2022/09/16 12:20:03 - 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: 460239037 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 ------------------------------------------------------------ 2022/09/16 12:20:05 - 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=(288, 384), heatmap_size=(72, 96), sigma=3, 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=(288, 384), heatmap_size=(72, 96), sigma=3, 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=(288, 384)), dict( type='GenerateTarget', target_type='heatmap', encoder=dict( type='MSRAHeatmap', input_size=(288, 384), heatmap_size=(72, 96), sigma=3, 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=(288, 384)), 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=(288, 384)), dict( type='GenerateTarget', target_type='heatmap', encoder=dict( type='MSRAHeatmap', input_size=(288, 384), heatmap_size=(72, 96), sigma=3, 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=(288, 384)), 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=(288, 384)), 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/20220916/dark_w32_384/' 2022/09/16 12:20:47 - 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. 2022/09/16 12:20:47 - 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. 2022/09/16 12:20:47 - 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. 2022/09/16 12:20:47 - 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. 2022/09/16 12:20:47 - 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. 2022/09/16 12:20:47 - 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. 2022/09/16 12:20:47 - 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. 2022/09/16 12:20:47 - 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. 2022/09/16 12:20:51 - 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. 2022/09/16 12:20:54 - 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. 2022/09/16 12:20:56 - 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. 2022/09/16 12:20:56 - 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 2022/09/16 12:21:11 - mmengine - INFO - Checkpoints will be saved to /mnt/lustre/liqikai/work_dirs/20220916/dark_w32_384 by HardDiskBackend. 2022/09/16 12:22:03 - mmengine - INFO - Epoch(train) [1][50/293] lr: 4.954910e-05 eta: 17:42:59 time: 1.037403 data_time: 0.326201 memory: 21676 loss_kpt: 0.002201 acc_pose: 0.165167 loss: 0.002201 2022/09/16 12:22:41 - mmengine - INFO - Epoch(train) [1][100/293] lr: 9.959920e-05 eta: 15:21:46 time: 0.763241 data_time: 0.103252 memory: 21676 loss_kpt: 0.001857 acc_pose: 0.349820 loss: 0.001857 2022/09/16 12:23:20 - mmengine - INFO - Epoch(train) [1][150/293] lr: 1.496493e-04 eta: 14:38:57 time: 0.776971 data_time: 0.099410 memory: 21676 loss_kpt: 0.001552 acc_pose: 0.485229 loss: 0.001552 2022/09/16 12:23:57 - mmengine - INFO - Epoch(train) [1][200/293] lr: 1.996994e-04 eta: 14:07:02 time: 0.737044 data_time: 0.097575 memory: 21676 loss_kpt: 0.001341 acc_pose: 0.550850 loss: 0.001341 2022/09/16 12:24:33 - mmengine - INFO - Epoch(train) [1][250/293] lr: 2.497495e-04 eta: 13:46:08 time: 0.729728 data_time: 0.095642 memory: 21676 loss_kpt: 0.001239 acc_pose: 0.576604 loss: 0.001239 2022/09/16 12:25:05 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 12:25:05 - mmengine - INFO - Saving checkpoint at 1 epochs 2022/09/16 12:25:49 - mmengine - INFO - Epoch(train) [2][50/293] lr: 3.428427e-04 eta: 11:56:37 time: 0.776330 data_time: 0.104630 memory: 21676 loss_kpt: 0.001127 acc_pose: 0.559673 loss: 0.001127 2022/09/16 12:26:27 - mmengine - INFO - Epoch(train) [2][100/293] lr: 3.928928e-04 eta: 12:04:17 time: 0.766360 data_time: 0.096320 memory: 21676 loss_kpt: 0.001075 acc_pose: 0.594667 loss: 0.001075 2022/09/16 12:27:05 - mmengine - INFO - Epoch(train) [2][150/293] lr: 4.429429e-04 eta: 12:09:26 time: 0.760794 data_time: 0.095709 memory: 21676 loss_kpt: 0.001061 acc_pose: 0.650266 loss: 0.001061 2022/09/16 12:27:44 - mmengine - INFO - Epoch(train) [2][200/293] lr: 4.929930e-04 eta: 12:14:45 time: 0.773703 data_time: 0.106047 memory: 21676 loss_kpt: 0.001069 acc_pose: 0.692145 loss: 0.001069 2022/09/16 12:28:22 - mmengine - INFO - Epoch(train) [2][250/293] lr: 5.000000e-04 eta: 12:18:06 time: 0.764543 data_time: 0.096414 memory: 21676 loss_kpt: 0.001025 acc_pose: 0.715875 loss: 0.001025 2022/09/16 12:28:55 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 12:28:55 - mmengine - INFO - Saving checkpoint at 2 epochs 2022/09/16 12:29:38 - mmengine - INFO - Epoch(train) [3][50/293] lr: 5.000000e-04 eta: 11:31:36 time: 0.782038 data_time: 0.116924 memory: 21676 loss_kpt: 0.000993 acc_pose: 0.587664 loss: 0.000993 2022/09/16 12:30:16 - mmengine - INFO - Epoch(train) [3][100/293] lr: 5.000000e-04 eta: 11:36:41 time: 0.757929 data_time: 0.098464 memory: 21676 loss_kpt: 0.000959 acc_pose: 0.733112 loss: 0.000959 2022/09/16 12:30:55 - mmengine - INFO - Epoch(train) [3][150/293] lr: 5.000000e-04 eta: 11:41:40 time: 0.767628 data_time: 0.102784 memory: 21676 loss_kpt: 0.000955 acc_pose: 0.672801 loss: 0.000955 2022/09/16 12:31:34 - mmengine - INFO - Epoch(train) [3][200/293] lr: 5.000000e-04 eta: 11:46:43 time: 0.779808 data_time: 0.108077 memory: 21676 loss_kpt: 0.000944 acc_pose: 0.709147 loss: 0.000944 2022/09/16 12:32:12 - mmengine - INFO - Epoch(train) [3][250/293] lr: 5.000000e-04 eta: 11:50:08 time: 0.764164 data_time: 0.105022 memory: 21676 loss_kpt: 0.000932 acc_pose: 0.682869 loss: 0.000932 2022/09/16 12:32:45 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 12:32:45 - mmengine - INFO - Saving checkpoint at 3 epochs 2022/09/16 12:33:28 - mmengine - INFO - Epoch(train) [4][50/293] lr: 5.000000e-04 eta: 11:20:18 time: 0.777001 data_time: 0.105976 memory: 21676 loss_kpt: 0.000901 acc_pose: 0.697111 loss: 0.000901 2022/09/16 12:34:07 - mmengine - INFO - Epoch(train) [4][100/293] lr: 5.000000e-04 eta: 11:25:08 time: 0.778256 data_time: 0.103811 memory: 21676 loss_kpt: 0.000926 acc_pose: 0.720667 loss: 0.000926 2022/09/16 12:34:23 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 12:34:45 - mmengine - INFO - Epoch(train) [4][150/293] lr: 5.000000e-04 eta: 11:29:06 time: 0.771410 data_time: 0.108060 memory: 21676 loss_kpt: 0.000910 acc_pose: 0.637913 loss: 0.000910 2022/09/16 12:35:23 - mmengine - INFO - Epoch(train) [4][200/293] lr: 5.000000e-04 eta: 11:32:10 time: 0.761218 data_time: 0.096965 memory: 21676 loss_kpt: 0.000899 acc_pose: 0.700780 loss: 0.000899 2022/09/16 12:36:01 - mmengine - INFO - Epoch(train) [4][250/293] lr: 5.000000e-04 eta: 11:34:18 time: 0.747864 data_time: 0.092238 memory: 21676 loss_kpt: 0.000881 acc_pose: 0.719860 loss: 0.000881 2022/09/16 12:36:33 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 12:36:33 - mmengine - INFO - Saving checkpoint at 4 epochs 2022/09/16 12:37:17 - mmengine - INFO - Epoch(train) [5][50/293] lr: 5.000000e-04 eta: 11:12:14 time: 0.772084 data_time: 0.106822 memory: 21676 loss_kpt: 0.000864 acc_pose: 0.738839 loss: 0.000864 2022/09/16 12:37:56 - mmengine - INFO - Epoch(train) [5][100/293] lr: 5.000000e-04 eta: 11:16:10 time: 0.782928 data_time: 0.096676 memory: 21676 loss_kpt: 0.000873 acc_pose: 0.692071 loss: 0.000873 2022/09/16 12:38:34 - mmengine - INFO - Epoch(train) [5][150/293] lr: 5.000000e-04 eta: 11:19:30 time: 0.775582 data_time: 0.093750 memory: 21676 loss_kpt: 0.000874 acc_pose: 0.686014 loss: 0.000874 2022/09/16 12:39:12 - mmengine - INFO - Epoch(train) [5][200/293] lr: 5.000000e-04 eta: 11:21:43 time: 0.753538 data_time: 0.096446 memory: 21676 loss_kpt: 0.000849 acc_pose: 0.724210 loss: 0.000849 2022/09/16 12:39:50 - mmengine - INFO - Epoch(train) [5][250/293] lr: 5.000000e-04 eta: 11:23:49 time: 0.755528 data_time: 0.098447 memory: 21676 loss_kpt: 0.000845 acc_pose: 0.699943 loss: 0.000845 2022/09/16 12:40:22 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 12:40:22 - mmengine - INFO - Saving checkpoint at 5 epochs 2022/09/16 12:41:06 - mmengine - INFO - Epoch(train) [6][50/293] lr: 5.000000e-04 eta: 11:06:47 time: 0.785614 data_time: 0.110750 memory: 21676 loss_kpt: 0.000836 acc_pose: 0.744297 loss: 0.000836 2022/09/16 12:41:44 - mmengine - INFO - Epoch(train) [6][100/293] lr: 5.000000e-04 eta: 11:09:17 time: 0.762321 data_time: 0.098251 memory: 21676 loss_kpt: 0.000832 acc_pose: 0.740673 loss: 0.000832 2022/09/16 12:42:22 - mmengine - INFO - Epoch(train) [6][150/293] lr: 5.000000e-04 eta: 11:11:25 time: 0.756904 data_time: 0.095054 memory: 21676 loss_kpt: 0.000846 acc_pose: 0.680202 loss: 0.000846 2022/09/16 12:43:00 - mmengine - INFO - Epoch(train) [6][200/293] lr: 5.000000e-04 eta: 11:13:47 time: 0.770055 data_time: 0.096868 memory: 21676 loss_kpt: 0.000835 acc_pose: 0.723215 loss: 0.000835 2022/09/16 12:43:38 - mmengine - INFO - Epoch(train) [6][250/293] lr: 5.000000e-04 eta: 11:15:25 time: 0.750985 data_time: 0.095945 memory: 21676 loss_kpt: 0.000831 acc_pose: 0.743529 loss: 0.000831 2022/09/16 12:44:10 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 12:44:10 - mmengine - INFO - Saving checkpoint at 6 epochs 2022/09/16 12:44:54 - mmengine - INFO - Epoch(train) [7][50/293] lr: 5.000000e-04 eta: 11:01:11 time: 0.780749 data_time: 0.112221 memory: 21676 loss_kpt: 0.000831 acc_pose: 0.716215 loss: 0.000831 2022/09/16 12:45:32 - mmengine - INFO - Epoch(train) [7][100/293] lr: 5.000000e-04 eta: 11:03:26 time: 0.769003 data_time: 0.098256 memory: 21676 loss_kpt: 0.000810 acc_pose: 0.745277 loss: 0.000810 2022/09/16 12:46:11 - mmengine - INFO - Epoch(train) [7][150/293] lr: 5.000000e-04 eta: 11:05:31 time: 0.768489 data_time: 0.096859 memory: 21676 loss_kpt: 0.000806 acc_pose: 0.745674 loss: 0.000806 2022/09/16 12:46:49 - mmengine - INFO - Epoch(train) [7][200/293] lr: 5.000000e-04 eta: 11:07:20 time: 0.763514 data_time: 0.099766 memory: 21676 loss_kpt: 0.000805 acc_pose: 0.701489 loss: 0.000805 2022/09/16 12:47:21 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 12:47:27 - mmengine - INFO - Epoch(train) [7][250/293] lr: 5.000000e-04 eta: 11:08:55 time: 0.759370 data_time: 0.099260 memory: 21676 loss_kpt: 0.000802 acc_pose: 0.704076 loss: 0.000802 2022/09/16 12:47:59 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 12:47:59 - mmengine - INFO - Saving checkpoint at 7 epochs 2022/09/16 12:48:43 - mmengine - INFO - Epoch(train) [8][50/293] lr: 5.000000e-04 eta: 10:56:53 time: 0.787690 data_time: 0.109857 memory: 21676 loss_kpt: 0.000787 acc_pose: 0.762868 loss: 0.000787 2022/09/16 12:49:20 - mmengine - INFO - Epoch(train) [8][100/293] lr: 5.000000e-04 eta: 10:58:29 time: 0.756733 data_time: 0.094877 memory: 21676 loss_kpt: 0.000797 acc_pose: 0.712103 loss: 0.000797 2022/09/16 12:49:58 - mmengine - INFO - Epoch(train) [8][150/293] lr: 5.000000e-04 eta: 10:59:52 time: 0.751704 data_time: 0.095345 memory: 21676 loss_kpt: 0.000781 acc_pose: 0.736399 loss: 0.000781 2022/09/16 12:50:36 - mmengine - INFO - Epoch(train) [8][200/293] lr: 5.000000e-04 eta: 11:01:18 time: 0.757925 data_time: 0.102911 memory: 21676 loss_kpt: 0.000778 acc_pose: 0.797919 loss: 0.000778 2022/09/16 12:51:14 - mmengine - INFO - Epoch(train) [8][250/293] lr: 5.000000e-04 eta: 11:02:36 time: 0.755960 data_time: 0.096775 memory: 21676 loss_kpt: 0.000780 acc_pose: 0.783535 loss: 0.000780 2022/09/16 12:51:46 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 12:51:46 - mmengine - INFO - Saving checkpoint at 8 epochs 2022/09/16 12:52:29 - mmengine - INFO - Epoch(train) [9][50/293] lr: 5.000000e-04 eta: 10:51:44 time: 0.771321 data_time: 0.105756 memory: 21676 loss_kpt: 0.000772 acc_pose: 0.726438 loss: 0.000772 2022/09/16 12:53:07 - mmengine - INFO - Epoch(train) [9][100/293] lr: 5.000000e-04 eta: 10:53:19 time: 0.767325 data_time: 0.104611 memory: 21676 loss_kpt: 0.000782 acc_pose: 0.708694 loss: 0.000782 2022/09/16 12:53:46 - mmengine - INFO - Epoch(train) [9][150/293] lr: 5.000000e-04 eta: 10:54:50 time: 0.767779 data_time: 0.096895 memory: 21676 loss_kpt: 0.000781 acc_pose: 0.687528 loss: 0.000781 2022/09/16 12:54:25 - mmengine - INFO - Epoch(train) [9][200/293] lr: 5.000000e-04 eta: 10:56:29 time: 0.780040 data_time: 0.101788 memory: 21676 loss_kpt: 0.000762 acc_pose: 0.769849 loss: 0.000762 2022/09/16 12:55:03 - mmengine - INFO - Epoch(train) [9][250/293] lr: 5.000000e-04 eta: 10:57:57 time: 0.774283 data_time: 0.096227 memory: 21676 loss_kpt: 0.000779 acc_pose: 0.729725 loss: 0.000779 2022/09/16 12:55:35 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 12:55:35 - mmengine - INFO - Saving checkpoint at 9 epochs 2022/09/16 12:56:20 - mmengine - INFO - Epoch(train) [10][50/293] lr: 5.000000e-04 eta: 10:48:31 time: 0.785777 data_time: 0.107278 memory: 21676 loss_kpt: 0.000775 acc_pose: 0.787263 loss: 0.000775 2022/09/16 12:56:58 - mmengine - INFO - Epoch(train) [10][100/293] lr: 5.000000e-04 eta: 10:49:46 time: 0.762156 data_time: 0.100765 memory: 21676 loss_kpt: 0.000762 acc_pose: 0.783360 loss: 0.000762 2022/09/16 12:57:35 - mmengine - INFO - Epoch(train) [10][150/293] lr: 5.000000e-04 eta: 10:50:38 time: 0.744321 data_time: 0.092888 memory: 21676 loss_kpt: 0.000752 acc_pose: 0.773382 loss: 0.000752 2022/09/16 12:58:13 - mmengine - INFO - Epoch(train) [10][200/293] lr: 5.000000e-04 eta: 10:51:37 time: 0.753865 data_time: 0.096854 memory: 21676 loss_kpt: 0.000745 acc_pose: 0.816451 loss: 0.000745 2022/09/16 12:58:50 - mmengine - INFO - Epoch(train) [10][250/293] lr: 5.000000e-04 eta: 10:52:35 time: 0.755439 data_time: 0.092519 memory: 21676 loss_kpt: 0.000772 acc_pose: 0.750217 loss: 0.000772 2022/09/16 12:59:22 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 12:59:22 - mmengine - INFO - Saving checkpoint at 10 epochs 2022/09/16 12:59:43 - mmengine - INFO - Epoch(val) [10][50/407] eta: 0:01:48 time: 0.304616 data_time: 0.097665 memory: 21676 2022/09/16 12:59:54 - mmengine - INFO - Epoch(val) [10][100/407] eta: 0:01:05 time: 0.212999 data_time: 0.009123 memory: 1375 2022/09/16 13:00:04 - mmengine - INFO - Epoch(val) [10][150/407] eta: 0:00:55 time: 0.215170 data_time: 0.008825 memory: 1375 2022/09/16 13:00:15 - mmengine - INFO - Epoch(val) [10][200/407] eta: 0:00:43 time: 0.209118 data_time: 0.008331 memory: 1375 2022/09/16 13:00:25 - mmengine - INFO - Epoch(val) [10][250/407] eta: 0:00:33 time: 0.211891 data_time: 0.008456 memory: 1375 2022/09/16 13:00:36 - mmengine - INFO - Epoch(val) [10][300/407] eta: 0:00:22 time: 0.211147 data_time: 0.008528 memory: 1375 2022/09/16 13:00:46 - mmengine - INFO - Epoch(val) [10][350/407] eta: 0:00:11 time: 0.209428 data_time: 0.008594 memory: 1375 2022/09/16 13:00:57 - mmengine - INFO - Epoch(val) [10][400/407] eta: 0:00:01 time: 0.212654 data_time: 0.013081 memory: 1375 2022/09/16 13:01:33 - mmengine - INFO - Evaluating CocoMetric... 2022/09/16 13:01:47 - mmengine - INFO - Epoch(val) [10][407/407] coco/AP: 0.672252 coco/AP .5: 0.870975 coco/AP .75: 0.740551 coco/AP (M): 0.628635 coco/AP (L): 0.746774 coco/AR: 0.730321 coco/AR .5: 0.912941 coco/AR .75: 0.792979 coco/AR (M): 0.681699 coco/AR (L): 0.799814 2022/09/16 13:01:50 - mmengine - INFO - The best checkpoint with 0.6723 coco/AP at 10 epoch is saved to best_coco/AP_epoch_10.pth. 2022/09/16 13:02:29 - mmengine - INFO - Epoch(train) [11][50/293] lr: 5.000000e-04 eta: 10:44:11 time: 0.792325 data_time: 0.110685 memory: 21676 loss_kpt: 0.000755 acc_pose: 0.778934 loss: 0.000755 2022/09/16 13:02:45 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 13:03:08 - mmengine - INFO - Epoch(train) [11][100/293] lr: 5.000000e-04 eta: 10:45:31 time: 0.776683 data_time: 0.093550 memory: 21676 loss_kpt: 0.000764 acc_pose: 0.791842 loss: 0.000764 2022/09/16 13:03:47 - mmengine - INFO - Epoch(train) [11][150/293] lr: 5.000000e-04 eta: 10:46:50 time: 0.780584 data_time: 0.094247 memory: 21676 loss_kpt: 0.000744 acc_pose: 0.788062 loss: 0.000744 2022/09/16 13:04:26 - mmengine - INFO - Epoch(train) [11][200/293] lr: 5.000000e-04 eta: 10:48:10 time: 0.785667 data_time: 0.094176 memory: 21676 loss_kpt: 0.000746 acc_pose: 0.715312 loss: 0.000746 2022/09/16 13:05:05 - mmengine - INFO - Epoch(train) [11][250/293] lr: 5.000000e-04 eta: 10:49:17 time: 0.775283 data_time: 0.095011 memory: 21676 loss_kpt: 0.000754 acc_pose: 0.780008 loss: 0.000754 2022/09/16 13:05:38 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 13:05:39 - mmengine - INFO - Saving checkpoint at 11 epochs 2022/09/16 13:06:22 - mmengine - INFO - Epoch(train) [12][50/293] lr: 5.000000e-04 eta: 10:41:25 time: 0.781448 data_time: 0.108110 memory: 21676 loss_kpt: 0.000774 acc_pose: 0.779068 loss: 0.000774 2022/09/16 13:07:01 - mmengine - INFO - Epoch(train) [12][100/293] lr: 5.000000e-04 eta: 10:42:29 time: 0.770566 data_time: 0.100312 memory: 21676 loss_kpt: 0.000760 acc_pose: 0.738551 loss: 0.000760 2022/09/16 13:07:39 - mmengine - INFO - Epoch(train) [12][150/293] lr: 5.000000e-04 eta: 10:43:32 time: 0.774430 data_time: 0.094732 memory: 21676 loss_kpt: 0.000719 acc_pose: 0.788367 loss: 0.000719 2022/09/16 13:08:18 - mmengine - INFO - Epoch(train) [12][200/293] lr: 5.000000e-04 eta: 10:44:28 time: 0.769109 data_time: 0.104759 memory: 21676 loss_kpt: 0.000733 acc_pose: 0.774515 loss: 0.000733 2022/09/16 13:08:56 - mmengine - INFO - Epoch(train) [12][250/293] lr: 5.000000e-04 eta: 10:45:21 time: 0.768657 data_time: 0.101336 memory: 21676 loss_kpt: 0.000726 acc_pose: 0.809289 loss: 0.000726 2022/09/16 13:09:29 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 13:09:29 - mmengine - INFO - Saving checkpoint at 12 epochs 2022/09/16 13:10:12 - mmengine - INFO - Epoch(train) [13][50/293] lr: 5.000000e-04 eta: 10:38:13 time: 0.789373 data_time: 0.112138 memory: 21676 loss_kpt: 0.000731 acc_pose: 0.782053 loss: 0.000731 2022/09/16 13:10:51 - mmengine - INFO - Epoch(train) [13][100/293] lr: 5.000000e-04 eta: 10:39:06 time: 0.768308 data_time: 0.094821 memory: 21676 loss_kpt: 0.000726 acc_pose: 0.820601 loss: 0.000726 2022/09/16 13:11:29 - mmengine - INFO - Epoch(train) [13][150/293] lr: 5.000000e-04 eta: 10:40:03 time: 0.776130 data_time: 0.100184 memory: 21676 loss_kpt: 0.000730 acc_pose: 0.711586 loss: 0.000730 2022/09/16 13:12:07 - mmengine - INFO - Epoch(train) [13][200/293] lr: 5.000000e-04 eta: 10:40:36 time: 0.749605 data_time: 0.098645 memory: 21676 loss_kpt: 0.000745 acc_pose: 0.769836 loss: 0.000745 2022/09/16 13:12:46 - mmengine - INFO - Epoch(train) [13][250/293] lr: 5.000000e-04 eta: 10:41:30 time: 0.777923 data_time: 0.098605 memory: 21676 loss_kpt: 0.000733 acc_pose: 0.720530 loss: 0.000733 2022/09/16 13:13:18 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 13:13:18 - mmengine - INFO - Saving checkpoint at 13 epochs 2022/09/16 13:14:02 - mmengine - INFO - Epoch(train) [14][50/293] lr: 5.000000e-04 eta: 10:34:43 time: 0.778066 data_time: 0.109700 memory: 21676 loss_kpt: 0.000720 acc_pose: 0.820355 loss: 0.000720 2022/09/16 13:14:41 - mmengine - INFO - Epoch(train) [14][100/293] lr: 5.000000e-04 eta: 10:35:31 time: 0.770559 data_time: 0.097825 memory: 21676 loss_kpt: 0.000716 acc_pose: 0.760923 loss: 0.000716 2022/09/16 13:15:19 - mmengine - INFO - Epoch(train) [14][150/293] lr: 5.000000e-04 eta: 10:36:09 time: 0.759589 data_time: 0.098082 memory: 21676 loss_kpt: 0.000739 acc_pose: 0.802623 loss: 0.000739 2022/09/16 13:15:49 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 13:15:56 - mmengine - INFO - Epoch(train) [14][200/293] lr: 5.000000e-04 eta: 10:36:39 time: 0.750501 data_time: 0.092586 memory: 21676 loss_kpt: 0.000709 acc_pose: 0.669748 loss: 0.000709 2022/09/16 13:16:34 - mmengine - INFO - Epoch(train) [14][250/293] lr: 5.000000e-04 eta: 10:37:15 time: 0.761629 data_time: 0.101294 memory: 21676 loss_kpt: 0.000730 acc_pose: 0.740244 loss: 0.000730 2022/09/16 13:17:06 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 13:17:06 - mmengine - INFO - Saving checkpoint at 14 epochs 2022/09/16 13:17:49 - mmengine - INFO - Epoch(train) [15][50/293] lr: 5.000000e-04 eta: 10:30:51 time: 0.771583 data_time: 0.107383 memory: 21676 loss_kpt: 0.000719 acc_pose: 0.788946 loss: 0.000719 2022/09/16 13:18:29 - mmengine - INFO - Epoch(train) [15][100/293] lr: 5.000000e-04 eta: 10:31:49 time: 0.792465 data_time: 0.105095 memory: 21676 loss_kpt: 0.000731 acc_pose: 0.758606 loss: 0.000731 2022/09/16 13:19:09 - mmengine - INFO - Epoch(train) [15][150/293] lr: 5.000000e-04 eta: 10:32:46 time: 0.795410 data_time: 0.103243 memory: 21676 loss_kpt: 0.000734 acc_pose: 0.750820 loss: 0.000734 2022/09/16 13:19:48 - mmengine - INFO - Epoch(train) [15][200/293] lr: 5.000000e-04 eta: 10:33:31 time: 0.780514 data_time: 0.105181 memory: 21676 loss_kpt: 0.000715 acc_pose: 0.778438 loss: 0.000715 2022/09/16 13:20:25 - mmengine - INFO - Epoch(train) [15][250/293] lr: 5.000000e-04 eta: 10:33:55 time: 0.751827 data_time: 0.103920 memory: 21676 loss_kpt: 0.000720 acc_pose: 0.736897 loss: 0.000720 2022/09/16 13:20:58 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 13:20:58 - mmengine - INFO - Saving checkpoint at 15 epochs 2022/09/16 13:21:41 - mmengine - INFO - Epoch(train) [16][50/293] lr: 5.000000e-04 eta: 10:27:59 time: 0.779188 data_time: 0.108306 memory: 21676 loss_kpt: 0.000726 acc_pose: 0.817000 loss: 0.000726 2022/09/16 13:22:19 - mmengine - INFO - Epoch(train) [16][100/293] lr: 5.000000e-04 eta: 10:28:32 time: 0.762866 data_time: 0.098383 memory: 21676 loss_kpt: 0.000718 acc_pose: 0.747281 loss: 0.000718 2022/09/16 13:22:57 - mmengine - INFO - Epoch(train) [16][150/293] lr: 5.000000e-04 eta: 10:28:59 time: 0.757298 data_time: 0.100450 memory: 21676 loss_kpt: 0.000707 acc_pose: 0.782643 loss: 0.000707 2022/09/16 13:23:35 - mmengine - INFO - Epoch(train) [16][200/293] lr: 5.000000e-04 eta: 10:29:24 time: 0.756563 data_time: 0.096224 memory: 21676 loss_kpt: 0.000705 acc_pose: 0.779510 loss: 0.000705 2022/09/16 13:24:13 - mmengine - INFO - Epoch(train) [16][250/293] lr: 5.000000e-04 eta: 10:29:46 time: 0.753559 data_time: 0.092159 memory: 21676 loss_kpt: 0.000712 acc_pose: 0.771189 loss: 0.000712 2022/09/16 13:24:45 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 13:24:45 - mmengine - INFO - Saving checkpoint at 16 epochs 2022/09/16 13:25:29 - mmengine - INFO - Epoch(train) [17][50/293] lr: 5.000000e-04 eta: 10:24:16 time: 0.787521 data_time: 0.109873 memory: 21676 loss_kpt: 0.000723 acc_pose: 0.717463 loss: 0.000723 2022/09/16 13:26:07 - mmengine - INFO - Epoch(train) [17][100/293] lr: 5.000000e-04 eta: 10:24:41 time: 0.758240 data_time: 0.098205 memory: 21676 loss_kpt: 0.000707 acc_pose: 0.737009 loss: 0.000707 2022/09/16 13:26:45 - mmengine - INFO - Epoch(train) [17][150/293] lr: 5.000000e-04 eta: 10:25:03 time: 0.753771 data_time: 0.098524 memory: 21676 loss_kpt: 0.000695 acc_pose: 0.806132 loss: 0.000695 2022/09/16 13:27:22 - mmengine - INFO - Epoch(train) [17][200/293] lr: 5.000000e-04 eta: 10:25:22 time: 0.751768 data_time: 0.091868 memory: 21676 loss_kpt: 0.000704 acc_pose: 0.814067 loss: 0.000704 2022/09/16 13:28:00 - mmengine - INFO - Epoch(train) [17][250/293] lr: 5.000000e-04 eta: 10:25:41 time: 0.753638 data_time: 0.096993 memory: 21676 loss_kpt: 0.000709 acc_pose: 0.788935 loss: 0.000709 2022/09/16 13:28:32 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 13:28:32 - mmengine - INFO - Saving checkpoint at 17 epochs 2022/09/16 13:28:53 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 13:29:17 - mmengine - INFO - Epoch(train) [18][50/293] lr: 5.000000e-04 eta: 10:20:37 time: 0.801416 data_time: 0.104815 memory: 21676 loss_kpt: 0.000705 acc_pose: 0.782129 loss: 0.000705 2022/09/16 13:29:56 - mmengine - INFO - Epoch(train) [18][100/293] lr: 5.000000e-04 eta: 10:21:14 time: 0.784908 data_time: 0.099020 memory: 21676 loss_kpt: 0.000706 acc_pose: 0.756018 loss: 0.000706 2022/09/16 13:30:35 - mmengine - INFO - Epoch(train) [18][150/293] lr: 5.000000e-04 eta: 10:21:49 time: 0.784014 data_time: 0.102235 memory: 21676 loss_kpt: 0.000701 acc_pose: 0.768402 loss: 0.000701 2022/09/16 13:31:14 - mmengine - INFO - Epoch(train) [18][200/293] lr: 5.000000e-04 eta: 10:22:22 time: 0.784114 data_time: 0.097344 memory: 21676 loss_kpt: 0.000720 acc_pose: 0.787298 loss: 0.000720 2022/09/16 13:31:53 - mmengine - INFO - Epoch(train) [18][250/293] lr: 5.000000e-04 eta: 10:22:51 time: 0.777044 data_time: 0.091857 memory: 21676 loss_kpt: 0.000702 acc_pose: 0.732467 loss: 0.000702 2022/09/16 13:32:26 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 13:32:26 - mmengine - INFO - Saving checkpoint at 18 epochs 2022/09/16 13:33:10 - mmengine - INFO - Epoch(train) [19][50/293] lr: 5.000000e-04 eta: 10:17:56 time: 0.793268 data_time: 0.108982 memory: 21676 loss_kpt: 0.000702 acc_pose: 0.795567 loss: 0.000702 2022/09/16 13:33:49 - mmengine - INFO - Epoch(train) [19][100/293] lr: 5.000000e-04 eta: 10:18:28 time: 0.784588 data_time: 0.102011 memory: 21676 loss_kpt: 0.000700 acc_pose: 0.802303 loss: 0.000700 2022/09/16 13:34:27 - mmengine - INFO - Epoch(train) [19][150/293] lr: 5.000000e-04 eta: 10:18:52 time: 0.771021 data_time: 0.097486 memory: 21676 loss_kpt: 0.000719 acc_pose: 0.735777 loss: 0.000719 2022/09/16 13:35:05 - mmengine - INFO - Epoch(train) [19][200/293] lr: 5.000000e-04 eta: 10:19:08 time: 0.756829 data_time: 0.096413 memory: 21676 loss_kpt: 0.000678 acc_pose: 0.791976 loss: 0.000678 2022/09/16 13:35:43 - mmengine - INFO - Epoch(train) [19][250/293] lr: 5.000000e-04 eta: 10:19:25 time: 0.762149 data_time: 0.092922 memory: 21676 loss_kpt: 0.000704 acc_pose: 0.821232 loss: 0.000704 2022/09/16 13:36:16 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 13:36:16 - mmengine - INFO - Saving checkpoint at 19 epochs 2022/09/16 13:36:59 - mmengine - INFO - Epoch(train) [20][50/293] lr: 5.000000e-04 eta: 10:14:41 time: 0.787333 data_time: 0.105803 memory: 21676 loss_kpt: 0.000689 acc_pose: 0.780575 loss: 0.000689 2022/09/16 13:37:38 - mmengine - INFO - Epoch(train) [20][100/293] lr: 5.000000e-04 eta: 10:14:58 time: 0.760931 data_time: 0.091319 memory: 21676 loss_kpt: 0.000677 acc_pose: 0.753708 loss: 0.000677 2022/09/16 13:38:16 - mmengine - INFO - Epoch(train) [20][150/293] lr: 5.000000e-04 eta: 10:15:18 time: 0.769159 data_time: 0.096282 memory: 21676 loss_kpt: 0.000671 acc_pose: 0.777812 loss: 0.000671 2022/09/16 13:38:54 - mmengine - INFO - Epoch(train) [20][200/293] lr: 5.000000e-04 eta: 10:15:35 time: 0.765918 data_time: 0.096950 memory: 21676 loss_kpt: 0.000702 acc_pose: 0.762799 loss: 0.000702 2022/09/16 13:39:33 - mmengine - INFO - Epoch(train) [20][250/293] lr: 5.000000e-04 eta: 10:15:53 time: 0.768064 data_time: 0.103518 memory: 21676 loss_kpt: 0.000699 acc_pose: 0.794996 loss: 0.000699 2022/09/16 13:40:05 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 13:40:05 - mmengine - INFO - Saving checkpoint at 20 epochs 2022/09/16 13:40:21 - mmengine - INFO - Epoch(val) [20][50/407] eta: 0:01:18 time: 0.218843 data_time: 0.013760 memory: 21676 2022/09/16 13:40:32 - mmengine - INFO - Epoch(val) [20][100/407] eta: 0:01:04 time: 0.211370 data_time: 0.008738 memory: 1375 2022/09/16 13:40:42 - mmengine - INFO - Epoch(val) [20][150/407] eta: 0:00:56 time: 0.219527 data_time: 0.008822 memory: 1375 2022/09/16 13:40:53 - mmengine - INFO - Epoch(val) [20][200/407] eta: 0:00:43 time: 0.210621 data_time: 0.008889 memory: 1375 2022/09/16 13:41:03 - mmengine - INFO - Epoch(val) [20][250/407] eta: 0:00:32 time: 0.209676 data_time: 0.008751 memory: 1375 2022/09/16 13:41:14 - mmengine - INFO - Epoch(val) [20][300/407] eta: 0:00:23 time: 0.216410 data_time: 0.010216 memory: 1375 2022/09/16 13:41:25 - mmengine - INFO - Epoch(val) [20][350/407] eta: 0:00:11 time: 0.208793 data_time: 0.008392 memory: 1375 2022/09/16 13:41:35 - mmengine - INFO - Epoch(val) [20][400/407] eta: 0:00:01 time: 0.210310 data_time: 0.009133 memory: 1375 2022/09/16 13:42:12 - mmengine - INFO - Evaluating CocoMetric... 2022/09/16 13:42:26 - mmengine - INFO - Epoch(val) [20][407/407] coco/AP: 0.708613 coco/AP .5: 0.885748 coco/AP .75: 0.775797 coco/AP (M): 0.668532 coco/AP (L): 0.780579 coco/AR: 0.761949 coco/AR .5: 0.923804 coco/AR .75: 0.823835 coco/AR (M): 0.714750 coco/AR (L): 0.829357 2022/09/16 13:42:26 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220916/dark_w32_384/best_coco/AP_epoch_10.pth is removed 2022/09/16 13:42:29 - mmengine - INFO - The best checkpoint with 0.7086 coco/AP at 20 epoch is saved to best_coco/AP_epoch_20.pth. 2022/09/16 13:43:08 - mmengine - INFO - Epoch(train) [21][50/293] lr: 5.000000e-04 eta: 10:11:18 time: 0.781347 data_time: 0.108839 memory: 21676 loss_kpt: 0.000695 acc_pose: 0.775175 loss: 0.000695 2022/09/16 13:43:47 - mmengine - INFO - Epoch(train) [21][100/293] lr: 5.000000e-04 eta: 10:11:45 time: 0.787912 data_time: 0.104271 memory: 21676 loss_kpt: 0.000690 acc_pose: 0.787550 loss: 0.000690 2022/09/16 13:44:18 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 13:44:27 - mmengine - INFO - Epoch(train) [21][150/293] lr: 5.000000e-04 eta: 10:12:12 time: 0.790225 data_time: 0.105752 memory: 21676 loss_kpt: 0.000686 acc_pose: 0.835108 loss: 0.000686 2022/09/16 13:45:05 - mmengine - INFO - Epoch(train) [21][200/293] lr: 5.000000e-04 eta: 10:12:30 time: 0.774196 data_time: 0.108200 memory: 21676 loss_kpt: 0.000688 acc_pose: 0.752939 loss: 0.000688 2022/09/16 13:45:45 - mmengine - INFO - Epoch(train) [21][250/293] lr: 5.000000e-04 eta: 10:12:55 time: 0.789327 data_time: 0.106877 memory: 21676 loss_kpt: 0.000700 acc_pose: 0.764493 loss: 0.000700 2022/09/16 13:46:18 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 13:46:18 - mmengine - INFO - Saving checkpoint at 21 epochs 2022/09/16 13:47:02 - mmengine - INFO - Epoch(train) [22][50/293] lr: 5.000000e-04 eta: 10:08:36 time: 0.792380 data_time: 0.112720 memory: 21676 loss_kpt: 0.000686 acc_pose: 0.782405 loss: 0.000686 2022/09/16 13:47:41 - mmengine - INFO - Epoch(train) [22][100/293] lr: 5.000000e-04 eta: 10:08:57 time: 0.781103 data_time: 0.094367 memory: 21676 loss_kpt: 0.000680 acc_pose: 0.782282 loss: 0.000680 2022/09/16 13:48:20 - mmengine - INFO - Epoch(train) [22][150/293] lr: 5.000000e-04 eta: 10:09:12 time: 0.770973 data_time: 0.098208 memory: 21676 loss_kpt: 0.000681 acc_pose: 0.813564 loss: 0.000681 2022/09/16 13:48:58 - mmengine - INFO - Epoch(train) [22][200/293] lr: 5.000000e-04 eta: 10:09:25 time: 0.768469 data_time: 0.092852 memory: 21676 loss_kpt: 0.000698 acc_pose: 0.769507 loss: 0.000698 2022/09/16 13:49:37 - mmengine - INFO - Epoch(train) [22][250/293] lr: 5.000000e-04 eta: 10:09:40 time: 0.774580 data_time: 0.093472 memory: 21676 loss_kpt: 0.000688 acc_pose: 0.709995 loss: 0.000688 2022/09/16 13:50:09 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 13:50:09 - mmengine - INFO - Saving checkpoint at 22 epochs 2022/09/16 13:50:54 - mmengine - INFO - Epoch(train) [23][50/293] lr: 5.000000e-04 eta: 10:05:32 time: 0.795758 data_time: 0.115130 memory: 21676 loss_kpt: 0.000682 acc_pose: 0.826608 loss: 0.000682 2022/09/16 13:51:32 - mmengine - INFO - Epoch(train) [23][100/293] lr: 5.000000e-04 eta: 10:05:48 time: 0.775073 data_time: 0.097631 memory: 21676 loss_kpt: 0.000684 acc_pose: 0.774531 loss: 0.000684 2022/09/16 13:52:12 - mmengine - INFO - Epoch(train) [23][150/293] lr: 5.000000e-04 eta: 10:06:06 time: 0.783224 data_time: 0.105527 memory: 21676 loss_kpt: 0.000675 acc_pose: 0.847246 loss: 0.000675 2022/09/16 13:52:50 - mmengine - INFO - Epoch(train) [23][200/293] lr: 5.000000e-04 eta: 10:06:17 time: 0.769355 data_time: 0.095894 memory: 21676 loss_kpt: 0.000694 acc_pose: 0.739641 loss: 0.000694 2022/09/16 13:53:29 - mmengine - INFO - Epoch(train) [23][250/293] lr: 5.000000e-04 eta: 10:06:29 time: 0.772621 data_time: 0.096167 memory: 21676 loss_kpt: 0.000681 acc_pose: 0.823187 loss: 0.000681 2022/09/16 13:54:02 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 13:54:02 - mmengine - INFO - Saving checkpoint at 23 epochs 2022/09/16 13:54:45 - mmengine - INFO - Epoch(train) [24][50/293] lr: 5.000000e-04 eta: 10:02:24 time: 0.781613 data_time: 0.104610 memory: 21676 loss_kpt: 0.000684 acc_pose: 0.759469 loss: 0.000684 2022/09/16 13:55:24 - mmengine - INFO - Epoch(train) [24][100/293] lr: 5.000000e-04 eta: 10:02:40 time: 0.781376 data_time: 0.091724 memory: 21676 loss_kpt: 0.000684 acc_pose: 0.733564 loss: 0.000684 2022/09/16 13:56:04 - mmengine - INFO - Epoch(train) [24][150/293] lr: 5.000000e-04 eta: 10:02:58 time: 0.791141 data_time: 0.100937 memory: 21676 loss_kpt: 0.000686 acc_pose: 0.831869 loss: 0.000686 2022/09/16 13:56:44 - mmengine - INFO - Epoch(train) [24][200/293] lr: 5.000000e-04 eta: 10:03:18 time: 0.797178 data_time: 0.093312 memory: 21676 loss_kpt: 0.000666 acc_pose: 0.788953 loss: 0.000666 2022/09/16 13:57:22 - mmengine - INFO - Epoch(train) [24][250/293] lr: 5.000000e-04 eta: 10:03:26 time: 0.766746 data_time: 0.092673 memory: 21676 loss_kpt: 0.000675 acc_pose: 0.738997 loss: 0.000675 2022/09/16 13:57:30 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 13:57:55 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 13:57:55 - mmengine - INFO - Saving checkpoint at 24 epochs 2022/09/16 13:58:39 - mmengine - INFO - Epoch(train) [25][50/293] lr: 5.000000e-04 eta: 9:59:31 time: 0.785212 data_time: 0.110859 memory: 21676 loss_kpt: 0.000667 acc_pose: 0.760171 loss: 0.000667 2022/09/16 13:59:21 - mmengine - INFO - Epoch(train) [25][100/293] lr: 5.000000e-04 eta: 10:00:06 time: 0.840129 data_time: 0.097119 memory: 21676 loss_kpt: 0.000670 acc_pose: 0.831474 loss: 0.000670 2022/09/16 14:00:00 - mmengine - INFO - Epoch(train) [25][150/293] lr: 5.000000e-04 eta: 10:00:19 time: 0.781674 data_time: 0.102764 memory: 21676 loss_kpt: 0.000684 acc_pose: 0.747322 loss: 0.000684 2022/09/16 14:00:39 - mmengine - INFO - Epoch(train) [25][200/293] lr: 5.000000e-04 eta: 10:00:32 time: 0.787915 data_time: 0.097438 memory: 21676 loss_kpt: 0.000652 acc_pose: 0.817674 loss: 0.000652 2022/09/16 14:01:18 - mmengine - INFO - Epoch(train) [25][250/293] lr: 5.000000e-04 eta: 10:00:40 time: 0.773148 data_time: 0.095395 memory: 21676 loss_kpt: 0.000680 acc_pose: 0.872024 loss: 0.000680 2022/09/16 14:01:50 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 14:01:50 - mmengine - INFO - Saving checkpoint at 25 epochs 2022/09/16 14:02:34 - mmengine - INFO - Epoch(train) [26][50/293] lr: 5.000000e-04 eta: 9:56:55 time: 0.789538 data_time: 0.104467 memory: 21676 loss_kpt: 0.000670 acc_pose: 0.825201 loss: 0.000670 2022/09/16 14:03:12 - mmengine - INFO - Epoch(train) [26][100/293] lr: 5.000000e-04 eta: 9:56:58 time: 0.761259 data_time: 0.097615 memory: 21676 loss_kpt: 0.000684 acc_pose: 0.811351 loss: 0.000684 2022/09/16 14:03:50 - mmengine - INFO - Epoch(train) [26][150/293] lr: 5.000000e-04 eta: 9:56:58 time: 0.754238 data_time: 0.093055 memory: 21676 loss_kpt: 0.000660 acc_pose: 0.839962 loss: 0.000660 2022/09/16 14:04:28 - mmengine - INFO - Epoch(train) [26][200/293] lr: 5.000000e-04 eta: 9:57:02 time: 0.765165 data_time: 0.096779 memory: 21676 loss_kpt: 0.000665 acc_pose: 0.794497 loss: 0.000665 2022/09/16 14:05:06 - mmengine - INFO - Epoch(train) [26][250/293] lr: 5.000000e-04 eta: 9:57:07 time: 0.770872 data_time: 0.092326 memory: 21676 loss_kpt: 0.000665 acc_pose: 0.768341 loss: 0.000665 2022/09/16 14:05:39 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 14:05:39 - mmengine - INFO - Saving checkpoint at 26 epochs 2022/09/16 14:06:23 - mmengine - INFO - Epoch(train) [27][50/293] lr: 5.000000e-04 eta: 9:53:29 time: 0.790810 data_time: 0.102096 memory: 21676 loss_kpt: 0.000682 acc_pose: 0.820580 loss: 0.000682 2022/09/16 14:07:02 - mmengine - INFO - Epoch(train) [27][100/293] lr: 5.000000e-04 eta: 9:53:39 time: 0.784257 data_time: 0.094266 memory: 21676 loss_kpt: 0.000676 acc_pose: 0.796264 loss: 0.000676 2022/09/16 14:07:41 - mmengine - INFO - Epoch(train) [27][150/293] lr: 5.000000e-04 eta: 9:53:44 time: 0.772444 data_time: 0.094967 memory: 21676 loss_kpt: 0.000666 acc_pose: 0.762588 loss: 0.000666 2022/09/16 14:08:20 - mmengine - INFO - Epoch(train) [27][200/293] lr: 5.000000e-04 eta: 9:53:49 time: 0.774079 data_time: 0.099693 memory: 21676 loss_kpt: 0.000668 acc_pose: 0.773893 loss: 0.000668 2022/09/16 14:08:58 - mmengine - INFO - Epoch(train) [27][250/293] lr: 5.000000e-04 eta: 9:53:51 time: 0.765414 data_time: 0.093143 memory: 21676 loss_kpt: 0.000672 acc_pose: 0.834719 loss: 0.000672 2022/09/16 14:09:30 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 14:09:30 - mmengine - INFO - Saving checkpoint at 27 epochs 2022/09/16 14:10:14 - mmengine - INFO - Epoch(train) [28][50/293] lr: 5.000000e-04 eta: 9:50:16 time: 0.780148 data_time: 0.107095 memory: 21676 loss_kpt: 0.000654 acc_pose: 0.856765 loss: 0.000654 2022/09/16 14:10:44 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 14:10:52 - mmengine - INFO - Epoch(train) [28][100/293] lr: 5.000000e-04 eta: 9:50:20 time: 0.770904 data_time: 0.095065 memory: 21676 loss_kpt: 0.000668 acc_pose: 0.802285 loss: 0.000668 2022/09/16 14:11:30 - mmengine - INFO - Epoch(train) [28][150/293] lr: 5.000000e-04 eta: 9:50:18 time: 0.757355 data_time: 0.099750 memory: 21676 loss_kpt: 0.000669 acc_pose: 0.756867 loss: 0.000669 2022/09/16 14:12:08 - mmengine - INFO - Epoch(train) [28][200/293] lr: 5.000000e-04 eta: 9:50:14 time: 0.751010 data_time: 0.095487 memory: 21676 loss_kpt: 0.000671 acc_pose: 0.786642 loss: 0.000671 2022/09/16 14:12:46 - mmengine - INFO - Epoch(train) [28][250/293] lr: 5.000000e-04 eta: 9:50:13 time: 0.761299 data_time: 0.100079 memory: 21676 loss_kpt: 0.000683 acc_pose: 0.756295 loss: 0.000683 2022/09/16 14:13:18 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 14:13:18 - mmengine - INFO - Saving checkpoint at 28 epochs 2022/09/16 14:14:02 - mmengine - INFO - Epoch(train) [29][50/293] lr: 5.000000e-04 eta: 9:46:47 time: 0.784856 data_time: 0.109529 memory: 21676 loss_kpt: 0.000663 acc_pose: 0.785066 loss: 0.000663 2022/09/16 14:14:40 - mmengine - INFO - Epoch(train) [29][100/293] lr: 5.000000e-04 eta: 9:46:46 time: 0.760583 data_time: 0.094090 memory: 21676 loss_kpt: 0.000649 acc_pose: 0.785458 loss: 0.000649 2022/09/16 14:15:18 - mmengine - INFO - Epoch(train) [29][150/293] lr: 5.000000e-04 eta: 9:46:45 time: 0.762325 data_time: 0.096301 memory: 21676 loss_kpt: 0.000678 acc_pose: 0.749989 loss: 0.000678 2022/09/16 14:15:56 - mmengine - INFO - Epoch(train) [29][200/293] lr: 5.000000e-04 eta: 9:46:43 time: 0.760876 data_time: 0.103365 memory: 21676 loss_kpt: 0.000672 acc_pose: 0.833458 loss: 0.000672 2022/09/16 14:16:34 - mmengine - INFO - Epoch(train) [29][250/293] lr: 5.000000e-04 eta: 9:46:39 time: 0.755911 data_time: 0.097369 memory: 21676 loss_kpt: 0.000653 acc_pose: 0.828896 loss: 0.000653 2022/09/16 14:17:07 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 14:17:07 - mmengine - INFO - Saving checkpoint at 29 epochs 2022/09/16 14:17:51 - mmengine - INFO - Epoch(train) [30][50/293] lr: 5.000000e-04 eta: 9:43:19 time: 0.787036 data_time: 0.112710 memory: 21676 loss_kpt: 0.000665 acc_pose: 0.826600 loss: 0.000665 2022/09/16 14:18:30 - mmengine - INFO - Epoch(train) [30][100/293] lr: 5.000000e-04 eta: 9:43:26 time: 0.791412 data_time: 0.092941 memory: 21676 loss_kpt: 0.000665 acc_pose: 0.809790 loss: 0.000665 2022/09/16 14:19:09 - mmengine - INFO - Epoch(train) [30][150/293] lr: 5.000000e-04 eta: 9:43:27 time: 0.772792 data_time: 0.099633 memory: 21676 loss_kpt: 0.000654 acc_pose: 0.813116 loss: 0.000654 2022/09/16 14:19:47 - mmengine - INFO - Epoch(train) [30][200/293] lr: 5.000000e-04 eta: 9:43:26 time: 0.766475 data_time: 0.100801 memory: 21676 loss_kpt: 0.000642 acc_pose: 0.860809 loss: 0.000642 2022/09/16 14:20:26 - mmengine - INFO - Epoch(train) [30][250/293] lr: 5.000000e-04 eta: 9:43:27 time: 0.777953 data_time: 0.093970 memory: 21676 loss_kpt: 0.000660 acc_pose: 0.764219 loss: 0.000660 2022/09/16 14:20:58 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 14:20:58 - mmengine - INFO - Saving checkpoint at 30 epochs 2022/09/16 14:21:14 - mmengine - INFO - Epoch(val) [30][50/407] eta: 0:01:17 time: 0.217594 data_time: 0.013500 memory: 21676 2022/09/16 14:21:24 - mmengine - INFO - Epoch(val) [30][100/407] eta: 0:01:04 time: 0.209052 data_time: 0.008672 memory: 1375 2022/09/16 14:21:35 - mmengine - INFO - Epoch(val) [30][150/407] eta: 0:00:54 time: 0.211407 data_time: 0.009045 memory: 1375 2022/09/16 14:21:45 - mmengine - INFO - Epoch(val) [30][200/407] eta: 0:00:43 time: 0.211014 data_time: 0.008669 memory: 1375 2022/09/16 14:21:56 - mmengine - INFO - Epoch(val) [30][250/407] eta: 0:00:33 time: 0.214754 data_time: 0.012435 memory: 1375 2022/09/16 14:22:06 - mmengine - INFO - Epoch(val) [30][300/407] eta: 0:00:22 time: 0.208626 data_time: 0.008462 memory: 1375 2022/09/16 14:22:17 - mmengine - INFO - Epoch(val) [30][350/407] eta: 0:00:12 time: 0.210623 data_time: 0.008765 memory: 1375 2022/09/16 14:22:27 - mmengine - INFO - Epoch(val) [30][400/407] eta: 0:00:01 time: 0.207140 data_time: 0.007935 memory: 1375 2022/09/16 14:23:02 - mmengine - INFO - Evaluating CocoMetric... 2022/09/16 14:23:16 - mmengine - INFO - Epoch(val) [30][407/407] coco/AP: 0.724164 coco/AP .5: 0.888827 coco/AP .75: 0.789137 coco/AP (M): 0.686579 coco/AP (L): 0.793271 coco/AR: 0.776622 coco/AR .5: 0.928684 coco/AR .75: 0.836115 coco/AR (M): 0.733106 coco/AR (L): 0.839391 2022/09/16 14:23:16 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220916/dark_w32_384/best_coco/AP_epoch_20.pth is removed 2022/09/16 14:23:19 - mmengine - INFO - The best checkpoint with 0.7242 coco/AP at 30 epoch is saved to best_coco/AP_epoch_30.pth. 2022/09/16 14:23:58 - mmengine - INFO - Epoch(train) [31][50/293] lr: 5.000000e-04 eta: 9:40:14 time: 0.792122 data_time: 0.108148 memory: 21676 loss_kpt: 0.000663 acc_pose: 0.860061 loss: 0.000663 2022/09/16 14:24:37 - mmengine - INFO - Epoch(train) [31][100/293] lr: 5.000000e-04 eta: 9:40:15 time: 0.776524 data_time: 0.097945 memory: 21676 loss_kpt: 0.000665 acc_pose: 0.769112 loss: 0.000665 2022/09/16 14:25:15 - mmengine - INFO - Epoch(train) [31][150/293] lr: 5.000000e-04 eta: 9:40:09 time: 0.753706 data_time: 0.100120 memory: 21676 loss_kpt: 0.000649 acc_pose: 0.817839 loss: 0.000649 2022/09/16 14:25:54 - mmengine - INFO - Epoch(train) [31][200/293] lr: 5.000000e-04 eta: 9:40:12 time: 0.782292 data_time: 0.095511 memory: 21676 loss_kpt: 0.000640 acc_pose: 0.790245 loss: 0.000640 2022/09/16 14:26:02 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 14:26:32 - mmengine - INFO - Epoch(train) [31][250/293] lr: 5.000000e-04 eta: 9:40:06 time: 0.758353 data_time: 0.092160 memory: 21676 loss_kpt: 0.000651 acc_pose: 0.740808 loss: 0.000651 2022/09/16 14:27:04 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 14:27:04 - mmengine - INFO - Saving checkpoint at 31 epochs 2022/09/16 14:27:49 - mmengine - INFO - Epoch(train) [32][50/293] lr: 5.000000e-04 eta: 9:36:58 time: 0.793418 data_time: 0.113629 memory: 21676 loss_kpt: 0.000664 acc_pose: 0.826486 loss: 0.000664 2022/09/16 14:28:28 - mmengine - INFO - Epoch(train) [32][100/293] lr: 5.000000e-04 eta: 9:36:59 time: 0.780013 data_time: 0.099348 memory: 21676 loss_kpt: 0.000651 acc_pose: 0.827501 loss: 0.000651 2022/09/16 14:29:07 - mmengine - INFO - Epoch(train) [32][150/293] lr: 5.000000e-04 eta: 9:36:59 time: 0.777457 data_time: 0.097944 memory: 21676 loss_kpt: 0.000651 acc_pose: 0.824203 loss: 0.000651 2022/09/16 14:29:44 - mmengine - INFO - Epoch(train) [32][200/293] lr: 5.000000e-04 eta: 9:36:52 time: 0.754193 data_time: 0.094205 memory: 21676 loss_kpt: 0.000647 acc_pose: 0.795649 loss: 0.000647 2022/09/16 14:30:22 - mmengine - INFO - Epoch(train) [32][250/293] lr: 5.000000e-04 eta: 9:36:46 time: 0.760160 data_time: 0.096474 memory: 21676 loss_kpt: 0.000643 acc_pose: 0.796555 loss: 0.000643 2022/09/16 14:30:55 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 14:30:55 - mmengine - INFO - Saving checkpoint at 32 epochs 2022/09/16 14:31:39 - mmengine - INFO - Epoch(train) [33][50/293] lr: 5.000000e-04 eta: 9:33:42 time: 0.789877 data_time: 0.108518 memory: 21676 loss_kpt: 0.000667 acc_pose: 0.795926 loss: 0.000667 2022/09/16 14:32:19 - mmengine - INFO - Epoch(train) [33][100/293] lr: 5.000000e-04 eta: 9:33:46 time: 0.796563 data_time: 0.097301 memory: 21676 loss_kpt: 0.000650 acc_pose: 0.837287 loss: 0.000650 2022/09/16 14:32:58 - mmengine - INFO - Epoch(train) [33][150/293] lr: 5.000000e-04 eta: 9:33:44 time: 0.773021 data_time: 0.095991 memory: 21676 loss_kpt: 0.000646 acc_pose: 0.806787 loss: 0.000646 2022/09/16 14:33:36 - mmengine - INFO - Epoch(train) [33][200/293] lr: 5.000000e-04 eta: 9:33:39 time: 0.766753 data_time: 0.097406 memory: 21676 loss_kpt: 0.000658 acc_pose: 0.786858 loss: 0.000658 2022/09/16 14:34:14 - mmengine - INFO - Epoch(train) [33][250/293] lr: 5.000000e-04 eta: 9:33:34 time: 0.765554 data_time: 0.092535 memory: 21676 loss_kpt: 0.000645 acc_pose: 0.817981 loss: 0.000645 2022/09/16 14:34:47 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 14:34:47 - mmengine - INFO - Saving checkpoint at 33 epochs 2022/09/16 14:35:31 - mmengine - INFO - Epoch(train) [34][50/293] lr: 5.000000e-04 eta: 9:30:35 time: 0.795969 data_time: 0.106487 memory: 21676 loss_kpt: 0.000634 acc_pose: 0.786821 loss: 0.000634 2022/09/16 14:36:10 - mmengine - INFO - Epoch(train) [34][100/293] lr: 5.000000e-04 eta: 9:30:35 time: 0.783185 data_time: 0.097113 memory: 21676 loss_kpt: 0.000635 acc_pose: 0.807144 loss: 0.000635 2022/09/16 14:36:49 - mmengine - INFO - Epoch(train) [34][150/293] lr: 5.000000e-04 eta: 9:30:32 time: 0.777896 data_time: 0.097248 memory: 21676 loss_kpt: 0.000646 acc_pose: 0.805973 loss: 0.000646 2022/09/16 14:37:28 - mmengine - INFO - Epoch(train) [34][200/293] lr: 5.000000e-04 eta: 9:30:28 time: 0.770000 data_time: 0.093564 memory: 21676 loss_kpt: 0.000649 acc_pose: 0.784765 loss: 0.000649 2022/09/16 14:38:05 - mmengine - INFO - Epoch(train) [34][250/293] lr: 5.000000e-04 eta: 9:30:18 time: 0.751544 data_time: 0.091526 memory: 21676 loss_kpt: 0.000647 acc_pose: 0.812366 loss: 0.000647 2022/09/16 14:38:37 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 14:38:37 - mmengine - INFO - Saving checkpoint at 34 epochs 2022/09/16 14:39:11 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 14:39:20 - mmengine - INFO - Epoch(train) [35][50/293] lr: 5.000000e-04 eta: 9:27:18 time: 0.774622 data_time: 0.107978 memory: 21676 loss_kpt: 0.000652 acc_pose: 0.827027 loss: 0.000652 2022/09/16 14:39:59 - mmengine - INFO - Epoch(train) [35][100/293] lr: 5.000000e-04 eta: 9:27:14 time: 0.774388 data_time: 0.091948 memory: 21676 loss_kpt: 0.000636 acc_pose: 0.830232 loss: 0.000636 2022/09/16 14:40:37 - mmengine - INFO - Epoch(train) [35][150/293] lr: 5.000000e-04 eta: 9:27:05 time: 0.756064 data_time: 0.097401 memory: 21676 loss_kpt: 0.000644 acc_pose: 0.793502 loss: 0.000644 2022/09/16 14:41:15 - mmengine - INFO - Epoch(train) [35][200/293] lr: 5.000000e-04 eta: 9:26:58 time: 0.765507 data_time: 0.099173 memory: 21676 loss_kpt: 0.000644 acc_pose: 0.827554 loss: 0.000644 2022/09/16 14:41:53 - mmengine - INFO - Epoch(train) [35][250/293] lr: 5.000000e-04 eta: 9:26:48 time: 0.753370 data_time: 0.096082 memory: 21676 loss_kpt: 0.000640 acc_pose: 0.881919 loss: 0.000640 2022/09/16 14:42:25 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 14:42:25 - mmengine - INFO - Saving checkpoint at 35 epochs 2022/09/16 14:43:09 - mmengine - INFO - Epoch(train) [36][50/293] lr: 5.000000e-04 eta: 9:23:57 time: 0.792818 data_time: 0.104211 memory: 21676 loss_kpt: 0.000642 acc_pose: 0.809086 loss: 0.000642 2022/09/16 14:43:48 - mmengine - INFO - Epoch(train) [36][100/293] lr: 5.000000e-04 eta: 9:23:53 time: 0.775923 data_time: 0.096235 memory: 21676 loss_kpt: 0.000643 acc_pose: 0.783201 loss: 0.000643 2022/09/16 14:44:27 - mmengine - INFO - Epoch(train) [36][150/293] lr: 5.000000e-04 eta: 9:23:48 time: 0.777102 data_time: 0.094032 memory: 21676 loss_kpt: 0.000633 acc_pose: 0.846840 loss: 0.000633 2022/09/16 14:45:05 - mmengine - INFO - Epoch(train) [36][200/293] lr: 5.000000e-04 eta: 9:23:37 time: 0.752391 data_time: 0.091889 memory: 21676 loss_kpt: 0.000646 acc_pose: 0.822355 loss: 0.000646 2022/09/16 14:45:43 - mmengine - INFO - Epoch(train) [36][250/293] lr: 5.000000e-04 eta: 9:23:30 time: 0.768371 data_time: 0.099358 memory: 21676 loss_kpt: 0.000644 acc_pose: 0.838547 loss: 0.000644 2022/09/16 14:46:16 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 14:46:16 - mmengine - INFO - Saving checkpoint at 36 epochs 2022/09/16 14:47:00 - mmengine - INFO - Epoch(train) [37][50/293] lr: 5.000000e-04 eta: 9:20:42 time: 0.791315 data_time: 0.109116 memory: 21676 loss_kpt: 0.000634 acc_pose: 0.797135 loss: 0.000634 2022/09/16 14:47:39 - mmengine - INFO - Epoch(train) [37][100/293] lr: 5.000000e-04 eta: 9:20:38 time: 0.780005 data_time: 0.100885 memory: 21676 loss_kpt: 0.000647 acc_pose: 0.808592 loss: 0.000647 2022/09/16 14:48:18 - mmengine - INFO - Epoch(train) [37][150/293] lr: 5.000000e-04 eta: 9:20:32 time: 0.776173 data_time: 0.099487 memory: 21676 loss_kpt: 0.000643 acc_pose: 0.874222 loss: 0.000643 2022/09/16 14:48:58 - mmengine - INFO - Epoch(train) [37][200/293] lr: 5.000000e-04 eta: 9:20:29 time: 0.790813 data_time: 0.094774 memory: 21676 loss_kpt: 0.000639 acc_pose: 0.762448 loss: 0.000639 2022/09/16 14:49:35 - mmengine - INFO - Epoch(train) [37][250/293] lr: 5.000000e-04 eta: 9:20:18 time: 0.756464 data_time: 0.098398 memory: 21676 loss_kpt: 0.000648 acc_pose: 0.862039 loss: 0.000648 2022/09/16 14:50:08 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 14:50:08 - mmengine - INFO - Saving checkpoint at 37 epochs 2022/09/16 14:50:52 - mmengine - INFO - Epoch(train) [38][50/293] lr: 5.000000e-04 eta: 9:17:32 time: 0.782990 data_time: 0.108353 memory: 21676 loss_kpt: 0.000635 acc_pose: 0.787714 loss: 0.000635 2022/09/16 14:51:32 - mmengine - INFO - Epoch(train) [38][100/293] lr: 5.000000e-04 eta: 9:17:32 time: 0.801150 data_time: 0.099179 memory: 21676 loss_kpt: 0.000642 acc_pose: 0.821654 loss: 0.000642 2022/09/16 14:52:12 - mmengine - INFO - Epoch(train) [38][150/293] lr: 5.000000e-04 eta: 9:17:29 time: 0.793478 data_time: 0.094277 memory: 21676 loss_kpt: 0.000641 acc_pose: 0.799280 loss: 0.000641 2022/09/16 14:52:19 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 14:52:51 - mmengine - INFO - Epoch(train) [38][200/293] lr: 5.000000e-04 eta: 9:17:24 time: 0.786104 data_time: 0.100277 memory: 21676 loss_kpt: 0.000653 acc_pose: 0.818068 loss: 0.000653 2022/09/16 14:53:29 - mmengine - INFO - Epoch(train) [38][250/293] lr: 5.000000e-04 eta: 9:17:12 time: 0.753890 data_time: 0.098783 memory: 21676 loss_kpt: 0.000627 acc_pose: 0.801462 loss: 0.000627 2022/09/16 14:54:01 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 14:54:01 - mmengine - INFO - Saving checkpoint at 38 epochs 2022/09/16 14:54:45 - mmengine - INFO - Epoch(train) [39][50/293] lr: 5.000000e-04 eta: 9:14:33 time: 0.798476 data_time: 0.108535 memory: 21676 loss_kpt: 0.000647 acc_pose: 0.812491 loss: 0.000647 2022/09/16 14:55:25 - mmengine - INFO - Epoch(train) [39][100/293] lr: 5.000000e-04 eta: 9:14:27 time: 0.783455 data_time: 0.101173 memory: 21676 loss_kpt: 0.000639 acc_pose: 0.837063 loss: 0.000639 2022/09/16 14:56:03 - mmengine - INFO - Epoch(train) [39][150/293] lr: 5.000000e-04 eta: 9:14:19 time: 0.775964 data_time: 0.097301 memory: 21676 loss_kpt: 0.000653 acc_pose: 0.823994 loss: 0.000653 2022/09/16 14:56:42 - mmengine - INFO - Epoch(train) [39][200/293] lr: 5.000000e-04 eta: 9:14:13 time: 0.783330 data_time: 0.095636 memory: 21676 loss_kpt: 0.000623 acc_pose: 0.786111 loss: 0.000623 2022/09/16 14:57:21 - mmengine - INFO - Epoch(train) [39][250/293] lr: 5.000000e-04 eta: 9:14:03 time: 0.765682 data_time: 0.097389 memory: 21676 loss_kpt: 0.000656 acc_pose: 0.818377 loss: 0.000656 2022/09/16 14:57:53 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 14:57:53 - mmengine - INFO - Saving checkpoint at 39 epochs 2022/09/16 14:58:37 - mmengine - INFO - Epoch(train) [40][50/293] lr: 5.000000e-04 eta: 9:11:24 time: 0.789234 data_time: 0.104107 memory: 21676 loss_kpt: 0.000642 acc_pose: 0.852190 loss: 0.000642 2022/09/16 14:59:16 - mmengine - INFO - Epoch(train) [40][100/293] lr: 5.000000e-04 eta: 9:11:17 time: 0.779052 data_time: 0.096661 memory: 21676 loss_kpt: 0.000623 acc_pose: 0.821620 loss: 0.000623 2022/09/16 14:59:55 - mmengine - INFO - Epoch(train) [40][150/293] lr: 5.000000e-04 eta: 9:11:10 time: 0.781637 data_time: 0.092982 memory: 21676 loss_kpt: 0.000636 acc_pose: 0.790109 loss: 0.000636 2022/09/16 15:00:34 - mmengine - INFO - Epoch(train) [40][200/293] lr: 5.000000e-04 eta: 9:10:59 time: 0.766430 data_time: 0.100401 memory: 21676 loss_kpt: 0.000637 acc_pose: 0.821766 loss: 0.000637 2022/09/16 15:01:12 - mmengine - INFO - Epoch(train) [40][250/293] lr: 5.000000e-04 eta: 9:10:46 time: 0.758133 data_time: 0.101781 memory: 21676 loss_kpt: 0.000635 acc_pose: 0.796135 loss: 0.000635 2022/09/16 15:01:43 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 15:01:43 - mmengine - INFO - Saving checkpoint at 40 epochs 2022/09/16 15:01:59 - mmengine - INFO - Epoch(val) [40][50/407] eta: 0:01:18 time: 0.219556 data_time: 0.013979 memory: 21676 2022/09/16 15:02:10 - mmengine - INFO - Epoch(val) [40][100/407] eta: 0:01:06 time: 0.216103 data_time: 0.008907 memory: 1375 2022/09/16 15:02:20 - mmengine - INFO - Epoch(val) [40][150/407] eta: 0:00:54 time: 0.212789 data_time: 0.009156 memory: 1375 2022/09/16 15:02:31 - mmengine - INFO - Epoch(val) [40][200/407] eta: 0:00:43 time: 0.211925 data_time: 0.008727 memory: 1375 2022/09/16 15:02:42 - mmengine - INFO - Epoch(val) [40][250/407] eta: 0:00:33 time: 0.212499 data_time: 0.008509 memory: 1375 2022/09/16 15:02:52 - mmengine - INFO - Epoch(val) [40][300/407] eta: 0:00:22 time: 0.209387 data_time: 0.008749 memory: 1375 2022/09/16 15:03:03 - mmengine - INFO - Epoch(val) [40][350/407] eta: 0:00:12 time: 0.213343 data_time: 0.009036 memory: 1375 2022/09/16 15:03:13 - mmengine - INFO - Epoch(val) [40][400/407] eta: 0:00:01 time: 0.205282 data_time: 0.007944 memory: 1375 2022/09/16 15:03:49 - mmengine - INFO - Evaluating CocoMetric... 2022/09/16 15:04:02 - mmengine - INFO - Epoch(val) [40][407/407] coco/AP: 0.731367 coco/AP .5: 0.890229 coco/AP .75: 0.798471 coco/AP (M): 0.692270 coco/AP (L): 0.802070 coco/AR: 0.782746 coco/AR .5: 0.928999 coco/AR .75: 0.843829 coco/AR (M): 0.738787 coco/AR (L): 0.846377 2022/09/16 15:04:02 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220916/dark_w32_384/best_coco/AP_epoch_30.pth is removed 2022/09/16 15:04:05 - mmengine - INFO - The best checkpoint with 0.7314 coco/AP at 40 epoch is saved to best_coco/AP_epoch_40.pth. 2022/09/16 15:04:45 - mmengine - INFO - Epoch(train) [41][50/293] lr: 5.000000e-04 eta: 9:08:11 time: 0.791577 data_time: 0.106117 memory: 21676 loss_kpt: 0.000634 acc_pose: 0.805593 loss: 0.000634 2022/09/16 15:05:23 - mmengine - INFO - Epoch(train) [41][100/293] lr: 5.000000e-04 eta: 9:08:02 time: 0.775297 data_time: 0.097967 memory: 21676 loss_kpt: 0.000634 acc_pose: 0.854484 loss: 0.000634 2022/09/16 15:06:02 - mmengine - INFO - Epoch(train) [41][150/293] lr: 5.000000e-04 eta: 9:07:51 time: 0.766955 data_time: 0.099595 memory: 21676 loss_kpt: 0.000636 acc_pose: 0.806188 loss: 0.000636 2022/09/16 15:06:41 - mmengine - INFO - Epoch(train) [41][200/293] lr: 5.000000e-04 eta: 9:07:44 time: 0.786587 data_time: 0.092426 memory: 21676 loss_kpt: 0.000617 acc_pose: 0.860704 loss: 0.000617 2022/09/16 15:07:20 - mmengine - INFO - Epoch(train) [41][250/293] lr: 5.000000e-04 eta: 9:07:33 time: 0.768682 data_time: 0.101516 memory: 21676 loss_kpt: 0.000622 acc_pose: 0.794546 loss: 0.000622 2022/09/16 15:07:43 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 15:07:52 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 15:07:52 - mmengine - INFO - Saving checkpoint at 41 epochs 2022/09/16 15:08:36 - mmengine - INFO - Epoch(train) [42][50/293] lr: 5.000000e-04 eta: 9:04:58 time: 0.778793 data_time: 0.103270 memory: 21676 loss_kpt: 0.000634 acc_pose: 0.837291 loss: 0.000634 2022/09/16 15:09:13 - mmengine - INFO - Epoch(train) [42][100/293] lr: 5.000000e-04 eta: 9:04:41 time: 0.738822 data_time: 0.098263 memory: 21676 loss_kpt: 0.000627 acc_pose: 0.863775 loss: 0.000627 2022/09/16 15:09:51 - mmengine - INFO - Epoch(train) [42][150/293] lr: 5.000000e-04 eta: 9:04:28 time: 0.761089 data_time: 0.100881 memory: 21676 loss_kpt: 0.000625 acc_pose: 0.798228 loss: 0.000625 2022/09/16 15:10:29 - mmengine - INFO - Epoch(train) [42][200/293] lr: 5.000000e-04 eta: 9:04:17 time: 0.770983 data_time: 0.095293 memory: 21676 loss_kpt: 0.000648 acc_pose: 0.814783 loss: 0.000648 2022/09/16 15:11:08 - mmengine - INFO - Epoch(train) [42][250/293] lr: 5.000000e-04 eta: 9:04:05 time: 0.767976 data_time: 0.102157 memory: 21676 loss_kpt: 0.000639 acc_pose: 0.812400 loss: 0.000639 2022/09/16 15:11:40 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 15:11:40 - mmengine - INFO - Saving checkpoint at 42 epochs 2022/09/16 15:12:24 - mmengine - INFO - Epoch(train) [43][50/293] lr: 5.000000e-04 eta: 9:01:33 time: 0.776212 data_time: 0.107213 memory: 21676 loss_kpt: 0.000633 acc_pose: 0.809150 loss: 0.000633 2022/09/16 15:13:03 - mmengine - INFO - Epoch(train) [43][100/293] lr: 5.000000e-04 eta: 9:01:25 time: 0.788746 data_time: 0.100014 memory: 21676 loss_kpt: 0.000637 acc_pose: 0.811195 loss: 0.000637 2022/09/16 15:13:43 - mmengine - INFO - Epoch(train) [43][150/293] lr: 5.000000e-04 eta: 9:01:17 time: 0.785471 data_time: 0.094071 memory: 21676 loss_kpt: 0.000637 acc_pose: 0.826587 loss: 0.000637 2022/09/16 15:14:21 - mmengine - INFO - Epoch(train) [43][200/293] lr: 5.000000e-04 eta: 9:01:06 time: 0.775570 data_time: 0.096466 memory: 21676 loss_kpt: 0.000618 acc_pose: 0.788101 loss: 0.000618 2022/09/16 15:15:00 - mmengine - INFO - Epoch(train) [43][250/293] lr: 5.000000e-04 eta: 9:00:54 time: 0.772033 data_time: 0.101488 memory: 21676 loss_kpt: 0.000626 acc_pose: 0.817163 loss: 0.000626 2022/09/16 15:15:33 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 15:15:33 - mmengine - INFO - Saving checkpoint at 43 epochs 2022/09/16 15:16:17 - mmengine - INFO - Epoch(train) [44][50/293] lr: 5.000000e-04 eta: 8:58:27 time: 0.790892 data_time: 0.112748 memory: 21676 loss_kpt: 0.000645 acc_pose: 0.815812 loss: 0.000645 2022/09/16 15:16:56 - mmengine - INFO - Epoch(train) [44][100/293] lr: 5.000000e-04 eta: 8:58:18 time: 0.787128 data_time: 0.097089 memory: 21676 loss_kpt: 0.000615 acc_pose: 0.836990 loss: 0.000615 2022/09/16 15:17:35 - mmengine - INFO - Epoch(train) [44][150/293] lr: 5.000000e-04 eta: 8:58:08 time: 0.781653 data_time: 0.098439 memory: 21676 loss_kpt: 0.000634 acc_pose: 0.785649 loss: 0.000634 2022/09/16 15:18:14 - mmengine - INFO - Epoch(train) [44][200/293] lr: 5.000000e-04 eta: 8:57:55 time: 0.768249 data_time: 0.096237 memory: 21676 loss_kpt: 0.000620 acc_pose: 0.860131 loss: 0.000620 2022/09/16 15:18:52 - mmengine - INFO - Epoch(train) [44][250/293] lr: 5.000000e-04 eta: 8:57:40 time: 0.757997 data_time: 0.092203 memory: 21676 loss_kpt: 0.000620 acc_pose: 0.838240 loss: 0.000620 2022/09/16 15:19:25 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 15:19:25 - mmengine - INFO - Saving checkpoint at 44 epochs 2022/09/16 15:20:09 - mmengine - INFO - Epoch(train) [45][50/293] lr: 5.000000e-04 eta: 8:55:16 time: 0.790212 data_time: 0.108710 memory: 21676 loss_kpt: 0.000638 acc_pose: 0.815153 loss: 0.000638 2022/09/16 15:20:48 - mmengine - INFO - Epoch(train) [45][100/293] lr: 5.000000e-04 eta: 8:55:05 time: 0.780808 data_time: 0.096445 memory: 21676 loss_kpt: 0.000645 acc_pose: 0.840532 loss: 0.000645 2022/09/16 15:20:54 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 15:21:27 - mmengine - INFO - Epoch(train) [45][150/293] lr: 5.000000e-04 eta: 8:54:56 time: 0.788233 data_time: 0.095947 memory: 21676 loss_kpt: 0.000633 acc_pose: 0.796573 loss: 0.000633 2022/09/16 15:22:06 - mmengine - INFO - Epoch(train) [45][200/293] lr: 5.000000e-04 eta: 8:54:42 time: 0.769633 data_time: 0.097578 memory: 21676 loss_kpt: 0.000623 acc_pose: 0.800832 loss: 0.000623 2022/09/16 15:22:44 - mmengine - INFO - Epoch(train) [45][250/293] lr: 5.000000e-04 eta: 8:54:29 time: 0.770737 data_time: 0.096740 memory: 21676 loss_kpt: 0.000634 acc_pose: 0.843008 loss: 0.000634 2022/09/16 15:23:16 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 15:23:16 - mmengine - INFO - Saving checkpoint at 45 epochs 2022/09/16 15:24:00 - mmengine - INFO - Epoch(train) [46][50/293] lr: 5.000000e-04 eta: 8:52:06 time: 0.785430 data_time: 0.107339 memory: 21676 loss_kpt: 0.000628 acc_pose: 0.799836 loss: 0.000628 2022/09/16 15:24:39 - mmengine - INFO - Epoch(train) [46][100/293] lr: 5.000000e-04 eta: 8:51:53 time: 0.772695 data_time: 0.105462 memory: 21676 loss_kpt: 0.000606 acc_pose: 0.837852 loss: 0.000606 2022/09/16 15:25:18 - mmengine - INFO - Epoch(train) [46][150/293] lr: 5.000000e-04 eta: 8:51:42 time: 0.784064 data_time: 0.103027 memory: 21676 loss_kpt: 0.000616 acc_pose: 0.837940 loss: 0.000616 2022/09/16 15:25:56 - mmengine - INFO - Epoch(train) [46][200/293] lr: 5.000000e-04 eta: 8:51:28 time: 0.766070 data_time: 0.097233 memory: 21676 loss_kpt: 0.000636 acc_pose: 0.833524 loss: 0.000636 2022/09/16 15:26:34 - mmengine - INFO - Epoch(train) [46][250/293] lr: 5.000000e-04 eta: 8:51:12 time: 0.758588 data_time: 0.096636 memory: 21676 loss_kpt: 0.000613 acc_pose: 0.841518 loss: 0.000613 2022/09/16 15:27:06 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 15:27:06 - mmengine - INFO - Saving checkpoint at 46 epochs 2022/09/16 15:27:49 - mmengine - INFO - Epoch(train) [47][50/293] lr: 5.000000e-04 eta: 8:48:48 time: 0.765438 data_time: 0.106345 memory: 21676 loss_kpt: 0.000624 acc_pose: 0.780931 loss: 0.000624 2022/09/16 15:28:27 - mmengine - INFO - Epoch(train) [47][100/293] lr: 5.000000e-04 eta: 8:48:32 time: 0.758595 data_time: 0.101748 memory: 21676 loss_kpt: 0.000618 acc_pose: 0.830141 loss: 0.000618 2022/09/16 15:29:05 - mmengine - INFO - Epoch(train) [47][150/293] lr: 5.000000e-04 eta: 8:48:16 time: 0.759427 data_time: 0.098504 memory: 21676 loss_kpt: 0.000622 acc_pose: 0.848562 loss: 0.000622 2022/09/16 15:29:43 - mmengine - INFO - Epoch(train) [47][200/293] lr: 5.000000e-04 eta: 8:48:00 time: 0.760843 data_time: 0.097461 memory: 21676 loss_kpt: 0.000626 acc_pose: 0.820787 loss: 0.000626 2022/09/16 15:30:21 - mmengine - INFO - Epoch(train) [47][250/293] lr: 5.000000e-04 eta: 8:47:43 time: 0.756199 data_time: 0.092532 memory: 21676 loss_kpt: 0.000618 acc_pose: 0.822886 loss: 0.000618 2022/09/16 15:30:53 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 15:30:53 - mmengine - INFO - Saving checkpoint at 47 epochs 2022/09/16 15:31:37 - mmengine - INFO - Epoch(train) [48][50/293] lr: 5.000000e-04 eta: 8:45:27 time: 0.797480 data_time: 0.110740 memory: 21676 loss_kpt: 0.000621 acc_pose: 0.840991 loss: 0.000621 2022/09/16 15:32:16 - mmengine - INFO - Epoch(train) [48][100/293] lr: 5.000000e-04 eta: 8:45:14 time: 0.779191 data_time: 0.100021 memory: 21676 loss_kpt: 0.000629 acc_pose: 0.854077 loss: 0.000629 2022/09/16 15:32:55 - mmengine - INFO - Epoch(train) [48][150/293] lr: 5.000000e-04 eta: 8:45:01 time: 0.776645 data_time: 0.100766 memory: 21676 loss_kpt: 0.000626 acc_pose: 0.841619 loss: 0.000626 2022/09/16 15:33:34 - mmengine - INFO - Epoch(train) [48][200/293] lr: 5.000000e-04 eta: 8:44:48 time: 0.781976 data_time: 0.095745 memory: 21676 loss_kpt: 0.000623 acc_pose: 0.796039 loss: 0.000623 2022/09/16 15:33:56 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 15:34:12 - mmengine - INFO - Epoch(train) [48][250/293] lr: 5.000000e-04 eta: 8:44:31 time: 0.754874 data_time: 0.098289 memory: 21676 loss_kpt: 0.000618 acc_pose: 0.796473 loss: 0.000618 2022/09/16 15:34:44 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 15:34:44 - mmengine - INFO - Saving checkpoint at 48 epochs 2022/09/16 15:35:28 - mmengine - INFO - Epoch(train) [49][50/293] lr: 5.000000e-04 eta: 8:42:14 time: 0.786292 data_time: 0.102607 memory: 21676 loss_kpt: 0.000627 acc_pose: 0.837153 loss: 0.000627 2022/09/16 15:36:06 - mmengine - INFO - Epoch(train) [49][100/293] lr: 5.000000e-04 eta: 8:41:57 time: 0.752417 data_time: 0.104100 memory: 21676 loss_kpt: 0.000624 acc_pose: 0.797844 loss: 0.000624 2022/09/16 15:36:44 - mmengine - INFO - Epoch(train) [49][150/293] lr: 5.000000e-04 eta: 8:41:41 time: 0.763176 data_time: 0.092512 memory: 21676 loss_kpt: 0.000626 acc_pose: 0.853567 loss: 0.000626 2022/09/16 15:37:22 - mmengine - INFO - Epoch(train) [49][200/293] lr: 5.000000e-04 eta: 8:41:25 time: 0.765633 data_time: 0.101855 memory: 21676 loss_kpt: 0.000613 acc_pose: 0.826428 loss: 0.000613 2022/09/16 15:38:00 - mmengine - INFO - Epoch(train) [49][250/293] lr: 5.000000e-04 eta: 8:41:06 time: 0.750844 data_time: 0.096337 memory: 21676 loss_kpt: 0.000633 acc_pose: 0.791101 loss: 0.000633 2022/09/16 15:38:32 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 15:38:32 - mmengine - INFO - Saving checkpoint at 49 epochs 2022/09/16 15:39:16 - mmengine - INFO - Epoch(train) [50][50/293] lr: 5.000000e-04 eta: 8:38:54 time: 0.796539 data_time: 0.115990 memory: 21676 loss_kpt: 0.000625 acc_pose: 0.809104 loss: 0.000625 2022/09/16 15:39:56 - mmengine - INFO - Epoch(train) [50][100/293] lr: 5.000000e-04 eta: 8:38:42 time: 0.791367 data_time: 0.102028 memory: 21676 loss_kpt: 0.000608 acc_pose: 0.797686 loss: 0.000608 2022/09/16 15:40:35 - mmengine - INFO - Epoch(train) [50][150/293] lr: 5.000000e-04 eta: 8:38:27 time: 0.776242 data_time: 0.097094 memory: 21676 loss_kpt: 0.000626 acc_pose: 0.836709 loss: 0.000626 2022/09/16 15:41:13 - mmengine - INFO - Epoch(train) [50][200/293] lr: 5.000000e-04 eta: 8:38:11 time: 0.763075 data_time: 0.096539 memory: 21676 loss_kpt: 0.000621 acc_pose: 0.816042 loss: 0.000621 2022/09/16 15:41:51 - mmengine - INFO - Epoch(train) [50][250/293] lr: 5.000000e-04 eta: 8:37:53 time: 0.760463 data_time: 0.097538 memory: 21676 loss_kpt: 0.000609 acc_pose: 0.806837 loss: 0.000609 2022/09/16 15:42:23 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 15:42:23 - mmengine - INFO - Saving checkpoint at 50 epochs 2022/09/16 15:42:38 - mmengine - INFO - Epoch(val) [50][50/407] eta: 0:01:16 time: 0.214975 data_time: 0.013829 memory: 21676 2022/09/16 15:42:49 - mmengine - INFO - Epoch(val) [50][100/407] eta: 0:01:04 time: 0.210774 data_time: 0.008718 memory: 1375 2022/09/16 15:42:59 - mmengine - INFO - Epoch(val) [50][150/407] eta: 0:00:53 time: 0.209935 data_time: 0.008386 memory: 1375 2022/09/16 15:43:10 - mmengine - INFO - Epoch(val) [50][200/407] eta: 0:00:44 time: 0.214608 data_time: 0.012028 memory: 1375 2022/09/16 15:43:21 - mmengine - INFO - Epoch(val) [50][250/407] eta: 0:00:33 time: 0.213320 data_time: 0.009235 memory: 1375 2022/09/16 15:43:31 - mmengine - INFO - Epoch(val) [50][300/407] eta: 0:00:22 time: 0.210588 data_time: 0.008654 memory: 1375 2022/09/16 15:43:42 - mmengine - INFO - Epoch(val) [50][350/407] eta: 0:00:11 time: 0.209856 data_time: 0.008834 memory: 1375 2022/09/16 15:43:52 - mmengine - INFO - Epoch(val) [50][400/407] eta: 0:00:01 time: 0.207215 data_time: 0.008207 memory: 1375 2022/09/16 15:44:27 - mmengine - INFO - Evaluating CocoMetric... 2022/09/16 15:44:41 - mmengine - INFO - Epoch(val) [50][407/407] coco/AP: 0.738807 coco/AP .5: 0.895380 coco/AP .75: 0.808614 coco/AP (M): 0.698031 coco/AP (L): 0.811744 coco/AR: 0.789295 coco/AR .5: 0.932777 coco/AR .75: 0.850441 coco/AR (M): 0.743567 coco/AR (L): 0.855258 2022/09/16 15:44:41 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220916/dark_w32_384/best_coco/AP_epoch_40.pth is removed 2022/09/16 15:44:44 - mmengine - INFO - The best checkpoint with 0.7388 coco/AP at 50 epoch is saved to best_coco/AP_epoch_50.pth. 2022/09/16 15:45:23 - mmengine - INFO - Epoch(train) [51][50/293] lr: 5.000000e-04 eta: 8:35:41 time: 0.784592 data_time: 0.106432 memory: 21676 loss_kpt: 0.000618 acc_pose: 0.839987 loss: 0.000618 2022/09/16 15:46:02 - mmengine - INFO - Epoch(train) [51][100/293] lr: 5.000000e-04 eta: 8:35:26 time: 0.774978 data_time: 0.096007 memory: 21676 loss_kpt: 0.000610 acc_pose: 0.789084 loss: 0.000610 2022/09/16 15:46:41 - mmengine - INFO - Epoch(train) [51][150/293] lr: 5.000000e-04 eta: 8:35:11 time: 0.774568 data_time: 0.097338 memory: 21676 loss_kpt: 0.000613 acc_pose: 0.847352 loss: 0.000613 2022/09/16 15:47:19 - mmengine - INFO - Epoch(train) [51][200/293] lr: 5.000000e-04 eta: 8:34:55 time: 0.773170 data_time: 0.095079 memory: 21676 loss_kpt: 0.000625 acc_pose: 0.819369 loss: 0.000625 2022/09/16 15:47:58 - mmengine - INFO - Epoch(train) [51][250/293] lr: 5.000000e-04 eta: 8:34:39 time: 0.771048 data_time: 0.097017 memory: 21676 loss_kpt: 0.000622 acc_pose: 0.816575 loss: 0.000622 2022/09/16 15:48:31 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 15:48:31 - mmengine - INFO - Saving checkpoint at 51 epochs 2022/09/16 15:49:15 - mmengine - INFO - Epoch(train) [52][50/293] lr: 5.000000e-04 eta: 8:32:27 time: 0.777854 data_time: 0.107156 memory: 21676 loss_kpt: 0.000606 acc_pose: 0.812167 loss: 0.000606 2022/09/16 15:49:20 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 15:49:52 - mmengine - INFO - Epoch(train) [52][100/293] lr: 5.000000e-04 eta: 8:32:08 time: 0.753035 data_time: 0.097384 memory: 21676 loss_kpt: 0.000613 acc_pose: 0.800096 loss: 0.000613 2022/09/16 15:50:30 - mmengine - INFO - Epoch(train) [52][150/293] lr: 5.000000e-04 eta: 8:31:50 time: 0.755900 data_time: 0.099266 memory: 21676 loss_kpt: 0.000612 acc_pose: 0.874569 loss: 0.000612 2022/09/16 15:51:09 - mmengine - INFO - Epoch(train) [52][200/293] lr: 5.000000e-04 eta: 8:31:33 time: 0.770533 data_time: 0.098880 memory: 21676 loss_kpt: 0.000614 acc_pose: 0.830417 loss: 0.000614 2022/09/16 15:51:46 - mmengine - INFO - Epoch(train) [52][250/293] lr: 5.000000e-04 eta: 8:31:14 time: 0.748174 data_time: 0.095571 memory: 21676 loss_kpt: 0.000625 acc_pose: 0.815910 loss: 0.000625 2022/09/16 15:52:19 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 15:52:19 - mmengine - INFO - Saving checkpoint at 52 epochs 2022/09/16 15:53:03 - mmengine - INFO - Epoch(train) [53][50/293] lr: 5.000000e-04 eta: 8:29:05 time: 0.787347 data_time: 0.108679 memory: 21676 loss_kpt: 0.000612 acc_pose: 0.821583 loss: 0.000612 2022/09/16 15:53:41 - mmengine - INFO - Epoch(train) [53][100/293] lr: 5.000000e-04 eta: 8:28:48 time: 0.768239 data_time: 0.095680 memory: 21676 loss_kpt: 0.000608 acc_pose: 0.810009 loss: 0.000608 2022/09/16 15:54:19 - mmengine - INFO - Epoch(train) [53][150/293] lr: 5.000000e-04 eta: 8:28:29 time: 0.754455 data_time: 0.096963 memory: 21676 loss_kpt: 0.000611 acc_pose: 0.819713 loss: 0.000611 2022/09/16 15:54:57 - mmengine - INFO - Epoch(train) [53][200/293] lr: 5.000000e-04 eta: 8:28:11 time: 0.761058 data_time: 0.097520 memory: 21676 loss_kpt: 0.000615 acc_pose: 0.844836 loss: 0.000615 2022/09/16 15:55:35 - mmengine - INFO - Epoch(train) [53][250/293] lr: 5.000000e-04 eta: 8:27:53 time: 0.765216 data_time: 0.101747 memory: 21676 loss_kpt: 0.000612 acc_pose: 0.876419 loss: 0.000612 2022/09/16 15:56:08 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 15:56:08 - mmengine - INFO - Saving checkpoint at 53 epochs 2022/09/16 15:56:52 - mmengine - INFO - Epoch(train) [54][50/293] lr: 5.000000e-04 eta: 8:25:46 time: 0.787043 data_time: 0.106934 memory: 21676 loss_kpt: 0.000600 acc_pose: 0.835118 loss: 0.000600 2022/09/16 15:57:30 - mmengine - INFO - Epoch(train) [54][100/293] lr: 5.000000e-04 eta: 8:25:29 time: 0.771456 data_time: 0.094518 memory: 21676 loss_kpt: 0.000616 acc_pose: 0.820999 loss: 0.000616 2022/09/16 15:58:09 - mmengine - INFO - Epoch(train) [54][150/293] lr: 5.000000e-04 eta: 8:25:12 time: 0.765184 data_time: 0.097782 memory: 21676 loss_kpt: 0.000611 acc_pose: 0.816035 loss: 0.000611 2022/09/16 15:58:46 - mmengine - INFO - Epoch(train) [54][200/293] lr: 5.000000e-04 eta: 8:24:52 time: 0.751680 data_time: 0.096248 memory: 21676 loss_kpt: 0.000609 acc_pose: 0.859969 loss: 0.000609 2022/09/16 15:59:24 - mmengine - INFO - Epoch(train) [54][250/293] lr: 5.000000e-04 eta: 8:24:33 time: 0.761582 data_time: 0.095849 memory: 21676 loss_kpt: 0.000607 acc_pose: 0.819910 loss: 0.000607 2022/09/16 15:59:57 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 15:59:57 - mmengine - INFO - Saving checkpoint at 54 epochs 2022/09/16 16:00:41 - mmengine - INFO - Epoch(train) [55][50/293] lr: 5.000000e-04 eta: 8:22:28 time: 0.785622 data_time: 0.116908 memory: 21676 loss_kpt: 0.000615 acc_pose: 0.815653 loss: 0.000615 2022/09/16 16:01:20 - mmengine - INFO - Epoch(train) [55][100/293] lr: 5.000000e-04 eta: 8:22:11 time: 0.776621 data_time: 0.095372 memory: 21676 loss_kpt: 0.000614 acc_pose: 0.855286 loss: 0.000614 2022/09/16 16:01:59 - mmengine - INFO - Epoch(train) [55][150/293] lr: 5.000000e-04 eta: 8:21:55 time: 0.777869 data_time: 0.098790 memory: 21676 loss_kpt: 0.000608 acc_pose: 0.815046 loss: 0.000608 2022/09/16 16:02:20 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 16:02:36 - mmengine - INFO - Epoch(train) [55][200/293] lr: 5.000000e-04 eta: 8:21:35 time: 0.755022 data_time: 0.099510 memory: 21676 loss_kpt: 0.000619 acc_pose: 0.806810 loss: 0.000619 2022/09/16 16:03:14 - mmengine - INFO - Epoch(train) [55][250/293] lr: 5.000000e-04 eta: 8:21:16 time: 0.756448 data_time: 0.093883 memory: 21676 loss_kpt: 0.000601 acc_pose: 0.835625 loss: 0.000601 2022/09/16 16:03:47 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 16:03:47 - mmengine - INFO - Saving checkpoint at 55 epochs 2022/09/16 16:04:31 - mmengine - INFO - Epoch(train) [56][50/293] lr: 5.000000e-04 eta: 8:19:12 time: 0.788800 data_time: 0.107367 memory: 21676 loss_kpt: 0.000623 acc_pose: 0.814860 loss: 0.000623 2022/09/16 16:05:10 - mmengine - INFO - Epoch(train) [56][100/293] lr: 5.000000e-04 eta: 8:18:57 time: 0.790499 data_time: 0.097115 memory: 21676 loss_kpt: 0.000604 acc_pose: 0.843433 loss: 0.000604 2022/09/16 16:05:49 - mmengine - INFO - Epoch(train) [56][150/293] lr: 5.000000e-04 eta: 8:18:41 time: 0.778057 data_time: 0.097696 memory: 21676 loss_kpt: 0.000613 acc_pose: 0.845781 loss: 0.000613 2022/09/16 16:06:27 - mmengine - INFO - Epoch(train) [56][200/293] lr: 5.000000e-04 eta: 8:18:20 time: 0.753038 data_time: 0.093580 memory: 21676 loss_kpt: 0.000606 acc_pose: 0.843000 loss: 0.000606 2022/09/16 16:07:04 - mmengine - INFO - Epoch(train) [56][250/293] lr: 5.000000e-04 eta: 8:17:59 time: 0.749417 data_time: 0.092144 memory: 21676 loss_kpt: 0.000615 acc_pose: 0.815475 loss: 0.000615 2022/09/16 16:07:36 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 16:07:36 - mmengine - INFO - Saving checkpoint at 56 epochs 2022/09/16 16:08:19 - mmengine - INFO - Epoch(train) [57][50/293] lr: 5.000000e-04 eta: 8:15:54 time: 0.763299 data_time: 0.104700 memory: 21676 loss_kpt: 0.000607 acc_pose: 0.823348 loss: 0.000607 2022/09/16 16:08:57 - mmengine - INFO - Epoch(train) [57][100/293] lr: 5.000000e-04 eta: 8:15:35 time: 0.763076 data_time: 0.094691 memory: 21676 loss_kpt: 0.000608 acc_pose: 0.816710 loss: 0.000608 2022/09/16 16:09:35 - mmengine - INFO - Epoch(train) [57][150/293] lr: 5.000000e-04 eta: 8:15:15 time: 0.756859 data_time: 0.095379 memory: 21676 loss_kpt: 0.000603 acc_pose: 0.852914 loss: 0.000603 2022/09/16 16:10:13 - mmengine - INFO - Epoch(train) [57][200/293] lr: 5.000000e-04 eta: 8:14:56 time: 0.765201 data_time: 0.102810 memory: 21676 loss_kpt: 0.000612 acc_pose: 0.820514 loss: 0.000612 2022/09/16 16:10:51 - mmengine - INFO - Epoch(train) [57][250/293] lr: 5.000000e-04 eta: 8:14:36 time: 0.758982 data_time: 0.091528 memory: 21676 loss_kpt: 0.000607 acc_pose: 0.842771 loss: 0.000607 2022/09/16 16:11:23 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 16:11:23 - mmengine - INFO - Saving checkpoint at 57 epochs 2022/09/16 16:12:08 - mmengine - INFO - Epoch(train) [58][50/293] lr: 5.000000e-04 eta: 8:12:37 time: 0.796542 data_time: 0.105260 memory: 21676 loss_kpt: 0.000613 acc_pose: 0.858334 loss: 0.000613 2022/09/16 16:12:47 - mmengine - INFO - Epoch(train) [58][100/293] lr: 5.000000e-04 eta: 8:12:21 time: 0.791161 data_time: 0.103869 memory: 21676 loss_kpt: 0.000602 acc_pose: 0.871239 loss: 0.000602 2022/09/16 16:13:26 - mmengine - INFO - Epoch(train) [58][150/293] lr: 5.000000e-04 eta: 8:12:03 time: 0.772192 data_time: 0.094383 memory: 21676 loss_kpt: 0.000601 acc_pose: 0.800865 loss: 0.000601 2022/09/16 16:14:04 - mmengine - INFO - Epoch(train) [58][200/293] lr: 5.000000e-04 eta: 8:11:44 time: 0.769993 data_time: 0.099716 memory: 21676 loss_kpt: 0.000614 acc_pose: 0.785504 loss: 0.000614 2022/09/16 16:14:43 - mmengine - INFO - Epoch(train) [58][250/293] lr: 5.000000e-04 eta: 8:11:26 time: 0.771857 data_time: 0.096516 memory: 21676 loss_kpt: 0.000613 acc_pose: 0.839943 loss: 0.000613 2022/09/16 16:15:16 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 16:15:16 - mmengine - INFO - Saving checkpoint at 58 epochs 2022/09/16 16:15:26 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 16:16:00 - mmengine - INFO - Epoch(train) [59][50/293] lr: 5.000000e-04 eta: 8:09:26 time: 0.782890 data_time: 0.100878 memory: 21676 loss_kpt: 0.000611 acc_pose: 0.788321 loss: 0.000611 2022/09/16 16:16:39 - mmengine - INFO - Epoch(train) [59][100/293] lr: 5.000000e-04 eta: 8:09:10 time: 0.790044 data_time: 0.104374 memory: 21676 loss_kpt: 0.000608 acc_pose: 0.858304 loss: 0.000608 2022/09/16 16:17:18 - mmengine - INFO - Epoch(train) [59][150/293] lr: 5.000000e-04 eta: 8:08:51 time: 0.767360 data_time: 0.095379 memory: 21676 loss_kpt: 0.000616 acc_pose: 0.868551 loss: 0.000616 2022/09/16 16:17:57 - mmengine - INFO - Epoch(train) [59][200/293] lr: 5.000000e-04 eta: 8:08:33 time: 0.776724 data_time: 0.095699 memory: 21676 loss_kpt: 0.000606 acc_pose: 0.838048 loss: 0.000606 2022/09/16 16:18:35 - mmengine - INFO - Epoch(train) [59][250/293] lr: 5.000000e-04 eta: 8:08:14 time: 0.774096 data_time: 0.099747 memory: 21676 loss_kpt: 0.000602 acc_pose: 0.809608 loss: 0.000602 2022/09/16 16:19:07 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 16:19:07 - mmengine - INFO - Saving checkpoint at 59 epochs 2022/09/16 16:19:52 - mmengine - INFO - Epoch(train) [60][50/293] lr: 5.000000e-04 eta: 8:06:18 time: 0.800260 data_time: 0.108638 memory: 21676 loss_kpt: 0.000612 acc_pose: 0.775846 loss: 0.000612 2022/09/16 16:20:31 - mmengine - INFO - Epoch(train) [60][100/293] lr: 5.000000e-04 eta: 8:05:59 time: 0.775564 data_time: 0.099155 memory: 21676 loss_kpt: 0.000617 acc_pose: 0.795421 loss: 0.000617 2022/09/16 16:21:10 - mmengine - INFO - Epoch(train) [60][150/293] lr: 5.000000e-04 eta: 8:05:41 time: 0.779853 data_time: 0.095307 memory: 21676 loss_kpt: 0.000598 acc_pose: 0.801346 loss: 0.000598 2022/09/16 16:21:48 - mmengine - INFO - Epoch(train) [60][200/293] lr: 5.000000e-04 eta: 8:05:23 time: 0.774321 data_time: 0.091816 memory: 21676 loss_kpt: 0.000604 acc_pose: 0.826869 loss: 0.000604 2022/09/16 16:22:28 - mmengine - INFO - Epoch(train) [60][250/293] lr: 5.000000e-04 eta: 8:05:05 time: 0.785756 data_time: 0.096334 memory: 21676 loss_kpt: 0.000608 acc_pose: 0.831173 loss: 0.000608 2022/09/16 16:23:01 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 16:23:01 - mmengine - INFO - Saving checkpoint at 60 epochs 2022/09/16 16:23:16 - mmengine - INFO - Epoch(val) [60][50/407] eta: 0:01:19 time: 0.222135 data_time: 0.016835 memory: 21676 2022/09/16 16:23:27 - mmengine - INFO - Epoch(val) [60][100/407] eta: 0:01:05 time: 0.212500 data_time: 0.009373 memory: 1375 2022/09/16 16:23:38 - mmengine - INFO - Epoch(val) [60][150/407] eta: 0:00:54 time: 0.212970 data_time: 0.008764 memory: 1375 2022/09/16 16:23:49 - mmengine - INFO - Epoch(val) [60][200/407] eta: 0:00:44 time: 0.217062 data_time: 0.008878 memory: 1375 2022/09/16 16:23:59 - mmengine - INFO - Epoch(val) [60][250/407] eta: 0:00:32 time: 0.209132 data_time: 0.008583 memory: 1375 2022/09/16 16:24:10 - mmengine - INFO - Epoch(val) [60][300/407] eta: 0:00:23 time: 0.215542 data_time: 0.012504 memory: 1375 2022/09/16 16:24:20 - mmengine - INFO - Epoch(val) [60][350/407] eta: 0:00:11 time: 0.209588 data_time: 0.008315 memory: 1375 2022/09/16 16:24:31 - mmengine - INFO - Epoch(val) [60][400/407] eta: 0:00:01 time: 0.210331 data_time: 0.010448 memory: 1375 2022/09/16 16:25:07 - mmengine - INFO - Evaluating CocoMetric... 2022/09/16 16:25:21 - mmengine - INFO - Epoch(val) [60][407/407] coco/AP: 0.742816 coco/AP .5: 0.898673 coco/AP .75: 0.808819 coco/AP (M): 0.703413 coco/AP (L): 0.812570 coco/AR: 0.792428 coco/AR .5: 0.935611 coco/AR .75: 0.851228 coco/AR (M): 0.748757 coco/AR (L): 0.855407 2022/09/16 16:25:21 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220916/dark_w32_384/best_coco/AP_epoch_50.pth is removed 2022/09/16 16:25:24 - mmengine - INFO - The best checkpoint with 0.7428 coco/AP at 60 epoch is saved to best_coco/AP_epoch_60.pth. 2022/09/16 16:26:02 - mmengine - INFO - Epoch(train) [61][50/293] lr: 5.000000e-04 eta: 8:03:07 time: 0.774024 data_time: 0.109132 memory: 21676 loss_kpt: 0.000598 acc_pose: 0.812052 loss: 0.000598 2022/09/16 16:26:41 - mmengine - INFO - Epoch(train) [61][100/293] lr: 5.000000e-04 eta: 8:02:47 time: 0.769474 data_time: 0.093465 memory: 21676 loss_kpt: 0.000596 acc_pose: 0.818064 loss: 0.000596 2022/09/16 16:27:20 - mmengine - INFO - Epoch(train) [61][150/293] lr: 5.000000e-04 eta: 8:02:30 time: 0.786224 data_time: 0.095569 memory: 21676 loss_kpt: 0.000601 acc_pose: 0.844327 loss: 0.000601 2022/09/16 16:27:59 - mmengine - INFO - Epoch(train) [61][200/293] lr: 5.000000e-04 eta: 8:02:12 time: 0.780950 data_time: 0.095405 memory: 21676 loss_kpt: 0.000600 acc_pose: 0.822812 loss: 0.000600 2022/09/16 16:28:38 - mmengine - INFO - Epoch(train) [61][250/293] lr: 5.000000e-04 eta: 8:01:52 time: 0.771058 data_time: 0.095620 memory: 21676 loss_kpt: 0.000603 acc_pose: 0.825982 loss: 0.000603 2022/09/16 16:29:11 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 16:29:11 - mmengine - INFO - Saving checkpoint at 61 epochs 2022/09/16 16:29:55 - mmengine - INFO - Epoch(train) [62][50/293] lr: 5.000000e-04 eta: 7:59:57 time: 0.790595 data_time: 0.110947 memory: 21676 loss_kpt: 0.000602 acc_pose: 0.837319 loss: 0.000602 2022/09/16 16:30:34 - mmengine - INFO - Epoch(train) [62][100/293] lr: 5.000000e-04 eta: 7:59:39 time: 0.786580 data_time: 0.099406 memory: 21676 loss_kpt: 0.000582 acc_pose: 0.798492 loss: 0.000582 2022/09/16 16:30:55 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 16:31:13 - mmengine - INFO - Epoch(train) [62][150/293] lr: 5.000000e-04 eta: 7:59:19 time: 0.771119 data_time: 0.101082 memory: 21676 loss_kpt: 0.000602 acc_pose: 0.851926 loss: 0.000602 2022/09/16 16:31:52 - mmengine - INFO - Epoch(train) [62][200/293] lr: 5.000000e-04 eta: 7:59:00 time: 0.776159 data_time: 0.103178 memory: 21676 loss_kpt: 0.000595 acc_pose: 0.791619 loss: 0.000595 2022/09/16 16:32:30 - mmengine - INFO - Epoch(train) [62][250/293] lr: 5.000000e-04 eta: 7:58:39 time: 0.761828 data_time: 0.094770 memory: 21676 loss_kpt: 0.000603 acc_pose: 0.824797 loss: 0.000603 2022/09/16 16:33:02 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 16:33:02 - mmengine - INFO - Saving checkpoint at 62 epochs 2022/09/16 16:33:46 - mmengine - INFO - Epoch(train) [63][50/293] lr: 5.000000e-04 eta: 7:56:45 time: 0.784994 data_time: 0.111398 memory: 21676 loss_kpt: 0.000600 acc_pose: 0.782178 loss: 0.000600 2022/09/16 16:34:24 - mmengine - INFO - Epoch(train) [63][100/293] lr: 5.000000e-04 eta: 7:56:25 time: 0.773172 data_time: 0.107044 memory: 21676 loss_kpt: 0.000604 acc_pose: 0.833178 loss: 0.000604 2022/09/16 16:35:03 - mmengine - INFO - Epoch(train) [63][150/293] lr: 5.000000e-04 eta: 7:56:05 time: 0.773699 data_time: 0.104163 memory: 21676 loss_kpt: 0.000603 acc_pose: 0.813506 loss: 0.000603 2022/09/16 16:35:41 - mmengine - INFO - Epoch(train) [63][200/293] lr: 5.000000e-04 eta: 7:55:43 time: 0.754146 data_time: 0.097041 memory: 21676 loss_kpt: 0.000598 acc_pose: 0.819543 loss: 0.000598 2022/09/16 16:36:18 - mmengine - INFO - Epoch(train) [63][250/293] lr: 5.000000e-04 eta: 7:55:21 time: 0.750355 data_time: 0.093310 memory: 21676 loss_kpt: 0.000595 acc_pose: 0.763456 loss: 0.000595 2022/09/16 16:36:51 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 16:36:51 - mmengine - INFO - Saving checkpoint at 63 epochs 2022/09/16 16:37:35 - mmengine - INFO - Epoch(train) [64][50/293] lr: 5.000000e-04 eta: 7:53:27 time: 0.783696 data_time: 0.113650 memory: 21676 loss_kpt: 0.000596 acc_pose: 0.859508 loss: 0.000596 2022/09/16 16:38:14 - mmengine - INFO - Epoch(train) [64][100/293] lr: 5.000000e-04 eta: 7:53:09 time: 0.787753 data_time: 0.094256 memory: 21676 loss_kpt: 0.000595 acc_pose: 0.834537 loss: 0.000595 2022/09/16 16:38:54 - mmengine - INFO - Epoch(train) [64][150/293] lr: 5.000000e-04 eta: 7:52:51 time: 0.789499 data_time: 0.096860 memory: 21676 loss_kpt: 0.000607 acc_pose: 0.835055 loss: 0.000607 2022/09/16 16:39:33 - mmengine - INFO - Epoch(train) [64][200/293] lr: 5.000000e-04 eta: 7:52:32 time: 0.784798 data_time: 0.099548 memory: 21676 loss_kpt: 0.000591 acc_pose: 0.815971 loss: 0.000591 2022/09/16 16:40:12 - mmengine - INFO - Epoch(train) [64][250/293] lr: 5.000000e-04 eta: 7:52:11 time: 0.772269 data_time: 0.093310 memory: 21676 loss_kpt: 0.000600 acc_pose: 0.836588 loss: 0.000600 2022/09/16 16:40:45 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 16:40:45 - mmengine - INFO - Saving checkpoint at 64 epochs 2022/09/16 16:41:30 - mmengine - INFO - Epoch(train) [65][50/293] lr: 5.000000e-04 eta: 7:50:21 time: 0.800438 data_time: 0.106789 memory: 21676 loss_kpt: 0.000599 acc_pose: 0.777442 loss: 0.000599 2022/09/16 16:42:08 - mmengine - INFO - Epoch(train) [65][100/293] lr: 5.000000e-04 eta: 7:50:01 time: 0.776351 data_time: 0.098438 memory: 21676 loss_kpt: 0.000596 acc_pose: 0.855273 loss: 0.000596 2022/09/16 16:42:48 - mmengine - INFO - Epoch(train) [65][150/293] lr: 5.000000e-04 eta: 7:49:42 time: 0.788523 data_time: 0.096406 memory: 21676 loss_kpt: 0.000587 acc_pose: 0.782314 loss: 0.000587 2022/09/16 16:43:27 - mmengine - INFO - Epoch(train) [65][200/293] lr: 5.000000e-04 eta: 7:49:22 time: 0.776628 data_time: 0.098989 memory: 21676 loss_kpt: 0.000592 acc_pose: 0.849106 loss: 0.000592 2022/09/16 16:44:03 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 16:44:04 - mmengine - INFO - Epoch(train) [65][250/293] lr: 5.000000e-04 eta: 7:48:59 time: 0.751858 data_time: 0.095152 memory: 21676 loss_kpt: 0.000602 acc_pose: 0.818936 loss: 0.000602 2022/09/16 16:44:37 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 16:44:37 - mmengine - INFO - Saving checkpoint at 65 epochs 2022/09/16 16:45:21 - mmengine - INFO - Epoch(train) [66][50/293] lr: 5.000000e-04 eta: 7:47:09 time: 0.787104 data_time: 0.111148 memory: 21676 loss_kpt: 0.000593 acc_pose: 0.860451 loss: 0.000593 2022/09/16 16:46:00 - mmengine - INFO - Epoch(train) [66][100/293] lr: 5.000000e-04 eta: 7:46:49 time: 0.780514 data_time: 0.096539 memory: 21676 loss_kpt: 0.000603 acc_pose: 0.828702 loss: 0.000603 2022/09/16 16:46:39 - mmengine - INFO - Epoch(train) [66][150/293] lr: 5.000000e-04 eta: 7:46:29 time: 0.781200 data_time: 0.098588 memory: 21676 loss_kpt: 0.000595 acc_pose: 0.805815 loss: 0.000595 2022/09/16 16:47:17 - mmengine - INFO - Epoch(train) [66][200/293] lr: 5.000000e-04 eta: 7:46:08 time: 0.770912 data_time: 0.092355 memory: 21676 loss_kpt: 0.000612 acc_pose: 0.851156 loss: 0.000612 2022/09/16 16:47:55 - mmengine - INFO - Epoch(train) [66][250/293] lr: 5.000000e-04 eta: 7:45:46 time: 0.758401 data_time: 0.100543 memory: 21676 loss_kpt: 0.000602 acc_pose: 0.844400 loss: 0.000602 2022/09/16 16:48:27 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 16:48:27 - mmengine - INFO - Saving checkpoint at 66 epochs 2022/09/16 16:49:11 - mmengine - INFO - Epoch(train) [67][50/293] lr: 5.000000e-04 eta: 7:43:55 time: 0.780365 data_time: 0.105347 memory: 21676 loss_kpt: 0.000583 acc_pose: 0.849977 loss: 0.000583 2022/09/16 16:49:49 - mmengine - INFO - Epoch(train) [67][100/293] lr: 5.000000e-04 eta: 7:43:34 time: 0.770386 data_time: 0.100511 memory: 21676 loss_kpt: 0.000593 acc_pose: 0.795842 loss: 0.000593 2022/09/16 16:50:27 - mmengine - INFO - Epoch(train) [67][150/293] lr: 5.000000e-04 eta: 7:43:12 time: 0.762343 data_time: 0.097178 memory: 21676 loss_kpt: 0.000582 acc_pose: 0.857980 loss: 0.000582 2022/09/16 16:51:05 - mmengine - INFO - Epoch(train) [67][200/293] lr: 5.000000e-04 eta: 7:42:49 time: 0.755935 data_time: 0.095431 memory: 21676 loss_kpt: 0.000597 acc_pose: 0.807734 loss: 0.000597 2022/09/16 16:51:43 - mmengine - INFO - Epoch(train) [67][250/293] lr: 5.000000e-04 eta: 7:42:26 time: 0.758956 data_time: 0.100916 memory: 21676 loss_kpt: 0.000593 acc_pose: 0.847378 loss: 0.000593 2022/09/16 16:52:15 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 16:52:15 - mmengine - INFO - Saving checkpoint at 67 epochs 2022/09/16 16:52:59 - mmengine - INFO - Epoch(train) [68][50/293] lr: 5.000000e-04 eta: 7:40:38 time: 0.784575 data_time: 0.105461 memory: 21676 loss_kpt: 0.000596 acc_pose: 0.841897 loss: 0.000596 2022/09/16 16:53:38 - mmengine - INFO - Epoch(train) [68][100/293] lr: 5.000000e-04 eta: 7:40:18 time: 0.784693 data_time: 0.097589 memory: 21676 loss_kpt: 0.000593 acc_pose: 0.878752 loss: 0.000593 2022/09/16 16:54:18 - mmengine - INFO - Epoch(train) [68][150/293] lr: 5.000000e-04 eta: 7:39:58 time: 0.786553 data_time: 0.103826 memory: 21676 loss_kpt: 0.000604 acc_pose: 0.757266 loss: 0.000604 2022/09/16 16:54:57 - mmengine - INFO - Epoch(train) [68][200/293] lr: 5.000000e-04 eta: 7:39:37 time: 0.774839 data_time: 0.095430 memory: 21676 loss_kpt: 0.000593 acc_pose: 0.808067 loss: 0.000593 2022/09/16 16:55:34 - mmengine - INFO - Epoch(train) [68][250/293] lr: 5.000000e-04 eta: 7:39:13 time: 0.753016 data_time: 0.096949 memory: 21676 loss_kpt: 0.000592 acc_pose: 0.835509 loss: 0.000592 2022/09/16 16:56:06 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 16:56:06 - mmengine - INFO - Saving checkpoint at 68 epochs 2022/09/16 16:56:51 - mmengine - INFO - Epoch(train) [69][50/293] lr: 5.000000e-04 eta: 7:37:27 time: 0.795079 data_time: 0.108238 memory: 21676 loss_kpt: 0.000584 acc_pose: 0.833036 loss: 0.000584 2022/09/16 16:57:11 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 16:57:29 - mmengine - INFO - Epoch(train) [69][100/293] lr: 5.000000e-04 eta: 7:37:05 time: 0.772377 data_time: 0.099237 memory: 21676 loss_kpt: 0.000591 acc_pose: 0.877104 loss: 0.000591 2022/09/16 16:58:08 - mmengine - INFO - Epoch(train) [69][150/293] lr: 5.000000e-04 eta: 7:36:44 time: 0.772330 data_time: 0.096474 memory: 21676 loss_kpt: 0.000595 acc_pose: 0.830344 loss: 0.000595 2022/09/16 16:58:47 - mmengine - INFO - Epoch(train) [69][200/293] lr: 5.000000e-04 eta: 7:36:22 time: 0.776344 data_time: 0.092050 memory: 21676 loss_kpt: 0.000598 acc_pose: 0.838006 loss: 0.000598 2022/09/16 16:59:26 - mmengine - INFO - Epoch(train) [69][250/293] lr: 5.000000e-04 eta: 7:36:01 time: 0.777941 data_time: 0.094653 memory: 21676 loss_kpt: 0.000596 acc_pose: 0.813670 loss: 0.000596 2022/09/16 16:59:58 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 16:59:58 - mmengine - INFO - Saving checkpoint at 69 epochs 2022/09/16 17:00:42 - mmengine - INFO - Epoch(train) [70][50/293] lr: 5.000000e-04 eta: 7:34:14 time: 0.781727 data_time: 0.105579 memory: 21676 loss_kpt: 0.000605 acc_pose: 0.771414 loss: 0.000605 2022/09/16 17:01:20 - mmengine - INFO - Epoch(train) [70][100/293] lr: 5.000000e-04 eta: 7:33:51 time: 0.762668 data_time: 0.100731 memory: 21676 loss_kpt: 0.000594 acc_pose: 0.857006 loss: 0.000594 2022/09/16 17:01:58 - mmengine - INFO - Epoch(train) [70][150/293] lr: 5.000000e-04 eta: 7:33:28 time: 0.760556 data_time: 0.094979 memory: 21676 loss_kpt: 0.000588 acc_pose: 0.816416 loss: 0.000588 2022/09/16 17:02:37 - mmengine - INFO - Epoch(train) [70][200/293] lr: 5.000000e-04 eta: 7:33:06 time: 0.768071 data_time: 0.099914 memory: 21676 loss_kpt: 0.000596 acc_pose: 0.841639 loss: 0.000596 2022/09/16 17:03:15 - mmengine - INFO - Epoch(train) [70][250/293] lr: 5.000000e-04 eta: 7:32:43 time: 0.759681 data_time: 0.094660 memory: 21676 loss_kpt: 0.000600 acc_pose: 0.820791 loss: 0.000600 2022/09/16 17:03:47 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 17:03:47 - mmengine - INFO - Saving checkpoint at 70 epochs 2022/09/16 17:04:02 - mmengine - INFO - Epoch(val) [70][50/407] eta: 0:01:17 time: 0.217373 data_time: 0.013943 memory: 21676 2022/09/16 17:04:13 - mmengine - INFO - Epoch(val) [70][100/407] eta: 0:01:04 time: 0.211078 data_time: 0.008961 memory: 1375 2022/09/16 17:04:23 - mmengine - INFO - Epoch(val) [70][150/407] eta: 0:00:53 time: 0.209203 data_time: 0.009126 memory: 1375 2022/09/16 17:04:34 - mmengine - INFO - Epoch(val) [70][200/407] eta: 0:00:44 time: 0.213810 data_time: 0.012838 memory: 1375 2022/09/16 17:04:44 - mmengine - INFO - Epoch(val) [70][250/407] eta: 0:00:32 time: 0.209567 data_time: 0.008845 memory: 1375 2022/09/16 17:04:55 - mmengine - INFO - Epoch(val) [70][300/407] eta: 0:00:22 time: 0.210802 data_time: 0.008759 memory: 1375 2022/09/16 17:05:05 - mmengine - INFO - Epoch(val) [70][350/407] eta: 0:00:11 time: 0.209359 data_time: 0.008187 memory: 1375 2022/09/16 17:05:16 - mmengine - INFO - Epoch(val) [70][400/407] eta: 0:00:01 time: 0.207345 data_time: 0.008071 memory: 1375 2022/09/16 17:05:51 - mmengine - INFO - Evaluating CocoMetric... 2022/09/16 17:06:05 - mmengine - INFO - Epoch(val) [70][407/407] coco/AP: 0.745913 coco/AP .5: 0.897503 coco/AP .75: 0.812137 coco/AP (M): 0.704789 coco/AP (L): 0.818175 coco/AR: 0.795797 coco/AR .5: 0.935296 coco/AR .75: 0.854691 coco/AR (M): 0.750150 coco/AR (L): 0.861501 2022/09/16 17:06:05 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220916/dark_w32_384/best_coco/AP_epoch_60.pth is removed 2022/09/16 17:06:09 - mmengine - INFO - The best checkpoint with 0.7459 coco/AP at 70 epoch is saved to best_coco/AP_epoch_70.pth. 2022/09/16 17:06:48 - mmengine - INFO - Epoch(train) [71][50/293] lr: 5.000000e-04 eta: 7:30:57 time: 0.785036 data_time: 0.104952 memory: 21676 loss_kpt: 0.000588 acc_pose: 0.835636 loss: 0.000588 2022/09/16 17:07:27 - mmengine - INFO - Epoch(train) [71][100/293] lr: 5.000000e-04 eta: 7:30:36 time: 0.777061 data_time: 0.092205 memory: 21676 loss_kpt: 0.000584 acc_pose: 0.834331 loss: 0.000584 2022/09/16 17:08:05 - mmengine - INFO - Epoch(train) [71][150/293] lr: 5.000000e-04 eta: 7:30:13 time: 0.762289 data_time: 0.097267 memory: 21676 loss_kpt: 0.000593 acc_pose: 0.872118 loss: 0.000593 2022/09/16 17:08:42 - mmengine - INFO - Epoch(train) [71][200/293] lr: 5.000000e-04 eta: 7:29:48 time: 0.748971 data_time: 0.091295 memory: 21676 loss_kpt: 0.000601 acc_pose: 0.814587 loss: 0.000601 2022/09/16 17:09:20 - mmengine - INFO - Epoch(train) [71][250/293] lr: 5.000000e-04 eta: 7:29:25 time: 0.758203 data_time: 0.091968 memory: 21676 loss_kpt: 0.000597 acc_pose: 0.818374 loss: 0.000597 2022/09/16 17:09:53 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 17:09:53 - mmengine - INFO - Saving checkpoint at 71 epochs 2022/09/16 17:10:37 - mmengine - INFO - Epoch(train) [72][50/293] lr: 5.000000e-04 eta: 7:27:40 time: 0.791787 data_time: 0.110779 memory: 21676 loss_kpt: 0.000590 acc_pose: 0.853215 loss: 0.000590 2022/09/16 17:11:16 - mmengine - INFO - Epoch(train) [72][100/293] lr: 5.000000e-04 eta: 7:27:20 time: 0.784758 data_time: 0.101121 memory: 21676 loss_kpt: 0.000591 acc_pose: 0.756356 loss: 0.000591 2022/09/16 17:11:56 - mmengine - INFO - Epoch(train) [72][150/293] lr: 5.000000e-04 eta: 7:26:58 time: 0.781804 data_time: 0.096029 memory: 21676 loss_kpt: 0.000600 acc_pose: 0.832555 loss: 0.000600 2022/09/16 17:12:32 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 17:12:35 - mmengine - INFO - Epoch(train) [72][200/293] lr: 5.000000e-04 eta: 7:26:37 time: 0.782577 data_time: 0.102167 memory: 21676 loss_kpt: 0.000587 acc_pose: 0.854489 loss: 0.000587 2022/09/16 17:13:14 - mmengine - INFO - Epoch(train) [72][250/293] lr: 5.000000e-04 eta: 7:26:16 time: 0.788182 data_time: 0.108190 memory: 21676 loss_kpt: 0.000588 acc_pose: 0.800064 loss: 0.000588 2022/09/16 17:13:47 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 17:13:47 - mmengine - INFO - Saving checkpoint at 72 epochs 2022/09/16 17:14:32 - mmengine - INFO - Epoch(train) [73][50/293] lr: 5.000000e-04 eta: 7:24:33 time: 0.794845 data_time: 0.115265 memory: 21676 loss_kpt: 0.000593 acc_pose: 0.817018 loss: 0.000593 2022/09/16 17:15:10 - mmengine - INFO - Epoch(train) [73][100/293] lr: 5.000000e-04 eta: 7:24:11 time: 0.775128 data_time: 0.097162 memory: 21676 loss_kpt: 0.000589 acc_pose: 0.840082 loss: 0.000589 2022/09/16 17:15:49 - mmengine - INFO - Epoch(train) [73][150/293] lr: 5.000000e-04 eta: 7:23:49 time: 0.780777 data_time: 0.100615 memory: 21676 loss_kpt: 0.000580 acc_pose: 0.822759 loss: 0.000580 2022/09/16 17:16:28 - mmengine - INFO - Epoch(train) [73][200/293] lr: 5.000000e-04 eta: 7:23:28 time: 0.781788 data_time: 0.100860 memory: 21676 loss_kpt: 0.000575 acc_pose: 0.820523 loss: 0.000575 2022/09/16 17:17:07 - mmengine - INFO - Epoch(train) [73][250/293] lr: 5.000000e-04 eta: 7:23:05 time: 0.772383 data_time: 0.094862 memory: 21676 loss_kpt: 0.000578 acc_pose: 0.828079 loss: 0.000578 2022/09/16 17:17:40 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 17:17:40 - mmengine - INFO - Saving checkpoint at 73 epochs 2022/09/16 17:18:24 - mmengine - INFO - Epoch(train) [74][50/293] lr: 5.000000e-04 eta: 7:21:23 time: 0.793691 data_time: 0.104613 memory: 21676 loss_kpt: 0.000587 acc_pose: 0.789150 loss: 0.000587 2022/09/16 17:19:04 - mmengine - INFO - Epoch(train) [74][100/293] lr: 5.000000e-04 eta: 7:21:02 time: 0.795173 data_time: 0.098554 memory: 21676 loss_kpt: 0.000588 acc_pose: 0.812162 loss: 0.000588 2022/09/16 17:19:42 - mmengine - INFO - Epoch(train) [74][150/293] lr: 5.000000e-04 eta: 7:20:40 time: 0.777954 data_time: 0.094719 memory: 21676 loss_kpt: 0.000596 acc_pose: 0.788221 loss: 0.000596 2022/09/16 17:20:21 - mmengine - INFO - Epoch(train) [74][200/293] lr: 5.000000e-04 eta: 7:20:17 time: 0.767080 data_time: 0.095956 memory: 21676 loss_kpt: 0.000586 acc_pose: 0.816789 loss: 0.000586 2022/09/16 17:20:59 - mmengine - INFO - Epoch(train) [74][250/293] lr: 5.000000e-04 eta: 7:19:52 time: 0.756569 data_time: 0.095477 memory: 21676 loss_kpt: 0.000593 acc_pose: 0.807542 loss: 0.000593 2022/09/16 17:21:31 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 17:21:31 - mmengine - INFO - Saving checkpoint at 74 epochs 2022/09/16 17:22:15 - mmengine - INFO - Epoch(train) [75][50/293] lr: 5.000000e-04 eta: 7:18:11 time: 0.793015 data_time: 0.112150 memory: 21676 loss_kpt: 0.000590 acc_pose: 0.845457 loss: 0.000590 2022/09/16 17:22:53 - mmengine - INFO - Epoch(train) [75][100/293] lr: 5.000000e-04 eta: 7:17:47 time: 0.759212 data_time: 0.092721 memory: 21676 loss_kpt: 0.000593 acc_pose: 0.841703 loss: 0.000593 2022/09/16 17:23:31 - mmengine - INFO - Epoch(train) [75][150/293] lr: 5.000000e-04 eta: 7:17:23 time: 0.760847 data_time: 0.095768 memory: 21676 loss_kpt: 0.000592 acc_pose: 0.818295 loss: 0.000592 2022/09/16 17:24:10 - mmengine - INFO - Epoch(train) [75][200/293] lr: 5.000000e-04 eta: 7:17:00 time: 0.769183 data_time: 0.096684 memory: 21676 loss_kpt: 0.000580 acc_pose: 0.863701 loss: 0.000580 2022/09/16 17:24:47 - mmengine - INFO - Epoch(train) [75][250/293] lr: 5.000000e-04 eta: 7:16:35 time: 0.758198 data_time: 0.096548 memory: 21676 loss_kpt: 0.000593 acc_pose: 0.853248 loss: 0.000593 2022/09/16 17:25:20 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 17:25:20 - mmengine - INFO - Saving checkpoint at 75 epochs 2022/09/16 17:25:45 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 17:26:04 - mmengine - INFO - Epoch(train) [76][50/293] lr: 5.000000e-04 eta: 7:14:54 time: 0.782794 data_time: 0.103100 memory: 21676 loss_kpt: 0.000582 acc_pose: 0.811048 loss: 0.000582 2022/09/16 17:26:43 - mmengine - INFO - Epoch(train) [76][100/293] lr: 5.000000e-04 eta: 7:14:31 time: 0.779558 data_time: 0.092932 memory: 21676 loss_kpt: 0.000584 acc_pose: 0.816404 loss: 0.000584 2022/09/16 17:27:22 - mmengine - INFO - Epoch(train) [76][150/293] lr: 5.000000e-04 eta: 7:14:09 time: 0.785998 data_time: 0.095528 memory: 21676 loss_kpt: 0.000587 acc_pose: 0.864273 loss: 0.000587 2022/09/16 17:28:01 - mmengine - INFO - Epoch(train) [76][200/293] lr: 5.000000e-04 eta: 7:13:46 time: 0.773729 data_time: 0.095060 memory: 21676 loss_kpt: 0.000613 acc_pose: 0.833775 loss: 0.000613 2022/09/16 17:28:40 - mmengine - INFO - Epoch(train) [76][250/293] lr: 5.000000e-04 eta: 7:13:23 time: 0.769789 data_time: 0.091976 memory: 21676 loss_kpt: 0.000596 acc_pose: 0.862194 loss: 0.000596 2022/09/16 17:29:12 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 17:29:12 - mmengine - INFO - Saving checkpoint at 76 epochs 2022/09/16 17:29:55 - mmengine - INFO - Epoch(train) [77][50/293] lr: 5.000000e-04 eta: 7:11:42 time: 0.782210 data_time: 0.107556 memory: 21676 loss_kpt: 0.000572 acc_pose: 0.862392 loss: 0.000572 2022/09/16 17:30:35 - mmengine - INFO - Epoch(train) [77][100/293] lr: 5.000000e-04 eta: 7:11:20 time: 0.788634 data_time: 0.098258 memory: 21676 loss_kpt: 0.000581 acc_pose: 0.859699 loss: 0.000581 2022/09/16 17:31:14 - mmengine - INFO - Epoch(train) [77][150/293] lr: 5.000000e-04 eta: 7:10:57 time: 0.775417 data_time: 0.095635 memory: 21676 loss_kpt: 0.000583 acc_pose: 0.813112 loss: 0.000583 2022/09/16 17:31:52 - mmengine - INFO - Epoch(train) [77][200/293] lr: 5.000000e-04 eta: 7:10:34 time: 0.775913 data_time: 0.100011 memory: 21676 loss_kpt: 0.000589 acc_pose: 0.801192 loss: 0.000589 2022/09/16 17:32:31 - mmengine - INFO - Epoch(train) [77][250/293] lr: 5.000000e-04 eta: 7:10:11 time: 0.773949 data_time: 0.099133 memory: 21676 loss_kpt: 0.000604 acc_pose: 0.766701 loss: 0.000604 2022/09/16 17:33:04 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 17:33:04 - mmengine - INFO - Saving checkpoint at 77 epochs 2022/09/16 17:33:48 - mmengine - INFO - Epoch(train) [78][50/293] lr: 5.000000e-04 eta: 7:08:32 time: 0.795654 data_time: 0.101836 memory: 21676 loss_kpt: 0.000582 acc_pose: 0.845765 loss: 0.000582 2022/09/16 17:34:27 - mmengine - INFO - Epoch(train) [78][100/293] lr: 5.000000e-04 eta: 7:08:08 time: 0.775922 data_time: 0.099438 memory: 21676 loss_kpt: 0.000586 acc_pose: 0.866831 loss: 0.000586 2022/09/16 17:35:05 - mmengine - INFO - Epoch(train) [78][150/293] lr: 5.000000e-04 eta: 7:07:44 time: 0.761552 data_time: 0.095557 memory: 21676 loss_kpt: 0.000592 acc_pose: 0.775277 loss: 0.000592 2022/09/16 17:35:44 - mmengine - INFO - Epoch(train) [78][200/293] lr: 5.000000e-04 eta: 7:07:20 time: 0.766992 data_time: 0.097471 memory: 21676 loss_kpt: 0.000595 acc_pose: 0.820270 loss: 0.000595 2022/09/16 17:36:22 - mmengine - INFO - Epoch(train) [78][250/293] lr: 5.000000e-04 eta: 7:06:56 time: 0.766721 data_time: 0.094867 memory: 21676 loss_kpt: 0.000591 acc_pose: 0.829251 loss: 0.000591 2022/09/16 17:36:54 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 17:36:54 - mmengine - INFO - Saving checkpoint at 78 epochs 2022/09/16 17:37:39 - mmengine - INFO - Epoch(train) [79][50/293] lr: 5.000000e-04 eta: 7:05:18 time: 0.795318 data_time: 0.107555 memory: 21676 loss_kpt: 0.000591 acc_pose: 0.789088 loss: 0.000591 2022/09/16 17:38:18 - mmengine - INFO - Epoch(train) [79][100/293] lr: 5.000000e-04 eta: 7:04:55 time: 0.783433 data_time: 0.097740 memory: 21676 loss_kpt: 0.000585 acc_pose: 0.838154 loss: 0.000585 2022/09/16 17:38:54 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 17:38:57 - mmengine - INFO - Epoch(train) [79][150/293] lr: 5.000000e-04 eta: 7:04:33 time: 0.789293 data_time: 0.094523 memory: 21676 loss_kpt: 0.000580 acc_pose: 0.839244 loss: 0.000580 2022/09/16 17:39:37 - mmengine - INFO - Epoch(train) [79][200/293] lr: 5.000000e-04 eta: 7:04:10 time: 0.792425 data_time: 0.096067 memory: 21676 loss_kpt: 0.000588 acc_pose: 0.835463 loss: 0.000588 2022/09/16 17:40:16 - mmengine - INFO - Epoch(train) [79][250/293] lr: 5.000000e-04 eta: 7:03:47 time: 0.782657 data_time: 0.099749 memory: 21676 loss_kpt: 0.000585 acc_pose: 0.820620 loss: 0.000585 2022/09/16 17:40:49 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 17:40:49 - mmengine - INFO - Saving checkpoint at 79 epochs 2022/09/16 17:41:32 - mmengine - INFO - Epoch(train) [80][50/293] lr: 5.000000e-04 eta: 7:02:08 time: 0.770011 data_time: 0.102055 memory: 21676 loss_kpt: 0.000587 acc_pose: 0.891662 loss: 0.000587 2022/09/16 17:42:10 - mmengine - INFO - Epoch(train) [80][100/293] lr: 5.000000e-04 eta: 7:01:42 time: 0.751153 data_time: 0.095825 memory: 21676 loss_kpt: 0.000585 acc_pose: 0.852412 loss: 0.000585 2022/09/16 17:42:47 - mmengine - INFO - Epoch(train) [80][150/293] lr: 5.000000e-04 eta: 7:01:17 time: 0.751457 data_time: 0.095335 memory: 21676 loss_kpt: 0.000581 acc_pose: 0.818925 loss: 0.000581 2022/09/16 17:43:26 - mmengine - INFO - Epoch(train) [80][200/293] lr: 5.000000e-04 eta: 7:00:53 time: 0.775952 data_time: 0.101040 memory: 21676 loss_kpt: 0.000582 acc_pose: 0.806204 loss: 0.000582 2022/09/16 17:44:04 - mmengine - INFO - Epoch(train) [80][250/293] lr: 5.000000e-04 eta: 7:00:28 time: 0.755343 data_time: 0.094504 memory: 21676 loss_kpt: 0.000582 acc_pose: 0.827544 loss: 0.000582 2022/09/16 17:44:36 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 17:44:36 - mmengine - INFO - Saving checkpoint at 80 epochs 2022/09/16 17:44:52 - mmengine - INFO - Epoch(val) [80][50/407] eta: 0:01:19 time: 0.221943 data_time: 0.015467 memory: 21676 2022/09/16 17:45:03 - mmengine - INFO - Epoch(val) [80][100/407] eta: 0:01:04 time: 0.209497 data_time: 0.008984 memory: 1375 2022/09/16 17:45:13 - mmengine - INFO - Epoch(val) [80][150/407] eta: 0:00:54 time: 0.210300 data_time: 0.008542 memory: 1375 2022/09/16 17:45:23 - mmengine - INFO - Epoch(val) [80][200/407] eta: 0:00:43 time: 0.208989 data_time: 0.008278 memory: 1375 2022/09/16 17:45:34 - mmengine - INFO - Epoch(val) [80][250/407] eta: 0:00:34 time: 0.219106 data_time: 0.008978 memory: 1375 2022/09/16 17:45:45 - mmengine - INFO - Epoch(val) [80][300/407] eta: 0:00:22 time: 0.211538 data_time: 0.008917 memory: 1375 2022/09/16 17:45:56 - mmengine - INFO - Epoch(val) [80][350/407] eta: 0:00:12 time: 0.210635 data_time: 0.008359 memory: 1375 2022/09/16 17:46:06 - mmengine - INFO - Epoch(val) [80][400/407] eta: 0:00:01 time: 0.206684 data_time: 0.008082 memory: 1375 2022/09/16 17:46:41 - mmengine - INFO - Evaluating CocoMetric... 2022/09/16 17:46:55 - mmengine - INFO - Epoch(val) [80][407/407] coco/AP: 0.748185 coco/AP .5: 0.900086 coco/AP .75: 0.811346 coco/AP (M): 0.708928 coco/AP (L): 0.817818 coco/AR: 0.796552 coco/AR .5: 0.937185 coco/AR .75: 0.853275 coco/AR (M): 0.753647 coco/AR (L): 0.858677 2022/09/16 17:46:55 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220916/dark_w32_384/best_coco/AP_epoch_70.pth is removed 2022/09/16 17:46:58 - mmengine - INFO - The best checkpoint with 0.7482 coco/AP at 80 epoch is saved to best_coco/AP_epoch_80.pth. 2022/09/16 17:47:37 - mmengine - INFO - Epoch(train) [81][50/293] lr: 5.000000e-04 eta: 6:58:50 time: 0.791795 data_time: 0.104624 memory: 21676 loss_kpt: 0.000588 acc_pose: 0.843165 loss: 0.000588 2022/09/16 17:48:17 - mmengine - INFO - Epoch(train) [81][100/293] lr: 5.000000e-04 eta: 6:58:28 time: 0.788167 data_time: 0.096656 memory: 21676 loss_kpt: 0.000576 acc_pose: 0.829516 loss: 0.000576 2022/09/16 17:48:56 - mmengine - INFO - Epoch(train) [81][150/293] lr: 5.000000e-04 eta: 6:58:05 time: 0.785295 data_time: 0.096617 memory: 21676 loss_kpt: 0.000584 acc_pose: 0.847383 loss: 0.000584 2022/09/16 17:49:36 - mmengine - INFO - Epoch(train) [81][200/293] lr: 5.000000e-04 eta: 6:57:42 time: 0.795873 data_time: 0.095588 memory: 21676 loss_kpt: 0.000586 acc_pose: 0.814590 loss: 0.000586 2022/09/16 17:50:15 - mmengine - INFO - Epoch(train) [81][250/293] lr: 5.000000e-04 eta: 6:57:19 time: 0.777556 data_time: 0.095327 memory: 21676 loss_kpt: 0.000589 acc_pose: 0.758209 loss: 0.000589 2022/09/16 17:50:47 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 17:50:47 - mmengine - INFO - Saving checkpoint at 81 epochs 2022/09/16 17:51:31 - mmengine - INFO - Epoch(train) [82][50/293] lr: 5.000000e-04 eta: 6:55:42 time: 0.782441 data_time: 0.111785 memory: 21676 loss_kpt: 0.000579 acc_pose: 0.839362 loss: 0.000579 2022/09/16 17:52:09 - mmengine - INFO - Epoch(train) [82][100/293] lr: 5.000000e-04 eta: 6:55:17 time: 0.770393 data_time: 0.093924 memory: 21676 loss_kpt: 0.000595 acc_pose: 0.833457 loss: 0.000595 2022/09/16 17:52:47 - mmengine - INFO - Epoch(train) [82][150/293] lr: 5.000000e-04 eta: 6:54:51 time: 0.750684 data_time: 0.100296 memory: 21676 loss_kpt: 0.000580 acc_pose: 0.762815 loss: 0.000580 2022/09/16 17:53:26 - mmengine - INFO - Epoch(train) [82][200/293] lr: 5.000000e-04 eta: 6:54:27 time: 0.775191 data_time: 0.097168 memory: 21676 loss_kpt: 0.000577 acc_pose: 0.847800 loss: 0.000577 2022/09/16 17:54:03 - mmengine - INFO - Epoch(train) [82][250/293] lr: 5.000000e-04 eta: 6:54:02 time: 0.757833 data_time: 0.097194 memory: 21676 loss_kpt: 0.000586 acc_pose: 0.847171 loss: 0.000586 2022/09/16 17:54:17 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 17:54:35 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 17:54:36 - mmengine - INFO - Saving checkpoint at 82 epochs 2022/09/16 17:55:20 - mmengine - INFO - Epoch(train) [83][50/293] lr: 5.000000e-04 eta: 6:52:26 time: 0.795321 data_time: 0.113508 memory: 21676 loss_kpt: 0.000587 acc_pose: 0.805257 loss: 0.000587 2022/09/16 17:55:59 - mmengine - INFO - Epoch(train) [83][100/293] lr: 5.000000e-04 eta: 6:52:03 time: 0.789010 data_time: 0.102949 memory: 21676 loss_kpt: 0.000573 acc_pose: 0.805857 loss: 0.000573 2022/09/16 17:56:39 - mmengine - INFO - Epoch(train) [83][150/293] lr: 5.000000e-04 eta: 6:51:41 time: 0.802710 data_time: 0.096455 memory: 21676 loss_kpt: 0.000578 acc_pose: 0.876934 loss: 0.000578 2022/09/16 17:57:18 - mmengine - INFO - Epoch(train) [83][200/293] lr: 5.000000e-04 eta: 6:51:16 time: 0.769793 data_time: 0.097015 memory: 21676 loss_kpt: 0.000582 acc_pose: 0.871933 loss: 0.000582 2022/09/16 17:57:56 - mmengine - INFO - Epoch(train) [83][250/293] lr: 5.000000e-04 eta: 6:50:51 time: 0.760732 data_time: 0.093019 memory: 21676 loss_kpt: 0.000582 acc_pose: 0.857066 loss: 0.000582 2022/09/16 17:58:28 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 17:58:28 - mmengine - INFO - Saving checkpoint at 83 epochs 2022/09/16 17:59:13 - mmengine - INFO - Epoch(train) [84][50/293] lr: 5.000000e-04 eta: 6:49:16 time: 0.794607 data_time: 0.108553 memory: 21676 loss_kpt: 0.000574 acc_pose: 0.845663 loss: 0.000574 2022/09/16 17:59:52 - mmengine - INFO - Epoch(train) [84][100/293] lr: 5.000000e-04 eta: 6:48:53 time: 0.788851 data_time: 0.097113 memory: 21676 loss_kpt: 0.000582 acc_pose: 0.859493 loss: 0.000582 2022/09/16 18:00:34 - mmengine - INFO - Epoch(train) [84][150/293] lr: 5.000000e-04 eta: 6:48:33 time: 0.839136 data_time: 0.107024 memory: 21676 loss_kpt: 0.000597 acc_pose: 0.852715 loss: 0.000597 2022/09/16 18:01:13 - mmengine - INFO - Epoch(train) [84][200/293] lr: 5.000000e-04 eta: 6:48:09 time: 0.780619 data_time: 0.095326 memory: 21676 loss_kpt: 0.000572 acc_pose: 0.834241 loss: 0.000572 2022/09/16 18:01:52 - mmengine - INFO - Epoch(train) [84][250/293] lr: 5.000000e-04 eta: 6:47:44 time: 0.768787 data_time: 0.097187 memory: 21676 loss_kpt: 0.000581 acc_pose: 0.851817 loss: 0.000581 2022/09/16 18:02:24 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 18:02:24 - mmengine - INFO - Saving checkpoint at 84 epochs 2022/09/16 18:03:08 - mmengine - INFO - Epoch(train) [85][50/293] lr: 5.000000e-04 eta: 6:46:10 time: 0.797507 data_time: 0.108800 memory: 21676 loss_kpt: 0.000596 acc_pose: 0.828057 loss: 0.000596 2022/09/16 18:03:47 - mmengine - INFO - Epoch(train) [85][100/293] lr: 5.000000e-04 eta: 6:45:46 time: 0.787083 data_time: 0.094965 memory: 21676 loss_kpt: 0.000579 acc_pose: 0.812235 loss: 0.000579 2022/09/16 18:04:27 - mmengine - INFO - Epoch(train) [85][150/293] lr: 5.000000e-04 eta: 6:45:23 time: 0.788945 data_time: 0.095600 memory: 21676 loss_kpt: 0.000575 acc_pose: 0.841068 loss: 0.000575 2022/09/16 18:05:05 - mmengine - INFO - Epoch(train) [85][200/293] lr: 5.000000e-04 eta: 6:44:57 time: 0.761812 data_time: 0.098622 memory: 21676 loss_kpt: 0.000577 acc_pose: 0.815503 loss: 0.000577 2022/09/16 18:05:43 - mmengine - INFO - Epoch(train) [85][250/293] lr: 5.000000e-04 eta: 6:44:31 time: 0.759609 data_time: 0.096428 memory: 21676 loss_kpt: 0.000571 acc_pose: 0.861323 loss: 0.000571 2022/09/16 18:06:15 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 18:06:15 - mmengine - INFO - Saving checkpoint at 85 epochs 2022/09/16 18:06:59 - mmengine - INFO - Epoch(train) [86][50/293] lr: 5.000000e-04 eta: 6:42:58 time: 0.794516 data_time: 0.112717 memory: 21676 loss_kpt: 0.000592 acc_pose: 0.835237 loss: 0.000592 2022/09/16 18:07:34 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 18:07:38 - mmengine - INFO - Epoch(train) [86][100/293] lr: 5.000000e-04 eta: 6:42:33 time: 0.779984 data_time: 0.099722 memory: 21676 loss_kpt: 0.000582 acc_pose: 0.847972 loss: 0.000582 2022/09/16 18:08:17 - mmengine - INFO - Epoch(train) [86][150/293] lr: 5.000000e-04 eta: 6:42:08 time: 0.770779 data_time: 0.103892 memory: 21676 loss_kpt: 0.000586 acc_pose: 0.811214 loss: 0.000586 2022/09/16 18:08:55 - mmengine - INFO - Epoch(train) [86][200/293] lr: 5.000000e-04 eta: 6:41:43 time: 0.775812 data_time: 0.101145 memory: 21676 loss_kpt: 0.000583 acc_pose: 0.832339 loss: 0.000583 2022/09/16 18:09:34 - mmengine - INFO - Epoch(train) [86][250/293] lr: 5.000000e-04 eta: 6:41:19 time: 0.781579 data_time: 0.106264 memory: 21676 loss_kpt: 0.000590 acc_pose: 0.835008 loss: 0.000590 2022/09/16 18:10:06 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 18:10:06 - mmengine - INFO - Saving checkpoint at 86 epochs 2022/09/16 18:10:51 - mmengine - INFO - Epoch(train) [87][50/293] lr: 5.000000e-04 eta: 6:39:46 time: 0.792381 data_time: 0.108057 memory: 21676 loss_kpt: 0.000567 acc_pose: 0.853669 loss: 0.000567 2022/09/16 18:11:29 - mmengine - INFO - Epoch(train) [87][100/293] lr: 5.000000e-04 eta: 6:39:20 time: 0.760539 data_time: 0.095668 memory: 21676 loss_kpt: 0.000590 acc_pose: 0.832486 loss: 0.000590 2022/09/16 18:12:07 - mmengine - INFO - Epoch(train) [87][150/293] lr: 5.000000e-04 eta: 6:38:54 time: 0.758871 data_time: 0.095516 memory: 21676 loss_kpt: 0.000581 acc_pose: 0.857067 loss: 0.000581 2022/09/16 18:12:45 - mmengine - INFO - Epoch(train) [87][200/293] lr: 5.000000e-04 eta: 6:38:29 time: 0.775285 data_time: 0.102914 memory: 21676 loss_kpt: 0.000575 acc_pose: 0.843230 loss: 0.000575 2022/09/16 18:13:23 - mmengine - INFO - Epoch(train) [87][250/293] lr: 5.000000e-04 eta: 6:38:02 time: 0.751841 data_time: 0.094933 memory: 21676 loss_kpt: 0.000591 acc_pose: 0.825559 loss: 0.000591 2022/09/16 18:13:55 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 18:13:55 - mmengine - INFO - Saving checkpoint at 87 epochs 2022/09/16 18:14:40 - mmengine - INFO - Epoch(train) [88][50/293] lr: 5.000000e-04 eta: 6:36:30 time: 0.793111 data_time: 0.104602 memory: 21676 loss_kpt: 0.000582 acc_pose: 0.815439 loss: 0.000582 2022/09/16 18:15:19 - mmengine - INFO - Epoch(train) [88][100/293] lr: 5.000000e-04 eta: 6:36:05 time: 0.783406 data_time: 0.098718 memory: 21676 loss_kpt: 0.000581 acc_pose: 0.810192 loss: 0.000581 2022/09/16 18:15:58 - mmengine - INFO - Epoch(train) [88][150/293] lr: 5.000000e-04 eta: 6:35:41 time: 0.792650 data_time: 0.109767 memory: 21676 loss_kpt: 0.000588 acc_pose: 0.822130 loss: 0.000588 2022/09/16 18:16:37 - mmengine - INFO - Epoch(train) [88][200/293] lr: 5.000000e-04 eta: 6:35:16 time: 0.766513 data_time: 0.100105 memory: 21676 loss_kpt: 0.000590 acc_pose: 0.894411 loss: 0.000590 2022/09/16 18:17:14 - mmengine - INFO - Epoch(train) [88][250/293] lr: 5.000000e-04 eta: 6:34:49 time: 0.753448 data_time: 0.091174 memory: 21676 loss_kpt: 0.000595 acc_pose: 0.817014 loss: 0.000595 2022/09/16 18:17:47 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 18:17:47 - mmengine - INFO - Saving checkpoint at 88 epochs 2022/09/16 18:18:31 - mmengine - INFO - Epoch(train) [89][50/293] lr: 5.000000e-04 eta: 6:33:17 time: 0.786882 data_time: 0.103211 memory: 21676 loss_kpt: 0.000578 acc_pose: 0.853218 loss: 0.000578 2022/09/16 18:19:10 - mmengine - INFO - Epoch(train) [89][100/293] lr: 5.000000e-04 eta: 6:32:52 time: 0.780154 data_time: 0.095239 memory: 21676 loss_kpt: 0.000579 acc_pose: 0.833140 loss: 0.000579 2022/09/16 18:19:48 - mmengine - INFO - Epoch(train) [89][150/293] lr: 5.000000e-04 eta: 6:32:27 time: 0.774483 data_time: 0.095724 memory: 21676 loss_kpt: 0.000578 acc_pose: 0.840318 loss: 0.000578 2022/09/16 18:20:28 - mmengine - INFO - Epoch(train) [89][200/293] lr: 5.000000e-04 eta: 6:32:02 time: 0.791436 data_time: 0.099746 memory: 21676 loss_kpt: 0.000575 acc_pose: 0.876220 loss: 0.000575 2022/09/16 18:20:40 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 18:21:06 - mmengine - INFO - Epoch(train) [89][250/293] lr: 5.000000e-04 eta: 6:31:37 time: 0.771309 data_time: 0.095880 memory: 21676 loss_kpt: 0.000583 acc_pose: 0.814646 loss: 0.000583 2022/09/16 18:21:39 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 18:21:39 - mmengine - INFO - Saving checkpoint at 89 epochs 2022/09/16 18:22:24 - mmengine - INFO - Epoch(train) [90][50/293] lr: 5.000000e-04 eta: 6:30:06 time: 0.795624 data_time: 0.104434 memory: 21676 loss_kpt: 0.000575 acc_pose: 0.849581 loss: 0.000575 2022/09/16 18:23:03 - mmengine - INFO - Epoch(train) [90][100/293] lr: 5.000000e-04 eta: 6:29:41 time: 0.783185 data_time: 0.096682 memory: 21676 loss_kpt: 0.000563 acc_pose: 0.844118 loss: 0.000563 2022/09/16 18:23:42 - mmengine - INFO - Epoch(train) [90][150/293] lr: 5.000000e-04 eta: 6:29:16 time: 0.785328 data_time: 0.102312 memory: 21676 loss_kpt: 0.000574 acc_pose: 0.833544 loss: 0.000574 2022/09/16 18:24:22 - mmengine - INFO - Epoch(train) [90][200/293] lr: 5.000000e-04 eta: 6:28:51 time: 0.786770 data_time: 0.098672 memory: 21676 loss_kpt: 0.000575 acc_pose: 0.857131 loss: 0.000575 2022/09/16 18:25:00 - mmengine - INFO - Epoch(train) [90][250/293] lr: 5.000000e-04 eta: 6:28:26 time: 0.768412 data_time: 0.095386 memory: 21676 loss_kpt: 0.000582 acc_pose: 0.804473 loss: 0.000582 2022/09/16 18:25:32 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 18:25:32 - mmengine - INFO - Saving checkpoint at 90 epochs 2022/09/16 18:25:48 - mmengine - INFO - Epoch(val) [90][50/407] eta: 0:01:17 time: 0.215819 data_time: 0.013144 memory: 21676 2022/09/16 18:25:59 - mmengine - INFO - Epoch(val) [90][100/407] eta: 0:01:05 time: 0.211863 data_time: 0.008910 memory: 1375 2022/09/16 18:26:09 - mmengine - INFO - Epoch(val) [90][150/407] eta: 0:00:54 time: 0.213618 data_time: 0.009161 memory: 1375 2022/09/16 18:26:20 - mmengine - INFO - Epoch(val) [90][200/407] eta: 0:00:43 time: 0.212172 data_time: 0.009012 memory: 1375 2022/09/16 18:26:31 - mmengine - INFO - Epoch(val) [90][250/407] eta: 0:00:33 time: 0.215130 data_time: 0.008617 memory: 1375 2022/09/16 18:26:41 - mmengine - INFO - Epoch(val) [90][300/407] eta: 0:00:22 time: 0.211615 data_time: 0.008840 memory: 1375 2022/09/16 18:26:52 - mmengine - INFO - Epoch(val) [90][350/407] eta: 0:00:11 time: 0.210017 data_time: 0.008992 memory: 1375 2022/09/16 18:27:02 - mmengine - INFO - Epoch(val) [90][400/407] eta: 0:00:01 time: 0.208766 data_time: 0.008249 memory: 1375 2022/09/16 18:27:38 - mmengine - INFO - Evaluating CocoMetric... 2022/09/16 18:27:52 - mmengine - INFO - Epoch(val) [90][407/407] coco/AP: 0.747421 coco/AP .5: 0.898224 coco/AP .75: 0.814413 coco/AP (M): 0.707366 coco/AP (L): 0.817726 coco/AR: 0.797213 coco/AR .5: 0.935926 coco/AR .75: 0.857210 coco/AR (M): 0.753865 coco/AR (L): 0.859941 2022/09/16 18:28:32 - mmengine - INFO - Epoch(train) [91][50/293] lr: 5.000000e-04 eta: 6:26:55 time: 0.793330 data_time: 0.107234 memory: 21676 loss_kpt: 0.000579 acc_pose: 0.780134 loss: 0.000579 2022/09/16 18:29:11 - mmengine - INFO - Epoch(train) [91][100/293] lr: 5.000000e-04 eta: 6:26:29 time: 0.776600 data_time: 0.102468 memory: 21676 loss_kpt: 0.000583 acc_pose: 0.870589 loss: 0.000583 2022/09/16 18:29:49 - mmengine - INFO - Epoch(train) [91][150/293] lr: 5.000000e-04 eta: 6:26:04 time: 0.778669 data_time: 0.104584 memory: 21676 loss_kpt: 0.000574 acc_pose: 0.852639 loss: 0.000574 2022/09/16 18:30:28 - mmengine - INFO - Epoch(train) [91][200/293] lr: 5.000000e-04 eta: 6:25:38 time: 0.772224 data_time: 0.104186 memory: 21676 loss_kpt: 0.000567 acc_pose: 0.871247 loss: 0.000567 2022/09/16 18:31:07 - mmengine - INFO - Epoch(train) [91][250/293] lr: 5.000000e-04 eta: 6:25:13 time: 0.774339 data_time: 0.101789 memory: 21676 loss_kpt: 0.000581 acc_pose: 0.834780 loss: 0.000581 2022/09/16 18:31:39 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 18:31:39 - mmengine - INFO - Saving checkpoint at 91 epochs 2022/09/16 18:32:23 - mmengine - INFO - Epoch(train) [92][50/293] lr: 5.000000e-04 eta: 6:23:42 time: 0.782857 data_time: 0.109203 memory: 21676 loss_kpt: 0.000577 acc_pose: 0.859428 loss: 0.000577 2022/09/16 18:33:03 - mmengine - INFO - Epoch(train) [92][100/293] lr: 5.000000e-04 eta: 6:23:17 time: 0.785920 data_time: 0.098475 memory: 21676 loss_kpt: 0.000582 acc_pose: 0.850350 loss: 0.000582 2022/09/16 18:33:42 - mmengine - INFO - Epoch(train) [92][150/293] lr: 5.000000e-04 eta: 6:22:52 time: 0.782630 data_time: 0.097484 memory: 21676 loss_kpt: 0.000591 acc_pose: 0.815482 loss: 0.000591 2022/09/16 18:34:20 - mmengine - INFO - Epoch(train) [92][200/293] lr: 5.000000e-04 eta: 6:22:26 time: 0.774746 data_time: 0.099032 memory: 21676 loss_kpt: 0.000572 acc_pose: 0.826255 loss: 0.000572 2022/09/16 18:34:59 - mmengine - INFO - Epoch(train) [92][250/293] lr: 5.000000e-04 eta: 6:21:59 time: 0.763333 data_time: 0.096161 memory: 21676 loss_kpt: 0.000558 acc_pose: 0.864545 loss: 0.000558 2022/09/16 18:35:30 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 18:35:31 - mmengine - INFO - Saving checkpoint at 92 epochs 2022/09/16 18:36:10 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 18:36:14 - mmengine - INFO - Epoch(train) [93][50/293] lr: 5.000000e-04 eta: 6:20:29 time: 0.786130 data_time: 0.103414 memory: 21676 loss_kpt: 0.000574 acc_pose: 0.848305 loss: 0.000574 2022/09/16 18:36:53 - mmengine - INFO - Epoch(train) [93][100/293] lr: 5.000000e-04 eta: 6:20:03 time: 0.776341 data_time: 0.093714 memory: 21676 loss_kpt: 0.000573 acc_pose: 0.846369 loss: 0.000573 2022/09/16 18:37:32 - mmengine - INFO - Epoch(train) [93][150/293] lr: 5.000000e-04 eta: 6:19:38 time: 0.775423 data_time: 0.091996 memory: 21676 loss_kpt: 0.000568 acc_pose: 0.871133 loss: 0.000568 2022/09/16 18:38:11 - mmengine - INFO - Epoch(train) [93][200/293] lr: 5.000000e-04 eta: 6:19:12 time: 0.772329 data_time: 0.092649 memory: 21676 loss_kpt: 0.000588 acc_pose: 0.815332 loss: 0.000588 2022/09/16 18:38:50 - mmengine - INFO - Epoch(train) [93][250/293] lr: 5.000000e-04 eta: 6:18:46 time: 0.784740 data_time: 0.097312 memory: 21676 loss_kpt: 0.000567 acc_pose: 0.772476 loss: 0.000567 2022/09/16 18:39:22 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 18:39:22 - mmengine - INFO - Saving checkpoint at 93 epochs 2022/09/16 18:40:06 - mmengine - INFO - Epoch(train) [94][50/293] lr: 5.000000e-04 eta: 6:17:17 time: 0.787202 data_time: 0.109778 memory: 21676 loss_kpt: 0.000558 acc_pose: 0.899175 loss: 0.000558 2022/09/16 18:40:45 - mmengine - INFO - Epoch(train) [94][100/293] lr: 5.000000e-04 eta: 6:16:52 time: 0.786845 data_time: 0.099631 memory: 21676 loss_kpt: 0.000584 acc_pose: 0.856776 loss: 0.000584 2022/09/16 18:41:23 - mmengine - INFO - Epoch(train) [94][150/293] lr: 5.000000e-04 eta: 6:16:25 time: 0.766991 data_time: 0.098640 memory: 21676 loss_kpt: 0.000558 acc_pose: 0.852772 loss: 0.000558 2022/09/16 18:42:02 - mmengine - INFO - Epoch(train) [94][200/293] lr: 5.000000e-04 eta: 6:15:58 time: 0.765212 data_time: 0.099777 memory: 21676 loss_kpt: 0.000559 acc_pose: 0.852838 loss: 0.000559 2022/09/16 18:42:40 - mmengine - INFO - Epoch(train) [94][250/293] lr: 5.000000e-04 eta: 6:15:32 time: 0.770392 data_time: 0.095991 memory: 21676 loss_kpt: 0.000558 acc_pose: 0.831804 loss: 0.000558 2022/09/16 18:43:13 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 18:43:13 - mmengine - INFO - Saving checkpoint at 94 epochs 2022/09/16 18:43:57 - mmengine - INFO - Epoch(train) [95][50/293] lr: 5.000000e-04 eta: 6:14:03 time: 0.788532 data_time: 0.109020 memory: 21676 loss_kpt: 0.000569 acc_pose: 0.806204 loss: 0.000569 2022/09/16 18:44:35 - mmengine - INFO - Epoch(train) [95][100/293] lr: 5.000000e-04 eta: 6:13:37 time: 0.773207 data_time: 0.095415 memory: 21676 loss_kpt: 0.000573 acc_pose: 0.827230 loss: 0.000573 2022/09/16 18:45:13 - mmengine - INFO - Epoch(train) [95][150/293] lr: 5.000000e-04 eta: 6:13:09 time: 0.746352 data_time: 0.092856 memory: 21676 loss_kpt: 0.000572 acc_pose: 0.810483 loss: 0.000572 2022/09/16 18:45:51 - mmengine - INFO - Epoch(train) [95][200/293] lr: 5.000000e-04 eta: 6:12:42 time: 0.761225 data_time: 0.092783 memory: 21676 loss_kpt: 0.000572 acc_pose: 0.850193 loss: 0.000572 2022/09/16 18:46:28 - mmengine - INFO - Epoch(train) [95][250/293] lr: 5.000000e-04 eta: 6:12:14 time: 0.748429 data_time: 0.094553 memory: 21676 loss_kpt: 0.000583 acc_pose: 0.869155 loss: 0.000583 2022/09/16 18:47:01 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 18:47:01 - mmengine - INFO - Saving checkpoint at 95 epochs 2022/09/16 18:47:44 - mmengine - INFO - Epoch(train) [96][50/293] lr: 5.000000e-04 eta: 6:10:45 time: 0.774271 data_time: 0.107990 memory: 21676 loss_kpt: 0.000575 acc_pose: 0.785627 loss: 0.000575 2022/09/16 18:48:23 - mmengine - INFO - Epoch(train) [96][100/293] lr: 5.000000e-04 eta: 6:10:19 time: 0.774874 data_time: 0.097779 memory: 21676 loss_kpt: 0.000555 acc_pose: 0.839448 loss: 0.000555 2022/09/16 18:49:02 - mmengine - INFO - Epoch(train) [96][150/293] lr: 5.000000e-04 eta: 6:09:53 time: 0.777932 data_time: 0.091947 memory: 21676 loss_kpt: 0.000571 acc_pose: 0.796113 loss: 0.000571 2022/09/16 18:49:14 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 18:49:40 - mmengine - INFO - Epoch(train) [96][200/293] lr: 5.000000e-04 eta: 6:09:26 time: 0.769100 data_time: 0.099090 memory: 21676 loss_kpt: 0.000581 acc_pose: 0.859549 loss: 0.000581 2022/09/16 18:50:19 - mmengine - INFO - Epoch(train) [96][250/293] lr: 5.000000e-04 eta: 6:08:59 time: 0.766852 data_time: 0.093072 memory: 21676 loss_kpt: 0.000592 acc_pose: 0.846262 loss: 0.000592 2022/09/16 18:50:51 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 18:50:51 - mmengine - INFO - Saving checkpoint at 96 epochs 2022/09/16 18:51:34 - mmengine - INFO - Epoch(train) [97][50/293] lr: 5.000000e-04 eta: 6:07:31 time: 0.778950 data_time: 0.105091 memory: 21676 loss_kpt: 0.000598 acc_pose: 0.789573 loss: 0.000598 2022/09/16 18:52:13 - mmengine - INFO - Epoch(train) [97][100/293] lr: 5.000000e-04 eta: 6:07:05 time: 0.780552 data_time: 0.096421 memory: 21676 loss_kpt: 0.000576 acc_pose: 0.844539 loss: 0.000576 2022/09/16 18:52:51 - mmengine - INFO - Epoch(train) [97][150/293] lr: 5.000000e-04 eta: 6:06:38 time: 0.768049 data_time: 0.092096 memory: 21676 loss_kpt: 0.000576 acc_pose: 0.849045 loss: 0.000576 2022/09/16 18:53:30 - mmengine - INFO - Epoch(train) [97][200/293] lr: 5.000000e-04 eta: 6:06:12 time: 0.777531 data_time: 0.094704 memory: 21676 loss_kpt: 0.000571 acc_pose: 0.866580 loss: 0.000571 2022/09/16 18:54:08 - mmengine - INFO - Epoch(train) [97][250/293] lr: 5.000000e-04 eta: 6:05:44 time: 0.757745 data_time: 0.103597 memory: 21676 loss_kpt: 0.000575 acc_pose: 0.842139 loss: 0.000575 2022/09/16 18:54:41 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 18:54:41 - mmengine - INFO - Saving checkpoint at 97 epochs 2022/09/16 18:55:24 - mmengine - INFO - Epoch(train) [98][50/293] lr: 5.000000e-04 eta: 6:04:16 time: 0.778165 data_time: 0.107417 memory: 21676 loss_kpt: 0.000577 acc_pose: 0.829245 loss: 0.000577 2022/09/16 18:56:02 - mmengine - INFO - Epoch(train) [98][100/293] lr: 5.000000e-04 eta: 6:03:49 time: 0.760636 data_time: 0.095880 memory: 21676 loss_kpt: 0.000588 acc_pose: 0.859096 loss: 0.000588 2022/09/16 18:56:40 - mmengine - INFO - Epoch(train) [98][150/293] lr: 5.000000e-04 eta: 6:03:22 time: 0.760582 data_time: 0.096582 memory: 21676 loss_kpt: 0.000589 acc_pose: 0.847393 loss: 0.000589 2022/09/16 18:57:18 - mmengine - INFO - Epoch(train) [98][200/293] lr: 5.000000e-04 eta: 6:02:54 time: 0.748672 data_time: 0.096493 memory: 21676 loss_kpt: 0.000571 acc_pose: 0.840344 loss: 0.000571 2022/09/16 18:57:55 - mmengine - INFO - Epoch(train) [98][250/293] lr: 5.000000e-04 eta: 6:02:26 time: 0.756617 data_time: 0.091689 memory: 21676 loss_kpt: 0.000553 acc_pose: 0.815759 loss: 0.000553 2022/09/16 18:58:28 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 18:58:28 - mmengine - INFO - Saving checkpoint at 98 epochs 2022/09/16 18:59:12 - mmengine - INFO - Epoch(train) [99][50/293] lr: 5.000000e-04 eta: 6:00:59 time: 0.787597 data_time: 0.108889 memory: 21676 loss_kpt: 0.000561 acc_pose: 0.868979 loss: 0.000561 2022/09/16 18:59:49 - mmengine - INFO - Epoch(train) [99][100/293] lr: 5.000000e-04 eta: 6:00:32 time: 0.754984 data_time: 0.092311 memory: 21676 loss_kpt: 0.000558 acc_pose: 0.827797 loss: 0.000558 2022/09/16 19:00:27 - mmengine - INFO - Epoch(train) [99][150/293] lr: 5.000000e-04 eta: 6:00:04 time: 0.758300 data_time: 0.096178 memory: 21676 loss_kpt: 0.000565 acc_pose: 0.882754 loss: 0.000565 2022/09/16 19:01:05 - mmengine - INFO - Epoch(train) [99][200/293] lr: 5.000000e-04 eta: 5:59:36 time: 0.751599 data_time: 0.093099 memory: 21676 loss_kpt: 0.000572 acc_pose: 0.854366 loss: 0.000572 2022/09/16 19:01:43 - mmengine - INFO - Epoch(train) [99][250/293] lr: 5.000000e-04 eta: 5:59:09 time: 0.760793 data_time: 0.091881 memory: 21676 loss_kpt: 0.000574 acc_pose: 0.838865 loss: 0.000574 2022/09/16 19:02:11 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 19:02:16 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 19:02:16 - mmengine - INFO - Saving checkpoint at 99 epochs 2022/09/16 19:03:00 - mmengine - INFO - Epoch(train) [100][50/293] lr: 5.000000e-04 eta: 5:57:43 time: 0.796763 data_time: 0.109846 memory: 21676 loss_kpt: 0.000571 acc_pose: 0.784141 loss: 0.000571 2022/09/16 19:03:39 - mmengine - INFO - Epoch(train) [100][100/293] lr: 5.000000e-04 eta: 5:57:16 time: 0.779757 data_time: 0.103277 memory: 21676 loss_kpt: 0.000554 acc_pose: 0.860691 loss: 0.000554 2022/09/16 19:04:18 - mmengine - INFO - Epoch(train) [100][150/293] lr: 5.000000e-04 eta: 5:56:50 time: 0.776553 data_time: 0.104101 memory: 21676 loss_kpt: 0.000569 acc_pose: 0.802704 loss: 0.000569 2022/09/16 19:04:56 - mmengine - INFO - Epoch(train) [100][200/293] lr: 5.000000e-04 eta: 5:56:23 time: 0.769642 data_time: 0.103496 memory: 21676 loss_kpt: 0.000571 acc_pose: 0.837701 loss: 0.000571 2022/09/16 19:05:35 - mmengine - INFO - Epoch(train) [100][250/293] lr: 5.000000e-04 eta: 5:55:55 time: 0.768827 data_time: 0.104072 memory: 21676 loss_kpt: 0.000568 acc_pose: 0.847098 loss: 0.000568 2022/09/16 19:06:07 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 19:06:07 - mmengine - INFO - Saving checkpoint at 100 epochs 2022/09/16 19:06:23 - mmengine - INFO - Epoch(val) [100][50/407] eta: 0:01:19 time: 0.223181 data_time: 0.015776 memory: 21676 2022/09/16 19:06:34 - mmengine - INFO - Epoch(val) [100][100/407] eta: 0:01:05 time: 0.212689 data_time: 0.012010 memory: 1375 2022/09/16 19:06:44 - mmengine - INFO - Epoch(val) [100][150/407] eta: 0:00:54 time: 0.211652 data_time: 0.009347 memory: 1375 2022/09/16 19:06:55 - mmengine - INFO - Epoch(val) [100][200/407] eta: 0:00:43 time: 0.210385 data_time: 0.009089 memory: 1375 2022/09/16 19:07:05 - mmengine - INFO - Epoch(val) [100][250/407] eta: 0:00:33 time: 0.211354 data_time: 0.008768 memory: 1375 2022/09/16 19:07:16 - mmengine - INFO - Epoch(val) [100][300/407] eta: 0:00:22 time: 0.209808 data_time: 0.008386 memory: 1375 2022/09/16 19:07:26 - mmengine - INFO - Epoch(val) [100][350/407] eta: 0:00:12 time: 0.211845 data_time: 0.008796 memory: 1375 2022/09/16 19:07:37 - mmengine - INFO - Epoch(val) [100][400/407] eta: 0:00:01 time: 0.206975 data_time: 0.007936 memory: 1375 2022/09/16 19:08:13 - mmengine - INFO - Evaluating CocoMetric... 2022/09/16 19:08:26 - mmengine - INFO - Epoch(val) [100][407/407] coco/AP: 0.749969 coco/AP .5: 0.899015 coco/AP .75: 0.814007 coco/AP (M): 0.710956 coco/AP (L): 0.819659 coco/AR: 0.799575 coco/AR .5: 0.937500 coco/AR .75: 0.857210 coco/AR (M): 0.756460 coco/AR (L): 0.862096 2022/09/16 19:08:27 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220916/dark_w32_384/best_coco/AP_epoch_80.pth is removed 2022/09/16 19:08:30 - mmengine - INFO - The best checkpoint with 0.7500 coco/AP at 100 epoch is saved to best_coco/AP_epoch_100.pth. 2022/09/16 19:09:09 - mmengine - INFO - Epoch(train) [101][50/293] lr: 5.000000e-04 eta: 5:54:30 time: 0.794722 data_time: 0.104309 memory: 21676 loss_kpt: 0.000569 acc_pose: 0.815513 loss: 0.000569 2022/09/16 19:09:49 - mmengine - INFO - Epoch(train) [101][100/293] lr: 5.000000e-04 eta: 5:54:04 time: 0.782811 data_time: 0.096191 memory: 21676 loss_kpt: 0.000571 acc_pose: 0.845052 loss: 0.000571 2022/09/16 19:10:27 - mmengine - INFO - Epoch(train) [101][150/293] lr: 5.000000e-04 eta: 5:53:37 time: 0.779737 data_time: 0.100057 memory: 21676 loss_kpt: 0.000579 acc_pose: 0.815441 loss: 0.000579 2022/09/16 19:11:06 - mmengine - INFO - Epoch(train) [101][200/293] lr: 5.000000e-04 eta: 5:53:10 time: 0.766029 data_time: 0.098426 memory: 21676 loss_kpt: 0.000565 acc_pose: 0.878007 loss: 0.000565 2022/09/16 19:11:43 - mmengine - INFO - Epoch(train) [101][250/293] lr: 5.000000e-04 eta: 5:52:41 time: 0.747470 data_time: 0.095260 memory: 21676 loss_kpt: 0.000576 acc_pose: 0.833080 loss: 0.000576 2022/09/16 19:12:16 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 19:12:16 - mmengine - INFO - Saving checkpoint at 101 epochs 2022/09/16 19:13:00 - mmengine - INFO - Epoch(train) [102][50/293] lr: 5.000000e-04 eta: 5:51:16 time: 0.788413 data_time: 0.109286 memory: 21676 loss_kpt: 0.000552 acc_pose: 0.825148 loss: 0.000552 2022/09/16 19:13:38 - mmengine - INFO - Epoch(train) [102][100/293] lr: 5.000000e-04 eta: 5:50:48 time: 0.766553 data_time: 0.099349 memory: 21676 loss_kpt: 0.000566 acc_pose: 0.806352 loss: 0.000566 2022/09/16 19:14:18 - mmengine - INFO - Epoch(train) [102][150/293] lr: 5.000000e-04 eta: 5:50:22 time: 0.783022 data_time: 0.097891 memory: 21676 loss_kpt: 0.000565 acc_pose: 0.805729 loss: 0.000565 2022/09/16 19:14:56 - mmengine - INFO - Epoch(train) [102][200/293] lr: 5.000000e-04 eta: 5:49:55 time: 0.776894 data_time: 0.093101 memory: 21676 loss_kpt: 0.000553 acc_pose: 0.856294 loss: 0.000553 2022/09/16 19:15:35 - mmengine - INFO - Epoch(train) [102][250/293] lr: 5.000000e-04 eta: 5:49:28 time: 0.773493 data_time: 0.092887 memory: 21676 loss_kpt: 0.000562 acc_pose: 0.833688 loss: 0.000562 2022/09/16 19:16:08 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 19:16:08 - mmengine - INFO - Saving checkpoint at 102 epochs 2022/09/16 19:16:52 - mmengine - INFO - Epoch(train) [103][50/293] lr: 5.000000e-04 eta: 5:48:03 time: 0.787040 data_time: 0.104974 memory: 21676 loss_kpt: 0.000559 acc_pose: 0.878822 loss: 0.000559 2022/09/16 19:17:31 - mmengine - INFO - Epoch(train) [103][100/293] lr: 5.000000e-04 eta: 5:47:36 time: 0.773820 data_time: 0.091950 memory: 21676 loss_kpt: 0.000564 acc_pose: 0.823825 loss: 0.000564 2022/09/16 19:17:41 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 19:18:10 - mmengine - INFO - Epoch(train) [103][150/293] lr: 5.000000e-04 eta: 5:47:09 time: 0.787583 data_time: 0.092084 memory: 21676 loss_kpt: 0.000579 acc_pose: 0.851670 loss: 0.000579 2022/09/16 19:18:48 - mmengine - INFO - Epoch(train) [103][200/293] lr: 5.000000e-04 eta: 5:46:41 time: 0.756414 data_time: 0.091911 memory: 21676 loss_kpt: 0.000576 acc_pose: 0.831363 loss: 0.000576 2022/09/16 19:19:25 - mmengine - INFO - Epoch(train) [103][250/293] lr: 5.000000e-04 eta: 5:46:13 time: 0.749941 data_time: 0.092102 memory: 21676 loss_kpt: 0.000570 acc_pose: 0.829755 loss: 0.000570 2022/09/16 19:19:58 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 19:19:58 - mmengine - INFO - Saving checkpoint at 103 epochs 2022/09/16 19:20:41 - mmengine - INFO - Epoch(train) [104][50/293] lr: 5.000000e-04 eta: 5:44:47 time: 0.770116 data_time: 0.103186 memory: 21676 loss_kpt: 0.000555 acc_pose: 0.867554 loss: 0.000555 2022/09/16 19:21:19 - mmengine - INFO - Epoch(train) [104][100/293] lr: 5.000000e-04 eta: 5:44:19 time: 0.758510 data_time: 0.093763 memory: 21676 loss_kpt: 0.000565 acc_pose: 0.849276 loss: 0.000565 2022/09/16 19:21:57 - mmengine - INFO - Epoch(train) [104][150/293] lr: 5.000000e-04 eta: 5:43:51 time: 0.755122 data_time: 0.094911 memory: 21676 loss_kpt: 0.000569 acc_pose: 0.793786 loss: 0.000569 2022/09/16 19:22:35 - mmengine - INFO - Epoch(train) [104][200/293] lr: 5.000000e-04 eta: 5:43:23 time: 0.753712 data_time: 0.094781 memory: 21676 loss_kpt: 0.000568 acc_pose: 0.828056 loss: 0.000568 2022/09/16 19:23:13 - mmengine - INFO - Epoch(train) [104][250/293] lr: 5.000000e-04 eta: 5:42:55 time: 0.757123 data_time: 0.094484 memory: 21676 loss_kpt: 0.000579 acc_pose: 0.843699 loss: 0.000579 2022/09/16 19:23:44 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 19:23:44 - mmengine - INFO - Saving checkpoint at 104 epochs 2022/09/16 19:24:28 - mmengine - INFO - Epoch(train) [105][50/293] lr: 5.000000e-04 eta: 5:41:31 time: 0.789886 data_time: 0.105376 memory: 21676 loss_kpt: 0.000560 acc_pose: 0.821929 loss: 0.000560 2022/09/16 19:25:08 - mmengine - INFO - Epoch(train) [105][100/293] lr: 5.000000e-04 eta: 5:41:05 time: 0.798326 data_time: 0.097789 memory: 21676 loss_kpt: 0.000566 acc_pose: 0.826642 loss: 0.000566 2022/09/16 19:25:47 - mmengine - INFO - Epoch(train) [105][150/293] lr: 5.000000e-04 eta: 5:40:37 time: 0.767689 data_time: 0.091470 memory: 21676 loss_kpt: 0.000562 acc_pose: 0.887804 loss: 0.000562 2022/09/16 19:26:25 - mmengine - INFO - Epoch(train) [105][200/293] lr: 5.000000e-04 eta: 5:40:09 time: 0.770862 data_time: 0.095038 memory: 21676 loss_kpt: 0.000563 acc_pose: 0.847163 loss: 0.000563 2022/09/16 19:27:04 - mmengine - INFO - Epoch(train) [105][250/293] lr: 5.000000e-04 eta: 5:39:42 time: 0.781178 data_time: 0.092565 memory: 21676 loss_kpt: 0.000561 acc_pose: 0.774598 loss: 0.000561 2022/09/16 19:27:37 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 19:27:37 - mmengine - INFO - Saving checkpoint at 105 epochs 2022/09/16 19:28:22 - mmengine - INFO - Epoch(train) [106][50/293] lr: 5.000000e-04 eta: 5:38:19 time: 0.801128 data_time: 0.111352 memory: 21676 loss_kpt: 0.000574 acc_pose: 0.852702 loss: 0.000574 2022/09/16 19:29:00 - mmengine - INFO - Epoch(train) [106][100/293] lr: 5.000000e-04 eta: 5:37:52 time: 0.775837 data_time: 0.095989 memory: 21676 loss_kpt: 0.000570 acc_pose: 0.841970 loss: 0.000570 2022/09/16 19:29:39 - mmengine - INFO - Epoch(train) [106][150/293] lr: 5.000000e-04 eta: 5:37:24 time: 0.769034 data_time: 0.093397 memory: 21676 loss_kpt: 0.000565 acc_pose: 0.854956 loss: 0.000565 2022/09/16 19:30:18 - mmengine - INFO - Epoch(train) [106][200/293] lr: 5.000000e-04 eta: 5:36:57 time: 0.776236 data_time: 0.095642 memory: 21676 loss_kpt: 0.000582 acc_pose: 0.818017 loss: 0.000582 2022/09/16 19:30:45 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 19:30:57 - mmengine - INFO - Epoch(train) [106][250/293] lr: 5.000000e-04 eta: 5:36:30 time: 0.775760 data_time: 0.095923 memory: 21676 loss_kpt: 0.000568 acc_pose: 0.861756 loss: 0.000568 2022/09/16 19:31:29 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 19:31:29 - mmengine - INFO - Saving checkpoint at 106 epochs 2022/09/16 19:32:13 - mmengine - INFO - Epoch(train) [107][50/293] lr: 5.000000e-04 eta: 5:35:07 time: 0.791511 data_time: 0.104990 memory: 21676 loss_kpt: 0.000550 acc_pose: 0.855757 loss: 0.000550 2022/09/16 19:32:52 - mmengine - INFO - Epoch(train) [107][100/293] lr: 5.000000e-04 eta: 5:34:39 time: 0.766246 data_time: 0.092346 memory: 21676 loss_kpt: 0.000571 acc_pose: 0.854999 loss: 0.000571 2022/09/16 19:33:31 - mmengine - INFO - Epoch(train) [107][150/293] lr: 5.000000e-04 eta: 5:34:11 time: 0.775615 data_time: 0.096959 memory: 21676 loss_kpt: 0.000570 acc_pose: 0.876522 loss: 0.000570 2022/09/16 19:34:10 - mmengine - INFO - Epoch(train) [107][200/293] lr: 5.000000e-04 eta: 5:33:44 time: 0.783578 data_time: 0.093338 memory: 21676 loss_kpt: 0.000573 acc_pose: 0.816122 loss: 0.000573 2022/09/16 19:34:49 - mmengine - INFO - Epoch(train) [107][250/293] lr: 5.000000e-04 eta: 5:33:17 time: 0.781820 data_time: 0.096085 memory: 21676 loss_kpt: 0.000571 acc_pose: 0.864508 loss: 0.000571 2022/09/16 19:35:22 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 19:35:22 - mmengine - INFO - Saving checkpoint at 107 epochs 2022/09/16 19:36:06 - mmengine - INFO - Epoch(train) [108][50/293] lr: 5.000000e-04 eta: 5:31:54 time: 0.792391 data_time: 0.104452 memory: 21676 loss_kpt: 0.000563 acc_pose: 0.833163 loss: 0.000563 2022/09/16 19:36:45 - mmengine - INFO - Epoch(train) [108][100/293] lr: 5.000000e-04 eta: 5:31:27 time: 0.783388 data_time: 0.106933 memory: 21676 loss_kpt: 0.000563 acc_pose: 0.843120 loss: 0.000563 2022/09/16 19:37:25 - mmengine - INFO - Epoch(train) [108][150/293] lr: 5.000000e-04 eta: 5:31:00 time: 0.791656 data_time: 0.099791 memory: 21676 loss_kpt: 0.000554 acc_pose: 0.856144 loss: 0.000554 2022/09/16 19:38:03 - mmengine - INFO - Epoch(train) [108][200/293] lr: 5.000000e-04 eta: 5:30:32 time: 0.773162 data_time: 0.100383 memory: 21676 loss_kpt: 0.000566 acc_pose: 0.873679 loss: 0.000566 2022/09/16 19:38:43 - mmengine - INFO - Epoch(train) [108][250/293] lr: 5.000000e-04 eta: 5:30:06 time: 0.794265 data_time: 0.100934 memory: 21676 loss_kpt: 0.000569 acc_pose: 0.869648 loss: 0.000569 2022/09/16 19:39:16 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 19:39:16 - mmengine - INFO - Saving checkpoint at 108 epochs 2022/09/16 19:40:00 - mmengine - INFO - Epoch(train) [109][50/293] lr: 5.000000e-04 eta: 5:28:43 time: 0.793270 data_time: 0.108497 memory: 21676 loss_kpt: 0.000565 acc_pose: 0.863168 loss: 0.000565 2022/09/16 19:40:39 - mmengine - INFO - Epoch(train) [109][100/293] lr: 5.000000e-04 eta: 5:28:16 time: 0.779256 data_time: 0.099605 memory: 21676 loss_kpt: 0.000560 acc_pose: 0.863949 loss: 0.000560 2022/09/16 19:41:18 - mmengine - INFO - Epoch(train) [109][150/293] lr: 5.000000e-04 eta: 5:27:48 time: 0.778963 data_time: 0.092152 memory: 21676 loss_kpt: 0.000564 acc_pose: 0.888225 loss: 0.000564 2022/09/16 19:41:57 - mmengine - INFO - Epoch(train) [109][200/293] lr: 5.000000e-04 eta: 5:27:20 time: 0.766753 data_time: 0.095112 memory: 21676 loss_kpt: 0.000566 acc_pose: 0.837296 loss: 0.000566 2022/09/16 19:42:34 - mmengine - INFO - Epoch(train) [109][250/293] lr: 5.000000e-04 eta: 5:26:52 time: 0.756536 data_time: 0.095617 memory: 21676 loss_kpt: 0.000572 acc_pose: 0.859597 loss: 0.000572 2022/09/16 19:43:07 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 19:43:07 - mmengine - INFO - Saving checkpoint at 109 epochs 2022/09/16 19:43:52 - mmengine - INFO - Epoch(train) [110][50/293] lr: 5.000000e-04 eta: 5:25:30 time: 0.793834 data_time: 0.109822 memory: 21676 loss_kpt: 0.000568 acc_pose: 0.812840 loss: 0.000568 2022/09/16 19:44:02 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 19:44:31 - mmengine - INFO - Epoch(train) [110][100/293] lr: 5.000000e-04 eta: 5:25:02 time: 0.784681 data_time: 0.100696 memory: 21676 loss_kpt: 0.000561 acc_pose: 0.862155 loss: 0.000561 2022/09/16 19:45:10 - mmengine - INFO - Epoch(train) [110][150/293] lr: 5.000000e-04 eta: 5:24:35 time: 0.777288 data_time: 0.093450 memory: 21676 loss_kpt: 0.000567 acc_pose: 0.793472 loss: 0.000567 2022/09/16 19:45:48 - mmengine - INFO - Epoch(train) [110][200/293] lr: 5.000000e-04 eta: 5:24:07 time: 0.770273 data_time: 0.096643 memory: 21676 loss_kpt: 0.000555 acc_pose: 0.860679 loss: 0.000555 2022/09/16 19:46:26 - mmengine - INFO - Epoch(train) [110][250/293] lr: 5.000000e-04 eta: 5:23:38 time: 0.750716 data_time: 0.096175 memory: 21676 loss_kpt: 0.000564 acc_pose: 0.819073 loss: 0.000564 2022/09/16 19:46:58 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 19:46:58 - mmengine - INFO - Saving checkpoint at 110 epochs 2022/09/16 19:47:13 - mmengine - INFO - Epoch(val) [110][50/407] eta: 0:01:16 time: 0.214934 data_time: 0.013583 memory: 21676 2022/09/16 19:47:24 - mmengine - INFO - Epoch(val) [110][100/407] eta: 0:01:04 time: 0.210185 data_time: 0.008630 memory: 1375 2022/09/16 19:47:35 - mmengine - INFO - Epoch(val) [110][150/407] eta: 0:00:55 time: 0.215410 data_time: 0.008870 memory: 1375 2022/09/16 19:47:45 - mmengine - INFO - Epoch(val) [110][200/407] eta: 0:00:43 time: 0.208728 data_time: 0.008524 memory: 1375 2022/09/16 19:47:56 - mmengine - INFO - Epoch(val) [110][250/407] eta: 0:00:32 time: 0.208762 data_time: 0.008431 memory: 1375 2022/09/16 19:48:06 - mmengine - INFO - Epoch(val) [110][300/407] eta: 0:00:22 time: 0.212672 data_time: 0.008895 memory: 1375 2022/09/16 19:48:17 - mmengine - INFO - Epoch(val) [110][350/407] eta: 0:00:11 time: 0.209546 data_time: 0.008595 memory: 1375 2022/09/16 19:48:27 - mmengine - INFO - Epoch(val) [110][400/407] eta: 0:00:01 time: 0.206778 data_time: 0.007706 memory: 1375 2022/09/16 19:49:03 - mmengine - INFO - Evaluating CocoMetric... 2022/09/16 19:49:16 - mmengine - INFO - Epoch(val) [110][407/407] coco/AP: 0.750338 coco/AP .5: 0.899718 coco/AP .75: 0.812848 coco/AP (M): 0.710020 coco/AP (L): 0.821588 coco/AR: 0.799244 coco/AR .5: 0.937500 coco/AR .75: 0.856266 coco/AR (M): 0.754247 coco/AR (L): 0.864326 2022/09/16 19:49:16 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220916/dark_w32_384/best_coco/AP_epoch_100.pth is removed 2022/09/16 19:49:20 - mmengine - INFO - The best checkpoint with 0.7503 coco/AP at 110 epoch is saved to best_coco/AP_epoch_110.pth. 2022/09/16 19:50:00 - mmengine - INFO - Epoch(train) [111][50/293] lr: 5.000000e-04 eta: 5:22:16 time: 0.798729 data_time: 0.103774 memory: 21676 loss_kpt: 0.000558 acc_pose: 0.866642 loss: 0.000558 2022/09/16 19:50:39 - mmengine - INFO - Epoch(train) [111][100/293] lr: 5.000000e-04 eta: 5:21:49 time: 0.787562 data_time: 0.099695 memory: 21676 loss_kpt: 0.000556 acc_pose: 0.851939 loss: 0.000556 2022/09/16 19:51:18 - mmengine - INFO - Epoch(train) [111][150/293] lr: 5.000000e-04 eta: 5:21:21 time: 0.775912 data_time: 0.096838 memory: 21676 loss_kpt: 0.000567 acc_pose: 0.872056 loss: 0.000567 2022/09/16 19:51:57 - mmengine - INFO - Epoch(train) [111][200/293] lr: 5.000000e-04 eta: 5:20:53 time: 0.777994 data_time: 0.098959 memory: 21676 loss_kpt: 0.000564 acc_pose: 0.846965 loss: 0.000564 2022/09/16 19:52:36 - mmengine - INFO - Epoch(train) [111][250/293] lr: 5.000000e-04 eta: 5:20:26 time: 0.785166 data_time: 0.092402 memory: 21676 loss_kpt: 0.000556 acc_pose: 0.846045 loss: 0.000556 2022/09/16 19:53:09 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 19:53:09 - mmengine - INFO - Saving checkpoint at 111 epochs 2022/09/16 19:53:54 - mmengine - INFO - Epoch(train) [112][50/293] lr: 5.000000e-04 eta: 5:19:05 time: 0.800838 data_time: 0.112235 memory: 21676 loss_kpt: 0.000562 acc_pose: 0.861932 loss: 0.000562 2022/09/16 19:54:33 - mmengine - INFO - Epoch(train) [112][100/293] lr: 5.000000e-04 eta: 5:18:37 time: 0.769203 data_time: 0.096095 memory: 21676 loss_kpt: 0.000560 acc_pose: 0.858318 loss: 0.000560 2022/09/16 19:55:12 - mmengine - INFO - Epoch(train) [112][150/293] lr: 5.000000e-04 eta: 5:18:09 time: 0.778948 data_time: 0.101657 memory: 21676 loss_kpt: 0.000566 acc_pose: 0.832228 loss: 0.000566 2022/09/16 19:55:50 - mmengine - INFO - Epoch(train) [112][200/293] lr: 5.000000e-04 eta: 5:17:41 time: 0.775590 data_time: 0.102364 memory: 21676 loss_kpt: 0.000560 acc_pose: 0.871046 loss: 0.000560 2022/09/16 19:56:29 - mmengine - INFO - Epoch(train) [112][250/293] lr: 5.000000e-04 eta: 5:17:13 time: 0.779024 data_time: 0.101658 memory: 21676 loss_kpt: 0.000561 acc_pose: 0.847676 loss: 0.000561 2022/09/16 19:57:02 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 19:57:02 - mmengine - INFO - Saving checkpoint at 112 epochs 2022/09/16 19:57:46 - mmengine - INFO - Epoch(train) [113][50/293] lr: 5.000000e-04 eta: 5:15:52 time: 0.786289 data_time: 0.105800 memory: 21676 loss_kpt: 0.000550 acc_pose: 0.874366 loss: 0.000550 2022/09/16 19:58:25 - mmengine - INFO - Epoch(train) [113][100/293] lr: 5.000000e-04 eta: 5:15:24 time: 0.782925 data_time: 0.096742 memory: 21676 loss_kpt: 0.000572 acc_pose: 0.857430 loss: 0.000572 2022/09/16 19:59:04 - mmengine - INFO - Epoch(train) [113][150/293] lr: 5.000000e-04 eta: 5:14:56 time: 0.781152 data_time: 0.099468 memory: 21676 loss_kpt: 0.000559 acc_pose: 0.829122 loss: 0.000559 2022/09/16 19:59:31 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 19:59:43 - mmengine - INFO - Epoch(train) [113][200/293] lr: 5.000000e-04 eta: 5:14:29 time: 0.782823 data_time: 0.096127 memory: 21676 loss_kpt: 0.000569 acc_pose: 0.844015 loss: 0.000569 2022/09/16 20:00:23 - mmengine - INFO - Epoch(train) [113][250/293] lr: 5.000000e-04 eta: 5:14:01 time: 0.791858 data_time: 0.093460 memory: 21676 loss_kpt: 0.000584 acc_pose: 0.863498 loss: 0.000584 2022/09/16 20:00:56 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 20:00:56 - mmengine - INFO - Saving checkpoint at 113 epochs 2022/09/16 20:01:40 - mmengine - INFO - Epoch(train) [114][50/293] lr: 5.000000e-04 eta: 5:12:41 time: 0.792604 data_time: 0.100495 memory: 21676 loss_kpt: 0.000560 acc_pose: 0.801484 loss: 0.000560 2022/09/16 20:02:19 - mmengine - INFO - Epoch(train) [114][100/293] lr: 5.000000e-04 eta: 5:12:13 time: 0.788140 data_time: 0.104933 memory: 21676 loss_kpt: 0.000561 acc_pose: 0.821979 loss: 0.000561 2022/09/16 20:02:58 - mmengine - INFO - Epoch(train) [114][150/293] lr: 5.000000e-04 eta: 5:11:45 time: 0.778937 data_time: 0.097610 memory: 21676 loss_kpt: 0.000553 acc_pose: 0.823478 loss: 0.000553 2022/09/16 20:03:37 - mmengine - INFO - Epoch(train) [114][200/293] lr: 5.000000e-04 eta: 5:11:17 time: 0.783101 data_time: 0.094617 memory: 21676 loss_kpt: 0.000564 acc_pose: 0.810547 loss: 0.000564 2022/09/16 20:04:16 - mmengine - INFO - Epoch(train) [114][250/293] lr: 5.000000e-04 eta: 5:10:49 time: 0.777128 data_time: 0.095591 memory: 21676 loss_kpt: 0.000559 acc_pose: 0.857481 loss: 0.000559 2022/09/16 20:04:49 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 20:04:49 - mmengine - INFO - Saving checkpoint at 114 epochs 2022/09/16 20:05:34 - mmengine - INFO - Epoch(train) [115][50/293] lr: 5.000000e-04 eta: 5:09:29 time: 0.793586 data_time: 0.108011 memory: 21676 loss_kpt: 0.000554 acc_pose: 0.801044 loss: 0.000554 2022/09/16 20:06:13 - mmengine - INFO - Epoch(train) [115][100/293] lr: 5.000000e-04 eta: 5:09:01 time: 0.783632 data_time: 0.095500 memory: 21676 loss_kpt: 0.000541 acc_pose: 0.853804 loss: 0.000541 2022/09/16 20:06:52 - mmengine - INFO - Epoch(train) [115][150/293] lr: 5.000000e-04 eta: 5:08:33 time: 0.787679 data_time: 0.094930 memory: 21676 loss_kpt: 0.000549 acc_pose: 0.798576 loss: 0.000549 2022/09/16 20:07:31 - mmengine - INFO - Epoch(train) [115][200/293] lr: 5.000000e-04 eta: 5:08:05 time: 0.772416 data_time: 0.094880 memory: 21676 loss_kpt: 0.000565 acc_pose: 0.870882 loss: 0.000565 2022/09/16 20:08:10 - mmengine - INFO - Epoch(train) [115][250/293] lr: 5.000000e-04 eta: 5:07:36 time: 0.776888 data_time: 0.092506 memory: 21676 loss_kpt: 0.000572 acc_pose: 0.831634 loss: 0.000572 2022/09/16 20:08:42 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 20:08:42 - mmengine - INFO - Saving checkpoint at 115 epochs 2022/09/16 20:09:27 - mmengine - INFO - Epoch(train) [116][50/293] lr: 5.000000e-04 eta: 5:06:17 time: 0.796854 data_time: 0.108639 memory: 21676 loss_kpt: 0.000557 acc_pose: 0.858115 loss: 0.000557 2022/09/16 20:10:05 - mmengine - INFO - Epoch(train) [116][100/293] lr: 5.000000e-04 eta: 5:05:49 time: 0.776039 data_time: 0.098150 memory: 21676 loss_kpt: 0.000552 acc_pose: 0.849869 loss: 0.000552 2022/09/16 20:10:44 - mmengine - INFO - Epoch(train) [116][150/293] lr: 5.000000e-04 eta: 5:05:20 time: 0.776748 data_time: 0.101508 memory: 21676 loss_kpt: 0.000572 acc_pose: 0.843052 loss: 0.000572 2022/09/16 20:11:23 - mmengine - INFO - Epoch(train) [116][200/293] lr: 5.000000e-04 eta: 5:04:52 time: 0.781111 data_time: 0.104637 memory: 21676 loss_kpt: 0.000568 acc_pose: 0.865180 loss: 0.000568 2022/09/16 20:12:01 - mmengine - INFO - Epoch(train) [116][250/293] lr: 5.000000e-04 eta: 5:04:23 time: 0.758368 data_time: 0.097876 memory: 21676 loss_kpt: 0.000562 acc_pose: 0.821089 loss: 0.000562 2022/09/16 20:12:33 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 20:12:33 - mmengine - INFO - Saving checkpoint at 116 epochs 2022/09/16 20:12:48 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 20:13:17 - mmengine - INFO - Epoch(train) [117][50/293] lr: 5.000000e-04 eta: 5:03:03 time: 0.785705 data_time: 0.108063 memory: 21676 loss_kpt: 0.000563 acc_pose: 0.860498 loss: 0.000563 2022/09/16 20:13:56 - mmengine - INFO - Epoch(train) [117][100/293] lr: 5.000000e-04 eta: 5:02:35 time: 0.777717 data_time: 0.098167 memory: 21676 loss_kpt: 0.000547 acc_pose: 0.862712 loss: 0.000547 2022/09/16 20:14:35 - mmengine - INFO - Epoch(train) [117][150/293] lr: 5.000000e-04 eta: 5:02:06 time: 0.779742 data_time: 0.099145 memory: 21676 loss_kpt: 0.000548 acc_pose: 0.829182 loss: 0.000548 2022/09/16 20:15:14 - mmengine - INFO - Epoch(train) [117][200/293] lr: 5.000000e-04 eta: 5:01:38 time: 0.776015 data_time: 0.096044 memory: 21676 loss_kpt: 0.000557 acc_pose: 0.789717 loss: 0.000557 2022/09/16 20:15:53 - mmengine - INFO - Epoch(train) [117][250/293] lr: 5.000000e-04 eta: 5:01:10 time: 0.786979 data_time: 0.095200 memory: 21676 loss_kpt: 0.000550 acc_pose: 0.837492 loss: 0.000550 2022/09/16 20:16:26 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 20:16:26 - mmengine - INFO - Saving checkpoint at 117 epochs 2022/09/16 20:17:10 - mmengine - INFO - Epoch(train) [118][50/293] lr: 5.000000e-04 eta: 4:59:51 time: 0.785399 data_time: 0.102130 memory: 21676 loss_kpt: 0.000563 acc_pose: 0.820568 loss: 0.000563 2022/09/16 20:17:49 - mmengine - INFO - Epoch(train) [118][100/293] lr: 5.000000e-04 eta: 4:59:22 time: 0.776569 data_time: 0.095670 memory: 21676 loss_kpt: 0.000564 acc_pose: 0.823087 loss: 0.000564 2022/09/16 20:18:29 - mmengine - INFO - Epoch(train) [118][150/293] lr: 5.000000e-04 eta: 4:58:54 time: 0.793112 data_time: 0.095905 memory: 21676 loss_kpt: 0.000566 acc_pose: 0.818798 loss: 0.000566 2022/09/16 20:19:08 - mmengine - INFO - Epoch(train) [118][200/293] lr: 5.000000e-04 eta: 4:58:26 time: 0.780473 data_time: 0.093279 memory: 21676 loss_kpt: 0.000562 acc_pose: 0.833777 loss: 0.000562 2022/09/16 20:19:46 - mmengine - INFO - Epoch(train) [118][250/293] lr: 5.000000e-04 eta: 4:57:56 time: 0.753388 data_time: 0.092640 memory: 21676 loss_kpt: 0.000558 acc_pose: 0.826572 loss: 0.000558 2022/09/16 20:20:18 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 20:20:18 - mmengine - INFO - Saving checkpoint at 118 epochs 2022/09/16 20:21:02 - mmengine - INFO - Epoch(train) [119][50/293] lr: 5.000000e-04 eta: 4:56:37 time: 0.786703 data_time: 0.102092 memory: 21676 loss_kpt: 0.000553 acc_pose: 0.837895 loss: 0.000553 2022/09/16 20:21:41 - mmengine - INFO - Epoch(train) [119][100/293] lr: 5.000000e-04 eta: 4:56:09 time: 0.775557 data_time: 0.099595 memory: 21676 loss_kpt: 0.000552 acc_pose: 0.894070 loss: 0.000552 2022/09/16 20:22:20 - mmengine - INFO - Epoch(train) [119][150/293] lr: 5.000000e-04 eta: 4:55:40 time: 0.778097 data_time: 0.097747 memory: 21676 loss_kpt: 0.000554 acc_pose: 0.854032 loss: 0.000554 2022/09/16 20:22:58 - mmengine - INFO - Epoch(train) [119][200/293] lr: 5.000000e-04 eta: 4:55:11 time: 0.769651 data_time: 0.098343 memory: 21676 loss_kpt: 0.000545 acc_pose: 0.852941 loss: 0.000545 2022/09/16 20:23:37 - mmengine - INFO - Epoch(train) [119][250/293] lr: 5.000000e-04 eta: 4:54:42 time: 0.764753 data_time: 0.097152 memory: 21676 loss_kpt: 0.000558 acc_pose: 0.852303 loss: 0.000558 2022/09/16 20:24:09 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 20:24:09 - mmengine - INFO - Saving checkpoint at 119 epochs 2022/09/16 20:24:53 - mmengine - INFO - Epoch(train) [120][50/293] lr: 5.000000e-04 eta: 4:53:23 time: 0.788613 data_time: 0.112626 memory: 21676 loss_kpt: 0.000560 acc_pose: 0.833008 loss: 0.000560 2022/09/16 20:25:32 - mmengine - INFO - Epoch(train) [120][100/293] lr: 5.000000e-04 eta: 4:52:55 time: 0.772940 data_time: 0.097738 memory: 21676 loss_kpt: 0.000560 acc_pose: 0.805427 loss: 0.000560 2022/09/16 20:25:57 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 20:26:10 - mmengine - INFO - Epoch(train) [120][150/293] lr: 5.000000e-04 eta: 4:52:25 time: 0.763345 data_time: 0.106093 memory: 21676 loss_kpt: 0.000562 acc_pose: 0.850340 loss: 0.000562 2022/09/16 20:26:49 - mmengine - INFO - Epoch(train) [120][200/293] lr: 5.000000e-04 eta: 4:51:57 time: 0.783586 data_time: 0.105336 memory: 21676 loss_kpt: 0.000559 acc_pose: 0.826528 loss: 0.000559 2022/09/16 20:27:28 - mmengine - INFO - Epoch(train) [120][250/293] lr: 5.000000e-04 eta: 4:51:28 time: 0.773050 data_time: 0.106171 memory: 21676 loss_kpt: 0.000557 acc_pose: 0.796605 loss: 0.000557 2022/09/16 20:28:01 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 20:28:01 - mmengine - INFO - Saving checkpoint at 120 epochs 2022/09/16 20:28:17 - mmengine - INFO - Epoch(val) [120][50/407] eta: 0:01:17 time: 0.216476 data_time: 0.014382 memory: 21676 2022/09/16 20:28:27 - mmengine - INFO - Epoch(val) [120][100/407] eta: 0:01:05 time: 0.213243 data_time: 0.009610 memory: 1375 2022/09/16 20:28:38 - mmengine - INFO - Epoch(val) [120][150/407] eta: 0:00:54 time: 0.212282 data_time: 0.008607 memory: 1375 2022/09/16 20:28:48 - mmengine - INFO - Epoch(val) [120][200/407] eta: 0:00:43 time: 0.212419 data_time: 0.008908 memory: 1375 2022/09/16 20:28:59 - mmengine - INFO - Epoch(val) [120][250/407] eta: 0:00:33 time: 0.211045 data_time: 0.008542 memory: 1375 2022/09/16 20:29:10 - mmengine - INFO - Epoch(val) [120][300/407] eta: 0:00:22 time: 0.210270 data_time: 0.008312 memory: 1375 2022/09/16 20:29:20 - mmengine - INFO - Epoch(val) [120][350/407] eta: 0:00:12 time: 0.212970 data_time: 0.008238 memory: 1375 2022/09/16 20:29:31 - mmengine - INFO - Epoch(val) [120][400/407] eta: 0:00:01 time: 0.210675 data_time: 0.008622 memory: 1375 2022/09/16 20:30:06 - mmengine - INFO - Evaluating CocoMetric... 2022/09/16 20:30:19 - mmengine - INFO - Epoch(val) [120][407/407] coco/AP: 0.752511 coco/AP .5: 0.900497 coco/AP .75: 0.818786 coco/AP (M): 0.714263 coco/AP (L): 0.822926 coco/AR: 0.802298 coco/AR .5: 0.939704 coco/AR .75: 0.862091 coco/AR (M): 0.758836 coco/AR (L): 0.865403 2022/09/16 20:30:20 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220916/dark_w32_384/best_coco/AP_epoch_110.pth is removed 2022/09/16 20:30:23 - mmengine - INFO - The best checkpoint with 0.7525 coco/AP at 120 epoch is saved to best_coco/AP_epoch_120.pth. 2022/09/16 20:31:02 - mmengine - INFO - Epoch(train) [121][50/293] lr: 5.000000e-04 eta: 4:50:10 time: 0.782534 data_time: 0.105668 memory: 21676 loss_kpt: 0.000563 acc_pose: 0.814347 loss: 0.000563 2022/09/16 20:31:41 - mmengine - INFO - Epoch(train) [121][100/293] lr: 5.000000e-04 eta: 4:49:41 time: 0.779064 data_time: 0.089732 memory: 21676 loss_kpt: 0.000547 acc_pose: 0.828948 loss: 0.000547 2022/09/16 20:32:20 - mmengine - INFO - Epoch(train) [121][150/293] lr: 5.000000e-04 eta: 4:49:12 time: 0.781479 data_time: 0.097979 memory: 21676 loss_kpt: 0.000559 acc_pose: 0.833975 loss: 0.000559 2022/09/16 20:32:59 - mmengine - INFO - Epoch(train) [121][200/293] lr: 5.000000e-04 eta: 4:48:44 time: 0.781690 data_time: 0.095963 memory: 21676 loss_kpt: 0.000559 acc_pose: 0.816452 loss: 0.000559 2022/09/16 20:33:37 - mmengine - INFO - Epoch(train) [121][250/293] lr: 5.000000e-04 eta: 4:48:14 time: 0.748056 data_time: 0.096385 memory: 21676 loss_kpt: 0.000549 acc_pose: 0.871655 loss: 0.000549 2022/09/16 20:34:09 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 20:34:09 - mmengine - INFO - Saving checkpoint at 121 epochs 2022/09/16 20:34:53 - mmengine - INFO - Epoch(train) [122][50/293] lr: 5.000000e-04 eta: 4:46:56 time: 0.784315 data_time: 0.101871 memory: 21676 loss_kpt: 0.000551 acc_pose: 0.861913 loss: 0.000551 2022/09/16 20:35:32 - mmengine - INFO - Epoch(train) [122][100/293] lr: 5.000000e-04 eta: 4:46:27 time: 0.789729 data_time: 0.099317 memory: 21676 loss_kpt: 0.000553 acc_pose: 0.783302 loss: 0.000553 2022/09/16 20:36:11 - mmengine - INFO - Epoch(train) [122][150/293] lr: 5.000000e-04 eta: 4:45:59 time: 0.776897 data_time: 0.092202 memory: 21676 loss_kpt: 0.000551 acc_pose: 0.858259 loss: 0.000551 2022/09/16 20:36:49 - mmengine - INFO - Epoch(train) [122][200/293] lr: 5.000000e-04 eta: 4:45:29 time: 0.761250 data_time: 0.094952 memory: 21676 loss_kpt: 0.000557 acc_pose: 0.842811 loss: 0.000557 2022/09/16 20:37:27 - mmengine - INFO - Epoch(train) [122][250/293] lr: 5.000000e-04 eta: 4:44:59 time: 0.753130 data_time: 0.099592 memory: 21676 loss_kpt: 0.000553 acc_pose: 0.797215 loss: 0.000553 2022/09/16 20:37:59 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 20:37:59 - mmengine - INFO - Saving checkpoint at 122 epochs 2022/09/16 20:38:43 - mmengine - INFO - Epoch(train) [123][50/293] lr: 5.000000e-04 eta: 4:43:41 time: 0.780413 data_time: 0.110850 memory: 21676 loss_kpt: 0.000546 acc_pose: 0.872621 loss: 0.000546 2022/09/16 20:39:21 - mmengine - INFO - Epoch(train) [123][100/293] lr: 5.000000e-04 eta: 4:43:12 time: 0.772348 data_time: 0.098562 memory: 21676 loss_kpt: 0.000559 acc_pose: 0.892978 loss: 0.000559 2022/09/16 20:40:01 - mmengine - INFO - Epoch(train) [123][150/293] lr: 5.000000e-04 eta: 4:42:44 time: 0.792384 data_time: 0.102336 memory: 21676 loss_kpt: 0.000568 acc_pose: 0.848463 loss: 0.000568 2022/09/16 20:40:41 - mmengine - INFO - Epoch(train) [123][200/293] lr: 5.000000e-04 eta: 4:42:15 time: 0.790607 data_time: 0.106421 memory: 21676 loss_kpt: 0.000573 acc_pose: 0.834743 loss: 0.000573 2022/09/16 20:41:19 - mmengine - INFO - Epoch(train) [123][250/293] lr: 5.000000e-04 eta: 4:41:46 time: 0.766465 data_time: 0.094757 memory: 21676 loss_kpt: 0.000558 acc_pose: 0.822878 loss: 0.000558 2022/09/16 20:41:22 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 20:41:51 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 20:41:51 - mmengine - INFO - Saving checkpoint at 123 epochs 2022/09/16 20:42:35 - mmengine - INFO - Epoch(train) [124][50/293] lr: 5.000000e-04 eta: 4:40:29 time: 0.782210 data_time: 0.105473 memory: 21676 loss_kpt: 0.000551 acc_pose: 0.873360 loss: 0.000551 2022/09/16 20:43:13 - mmengine - INFO - Epoch(train) [124][100/293] lr: 5.000000e-04 eta: 4:39:59 time: 0.766389 data_time: 0.094653 memory: 21676 loss_kpt: 0.000565 acc_pose: 0.849172 loss: 0.000565 2022/09/16 20:43:52 - mmengine - INFO - Epoch(train) [124][150/293] lr: 5.000000e-04 eta: 4:39:30 time: 0.771626 data_time: 0.096157 memory: 21676 loss_kpt: 0.000556 acc_pose: 0.831950 loss: 0.000556 2022/09/16 20:44:31 - mmengine - INFO - Epoch(train) [124][200/293] lr: 5.000000e-04 eta: 4:39:01 time: 0.780767 data_time: 0.095276 memory: 21676 loss_kpt: 0.000558 acc_pose: 0.831884 loss: 0.000558 2022/09/16 20:45:10 - mmengine - INFO - Epoch(train) [124][250/293] lr: 5.000000e-04 eta: 4:38:32 time: 0.773433 data_time: 0.096902 memory: 21676 loss_kpt: 0.000550 acc_pose: 0.822003 loss: 0.000550 2022/09/16 20:45:43 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 20:45:43 - mmengine - INFO - Saving checkpoint at 124 epochs 2022/09/16 20:46:26 - mmengine - INFO - Epoch(train) [125][50/293] lr: 5.000000e-04 eta: 4:37:15 time: 0.783751 data_time: 0.106053 memory: 21676 loss_kpt: 0.000545 acc_pose: 0.872391 loss: 0.000545 2022/09/16 20:47:05 - mmengine - INFO - Epoch(train) [125][100/293] lr: 5.000000e-04 eta: 4:36:46 time: 0.783706 data_time: 0.097246 memory: 21676 loss_kpt: 0.000566 acc_pose: 0.861622 loss: 0.000566 2022/09/16 20:47:44 - mmengine - INFO - Epoch(train) [125][150/293] lr: 5.000000e-04 eta: 4:36:17 time: 0.775087 data_time: 0.091361 memory: 21676 loss_kpt: 0.000565 acc_pose: 0.834490 loss: 0.000565 2022/09/16 20:48:23 - mmengine - INFO - Epoch(train) [125][200/293] lr: 5.000000e-04 eta: 4:35:48 time: 0.784231 data_time: 0.099691 memory: 21676 loss_kpt: 0.000552 acc_pose: 0.854852 loss: 0.000552 2022/09/16 20:49:01 - mmengine - INFO - Epoch(train) [125][250/293] lr: 5.000000e-04 eta: 4:35:18 time: 0.763334 data_time: 0.100792 memory: 21676 loss_kpt: 0.000551 acc_pose: 0.781845 loss: 0.000551 2022/09/16 20:49:33 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 20:49:33 - mmengine - INFO - Saving checkpoint at 125 epochs 2022/09/16 20:50:17 - mmengine - INFO - Epoch(train) [126][50/293] lr: 5.000000e-04 eta: 4:34:01 time: 0.778735 data_time: 0.100862 memory: 21676 loss_kpt: 0.000547 acc_pose: 0.854414 loss: 0.000547 2022/09/16 20:50:55 - mmengine - INFO - Epoch(train) [126][100/293] lr: 5.000000e-04 eta: 4:33:32 time: 0.761647 data_time: 0.095819 memory: 21676 loss_kpt: 0.000554 acc_pose: 0.842270 loss: 0.000554 2022/09/16 20:51:33 - mmengine - INFO - Epoch(train) [126][150/293] lr: 5.000000e-04 eta: 4:33:01 time: 0.747113 data_time: 0.097274 memory: 21676 loss_kpt: 0.000553 acc_pose: 0.851670 loss: 0.000553 2022/09/16 20:52:11 - mmengine - INFO - Epoch(train) [126][200/293] lr: 5.000000e-04 eta: 4:32:32 time: 0.774168 data_time: 0.098511 memory: 21676 loss_kpt: 0.000557 acc_pose: 0.837038 loss: 0.000557 2022/09/16 20:52:49 - mmengine - INFO - Epoch(train) [126][250/293] lr: 5.000000e-04 eta: 4:32:02 time: 0.748815 data_time: 0.099506 memory: 21676 loss_kpt: 0.000559 acc_pose: 0.792690 loss: 0.000559 2022/09/16 20:53:21 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 20:53:21 - mmengine - INFO - Saving checkpoint at 126 epochs 2022/09/16 20:54:06 - mmengine - INFO - Epoch(train) [127][50/293] lr: 5.000000e-04 eta: 4:30:46 time: 0.792284 data_time: 0.103136 memory: 21676 loss_kpt: 0.000545 acc_pose: 0.846095 loss: 0.000545 2022/09/16 20:54:30 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 20:54:43 - mmengine - INFO - Epoch(train) [127][100/293] lr: 5.000000e-04 eta: 4:30:16 time: 0.752728 data_time: 0.097433 memory: 21676 loss_kpt: 0.000546 acc_pose: 0.840546 loss: 0.000546 2022/09/16 20:55:21 - mmengine - INFO - Epoch(train) [127][150/293] lr: 5.000000e-04 eta: 4:29:46 time: 0.751727 data_time: 0.092684 memory: 21676 loss_kpt: 0.000552 acc_pose: 0.884814 loss: 0.000552 2022/09/16 20:55:58 - mmengine - INFO - Epoch(train) [127][200/293] lr: 5.000000e-04 eta: 4:29:15 time: 0.751339 data_time: 0.098137 memory: 21676 loss_kpt: 0.000549 acc_pose: 0.840040 loss: 0.000549 2022/09/16 20:56:36 - mmengine - INFO - Epoch(train) [127][250/293] lr: 5.000000e-04 eta: 4:28:46 time: 0.759851 data_time: 0.098622 memory: 21676 loss_kpt: 0.000552 acc_pose: 0.865314 loss: 0.000552 2022/09/16 20:57:08 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 20:57:08 - mmengine - INFO - Saving checkpoint at 127 epochs 2022/09/16 20:57:53 - mmengine - INFO - Epoch(train) [128][50/293] lr: 5.000000e-04 eta: 4:27:30 time: 0.802343 data_time: 0.107969 memory: 21676 loss_kpt: 0.000535 acc_pose: 0.803739 loss: 0.000535 2022/09/16 20:58:32 - mmengine - INFO - Epoch(train) [128][100/293] lr: 5.000000e-04 eta: 4:27:01 time: 0.771772 data_time: 0.101216 memory: 21676 loss_kpt: 0.000545 acc_pose: 0.848918 loss: 0.000545 2022/09/16 20:59:11 - mmengine - INFO - Epoch(train) [128][150/293] lr: 5.000000e-04 eta: 4:26:31 time: 0.779047 data_time: 0.099200 memory: 21676 loss_kpt: 0.000535 acc_pose: 0.870910 loss: 0.000535 2022/09/16 20:59:50 - mmengine - INFO - Epoch(train) [128][200/293] lr: 5.000000e-04 eta: 4:26:02 time: 0.788294 data_time: 0.105030 memory: 21676 loss_kpt: 0.000560 acc_pose: 0.864180 loss: 0.000560 2022/09/16 21:00:29 - mmengine - INFO - Epoch(train) [128][250/293] lr: 5.000000e-04 eta: 4:25:33 time: 0.775649 data_time: 0.102880 memory: 21676 loss_kpt: 0.000556 acc_pose: 0.842251 loss: 0.000556 2022/09/16 21:01:01 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 21:01:01 - mmengine - INFO - Saving checkpoint at 128 epochs 2022/09/16 21:01:45 - mmengine - INFO - Epoch(train) [129][50/293] lr: 5.000000e-04 eta: 4:24:17 time: 0.787674 data_time: 0.104290 memory: 21676 loss_kpt: 0.000543 acc_pose: 0.847735 loss: 0.000543 2022/09/16 21:02:24 - mmengine - INFO - Epoch(train) [129][100/293] lr: 5.000000e-04 eta: 4:23:48 time: 0.776732 data_time: 0.097613 memory: 21676 loss_kpt: 0.000546 acc_pose: 0.857906 loss: 0.000546 2022/09/16 21:03:03 - mmengine - INFO - Epoch(train) [129][150/293] lr: 5.000000e-04 eta: 4:23:18 time: 0.782154 data_time: 0.095592 memory: 21676 loss_kpt: 0.000555 acc_pose: 0.836011 loss: 0.000555 2022/09/16 21:03:42 - mmengine - INFO - Epoch(train) [129][200/293] lr: 5.000000e-04 eta: 4:22:49 time: 0.770165 data_time: 0.096567 memory: 21676 loss_kpt: 0.000556 acc_pose: 0.820801 loss: 0.000556 2022/09/16 21:04:21 - mmengine - INFO - Epoch(train) [129][250/293] lr: 5.000000e-04 eta: 4:22:19 time: 0.779996 data_time: 0.099665 memory: 21676 loss_kpt: 0.000553 acc_pose: 0.834032 loss: 0.000553 2022/09/16 21:04:53 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 21:04:53 - mmengine - INFO - Saving checkpoint at 129 epochs 2022/09/16 21:05:37 - mmengine - INFO - Epoch(train) [130][50/293] lr: 5.000000e-04 eta: 4:21:04 time: 0.781505 data_time: 0.113689 memory: 21676 loss_kpt: 0.000557 acc_pose: 0.829368 loss: 0.000557 2022/09/16 21:06:16 - mmengine - INFO - Epoch(train) [130][100/293] lr: 5.000000e-04 eta: 4:20:34 time: 0.776216 data_time: 0.103766 memory: 21676 loss_kpt: 0.000557 acc_pose: 0.887489 loss: 0.000557 2022/09/16 21:06:55 - mmengine - INFO - Epoch(train) [130][150/293] lr: 5.000000e-04 eta: 4:20:05 time: 0.784665 data_time: 0.108675 memory: 21676 loss_kpt: 0.000552 acc_pose: 0.862932 loss: 0.000552 2022/09/16 21:07:34 - mmengine - INFO - Epoch(train) [130][200/293] lr: 5.000000e-04 eta: 4:19:35 time: 0.772816 data_time: 0.101906 memory: 21676 loss_kpt: 0.000559 acc_pose: 0.870551 loss: 0.000559 2022/09/16 21:07:36 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 21:08:11 - mmengine - INFO - Epoch(train) [130][250/293] lr: 5.000000e-04 eta: 4:19:05 time: 0.747846 data_time: 0.092126 memory: 21676 loss_kpt: 0.000557 acc_pose: 0.826345 loss: 0.000557 2022/09/16 21:08:43 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 21:08:43 - mmengine - INFO - Saving checkpoint at 130 epochs 2022/09/16 21:08:59 - mmengine - INFO - Epoch(val) [130][50/407] eta: 0:01:18 time: 0.219589 data_time: 0.014499 memory: 21676 2022/09/16 21:09:09 - mmengine - INFO - Epoch(val) [130][100/407] eta: 0:01:03 time: 0.208351 data_time: 0.008245 memory: 1375 2022/09/16 21:09:20 - mmengine - INFO - Epoch(val) [130][150/407] eta: 0:00:54 time: 0.212011 data_time: 0.008538 memory: 1375 2022/09/16 21:09:30 - mmengine - INFO - Epoch(val) [130][200/407] eta: 0:00:43 time: 0.210166 data_time: 0.008455 memory: 1375 2022/09/16 21:09:41 - mmengine - INFO - Epoch(val) [130][250/407] eta: 0:00:33 time: 0.212142 data_time: 0.008566 memory: 1375 2022/09/16 21:09:51 - mmengine - INFO - Epoch(val) [130][300/407] eta: 0:00:22 time: 0.210189 data_time: 0.008429 memory: 1375 2022/09/16 21:10:02 - mmengine - INFO - Epoch(val) [130][350/407] eta: 0:00:12 time: 0.214905 data_time: 0.012554 memory: 1375 2022/09/16 21:10:12 - mmengine - INFO - Epoch(val) [130][400/407] eta: 0:00:01 time: 0.206512 data_time: 0.008465 memory: 1375 2022/09/16 21:10:48 - mmengine - INFO - Evaluating CocoMetric... 2022/09/16 21:11:01 - mmengine - INFO - Epoch(val) [130][407/407] coco/AP: 0.753913 coco/AP .5: 0.899989 coco/AP .75: 0.820734 coco/AP (M): 0.716101 coco/AP (L): 0.822767 coco/AR: 0.803605 coco/AR .5: 0.937185 coco/AR .75: 0.863508 coco/AR (M): 0.761185 coco/AR (L): 0.865440 2022/09/16 21:11:01 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220916/dark_w32_384/best_coco/AP_epoch_120.pth is removed 2022/09/16 21:11:05 - mmengine - INFO - The best checkpoint with 0.7539 coco/AP at 130 epoch is saved to best_coco/AP_epoch_130.pth. 2022/09/16 21:11:44 - mmengine - INFO - Epoch(train) [131][50/293] lr: 5.000000e-04 eta: 4:17:50 time: 0.783130 data_time: 0.106067 memory: 21676 loss_kpt: 0.000539 acc_pose: 0.818826 loss: 0.000539 2022/09/16 21:12:22 - mmengine - INFO - Epoch(train) [131][100/293] lr: 5.000000e-04 eta: 4:17:20 time: 0.772985 data_time: 0.096328 memory: 21676 loss_kpt: 0.000539 acc_pose: 0.804794 loss: 0.000539 2022/09/16 21:13:01 - mmengine - INFO - Epoch(train) [131][150/293] lr: 5.000000e-04 eta: 4:16:50 time: 0.766200 data_time: 0.095023 memory: 21676 loss_kpt: 0.000552 acc_pose: 0.852343 loss: 0.000552 2022/09/16 21:13:38 - mmengine - INFO - Epoch(train) [131][200/293] lr: 5.000000e-04 eta: 4:16:20 time: 0.756445 data_time: 0.094853 memory: 21676 loss_kpt: 0.000544 acc_pose: 0.867968 loss: 0.000544 2022/09/16 21:14:16 - mmengine - INFO - Epoch(train) [131][250/293] lr: 5.000000e-04 eta: 4:15:50 time: 0.752772 data_time: 0.096321 memory: 21676 loss_kpt: 0.000557 acc_pose: 0.887515 loss: 0.000557 2022/09/16 21:14:49 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 21:14:49 - mmengine - INFO - Saving checkpoint at 131 epochs 2022/09/16 21:15:34 - mmengine - INFO - Epoch(train) [132][50/293] lr: 5.000000e-04 eta: 4:14:35 time: 0.797413 data_time: 0.109948 memory: 21676 loss_kpt: 0.000543 acc_pose: 0.825895 loss: 0.000543 2022/09/16 21:16:13 - mmengine - INFO - Epoch(train) [132][100/293] lr: 5.000000e-04 eta: 4:14:05 time: 0.782087 data_time: 0.103863 memory: 21676 loss_kpt: 0.000555 acc_pose: 0.845368 loss: 0.000555 2022/09/16 21:16:52 - mmengine - INFO - Epoch(train) [132][150/293] lr: 5.000000e-04 eta: 4:13:36 time: 0.790464 data_time: 0.100145 memory: 21676 loss_kpt: 0.000546 acc_pose: 0.870996 loss: 0.000546 2022/09/16 21:17:31 - mmengine - INFO - Epoch(train) [132][200/293] lr: 5.000000e-04 eta: 4:13:07 time: 0.783118 data_time: 0.100467 memory: 21676 loss_kpt: 0.000550 acc_pose: 0.810397 loss: 0.000550 2022/09/16 21:18:10 - mmengine - INFO - Epoch(train) [132][250/293] lr: 5.000000e-04 eta: 4:12:37 time: 0.774622 data_time: 0.092531 memory: 21676 loss_kpt: 0.000547 acc_pose: 0.851307 loss: 0.000547 2022/09/16 21:18:43 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 21:18:43 - mmengine - INFO - Saving checkpoint at 132 epochs 2022/09/16 21:19:27 - mmengine - INFO - Epoch(train) [133][50/293] lr: 5.000000e-04 eta: 4:11:22 time: 0.790516 data_time: 0.102918 memory: 21676 loss_kpt: 0.000552 acc_pose: 0.846774 loss: 0.000552 2022/09/16 21:20:07 - mmengine - INFO - Epoch(train) [133][100/293] lr: 5.000000e-04 eta: 4:10:53 time: 0.788463 data_time: 0.099458 memory: 21676 loss_kpt: 0.000536 acc_pose: 0.857496 loss: 0.000536 2022/09/16 21:20:47 - mmengine - INFO - Epoch(train) [133][150/293] lr: 5.000000e-04 eta: 4:10:24 time: 0.793323 data_time: 0.095798 memory: 21676 loss_kpt: 0.000561 acc_pose: 0.864983 loss: 0.000561 2022/09/16 21:21:25 - mmengine - INFO - Epoch(train) [133][200/293] lr: 5.000000e-04 eta: 4:09:54 time: 0.777250 data_time: 0.093102 memory: 21676 loss_kpt: 0.000539 acc_pose: 0.820538 loss: 0.000539 2022/09/16 21:22:04 - mmengine - INFO - Epoch(train) [133][250/293] lr: 5.000000e-04 eta: 4:09:24 time: 0.777002 data_time: 0.096021 memory: 21676 loss_kpt: 0.000562 acc_pose: 0.870410 loss: 0.000562 2022/09/16 21:22:37 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 21:22:37 - mmengine - INFO - Saving checkpoint at 133 epochs 2022/09/16 21:23:06 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 21:23:21 - mmengine - INFO - Epoch(train) [134][50/293] lr: 5.000000e-04 eta: 4:08:10 time: 0.789869 data_time: 0.108317 memory: 21676 loss_kpt: 0.000529 acc_pose: 0.851734 loss: 0.000529 2022/09/16 21:24:00 - mmengine - INFO - Epoch(train) [134][100/293] lr: 5.000000e-04 eta: 4:07:41 time: 0.786595 data_time: 0.099119 memory: 21676 loss_kpt: 0.000534 acc_pose: 0.838227 loss: 0.000534 2022/09/16 21:24:39 - mmengine - INFO - Epoch(train) [134][150/293] lr: 5.000000e-04 eta: 4:07:11 time: 0.778435 data_time: 0.093040 memory: 21676 loss_kpt: 0.000544 acc_pose: 0.859767 loss: 0.000544 2022/09/16 21:25:17 - mmengine - INFO - Epoch(train) [134][200/293] lr: 5.000000e-04 eta: 4:06:41 time: 0.759697 data_time: 0.100212 memory: 21676 loss_kpt: 0.000537 acc_pose: 0.868206 loss: 0.000537 2022/09/16 21:25:54 - mmengine - INFO - Epoch(train) [134][250/293] lr: 5.000000e-04 eta: 4:06:10 time: 0.750987 data_time: 0.096541 memory: 21676 loss_kpt: 0.000539 acc_pose: 0.847508 loss: 0.000539 2022/09/16 21:26:27 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 21:26:27 - mmengine - INFO - Saving checkpoint at 134 epochs 2022/09/16 21:27:11 - mmengine - INFO - Epoch(train) [135][50/293] lr: 5.000000e-04 eta: 4:04:56 time: 0.788231 data_time: 0.108409 memory: 21676 loss_kpt: 0.000546 acc_pose: 0.823502 loss: 0.000546 2022/09/16 21:27:50 - mmengine - INFO - Epoch(train) [135][100/293] lr: 5.000000e-04 eta: 4:04:26 time: 0.788975 data_time: 0.092249 memory: 21676 loss_kpt: 0.000533 acc_pose: 0.875164 loss: 0.000533 2022/09/16 21:28:30 - mmengine - INFO - Epoch(train) [135][150/293] lr: 5.000000e-04 eta: 4:03:57 time: 0.789069 data_time: 0.091809 memory: 21676 loss_kpt: 0.000542 acc_pose: 0.853341 loss: 0.000542 2022/09/16 21:29:09 - mmengine - INFO - Epoch(train) [135][200/293] lr: 5.000000e-04 eta: 4:03:27 time: 0.786787 data_time: 0.095879 memory: 21676 loss_kpt: 0.000550 acc_pose: 0.825258 loss: 0.000550 2022/09/16 21:29:48 - mmengine - INFO - Epoch(train) [135][250/293] lr: 5.000000e-04 eta: 4:02:58 time: 0.782208 data_time: 0.091984 memory: 21676 loss_kpt: 0.000546 acc_pose: 0.889244 loss: 0.000546 2022/09/16 21:30:21 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 21:30:21 - mmengine - INFO - Saving checkpoint at 135 epochs 2022/09/16 21:31:06 - mmengine - INFO - Epoch(train) [136][50/293] lr: 5.000000e-04 eta: 4:01:44 time: 0.801378 data_time: 0.107714 memory: 21676 loss_kpt: 0.000553 acc_pose: 0.855078 loss: 0.000553 2022/09/16 21:31:45 - mmengine - INFO - Epoch(train) [136][100/293] lr: 5.000000e-04 eta: 4:01:14 time: 0.777242 data_time: 0.096577 memory: 21676 loss_kpt: 0.000552 acc_pose: 0.804044 loss: 0.000552 2022/09/16 21:32:24 - mmengine - INFO - Epoch(train) [136][150/293] lr: 5.000000e-04 eta: 4:00:44 time: 0.780352 data_time: 0.097618 memory: 21676 loss_kpt: 0.000556 acc_pose: 0.842358 loss: 0.000556 2022/09/16 21:33:03 - mmengine - INFO - Epoch(train) [136][200/293] lr: 5.000000e-04 eta: 4:00:15 time: 0.789658 data_time: 0.092430 memory: 21676 loss_kpt: 0.000545 acc_pose: 0.856486 loss: 0.000545 2022/09/16 21:33:42 - mmengine - INFO - Epoch(train) [136][250/293] lr: 5.000000e-04 eta: 3:59:45 time: 0.771544 data_time: 0.099417 memory: 21676 loss_kpt: 0.000561 acc_pose: 0.888226 loss: 0.000561 2022/09/16 21:34:15 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 21:34:15 - mmengine - INFO - Saving checkpoint at 136 epochs 2022/09/16 21:34:59 - mmengine - INFO - Epoch(train) [137][50/293] lr: 5.000000e-04 eta: 3:58:31 time: 0.784861 data_time: 0.106132 memory: 21676 loss_kpt: 0.000538 acc_pose: 0.855357 loss: 0.000538 2022/09/16 21:35:37 - mmengine - INFO - Epoch(train) [137][100/293] lr: 5.000000e-04 eta: 3:58:01 time: 0.767028 data_time: 0.099075 memory: 21676 loss_kpt: 0.000537 acc_pose: 0.835606 loss: 0.000537 2022/09/16 21:36:15 - mmengine - INFO - Epoch(train) [137][150/293] lr: 5.000000e-04 eta: 3:57:30 time: 0.760315 data_time: 0.094895 memory: 21676 loss_kpt: 0.000543 acc_pose: 0.825081 loss: 0.000543 2022/09/16 21:36:17 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 21:36:53 - mmengine - INFO - Epoch(train) [137][200/293] lr: 5.000000e-04 eta: 3:57:00 time: 0.755214 data_time: 0.092154 memory: 21676 loss_kpt: 0.000544 acc_pose: 0.874087 loss: 0.000544 2022/09/16 21:37:31 - mmengine - INFO - Epoch(train) [137][250/293] lr: 5.000000e-04 eta: 3:56:29 time: 0.751252 data_time: 0.098990 memory: 21676 loss_kpt: 0.000552 acc_pose: 0.879838 loss: 0.000552 2022/09/16 21:38:03 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 21:38:03 - mmengine - INFO - Saving checkpoint at 137 epochs 2022/09/16 21:38:46 - mmengine - INFO - Epoch(train) [138][50/293] lr: 5.000000e-04 eta: 3:55:15 time: 0.773755 data_time: 0.101868 memory: 21676 loss_kpt: 0.000548 acc_pose: 0.853322 loss: 0.000548 2022/09/16 21:39:24 - mmengine - INFO - Epoch(train) [138][100/293] lr: 5.000000e-04 eta: 3:54:45 time: 0.762528 data_time: 0.096222 memory: 21676 loss_kpt: 0.000545 acc_pose: 0.892486 loss: 0.000545 2022/09/16 21:40:02 - mmengine - INFO - Epoch(train) [138][150/293] lr: 5.000000e-04 eta: 3:54:15 time: 0.761697 data_time: 0.093195 memory: 21676 loss_kpt: 0.000544 acc_pose: 0.821711 loss: 0.000544 2022/09/16 21:40:41 - mmengine - INFO - Epoch(train) [138][200/293] lr: 5.000000e-04 eta: 3:53:44 time: 0.767026 data_time: 0.100355 memory: 21676 loss_kpt: 0.000553 acc_pose: 0.845369 loss: 0.000553 2022/09/16 21:41:18 - mmengine - INFO - Epoch(train) [138][250/293] lr: 5.000000e-04 eta: 3:53:13 time: 0.751801 data_time: 0.098827 memory: 21676 loss_kpt: 0.000538 acc_pose: 0.859336 loss: 0.000538 2022/09/16 21:41:50 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 21:41:50 - mmengine - INFO - Saving checkpoint at 138 epochs 2022/09/16 21:42:34 - mmengine - INFO - Epoch(train) [139][50/293] lr: 5.000000e-04 eta: 3:52:00 time: 0.792451 data_time: 0.115356 memory: 21676 loss_kpt: 0.000568 acc_pose: 0.851139 loss: 0.000568 2022/09/16 21:43:13 - mmengine - INFO - Epoch(train) [139][100/293] lr: 5.000000e-04 eta: 3:51:30 time: 0.773168 data_time: 0.096922 memory: 21676 loss_kpt: 0.000552 acc_pose: 0.822918 loss: 0.000552 2022/09/16 21:43:53 - mmengine - INFO - Epoch(train) [139][150/293] lr: 5.000000e-04 eta: 3:51:01 time: 0.790078 data_time: 0.106977 memory: 21676 loss_kpt: 0.000547 acc_pose: 0.847965 loss: 0.000547 2022/09/16 21:44:32 - mmengine - INFO - Epoch(train) [139][200/293] lr: 5.000000e-04 eta: 3:50:31 time: 0.783200 data_time: 0.101950 memory: 21676 loss_kpt: 0.000543 acc_pose: 0.861636 loss: 0.000543 2022/09/16 21:45:11 - mmengine - INFO - Epoch(train) [139][250/293] lr: 5.000000e-04 eta: 3:50:00 time: 0.777080 data_time: 0.099724 memory: 21676 loss_kpt: 0.000536 acc_pose: 0.836633 loss: 0.000536 2022/09/16 21:45:43 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 21:45:43 - mmengine - INFO - Saving checkpoint at 139 epochs 2022/09/16 21:46:26 - mmengine - INFO - Epoch(train) [140][50/293] lr: 5.000000e-04 eta: 3:48:47 time: 0.781972 data_time: 0.104377 memory: 21676 loss_kpt: 0.000542 acc_pose: 0.861213 loss: 0.000542 2022/09/16 21:47:05 - mmengine - INFO - Epoch(train) [140][100/293] lr: 5.000000e-04 eta: 3:48:17 time: 0.767312 data_time: 0.096887 memory: 21676 loss_kpt: 0.000545 acc_pose: 0.844912 loss: 0.000545 2022/09/16 21:47:43 - mmengine - INFO - Epoch(train) [140][150/293] lr: 5.000000e-04 eta: 3:47:47 time: 0.768081 data_time: 0.100182 memory: 21676 loss_kpt: 0.000541 acc_pose: 0.880447 loss: 0.000541 2022/09/16 21:48:21 - mmengine - INFO - Epoch(train) [140][200/293] lr: 5.000000e-04 eta: 3:47:16 time: 0.767392 data_time: 0.101584 memory: 21676 loss_kpt: 0.000539 acc_pose: 0.837997 loss: 0.000539 2022/09/16 21:48:59 - mmengine - INFO - Epoch(train) [140][250/293] lr: 5.000000e-04 eta: 3:46:45 time: 0.752382 data_time: 0.097635 memory: 21676 loss_kpt: 0.000540 acc_pose: 0.870887 loss: 0.000540 2022/09/16 21:49:17 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 21:49:32 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 21:49:32 - mmengine - INFO - Saving checkpoint at 140 epochs 2022/09/16 21:49:47 - mmengine - INFO - Epoch(val) [140][50/407] eta: 0:01:17 time: 0.217329 data_time: 0.013995 memory: 21676 2022/09/16 21:49:58 - mmengine - INFO - Epoch(val) [140][100/407] eta: 0:01:04 time: 0.210045 data_time: 0.008584 memory: 1375 2022/09/16 21:50:08 - mmengine - INFO - Epoch(val) [140][150/407] eta: 0:00:54 time: 0.211582 data_time: 0.008434 memory: 1375 2022/09/16 21:50:19 - mmengine - INFO - Epoch(val) [140][200/407] eta: 0:00:44 time: 0.213225 data_time: 0.008963 memory: 1375 2022/09/16 21:50:30 - mmengine - INFO - Epoch(val) [140][250/407] eta: 0:00:33 time: 0.210669 data_time: 0.008710 memory: 1375 2022/09/16 21:50:40 - mmengine - INFO - Epoch(val) [140][300/407] eta: 0:00:22 time: 0.213587 data_time: 0.011733 memory: 1375 2022/09/16 21:50:51 - mmengine - INFO - Epoch(val) [140][350/407] eta: 0:00:11 time: 0.209569 data_time: 0.008355 memory: 1375 2022/09/16 21:51:01 - mmengine - INFO - Epoch(val) [140][400/407] eta: 0:00:01 time: 0.206666 data_time: 0.007980 memory: 1375 2022/09/16 21:51:37 - mmengine - INFO - Evaluating CocoMetric... 2022/09/16 21:51:50 - mmengine - INFO - Epoch(val) [140][407/407] coco/AP: 0.755495 coco/AP .5: 0.902277 coco/AP .75: 0.821300 coco/AP (M): 0.716498 coco/AP (L): 0.825410 coco/AR: 0.804660 coco/AR .5: 0.939861 coco/AR .75: 0.863193 coco/AR (M): 0.761568 coco/AR (L): 0.867596 2022/09/16 21:51:50 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220916/dark_w32_384/best_coco/AP_epoch_130.pth is removed 2022/09/16 21:51:53 - mmengine - INFO - The best checkpoint with 0.7555 coco/AP at 140 epoch is saved to best_coco/AP_epoch_140.pth. 2022/09/16 21:52:32 - mmengine - INFO - Epoch(train) [141][50/293] lr: 5.000000e-04 eta: 3:45:33 time: 0.780528 data_time: 0.106179 memory: 21676 loss_kpt: 0.000552 acc_pose: 0.833170 loss: 0.000552 2022/09/16 21:53:11 - mmengine - INFO - Epoch(train) [141][100/293] lr: 5.000000e-04 eta: 3:45:02 time: 0.777732 data_time: 0.096030 memory: 21676 loss_kpt: 0.000560 acc_pose: 0.840273 loss: 0.000560 2022/09/16 21:53:50 - mmengine - INFO - Epoch(train) [141][150/293] lr: 5.000000e-04 eta: 3:44:32 time: 0.779641 data_time: 0.096643 memory: 21676 loss_kpt: 0.000539 acc_pose: 0.848706 loss: 0.000539 2022/09/16 21:54:28 - mmengine - INFO - Epoch(train) [141][200/293] lr: 5.000000e-04 eta: 3:44:02 time: 0.763889 data_time: 0.096388 memory: 21676 loss_kpt: 0.000530 acc_pose: 0.854458 loss: 0.000530 2022/09/16 21:55:06 - mmengine - INFO - Epoch(train) [141][250/293] lr: 5.000000e-04 eta: 3:43:31 time: 0.763715 data_time: 0.098023 memory: 21676 loss_kpt: 0.000539 acc_pose: 0.878714 loss: 0.000539 2022/09/16 21:55:38 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 21:55:38 - mmengine - INFO - Saving checkpoint at 141 epochs 2022/09/16 21:56:23 - mmengine - INFO - Epoch(train) [142][50/293] lr: 5.000000e-04 eta: 3:42:19 time: 0.798907 data_time: 0.110009 memory: 21676 loss_kpt: 0.000538 acc_pose: 0.889272 loss: 0.000538 2022/09/16 21:57:02 - mmengine - INFO - Epoch(train) [142][100/293] lr: 5.000000e-04 eta: 3:41:49 time: 0.776984 data_time: 0.095316 memory: 21676 loss_kpt: 0.000547 acc_pose: 0.849608 loss: 0.000547 2022/09/16 21:57:40 - mmengine - INFO - Epoch(train) [142][150/293] lr: 5.000000e-04 eta: 3:41:18 time: 0.774570 data_time: 0.094183 memory: 21676 loss_kpt: 0.000542 acc_pose: 0.837581 loss: 0.000542 2022/09/16 21:58:20 - mmengine - INFO - Epoch(train) [142][200/293] lr: 5.000000e-04 eta: 3:40:48 time: 0.787499 data_time: 0.098267 memory: 21676 loss_kpt: 0.000545 acc_pose: 0.870949 loss: 0.000545 2022/09/16 21:58:58 - mmengine - INFO - Epoch(train) [142][250/293] lr: 5.000000e-04 eta: 3:40:18 time: 0.772212 data_time: 0.096048 memory: 21676 loss_kpt: 0.000547 acc_pose: 0.851672 loss: 0.000547 2022/09/16 21:59:31 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 21:59:31 - mmengine - INFO - Saving checkpoint at 142 epochs 2022/09/16 22:00:15 - mmengine - INFO - Epoch(train) [143][50/293] lr: 5.000000e-04 eta: 3:39:06 time: 0.780170 data_time: 0.110754 memory: 21676 loss_kpt: 0.000549 acc_pose: 0.849039 loss: 0.000549 2022/09/16 22:00:54 - mmengine - INFO - Epoch(train) [143][100/293] lr: 5.000000e-04 eta: 3:38:35 time: 0.784590 data_time: 0.097818 memory: 21676 loss_kpt: 0.000534 acc_pose: 0.832926 loss: 0.000534 2022/09/16 22:01:33 - mmengine - INFO - Epoch(train) [143][150/293] lr: 5.000000e-04 eta: 3:38:05 time: 0.784344 data_time: 0.098835 memory: 21676 loss_kpt: 0.000548 acc_pose: 0.808573 loss: 0.000548 2022/09/16 22:02:12 - mmengine - INFO - Epoch(train) [143][200/293] lr: 5.000000e-04 eta: 3:37:35 time: 0.777305 data_time: 0.092573 memory: 21676 loss_kpt: 0.000551 acc_pose: 0.848851 loss: 0.000551 2022/09/16 22:02:51 - mmengine - INFO - Epoch(train) [143][250/293] lr: 5.000000e-04 eta: 3:37:05 time: 0.782829 data_time: 0.100184 memory: 21676 loss_kpt: 0.000550 acc_pose: 0.826736 loss: 0.000550 2022/09/16 22:03:24 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 22:03:24 - mmengine - INFO - Saving checkpoint at 143 epochs 2022/09/16 22:04:08 - mmengine - INFO - Epoch(train) [144][50/293] lr: 5.000000e-04 eta: 3:35:53 time: 0.786116 data_time: 0.103148 memory: 21676 loss_kpt: 0.000548 acc_pose: 0.836722 loss: 0.000548 2022/09/16 22:04:47 - mmengine - INFO - Epoch(train) [144][100/293] lr: 5.000000e-04 eta: 3:35:22 time: 0.776861 data_time: 0.098504 memory: 21676 loss_kpt: 0.000543 acc_pose: 0.873809 loss: 0.000543 2022/09/16 22:04:48 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 22:05:26 - mmengine - INFO - Epoch(train) [144][150/293] lr: 5.000000e-04 eta: 3:34:52 time: 0.778290 data_time: 0.098063 memory: 21676 loss_kpt: 0.000548 acc_pose: 0.841509 loss: 0.000548 2022/09/16 22:06:05 - mmengine - INFO - Epoch(train) [144][200/293] lr: 5.000000e-04 eta: 3:34:22 time: 0.780658 data_time: 0.093583 memory: 21676 loss_kpt: 0.000533 acc_pose: 0.831062 loss: 0.000533 2022/09/16 22:06:44 - mmengine - INFO - Epoch(train) [144][250/293] lr: 5.000000e-04 eta: 3:33:51 time: 0.771354 data_time: 0.095545 memory: 21676 loss_kpt: 0.000535 acc_pose: 0.858556 loss: 0.000535 2022/09/16 22:07:16 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 22:07:16 - mmengine - INFO - Saving checkpoint at 144 epochs 2022/09/16 22:08:00 - mmengine - INFO - Epoch(train) [145][50/293] lr: 5.000000e-04 eta: 3:32:39 time: 0.783411 data_time: 0.104441 memory: 21676 loss_kpt: 0.000532 acc_pose: 0.863697 loss: 0.000532 2022/09/16 22:08:39 - mmengine - INFO - Epoch(train) [145][100/293] lr: 5.000000e-04 eta: 3:32:09 time: 0.782522 data_time: 0.093270 memory: 21676 loss_kpt: 0.000543 acc_pose: 0.840275 loss: 0.000543 2022/09/16 22:09:18 - mmengine - INFO - Epoch(train) [145][150/293] lr: 5.000000e-04 eta: 3:31:39 time: 0.791310 data_time: 0.095242 memory: 21676 loss_kpt: 0.000548 acc_pose: 0.861917 loss: 0.000548 2022/09/16 22:09:56 - mmengine - INFO - Epoch(train) [145][200/293] lr: 5.000000e-04 eta: 3:31:07 time: 0.744476 data_time: 0.091740 memory: 21676 loss_kpt: 0.000539 acc_pose: 0.863877 loss: 0.000539 2022/09/16 22:10:33 - mmengine - INFO - Epoch(train) [145][250/293] lr: 5.000000e-04 eta: 3:30:36 time: 0.755196 data_time: 0.093170 memory: 21676 loss_kpt: 0.000543 acc_pose: 0.836077 loss: 0.000543 2022/09/16 22:11:06 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 22:11:06 - mmengine - INFO - Saving checkpoint at 145 epochs 2022/09/16 22:11:50 - mmengine - INFO - Epoch(train) [146][50/293] lr: 5.000000e-04 eta: 3:29:25 time: 0.789846 data_time: 0.110345 memory: 21676 loss_kpt: 0.000549 acc_pose: 0.854370 loss: 0.000549 2022/09/16 22:12:29 - mmengine - INFO - Epoch(train) [146][100/293] lr: 5.000000e-04 eta: 3:28:55 time: 0.784174 data_time: 0.096185 memory: 21676 loss_kpt: 0.000541 acc_pose: 0.879252 loss: 0.000541 2022/09/16 22:13:08 - mmengine - INFO - Epoch(train) [146][150/293] lr: 5.000000e-04 eta: 3:28:24 time: 0.780756 data_time: 0.094406 memory: 21676 loss_kpt: 0.000539 acc_pose: 0.889137 loss: 0.000539 2022/09/16 22:13:47 - mmengine - INFO - Epoch(train) [146][200/293] lr: 5.000000e-04 eta: 3:27:54 time: 0.776902 data_time: 0.095209 memory: 21676 loss_kpt: 0.000538 acc_pose: 0.847083 loss: 0.000538 2022/09/16 22:14:26 - mmengine - INFO - Epoch(train) [146][250/293] lr: 5.000000e-04 eta: 3:27:23 time: 0.776300 data_time: 0.095008 memory: 21676 loss_kpt: 0.000554 acc_pose: 0.844220 loss: 0.000554 2022/09/16 22:14:58 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 22:14:58 - mmengine - INFO - Saving checkpoint at 146 epochs 2022/09/16 22:15:43 - mmengine - INFO - Epoch(train) [147][50/293] lr: 5.000000e-04 eta: 3:26:12 time: 0.793820 data_time: 0.104989 memory: 21676 loss_kpt: 0.000551 acc_pose: 0.852278 loss: 0.000551 2022/09/16 22:16:22 - mmengine - INFO - Epoch(train) [147][100/293] lr: 5.000000e-04 eta: 3:25:42 time: 0.782576 data_time: 0.096395 memory: 21676 loss_kpt: 0.000537 acc_pose: 0.872039 loss: 0.000537 2022/09/16 22:17:01 - mmengine - INFO - Epoch(train) [147][150/293] lr: 5.000000e-04 eta: 3:25:11 time: 0.786150 data_time: 0.097126 memory: 21676 loss_kpt: 0.000539 acc_pose: 0.854332 loss: 0.000539 2022/09/16 22:17:40 - mmengine - INFO - Epoch(train) [147][200/293] lr: 5.000000e-04 eta: 3:24:41 time: 0.779178 data_time: 0.100306 memory: 21676 loss_kpt: 0.000541 acc_pose: 0.843317 loss: 0.000541 2022/09/16 22:17:57 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 22:18:18 - mmengine - INFO - Epoch(train) [147][250/293] lr: 5.000000e-04 eta: 3:24:09 time: 0.756206 data_time: 0.100582 memory: 21676 loss_kpt: 0.000535 acc_pose: 0.852430 loss: 0.000535 2022/09/16 22:18:50 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 22:18:50 - mmengine - INFO - Saving checkpoint at 147 epochs 2022/09/16 22:19:34 - mmengine - INFO - Epoch(train) [148][50/293] lr: 5.000000e-04 eta: 3:22:58 time: 0.789799 data_time: 0.107218 memory: 21676 loss_kpt: 0.000538 acc_pose: 0.852447 loss: 0.000538 2022/09/16 22:20:13 - mmengine - INFO - Epoch(train) [148][100/293] lr: 5.000000e-04 eta: 3:22:28 time: 0.779432 data_time: 0.096391 memory: 21676 loss_kpt: 0.000538 acc_pose: 0.826779 loss: 0.000538 2022/09/16 22:20:52 - mmengine - INFO - Epoch(train) [148][150/293] lr: 5.000000e-04 eta: 3:21:57 time: 0.775311 data_time: 0.100816 memory: 21676 loss_kpt: 0.000535 acc_pose: 0.850016 loss: 0.000535 2022/09/16 22:21:31 - mmengine - INFO - Epoch(train) [148][200/293] lr: 5.000000e-04 eta: 3:21:26 time: 0.770479 data_time: 0.096667 memory: 21676 loss_kpt: 0.000553 acc_pose: 0.870029 loss: 0.000553 2022/09/16 22:22:10 - mmengine - INFO - Epoch(train) [148][250/293] lr: 5.000000e-04 eta: 3:20:56 time: 0.775244 data_time: 0.092553 memory: 21676 loss_kpt: 0.000539 acc_pose: 0.806651 loss: 0.000539 2022/09/16 22:22:44 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 22:22:44 - mmengine - INFO - Saving checkpoint at 148 epochs 2022/09/16 22:23:28 - mmengine - INFO - Epoch(train) [149][50/293] lr: 5.000000e-04 eta: 3:19:45 time: 0.778570 data_time: 0.113260 memory: 21676 loss_kpt: 0.000532 acc_pose: 0.853560 loss: 0.000532 2022/09/16 22:24:06 - mmengine - INFO - Epoch(train) [149][100/293] lr: 5.000000e-04 eta: 3:19:14 time: 0.762879 data_time: 0.093345 memory: 21676 loss_kpt: 0.000545 acc_pose: 0.865273 loss: 0.000545 2022/09/16 22:24:44 - mmengine - INFO - Epoch(train) [149][150/293] lr: 5.000000e-04 eta: 3:18:43 time: 0.766626 data_time: 0.099282 memory: 21676 loss_kpt: 0.000546 acc_pose: 0.802479 loss: 0.000546 2022/09/16 22:25:23 - mmengine - INFO - Epoch(train) [149][200/293] lr: 5.000000e-04 eta: 3:18:12 time: 0.774879 data_time: 0.097469 memory: 21676 loss_kpt: 0.000532 acc_pose: 0.867849 loss: 0.000532 2022/09/16 22:26:01 - mmengine - INFO - Epoch(train) [149][250/293] lr: 5.000000e-04 eta: 3:17:41 time: 0.755290 data_time: 0.092201 memory: 21676 loss_kpt: 0.000541 acc_pose: 0.846884 loss: 0.000541 2022/09/16 22:26:33 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 22:26:33 - mmengine - INFO - Saving checkpoint at 149 epochs 2022/09/16 22:27:17 - mmengine - INFO - Epoch(train) [150][50/293] lr: 5.000000e-04 eta: 3:16:31 time: 0.800842 data_time: 0.106203 memory: 21676 loss_kpt: 0.000538 acc_pose: 0.798336 loss: 0.000538 2022/09/16 22:27:56 - mmengine - INFO - Epoch(train) [150][100/293] lr: 5.000000e-04 eta: 3:16:00 time: 0.780495 data_time: 0.102718 memory: 21676 loss_kpt: 0.000547 acc_pose: 0.812933 loss: 0.000547 2022/09/16 22:28:35 - mmengine - INFO - Epoch(train) [150][150/293] lr: 5.000000e-04 eta: 3:15:29 time: 0.780593 data_time: 0.093089 memory: 21676 loss_kpt: 0.000547 acc_pose: 0.851261 loss: 0.000547 2022/09/16 22:29:14 - mmengine - INFO - Epoch(train) [150][200/293] lr: 5.000000e-04 eta: 3:14:58 time: 0.780487 data_time: 0.098044 memory: 21676 loss_kpt: 0.000544 acc_pose: 0.824918 loss: 0.000544 2022/09/16 22:29:53 - mmengine - INFO - Epoch(train) [150][250/293] lr: 5.000000e-04 eta: 3:14:28 time: 0.779809 data_time: 0.094810 memory: 21676 loss_kpt: 0.000547 acc_pose: 0.860533 loss: 0.000547 2022/09/16 22:30:26 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 22:30:26 - mmengine - INFO - Saving checkpoint at 150 epochs 2022/09/16 22:30:42 - mmengine - INFO - Epoch(val) [150][50/407] eta: 0:01:18 time: 0.218630 data_time: 0.016474 memory: 21676 2022/09/16 22:30:52 - mmengine - INFO - Epoch(val) [150][100/407] eta: 0:01:04 time: 0.210707 data_time: 0.008419 memory: 1375 2022/09/16 22:31:03 - mmengine - INFO - Epoch(val) [150][150/407] eta: 0:00:54 time: 0.210918 data_time: 0.008697 memory: 1375 2022/09/16 22:31:13 - mmengine - INFO - Epoch(val) [150][200/407] eta: 0:00:43 time: 0.209423 data_time: 0.008307 memory: 1375 2022/09/16 22:31:24 - mmengine - INFO - Epoch(val) [150][250/407] eta: 0:00:33 time: 0.210437 data_time: 0.008816 memory: 1375 2022/09/16 22:31:35 - mmengine - INFO - Epoch(val) [150][300/407] eta: 0:00:22 time: 0.212946 data_time: 0.008354 memory: 1375 2022/09/16 22:31:45 - mmengine - INFO - Epoch(val) [150][350/407] eta: 0:00:12 time: 0.210540 data_time: 0.008467 memory: 1375 2022/09/16 22:31:55 - mmengine - INFO - Epoch(val) [150][400/407] eta: 0:00:01 time: 0.208116 data_time: 0.008468 memory: 1375 2022/09/16 22:32:32 - mmengine - INFO - Evaluating CocoMetric... 2022/09/16 22:32:45 - mmengine - INFO - Epoch(val) [150][407/407] coco/AP: 0.755617 coco/AP .5: 0.904403 coco/AP .75: 0.821652 coco/AP (M): 0.716808 coco/AP (L): 0.824584 coco/AR: 0.803479 coco/AR .5: 0.940019 coco/AR .75: 0.861776 coco/AR (M): 0.760557 coco/AR (L): 0.865923 2022/09/16 22:32:45 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220916/dark_w32_384/best_coco/AP_epoch_140.pth is removed 2022/09/16 22:32:48 - mmengine - INFO - The best checkpoint with 0.7556 coco/AP at 150 epoch is saved to best_coco/AP_epoch_150.pth. 2022/09/16 22:33:28 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 22:33:28 - mmengine - INFO - Epoch(train) [151][50/293] lr: 5.000000e-04 eta: 3:13:17 time: 0.791322 data_time: 0.108077 memory: 21676 loss_kpt: 0.000542 acc_pose: 0.823134 loss: 0.000542 2022/09/16 22:34:08 - mmengine - INFO - Epoch(train) [151][100/293] lr: 5.000000e-04 eta: 3:12:47 time: 0.792286 data_time: 0.098516 memory: 21676 loss_kpt: 0.000546 acc_pose: 0.865387 loss: 0.000546 2022/09/16 22:34:47 - mmengine - INFO - Epoch(train) [151][150/293] lr: 5.000000e-04 eta: 3:12:16 time: 0.782021 data_time: 0.095979 memory: 21676 loss_kpt: 0.000541 acc_pose: 0.868723 loss: 0.000541 2022/09/16 22:35:26 - mmengine - INFO - Epoch(train) [151][200/293] lr: 5.000000e-04 eta: 3:11:46 time: 0.785330 data_time: 0.099080 memory: 21676 loss_kpt: 0.000547 acc_pose: 0.835087 loss: 0.000547 2022/09/16 22:36:05 - mmengine - INFO - Epoch(train) [151][250/293] lr: 5.000000e-04 eta: 3:11:15 time: 0.785326 data_time: 0.096765 memory: 21676 loss_kpt: 0.000539 acc_pose: 0.848226 loss: 0.000539 2022/09/16 22:36:39 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 22:36:39 - mmengine - INFO - Saving checkpoint at 151 epochs 2022/09/16 22:37:23 - mmengine - INFO - Epoch(train) [152][50/293] lr: 5.000000e-04 eta: 3:10:05 time: 0.789638 data_time: 0.103077 memory: 21676 loss_kpt: 0.000551 acc_pose: 0.871272 loss: 0.000551 2022/09/16 22:38:02 - mmengine - INFO - Epoch(train) [152][100/293] lr: 5.000000e-04 eta: 3:09:34 time: 0.787746 data_time: 0.095146 memory: 21676 loss_kpt: 0.000538 acc_pose: 0.820021 loss: 0.000538 2022/09/16 22:38:41 - mmengine - INFO - Epoch(train) [152][150/293] lr: 5.000000e-04 eta: 3:09:03 time: 0.777597 data_time: 0.094770 memory: 21676 loss_kpt: 0.000538 acc_pose: 0.811061 loss: 0.000538 2022/09/16 22:39:19 - mmengine - INFO - Epoch(train) [152][200/293] lr: 5.000000e-04 eta: 3:08:32 time: 0.753373 data_time: 0.101845 memory: 21676 loss_kpt: 0.000542 acc_pose: 0.879333 loss: 0.000542 2022/09/16 22:39:57 - mmengine - INFO - Epoch(train) [152][250/293] lr: 5.000000e-04 eta: 3:08:01 time: 0.755634 data_time: 0.092486 memory: 21676 loss_kpt: 0.000536 acc_pose: 0.839948 loss: 0.000536 2022/09/16 22:40:29 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 22:40:29 - mmengine - INFO - Saving checkpoint at 152 epochs 2022/09/16 22:41:13 - mmengine - INFO - Epoch(train) [153][50/293] lr: 5.000000e-04 eta: 3:06:51 time: 0.792999 data_time: 0.103553 memory: 21676 loss_kpt: 0.000530 acc_pose: 0.852040 loss: 0.000530 2022/09/16 22:41:52 - mmengine - INFO - Epoch(train) [153][100/293] lr: 5.000000e-04 eta: 3:06:20 time: 0.786360 data_time: 0.101690 memory: 21676 loss_kpt: 0.000550 acc_pose: 0.869142 loss: 0.000550 2022/09/16 22:42:31 - mmengine - INFO - Epoch(train) [153][150/293] lr: 5.000000e-04 eta: 3:05:49 time: 0.780694 data_time: 0.095433 memory: 21676 loss_kpt: 0.000540 acc_pose: 0.823458 loss: 0.000540 2022/09/16 22:43:09 - mmengine - INFO - Epoch(train) [153][200/293] lr: 5.000000e-04 eta: 3:05:18 time: 0.759155 data_time: 0.096206 memory: 21676 loss_kpt: 0.000539 acc_pose: 0.830081 loss: 0.000539 2022/09/16 22:43:46 - mmengine - INFO - Epoch(train) [153][250/293] lr: 5.000000e-04 eta: 3:04:46 time: 0.751667 data_time: 0.091485 memory: 21676 loss_kpt: 0.000528 acc_pose: 0.863345 loss: 0.000528 2022/09/16 22:44:19 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 22:44:19 - mmengine - INFO - Saving checkpoint at 153 epochs 2022/09/16 22:45:03 - mmengine - INFO - Epoch(train) [154][50/293] lr: 5.000000e-04 eta: 3:03:37 time: 0.788846 data_time: 0.105432 memory: 21676 loss_kpt: 0.000545 acc_pose: 0.858584 loss: 0.000545 2022/09/16 22:45:42 - mmengine - INFO - Epoch(train) [154][100/293] lr: 5.000000e-04 eta: 3:03:06 time: 0.781875 data_time: 0.095877 memory: 21676 loss_kpt: 0.000541 acc_pose: 0.870636 loss: 0.000541 2022/09/16 22:46:21 - mmengine - INFO - Epoch(train) [154][150/293] lr: 5.000000e-04 eta: 3:02:35 time: 0.785073 data_time: 0.095236 memory: 21676 loss_kpt: 0.000531 acc_pose: 0.815139 loss: 0.000531 2022/09/16 22:46:38 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 22:47:00 - mmengine - INFO - Epoch(train) [154][200/293] lr: 5.000000e-04 eta: 3:02:04 time: 0.775456 data_time: 0.098133 memory: 21676 loss_kpt: 0.000533 acc_pose: 0.842550 loss: 0.000533 2022/09/16 22:47:39 - mmengine - INFO - Epoch(train) [154][250/293] lr: 5.000000e-04 eta: 3:01:33 time: 0.781132 data_time: 0.091369 memory: 21676 loss_kpt: 0.000545 acc_pose: 0.863971 loss: 0.000545 2022/09/16 22:48:13 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 22:48:13 - mmengine - INFO - Saving checkpoint at 154 epochs 2022/09/16 22:48:56 - mmengine - INFO - Epoch(train) [155][50/293] lr: 5.000000e-04 eta: 3:00:23 time: 0.783186 data_time: 0.101949 memory: 21676 loss_kpt: 0.000544 acc_pose: 0.872274 loss: 0.000544 2022/09/16 22:49:36 - mmengine - INFO - Epoch(train) [155][100/293] lr: 5.000000e-04 eta: 2:59:52 time: 0.781773 data_time: 0.095566 memory: 21676 loss_kpt: 0.000520 acc_pose: 0.837882 loss: 0.000520 2022/09/16 22:50:15 - mmengine - INFO - Epoch(train) [155][150/293] lr: 5.000000e-04 eta: 2:59:21 time: 0.782706 data_time: 0.095126 memory: 21676 loss_kpt: 0.000540 acc_pose: 0.848777 loss: 0.000540 2022/09/16 22:50:53 - mmengine - INFO - Epoch(train) [155][200/293] lr: 5.000000e-04 eta: 2:58:50 time: 0.773218 data_time: 0.099609 memory: 21676 loss_kpt: 0.000537 acc_pose: 0.859207 loss: 0.000537 2022/09/16 22:51:31 - mmengine - INFO - Epoch(train) [155][250/293] lr: 5.000000e-04 eta: 2:58:19 time: 0.754195 data_time: 0.095773 memory: 21676 loss_kpt: 0.000543 acc_pose: 0.853359 loss: 0.000543 2022/09/16 22:52:04 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 22:52:04 - mmengine - INFO - Saving checkpoint at 155 epochs 2022/09/16 22:52:48 - mmengine - INFO - Epoch(train) [156][50/293] lr: 5.000000e-04 eta: 2:57:09 time: 0.790076 data_time: 0.108143 memory: 21676 loss_kpt: 0.000543 acc_pose: 0.844052 loss: 0.000543 2022/09/16 22:53:27 - mmengine - INFO - Epoch(train) [156][100/293] lr: 5.000000e-04 eta: 2:56:39 time: 0.787987 data_time: 0.100625 memory: 21676 loss_kpt: 0.000535 acc_pose: 0.874560 loss: 0.000535 2022/09/16 22:54:06 - mmengine - INFO - Epoch(train) [156][150/293] lr: 5.000000e-04 eta: 2:56:08 time: 0.780001 data_time: 0.096738 memory: 21676 loss_kpt: 0.000528 acc_pose: 0.855503 loss: 0.000528 2022/09/16 22:54:45 - mmengine - INFO - Epoch(train) [156][200/293] lr: 5.000000e-04 eta: 2:55:36 time: 0.778204 data_time: 0.095946 memory: 21676 loss_kpt: 0.000536 acc_pose: 0.831105 loss: 0.000536 2022/09/16 22:55:24 - mmengine - INFO - Epoch(train) [156][250/293] lr: 5.000000e-04 eta: 2:55:05 time: 0.778168 data_time: 0.091891 memory: 21676 loss_kpt: 0.000538 acc_pose: 0.816563 loss: 0.000538 2022/09/16 22:55:58 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 22:55:58 - mmengine - INFO - Saving checkpoint at 156 epochs 2022/09/16 22:56:42 - mmengine - INFO - Epoch(train) [157][50/293] lr: 5.000000e-04 eta: 2:53:56 time: 0.795398 data_time: 0.104771 memory: 21676 loss_kpt: 0.000534 acc_pose: 0.835613 loss: 0.000534 2022/09/16 22:57:21 - mmengine - INFO - Epoch(train) [157][100/293] lr: 5.000000e-04 eta: 2:53:25 time: 0.779939 data_time: 0.096797 memory: 21676 loss_kpt: 0.000543 acc_pose: 0.842406 loss: 0.000543 2022/09/16 22:57:59 - mmengine - INFO - Epoch(train) [157][150/293] lr: 5.000000e-04 eta: 2:52:54 time: 0.774403 data_time: 0.101940 memory: 21676 loss_kpt: 0.000524 acc_pose: 0.852161 loss: 0.000524 2022/09/16 22:58:38 - mmengine - INFO - Epoch(train) [157][200/293] lr: 5.000000e-04 eta: 2:52:23 time: 0.777681 data_time: 0.094591 memory: 21676 loss_kpt: 0.000531 acc_pose: 0.853628 loss: 0.000531 2022/09/16 22:59:16 - mmengine - INFO - Epoch(train) [157][250/293] lr: 5.000000e-04 eta: 2:51:51 time: 0.760856 data_time: 0.092758 memory: 21676 loss_kpt: 0.000549 acc_pose: 0.806598 loss: 0.000549 2022/09/16 22:59:48 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 22:59:49 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 22:59:49 - mmengine - INFO - Saving checkpoint at 157 epochs 2022/09/16 23:00:32 - mmengine - INFO - Epoch(train) [158][50/293] lr: 5.000000e-04 eta: 2:50:42 time: 0.785199 data_time: 0.106775 memory: 21676 loss_kpt: 0.000536 acc_pose: 0.861382 loss: 0.000536 2022/09/16 23:01:11 - mmengine - INFO - Epoch(train) [158][100/293] lr: 5.000000e-04 eta: 2:50:11 time: 0.778194 data_time: 0.111422 memory: 21676 loss_kpt: 0.000536 acc_pose: 0.834907 loss: 0.000536 2022/09/16 23:01:50 - mmengine - INFO - Epoch(train) [158][150/293] lr: 5.000000e-04 eta: 2:49:40 time: 0.780840 data_time: 0.098443 memory: 21676 loss_kpt: 0.000544 acc_pose: 0.835895 loss: 0.000544 2022/09/16 23:02:29 - mmengine - INFO - Epoch(train) [158][200/293] lr: 5.000000e-04 eta: 2:49:09 time: 0.781505 data_time: 0.102158 memory: 21676 loss_kpt: 0.000541 acc_pose: 0.885688 loss: 0.000541 2022/09/16 23:03:09 - mmengine - INFO - Epoch(train) [158][250/293] lr: 5.000000e-04 eta: 2:48:38 time: 0.786502 data_time: 0.101134 memory: 21676 loss_kpt: 0.000538 acc_pose: 0.899913 loss: 0.000538 2022/09/16 23:03:41 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 23:03:41 - mmengine - INFO - Saving checkpoint at 158 epochs 2022/09/16 23:04:25 - mmengine - INFO - Epoch(train) [159][50/293] lr: 5.000000e-04 eta: 2:47:29 time: 0.788676 data_time: 0.108349 memory: 21676 loss_kpt: 0.000557 acc_pose: 0.837227 loss: 0.000557 2022/09/16 23:05:05 - mmengine - INFO - Epoch(train) [159][100/293] lr: 5.000000e-04 eta: 2:46:58 time: 0.788807 data_time: 0.102405 memory: 21676 loss_kpt: 0.000536 acc_pose: 0.859866 loss: 0.000536 2022/09/16 23:05:43 - mmengine - INFO - Epoch(train) [159][150/293] lr: 5.000000e-04 eta: 2:46:27 time: 0.770421 data_time: 0.102408 memory: 21676 loss_kpt: 0.000541 acc_pose: 0.858547 loss: 0.000541 2022/09/16 23:06:23 - mmengine - INFO - Epoch(train) [159][200/293] lr: 5.000000e-04 eta: 2:45:56 time: 0.787366 data_time: 0.097639 memory: 21676 loss_kpt: 0.000537 acc_pose: 0.856265 loss: 0.000537 2022/09/16 23:07:02 - mmengine - INFO - Epoch(train) [159][250/293] lr: 5.000000e-04 eta: 2:45:25 time: 0.782697 data_time: 0.094691 memory: 21676 loss_kpt: 0.000540 acc_pose: 0.891672 loss: 0.000540 2022/09/16 23:07:35 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 23:07:35 - mmengine - INFO - Saving checkpoint at 159 epochs 2022/09/16 23:08:19 - mmengine - INFO - Epoch(train) [160][50/293] lr: 5.000000e-04 eta: 2:44:16 time: 0.787382 data_time: 0.105039 memory: 21676 loss_kpt: 0.000536 acc_pose: 0.858469 loss: 0.000536 2022/09/16 23:08:58 - mmengine - INFO - Epoch(train) [160][100/293] lr: 5.000000e-04 eta: 2:43:45 time: 0.777490 data_time: 0.101609 memory: 21676 loss_kpt: 0.000529 acc_pose: 0.856824 loss: 0.000529 2022/09/16 23:09:38 - mmengine - INFO - Epoch(train) [160][150/293] lr: 5.000000e-04 eta: 2:43:14 time: 0.788624 data_time: 0.097439 memory: 21676 loss_kpt: 0.000542 acc_pose: 0.844275 loss: 0.000542 2022/09/16 23:10:16 - mmengine - INFO - Epoch(train) [160][200/293] lr: 5.000000e-04 eta: 2:42:42 time: 0.777818 data_time: 0.097286 memory: 21676 loss_kpt: 0.000538 acc_pose: 0.797032 loss: 0.000538 2022/09/16 23:10:55 - mmengine - INFO - Epoch(train) [160][250/293] lr: 5.000000e-04 eta: 2:42:11 time: 0.772799 data_time: 0.094097 memory: 21676 loss_kpt: 0.000530 acc_pose: 0.847359 loss: 0.000530 2022/09/16 23:11:27 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 23:11:27 - mmengine - INFO - Saving checkpoint at 160 epochs 2022/09/16 23:11:43 - mmengine - INFO - Epoch(val) [160][50/407] eta: 0:01:17 time: 0.216962 data_time: 0.013757 memory: 21676 2022/09/16 23:11:53 - mmengine - INFO - Epoch(val) [160][100/407] eta: 0:01:05 time: 0.214374 data_time: 0.009222 memory: 1375 2022/09/16 23:12:04 - mmengine - INFO - Epoch(val) [160][150/407] eta: 0:00:54 time: 0.211739 data_time: 0.009050 memory: 1375 2022/09/16 23:12:14 - mmengine - INFO - Epoch(val) [160][200/407] eta: 0:00:43 time: 0.209409 data_time: 0.008645 memory: 1375 2022/09/16 23:12:25 - mmengine - INFO - Epoch(val) [160][250/407] eta: 0:00:33 time: 0.210629 data_time: 0.008589 memory: 1375 2022/09/16 23:12:36 - mmengine - INFO - Epoch(val) [160][300/407] eta: 0:00:23 time: 0.215203 data_time: 0.008516 memory: 1375 2022/09/16 23:12:46 - mmengine - INFO - Epoch(val) [160][350/407] eta: 0:00:11 time: 0.210518 data_time: 0.008826 memory: 1375 2022/09/16 23:12:57 - mmengine - INFO - Epoch(val) [160][400/407] eta: 0:00:01 time: 0.206874 data_time: 0.008299 memory: 1375 2022/09/16 23:13:32 - mmengine - INFO - Evaluating CocoMetric... 2022/09/16 23:13:45 - mmengine - INFO - Epoch(val) [160][407/407] coco/AP: 0.755310 coco/AP .5: 0.898992 coco/AP .75: 0.820194 coco/AP (M): 0.716898 coco/AP (L): 0.825999 coco/AR: 0.805652 coco/AR .5: 0.938445 coco/AR .75: 0.864137 coco/AR (M): 0.761978 coco/AR (L): 0.869045 2022/09/16 23:14:25 - mmengine - INFO - Epoch(train) [161][50/293] lr: 5.000000e-04 eta: 2:41:02 time: 0.790883 data_time: 0.107808 memory: 21676 loss_kpt: 0.000524 acc_pose: 0.869637 loss: 0.000524 2022/09/16 23:15:03 - mmengine - INFO - Epoch(train) [161][100/293] lr: 5.000000e-04 eta: 2:40:31 time: 0.754054 data_time: 0.094788 memory: 21676 loss_kpt: 0.000540 acc_pose: 0.881981 loss: 0.000540 2022/09/16 23:15:18 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 23:15:41 - mmengine - INFO - Epoch(train) [161][150/293] lr: 5.000000e-04 eta: 2:39:59 time: 0.758342 data_time: 0.098389 memory: 21676 loss_kpt: 0.000540 acc_pose: 0.848997 loss: 0.000540 2022/09/16 23:16:19 - mmengine - INFO - Epoch(train) [161][200/293] lr: 5.000000e-04 eta: 2:39:28 time: 0.766009 data_time: 0.099290 memory: 21676 loss_kpt: 0.000535 acc_pose: 0.886681 loss: 0.000535 2022/09/16 23:16:57 - mmengine - INFO - Epoch(train) [161][250/293] lr: 5.000000e-04 eta: 2:38:56 time: 0.758741 data_time: 0.100270 memory: 21676 loss_kpt: 0.000539 acc_pose: 0.811256 loss: 0.000539 2022/09/16 23:17:29 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 23:17:29 - mmengine - INFO - Saving checkpoint at 161 epochs 2022/09/16 23:18:13 - mmengine - INFO - Epoch(train) [162][50/293] lr: 5.000000e-04 eta: 2:37:48 time: 0.786315 data_time: 0.108097 memory: 21676 loss_kpt: 0.000536 acc_pose: 0.846787 loss: 0.000536 2022/09/16 23:18:52 - mmengine - INFO - Epoch(train) [162][100/293] lr: 5.000000e-04 eta: 2:37:16 time: 0.773609 data_time: 0.096822 memory: 21676 loss_kpt: 0.000531 acc_pose: 0.835652 loss: 0.000531 2022/09/16 23:19:31 - mmengine - INFO - Epoch(train) [162][150/293] lr: 5.000000e-04 eta: 2:36:45 time: 0.783152 data_time: 0.098352 memory: 21676 loss_kpt: 0.000550 acc_pose: 0.866073 loss: 0.000550 2022/09/16 23:20:10 - mmengine - INFO - Epoch(train) [162][200/293] lr: 5.000000e-04 eta: 2:36:14 time: 0.776703 data_time: 0.099002 memory: 21676 loss_kpt: 0.000545 acc_pose: 0.820820 loss: 0.000545 2022/09/16 23:20:48 - mmengine - INFO - Epoch(train) [162][250/293] lr: 5.000000e-04 eta: 2:35:42 time: 0.768438 data_time: 0.096117 memory: 21676 loss_kpt: 0.000538 acc_pose: 0.876561 loss: 0.000538 2022/09/16 23:21:20 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 23:21:20 - mmengine - INFO - Saving checkpoint at 162 epochs 2022/09/16 23:22:04 - mmengine - INFO - Epoch(train) [163][50/293] lr: 5.000000e-04 eta: 2:34:34 time: 0.788732 data_time: 0.107477 memory: 21676 loss_kpt: 0.000535 acc_pose: 0.870207 loss: 0.000535 2022/09/16 23:22:44 - mmengine - INFO - Epoch(train) [163][100/293] lr: 5.000000e-04 eta: 2:34:03 time: 0.787718 data_time: 0.096985 memory: 21676 loss_kpt: 0.000533 acc_pose: 0.850747 loss: 0.000533 2022/09/16 23:23:23 - mmengine - INFO - Epoch(train) [163][150/293] lr: 5.000000e-04 eta: 2:33:31 time: 0.784744 data_time: 0.100651 memory: 21676 loss_kpt: 0.000532 acc_pose: 0.862479 loss: 0.000532 2022/09/16 23:24:02 - mmengine - INFO - Epoch(train) [163][200/293] lr: 5.000000e-04 eta: 2:33:00 time: 0.778886 data_time: 0.091786 memory: 21676 loss_kpt: 0.000530 acc_pose: 0.847135 loss: 0.000530 2022/09/16 23:24:41 - mmengine - INFO - Epoch(train) [163][250/293] lr: 5.000000e-04 eta: 2:32:29 time: 0.779508 data_time: 0.090847 memory: 21676 loss_kpt: 0.000528 acc_pose: 0.878382 loss: 0.000528 2022/09/16 23:25:14 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 23:25:14 - mmengine - INFO - Saving checkpoint at 163 epochs 2022/09/16 23:25:57 - mmengine - INFO - Epoch(train) [164][50/293] lr: 5.000000e-04 eta: 2:31:20 time: 0.779433 data_time: 0.108875 memory: 21676 loss_kpt: 0.000541 acc_pose: 0.851842 loss: 0.000541 2022/09/16 23:26:36 - mmengine - INFO - Epoch(train) [164][100/293] lr: 5.000000e-04 eta: 2:30:49 time: 0.781653 data_time: 0.097465 memory: 21676 loss_kpt: 0.000538 acc_pose: 0.811230 loss: 0.000538 2022/09/16 23:27:15 - mmengine - INFO - Epoch(train) [164][150/293] lr: 5.000000e-04 eta: 2:30:18 time: 0.780065 data_time: 0.095321 memory: 21676 loss_kpt: 0.000525 acc_pose: 0.873224 loss: 0.000525 2022/09/16 23:27:55 - mmengine - INFO - Epoch(train) [164][200/293] lr: 5.000000e-04 eta: 2:29:46 time: 0.785179 data_time: 0.095780 memory: 21676 loss_kpt: 0.000530 acc_pose: 0.831956 loss: 0.000530 2022/09/16 23:28:26 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 23:28:33 - mmengine - INFO - Epoch(train) [164][250/293] lr: 5.000000e-04 eta: 2:29:15 time: 0.766770 data_time: 0.095027 memory: 21676 loss_kpt: 0.000539 acc_pose: 0.893445 loss: 0.000539 2022/09/16 23:29:05 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 23:29:05 - mmengine - INFO - Saving checkpoint at 164 epochs 2022/09/16 23:29:49 - mmengine - INFO - Epoch(train) [165][50/293] lr: 5.000000e-04 eta: 2:28:07 time: 0.793359 data_time: 0.108924 memory: 21676 loss_kpt: 0.000523 acc_pose: 0.821686 loss: 0.000523 2022/09/16 23:30:28 - mmengine - INFO - Epoch(train) [165][100/293] lr: 5.000000e-04 eta: 2:27:35 time: 0.766254 data_time: 0.098817 memory: 21676 loss_kpt: 0.000534 acc_pose: 0.860900 loss: 0.000534 2022/09/16 23:31:07 - mmengine - INFO - Epoch(train) [165][150/293] lr: 5.000000e-04 eta: 2:27:04 time: 0.781095 data_time: 0.104137 memory: 21676 loss_kpt: 0.000549 acc_pose: 0.869359 loss: 0.000549 2022/09/16 23:31:46 - mmengine - INFO - Epoch(train) [165][200/293] lr: 5.000000e-04 eta: 2:26:32 time: 0.779437 data_time: 0.100019 memory: 21676 loss_kpt: 0.000536 acc_pose: 0.913695 loss: 0.000536 2022/09/16 23:32:25 - mmengine - INFO - Epoch(train) [165][250/293] lr: 5.000000e-04 eta: 2:26:01 time: 0.788745 data_time: 0.103962 memory: 21676 loss_kpt: 0.000538 acc_pose: 0.850681 loss: 0.000538 2022/09/16 23:32:58 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 23:32:58 - mmengine - INFO - Saving checkpoint at 165 epochs 2022/09/16 23:33:42 - mmengine - INFO - Epoch(train) [166][50/293] lr: 5.000000e-04 eta: 2:24:53 time: 0.787903 data_time: 0.102436 memory: 21676 loss_kpt: 0.000536 acc_pose: 0.847326 loss: 0.000536 2022/09/16 23:34:21 - mmengine - INFO - Epoch(train) [166][100/293] lr: 5.000000e-04 eta: 2:24:22 time: 0.773863 data_time: 0.094648 memory: 21676 loss_kpt: 0.000532 acc_pose: 0.854165 loss: 0.000532 2022/09/16 23:35:01 - mmengine - INFO - Epoch(train) [166][150/293] lr: 5.000000e-04 eta: 2:23:50 time: 0.790217 data_time: 0.099849 memory: 21676 loss_kpt: 0.000554 acc_pose: 0.849419 loss: 0.000554 2022/09/16 23:35:40 - mmengine - INFO - Epoch(train) [166][200/293] lr: 5.000000e-04 eta: 2:23:19 time: 0.777359 data_time: 0.091794 memory: 21676 loss_kpt: 0.000532 acc_pose: 0.840119 loss: 0.000532 2022/09/16 23:36:18 - mmengine - INFO - Epoch(train) [166][250/293] lr: 5.000000e-04 eta: 2:22:47 time: 0.778444 data_time: 0.092465 memory: 21676 loss_kpt: 0.000539 acc_pose: 0.889036 loss: 0.000539 2022/09/16 23:36:51 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 23:36:51 - mmengine - INFO - Saving checkpoint at 166 epochs 2022/09/16 23:37:35 - mmengine - INFO - Epoch(train) [167][50/293] lr: 5.000000e-04 eta: 2:21:40 time: 0.793911 data_time: 0.113143 memory: 21676 loss_kpt: 0.000534 acc_pose: 0.835334 loss: 0.000534 2022/09/16 23:38:14 - mmengine - INFO - Epoch(train) [167][100/293] lr: 5.000000e-04 eta: 2:21:09 time: 0.792562 data_time: 0.098399 memory: 21676 loss_kpt: 0.000546 acc_pose: 0.833585 loss: 0.000546 2022/09/16 23:38:54 - mmengine - INFO - Epoch(train) [167][150/293] lr: 5.000000e-04 eta: 2:20:37 time: 0.783156 data_time: 0.096336 memory: 21676 loss_kpt: 0.000521 acc_pose: 0.884808 loss: 0.000521 2022/09/16 23:39:33 - mmengine - INFO - Epoch(train) [167][200/293] lr: 5.000000e-04 eta: 2:20:05 time: 0.779988 data_time: 0.097669 memory: 21676 loss_kpt: 0.000538 acc_pose: 0.858015 loss: 0.000538 2022/09/16 23:40:10 - mmengine - INFO - Epoch(train) [167][250/293] lr: 5.000000e-04 eta: 2:19:34 time: 0.754663 data_time: 0.095857 memory: 21676 loss_kpt: 0.000536 acc_pose: 0.805083 loss: 0.000536 2022/09/16 23:40:42 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 23:40:42 - mmengine - INFO - Saving checkpoint at 167 epochs 2022/09/16 23:41:27 - mmengine - INFO - Epoch(train) [168][50/293] lr: 5.000000e-04 eta: 2:18:26 time: 0.800556 data_time: 0.101356 memory: 21676 loss_kpt: 0.000531 acc_pose: 0.874589 loss: 0.000531 2022/09/16 23:41:43 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 23:42:07 - mmengine - INFO - Epoch(train) [168][100/293] lr: 5.000000e-04 eta: 2:17:55 time: 0.799762 data_time: 0.094382 memory: 21676 loss_kpt: 0.000543 acc_pose: 0.853028 loss: 0.000543 2022/09/16 23:42:45 - mmengine - INFO - Epoch(train) [168][150/293] lr: 5.000000e-04 eta: 2:17:23 time: 0.758880 data_time: 0.100352 memory: 21676 loss_kpt: 0.000541 acc_pose: 0.795945 loss: 0.000541 2022/09/16 23:43:23 - mmengine - INFO - Epoch(train) [168][200/293] lr: 5.000000e-04 eta: 2:16:51 time: 0.758231 data_time: 0.095121 memory: 21676 loss_kpt: 0.000535 acc_pose: 0.885548 loss: 0.000535 2022/09/16 23:44:01 - mmengine - INFO - Epoch(train) [168][250/293] lr: 5.000000e-04 eta: 2:16:20 time: 0.770128 data_time: 0.094121 memory: 21676 loss_kpt: 0.000537 acc_pose: 0.861281 loss: 0.000537 2022/09/16 23:44:34 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 23:44:34 - mmengine - INFO - Saving checkpoint at 168 epochs 2022/09/16 23:45:18 - mmengine - INFO - Epoch(train) [169][50/293] lr: 5.000000e-04 eta: 2:15:12 time: 0.793781 data_time: 0.113803 memory: 21676 loss_kpt: 0.000548 acc_pose: 0.866190 loss: 0.000548 2022/09/16 23:45:56 - mmengine - INFO - Epoch(train) [169][100/293] lr: 5.000000e-04 eta: 2:14:41 time: 0.764976 data_time: 0.102843 memory: 21676 loss_kpt: 0.000536 acc_pose: 0.864965 loss: 0.000536 2022/09/16 23:46:34 - mmengine - INFO - Epoch(train) [169][150/293] lr: 5.000000e-04 eta: 2:14:09 time: 0.770120 data_time: 0.107811 memory: 21676 loss_kpt: 0.000533 acc_pose: 0.878788 loss: 0.000533 2022/09/16 23:47:13 - mmengine - INFO - Epoch(train) [169][200/293] lr: 5.000000e-04 eta: 2:13:37 time: 0.777726 data_time: 0.104110 memory: 21676 loss_kpt: 0.000537 acc_pose: 0.868710 loss: 0.000537 2022/09/16 23:47:52 - mmengine - INFO - Epoch(train) [169][250/293] lr: 5.000000e-04 eta: 2:13:05 time: 0.769881 data_time: 0.104196 memory: 21676 loss_kpt: 0.000529 acc_pose: 0.822406 loss: 0.000529 2022/09/16 23:48:25 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 23:48:25 - mmengine - INFO - Saving checkpoint at 169 epochs 2022/09/16 23:49:09 - mmengine - INFO - Epoch(train) [170][50/293] lr: 5.000000e-04 eta: 2:11:58 time: 0.794087 data_time: 0.107876 memory: 21676 loss_kpt: 0.000542 acc_pose: 0.815530 loss: 0.000542 2022/09/16 23:49:48 - mmengine - INFO - Epoch(train) [170][100/293] lr: 5.000000e-04 eta: 2:11:27 time: 0.764515 data_time: 0.095685 memory: 21676 loss_kpt: 0.000530 acc_pose: 0.828977 loss: 0.000530 2022/09/16 23:50:26 - mmengine - INFO - Epoch(train) [170][150/293] lr: 5.000000e-04 eta: 2:10:55 time: 0.765836 data_time: 0.092960 memory: 21676 loss_kpt: 0.000540 acc_pose: 0.850213 loss: 0.000540 2022/09/16 23:51:05 - mmengine - INFO - Epoch(train) [170][200/293] lr: 5.000000e-04 eta: 2:10:23 time: 0.777346 data_time: 0.101816 memory: 21676 loss_kpt: 0.000533 acc_pose: 0.830281 loss: 0.000533 2022/09/16 23:51:43 - mmengine - INFO - Epoch(train) [170][250/293] lr: 5.000000e-04 eta: 2:09:51 time: 0.762308 data_time: 0.101409 memory: 21676 loss_kpt: 0.000533 acc_pose: 0.843067 loss: 0.000533 2022/09/16 23:52:15 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 23:52:15 - mmengine - INFO - Saving checkpoint at 170 epochs 2022/09/16 23:52:31 - mmengine - INFO - Epoch(val) [170][50/407] eta: 0:01:17 time: 0.216995 data_time: 0.014385 memory: 21676 2022/09/16 23:52:41 - mmengine - INFO - Epoch(val) [170][100/407] eta: 0:01:04 time: 0.210789 data_time: 0.008500 memory: 1375 2022/09/16 23:52:51 - mmengine - INFO - Epoch(val) [170][150/407] eta: 0:00:53 time: 0.206739 data_time: 0.008382 memory: 1375 2022/09/16 23:53:02 - mmengine - INFO - Epoch(val) [170][200/407] eta: 0:00:44 time: 0.212995 data_time: 0.008576 memory: 1375 2022/09/16 23:53:13 - mmengine - INFO - Epoch(val) [170][250/407] eta: 0:00:32 time: 0.209920 data_time: 0.008305 memory: 1375 2022/09/16 23:53:23 - mmengine - INFO - Epoch(val) [170][300/407] eta: 0:00:22 time: 0.211382 data_time: 0.008739 memory: 1375 2022/09/16 23:53:34 - mmengine - INFO - Epoch(val) [170][350/407] eta: 0:00:11 time: 0.209261 data_time: 0.008864 memory: 1375 2022/09/16 23:53:44 - mmengine - INFO - Epoch(val) [170][400/407] eta: 0:00:01 time: 0.206697 data_time: 0.007978 memory: 1375 2022/09/16 23:54:20 - mmengine - INFO - Evaluating CocoMetric... 2022/09/16 23:54:33 - mmengine - INFO - Epoch(val) [170][407/407] coco/AP: 0.756660 coco/AP .5: 0.900360 coco/AP .75: 0.820060 coco/AP (M): 0.717224 coco/AP (L): 0.827556 coco/AR: 0.806203 coco/AR .5: 0.938445 coco/AR .75: 0.862878 coco/AR (M): 0.762469 coco/AR (L): 0.869379 2022/09/16 23:54:33 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220916/dark_w32_384/best_coco/AP_epoch_150.pth is removed 2022/09/16 23:54:37 - mmengine - INFO - The best checkpoint with 0.7567 coco/AP at 170 epoch is saved to best_coco/AP_epoch_170.pth. 2022/09/16 23:55:16 - mmengine - INFO - Epoch(train) [171][50/293] lr: 5.000000e-05 eta: 2:08:44 time: 0.792387 data_time: 0.106454 memory: 21676 loss_kpt: 0.000524 acc_pose: 0.863196 loss: 0.000524 2022/09/16 23:55:55 - mmengine - INFO - Epoch(train) [171][100/293] lr: 5.000000e-05 eta: 2:08:12 time: 0.764509 data_time: 0.099057 memory: 21676 loss_kpt: 0.000531 acc_pose: 0.851306 loss: 0.000531 2022/09/16 23:56:33 - mmengine - INFO - Epoch(train) [171][150/293] lr: 5.000000e-05 eta: 2:07:41 time: 0.766317 data_time: 0.101660 memory: 21676 loss_kpt: 0.000527 acc_pose: 0.832541 loss: 0.000527 2022/09/16 23:57:04 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 23:57:11 - mmengine - INFO - Epoch(train) [171][200/293] lr: 5.000000e-05 eta: 2:07:09 time: 0.764637 data_time: 0.094955 memory: 21676 loss_kpt: 0.000517 acc_pose: 0.871566 loss: 0.000517 2022/09/16 23:57:49 - mmengine - INFO - Epoch(train) [171][250/293] lr: 5.000000e-05 eta: 2:06:37 time: 0.753716 data_time: 0.098031 memory: 21676 loss_kpt: 0.000512 acc_pose: 0.878781 loss: 0.000512 2022/09/16 23:58:21 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/16 23:58:21 - mmengine - INFO - Saving checkpoint at 171 epochs 2022/09/16 23:59:05 - mmengine - INFO - Epoch(train) [172][50/293] lr: 5.000000e-05 eta: 2:05:30 time: 0.782157 data_time: 0.099842 memory: 21676 loss_kpt: 0.000506 acc_pose: 0.866534 loss: 0.000506 2022/09/16 23:59:43 - mmengine - INFO - Epoch(train) [172][100/293] lr: 5.000000e-05 eta: 2:04:58 time: 0.769239 data_time: 0.098125 memory: 21676 loss_kpt: 0.000507 acc_pose: 0.840952 loss: 0.000507 2022/09/17 00:00:23 - mmengine - INFO - Epoch(train) [172][150/293] lr: 5.000000e-05 eta: 2:04:26 time: 0.803438 data_time: 0.099196 memory: 21676 loss_kpt: 0.000514 acc_pose: 0.869605 loss: 0.000514 2022/09/17 00:01:02 - mmengine - INFO - Epoch(train) [172][200/293] lr: 5.000000e-05 eta: 2:03:55 time: 0.773966 data_time: 0.095432 memory: 21676 loss_kpt: 0.000522 acc_pose: 0.873027 loss: 0.000522 2022/09/17 00:01:41 - mmengine - INFO - Epoch(train) [172][250/293] lr: 5.000000e-05 eta: 2:03:23 time: 0.784865 data_time: 0.094692 memory: 21676 loss_kpt: 0.000509 acc_pose: 0.876544 loss: 0.000509 2022/09/17 00:02:14 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/17 00:02:15 - mmengine - INFO - Saving checkpoint at 172 epochs 2022/09/17 00:02:59 - mmengine - INFO - Epoch(train) [173][50/293] lr: 5.000000e-05 eta: 2:02:16 time: 0.799483 data_time: 0.107328 memory: 21676 loss_kpt: 0.000509 acc_pose: 0.863993 loss: 0.000509 2022/09/17 00:03:38 - mmengine - INFO - Epoch(train) [173][100/293] lr: 5.000000e-05 eta: 2:01:45 time: 0.781673 data_time: 0.102630 memory: 21676 loss_kpt: 0.000509 acc_pose: 0.886296 loss: 0.000509 2022/09/17 00:04:18 - mmengine - INFO - Epoch(train) [173][150/293] lr: 5.000000e-05 eta: 2:01:13 time: 0.792658 data_time: 0.104757 memory: 21676 loss_kpt: 0.000529 acc_pose: 0.824187 loss: 0.000529 2022/09/17 00:04:57 - mmengine - INFO - Epoch(train) [173][200/293] lr: 5.000000e-05 eta: 2:00:41 time: 0.784395 data_time: 0.098200 memory: 21676 loss_kpt: 0.000508 acc_pose: 0.891737 loss: 0.000508 2022/09/17 00:05:36 - mmengine - INFO - Epoch(train) [173][250/293] lr: 5.000000e-05 eta: 2:00:09 time: 0.785315 data_time: 0.102921 memory: 21676 loss_kpt: 0.000503 acc_pose: 0.845525 loss: 0.000503 2022/09/17 00:06:09 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/17 00:06:09 - mmengine - INFO - Saving checkpoint at 173 epochs 2022/09/17 00:06:53 - mmengine - INFO - Epoch(train) [174][50/293] lr: 5.000000e-05 eta: 1:59:03 time: 0.771140 data_time: 0.102485 memory: 21676 loss_kpt: 0.000515 acc_pose: 0.856078 loss: 0.000515 2022/09/17 00:07:31 - mmengine - INFO - Epoch(train) [174][100/293] lr: 5.000000e-05 eta: 1:58:31 time: 0.773608 data_time: 0.098373 memory: 21676 loss_kpt: 0.000511 acc_pose: 0.846661 loss: 0.000511 2022/09/17 00:08:11 - mmengine - INFO - Epoch(train) [174][150/293] lr: 5.000000e-05 eta: 1:57:59 time: 0.785044 data_time: 0.100455 memory: 21676 loss_kpt: 0.000508 acc_pose: 0.871143 loss: 0.000508 2022/09/17 00:08:49 - mmengine - INFO - Epoch(train) [174][200/293] lr: 5.000000e-05 eta: 1:57:27 time: 0.772198 data_time: 0.095074 memory: 21676 loss_kpt: 0.000502 acc_pose: 0.887801 loss: 0.000502 2022/09/17 00:09:28 - mmengine - INFO - Epoch(train) [174][250/293] lr: 5.000000e-05 eta: 1:56:55 time: 0.768066 data_time: 0.095355 memory: 21676 loss_kpt: 0.000503 acc_pose: 0.831699 loss: 0.000503 2022/09/17 00:10:00 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/17 00:10:00 - mmengine - INFO - Saving checkpoint at 174 epochs 2022/09/17 00:10:19 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/17 00:10:44 - mmengine - INFO - Epoch(train) [175][50/293] lr: 5.000000e-05 eta: 1:55:49 time: 0.786783 data_time: 0.114649 memory: 21676 loss_kpt: 0.000489 acc_pose: 0.839804 loss: 0.000489 2022/09/17 00:11:23 - mmengine - INFO - Epoch(train) [175][100/293] lr: 5.000000e-05 eta: 1:55:17 time: 0.775151 data_time: 0.095326 memory: 21676 loss_kpt: 0.000494 acc_pose: 0.870280 loss: 0.000494 2022/09/17 00:12:02 - mmengine - INFO - Epoch(train) [175][150/293] lr: 5.000000e-05 eta: 1:54:45 time: 0.789923 data_time: 0.097172 memory: 21676 loss_kpt: 0.000511 acc_pose: 0.899345 loss: 0.000511 2022/09/17 00:12:40 - mmengine - INFO - Epoch(train) [175][200/293] lr: 5.000000e-05 eta: 1:54:13 time: 0.754647 data_time: 0.096154 memory: 21676 loss_kpt: 0.000503 acc_pose: 0.883314 loss: 0.000503 2022/09/17 00:13:18 - mmengine - INFO - Epoch(train) [175][250/293] lr: 5.000000e-05 eta: 1:53:41 time: 0.757337 data_time: 0.097903 memory: 21676 loss_kpt: 0.000499 acc_pose: 0.846489 loss: 0.000499 2022/09/17 00:13:50 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/17 00:13:50 - mmengine - INFO - Saving checkpoint at 175 epochs 2022/09/17 00:14:33 - mmengine - INFO - Epoch(train) [176][50/293] lr: 5.000000e-05 eta: 1:52:35 time: 0.784764 data_time: 0.108086 memory: 21676 loss_kpt: 0.000497 acc_pose: 0.836800 loss: 0.000497 2022/09/17 00:15:13 - mmengine - INFO - Epoch(train) [176][100/293] lr: 5.000000e-05 eta: 1:52:03 time: 0.785452 data_time: 0.099387 memory: 21676 loss_kpt: 0.000514 acc_pose: 0.868995 loss: 0.000514 2022/09/17 00:15:52 - mmengine - INFO - Epoch(train) [176][150/293] lr: 5.000000e-05 eta: 1:51:31 time: 0.776348 data_time: 0.097625 memory: 21676 loss_kpt: 0.000515 acc_pose: 0.880301 loss: 0.000515 2022/09/17 00:16:30 - mmengine - INFO - Epoch(train) [176][200/293] lr: 5.000000e-05 eta: 1:50:59 time: 0.771261 data_time: 0.096659 memory: 21676 loss_kpt: 0.000511 acc_pose: 0.889794 loss: 0.000511 2022/09/17 00:17:09 - mmengine - INFO - Epoch(train) [176][250/293] lr: 5.000000e-05 eta: 1:50:27 time: 0.779325 data_time: 0.098870 memory: 21676 loss_kpt: 0.000491 acc_pose: 0.843246 loss: 0.000491 2022/09/17 00:17:42 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/17 00:17:42 - mmengine - INFO - Saving checkpoint at 176 epochs 2022/09/17 00:18:26 - mmengine - INFO - Epoch(train) [177][50/293] lr: 5.000000e-05 eta: 1:49:21 time: 0.785712 data_time: 0.114439 memory: 21676 loss_kpt: 0.000502 acc_pose: 0.828155 loss: 0.000502 2022/09/17 00:19:04 - mmengine - INFO - Epoch(train) [177][100/293] lr: 5.000000e-05 eta: 1:48:49 time: 0.770133 data_time: 0.103115 memory: 21676 loss_kpt: 0.000506 acc_pose: 0.899663 loss: 0.000506 2022/09/17 00:19:43 - mmengine - INFO - Epoch(train) [177][150/293] lr: 5.000000e-05 eta: 1:48:17 time: 0.783715 data_time: 0.107508 memory: 21676 loss_kpt: 0.000502 acc_pose: 0.836831 loss: 0.000502 2022/09/17 00:20:22 - mmengine - INFO - Epoch(train) [177][200/293] lr: 5.000000e-05 eta: 1:47:45 time: 0.765154 data_time: 0.100417 memory: 21676 loss_kpt: 0.000496 acc_pose: 0.865021 loss: 0.000496 2022/09/17 00:21:00 - mmengine - INFO - Epoch(train) [177][250/293] lr: 5.000000e-05 eta: 1:47:13 time: 0.768121 data_time: 0.105412 memory: 21676 loss_kpt: 0.000501 acc_pose: 0.882738 loss: 0.000501 2022/09/17 00:21:33 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/17 00:21:33 - mmengine - INFO - Saving checkpoint at 177 epochs 2022/09/17 00:22:17 - mmengine - INFO - Epoch(train) [178][50/293] lr: 5.000000e-05 eta: 1:46:07 time: 0.790362 data_time: 0.102188 memory: 21676 loss_kpt: 0.000515 acc_pose: 0.877532 loss: 0.000515 2022/09/17 00:22:56 - mmengine - INFO - Epoch(train) [178][100/293] lr: 5.000000e-05 eta: 1:45:35 time: 0.777153 data_time: 0.095389 memory: 21676 loss_kpt: 0.000510 acc_pose: 0.891933 loss: 0.000510 2022/09/17 00:23:26 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/17 00:23:34 - mmengine - INFO - Epoch(train) [178][150/293] lr: 5.000000e-05 eta: 1:45:03 time: 0.774451 data_time: 0.099014 memory: 21676 loss_kpt: 0.000499 acc_pose: 0.874950 loss: 0.000499 2022/09/17 00:24:13 - mmengine - INFO - Epoch(train) [178][200/293] lr: 5.000000e-05 eta: 1:44:31 time: 0.775277 data_time: 0.096203 memory: 21676 loss_kpt: 0.000504 acc_pose: 0.845593 loss: 0.000504 2022/09/17 00:24:52 - mmengine - INFO - Epoch(train) [178][250/293] lr: 5.000000e-05 eta: 1:43:59 time: 0.783697 data_time: 0.094904 memory: 21676 loss_kpt: 0.000511 acc_pose: 0.868248 loss: 0.000511 2022/09/17 00:25:25 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/17 00:25:25 - mmengine - INFO - Saving checkpoint at 178 epochs 2022/09/17 00:26:10 - mmengine - INFO - Epoch(train) [179][50/293] lr: 5.000000e-05 eta: 1:42:53 time: 0.800847 data_time: 0.107972 memory: 21676 loss_kpt: 0.000493 acc_pose: 0.851469 loss: 0.000493 2022/09/17 00:26:49 - mmengine - INFO - Epoch(train) [179][100/293] lr: 5.000000e-05 eta: 1:42:21 time: 0.786682 data_time: 0.101199 memory: 21676 loss_kpt: 0.000502 acc_pose: 0.848022 loss: 0.000502 2022/09/17 00:27:28 - mmengine - INFO - Epoch(train) [179][150/293] lr: 5.000000e-05 eta: 1:41:49 time: 0.772331 data_time: 0.106381 memory: 21676 loss_kpt: 0.000487 acc_pose: 0.874275 loss: 0.000487 2022/09/17 00:28:07 - mmengine - INFO - Epoch(train) [179][200/293] lr: 5.000000e-05 eta: 1:41:17 time: 0.776337 data_time: 0.101386 memory: 21676 loss_kpt: 0.000515 acc_pose: 0.860889 loss: 0.000515 2022/09/17 00:28:46 - mmengine - INFO - Epoch(train) [179][250/293] lr: 5.000000e-05 eta: 1:40:45 time: 0.786091 data_time: 0.102696 memory: 21676 loss_kpt: 0.000502 acc_pose: 0.860942 loss: 0.000502 2022/09/17 00:29:19 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/17 00:29:19 - mmengine - INFO - Saving checkpoint at 179 epochs 2022/09/17 00:30:03 - mmengine - INFO - Epoch(train) [180][50/293] lr: 5.000000e-05 eta: 1:39:40 time: 0.788906 data_time: 0.104399 memory: 21676 loss_kpt: 0.000492 acc_pose: 0.874505 loss: 0.000492 2022/09/17 00:30:43 - mmengine - INFO - Epoch(train) [180][100/293] lr: 5.000000e-05 eta: 1:39:08 time: 0.787602 data_time: 0.102279 memory: 21676 loss_kpt: 0.000489 acc_pose: 0.874475 loss: 0.000489 2022/09/17 00:31:22 - mmengine - INFO - Epoch(train) [180][150/293] lr: 5.000000e-05 eta: 1:38:36 time: 0.775568 data_time: 0.095772 memory: 21676 loss_kpt: 0.000500 acc_pose: 0.864534 loss: 0.000500 2022/09/17 00:32:01 - mmengine - INFO - Epoch(train) [180][200/293] lr: 5.000000e-05 eta: 1:38:03 time: 0.779313 data_time: 0.099665 memory: 21676 loss_kpt: 0.000519 acc_pose: 0.832705 loss: 0.000519 2022/09/17 00:32:39 - mmengine - INFO - Epoch(train) [180][250/293] lr: 5.000000e-05 eta: 1:37:31 time: 0.777364 data_time: 0.099487 memory: 21676 loss_kpt: 0.000497 acc_pose: 0.829818 loss: 0.000497 2022/09/17 00:33:12 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/17 00:33:12 - mmengine - INFO - Saving checkpoint at 180 epochs 2022/09/17 00:33:28 - mmengine - INFO - Epoch(val) [180][50/407] eta: 0:01:17 time: 0.218460 data_time: 0.016261 memory: 21676 2022/09/17 00:33:38 - mmengine - INFO - Epoch(val) [180][100/407] eta: 0:01:05 time: 0.213290 data_time: 0.012904 memory: 1375 2022/09/17 00:33:49 - mmengine - INFO - Epoch(val) [180][150/407] eta: 0:00:54 time: 0.213021 data_time: 0.008957 memory: 1375 2022/09/17 00:33:59 - mmengine - INFO - Epoch(val) [180][200/407] eta: 0:00:43 time: 0.208241 data_time: 0.008739 memory: 1375 2022/09/17 00:34:10 - mmengine - INFO - Epoch(val) [180][250/407] eta: 0:00:32 time: 0.209232 data_time: 0.008440 memory: 1375 2022/09/17 00:34:20 - mmengine - INFO - Epoch(val) [180][300/407] eta: 0:00:22 time: 0.210133 data_time: 0.008468 memory: 1375 2022/09/17 00:34:31 - mmengine - INFO - Epoch(val) [180][350/407] eta: 0:00:12 time: 0.210581 data_time: 0.008610 memory: 1375 2022/09/17 00:34:41 - mmengine - INFO - Epoch(val) [180][400/407] eta: 0:00:01 time: 0.207690 data_time: 0.008780 memory: 1375 2022/09/17 00:35:17 - mmengine - INFO - Evaluating CocoMetric... 2022/09/17 00:35:30 - mmengine - INFO - Epoch(val) [180][407/407] coco/AP: 0.765988 coco/AP .5: 0.907179 coco/AP .75: 0.830286 coco/AP (M): 0.727245 coco/AP (L): 0.837181 coco/AR: 0.814232 coco/AR .5: 0.942695 coco/AR .75: 0.870277 coco/AR (M): 0.771019 coco/AR (L): 0.878038 2022/09/17 00:35:30 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220916/dark_w32_384/best_coco/AP_epoch_170.pth is removed 2022/09/17 00:35:33 - mmengine - INFO - The best checkpoint with 0.7660 coco/AP at 180 epoch is saved to best_coco/AP_epoch_180.pth. 2022/09/17 00:36:13 - mmengine - INFO - Epoch(train) [181][50/293] lr: 5.000000e-05 eta: 1:36:26 time: 0.797893 data_time: 0.105217 memory: 21676 loss_kpt: 0.000503 acc_pose: 0.840894 loss: 0.000503 2022/09/17 00:36:53 - mmengine - INFO - Epoch(train) [181][100/293] lr: 5.000000e-05 eta: 1:35:54 time: 0.785197 data_time: 0.098592 memory: 21676 loss_kpt: 0.000501 acc_pose: 0.893447 loss: 0.000501 2022/09/17 00:37:32 - mmengine - INFO - Epoch(train) [181][150/293] lr: 5.000000e-05 eta: 1:35:22 time: 0.782467 data_time: 0.099924 memory: 21676 loss_kpt: 0.000486 acc_pose: 0.853696 loss: 0.000486 2022/09/17 00:38:11 - mmengine - INFO - Epoch(train) [181][200/293] lr: 5.000000e-05 eta: 1:34:50 time: 0.793494 data_time: 0.091756 memory: 21676 loss_kpt: 0.000496 acc_pose: 0.871084 loss: 0.000496 2022/09/17 00:38:50 - mmengine - INFO - Epoch(train) [181][250/293] lr: 5.000000e-05 eta: 1:34:18 time: 0.768098 data_time: 0.096303 memory: 21676 loss_kpt: 0.000503 acc_pose: 0.874522 loss: 0.000503 2022/09/17 00:38:57 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/17 00:39:22 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/17 00:39:22 - mmengine - INFO - Saving checkpoint at 181 epochs 2022/09/17 00:40:06 - mmengine - INFO - Epoch(train) [182][50/293] lr: 5.000000e-05 eta: 1:33:12 time: 0.790400 data_time: 0.102711 memory: 21676 loss_kpt: 0.000512 acc_pose: 0.884757 loss: 0.000512 2022/09/17 00:40:44 - mmengine - INFO - Epoch(train) [182][100/293] lr: 5.000000e-05 eta: 1:32:40 time: 0.757781 data_time: 0.103138 memory: 21676 loss_kpt: 0.000508 acc_pose: 0.875484 loss: 0.000508 2022/09/17 00:41:22 - mmengine - INFO - Epoch(train) [182][150/293] lr: 5.000000e-05 eta: 1:32:08 time: 0.761587 data_time: 0.092957 memory: 21676 loss_kpt: 0.000501 acc_pose: 0.845473 loss: 0.000501 2022/09/17 00:42:00 - mmengine - INFO - Epoch(train) [182][200/293] lr: 5.000000e-05 eta: 1:31:35 time: 0.758727 data_time: 0.096014 memory: 21676 loss_kpt: 0.000507 acc_pose: 0.861381 loss: 0.000507 2022/09/17 00:42:38 - mmengine - INFO - Epoch(train) [182][250/293] lr: 5.000000e-05 eta: 1:31:03 time: 0.750027 data_time: 0.092327 memory: 21676 loss_kpt: 0.000495 acc_pose: 0.892573 loss: 0.000495 2022/09/17 00:43:11 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/17 00:43:11 - mmengine - INFO - Saving checkpoint at 182 epochs 2022/09/17 00:43:55 - mmengine - INFO - Epoch(train) [183][50/293] lr: 5.000000e-05 eta: 1:29:58 time: 0.793883 data_time: 0.109874 memory: 21676 loss_kpt: 0.000497 acc_pose: 0.885522 loss: 0.000497 2022/09/17 00:44:34 - mmengine - INFO - Epoch(train) [183][100/293] lr: 5.000000e-05 eta: 1:29:26 time: 0.785324 data_time: 0.098378 memory: 21676 loss_kpt: 0.000493 acc_pose: 0.828295 loss: 0.000493 2022/09/17 00:45:13 - mmengine - INFO - Epoch(train) [183][150/293] lr: 5.000000e-05 eta: 1:28:54 time: 0.785683 data_time: 0.092359 memory: 21676 loss_kpt: 0.000511 acc_pose: 0.864374 loss: 0.000511 2022/09/17 00:45:52 - mmengine - INFO - Epoch(train) [183][200/293] lr: 5.000000e-05 eta: 1:28:21 time: 0.770370 data_time: 0.091705 memory: 21676 loss_kpt: 0.000502 acc_pose: 0.806789 loss: 0.000502 2022/09/17 00:46:30 - mmengine - INFO - Epoch(train) [183][250/293] lr: 5.000000e-05 eta: 1:27:49 time: 0.767445 data_time: 0.092493 memory: 21676 loss_kpt: 0.000485 acc_pose: 0.894110 loss: 0.000485 2022/09/17 00:47:03 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/17 00:47:03 - mmengine - INFO - Saving checkpoint at 183 epochs 2022/09/17 00:47:46 - mmengine - INFO - Epoch(train) [184][50/293] lr: 5.000000e-05 eta: 1:26:44 time: 0.771665 data_time: 0.102161 memory: 21676 loss_kpt: 0.000504 acc_pose: 0.836529 loss: 0.000504 2022/09/17 00:48:25 - mmengine - INFO - Epoch(train) [184][100/293] lr: 5.000000e-05 eta: 1:26:12 time: 0.763529 data_time: 0.097266 memory: 21676 loss_kpt: 0.000514 acc_pose: 0.857172 loss: 0.000514 2022/09/17 00:49:03 - mmengine - INFO - Epoch(train) [184][150/293] lr: 5.000000e-05 eta: 1:25:39 time: 0.759350 data_time: 0.096090 memory: 21676 loss_kpt: 0.000499 acc_pose: 0.861142 loss: 0.000499 2022/09/17 00:49:41 - mmengine - INFO - Epoch(train) [184][200/293] lr: 5.000000e-05 eta: 1:25:07 time: 0.757582 data_time: 0.093029 memory: 21676 loss_kpt: 0.000507 acc_pose: 0.840539 loss: 0.000507 2022/09/17 00:50:19 - mmengine - INFO - Epoch(train) [184][250/293] lr: 5.000000e-05 eta: 1:24:34 time: 0.761487 data_time: 0.093366 memory: 21676 loss_kpt: 0.000493 acc_pose: 0.849636 loss: 0.000493 2022/09/17 00:50:51 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/17 00:50:51 - mmengine - INFO - Saving checkpoint at 184 epochs 2022/09/17 00:51:35 - mmengine - INFO - Epoch(train) [185][50/293] lr: 5.000000e-05 eta: 1:23:30 time: 0.787738 data_time: 0.104797 memory: 21676 loss_kpt: 0.000500 acc_pose: 0.855978 loss: 0.000500 2022/09/17 00:52:05 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/17 00:52:14 - mmengine - INFO - Epoch(train) [185][100/293] lr: 5.000000e-05 eta: 1:22:57 time: 0.779698 data_time: 0.100718 memory: 21676 loss_kpt: 0.000508 acc_pose: 0.847398 loss: 0.000508 2022/09/17 00:52:53 - mmengine - INFO - Epoch(train) [185][150/293] lr: 5.000000e-05 eta: 1:22:25 time: 0.786688 data_time: 0.091354 memory: 21676 loss_kpt: 0.000497 acc_pose: 0.888680 loss: 0.000497 2022/09/17 00:53:31 - mmengine - INFO - Epoch(train) [185][200/293] lr: 5.000000e-05 eta: 1:21:53 time: 0.759854 data_time: 0.095884 memory: 21676 loss_kpt: 0.000510 acc_pose: 0.860684 loss: 0.000510 2022/09/17 00:54:09 - mmengine - INFO - Epoch(train) [185][250/293] lr: 5.000000e-05 eta: 1:21:20 time: 0.754549 data_time: 0.096183 memory: 21676 loss_kpt: 0.000501 acc_pose: 0.884872 loss: 0.000501 2022/09/17 00:54:42 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/17 00:54:42 - mmengine - INFO - Saving checkpoint at 185 epochs 2022/09/17 00:55:25 - mmengine - INFO - Epoch(train) [186][50/293] lr: 5.000000e-05 eta: 1:20:16 time: 0.784293 data_time: 0.109852 memory: 21676 loss_kpt: 0.000501 acc_pose: 0.881798 loss: 0.000501 2022/09/17 00:56:05 - mmengine - INFO - Epoch(train) [186][100/293] lr: 5.000000e-05 eta: 1:19:43 time: 0.783859 data_time: 0.101164 memory: 21676 loss_kpt: 0.000498 acc_pose: 0.844819 loss: 0.000498 2022/09/17 00:56:44 - mmengine - INFO - Epoch(train) [186][150/293] lr: 5.000000e-05 eta: 1:19:11 time: 0.783075 data_time: 0.102039 memory: 21676 loss_kpt: 0.000499 acc_pose: 0.893300 loss: 0.000499 2022/09/17 00:57:23 - mmengine - INFO - Epoch(train) [186][200/293] lr: 5.000000e-05 eta: 1:18:39 time: 0.789915 data_time: 0.102683 memory: 21676 loss_kpt: 0.000480 acc_pose: 0.860691 loss: 0.000480 2022/09/17 00:58:02 - mmengine - INFO - Epoch(train) [186][250/293] lr: 5.000000e-05 eta: 1:18:06 time: 0.777197 data_time: 0.101082 memory: 21676 loss_kpt: 0.000492 acc_pose: 0.870520 loss: 0.000492 2022/09/17 00:58:35 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/17 00:58:35 - mmengine - INFO - Saving checkpoint at 186 epochs 2022/09/17 00:59:19 - mmengine - INFO - Epoch(train) [187][50/293] lr: 5.000000e-05 eta: 1:17:02 time: 0.786090 data_time: 0.106798 memory: 21676 loss_kpt: 0.000503 acc_pose: 0.890434 loss: 0.000503 2022/09/17 00:59:57 - mmengine - INFO - Epoch(train) [187][100/293] lr: 5.000000e-05 eta: 1:16:29 time: 0.752809 data_time: 0.095095 memory: 21676 loss_kpt: 0.000494 acc_pose: 0.891167 loss: 0.000494 2022/09/17 01:00:35 - mmengine - INFO - Epoch(train) [187][150/293] lr: 5.000000e-05 eta: 1:15:57 time: 0.766080 data_time: 0.099186 memory: 21676 loss_kpt: 0.000486 acc_pose: 0.912392 loss: 0.000486 2022/09/17 01:01:13 - mmengine - INFO - Epoch(train) [187][200/293] lr: 5.000000e-05 eta: 1:15:24 time: 0.761623 data_time: 0.097836 memory: 21676 loss_kpt: 0.000499 acc_pose: 0.929786 loss: 0.000499 2022/09/17 01:01:51 - mmengine - INFO - Epoch(train) [187][250/293] lr: 5.000000e-05 eta: 1:14:52 time: 0.756382 data_time: 0.095072 memory: 21676 loss_kpt: 0.000502 acc_pose: 0.824950 loss: 0.000502 2022/09/17 01:02:23 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/17 01:02:23 - mmengine - INFO - Saving checkpoint at 187 epochs 2022/09/17 01:03:08 - mmengine - INFO - Epoch(train) [188][50/293] lr: 5.000000e-05 eta: 1:13:48 time: 0.794985 data_time: 0.105718 memory: 21676 loss_kpt: 0.000498 acc_pose: 0.899855 loss: 0.000498 2022/09/17 01:03:47 - mmengine - INFO - Epoch(train) [188][100/293] lr: 5.000000e-05 eta: 1:13:15 time: 0.779897 data_time: 0.099743 memory: 21676 loss_kpt: 0.000494 acc_pose: 0.836360 loss: 0.000494 2022/09/17 01:04:26 - mmengine - INFO - Epoch(train) [188][150/293] lr: 5.000000e-05 eta: 1:12:43 time: 0.780519 data_time: 0.099583 memory: 21676 loss_kpt: 0.000498 acc_pose: 0.848949 loss: 0.000498 2022/09/17 01:05:05 - mmengine - INFO - Epoch(train) [188][200/293] lr: 5.000000e-05 eta: 1:12:10 time: 0.789108 data_time: 0.096864 memory: 21676 loss_kpt: 0.000505 acc_pose: 0.830832 loss: 0.000505 2022/09/17 01:05:13 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/17 01:05:44 - mmengine - INFO - Epoch(train) [188][250/293] lr: 5.000000e-05 eta: 1:11:38 time: 0.775218 data_time: 0.092666 memory: 21676 loss_kpt: 0.000497 acc_pose: 0.881905 loss: 0.000497 2022/09/17 01:06:17 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/17 01:06:17 - mmengine - INFO - Saving checkpoint at 188 epochs 2022/09/17 01:07:01 - mmengine - INFO - Epoch(train) [189][50/293] lr: 5.000000e-05 eta: 1:10:34 time: 0.783139 data_time: 0.109457 memory: 21676 loss_kpt: 0.000495 acc_pose: 0.883265 loss: 0.000495 2022/09/17 01:07:40 - mmengine - INFO - Epoch(train) [189][100/293] lr: 5.000000e-05 eta: 1:10:01 time: 0.782503 data_time: 0.103682 memory: 21676 loss_kpt: 0.000489 acc_pose: 0.863328 loss: 0.000489 2022/09/17 01:08:18 - mmengine - INFO - Epoch(train) [189][150/293] lr: 5.000000e-05 eta: 1:09:29 time: 0.752811 data_time: 0.094756 memory: 21676 loss_kpt: 0.000499 acc_pose: 0.846799 loss: 0.000499 2022/09/17 01:08:55 - mmengine - INFO - Epoch(train) [189][200/293] lr: 5.000000e-05 eta: 1:08:56 time: 0.751780 data_time: 0.096510 memory: 21676 loss_kpt: 0.000492 acc_pose: 0.891708 loss: 0.000492 2022/09/17 01:09:34 - mmengine - INFO - Epoch(train) [189][250/293] lr: 5.000000e-05 eta: 1:08:24 time: 0.768205 data_time: 0.095747 memory: 21676 loss_kpt: 0.000492 acc_pose: 0.890554 loss: 0.000492 2022/09/17 01:10:06 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/17 01:10:06 - mmengine - INFO - Saving checkpoint at 189 epochs 2022/09/17 01:10:50 - mmengine - INFO - Epoch(train) [190][50/293] lr: 5.000000e-05 eta: 1:07:20 time: 0.791693 data_time: 0.103358 memory: 21676 loss_kpt: 0.000493 acc_pose: 0.882513 loss: 0.000493 2022/09/17 01:11:30 - mmengine - INFO - Epoch(train) [190][100/293] lr: 5.000000e-05 eta: 1:06:47 time: 0.788854 data_time: 0.098741 memory: 21676 loss_kpt: 0.000493 acc_pose: 0.833693 loss: 0.000493 2022/09/17 01:12:09 - mmengine - INFO - Epoch(train) [190][150/293] lr: 5.000000e-05 eta: 1:06:15 time: 0.788997 data_time: 0.101183 memory: 21676 loss_kpt: 0.000507 acc_pose: 0.894903 loss: 0.000507 2022/09/17 01:12:49 - mmengine - INFO - Epoch(train) [190][200/293] lr: 5.000000e-05 eta: 1:05:42 time: 0.784242 data_time: 0.103365 memory: 21676 loss_kpt: 0.000499 acc_pose: 0.837053 loss: 0.000499 2022/09/17 01:13:27 - mmengine - INFO - Epoch(train) [190][250/293] lr: 5.000000e-05 eta: 1:05:10 time: 0.774557 data_time: 0.099537 memory: 21676 loss_kpt: 0.000497 acc_pose: 0.876000 loss: 0.000497 2022/09/17 01:14:00 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/17 01:14:00 - mmengine - INFO - Saving checkpoint at 190 epochs 2022/09/17 01:14:16 - mmengine - INFO - Epoch(val) [190][50/407] eta: 0:01:18 time: 0.219299 data_time: 0.014471 memory: 21676 2022/09/17 01:14:27 - mmengine - INFO - Epoch(val) [190][100/407] eta: 0:01:03 time: 0.208448 data_time: 0.008417 memory: 1375 2022/09/17 01:14:37 - mmengine - INFO - Epoch(val) [190][150/407] eta: 0:00:53 time: 0.209400 data_time: 0.008166 memory: 1375 2022/09/17 01:14:48 - mmengine - INFO - Epoch(val) [190][200/407] eta: 0:00:43 time: 0.210076 data_time: 0.008591 memory: 1375 2022/09/17 01:14:58 - mmengine - INFO - Epoch(val) [190][250/407] eta: 0:00:32 time: 0.210072 data_time: 0.008468 memory: 1375 2022/09/17 01:15:09 - mmengine - INFO - Epoch(val) [190][300/407] eta: 0:00:22 time: 0.209452 data_time: 0.008546 memory: 1375 2022/09/17 01:15:19 - mmengine - INFO - Epoch(val) [190][350/407] eta: 0:00:12 time: 0.213864 data_time: 0.009524 memory: 1375 2022/09/17 01:15:30 - mmengine - INFO - Epoch(val) [190][400/407] eta: 0:00:01 time: 0.205765 data_time: 0.007935 memory: 1375 2022/09/17 01:16:05 - mmengine - INFO - Evaluating CocoMetric... 2022/09/17 01:16:19 - mmengine - INFO - Epoch(val) [190][407/407] coco/AP: 0.765695 coco/AP .5: 0.905785 coco/AP .75: 0.829772 coco/AP (M): 0.725085 coco/AP (L): 0.838560 coco/AR: 0.813649 coco/AR .5: 0.942223 coco/AR .75: 0.870749 coco/AR (M): 0.769079 coco/AR (L): 0.878632 2022/09/17 01:16:59 - mmengine - INFO - Epoch(train) [191][50/293] lr: 5.000000e-05 eta: 1:04:06 time: 0.810517 data_time: 0.109573 memory: 21676 loss_kpt: 0.000499 acc_pose: 0.851318 loss: 0.000499 2022/09/17 01:17:39 - mmengine - INFO - Epoch(train) [191][100/293] lr: 5.000000e-05 eta: 1:03:34 time: 0.794271 data_time: 0.091201 memory: 21676 loss_kpt: 0.000496 acc_pose: 0.838334 loss: 0.000496 2022/09/17 01:18:18 - mmengine - INFO - Epoch(train) [191][150/293] lr: 5.000000e-05 eta: 1:03:01 time: 0.771344 data_time: 0.093518 memory: 21676 loss_kpt: 0.000495 acc_pose: 0.860044 loss: 0.000495 2022/09/17 01:18:57 - mmengine - INFO - Epoch(train) [191][200/293] lr: 5.000000e-05 eta: 1:02:29 time: 0.784623 data_time: 0.094374 memory: 21676 loss_kpt: 0.000501 acc_pose: 0.883991 loss: 0.000501 2022/09/17 01:19:36 - mmengine - INFO - Epoch(train) [191][250/293] lr: 5.000000e-05 eta: 1:01:56 time: 0.778117 data_time: 0.095177 memory: 21676 loss_kpt: 0.000482 acc_pose: 0.851684 loss: 0.000482 2022/09/17 01:20:09 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/17 01:20:09 - mmengine - INFO - Saving checkpoint at 191 epochs 2022/09/17 01:20:44 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/17 01:20:54 - mmengine - INFO - Epoch(train) [192][50/293] lr: 5.000000e-05 eta: 1:00:52 time: 0.797697 data_time: 0.107773 memory: 21676 loss_kpt: 0.000494 acc_pose: 0.861002 loss: 0.000494 2022/09/17 01:21:32 - mmengine - INFO - Epoch(train) [192][100/293] lr: 5.000000e-05 eta: 1:00:20 time: 0.777379 data_time: 0.093683 memory: 21676 loss_kpt: 0.000506 acc_pose: 0.874513 loss: 0.000506 2022/09/17 01:22:11 - mmengine - INFO - Epoch(train) [192][150/293] lr: 5.000000e-05 eta: 0:59:47 time: 0.773517 data_time: 0.090770 memory: 21676 loss_kpt: 0.000486 acc_pose: 0.874058 loss: 0.000486 2022/09/17 01:22:50 - mmengine - INFO - Epoch(train) [192][200/293] lr: 5.000000e-05 eta: 0:59:15 time: 0.779115 data_time: 0.096142 memory: 21676 loss_kpt: 0.000497 acc_pose: 0.862027 loss: 0.000497 2022/09/17 01:23:29 - mmengine - INFO - Epoch(train) [192][250/293] lr: 5.000000e-05 eta: 0:58:42 time: 0.770033 data_time: 0.091995 memory: 21676 loss_kpt: 0.000504 acc_pose: 0.861929 loss: 0.000504 2022/09/17 01:24:02 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/17 01:24:02 - mmengine - INFO - Saving checkpoint at 192 epochs 2022/09/17 01:24:45 - mmengine - INFO - Epoch(train) [193][50/293] lr: 5.000000e-05 eta: 0:57:38 time: 0.784487 data_time: 0.104937 memory: 21676 loss_kpt: 0.000502 acc_pose: 0.877101 loss: 0.000502 2022/09/17 01:25:24 - mmengine - INFO - Epoch(train) [193][100/293] lr: 5.000000e-05 eta: 0:57:06 time: 0.778775 data_time: 0.095679 memory: 21676 loss_kpt: 0.000486 acc_pose: 0.872562 loss: 0.000486 2022/09/17 01:26:03 - mmengine - INFO - Epoch(train) [193][150/293] lr: 5.000000e-05 eta: 0:56:33 time: 0.781519 data_time: 0.099138 memory: 21676 loss_kpt: 0.000499 acc_pose: 0.881727 loss: 0.000499 2022/09/17 01:26:42 - mmengine - INFO - Epoch(train) [193][200/293] lr: 5.000000e-05 eta: 0:56:01 time: 0.777104 data_time: 0.092484 memory: 21676 loss_kpt: 0.000492 acc_pose: 0.883262 loss: 0.000492 2022/09/17 01:27:21 - mmengine - INFO - Epoch(train) [193][250/293] lr: 5.000000e-05 eta: 0:55:28 time: 0.775405 data_time: 0.099051 memory: 21676 loss_kpt: 0.000498 acc_pose: 0.873938 loss: 0.000498 2022/09/17 01:27:54 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/17 01:27:54 - mmengine - INFO - Saving checkpoint at 193 epochs 2022/09/17 01:28:37 - mmengine - INFO - Epoch(train) [194][50/293] lr: 5.000000e-05 eta: 0:54:24 time: 0.775186 data_time: 0.106790 memory: 21676 loss_kpt: 0.000492 acc_pose: 0.855493 loss: 0.000492 2022/09/17 01:29:15 - mmengine - INFO - Epoch(train) [194][100/293] lr: 5.000000e-05 eta: 0:53:52 time: 0.758814 data_time: 0.095607 memory: 21676 loss_kpt: 0.000498 acc_pose: 0.870251 loss: 0.000498 2022/09/17 01:29:53 - mmengine - INFO - Epoch(train) [194][150/293] lr: 5.000000e-05 eta: 0:53:19 time: 0.759678 data_time: 0.091659 memory: 21676 loss_kpt: 0.000491 acc_pose: 0.873978 loss: 0.000491 2022/09/17 01:30:31 - mmengine - INFO - Epoch(train) [194][200/293] lr: 5.000000e-05 eta: 0:52:46 time: 0.756087 data_time: 0.092064 memory: 21676 loss_kpt: 0.000499 acc_pose: 0.816475 loss: 0.000499 2022/09/17 01:31:09 - mmengine - INFO - Epoch(train) [194][250/293] lr: 5.000000e-05 eta: 0:52:14 time: 0.767453 data_time: 0.096421 memory: 21676 loss_kpt: 0.000499 acc_pose: 0.862185 loss: 0.000499 2022/09/17 01:31:41 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/17 01:31:41 - mmengine - INFO - Saving checkpoint at 194 epochs 2022/09/17 01:32:25 - mmengine - INFO - Epoch(train) [195][50/293] lr: 5.000000e-05 eta: 0:51:10 time: 0.788261 data_time: 0.112611 memory: 21676 loss_kpt: 0.000508 acc_pose: 0.863077 loss: 0.000508 2022/09/17 01:33:04 - mmengine - INFO - Epoch(train) [195][100/293] lr: 5.000000e-05 eta: 0:50:38 time: 0.788379 data_time: 0.098858 memory: 21676 loss_kpt: 0.000502 acc_pose: 0.885555 loss: 0.000502 2022/09/17 01:33:44 - mmengine - INFO - Epoch(train) [195][150/293] lr: 5.000000e-05 eta: 0:50:05 time: 0.782155 data_time: 0.097352 memory: 21676 loss_kpt: 0.000503 acc_pose: 0.860668 loss: 0.000503 2022/09/17 01:33:50 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/17 01:34:22 - mmengine - INFO - Epoch(train) [195][200/293] lr: 5.000000e-05 eta: 0:49:32 time: 0.770673 data_time: 0.092777 memory: 21676 loss_kpt: 0.000491 acc_pose: 0.890871 loss: 0.000491 2022/09/17 01:35:00 - mmengine - INFO - Epoch(train) [195][250/293] lr: 5.000000e-05 eta: 0:48:59 time: 0.751779 data_time: 0.096087 memory: 21676 loss_kpt: 0.000502 acc_pose: 0.844484 loss: 0.000502 2022/09/17 01:35:32 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/17 01:35:32 - mmengine - INFO - Saving checkpoint at 195 epochs 2022/09/17 01:36:16 - mmengine - INFO - Epoch(train) [196][50/293] lr: 5.000000e-05 eta: 0:47:56 time: 0.792113 data_time: 0.111376 memory: 21676 loss_kpt: 0.000490 acc_pose: 0.889959 loss: 0.000490 2022/09/17 01:36:54 - mmengine - INFO - Epoch(train) [196][100/293] lr: 5.000000e-05 eta: 0:47:23 time: 0.762749 data_time: 0.092379 memory: 21676 loss_kpt: 0.000500 acc_pose: 0.879903 loss: 0.000500 2022/09/17 01:37:33 - mmengine - INFO - Epoch(train) [196][150/293] lr: 5.000000e-05 eta: 0:46:51 time: 0.773679 data_time: 0.101352 memory: 21676 loss_kpt: 0.000499 acc_pose: 0.876617 loss: 0.000499 2022/09/17 01:38:11 - mmengine - INFO - Epoch(train) [196][200/293] lr: 5.000000e-05 eta: 0:46:18 time: 0.766448 data_time: 0.093138 memory: 21676 loss_kpt: 0.000502 acc_pose: 0.808169 loss: 0.000502 2022/09/17 01:38:49 - mmengine - INFO - Epoch(train) [196][250/293] lr: 5.000000e-05 eta: 0:45:45 time: 0.747299 data_time: 0.096634 memory: 21676 loss_kpt: 0.000511 acc_pose: 0.841669 loss: 0.000511 2022/09/17 01:39:21 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/17 01:39:21 - mmengine - INFO - Saving checkpoint at 196 epochs 2022/09/17 01:40:05 - mmengine - INFO - Epoch(train) [197][50/293] lr: 5.000000e-05 eta: 0:44:42 time: 0.791226 data_time: 0.103027 memory: 21676 loss_kpt: 0.000496 acc_pose: 0.861361 loss: 0.000496 2022/09/17 01:40:43 - mmengine - INFO - Epoch(train) [197][100/293] lr: 5.000000e-05 eta: 0:44:09 time: 0.762289 data_time: 0.098635 memory: 21676 loss_kpt: 0.000503 acc_pose: 0.860362 loss: 0.000503 2022/09/17 01:41:21 - mmengine - INFO - Epoch(train) [197][150/293] lr: 5.000000e-05 eta: 0:43:37 time: 0.761706 data_time: 0.092032 memory: 21676 loss_kpt: 0.000499 acc_pose: 0.864436 loss: 0.000499 2022/09/17 01:41:59 - mmengine - INFO - Epoch(train) [197][200/293] lr: 5.000000e-05 eta: 0:43:04 time: 0.753473 data_time: 0.099800 memory: 21676 loss_kpt: 0.000492 acc_pose: 0.839843 loss: 0.000492 2022/09/17 01:42:37 - mmengine - INFO - Epoch(train) [197][250/293] lr: 5.000000e-05 eta: 0:42:31 time: 0.767199 data_time: 0.095749 memory: 21676 loss_kpt: 0.000484 acc_pose: 0.895316 loss: 0.000484 2022/09/17 01:43:10 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/17 01:43:10 - mmengine - INFO - Saving checkpoint at 197 epochs 2022/09/17 01:43:54 - mmengine - INFO - Epoch(train) [198][50/293] lr: 5.000000e-05 eta: 0:41:28 time: 0.800239 data_time: 0.113449 memory: 21676 loss_kpt: 0.000487 acc_pose: 0.819968 loss: 0.000487 2022/09/17 01:44:33 - mmengine - INFO - Epoch(train) [198][100/293] lr: 5.000000e-05 eta: 0:40:55 time: 0.779614 data_time: 0.094479 memory: 21676 loss_kpt: 0.000489 acc_pose: 0.862534 loss: 0.000489 2022/09/17 01:45:12 - mmengine - INFO - Epoch(train) [198][150/293] lr: 5.000000e-05 eta: 0:40:23 time: 0.774148 data_time: 0.097585 memory: 21676 loss_kpt: 0.000488 acc_pose: 0.876230 loss: 0.000488 2022/09/17 01:45:51 - mmengine - INFO - Epoch(train) [198][200/293] lr: 5.000000e-05 eta: 0:39:50 time: 0.783303 data_time: 0.096806 memory: 21676 loss_kpt: 0.000493 acc_pose: 0.865616 loss: 0.000493 2022/09/17 01:46:29 - mmengine - INFO - Epoch(train) [198][250/293] lr: 5.000000e-05 eta: 0:39:17 time: 0.764301 data_time: 0.097467 memory: 21676 loss_kpt: 0.000504 acc_pose: 0.815272 loss: 0.000504 2022/09/17 01:46:51 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/17 01:47:02 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/17 01:47:02 - mmengine - INFO - Saving checkpoint at 198 epochs 2022/09/17 01:47:44 - mmengine - INFO - Epoch(train) [199][50/293] lr: 5.000000e-05 eta: 0:38:14 time: 0.765831 data_time: 0.109194 memory: 21676 loss_kpt: 0.000495 acc_pose: 0.811512 loss: 0.000495 2022/09/17 01:48:23 - mmengine - INFO - Epoch(train) [199][100/293] lr: 5.000000e-05 eta: 0:37:41 time: 0.761462 data_time: 0.093462 memory: 21676 loss_kpt: 0.000492 acc_pose: 0.906743 loss: 0.000492 2022/09/17 01:49:01 - mmengine - INFO - Epoch(train) [199][150/293] lr: 5.000000e-05 eta: 0:37:08 time: 0.766237 data_time: 0.100164 memory: 21676 loss_kpt: 0.000495 acc_pose: 0.880441 loss: 0.000495 2022/09/17 01:49:38 - mmengine - INFO - Epoch(train) [199][200/293] lr: 5.000000e-05 eta: 0:36:36 time: 0.747781 data_time: 0.095346 memory: 21676 loss_kpt: 0.000487 acc_pose: 0.883876 loss: 0.000487 2022/09/17 01:50:17 - mmengine - INFO - Epoch(train) [199][250/293] lr: 5.000000e-05 eta: 0:36:03 time: 0.766597 data_time: 0.091882 memory: 21676 loss_kpt: 0.000495 acc_pose: 0.856746 loss: 0.000495 2022/09/17 01:50:49 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/17 01:50:49 - mmengine - INFO - Saving checkpoint at 199 epochs 2022/09/17 01:51:34 - mmengine - INFO - Epoch(train) [200][50/293] lr: 5.000000e-05 eta: 0:35:00 time: 0.798362 data_time: 0.107247 memory: 21676 loss_kpt: 0.000485 acc_pose: 0.868881 loss: 0.000485 2022/09/17 01:52:13 - mmengine - INFO - Epoch(train) [200][100/293] lr: 5.000000e-05 eta: 0:34:27 time: 0.785002 data_time: 0.096712 memory: 21676 loss_kpt: 0.000494 acc_pose: 0.808339 loss: 0.000494 2022/09/17 01:52:52 - mmengine - INFO - Epoch(train) [200][150/293] lr: 5.000000e-05 eta: 0:33:54 time: 0.775277 data_time: 0.094811 memory: 21676 loss_kpt: 0.000491 acc_pose: 0.881837 loss: 0.000491 2022/09/17 01:53:31 - mmengine - INFO - Epoch(train) [200][200/293] lr: 5.000000e-05 eta: 0:33:22 time: 0.783433 data_time: 0.099361 memory: 21676 loss_kpt: 0.000493 acc_pose: 0.844689 loss: 0.000493 2022/09/17 01:54:10 - mmengine - INFO - Epoch(train) [200][250/293] lr: 5.000000e-05 eta: 0:32:49 time: 0.767623 data_time: 0.092843 memory: 21676 loss_kpt: 0.000490 acc_pose: 0.832847 loss: 0.000490 2022/09/17 01:54:42 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/17 01:54:42 - mmengine - INFO - Saving checkpoint at 200 epochs 2022/09/17 01:54:58 - mmengine - INFO - Epoch(val) [200][50/407] eta: 0:01:18 time: 0.219701 data_time: 0.016449 memory: 21676 2022/09/17 01:55:08 - mmengine - INFO - Epoch(val) [200][100/407] eta: 0:01:05 time: 0.212076 data_time: 0.009083 memory: 1375 2022/09/17 01:55:19 - mmengine - INFO - Epoch(val) [200][150/407] eta: 0:00:55 time: 0.217428 data_time: 0.014219 memory: 1375 2022/09/17 01:55:30 - mmengine - INFO - Epoch(val) [200][200/407] eta: 0:00:43 time: 0.211233 data_time: 0.008362 memory: 1375 2022/09/17 01:55:40 - mmengine - INFO - Epoch(val) [200][250/407] eta: 0:00:32 time: 0.207513 data_time: 0.008667 memory: 1375 2022/09/17 01:55:51 - mmengine - INFO - Epoch(val) [200][300/407] eta: 0:00:22 time: 0.210491 data_time: 0.008483 memory: 1375 2022/09/17 01:56:01 - mmengine - INFO - Epoch(val) [200][350/407] eta: 0:00:11 time: 0.209111 data_time: 0.008798 memory: 1375 2022/09/17 01:56:12 - mmengine - INFO - Epoch(val) [200][400/407] eta: 0:00:01 time: 0.207723 data_time: 0.008146 memory: 1375 2022/09/17 01:56:47 - mmengine - INFO - Evaluating CocoMetric... 2022/09/17 01:57:01 - mmengine - INFO - Epoch(val) [200][407/407] coco/AP: 0.766546 coco/AP .5: 0.907306 coco/AP .75: 0.828813 coco/AP (M): 0.726833 coco/AP (L): 0.838642 coco/AR: 0.814846 coco/AR .5: 0.943482 coco/AR .75: 0.870749 coco/AR (M): 0.771210 coco/AR (L): 0.878930 2022/09/17 01:57:01 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220916/dark_w32_384/best_coco/AP_epoch_180.pth is removed 2022/09/17 01:57:04 - mmengine - INFO - The best checkpoint with 0.7665 coco/AP at 200 epoch is saved to best_coco/AP_epoch_200.pth. 2022/09/17 01:57:43 - mmengine - INFO - Epoch(train) [201][50/293] lr: 5.000000e-06 eta: 0:31:46 time: 0.781387 data_time: 0.108613 memory: 21676 loss_kpt: 0.000490 acc_pose: 0.861040 loss: 0.000490 2022/09/17 01:58:23 - mmengine - INFO - Epoch(train) [201][100/293] lr: 5.000000e-06 eta: 0:31:13 time: 0.800356 data_time: 0.094901 memory: 21676 loss_kpt: 0.000489 acc_pose: 0.832065 loss: 0.000489 2022/09/17 01:59:02 - mmengine - INFO - Epoch(train) [201][150/293] lr: 5.000000e-06 eta: 0:30:40 time: 0.776425 data_time: 0.095700 memory: 21676 loss_kpt: 0.000489 acc_pose: 0.887377 loss: 0.000489 2022/09/17 01:59:41 - mmengine - INFO - Epoch(train) [201][200/293] lr: 5.000000e-06 eta: 0:30:08 time: 0.785795 data_time: 0.097313 memory: 21676 loss_kpt: 0.000481 acc_pose: 0.852038 loss: 0.000481 2022/09/17 02:00:20 - mmengine - INFO - Epoch(train) [201][250/293] lr: 5.000000e-06 eta: 0:29:35 time: 0.774354 data_time: 0.101861 memory: 21676 loss_kpt: 0.000491 acc_pose: 0.864244 loss: 0.000491 2022/09/17 02:00:52 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/17 02:00:52 - mmengine - INFO - Saving checkpoint at 201 epochs 2022/09/17 02:01:36 - mmengine - INFO - Epoch(train) [202][50/293] lr: 5.000000e-06 eta: 0:28:32 time: 0.783174 data_time: 0.107581 memory: 21676 loss_kpt: 0.000496 acc_pose: 0.844040 loss: 0.000496 2022/09/17 02:02:14 - mmengine - INFO - Epoch(train) [202][100/293] lr: 5.000000e-06 eta: 0:27:59 time: 0.765991 data_time: 0.093668 memory: 21676 loss_kpt: 0.000489 acc_pose: 0.923199 loss: 0.000489 2022/09/17 02:02:20 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/17 02:02:52 - mmengine - INFO - Epoch(train) [202][150/293] lr: 5.000000e-06 eta: 0:27:26 time: 0.756882 data_time: 0.094835 memory: 21676 loss_kpt: 0.000493 acc_pose: 0.848264 loss: 0.000493 2022/09/17 02:03:30 - mmengine - INFO - Epoch(train) [202][200/293] lr: 5.000000e-06 eta: 0:26:53 time: 0.771612 data_time: 0.094892 memory: 21676 loss_kpt: 0.000489 acc_pose: 0.851716 loss: 0.000489 2022/09/17 02:04:08 - mmengine - INFO - Epoch(train) [202][250/293] lr: 5.000000e-06 eta: 0:26:21 time: 0.752577 data_time: 0.098154 memory: 21676 loss_kpt: 0.000491 acc_pose: 0.875100 loss: 0.000491 2022/09/17 02:04:41 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/17 02:04:41 - mmengine - INFO - Saving checkpoint at 202 epochs 2022/09/17 02:05:24 - mmengine - INFO - Epoch(train) [203][50/293] lr: 5.000000e-06 eta: 0:25:18 time: 0.775380 data_time: 0.107347 memory: 21676 loss_kpt: 0.000495 acc_pose: 0.834330 loss: 0.000495 2022/09/17 02:06:03 - mmengine - INFO - Epoch(train) [203][100/293] lr: 5.000000e-06 eta: 0:24:45 time: 0.786295 data_time: 0.098743 memory: 21676 loss_kpt: 0.000492 acc_pose: 0.891282 loss: 0.000492 2022/09/17 02:06:43 - mmengine - INFO - Epoch(train) [203][150/293] lr: 5.000000e-06 eta: 0:24:12 time: 0.796132 data_time: 0.101257 memory: 21676 loss_kpt: 0.000493 acc_pose: 0.866625 loss: 0.000493 2022/09/17 02:07:22 - mmengine - INFO - Epoch(train) [203][200/293] lr: 5.000000e-06 eta: 0:23:39 time: 0.784937 data_time: 0.100062 memory: 21676 loss_kpt: 0.000492 acc_pose: 0.852205 loss: 0.000492 2022/09/17 02:08:00 - mmengine - INFO - Epoch(train) [203][250/293] lr: 5.000000e-06 eta: 0:23:06 time: 0.763803 data_time: 0.099509 memory: 21676 loss_kpt: 0.000491 acc_pose: 0.898006 loss: 0.000491 2022/09/17 02:08:32 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/17 02:08:32 - mmengine - INFO - Saving checkpoint at 203 epochs 2022/09/17 02:09:16 - mmengine - INFO - Epoch(train) [204][50/293] lr: 5.000000e-06 eta: 0:22:04 time: 0.781454 data_time: 0.108605 memory: 21676 loss_kpt: 0.000496 acc_pose: 0.886926 loss: 0.000496 2022/09/17 02:09:55 - mmengine - INFO - Epoch(train) [204][100/293] lr: 5.000000e-06 eta: 0:21:31 time: 0.778499 data_time: 0.102430 memory: 21676 loss_kpt: 0.000478 acc_pose: 0.843681 loss: 0.000478 2022/09/17 02:10:33 - mmengine - INFO - Epoch(train) [204][150/293] lr: 5.000000e-06 eta: 0:20:58 time: 0.774725 data_time: 0.102911 memory: 21676 loss_kpt: 0.000488 acc_pose: 0.896035 loss: 0.000488 2022/09/17 02:11:12 - mmengine - INFO - Epoch(train) [204][200/293] lr: 5.000000e-06 eta: 0:20:25 time: 0.777140 data_time: 0.101484 memory: 21676 loss_kpt: 0.000493 acc_pose: 0.831179 loss: 0.000493 2022/09/17 02:11:51 - mmengine - INFO - Epoch(train) [204][250/293] lr: 5.000000e-06 eta: 0:19:52 time: 0.768298 data_time: 0.100175 memory: 21676 loss_kpt: 0.000494 acc_pose: 0.859680 loss: 0.000494 2022/09/17 02:12:24 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/17 02:12:24 - mmengine - INFO - Saving checkpoint at 204 epochs 2022/09/17 02:13:08 - mmengine - INFO - Epoch(train) [205][50/293] lr: 5.000000e-06 eta: 0:18:50 time: 0.787554 data_time: 0.100157 memory: 21676 loss_kpt: 0.000484 acc_pose: 0.843436 loss: 0.000484 2022/09/17 02:13:47 - mmengine - INFO - Epoch(train) [205][100/293] lr: 5.000000e-06 eta: 0:18:17 time: 0.784467 data_time: 0.100170 memory: 21676 loss_kpt: 0.000488 acc_pose: 0.851756 loss: 0.000488 2022/09/17 02:14:27 - mmengine - INFO - Epoch(train) [205][150/293] lr: 5.000000e-06 eta: 0:17:44 time: 0.788357 data_time: 0.095944 memory: 21676 loss_kpt: 0.000495 acc_pose: 0.844393 loss: 0.000495 2022/09/17 02:15:05 - mmengine - INFO - Epoch(train) [205][200/293] lr: 5.000000e-06 eta: 0:17:11 time: 0.771708 data_time: 0.100391 memory: 21676 loss_kpt: 0.000492 acc_pose: 0.877690 loss: 0.000492 2022/09/17 02:15:27 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/17 02:15:43 - mmengine - INFO - Epoch(train) [205][250/293] lr: 5.000000e-06 eta: 0:16:38 time: 0.762693 data_time: 0.094478 memory: 21676 loss_kpt: 0.000504 acc_pose: 0.832098 loss: 0.000504 2022/09/17 02:16:15 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/17 02:16:15 - mmengine - INFO - Saving checkpoint at 205 epochs 2022/09/17 02:16:59 - mmengine - INFO - Epoch(train) [206][50/293] lr: 5.000000e-06 eta: 0:15:36 time: 0.784218 data_time: 0.114343 memory: 21676 loss_kpt: 0.000489 acc_pose: 0.881035 loss: 0.000489 2022/09/17 02:17:38 - mmengine - INFO - Epoch(train) [206][100/293] lr: 5.000000e-06 eta: 0:15:03 time: 0.776449 data_time: 0.098205 memory: 21676 loss_kpt: 0.000497 acc_pose: 0.856420 loss: 0.000497 2022/09/17 02:18:17 - mmengine - INFO - Epoch(train) [206][150/293] lr: 5.000000e-06 eta: 0:14:30 time: 0.785150 data_time: 0.098109 memory: 21676 loss_kpt: 0.000486 acc_pose: 0.840227 loss: 0.000486 2022/09/17 02:18:57 - mmengine - INFO - Epoch(train) [206][200/293] lr: 5.000000e-06 eta: 0:13:57 time: 0.781399 data_time: 0.096582 memory: 21676 loss_kpt: 0.000484 acc_pose: 0.900803 loss: 0.000484 2022/09/17 02:19:35 - mmengine - INFO - Epoch(train) [206][250/293] lr: 5.000000e-06 eta: 0:13:24 time: 0.777868 data_time: 0.097584 memory: 21676 loss_kpt: 0.000487 acc_pose: 0.834994 loss: 0.000487 2022/09/17 02:20:08 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/17 02:20:08 - mmengine - INFO - Saving checkpoint at 206 epochs 2022/09/17 02:20:51 - mmengine - INFO - Epoch(train) [207][50/293] lr: 5.000000e-06 eta: 0:12:22 time: 0.786273 data_time: 0.108495 memory: 21676 loss_kpt: 0.000493 acc_pose: 0.851610 loss: 0.000493 2022/09/17 02:21:30 - mmengine - INFO - Epoch(train) [207][100/293] lr: 5.000000e-06 eta: 0:11:49 time: 0.775130 data_time: 0.096001 memory: 21676 loss_kpt: 0.000487 acc_pose: 0.875846 loss: 0.000487 2022/09/17 02:22:09 - mmengine - INFO - Epoch(train) [207][150/293] lr: 5.000000e-06 eta: 0:11:16 time: 0.776733 data_time: 0.095440 memory: 21676 loss_kpt: 0.000491 acc_pose: 0.876358 loss: 0.000491 2022/09/17 02:22:48 - mmengine - INFO - Epoch(train) [207][200/293] lr: 5.000000e-06 eta: 0:10:43 time: 0.782440 data_time: 0.100323 memory: 21676 loss_kpt: 0.000484 acc_pose: 0.854565 loss: 0.000484 2022/09/17 02:23:27 - mmengine - INFO - Epoch(train) [207][250/293] lr: 5.000000e-06 eta: 0:10:10 time: 0.777506 data_time: 0.095510 memory: 21676 loss_kpt: 0.000476 acc_pose: 0.854795 loss: 0.000476 2022/09/17 02:24:00 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/17 02:24:00 - mmengine - INFO - Saving checkpoint at 207 epochs 2022/09/17 02:24:43 - mmengine - INFO - Epoch(train) [208][50/293] lr: 5.000000e-06 eta: 0:09:08 time: 0.778617 data_time: 0.105715 memory: 21676 loss_kpt: 0.000490 acc_pose: 0.884960 loss: 0.000490 2022/09/17 02:25:21 - mmengine - INFO - Epoch(train) [208][100/293] lr: 5.000000e-06 eta: 0:08:35 time: 0.759053 data_time: 0.095475 memory: 21676 loss_kpt: 0.000485 acc_pose: 0.849874 loss: 0.000485 2022/09/17 02:26:00 - mmengine - INFO - Epoch(train) [208][150/293] lr: 5.000000e-06 eta: 0:08:02 time: 0.770215 data_time: 0.096672 memory: 21676 loss_kpt: 0.000497 acc_pose: 0.862830 loss: 0.000497 2022/09/17 02:26:38 - mmengine - INFO - Epoch(train) [208][200/293] lr: 5.000000e-06 eta: 0:07:29 time: 0.758407 data_time: 0.098547 memory: 21676 loss_kpt: 0.000494 acc_pose: 0.893673 loss: 0.000494 2022/09/17 02:27:15 - mmengine - INFO - Epoch(train) [208][250/293] lr: 5.000000e-06 eta: 0:06:56 time: 0.748305 data_time: 0.093409 memory: 21676 loss_kpt: 0.000486 acc_pose: 0.865512 loss: 0.000486 2022/09/17 02:27:48 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/17 02:27:48 - mmengine - INFO - Saving checkpoint at 208 epochs 2022/09/17 02:28:32 - mmengine - INFO - Epoch(train) [209][50/293] lr: 5.000000e-06 eta: 0:05:54 time: 0.785627 data_time: 0.108013 memory: 21676 loss_kpt: 0.000488 acc_pose: 0.878208 loss: 0.000488 2022/09/17 02:28:37 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/17 02:29:11 - mmengine - INFO - Epoch(train) [209][100/293] lr: 5.000000e-06 eta: 0:05:21 time: 0.776039 data_time: 0.095684 memory: 21676 loss_kpt: 0.000492 acc_pose: 0.858121 loss: 0.000492 2022/09/17 02:29:48 - mmengine - INFO - Epoch(train) [209][150/293] lr: 5.000000e-06 eta: 0:04:48 time: 0.757045 data_time: 0.095451 memory: 21676 loss_kpt: 0.000489 acc_pose: 0.867695 loss: 0.000489 2022/09/17 02:30:27 - mmengine - INFO - Epoch(train) [209][200/293] lr: 5.000000e-06 eta: 0:04:15 time: 0.762358 data_time: 0.097292 memory: 21676 loss_kpt: 0.000486 acc_pose: 0.858526 loss: 0.000486 2022/09/17 02:31:04 - mmengine - INFO - Epoch(train) [209][250/293] lr: 5.000000e-06 eta: 0:03:42 time: 0.755614 data_time: 0.095917 memory: 21676 loss_kpt: 0.000492 acc_pose: 0.884237 loss: 0.000492 2022/09/17 02:31:37 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/17 02:31:37 - mmengine - INFO - Saving checkpoint at 209 epochs 2022/09/17 02:32:21 - mmengine - INFO - Epoch(train) [210][50/293] lr: 5.000000e-06 eta: 0:02:40 time: 0.796343 data_time: 0.107674 memory: 21676 loss_kpt: 0.000498 acc_pose: 0.859582 loss: 0.000498 2022/09/17 02:33:01 - mmengine - INFO - Epoch(train) [210][100/293] lr: 5.000000e-06 eta: 0:02:07 time: 0.787536 data_time: 0.099676 memory: 21676 loss_kpt: 0.000490 acc_pose: 0.888690 loss: 0.000490 2022/09/17 02:33:40 - mmengine - INFO - Epoch(train) [210][150/293] lr: 5.000000e-06 eta: 0:01:34 time: 0.780320 data_time: 0.091079 memory: 21676 loss_kpt: 0.000490 acc_pose: 0.856944 loss: 0.000490 2022/09/17 02:34:19 - mmengine - INFO - Epoch(train) [210][200/293] lr: 5.000000e-06 eta: 0:01:01 time: 0.786947 data_time: 0.098452 memory: 21676 loss_kpt: 0.000485 acc_pose: 0.881606 loss: 0.000485 2022/09/17 02:34:58 - mmengine - INFO - Epoch(train) [210][250/293] lr: 5.000000e-06 eta: 0:00:28 time: 0.785635 data_time: 0.095683 memory: 21676 loss_kpt: 0.000492 acc_pose: 0.824010 loss: 0.000492 2022/09/17 02:35:31 - mmengine - INFO - Exp name: td-hm_hrnet-w32_dark-8xb64-210e_coco-384x288_20220916_121953 2022/09/17 02:35:31 - mmengine - INFO - Saving checkpoint at 210 epochs 2022/09/17 02:35:47 - mmengine - INFO - Epoch(val) [210][50/407] eta: 0:01:17 time: 0.217017 data_time: 0.013986 memory: 21676 2022/09/17 02:35:57 - mmengine - INFO - Epoch(val) [210][100/407] eta: 0:01:04 time: 0.210529 data_time: 0.008576 memory: 1375 2022/09/17 02:36:08 - mmengine - INFO - Epoch(val) [210][150/407] eta: 0:00:54 time: 0.211370 data_time: 0.008607 memory: 1375 2022/09/17 02:36:18 - mmengine - INFO - Epoch(val) [210][200/407] eta: 0:00:43 time: 0.211922 data_time: 0.008566 memory: 1375 2022/09/17 02:36:29 - mmengine - INFO - Epoch(val) [210][250/407] eta: 0:00:32 time: 0.207907 data_time: 0.008261 memory: 1375 2022/09/17 02:36:40 - mmengine - INFO - Epoch(val) [210][300/407] eta: 0:00:22 time: 0.214092 data_time: 0.008754 memory: 1375 2022/09/17 02:36:50 - mmengine - INFO - Epoch(val) [210][350/407] eta: 0:00:11 time: 0.208956 data_time: 0.008700 memory: 1375 2022/09/17 02:37:00 - mmengine - INFO - Epoch(val) [210][400/407] eta: 0:00:01 time: 0.207212 data_time: 0.008056 memory: 1375 2022/09/17 02:37:36 - mmengine - INFO - Evaluating CocoMetric... 2022/09/17 02:37:50 - mmengine - INFO - Epoch(val) [210][407/407] coco/AP: 0.765889 coco/AP .5: 0.906824 coco/AP .75: 0.828897 coco/AP (M): 0.726312 coco/AP (L): 0.838062 coco/AR: 0.814011 coco/AR .5: 0.942853 coco/AR .75: 0.870592 coco/AR (M): 0.770554 coco/AR (L): 0.877926