56 time: 0.515136 data_time: 0.092231 memory: 9871 loss_kpt: 0.000525 acc_pose: 0.857550 loss: 0.000525 2022/09/13 21:29:56 - mmengine - INFO - Epoch(train) [208][100/293] lr: 5.000000e-06 eta: 0:05:35 time: 0.503377 data_time: 0.077295 memory: 9871 loss_kpt: 0.000516 acc_pose: 0.885809 loss: 0.000516 2022/09/13 21:30:21 - mmengine - INFO - Epoch(train) [208][150/293] lr: 5.000000e-06 eta: 0:05:13 time: 0.501053 data_time: 0.079084 memory: 9871 loss_kpt: 0.000524 acc_pose: 0.889572 loss: 0.000524 2022/09/13 21:30:46 - mmengine - INFO - Epoch(train) [208][200/293] lr: 5.000000e-06 eta: 0:04:52 time: 0.503336 data_time: 0.076166 memory: 9871 loss_kpt: 0.000521 acc_pose: 0.874820 loss: 0.000521 2022/09/13 21:31:11 - mmengine - INFO - Epoch(train) [208][250/293] lr: 5.000000e-06 eta: 0:04:30 time: 0.499672 data_time: 0.078152 memory: 9871 loss_kpt: 0.000512 acc_pose: 0.835519 loss: 0.000512 2022/09/13 21:31:33 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 21:31:33 - mmengine - INFO - Saving checkpoint at 208 epochs 2022/09/13 21:32:03 - mmengine - INFO - Epoch(train) [209][50/293] lr: 5.000000e-06 eta: 0:03:50 time: 0.517853 data_time: 0.085229 memory: 9871 loss_kpt: 0.000516 acc_pose: 0.863471 loss: 0.000516 2022/09/13 21:32:06 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 21:32:28 - mmengine - INFO - Epoch(train) [209][100/293] lr: 5.000000e-06 eta: 0:03:29 time: 0.497242 data_time: 0.072854 memory: 9871 loss_kpt: 0.000514 acc_pose: 0.862169 loss: 0.000514 2022/09/13 21:32:53 - mmengine - INFO - Epoch(train) [209][150/293] lr: 5.000000e-06 eta: 0:03:07 time: 0.501879 data_time: 0.080396 memory: 9871 loss_kpt: 0.000521 acc_pose: 0.839576 loss: 0.000521 2022/09/13 21:33:19 - mmengine - INFO - Epoch(train) [209][200/293] lr: 5.000000e-06 eta: 0:02:46 time: 0.506333 data_time: 0.080894 memory: 9871 loss_kpt: 0.000520 acc_pose: 0.858290 loss: 0.000520 2022/09/13 21:33:44 - mmengine - INFO - Epoch(train) [209][250/293] lr: 5.000000e-06 eta: 0:02:24 time: 0.499024 data_time: 0.078876 memory: 9871 loss_kpt: 0.000516 acc_pose: 0.889215 loss: 0.000516 2022/09/13 21:34:06 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 21:34:06 - mmengine - INFO - Saving checkpoint at 209 epochs 2022/09/13 21:34:36 - mmengine - INFO - Epoch(train) [210][50/293] lr: 5.000000e-06 eta: 0:01:44 time: 0.518206 data_time: 0.085119 memory: 9871 loss_kpt: 0.000511 acc_pose: 0.887654 loss: 0.000511 2022/09/13 21:35:01 - mmengine - INFO - Epoch(train) [210][100/293] lr: 5.000000e-06 eta: 0:01:23 time: 0.499190 data_time: 0.078471 memory: 9871 loss_kpt: 0.000535 acc_pose: 0.839994 loss: 0.000535 2022/09/13 21:35:26 - mmengine - INFO - Epoch(train) [210][150/293] lr: 5.000000e-06 eta: 0:01:01 time: 0.511222 data_time: 0.081615 memory: 9871 loss_kpt: 0.000526 acc_pose: 0.892376 loss: 0.000526 2022/09/13 21:35:51 - mmengine - INFO - Epoch(train) [210][200/293] lr: 5.000000e-06 eta: 0:00:40 time: 0.490048 data_time: 0.073962 memory: 9871 loss_kpt: 0.000527 acc_pose: 0.876091 loss: 0.000527 2022/09/13 21:36:16 - mmengine - INFO - Epoch(train) [210][250/293] lr: 5.000000e-06 eta: 0:00:18 time: 0.504136 data_time: 0.082142 memory: 9871 loss_kpt: 0.000514 acc_pose: 0.852460 loss: 0.000514 2022/09/13 21:36:38 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-256x192_20220913_120406 2022/09/13 21:36:38 - mmengine - INFO - Saving checkpoint at 210 epochs 2022/09/13 21:36:51 - mmengine - INFO - Epoch(val) [210][50/407] eta: 0:00:58 time: 0.164180 data_time: 0.012315 memory: 9871 2022/09/13 21:36:59 - mmengine - INFO - Epoch(val) [210][100/407] eta: 0:00:51 time: 0.166763 data_time: 0.007796 memory: 920 2022/09/13 21:37:07 - mmengine - INFO - Epoch(val) [210][150/407] eta: 0:00:41 time: 0.159567 data_time: 0.007985 memory: 920 2022/09/13 21:37:15 - mmengine - INFO - Epoch(val) [210][200/407] eta: 0:00:32 time: 0.158328 data_time: 0.008045 memory: 920 2022/09/13 21:37:23 - mmengine - INFO - Epoch(val) [210][250/407] eta: 0:00:24 time: 0.156932 data_time: 0.007633 memory: 920 2022/09/13 21:37:31 - mmengine - INFO - Epoch(val) [210][300/407] eta: 0:00:16 time: 0.157548 data_time: 0.007509 memory: 920 2022/09/13 21:37:39 - mmengine - INFO - Epoch(val) [210][350/407] eta: 0:00:08 time: 0.156353 data_time: 0.007677 memory: 920 2022/09/13 21:37:47 - mmengine - INFO - Epoch(val) [210][400/407] eta: 0:00:01 time: 0.155509 data_time: 0.007245 memory: 920 2022/09/13 21:38:22 - mmengine - INFO - Evaluating CocoMetric... 2022/09/13 21:38:36 - mmengine - INFO - Epoch(val) [210][407/407] coco/AP: 0.757120 coco/AP .5: 0.906605 coco/AP .75: 0.825454 coco/AP (M): 0.720846 coco/AP (L): 0.824681 coco/AR: 0.806958 coco/AR .5: 0.942695 coco/AR .75: 0.869332 coco/AR (M): 0.764900 coco/AR (L): 0.868042 2022/09/13 21:38:36 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220913/dark_w32_256_v1/best_coco/AP_epoch_200.pth is removed 2022/09/13 21:38:40 - mmengine - INFO - The best checkpoint with 0.7571 coco/AP at 210 epoch is saved to best_coco/AP_epoch_210.pth.