2022/09/14 00:10:57 - 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: 1592644221 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 ------------------------------------------------------------ 2022/09/14 00:10:59 - 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='UDPHeatmap', input_size=(192, 256), heatmap_size=(48, 64), sigma=2) 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='UDPHeatmap', input_size=(192, 256), heatmap_size=(48, 64), sigma=2)), test_cfg=dict(flip_test=True, flip_mode='heatmap', shift_heatmap=False)) dataset_type = 'CocoDataset' data_mode = 'topdown' data_root = 'data/coco/' train_pipeline = [ dict( type='LoadImage', file_client_args=dict( backend='petrel', path_mapping=dict({ './data/': 's3://openmmlab/datasets/detection/', 'data/': 's3://openmmlab/datasets/detection/' }))), dict(type='GetBBoxCenterScale'), dict(type='RandomFlip', direction='horizontal'), dict(type='RandomHalfBody'), dict(type='RandomBBoxTransform'), dict(type='TopdownAffine', input_size=(192, 256), use_udp=True), dict( type='GenerateTarget', target_type='heatmap', encoder=dict( type='UDPHeatmap', input_size=(192, 256), heatmap_size=(48, 64), sigma=2)), dict(type='PackPoseInputs') ] test_pipeline = [ dict( type='LoadImage', file_client_args=dict( backend='petrel', path_mapping=dict({ './data/': 's3://openmmlab/datasets/detection/', 'data/': 's3://openmmlab/datasets/detection/' }))), dict(type='GetBBoxCenterScale'), dict(type='TopdownAffine', input_size=(192, 256), use_udp=True), dict(type='PackPoseInputs') ] train_dataloader = dict( batch_size=64, num_workers=2, persistent_workers=True, sampler=dict(type='DefaultSampler', shuffle=True), dataset=dict( type='CocoDataset', data_root='data/coco/', data_mode='topdown', ann_file='annotations/person_keypoints_train2017.json', data_prefix=dict(img='train2017/'), pipeline=[ dict( type='LoadImage', file_client_args=dict( backend='petrel', path_mapping=dict({ './data/': 's3://openmmlab/datasets/detection/', 'data/': 's3://openmmlab/datasets/detection/' }))), dict(type='GetBBoxCenterScale'), dict(type='RandomFlip', direction='horizontal'), dict(type='RandomHalfBody'), dict(type='RandomBBoxTransform'), dict(type='TopdownAffine', input_size=(192, 256), use_udp=True), dict( type='GenerateTarget', target_type='heatmap', encoder=dict( type='UDPHeatmap', input_size=(192, 256), heatmap_size=(48, 64), sigma=2)), dict(type='PackPoseInputs') ])) val_dataloader = dict( batch_size=32, num_workers=2, persistent_workers=True, drop_last=False, sampler=dict(type='DefaultSampler', shuffle=False, round_up=False), dataset=dict( type='CocoDataset', data_root='data/coco/', data_mode='topdown', ann_file='annotations/person_keypoints_val2017.json', bbox_file= 'data/coco/person_detection_results/COCO_val2017_detections_AP_H_56_person.json', data_prefix=dict(img='val2017/'), test_mode=True, pipeline=[ dict( type='LoadImage', file_client_args=dict( backend='petrel', path_mapping=dict({ './data/': 's3://openmmlab/datasets/detection/', 'data/': 's3://openmmlab/datasets/detection/' }))), dict(type='GetBBoxCenterScale'), dict(type='TopdownAffine', input_size=(192, 256), use_udp=True), dict(type='PackPoseInputs') ])) test_dataloader = dict( batch_size=32, num_workers=2, persistent_workers=True, drop_last=False, sampler=dict(type='DefaultSampler', shuffle=False, round_up=False), dataset=dict( type='CocoDataset', data_root='data/coco/', data_mode='topdown', ann_file='annotations/person_keypoints_val2017.json', bbox_file= 'data/coco/person_detection_results/COCO_val2017_detections_AP_H_56_person.json', data_prefix=dict(img='val2017/'), test_mode=True, pipeline=[ dict( type='LoadImage', file_client_args=dict( backend='petrel', path_mapping=dict({ './data/': 's3://openmmlab/datasets/detection/', 'data/': 's3://openmmlab/datasets/detection/' }))), dict(type='GetBBoxCenterScale'), dict(type='TopdownAffine', input_size=(192, 256), use_udp=True), 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/20220914/udp_w32_256_v1/' 2022/09/14 00:11:50 - 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. 2022/09/14 00:11:50 - 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. 2022/09/14 00:11:50 - 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. 2022/09/14 00:11:50 - 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. 2022/09/14 00:11:50 - 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. 2022/09/14 00:11:50 - 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. 2022/09/14 00:11:50 - 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. 2022/09/14 00:11:50 - 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. 2022/09/14 00:11:54 - 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. 2022/09/14 00:11:56 - 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. 2022/09/14 00:11:57 - 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. 2022/09/14 00:11:57 - 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 2022/09/14 00:12:11 - mmengine - INFO - Checkpoints will be saved to /mnt/lustre/liqikai/work_dirs/20220914/udp_w32_256_v1 by HardDiskBackend. 2022/09/14 00:12:47 - mmengine - INFO - Epoch(train) [1][50/293] lr: 4.954910e-05 eta: 12:09:13 time: 0.711670 data_time: 0.260766 memory: 9871 loss_kpt: 0.002211 acc_pose: 0.126493 loss: 0.002211 2022/09/14 00:13:11 - mmengine - INFO - Epoch(train) [1][100/293] lr: 9.959920e-05 eta: 10:12:30 time: 0.484844 data_time: 0.069656 memory: 9871 loss_kpt: 0.001914 acc_pose: 0.290544 loss: 0.001914 2022/09/14 00:13:36 - mmengine - INFO - Epoch(train) [1][150/293] lr: 1.496493e-04 eta: 9:34:00 time: 0.486778 data_time: 0.075282 memory: 9871 loss_kpt: 0.001614 acc_pose: 0.442846 loss: 0.001614 2022/09/14 00:14:00 - mmengine - INFO - Epoch(train) [1][200/293] lr: 1.996994e-04 eta: 9:13:21 time: 0.482157 data_time: 0.076573 memory: 9871 loss_kpt: 0.001419 acc_pose: 0.583641 loss: 0.001419 2022/09/14 00:14:24 - mmengine - INFO - Epoch(train) [1][250/293] lr: 2.497495e-04 eta: 8:59:58 time: 0.478067 data_time: 0.069587 memory: 9871 loss_kpt: 0.001306 acc_pose: 0.543585 loss: 0.001306 2022/09/14 00:14:44 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 00:14:44 - mmengine - INFO - Saving checkpoint at 1 epochs 2022/09/14 00:15:12 - mmengine - INFO - Epoch(train) [2][50/293] lr: 3.428427e-04 eta: 7:45:45 time: 0.489578 data_time: 0.080826 memory: 9871 loss_kpt: 0.001190 acc_pose: 0.651635 loss: 0.001190 2022/09/14 00:15:36 - mmengine - INFO - Epoch(train) [2][100/293] lr: 3.928928e-04 eta: 7:48:31 time: 0.480999 data_time: 0.072511 memory: 9871 loss_kpt: 0.001158 acc_pose: 0.579507 loss: 0.001158 2022/09/14 00:16:01 - mmengine - INFO - Epoch(train) [2][150/293] lr: 4.429429e-04 eta: 7:52:11 time: 0.495149 data_time: 0.071096 memory: 9871 loss_kpt: 0.001113 acc_pose: 0.649334 loss: 0.001113 2022/09/14 00:16:25 - mmengine - INFO - Epoch(train) [2][200/293] lr: 4.929930e-04 eta: 7:53:52 time: 0.483816 data_time: 0.076660 memory: 9871 loss_kpt: 0.001109 acc_pose: 0.656064 loss: 0.001109 2022/09/14 00:16:49 - mmengine - INFO - Epoch(train) [2][250/293] lr: 5.000000e-04 eta: 7:55:24 time: 0.486335 data_time: 0.069227 memory: 9871 loss_kpt: 0.001095 acc_pose: 0.630493 loss: 0.001095 2022/09/14 00:17:11 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 00:17:11 - mmengine - INFO - Saving checkpoint at 2 epochs 2022/09/14 00:17:40 - mmengine - INFO - Epoch(train) [3][50/293] lr: 5.000000e-04 eta: 7:26:04 time: 0.511363 data_time: 0.081131 memory: 9871 loss_kpt: 0.001034 acc_pose: 0.707171 loss: 0.001034 2022/09/14 00:18:04 - mmengine - INFO - Epoch(train) [3][100/293] lr: 5.000000e-04 eta: 7:28:43 time: 0.480358 data_time: 0.070510 memory: 9871 loss_kpt: 0.001033 acc_pose: 0.619306 loss: 0.001033 2022/09/14 00:18:28 - mmengine - INFO - Epoch(train) [3][150/293] lr: 5.000000e-04 eta: 7:31:58 time: 0.494978 data_time: 0.079357 memory: 9871 loss_kpt: 0.001022 acc_pose: 0.720335 loss: 0.001022 2022/09/14 00:18:53 - mmengine - INFO - Epoch(train) [3][200/293] lr: 5.000000e-04 eta: 7:35:17 time: 0.503439 data_time: 0.073113 memory: 9871 loss_kpt: 0.000998 acc_pose: 0.690756 loss: 0.000998 2022/09/14 00:19:18 - mmengine - INFO - Epoch(train) [3][250/293] lr: 5.000000e-04 eta: 7:37:21 time: 0.490070 data_time: 0.074326 memory: 9871 loss_kpt: 0.000978 acc_pose: 0.709646 loss: 0.000978 2022/09/14 00:19:39 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 00:19:39 - mmengine - INFO - Saving checkpoint at 3 epochs 2022/09/14 00:20:08 - mmengine - INFO - Epoch(train) [4][50/293] lr: 5.000000e-04 eta: 7:18:30 time: 0.507210 data_time: 0.079865 memory: 9871 loss_kpt: 0.000955 acc_pose: 0.731943 loss: 0.000955 2022/09/14 00:20:32 - mmengine - INFO - Epoch(train) [4][100/293] lr: 5.000000e-04 eta: 7:21:06 time: 0.491569 data_time: 0.073801 memory: 9871 loss_kpt: 0.000945 acc_pose: 0.735949 loss: 0.000945 2022/09/14 00:20:43 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 00:20:58 - mmengine - INFO - Epoch(train) [4][150/293] lr: 5.000000e-04 eta: 7:24:17 time: 0.509317 data_time: 0.073972 memory: 9871 loss_kpt: 0.000968 acc_pose: 0.615105 loss: 0.000968 2022/09/14 00:21:22 - mmengine - INFO - Epoch(train) [4][200/293] lr: 5.000000e-04 eta: 7:26:16 time: 0.491171 data_time: 0.078037 memory: 9871 loss_kpt: 0.000947 acc_pose: 0.658097 loss: 0.000947 2022/09/14 00:21:47 - mmengine - INFO - Epoch(train) [4][250/293] lr: 5.000000e-04 eta: 7:28:03 time: 0.491068 data_time: 0.073381 memory: 9871 loss_kpt: 0.000925 acc_pose: 0.657274 loss: 0.000925 2022/09/14 00:22:07 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 00:22:07 - mmengine - INFO - Saving checkpoint at 4 epochs 2022/09/14 00:22:36 - mmengine - INFO - Epoch(train) [5][50/293] lr: 5.000000e-04 eta: 7:14:03 time: 0.504234 data_time: 0.084512 memory: 9871 loss_kpt: 0.000924 acc_pose: 0.730605 loss: 0.000924 2022/09/14 00:23:01 - mmengine - INFO - Epoch(train) [5][100/293] lr: 5.000000e-04 eta: 7:16:14 time: 0.496097 data_time: 0.073973 memory: 9871 loss_kpt: 0.000925 acc_pose: 0.720303 loss: 0.000925 2022/09/14 00:23:25 - mmengine - INFO - Epoch(train) [5][150/293] lr: 5.000000e-04 eta: 7:18:10 time: 0.495020 data_time: 0.070031 memory: 9871 loss_kpt: 0.000888 acc_pose: 0.725200 loss: 0.000888 2022/09/14 00:23:50 - mmengine - INFO - Epoch(train) [5][200/293] lr: 5.000000e-04 eta: 7:19:49 time: 0.491952 data_time: 0.074426 memory: 9871 loss_kpt: 0.000907 acc_pose: 0.688387 loss: 0.000907 2022/09/14 00:24:14 - mmengine - INFO - Epoch(train) [5][250/293] lr: 5.000000e-04 eta: 7:21:18 time: 0.490815 data_time: 0.077721 memory: 9871 loss_kpt: 0.000894 acc_pose: 0.724175 loss: 0.000894 2022/09/14 00:24:36 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 00:24:36 - mmengine - INFO - Saving checkpoint at 5 epochs 2022/09/14 00:25:04 - mmengine - INFO - Epoch(train) [6][50/293] lr: 5.000000e-04 eta: 7:10:10 time: 0.502928 data_time: 0.082004 memory: 9871 loss_kpt: 0.000876 acc_pose: 0.724857 loss: 0.000876 2022/09/14 00:25:29 - mmengine - INFO - Epoch(train) [6][100/293] lr: 5.000000e-04 eta: 7:12:04 time: 0.500806 data_time: 0.074101 memory: 9871 loss_kpt: 0.000868 acc_pose: 0.716726 loss: 0.000868 2022/09/14 00:25:54 - mmengine - INFO - Epoch(train) [6][150/293] lr: 5.000000e-04 eta: 7:13:30 time: 0.490581 data_time: 0.068361 memory: 9871 loss_kpt: 0.000886 acc_pose: 0.666373 loss: 0.000886 2022/09/14 00:26:18 - mmengine - INFO - Epoch(train) [6][200/293] lr: 5.000000e-04 eta: 7:14:52 time: 0.491505 data_time: 0.079769 memory: 9871 loss_kpt: 0.000867 acc_pose: 0.619332 loss: 0.000867 2022/09/14 00:26:43 - mmengine - INFO - Epoch(train) [6][250/293] lr: 5.000000e-04 eta: 7:16:23 time: 0.500781 data_time: 0.072631 memory: 9871 loss_kpt: 0.000867 acc_pose: 0.739528 loss: 0.000867 2022/09/14 00:27:04 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 00:27:04 - mmengine - INFO - Saving checkpoint at 6 epochs 2022/09/14 00:27:33 - mmengine - INFO - Epoch(train) [7][50/293] lr: 5.000000e-04 eta: 7:07:16 time: 0.507558 data_time: 0.079997 memory: 9871 loss_kpt: 0.000850 acc_pose: 0.792557 loss: 0.000850 2022/09/14 00:27:58 - mmengine - INFO - Epoch(train) [7][100/293] lr: 5.000000e-04 eta: 7:08:50 time: 0.501090 data_time: 0.076306 memory: 9871 loss_kpt: 0.000840 acc_pose: 0.699195 loss: 0.000840 2022/09/14 00:28:23 - mmengine - INFO - Epoch(train) [7][150/293] lr: 5.000000e-04 eta: 7:10:24 time: 0.505189 data_time: 0.072397 memory: 9871 loss_kpt: 0.000855 acc_pose: 0.712744 loss: 0.000855 2022/09/14 00:28:48 - mmengine - INFO - Epoch(train) [7][200/293] lr: 5.000000e-04 eta: 7:11:42 time: 0.498644 data_time: 0.070130 memory: 9871 loss_kpt: 0.000847 acc_pose: 0.719889 loss: 0.000847 2022/09/14 00:29:09 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 00:29:13 - mmengine - INFO - Epoch(train) [7][250/293] lr: 5.000000e-04 eta: 7:12:57 time: 0.499841 data_time: 0.078632 memory: 9871 loss_kpt: 0.000842 acc_pose: 0.737682 loss: 0.000842 2022/09/14 00:29:34 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 00:29:34 - mmengine - INFO - Saving checkpoint at 7 epochs 2022/09/14 00:30:03 - mmengine - INFO - Epoch(train) [8][50/293] lr: 5.000000e-04 eta: 7:05:15 time: 0.514261 data_time: 0.089058 memory: 9871 loss_kpt: 0.000828 acc_pose: 0.745630 loss: 0.000828 2022/09/14 00:30:28 - mmengine - INFO - Epoch(train) [8][100/293] lr: 5.000000e-04 eta: 7:06:15 time: 0.488060 data_time: 0.078400 memory: 9871 loss_kpt: 0.000833 acc_pose: 0.717972 loss: 0.000833 2022/09/14 00:30:52 - mmengine - INFO - Epoch(train) [8][150/293] lr: 5.000000e-04 eta: 7:07:19 time: 0.494447 data_time: 0.071008 memory: 9871 loss_kpt: 0.000810 acc_pose: 0.653467 loss: 0.000810 2022/09/14 00:31:17 - mmengine - INFO - Epoch(train) [8][200/293] lr: 5.000000e-04 eta: 7:08:27 time: 0.500117 data_time: 0.076497 memory: 9871 loss_kpt: 0.000814 acc_pose: 0.751323 loss: 0.000814 2022/09/14 00:31:42 - mmengine - INFO - Epoch(train) [8][250/293] lr: 5.000000e-04 eta: 7:09:26 time: 0.496045 data_time: 0.071126 memory: 9871 loss_kpt: 0.000846 acc_pose: 0.758029 loss: 0.000846 2022/09/14 00:32:04 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 00:32:04 - mmengine - INFO - Saving checkpoint at 8 epochs 2022/09/14 00:32:33 - mmengine - INFO - Epoch(train) [9][50/293] lr: 5.000000e-04 eta: 7:02:51 time: 0.522484 data_time: 0.103505 memory: 9871 loss_kpt: 0.000832 acc_pose: 0.721027 loss: 0.000832 2022/09/14 00:32:57 - mmengine - INFO - Epoch(train) [9][100/293] lr: 5.000000e-04 eta: 7:03:46 time: 0.492008 data_time: 0.076333 memory: 9871 loss_kpt: 0.000816 acc_pose: 0.746120 loss: 0.000816 2022/09/14 00:33:22 - mmengine - INFO - Epoch(train) [9][150/293] lr: 5.000000e-04 eta: 7:04:42 time: 0.496166 data_time: 0.075736 memory: 9871 loss_kpt: 0.000824 acc_pose: 0.721650 loss: 0.000824 2022/09/14 00:33:47 - mmengine - INFO - Epoch(train) [9][200/293] lr: 5.000000e-04 eta: 7:05:38 time: 0.498337 data_time: 0.080685 memory: 9871 loss_kpt: 0.000819 acc_pose: 0.761080 loss: 0.000819 2022/09/14 00:34:12 - mmengine - INFO - Epoch(train) [9][250/293] lr: 5.000000e-04 eta: 7:06:36 time: 0.503241 data_time: 0.074436 memory: 9871 loss_kpt: 0.000838 acc_pose: 0.744026 loss: 0.000838 2022/09/14 00:34:33 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 00:34:33 - mmengine - INFO - Saving checkpoint at 9 epochs 2022/09/14 00:35:02 - mmengine - INFO - Epoch(train) [10][50/293] lr: 5.000000e-04 eta: 7:00:33 time: 0.512699 data_time: 0.088574 memory: 9871 loss_kpt: 0.000816 acc_pose: 0.708630 loss: 0.000816 2022/09/14 00:35:27 - mmengine - INFO - Epoch(train) [10][100/293] lr: 5.000000e-04 eta: 7:01:20 time: 0.493207 data_time: 0.070258 memory: 9871 loss_kpt: 0.000793 acc_pose: 0.784281 loss: 0.000793 2022/09/14 00:35:51 - mmengine - INFO - Epoch(train) [10][150/293] lr: 5.000000e-04 eta: 7:02:06 time: 0.494196 data_time: 0.074443 memory: 9871 loss_kpt: 0.000812 acc_pose: 0.767300 loss: 0.000812 2022/09/14 00:36:16 - mmengine - INFO - Epoch(train) [10][200/293] lr: 5.000000e-04 eta: 7:02:48 time: 0.492209 data_time: 0.077119 memory: 9871 loss_kpt: 0.000818 acc_pose: 0.725228 loss: 0.000818 2022/09/14 00:36:41 - mmengine - INFO - Epoch(train) [10][250/293] lr: 5.000000e-04 eta: 7:03:30 time: 0.494543 data_time: 0.083079 memory: 9871 loss_kpt: 0.000809 acc_pose: 0.755059 loss: 0.000809 2022/09/14 00:37:02 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 00:37:02 - mmengine - INFO - Saving checkpoint at 10 epochs 2022/09/14 00:37:19 - mmengine - INFO - Epoch(val) [10][50/407] eta: 0:01:13 time: 0.204912 data_time: 0.081152 memory: 9871 2022/09/14 00:37:25 - mmengine - INFO - Epoch(val) [10][100/407] eta: 0:00:41 time: 0.135060 data_time: 0.008393 memory: 920 2022/09/14 00:37:32 - mmengine - INFO - Epoch(val) [10][150/407] eta: 0:00:34 time: 0.133485 data_time: 0.009396 memory: 920 2022/09/14 00:37:39 - mmengine - INFO - Epoch(val) [10][200/407] eta: 0:00:27 time: 0.131167 data_time: 0.008532 memory: 920 2022/09/14 00:37:45 - mmengine - INFO - Epoch(val) [10][250/407] eta: 0:00:20 time: 0.130296 data_time: 0.008720 memory: 920 2022/09/14 00:37:52 - mmengine - INFO - Epoch(val) [10][300/407] eta: 0:00:14 time: 0.132078 data_time: 0.008677 memory: 920 2022/09/14 00:37:58 - mmengine - INFO - Epoch(val) [10][350/407] eta: 0:00:07 time: 0.133522 data_time: 0.008611 memory: 920 2022/09/14 00:38:05 - mmengine - INFO - Epoch(val) [10][400/407] eta: 0:00:00 time: 0.129487 data_time: 0.008338 memory: 920 2022/09/14 00:38:43 - mmengine - INFO - Evaluating CocoMetric... 2022/09/14 00:38:57 - mmengine - INFO - Epoch(val) [10][407/407] coco/AP: 0.658256 coco/AP .5: 0.868179 coco/AP .75: 0.721969 coco/AP (M): 0.619252 coco/AP (L): 0.726363 coco/AR: 0.718467 coco/AR .5: 0.910579 coco/AR .75: 0.776763 coco/AR (M): 0.672548 coco/AR (L): 0.783798 2022/09/14 00:39:00 - mmengine - INFO - The best checkpoint with 0.6583 coco/AP at 10 epoch is saved to best_coco/AP_epoch_10.pth. 2022/09/14 00:39:25 - mmengine - INFO - Epoch(train) [11][50/293] lr: 5.000000e-04 eta: 6:57:55 time: 0.506342 data_time: 0.079425 memory: 9871 loss_kpt: 0.000804 acc_pose: 0.739380 loss: 0.000804 2022/09/14 00:39:36 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 00:39:51 - mmengine - INFO - Epoch(train) [11][100/293] lr: 5.000000e-04 eta: 6:59:00 time: 0.517753 data_time: 0.079208 memory: 9871 loss_kpt: 0.000810 acc_pose: 0.752045 loss: 0.000810 2022/09/14 00:40:16 - mmengine - INFO - Epoch(train) [11][150/293] lr: 5.000000e-04 eta: 6:59:46 time: 0.500677 data_time: 0.077047 memory: 9871 loss_kpt: 0.000771 acc_pose: 0.746700 loss: 0.000771 2022/09/14 00:40:41 - mmengine - INFO - Epoch(train) [11][200/293] lr: 5.000000e-04 eta: 7:00:25 time: 0.496144 data_time: 0.077203 memory: 9871 loss_kpt: 0.000794 acc_pose: 0.776653 loss: 0.000794 2022/09/14 00:41:06 - mmengine - INFO - Epoch(train) [11][250/293] lr: 5.000000e-04 eta: 7:01:18 time: 0.513134 data_time: 0.072980 memory: 9871 loss_kpt: 0.000794 acc_pose: 0.746307 loss: 0.000794 2022/09/14 00:41:28 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 00:41:28 - mmengine - INFO - Saving checkpoint at 11 epochs 2022/09/14 00:41:57 - mmengine - INFO - Epoch(train) [12][50/293] lr: 5.000000e-04 eta: 6:56:28 time: 0.525529 data_time: 0.088362 memory: 9871 loss_kpt: 0.000786 acc_pose: 0.744110 loss: 0.000786 2022/09/14 00:42:22 - mmengine - INFO - Epoch(train) [12][100/293] lr: 5.000000e-04 eta: 6:57:14 time: 0.505602 data_time: 0.073248 memory: 9871 loss_kpt: 0.000791 acc_pose: 0.670823 loss: 0.000791 2022/09/14 00:42:47 - mmengine - INFO - Epoch(train) [12][150/293] lr: 5.000000e-04 eta: 6:57:39 time: 0.484375 data_time: 0.075582 memory: 9871 loss_kpt: 0.000784 acc_pose: 0.769844 loss: 0.000784 2022/09/14 00:43:12 - mmengine - INFO - Epoch(train) [12][200/293] lr: 5.000000e-04 eta: 6:58:20 time: 0.503727 data_time: 0.077188 memory: 9871 loss_kpt: 0.000776 acc_pose: 0.742909 loss: 0.000776 2022/09/14 00:43:37 - mmengine - INFO - Epoch(train) [12][250/293] lr: 5.000000e-04 eta: 6:58:53 time: 0.497945 data_time: 0.079695 memory: 9871 loss_kpt: 0.000801 acc_pose: 0.763877 loss: 0.000801 2022/09/14 00:43:58 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 00:43:58 - mmengine - INFO - Saving checkpoint at 12 epochs 2022/09/14 00:44:26 - mmengine - INFO - Epoch(train) [13][50/293] lr: 5.000000e-04 eta: 6:54:15 time: 0.512291 data_time: 0.084319 memory: 9871 loss_kpt: 0.000771 acc_pose: 0.731695 loss: 0.000771 2022/09/14 00:44:51 - mmengine - INFO - Epoch(train) [13][100/293] lr: 5.000000e-04 eta: 6:54:44 time: 0.492360 data_time: 0.074831 memory: 9871 loss_kpt: 0.000786 acc_pose: 0.741969 loss: 0.000786 2022/09/14 00:45:16 - mmengine - INFO - Epoch(train) [13][150/293] lr: 5.000000e-04 eta: 6:55:13 time: 0.492657 data_time: 0.073207 memory: 9871 loss_kpt: 0.000771 acc_pose: 0.803568 loss: 0.000771 2022/09/14 00:45:40 - mmengine - INFO - Epoch(train) [13][200/293] lr: 5.000000e-04 eta: 6:55:41 time: 0.494760 data_time: 0.076696 memory: 9871 loss_kpt: 0.000749 acc_pose: 0.738405 loss: 0.000749 2022/09/14 00:46:06 - mmengine - INFO - Epoch(train) [13][250/293] lr: 5.000000e-04 eta: 6:56:15 time: 0.503465 data_time: 0.081704 memory: 9871 loss_kpt: 0.000764 acc_pose: 0.747345 loss: 0.000764 2022/09/14 00:46:27 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 00:46:27 - mmengine - INFO - Saving checkpoint at 13 epochs 2022/09/14 00:46:55 - mmengine - INFO - Epoch(train) [14][50/293] lr: 5.000000e-04 eta: 6:51:51 time: 0.505632 data_time: 0.082124 memory: 9871 loss_kpt: 0.000785 acc_pose: 0.757150 loss: 0.000785 2022/09/14 00:47:20 - mmengine - INFO - Epoch(train) [14][100/293] lr: 5.000000e-04 eta: 6:52:21 time: 0.498126 data_time: 0.074655 memory: 9871 loss_kpt: 0.000781 acc_pose: 0.690394 loss: 0.000781 2022/09/14 00:47:46 - mmengine - INFO - Epoch(train) [14][150/293] lr: 5.000000e-04 eta: 6:52:53 time: 0.502528 data_time: 0.081596 memory: 9871 loss_kpt: 0.000783 acc_pose: 0.762891 loss: 0.000783 2022/09/14 00:48:06 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 00:48:10 - mmengine - INFO - Epoch(train) [14][200/293] lr: 5.000000e-04 eta: 6:53:19 time: 0.497282 data_time: 0.075857 memory: 9871 loss_kpt: 0.000769 acc_pose: 0.780799 loss: 0.000769 2022/09/14 00:48:35 - mmengine - INFO - Epoch(train) [14][250/293] lr: 5.000000e-04 eta: 6:53:45 time: 0.497290 data_time: 0.074353 memory: 9871 loss_kpt: 0.000789 acc_pose: 0.750718 loss: 0.000789 2022/09/14 00:48:56 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 00:48:56 - mmengine - INFO - Saving checkpoint at 14 epochs 2022/09/14 00:49:25 - mmengine - INFO - Epoch(train) [15][50/293] lr: 5.000000e-04 eta: 6:49:42 time: 0.510711 data_time: 0.077856 memory: 9871 loss_kpt: 0.000756 acc_pose: 0.801796 loss: 0.000756 2022/09/14 00:49:50 - mmengine - INFO - Epoch(train) [15][100/293] lr: 5.000000e-04 eta: 6:50:15 time: 0.508103 data_time: 0.078273 memory: 9871 loss_kpt: 0.000771 acc_pose: 0.682620 loss: 0.000771 2022/09/14 00:50:15 - mmengine - INFO - Epoch(train) [15][150/293] lr: 5.000000e-04 eta: 6:50:39 time: 0.496949 data_time: 0.075272 memory: 9871 loss_kpt: 0.000763 acc_pose: 0.754927 loss: 0.000763 2022/09/14 00:50:40 - mmengine - INFO - Epoch(train) [15][200/293] lr: 5.000000e-04 eta: 6:51:04 time: 0.499791 data_time: 0.074442 memory: 9871 loss_kpt: 0.000766 acc_pose: 0.789141 loss: 0.000766 2022/09/14 00:51:05 - mmengine - INFO - Epoch(train) [15][250/293] lr: 5.000000e-04 eta: 6:51:28 time: 0.500946 data_time: 0.079364 memory: 9871 loss_kpt: 0.000749 acc_pose: 0.791687 loss: 0.000749 2022/09/14 00:51:26 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 00:51:26 - mmengine - INFO - Saving checkpoint at 15 epochs 2022/09/14 00:51:55 - mmengine - INFO - Epoch(train) [16][50/293] lr: 5.000000e-04 eta: 6:47:43 time: 0.515173 data_time: 0.085910 memory: 9871 loss_kpt: 0.000759 acc_pose: 0.712423 loss: 0.000759 2022/09/14 00:52:21 - mmengine - INFO - Epoch(train) [16][100/293] lr: 5.000000e-04 eta: 6:48:09 time: 0.502460 data_time: 0.071357 memory: 9871 loss_kpt: 0.000759 acc_pose: 0.767385 loss: 0.000759 2022/09/14 00:52:46 - mmengine - INFO - Epoch(train) [16][150/293] lr: 5.000000e-04 eta: 6:48:33 time: 0.502267 data_time: 0.078803 memory: 9871 loss_kpt: 0.000756 acc_pose: 0.734190 loss: 0.000756 2022/09/14 00:53:11 - mmengine - INFO - Epoch(train) [16][200/293] lr: 5.000000e-04 eta: 6:48:58 time: 0.504505 data_time: 0.079583 memory: 9871 loss_kpt: 0.000763 acc_pose: 0.766616 loss: 0.000763 2022/09/14 00:53:36 - mmengine - INFO - Epoch(train) [16][250/293] lr: 5.000000e-04 eta: 6:49:15 time: 0.494604 data_time: 0.072568 memory: 9871 loss_kpt: 0.000753 acc_pose: 0.787591 loss: 0.000753 2022/09/14 00:53:56 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 00:53:56 - mmengine - INFO - Saving checkpoint at 16 epochs 2022/09/14 00:54:28 - mmengine - INFO - Epoch(train) [17][50/293] lr: 5.000000e-04 eta: 6:45:37 time: 0.505742 data_time: 0.079962 memory: 9871 loss_kpt: 0.000731 acc_pose: 0.782272 loss: 0.000731 2022/09/14 00:54:53 - mmengine - INFO - Epoch(train) [17][100/293] lr: 5.000000e-04 eta: 6:45:59 time: 0.502187 data_time: 0.079454 memory: 9871 loss_kpt: 0.000737 acc_pose: 0.765961 loss: 0.000737 2022/09/14 00:55:17 - mmengine - INFO - Epoch(train) [17][150/293] lr: 5.000000e-04 eta: 6:46:14 time: 0.492205 data_time: 0.071876 memory: 9871 loss_kpt: 0.000754 acc_pose: 0.784635 loss: 0.000754 2022/09/14 00:55:42 - mmengine - INFO - Epoch(train) [17][200/293] lr: 5.000000e-04 eta: 6:46:31 time: 0.495918 data_time: 0.075007 memory: 9871 loss_kpt: 0.000748 acc_pose: 0.771167 loss: 0.000748 2022/09/14 00:56:07 - mmengine - INFO - Epoch(train) [17][250/293] lr: 5.000000e-04 eta: 6:46:44 time: 0.490478 data_time: 0.079210 memory: 9871 loss_kpt: 0.000751 acc_pose: 0.734120 loss: 0.000751 2022/09/14 00:56:28 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 00:56:28 - mmengine - INFO - Saving checkpoint at 17 epochs 2022/09/14 00:56:41 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 00:56:57 - mmengine - INFO - Epoch(train) [18][50/293] lr: 5.000000e-04 eta: 6:43:18 time: 0.507720 data_time: 0.076630 memory: 9871 loss_kpt: 0.000739 acc_pose: 0.736263 loss: 0.000739 2022/09/14 00:57:22 - mmengine - INFO - Epoch(train) [18][100/293] lr: 5.000000e-04 eta: 6:43:38 time: 0.501228 data_time: 0.077178 memory: 9871 loss_kpt: 0.000745 acc_pose: 0.755643 loss: 0.000745 2022/09/14 00:57:47 - mmengine - INFO - Epoch(train) [18][150/293] lr: 5.000000e-04 eta: 6:43:55 time: 0.500224 data_time: 0.074291 memory: 9871 loss_kpt: 0.000738 acc_pose: 0.726921 loss: 0.000738 2022/09/14 00:58:12 - mmengine - INFO - Epoch(train) [18][200/293] lr: 5.000000e-04 eta: 6:44:15 time: 0.504695 data_time: 0.078389 memory: 9871 loss_kpt: 0.000731 acc_pose: 0.769892 loss: 0.000731 2022/09/14 00:58:37 - mmengine - INFO - Epoch(train) [18][250/293] lr: 5.000000e-04 eta: 6:44:28 time: 0.495091 data_time: 0.072196 memory: 9871 loss_kpt: 0.000749 acc_pose: 0.756232 loss: 0.000749 2022/09/14 00:58:57 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 00:58:57 - mmengine - INFO - Saving checkpoint at 18 epochs 2022/09/14 00:59:26 - mmengine - INFO - Epoch(train) [19][50/293] lr: 5.000000e-04 eta: 6:41:11 time: 0.504117 data_time: 0.083314 memory: 9871 loss_kpt: 0.000733 acc_pose: 0.783284 loss: 0.000733 2022/09/14 00:59:51 - mmengine - INFO - Epoch(train) [19][100/293] lr: 5.000000e-04 eta: 6:41:29 time: 0.504319 data_time: 0.078299 memory: 9871 loss_kpt: 0.000734 acc_pose: 0.790563 loss: 0.000734 2022/09/14 01:00:16 - mmengine - INFO - Epoch(train) [19][150/293] lr: 5.000000e-04 eta: 6:41:42 time: 0.495214 data_time: 0.074835 memory: 9871 loss_kpt: 0.000734 acc_pose: 0.806858 loss: 0.000734 2022/09/14 01:00:40 - mmengine - INFO - Epoch(train) [19][200/293] lr: 5.000000e-04 eta: 6:41:53 time: 0.493162 data_time: 0.073231 memory: 9871 loss_kpt: 0.000741 acc_pose: 0.791195 loss: 0.000741 2022/09/14 01:01:05 - mmengine - INFO - Epoch(train) [19][250/293] lr: 5.000000e-04 eta: 6:42:01 time: 0.489399 data_time: 0.075754 memory: 9871 loss_kpt: 0.000725 acc_pose: 0.744695 loss: 0.000725 2022/09/14 01:01:26 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 01:01:26 - mmengine - INFO - Saving checkpoint at 19 epochs 2022/09/14 01:01:54 - mmengine - INFO - Epoch(train) [20][50/293] lr: 5.000000e-04 eta: 6:38:56 time: 0.508599 data_time: 0.077860 memory: 9871 loss_kpt: 0.000728 acc_pose: 0.763938 loss: 0.000728 2022/09/14 01:02:19 - mmengine - INFO - Epoch(train) [20][100/293] lr: 5.000000e-04 eta: 6:39:08 time: 0.496735 data_time: 0.082544 memory: 9871 loss_kpt: 0.000728 acc_pose: 0.783904 loss: 0.000728 2022/09/14 01:02:44 - mmengine - INFO - Epoch(train) [20][150/293] lr: 5.000000e-04 eta: 6:39:20 time: 0.495967 data_time: 0.075735 memory: 9871 loss_kpt: 0.000733 acc_pose: 0.767505 loss: 0.000733 2022/09/14 01:03:09 - mmengine - INFO - Epoch(train) [20][200/293] lr: 5.000000e-04 eta: 6:39:32 time: 0.500000 data_time: 0.076436 memory: 9871 loss_kpt: 0.000724 acc_pose: 0.774482 loss: 0.000724 2022/09/14 01:03:33 - mmengine - INFO - Epoch(train) [20][250/293] lr: 5.000000e-04 eta: 6:39:40 time: 0.490428 data_time: 0.071398 memory: 9871 loss_kpt: 0.000736 acc_pose: 0.743689 loss: 0.000736 2022/09/14 01:03:55 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 01:03:55 - mmengine - INFO - Saving checkpoint at 20 epochs 2022/09/14 01:04:05 - mmengine - INFO - Epoch(val) [20][50/407] eta: 0:00:51 time: 0.143133 data_time: 0.014717 memory: 9871 2022/09/14 01:04:12 - mmengine - INFO - Epoch(val) [20][100/407] eta: 0:00:42 time: 0.139015 data_time: 0.013956 memory: 920 2022/09/14 01:04:19 - mmengine - INFO - Epoch(val) [20][150/407] eta: 0:00:34 time: 0.135371 data_time: 0.009435 memory: 920 2022/09/14 01:04:26 - mmengine - INFO - Epoch(val) [20][200/407] eta: 0:00:28 time: 0.138353 data_time: 0.009227 memory: 920 2022/09/14 01:04:32 - mmengine - INFO - Epoch(val) [20][250/407] eta: 0:00:21 time: 0.135142 data_time: 0.008908 memory: 920 2022/09/14 01:04:39 - mmengine - INFO - Epoch(val) [20][300/407] eta: 0:00:14 time: 0.133923 data_time: 0.008690 memory: 920 2022/09/14 01:04:46 - mmengine - INFO - Epoch(val) [20][350/407] eta: 0:00:07 time: 0.137878 data_time: 0.009280 memory: 920 2022/09/14 01:04:53 - mmengine - INFO - Epoch(val) [20][400/407] eta: 0:00:00 time: 0.136182 data_time: 0.016547 memory: 920 2022/09/14 01:05:31 - mmengine - INFO - Evaluating CocoMetric... 2022/09/14 01:05:46 - mmengine - INFO - Epoch(val) [20][407/407] coco/AP: 0.694743 coco/AP .5: 0.883332 coco/AP .75: 0.768149 coco/AP (M): 0.657852 coco/AP (L): 0.761989 coco/AR: 0.750913 coco/AR .5: 0.923016 coco/AR .75: 0.817538 coco/AR (M): 0.707238 coco/AR (L): 0.813675 2022/09/14 01:05:46 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220914/udp_w32_256_v1/best_coco/AP_epoch_10.pth is removed 2022/09/14 01:05:48 - mmengine - INFO - The best checkpoint with 0.6947 coco/AP at 20 epoch is saved to best_coco/AP_epoch_20.pth. 2022/09/14 01:06:14 - mmengine - INFO - Epoch(train) [21][50/293] lr: 5.000000e-04 eta: 6:36:40 time: 0.503880 data_time: 0.087263 memory: 9871 loss_kpt: 0.000711 acc_pose: 0.811747 loss: 0.000711 2022/09/14 01:06:39 - mmengine - INFO - Epoch(train) [21][100/293] lr: 5.000000e-04 eta: 6:36:52 time: 0.498583 data_time: 0.078561 memory: 9871 loss_kpt: 0.000726 acc_pose: 0.789154 loss: 0.000726 2022/09/14 01:06:58 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 01:07:03 - mmengine - INFO - Epoch(train) [21][150/293] lr: 5.000000e-04 eta: 6:36:57 time: 0.486368 data_time: 0.071625 memory: 9871 loss_kpt: 0.000728 acc_pose: 0.804871 loss: 0.000728 2022/09/14 01:07:27 - mmengine - INFO - Epoch(train) [21][200/293] lr: 5.000000e-04 eta: 6:37:03 time: 0.489614 data_time: 0.077268 memory: 9871 loss_kpt: 0.000740 acc_pose: 0.812126 loss: 0.000740 2022/09/14 01:07:53 - mmengine - INFO - Epoch(train) [21][250/293] lr: 5.000000e-04 eta: 6:37:16 time: 0.504425 data_time: 0.080191 memory: 9871 loss_kpt: 0.000717 acc_pose: 0.802565 loss: 0.000717 2022/09/14 01:08:15 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 01:08:15 - mmengine - INFO - Saving checkpoint at 21 epochs 2022/09/14 01:08:43 - mmengine - INFO - Epoch(train) [22][50/293] lr: 5.000000e-04 eta: 6:34:27 time: 0.511857 data_time: 0.087334 memory: 9871 loss_kpt: 0.000732 acc_pose: 0.754991 loss: 0.000732 2022/09/14 01:09:08 - mmengine - INFO - Epoch(train) [22][100/293] lr: 5.000000e-04 eta: 6:34:34 time: 0.491186 data_time: 0.075363 memory: 9871 loss_kpt: 0.000730 acc_pose: 0.781455 loss: 0.000730 2022/09/14 01:09:33 - mmengine - INFO - Epoch(train) [22][150/293] lr: 5.000000e-04 eta: 6:34:42 time: 0.494607 data_time: 0.074553 memory: 9871 loss_kpt: 0.000709 acc_pose: 0.762643 loss: 0.000709 2022/09/14 01:09:58 - mmengine - INFO - Epoch(train) [22][200/293] lr: 5.000000e-04 eta: 6:34:50 time: 0.498195 data_time: 0.082315 memory: 9871 loss_kpt: 0.000726 acc_pose: 0.791801 loss: 0.000726 2022/09/14 01:10:22 - mmengine - INFO - Epoch(train) [22][250/293] lr: 5.000000e-04 eta: 6:34:57 time: 0.495729 data_time: 0.077043 memory: 9871 loss_kpt: 0.000728 acc_pose: 0.802527 loss: 0.000728 2022/09/14 01:10:44 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 01:10:44 - mmengine - INFO - Saving checkpoint at 22 epochs 2022/09/14 01:11:12 - mmengine - INFO - Epoch(train) [23][50/293] lr: 5.000000e-04 eta: 6:32:10 time: 0.498600 data_time: 0.083150 memory: 9871 loss_kpt: 0.000724 acc_pose: 0.731927 loss: 0.000724 2022/09/14 01:11:37 - mmengine - INFO - Epoch(train) [23][100/293] lr: 5.000000e-04 eta: 6:32:20 time: 0.502943 data_time: 0.072102 memory: 9871 loss_kpt: 0.000731 acc_pose: 0.770040 loss: 0.000731 2022/09/14 01:12:02 - mmengine - INFO - Epoch(train) [23][150/293] lr: 5.000000e-04 eta: 6:32:29 time: 0.499716 data_time: 0.081136 memory: 9871 loss_kpt: 0.000732 acc_pose: 0.788523 loss: 0.000732 2022/09/14 01:12:27 - mmengine - INFO - Epoch(train) [23][200/293] lr: 5.000000e-04 eta: 6:32:37 time: 0.500881 data_time: 0.075734 memory: 9871 loss_kpt: 0.000721 acc_pose: 0.766773 loss: 0.000721 2022/09/14 01:12:52 - mmengine - INFO - Epoch(train) [23][250/293] lr: 5.000000e-04 eta: 6:32:46 time: 0.503354 data_time: 0.079006 memory: 9871 loss_kpt: 0.000720 acc_pose: 0.770529 loss: 0.000720 2022/09/14 01:13:13 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 01:13:13 - mmengine - INFO - Saving checkpoint at 23 epochs 2022/09/14 01:13:42 - mmengine - INFO - Epoch(train) [24][50/293] lr: 5.000000e-04 eta: 6:30:09 time: 0.508681 data_time: 0.089920 memory: 9871 loss_kpt: 0.000715 acc_pose: 0.800477 loss: 0.000715 2022/09/14 01:14:07 - mmengine - INFO - Epoch(train) [24][100/293] lr: 5.000000e-04 eta: 6:30:19 time: 0.506292 data_time: 0.080825 memory: 9871 loss_kpt: 0.000718 acc_pose: 0.761725 loss: 0.000718 2022/09/14 01:14:32 - mmengine - INFO - Epoch(train) [24][150/293] lr: 5.000000e-04 eta: 6:30:22 time: 0.491463 data_time: 0.074930 memory: 9871 loss_kpt: 0.000718 acc_pose: 0.797569 loss: 0.000718 2022/09/14 01:14:57 - mmengine - INFO - Epoch(train) [24][200/293] lr: 5.000000e-04 eta: 6:30:29 time: 0.500805 data_time: 0.076863 memory: 9871 loss_kpt: 0.000707 acc_pose: 0.777289 loss: 0.000707 2022/09/14 01:15:22 - mmengine - INFO - Epoch(train) [24][250/293] lr: 5.000000e-04 eta: 6:30:33 time: 0.492781 data_time: 0.073550 memory: 9871 loss_kpt: 0.000727 acc_pose: 0.756892 loss: 0.000727 2022/09/14 01:15:27 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 01:15:43 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 01:15:43 - mmengine - INFO - Saving checkpoint at 24 epochs 2022/09/14 01:16:12 - mmengine - INFO - Epoch(train) [25][50/293] lr: 5.000000e-04 eta: 6:28:01 time: 0.508931 data_time: 0.080093 memory: 9871 loss_kpt: 0.000711 acc_pose: 0.775436 loss: 0.000711 2022/09/14 01:16:37 - mmengine - INFO - Epoch(train) [25][100/293] lr: 5.000000e-04 eta: 6:28:06 time: 0.495580 data_time: 0.075430 memory: 9871 loss_kpt: 0.000719 acc_pose: 0.809748 loss: 0.000719 2022/09/14 01:17:02 - mmengine - INFO - Epoch(train) [25][150/293] lr: 5.000000e-04 eta: 6:28:13 time: 0.504257 data_time: 0.077212 memory: 9871 loss_kpt: 0.000722 acc_pose: 0.754694 loss: 0.000722 2022/09/14 01:17:27 - mmengine - INFO - Epoch(train) [25][200/293] lr: 5.000000e-04 eta: 6:28:16 time: 0.493229 data_time: 0.075459 memory: 9871 loss_kpt: 0.000714 acc_pose: 0.756283 loss: 0.000714 2022/09/14 01:17:52 - mmengine - INFO - Epoch(train) [25][250/293] lr: 5.000000e-04 eta: 6:28:20 time: 0.498833 data_time: 0.080433 memory: 9871 loss_kpt: 0.000705 acc_pose: 0.770281 loss: 0.000705 2022/09/14 01:18:13 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 01:18:13 - mmengine - INFO - Saving checkpoint at 25 epochs 2022/09/14 01:18:42 - mmengine - INFO - Epoch(train) [26][50/293] lr: 5.000000e-04 eta: 6:25:57 time: 0.516325 data_time: 0.091205 memory: 9871 loss_kpt: 0.000699 acc_pose: 0.787737 loss: 0.000699 2022/09/14 01:19:07 - mmengine - INFO - Epoch(train) [26][100/293] lr: 5.000000e-04 eta: 6:25:57 time: 0.487747 data_time: 0.073284 memory: 9871 loss_kpt: 0.000720 acc_pose: 0.761879 loss: 0.000720 2022/09/14 01:19:32 - mmengine - INFO - Epoch(train) [26][150/293] lr: 5.000000e-04 eta: 6:26:03 time: 0.504092 data_time: 0.077067 memory: 9871 loss_kpt: 0.000707 acc_pose: 0.765224 loss: 0.000707 2022/09/14 01:19:57 - mmengine - INFO - Epoch(train) [26][200/293] lr: 5.000000e-04 eta: 6:26:08 time: 0.500460 data_time: 0.074574 memory: 9871 loss_kpt: 0.000705 acc_pose: 0.828108 loss: 0.000705 2022/09/14 01:20:22 - mmengine - INFO - Epoch(train) [26][250/293] lr: 5.000000e-04 eta: 6:26:13 time: 0.504369 data_time: 0.076661 memory: 9871 loss_kpt: 0.000706 acc_pose: 0.817700 loss: 0.000706 2022/09/14 01:20:44 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 01:20:44 - mmengine - INFO - Saving checkpoint at 26 epochs 2022/09/14 01:21:13 - mmengine - INFO - Epoch(train) [27][50/293] lr: 5.000000e-04 eta: 6:23:53 time: 0.513840 data_time: 0.080153 memory: 9871 loss_kpt: 0.000690 acc_pose: 0.832977 loss: 0.000690 2022/09/14 01:21:37 - mmengine - INFO - Epoch(train) [27][100/293] lr: 5.000000e-04 eta: 6:23:53 time: 0.488257 data_time: 0.075589 memory: 9871 loss_kpt: 0.000712 acc_pose: 0.800015 loss: 0.000712 2022/09/14 01:22:02 - mmengine - INFO - Epoch(train) [27][150/293] lr: 5.000000e-04 eta: 6:23:59 time: 0.506424 data_time: 0.072533 memory: 9871 loss_kpt: 0.000719 acc_pose: 0.774147 loss: 0.000719 2022/09/14 01:22:27 - mmengine - INFO - Epoch(train) [27][200/293] lr: 5.000000e-04 eta: 6:24:02 time: 0.500072 data_time: 0.078016 memory: 9871 loss_kpt: 0.000701 acc_pose: 0.727592 loss: 0.000701 2022/09/14 01:22:52 - mmengine - INFO - Epoch(train) [27][250/293] lr: 5.000000e-04 eta: 6:24:03 time: 0.495893 data_time: 0.076471 memory: 9871 loss_kpt: 0.000699 acc_pose: 0.788001 loss: 0.000699 2022/09/14 01:23:13 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 01:23:13 - mmengine - INFO - Saving checkpoint at 27 epochs 2022/09/14 01:23:42 - mmengine - INFO - Epoch(train) [28][50/293] lr: 5.000000e-04 eta: 6:21:46 time: 0.508971 data_time: 0.080272 memory: 9871 loss_kpt: 0.000709 acc_pose: 0.770945 loss: 0.000709 2022/09/14 01:24:02 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 01:24:07 - mmengine - INFO - Epoch(train) [28][100/293] lr: 5.000000e-04 eta: 6:21:50 time: 0.505724 data_time: 0.071153 memory: 9871 loss_kpt: 0.000707 acc_pose: 0.846598 loss: 0.000707 2022/09/14 01:24:33 - mmengine - INFO - Epoch(train) [28][150/293] lr: 5.000000e-04 eta: 6:21:55 time: 0.506122 data_time: 0.075267 memory: 9871 loss_kpt: 0.000707 acc_pose: 0.837185 loss: 0.000707 2022/09/14 01:24:58 - mmengine - INFO - Epoch(train) [28][200/293] lr: 5.000000e-04 eta: 6:21:57 time: 0.498801 data_time: 0.075045 memory: 9871 loss_kpt: 0.000692 acc_pose: 0.777247 loss: 0.000692 2022/09/14 01:25:23 - mmengine - INFO - Epoch(train) [28][250/293] lr: 5.000000e-04 eta: 6:22:00 time: 0.503626 data_time: 0.078681 memory: 9871 loss_kpt: 0.000710 acc_pose: 0.759748 loss: 0.000710 2022/09/14 01:25:44 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 01:25:44 - mmengine - INFO - Saving checkpoint at 28 epochs 2022/09/14 01:26:13 - mmengine - INFO - Epoch(train) [29][50/293] lr: 5.000000e-04 eta: 6:19:43 time: 0.500335 data_time: 0.079193 memory: 9871 loss_kpt: 0.000690 acc_pose: 0.808537 loss: 0.000690 2022/09/14 01:26:38 - mmengine - INFO - Epoch(train) [29][100/293] lr: 5.000000e-04 eta: 6:19:45 time: 0.498591 data_time: 0.075188 memory: 9871 loss_kpt: 0.000710 acc_pose: 0.785097 loss: 0.000710 2022/09/14 01:27:03 - mmengine - INFO - Epoch(train) [29][150/293] lr: 5.000000e-04 eta: 6:19:45 time: 0.497814 data_time: 0.076281 memory: 9871 loss_kpt: 0.000698 acc_pose: 0.740292 loss: 0.000698 2022/09/14 01:27:27 - mmengine - INFO - Epoch(train) [29][200/293] lr: 5.000000e-04 eta: 6:19:44 time: 0.491005 data_time: 0.075605 memory: 9871 loss_kpt: 0.000708 acc_pose: 0.829240 loss: 0.000708 2022/09/14 01:27:52 - mmengine - INFO - Epoch(train) [29][250/293] lr: 5.000000e-04 eta: 6:19:43 time: 0.494385 data_time: 0.075665 memory: 9871 loss_kpt: 0.000695 acc_pose: 0.779705 loss: 0.000695 2022/09/14 01:28:13 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 01:28:13 - mmengine - INFO - Saving checkpoint at 29 epochs 2022/09/14 01:28:41 - mmengine - INFO - Epoch(train) [30][50/293] lr: 5.000000e-04 eta: 6:17:31 time: 0.500198 data_time: 0.078874 memory: 9871 loss_kpt: 0.000694 acc_pose: 0.870937 loss: 0.000694 2022/09/14 01:29:06 - mmengine - INFO - Epoch(train) [30][100/293] lr: 5.000000e-04 eta: 6:17:32 time: 0.500641 data_time: 0.072956 memory: 9871 loss_kpt: 0.000712 acc_pose: 0.799027 loss: 0.000712 2022/09/14 01:29:31 - mmengine - INFO - Epoch(train) [30][150/293] lr: 5.000000e-04 eta: 6:17:31 time: 0.495166 data_time: 0.074158 memory: 9871 loss_kpt: 0.000691 acc_pose: 0.831770 loss: 0.000691 2022/09/14 01:29:56 - mmengine - INFO - Epoch(train) [30][200/293] lr: 5.000000e-04 eta: 6:17:29 time: 0.493809 data_time: 0.077228 memory: 9871 loss_kpt: 0.000699 acc_pose: 0.765248 loss: 0.000699 2022/09/14 01:30:21 - mmengine - INFO - Epoch(train) [30][250/293] lr: 5.000000e-04 eta: 6:17:30 time: 0.501939 data_time: 0.076613 memory: 9871 loss_kpt: 0.000709 acc_pose: 0.787981 loss: 0.000709 2022/09/14 01:30:42 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 01:30:42 - mmengine - INFO - Saving checkpoint at 30 epochs 2022/09/14 01:30:53 - mmengine - INFO - Epoch(val) [30][50/407] eta: 0:00:49 time: 0.139915 data_time: 0.013951 memory: 9871 2022/09/14 01:30:59 - mmengine - INFO - Epoch(val) [30][100/407] eta: 0:00:41 time: 0.136392 data_time: 0.009487 memory: 920 2022/09/14 01:31:06 - mmengine - INFO - Epoch(val) [30][150/407] eta: 0:00:33 time: 0.130258 data_time: 0.008768 memory: 920 2022/09/14 01:31:13 - mmengine - INFO - Epoch(val) [30][200/407] eta: 0:00:27 time: 0.131559 data_time: 0.009357 memory: 920 2022/09/14 01:31:19 - mmengine - INFO - Epoch(val) [30][250/407] eta: 0:00:20 time: 0.131217 data_time: 0.008783 memory: 920 2022/09/14 01:31:26 - mmengine - INFO - Epoch(val) [30][300/407] eta: 0:00:14 time: 0.133037 data_time: 0.008318 memory: 920 2022/09/14 01:31:33 - mmengine - INFO - Epoch(val) [30][350/407] eta: 0:00:07 time: 0.136435 data_time: 0.008565 memory: 920 2022/09/14 01:31:39 - mmengine - INFO - Epoch(val) [30][400/407] eta: 0:00:00 time: 0.126567 data_time: 0.007275 memory: 920 2022/09/14 01:32:17 - mmengine - INFO - Evaluating CocoMetric... 2022/09/14 01:32:31 - mmengine - INFO - Epoch(val) [30][407/407] coco/AP: 0.710691 coco/AP .5: 0.887972 coco/AP .75: 0.781897 coco/AP (M): 0.673184 coco/AP (L): 0.778126 coco/AR: 0.765412 coco/AR .5: 0.927110 coco/AR .75: 0.830762 coco/AR (M): 0.720814 coco/AR (L): 0.829283 2022/09/14 01:32:31 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220914/udp_w32_256_v1/best_coco/AP_epoch_20.pth is removed 2022/09/14 01:32:33 - mmengine - INFO - The best checkpoint with 0.7107 coco/AP at 30 epoch is saved to best_coco/AP_epoch_30.pth. 2022/09/14 01:32:59 - mmengine - INFO - Epoch(train) [31][50/293] lr: 5.000000e-04 eta: 6:15:27 time: 0.518279 data_time: 0.092382 memory: 9871 loss_kpt: 0.000693 acc_pose: 0.771468 loss: 0.000693 2022/09/14 01:33:24 - mmengine - INFO - Epoch(train) [31][100/293] lr: 5.000000e-04 eta: 6:15:26 time: 0.497006 data_time: 0.073001 memory: 9871 loss_kpt: 0.000703 acc_pose: 0.825472 loss: 0.000703 2022/09/14 01:33:48 - mmengine - INFO - Epoch(train) [31][150/293] lr: 5.000000e-04 eta: 6:15:22 time: 0.486885 data_time: 0.077427 memory: 9871 loss_kpt: 0.000701 acc_pose: 0.736846 loss: 0.000701 2022/09/14 01:34:13 - mmengine - INFO - Epoch(train) [31][200/293] lr: 5.000000e-04 eta: 6:15:20 time: 0.494030 data_time: 0.075477 memory: 9871 loss_kpt: 0.000708 acc_pose: 0.746339 loss: 0.000708 2022/09/14 01:34:18 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 01:34:38 - mmengine - INFO - Epoch(train) [31][250/293] lr: 5.000000e-04 eta: 6:15:20 time: 0.502850 data_time: 0.079329 memory: 9871 loss_kpt: 0.000693 acc_pose: 0.793535 loss: 0.000693 2022/09/14 01:34:59 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 01:34:59 - mmengine - INFO - Saving checkpoint at 31 epochs 2022/09/14 01:35:29 - mmengine - INFO - Epoch(train) [32][50/293] lr: 5.000000e-04 eta: 6:13:21 time: 0.522027 data_time: 0.089248 memory: 9871 loss_kpt: 0.000694 acc_pose: 0.761644 loss: 0.000694 2022/09/14 01:35:53 - mmengine - INFO - Epoch(train) [32][100/293] lr: 5.000000e-04 eta: 6:13:19 time: 0.498140 data_time: 0.077127 memory: 9871 loss_kpt: 0.000684 acc_pose: 0.804826 loss: 0.000684 2022/09/14 01:36:18 - mmengine - INFO - Epoch(train) [32][150/293] lr: 5.000000e-04 eta: 6:13:15 time: 0.488565 data_time: 0.075524 memory: 9871 loss_kpt: 0.000684 acc_pose: 0.783029 loss: 0.000684 2022/09/14 01:36:43 - mmengine - INFO - Epoch(train) [32][200/293] lr: 5.000000e-04 eta: 6:13:14 time: 0.499836 data_time: 0.079788 memory: 9871 loss_kpt: 0.000691 acc_pose: 0.777947 loss: 0.000691 2022/09/14 01:37:07 - mmengine - INFO - Epoch(train) [32][250/293] lr: 5.000000e-04 eta: 6:13:10 time: 0.490588 data_time: 0.075779 memory: 9871 loss_kpt: 0.000680 acc_pose: 0.785708 loss: 0.000680 2022/09/14 01:37:29 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 01:37:29 - mmengine - INFO - Saving checkpoint at 32 epochs 2022/09/14 01:37:58 - mmengine - INFO - Epoch(train) [33][50/293] lr: 5.000000e-04 eta: 6:11:10 time: 0.510431 data_time: 0.088611 memory: 9871 loss_kpt: 0.000687 acc_pose: 0.761047 loss: 0.000687 2022/09/14 01:38:23 - mmengine - INFO - Epoch(train) [33][100/293] lr: 5.000000e-04 eta: 6:11:08 time: 0.498059 data_time: 0.075633 memory: 9871 loss_kpt: 0.000686 acc_pose: 0.811966 loss: 0.000686 2022/09/14 01:38:48 - mmengine - INFO - Epoch(train) [33][150/293] lr: 5.000000e-04 eta: 6:11:07 time: 0.501782 data_time: 0.080364 memory: 9871 loss_kpt: 0.000678 acc_pose: 0.809319 loss: 0.000678 2022/09/14 01:39:13 - mmengine - INFO - Epoch(train) [33][200/293] lr: 5.000000e-04 eta: 6:11:05 time: 0.499931 data_time: 0.077507 memory: 9871 loss_kpt: 0.000689 acc_pose: 0.810083 loss: 0.000689 2022/09/14 01:39:38 - mmengine - INFO - Epoch(train) [33][250/293] lr: 5.000000e-04 eta: 6:11:04 time: 0.503359 data_time: 0.086254 memory: 9871 loss_kpt: 0.000701 acc_pose: 0.786888 loss: 0.000701 2022/09/14 01:40:00 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 01:40:00 - mmengine - INFO - Saving checkpoint at 33 epochs 2022/09/14 01:40:28 - mmengine - INFO - Epoch(train) [34][50/293] lr: 5.000000e-04 eta: 6:09:05 time: 0.500354 data_time: 0.085421 memory: 9871 loss_kpt: 0.000674 acc_pose: 0.761718 loss: 0.000674 2022/09/14 01:40:53 - mmengine - INFO - Epoch(train) [34][100/293] lr: 5.000000e-04 eta: 6:09:03 time: 0.501497 data_time: 0.076865 memory: 9871 loss_kpt: 0.000686 acc_pose: 0.837553 loss: 0.000686 2022/09/14 01:41:17 - mmengine - INFO - Epoch(train) [34][150/293] lr: 5.000000e-04 eta: 6:08:57 time: 0.485126 data_time: 0.074750 memory: 9871 loss_kpt: 0.000675 acc_pose: 0.750753 loss: 0.000675 2022/09/14 01:41:43 - mmengine - INFO - Epoch(train) [34][200/293] lr: 5.000000e-04 eta: 6:08:55 time: 0.503866 data_time: 0.085746 memory: 9871 loss_kpt: 0.000685 acc_pose: 0.823185 loss: 0.000685 2022/09/14 01:42:07 - mmengine - INFO - Epoch(train) [34][250/293] lr: 5.000000e-04 eta: 6:08:50 time: 0.488904 data_time: 0.077549 memory: 9871 loss_kpt: 0.000700 acc_pose: 0.777762 loss: 0.000700 2022/09/14 01:42:28 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 01:42:28 - mmengine - INFO - Saving checkpoint at 34 epochs 2022/09/14 01:42:52 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 01:42:58 - mmengine - INFO - Epoch(train) [35][50/293] lr: 5.000000e-04 eta: 6:07:02 time: 0.533738 data_time: 0.105702 memory: 9871 loss_kpt: 0.000677 acc_pose: 0.819155 loss: 0.000677 2022/09/14 01:43:22 - mmengine - INFO - Epoch(train) [35][100/293] lr: 5.000000e-04 eta: 6:06:55 time: 0.484709 data_time: 0.075266 memory: 9871 loss_kpt: 0.000688 acc_pose: 0.764840 loss: 0.000688 2022/09/14 01:43:46 - mmengine - INFO - Epoch(train) [35][150/293] lr: 5.000000e-04 eta: 6:06:48 time: 0.485302 data_time: 0.070879 memory: 9871 loss_kpt: 0.000684 acc_pose: 0.765805 loss: 0.000684 2022/09/14 01:44:11 - mmengine - INFO - Epoch(train) [35][200/293] lr: 5.000000e-04 eta: 6:06:43 time: 0.492705 data_time: 0.074915 memory: 9871 loss_kpt: 0.000691 acc_pose: 0.807527 loss: 0.000691 2022/09/14 01:44:36 - mmengine - INFO - Epoch(train) [35][250/293] lr: 5.000000e-04 eta: 6:06:40 time: 0.500282 data_time: 0.083814 memory: 9871 loss_kpt: 0.000678 acc_pose: 0.789120 loss: 0.000678 2022/09/14 01:44:58 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 01:44:58 - mmengine - INFO - Saving checkpoint at 35 epochs 2022/09/14 01:45:26 - mmengine - INFO - Epoch(train) [36][50/293] lr: 5.000000e-04 eta: 6:04:48 time: 0.507932 data_time: 0.085728 memory: 9871 loss_kpt: 0.000681 acc_pose: 0.780426 loss: 0.000681 2022/09/14 01:45:51 - mmengine - INFO - Epoch(train) [36][100/293] lr: 5.000000e-04 eta: 6:04:43 time: 0.494809 data_time: 0.077068 memory: 9871 loss_kpt: 0.000690 acc_pose: 0.825956 loss: 0.000690 2022/09/14 01:46:17 - mmengine - INFO - Epoch(train) [36][150/293] lr: 5.000000e-04 eta: 6:04:42 time: 0.507566 data_time: 0.077435 memory: 9871 loss_kpt: 0.000677 acc_pose: 0.796950 loss: 0.000677 2022/09/14 01:46:42 - mmengine - INFO - Epoch(train) [36][200/293] lr: 5.000000e-04 eta: 6:04:39 time: 0.504251 data_time: 0.082772 memory: 9871 loss_kpt: 0.000684 acc_pose: 0.783211 loss: 0.000684 2022/09/14 01:47:07 - mmengine - INFO - Epoch(train) [36][250/293] lr: 5.000000e-04 eta: 6:04:34 time: 0.496163 data_time: 0.078517 memory: 9871 loss_kpt: 0.000676 acc_pose: 0.793439 loss: 0.000676 2022/09/14 01:47:28 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 01:47:28 - mmengine - INFO - Saving checkpoint at 36 epochs 2022/09/14 01:47:56 - mmengine - INFO - Epoch(train) [37][50/293] lr: 5.000000e-04 eta: 6:02:44 time: 0.507179 data_time: 0.080152 memory: 9871 loss_kpt: 0.000675 acc_pose: 0.825333 loss: 0.000675 2022/09/14 01:48:21 - mmengine - INFO - Epoch(train) [37][100/293] lr: 5.000000e-04 eta: 6:02:39 time: 0.495440 data_time: 0.079299 memory: 9871 loss_kpt: 0.000677 acc_pose: 0.798357 loss: 0.000677 2022/09/14 01:48:46 - mmengine - INFO - Epoch(train) [37][150/293] lr: 5.000000e-04 eta: 6:02:33 time: 0.492532 data_time: 0.078226 memory: 9871 loss_kpt: 0.000663 acc_pose: 0.819857 loss: 0.000663 2022/09/14 01:49:11 - mmengine - INFO - Epoch(train) [37][200/293] lr: 5.000000e-04 eta: 6:02:28 time: 0.497640 data_time: 0.080189 memory: 9871 loss_kpt: 0.000681 acc_pose: 0.766270 loss: 0.000681 2022/09/14 01:49:35 - mmengine - INFO - Epoch(train) [37][250/293] lr: 5.000000e-04 eta: 6:02:23 time: 0.497708 data_time: 0.076301 memory: 9871 loss_kpt: 0.000685 acc_pose: 0.850883 loss: 0.000685 2022/09/14 01:49:57 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 01:49:57 - mmengine - INFO - Saving checkpoint at 37 epochs 2022/09/14 01:50:25 - mmengine - INFO - Epoch(train) [38][50/293] lr: 5.000000e-04 eta: 6:00:35 time: 0.501495 data_time: 0.083914 memory: 9871 loss_kpt: 0.000671 acc_pose: 0.777944 loss: 0.000671 2022/09/14 01:50:50 - mmengine - INFO - Epoch(train) [38][100/293] lr: 5.000000e-04 eta: 6:00:29 time: 0.493643 data_time: 0.072073 memory: 9871 loss_kpt: 0.000677 acc_pose: 0.801091 loss: 0.000677 2022/09/14 01:51:14 - mmengine - INFO - Epoch(train) [38][150/293] lr: 5.000000e-04 eta: 6:00:24 time: 0.498896 data_time: 0.080711 memory: 9871 loss_kpt: 0.000675 acc_pose: 0.842390 loss: 0.000675 2022/09/14 01:51:19 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 01:51:39 - mmengine - INFO - Epoch(train) [38][200/293] lr: 5.000000e-04 eta: 6:00:19 time: 0.499414 data_time: 0.079893 memory: 9871 loss_kpt: 0.000693 acc_pose: 0.794507 loss: 0.000693 2022/09/14 01:52:04 - mmengine - INFO - Epoch(train) [38][250/293] lr: 5.000000e-04 eta: 6:00:11 time: 0.490656 data_time: 0.075536 memory: 9871 loss_kpt: 0.000687 acc_pose: 0.768313 loss: 0.000687 2022/09/14 01:52:25 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 01:52:25 - mmengine - INFO - Saving checkpoint at 38 epochs 2022/09/14 01:52:54 - mmengine - INFO - Epoch(train) [39][50/293] lr: 5.000000e-04 eta: 5:58:29 time: 0.520166 data_time: 0.083234 memory: 9871 loss_kpt: 0.000665 acc_pose: 0.792300 loss: 0.000665 2022/09/14 01:53:20 - mmengine - INFO - Epoch(train) [39][100/293] lr: 5.000000e-04 eta: 5:58:25 time: 0.504118 data_time: 0.076921 memory: 9871 loss_kpt: 0.000671 acc_pose: 0.801905 loss: 0.000671 2022/09/14 01:53:44 - mmengine - INFO - Epoch(train) [39][150/293] lr: 5.000000e-04 eta: 5:58:18 time: 0.492714 data_time: 0.078565 memory: 9871 loss_kpt: 0.000674 acc_pose: 0.797844 loss: 0.000674 2022/09/14 01:54:10 - mmengine - INFO - Epoch(train) [39][200/293] lr: 5.000000e-04 eta: 5:58:14 time: 0.505602 data_time: 0.076448 memory: 9871 loss_kpt: 0.000677 acc_pose: 0.801811 loss: 0.000677 2022/09/14 01:54:34 - mmengine - INFO - Epoch(train) [39][250/293] lr: 5.000000e-04 eta: 5:58:06 time: 0.489621 data_time: 0.071562 memory: 9871 loss_kpt: 0.000676 acc_pose: 0.780923 loss: 0.000676 2022/09/14 01:54:55 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 01:54:55 - mmengine - INFO - Saving checkpoint at 39 epochs 2022/09/14 01:55:24 - mmengine - INFO - Epoch(train) [40][50/293] lr: 5.000000e-04 eta: 5:56:23 time: 0.504842 data_time: 0.084779 memory: 9871 loss_kpt: 0.000677 acc_pose: 0.840776 loss: 0.000677 2022/09/14 01:55:49 - mmengine - INFO - Epoch(train) [40][100/293] lr: 5.000000e-04 eta: 5:56:19 time: 0.509724 data_time: 0.071920 memory: 9871 loss_kpt: 0.000664 acc_pose: 0.803119 loss: 0.000664 2022/09/14 01:56:14 - mmengine - INFO - Epoch(train) [40][150/293] lr: 5.000000e-04 eta: 5:56:13 time: 0.497934 data_time: 0.075723 memory: 9871 loss_kpt: 0.000674 acc_pose: 0.796232 loss: 0.000674 2022/09/14 01:56:39 - mmengine - INFO - Epoch(train) [40][200/293] lr: 5.000000e-04 eta: 5:56:07 time: 0.499783 data_time: 0.076236 memory: 9871 loss_kpt: 0.000662 acc_pose: 0.778038 loss: 0.000662 2022/09/14 01:57:04 - mmengine - INFO - Epoch(train) [40][250/293] lr: 5.000000e-04 eta: 5:56:01 time: 0.502288 data_time: 0.071281 memory: 9871 loss_kpt: 0.000680 acc_pose: 0.794987 loss: 0.000680 2022/09/14 01:57:26 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 01:57:26 - mmengine - INFO - Saving checkpoint at 40 epochs 2022/09/14 01:57:36 - mmengine - INFO - Epoch(val) [40][50/407] eta: 0:00:50 time: 0.141223 data_time: 0.014129 memory: 9871 2022/09/14 01:57:43 - mmengine - INFO - Epoch(val) [40][100/407] eta: 0:00:41 time: 0.136351 data_time: 0.009180 memory: 920 2022/09/14 01:57:50 - mmengine - INFO - Epoch(val) [40][150/407] eta: 0:00:36 time: 0.140460 data_time: 0.011021 memory: 920 2022/09/14 01:57:57 - mmengine - INFO - Epoch(val) [40][200/407] eta: 0:00:28 time: 0.135419 data_time: 0.011046 memory: 920 2022/09/14 01:58:04 - mmengine - INFO - Epoch(val) [40][250/407] eta: 0:00:21 time: 0.140029 data_time: 0.009229 memory: 920 2022/09/14 01:58:11 - mmengine - INFO - Epoch(val) [40][300/407] eta: 0:00:14 time: 0.139537 data_time: 0.009013 memory: 920 2022/09/14 01:58:18 - mmengine - INFO - Epoch(val) [40][350/407] eta: 0:00:07 time: 0.133193 data_time: 0.008843 memory: 920 2022/09/14 01:58:24 - mmengine - INFO - Epoch(val) [40][400/407] eta: 0:00:00 time: 0.125277 data_time: 0.007718 memory: 920 2022/09/14 01:59:02 - mmengine - INFO - Evaluating CocoMetric... 2022/09/14 01:59:17 - mmengine - INFO - Epoch(val) [40][407/407] coco/AP: 0.718338 coco/AP .5: 0.893091 coco/AP .75: 0.786842 coco/AP (M): 0.680299 coco/AP (L): 0.789562 coco/AR: 0.773741 coco/AR .5: 0.933722 coco/AR .75: 0.837217 coco/AR (M): 0.728708 coco/AR (L): 0.838239 2022/09/14 01:59:17 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220914/udp_w32_256_v1/best_coco/AP_epoch_30.pth is removed 2022/09/14 01:59:20 - mmengine - INFO - The best checkpoint with 0.7183 coco/AP at 40 epoch is saved to best_coco/AP_epoch_40.pth. 2022/09/14 01:59:45 - mmengine - INFO - Epoch(train) [41][50/293] lr: 5.000000e-04 eta: 5:54:22 time: 0.513585 data_time: 0.085354 memory: 9871 loss_kpt: 0.000669 acc_pose: 0.768957 loss: 0.000669 2022/09/14 02:00:10 - mmengine - INFO - Epoch(train) [41][100/293] lr: 5.000000e-04 eta: 5:54:16 time: 0.502140 data_time: 0.078110 memory: 9871 loss_kpt: 0.000674 acc_pose: 0.796889 loss: 0.000674 2022/09/14 02:00:36 - mmengine - INFO - Epoch(train) [41][150/293] lr: 5.000000e-04 eta: 5:54:14 time: 0.518325 data_time: 0.078943 memory: 9871 loss_kpt: 0.000670 acc_pose: 0.778555 loss: 0.000670 2022/09/14 02:01:02 - mmengine - INFO - Epoch(train) [41][200/293] lr: 5.000000e-04 eta: 5:54:08 time: 0.505913 data_time: 0.080933 memory: 9871 loss_kpt: 0.000667 acc_pose: 0.789814 loss: 0.000667 2022/09/14 02:01:27 - mmengine - INFO - Epoch(train) [41][250/293] lr: 5.000000e-04 eta: 5:54:02 time: 0.499291 data_time: 0.073340 memory: 9871 loss_kpt: 0.000669 acc_pose: 0.739663 loss: 0.000669 2022/09/14 02:01:42 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 02:01:48 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 02:01:48 - mmengine - INFO - Saving checkpoint at 41 epochs 2022/09/14 02:02:16 - mmengine - INFO - Epoch(train) [42][50/293] lr: 5.000000e-04 eta: 5:52:22 time: 0.505273 data_time: 0.086153 memory: 9871 loss_kpt: 0.000657 acc_pose: 0.812865 loss: 0.000657 2022/09/14 02:02:42 - mmengine - INFO - Epoch(train) [42][100/293] lr: 5.000000e-04 eta: 5:52:17 time: 0.506307 data_time: 0.077339 memory: 9871 loss_kpt: 0.000680 acc_pose: 0.743832 loss: 0.000680 2022/09/14 02:03:07 - mmengine - INFO - Epoch(train) [42][150/293] lr: 5.000000e-04 eta: 5:52:13 time: 0.512688 data_time: 0.080139 memory: 9871 loss_kpt: 0.000670 acc_pose: 0.784352 loss: 0.000670 2022/09/14 02:03:32 - mmengine - INFO - Epoch(train) [42][200/293] lr: 5.000000e-04 eta: 5:52:04 time: 0.493205 data_time: 0.076737 memory: 9871 loss_kpt: 0.000673 acc_pose: 0.801437 loss: 0.000673 2022/09/14 02:03:57 - mmengine - INFO - Epoch(train) [42][250/293] lr: 5.000000e-04 eta: 5:51:55 time: 0.491143 data_time: 0.073823 memory: 9871 loss_kpt: 0.000655 acc_pose: 0.792548 loss: 0.000655 2022/09/14 02:04:18 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 02:04:18 - mmengine - INFO - Saving checkpoint at 42 epochs 2022/09/14 02:04:46 - mmengine - INFO - Epoch(train) [43][50/293] lr: 5.000000e-04 eta: 5:50:18 time: 0.507896 data_time: 0.082146 memory: 9871 loss_kpt: 0.000672 acc_pose: 0.814094 loss: 0.000672 2022/09/14 02:05:12 - mmengine - INFO - Epoch(train) [43][100/293] lr: 5.000000e-04 eta: 5:50:12 time: 0.504733 data_time: 0.080807 memory: 9871 loss_kpt: 0.000645 acc_pose: 0.851292 loss: 0.000645 2022/09/14 02:05:37 - mmengine - INFO - Epoch(train) [43][150/293] lr: 5.000000e-04 eta: 5:50:05 time: 0.500374 data_time: 0.076134 memory: 9871 loss_kpt: 0.000662 acc_pose: 0.802820 loss: 0.000662 2022/09/14 02:06:01 - mmengine - INFO - Epoch(train) [43][200/293] lr: 5.000000e-04 eta: 5:49:55 time: 0.485049 data_time: 0.071827 memory: 9871 loss_kpt: 0.000672 acc_pose: 0.786847 loss: 0.000672 2022/09/14 02:06:26 - mmengine - INFO - Epoch(train) [43][250/293] lr: 5.000000e-04 eta: 5:49:46 time: 0.494844 data_time: 0.070536 memory: 9871 loss_kpt: 0.000660 acc_pose: 0.796145 loss: 0.000660 2022/09/14 02:06:47 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 02:06:47 - mmengine - INFO - Saving checkpoint at 43 epochs 2022/09/14 02:07:17 - mmengine - INFO - Epoch(train) [44][50/293] lr: 5.000000e-04 eta: 5:48:14 time: 0.524155 data_time: 0.092504 memory: 9871 loss_kpt: 0.000662 acc_pose: 0.788148 loss: 0.000662 2022/09/14 02:07:42 - mmengine - INFO - Epoch(train) [44][100/293] lr: 5.000000e-04 eta: 5:48:06 time: 0.500605 data_time: 0.075803 memory: 9871 loss_kpt: 0.000666 acc_pose: 0.703801 loss: 0.000666 2022/09/14 02:08:07 - mmengine - INFO - Epoch(train) [44][150/293] lr: 5.000000e-04 eta: 5:48:01 time: 0.511843 data_time: 0.075381 memory: 9871 loss_kpt: 0.000661 acc_pose: 0.791148 loss: 0.000661 2022/09/14 02:08:32 - mmengine - INFO - Epoch(train) [44][200/293] lr: 5.000000e-04 eta: 5:47:53 time: 0.496865 data_time: 0.071273 memory: 9871 loss_kpt: 0.000668 acc_pose: 0.802853 loss: 0.000668 2022/09/14 02:08:57 - mmengine - INFO - Epoch(train) [44][250/293] lr: 5.000000e-04 eta: 5:47:45 time: 0.499590 data_time: 0.074409 memory: 9871 loss_kpt: 0.000651 acc_pose: 0.863306 loss: 0.000651 2022/09/14 02:09:18 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 02:09:19 - mmengine - INFO - Saving checkpoint at 44 epochs 2022/09/14 02:09:47 - mmengine - INFO - Epoch(train) [45][50/293] lr: 5.000000e-04 eta: 5:46:10 time: 0.506491 data_time: 0.083800 memory: 9871 loss_kpt: 0.000670 acc_pose: 0.804687 loss: 0.000670 2022/09/14 02:10:13 - mmengine - INFO - Epoch(train) [45][100/293] lr: 5.000000e-04 eta: 5:46:05 time: 0.512499 data_time: 0.073596 memory: 9871 loss_kpt: 0.000679 acc_pose: 0.752296 loss: 0.000679 2022/09/14 02:10:17 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 02:10:37 - mmengine - INFO - Epoch(train) [45][150/293] lr: 5.000000e-04 eta: 5:45:56 time: 0.494197 data_time: 0.074068 memory: 9871 loss_kpt: 0.000674 acc_pose: 0.793717 loss: 0.000674 2022/09/14 02:11:02 - mmengine - INFO - Epoch(train) [45][200/293] lr: 5.000000e-04 eta: 5:45:48 time: 0.502135 data_time: 0.074083 memory: 9871 loss_kpt: 0.000651 acc_pose: 0.825231 loss: 0.000651 2022/09/14 02:11:27 - mmengine - INFO - Epoch(train) [45][250/293] lr: 5.000000e-04 eta: 5:45:40 time: 0.499330 data_time: 0.078141 memory: 9871 loss_kpt: 0.000669 acc_pose: 0.809015 loss: 0.000669 2022/09/14 02:11:48 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 02:11:48 - mmengine - INFO - Saving checkpoint at 45 epochs 2022/09/14 02:12:17 - mmengine - INFO - Epoch(train) [46][50/293] lr: 5.000000e-04 eta: 5:44:08 time: 0.509856 data_time: 0.088664 memory: 9871 loss_kpt: 0.000654 acc_pose: 0.785548 loss: 0.000654 2022/09/14 02:12:42 - mmengine - INFO - Epoch(train) [46][100/293] lr: 5.000000e-04 eta: 5:44:00 time: 0.503612 data_time: 0.080876 memory: 9871 loss_kpt: 0.000650 acc_pose: 0.811170 loss: 0.000650 2022/09/14 02:13:07 - mmengine - INFO - Epoch(train) [46][150/293] lr: 5.000000e-04 eta: 5:43:52 time: 0.501114 data_time: 0.075286 memory: 9871 loss_kpt: 0.000659 acc_pose: 0.784448 loss: 0.000659 2022/09/14 02:13:32 - mmengine - INFO - Epoch(train) [46][200/293] lr: 5.000000e-04 eta: 5:43:44 time: 0.501024 data_time: 0.075066 memory: 9871 loss_kpt: 0.000681 acc_pose: 0.811880 loss: 0.000681 2022/09/14 02:13:57 - mmengine - INFO - Epoch(train) [46][250/293] lr: 5.000000e-04 eta: 5:43:35 time: 0.499146 data_time: 0.081539 memory: 9871 loss_kpt: 0.000653 acc_pose: 0.769484 loss: 0.000653 2022/09/14 02:14:19 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 02:14:19 - mmengine - INFO - Saving checkpoint at 46 epochs 2022/09/14 02:14:49 - mmengine - INFO - Epoch(train) [47][50/293] lr: 5.000000e-04 eta: 5:42:02 time: 0.500991 data_time: 0.077879 memory: 9871 loss_kpt: 0.000642 acc_pose: 0.792555 loss: 0.000642 2022/09/14 02:15:13 - mmengine - INFO - Epoch(train) [47][100/293] lr: 5.000000e-04 eta: 5:41:52 time: 0.487413 data_time: 0.077496 memory: 9871 loss_kpt: 0.000644 acc_pose: 0.804271 loss: 0.000644 2022/09/14 02:15:38 - mmengine - INFO - Epoch(train) [47][150/293] lr: 5.000000e-04 eta: 5:41:42 time: 0.497122 data_time: 0.078817 memory: 9871 loss_kpt: 0.000647 acc_pose: 0.831446 loss: 0.000647 2022/09/14 02:16:03 - mmengine - INFO - Epoch(train) [47][200/293] lr: 5.000000e-04 eta: 5:41:34 time: 0.501443 data_time: 0.076667 memory: 9871 loss_kpt: 0.000653 acc_pose: 0.836987 loss: 0.000653 2022/09/14 02:16:29 - mmengine - INFO - Epoch(train) [47][250/293] lr: 5.000000e-04 eta: 5:41:26 time: 0.505486 data_time: 0.076552 memory: 9871 loss_kpt: 0.000664 acc_pose: 0.766407 loss: 0.000664 2022/09/14 02:16:50 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 02:16:50 - mmengine - INFO - Saving checkpoint at 47 epochs 2022/09/14 02:17:18 - mmengine - INFO - Epoch(train) [48][50/293] lr: 5.000000e-04 eta: 5:39:55 time: 0.504792 data_time: 0.081973 memory: 9871 loss_kpt: 0.000654 acc_pose: 0.816470 loss: 0.000654 2022/09/14 02:17:43 - mmengine - INFO - Epoch(train) [48][100/293] lr: 5.000000e-04 eta: 5:39:47 time: 0.500752 data_time: 0.074171 memory: 9871 loss_kpt: 0.000659 acc_pose: 0.757665 loss: 0.000659 2022/09/14 02:18:08 - mmengine - INFO - Epoch(train) [48][150/293] lr: 5.000000e-04 eta: 5:39:37 time: 0.494191 data_time: 0.071259 memory: 9871 loss_kpt: 0.000663 acc_pose: 0.761263 loss: 0.000663 2022/09/14 02:18:33 - mmengine - INFO - Epoch(train) [48][200/293] lr: 5.000000e-04 eta: 5:39:27 time: 0.499031 data_time: 0.085479 memory: 9871 loss_kpt: 0.000640 acc_pose: 0.836095 loss: 0.000640 2022/09/14 02:18:47 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 02:18:57 - mmengine - INFO - Epoch(train) [48][250/293] lr: 5.000000e-04 eta: 5:39:17 time: 0.494885 data_time: 0.074520 memory: 9871 loss_kpt: 0.000663 acc_pose: 0.836262 loss: 0.000663 2022/09/14 02:19:19 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 02:19:19 - mmengine - INFO - Saving checkpoint at 48 epochs 2022/09/14 02:19:48 - mmengine - INFO - Epoch(train) [49][50/293] lr: 5.000000e-04 eta: 5:37:52 time: 0.529365 data_time: 0.084635 memory: 9871 loss_kpt: 0.000649 acc_pose: 0.805312 loss: 0.000649 2022/09/14 02:20:13 - mmengine - INFO - Epoch(train) [49][100/293] lr: 5.000000e-04 eta: 5:37:42 time: 0.490200 data_time: 0.073377 memory: 9871 loss_kpt: 0.000662 acc_pose: 0.763337 loss: 0.000662 2022/09/14 02:20:38 - mmengine - INFO - Epoch(train) [49][150/293] lr: 5.000000e-04 eta: 5:37:35 time: 0.514225 data_time: 0.083534 memory: 9871 loss_kpt: 0.000645 acc_pose: 0.810901 loss: 0.000645 2022/09/14 02:21:04 - mmengine - INFO - Epoch(train) [49][200/293] lr: 5.000000e-04 eta: 5:37:26 time: 0.506708 data_time: 0.076102 memory: 9871 loss_kpt: 0.000646 acc_pose: 0.784889 loss: 0.000646 2022/09/14 02:21:29 - mmengine - INFO - Epoch(train) [49][250/293] lr: 5.000000e-04 eta: 5:37:16 time: 0.498776 data_time: 0.072059 memory: 9871 loss_kpt: 0.000663 acc_pose: 0.809700 loss: 0.000663 2022/09/14 02:21:50 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 02:21:50 - mmengine - INFO - Saving checkpoint at 49 epochs 2022/09/14 02:22:18 - mmengine - INFO - Epoch(train) [50][50/293] lr: 5.000000e-04 eta: 5:35:50 time: 0.515734 data_time: 0.088652 memory: 9871 loss_kpt: 0.000674 acc_pose: 0.833457 loss: 0.000674 2022/09/14 02:22:43 - mmengine - INFO - Epoch(train) [50][100/293] lr: 5.000000e-04 eta: 5:35:40 time: 0.494365 data_time: 0.071597 memory: 9871 loss_kpt: 0.000654 acc_pose: 0.791591 loss: 0.000654 2022/09/14 02:23:08 - mmengine - INFO - Epoch(train) [50][150/293] lr: 5.000000e-04 eta: 5:35:30 time: 0.497308 data_time: 0.076324 memory: 9871 loss_kpt: 0.000632 acc_pose: 0.836850 loss: 0.000632 2022/09/14 02:23:33 - mmengine - INFO - Epoch(train) [50][200/293] lr: 5.000000e-04 eta: 5:35:20 time: 0.498943 data_time: 0.076774 memory: 9871 loss_kpt: 0.000650 acc_pose: 0.772162 loss: 0.000650 2022/09/14 02:23:58 - mmengine - INFO - Epoch(train) [50][250/293] lr: 5.000000e-04 eta: 5:35:10 time: 0.500661 data_time: 0.076613 memory: 9871 loss_kpt: 0.000663 acc_pose: 0.819152 loss: 0.000663 2022/09/14 02:24:20 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 02:24:20 - mmengine - INFO - Saving checkpoint at 50 epochs 2022/09/14 02:24:30 - mmengine - INFO - Epoch(val) [50][50/407] eta: 0:00:50 time: 0.141339 data_time: 0.013629 memory: 9871 2022/09/14 02:24:37 - mmengine - INFO - Epoch(val) [50][100/407] eta: 0:00:40 time: 0.132452 data_time: 0.008688 memory: 920 2022/09/14 02:24:43 - mmengine - INFO - Epoch(val) [50][150/407] eta: 0:00:35 time: 0.136594 data_time: 0.012636 memory: 920 2022/09/14 02:24:50 - mmengine - INFO - Epoch(val) [50][200/407] eta: 0:00:27 time: 0.132317 data_time: 0.009020 memory: 920 2022/09/14 02:24:57 - mmengine - INFO - Epoch(val) [50][250/407] eta: 0:00:20 time: 0.130402 data_time: 0.008299 memory: 920 2022/09/14 02:25:03 - mmengine - INFO - Epoch(val) [50][300/407] eta: 0:00:14 time: 0.134634 data_time: 0.011415 memory: 920 2022/09/14 02:25:10 - mmengine - INFO - Epoch(val) [50][350/407] eta: 0:00:07 time: 0.129109 data_time: 0.008036 memory: 920 2022/09/14 02:25:16 - mmengine - INFO - Epoch(val) [50][400/407] eta: 0:00:00 time: 0.127654 data_time: 0.008209 memory: 920 2022/09/14 02:25:53 - mmengine - INFO - Evaluating CocoMetric... 2022/09/14 02:26:08 - mmengine - INFO - Epoch(val) [50][407/407] coco/AP: 0.721450 coco/AP .5: 0.887997 coco/AP .75: 0.791570 coco/AP (M): 0.683860 coco/AP (L): 0.791022 coco/AR: 0.777015 coco/AR .5: 0.928684 coco/AR .75: 0.839578 coco/AR (M): 0.732122 coco/AR (L): 0.841880 2022/09/14 02:26:08 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220914/udp_w32_256_v1/best_coco/AP_epoch_40.pth is removed 2022/09/14 02:26:10 - mmengine - INFO - The best checkpoint with 0.7214 coco/AP at 50 epoch is saved to best_coco/AP_epoch_50.pth. 2022/09/14 02:26:35 - mmengine - INFO - Epoch(train) [51][50/293] lr: 5.000000e-04 eta: 5:33:43 time: 0.503452 data_time: 0.077621 memory: 9871 loss_kpt: 0.000652 acc_pose: 0.837029 loss: 0.000652 2022/09/14 02:27:00 - mmengine - INFO - Epoch(train) [51][100/293] lr: 5.000000e-04 eta: 5:33:33 time: 0.499274 data_time: 0.075765 memory: 9871 loss_kpt: 0.000662 acc_pose: 0.796738 loss: 0.000662 2022/09/14 02:27:25 - mmengine - INFO - Epoch(train) [51][150/293] lr: 5.000000e-04 eta: 5:33:24 time: 0.501300 data_time: 0.076896 memory: 9871 loss_kpt: 0.000666 acc_pose: 0.784191 loss: 0.000666 2022/09/14 02:27:51 - mmengine - INFO - Epoch(train) [51][200/293] lr: 5.000000e-04 eta: 5:33:14 time: 0.504322 data_time: 0.081299 memory: 9871 loss_kpt: 0.000640 acc_pose: 0.823088 loss: 0.000640 2022/09/14 02:28:16 - mmengine - INFO - Epoch(train) [51][250/293] lr: 5.000000e-04 eta: 5:33:04 time: 0.500495 data_time: 0.076317 memory: 9871 loss_kpt: 0.000659 acc_pose: 0.816865 loss: 0.000659 2022/09/14 02:28:37 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 02:28:37 - mmengine - INFO - Saving checkpoint at 51 epochs 2022/09/14 02:29:07 - mmengine - INFO - Epoch(train) [52][50/293] lr: 5.000000e-04 eta: 5:31:38 time: 0.500902 data_time: 0.082806 memory: 9871 loss_kpt: 0.000661 acc_pose: 0.814514 loss: 0.000661 2022/09/14 02:29:11 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 02:29:33 - mmengine - INFO - Epoch(train) [52][100/293] lr: 5.000000e-04 eta: 5:31:30 time: 0.509960 data_time: 0.090100 memory: 9871 loss_kpt: 0.000645 acc_pose: 0.846669 loss: 0.000645 2022/09/14 02:29:57 - mmengine - INFO - Epoch(train) [52][150/293] lr: 5.000000e-04 eta: 5:31:18 time: 0.494944 data_time: 0.076173 memory: 9871 loss_kpt: 0.000662 acc_pose: 0.824041 loss: 0.000662 2022/09/14 02:30:22 - mmengine - INFO - Epoch(train) [52][200/293] lr: 5.000000e-04 eta: 5:31:07 time: 0.491635 data_time: 0.078804 memory: 9871 loss_kpt: 0.000657 acc_pose: 0.836870 loss: 0.000657 2022/09/14 02:30:47 - mmengine - INFO - Epoch(train) [52][250/293] lr: 5.000000e-04 eta: 5:30:55 time: 0.492003 data_time: 0.075231 memory: 9871 loss_kpt: 0.000643 acc_pose: 0.796624 loss: 0.000643 2022/09/14 02:31:08 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 02:31:08 - mmengine - INFO - Saving checkpoint at 52 epochs 2022/09/14 02:31:36 - mmengine - INFO - Epoch(train) [53][50/293] lr: 5.000000e-04 eta: 5:29:31 time: 0.506589 data_time: 0.082328 memory: 9871 loss_kpt: 0.000644 acc_pose: 0.815033 loss: 0.000644 2022/09/14 02:32:01 - mmengine - INFO - Epoch(train) [53][100/293] lr: 5.000000e-04 eta: 5:29:21 time: 0.502505 data_time: 0.079878 memory: 9871 loss_kpt: 0.000649 acc_pose: 0.798257 loss: 0.000649 2022/09/14 02:32:26 - mmengine - INFO - Epoch(train) [53][150/293] lr: 5.000000e-04 eta: 5:29:11 time: 0.499121 data_time: 0.074788 memory: 9871 loss_kpt: 0.000654 acc_pose: 0.800330 loss: 0.000654 2022/09/14 02:32:52 - mmengine - INFO - Epoch(train) [53][200/293] lr: 5.000000e-04 eta: 5:29:00 time: 0.503592 data_time: 0.079195 memory: 9871 loss_kpt: 0.000650 acc_pose: 0.789733 loss: 0.000650 2022/09/14 02:33:16 - mmengine - INFO - Epoch(train) [53][250/293] lr: 5.000000e-04 eta: 5:28:49 time: 0.496513 data_time: 0.078522 memory: 9871 loss_kpt: 0.000657 acc_pose: 0.777929 loss: 0.000657 2022/09/14 02:33:37 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 02:33:37 - mmengine - INFO - Saving checkpoint at 53 epochs 2022/09/14 02:34:06 - mmengine - INFO - Epoch(train) [54][50/293] lr: 5.000000e-04 eta: 5:27:28 time: 0.514006 data_time: 0.088584 memory: 9871 loss_kpt: 0.000657 acc_pose: 0.823131 loss: 0.000657 2022/09/14 02:34:31 - mmengine - INFO - Epoch(train) [54][100/293] lr: 5.000000e-04 eta: 5:27:17 time: 0.497993 data_time: 0.075613 memory: 9871 loss_kpt: 0.000645 acc_pose: 0.846243 loss: 0.000645 2022/09/14 02:34:56 - mmengine - INFO - Epoch(train) [54][150/293] lr: 5.000000e-04 eta: 5:27:05 time: 0.498694 data_time: 0.074151 memory: 9871 loss_kpt: 0.000633 acc_pose: 0.765477 loss: 0.000633 2022/09/14 02:35:21 - mmengine - INFO - Epoch(train) [54][200/293] lr: 5.000000e-04 eta: 5:26:55 time: 0.500271 data_time: 0.084218 memory: 9871 loss_kpt: 0.000654 acc_pose: 0.811786 loss: 0.000654 2022/09/14 02:35:46 - mmengine - INFO - Epoch(train) [54][250/293] lr: 5.000000e-04 eta: 5:26:44 time: 0.502445 data_time: 0.078342 memory: 9871 loss_kpt: 0.000642 acc_pose: 0.847761 loss: 0.000642 2022/09/14 02:36:07 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 02:36:07 - mmengine - INFO - Saving checkpoint at 54 epochs 2022/09/14 02:36:37 - mmengine - INFO - Epoch(train) [55][50/293] lr: 5.000000e-04 eta: 5:25:25 time: 0.524235 data_time: 0.091086 memory: 9871 loss_kpt: 0.000649 acc_pose: 0.784911 loss: 0.000649 2022/09/14 02:37:02 - mmengine - INFO - Epoch(train) [55][100/293] lr: 5.000000e-04 eta: 5:25:15 time: 0.507694 data_time: 0.069069 memory: 9871 loss_kpt: 0.000646 acc_pose: 0.798159 loss: 0.000646 2022/09/14 02:37:27 - mmengine - INFO - Epoch(train) [55][150/293] lr: 5.000000e-04 eta: 5:25:04 time: 0.497775 data_time: 0.072782 memory: 9871 loss_kpt: 0.000636 acc_pose: 0.834359 loss: 0.000636 2022/09/14 02:37:41 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 02:37:52 - mmengine - INFO - Epoch(train) [55][200/293] lr: 5.000000e-04 eta: 5:24:51 time: 0.493292 data_time: 0.072600 memory: 9871 loss_kpt: 0.000658 acc_pose: 0.831083 loss: 0.000658 2022/09/14 02:38:17 - mmengine - INFO - Epoch(train) [55][250/293] lr: 5.000000e-04 eta: 5:24:39 time: 0.494320 data_time: 0.077946 memory: 9871 loss_kpt: 0.000651 acc_pose: 0.833570 loss: 0.000651 2022/09/14 02:38:38 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 02:38:38 - mmengine - INFO - Saving checkpoint at 55 epochs 2022/09/14 02:39:07 - mmengine - INFO - Epoch(train) [56][50/293] lr: 5.000000e-04 eta: 5:23:19 time: 0.511788 data_time: 0.082724 memory: 9871 loss_kpt: 0.000636 acc_pose: 0.761589 loss: 0.000636 2022/09/14 02:39:32 - mmengine - INFO - Epoch(train) [56][100/293] lr: 5.000000e-04 eta: 5:23:08 time: 0.496212 data_time: 0.078219 memory: 9871 loss_kpt: 0.000643 acc_pose: 0.810059 loss: 0.000643 2022/09/14 02:39:57 - mmengine - INFO - Epoch(train) [56][150/293] lr: 5.000000e-04 eta: 5:22:56 time: 0.500110 data_time: 0.072677 memory: 9871 loss_kpt: 0.000655 acc_pose: 0.811379 loss: 0.000655 2022/09/14 02:40:21 - mmengine - INFO - Epoch(train) [56][200/293] lr: 5.000000e-04 eta: 5:22:44 time: 0.490995 data_time: 0.078631 memory: 9871 loss_kpt: 0.000652 acc_pose: 0.812243 loss: 0.000652 2022/09/14 02:40:46 - mmengine - INFO - Epoch(train) [56][250/293] lr: 5.000000e-04 eta: 5:22:31 time: 0.494650 data_time: 0.072967 memory: 9871 loss_kpt: 0.000646 acc_pose: 0.781999 loss: 0.000646 2022/09/14 02:41:08 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 02:41:08 - mmengine - INFO - Saving checkpoint at 56 epochs 2022/09/14 02:41:36 - mmengine - INFO - Epoch(train) [57][50/293] lr: 5.000000e-04 eta: 5:21:11 time: 0.498620 data_time: 0.084413 memory: 9871 loss_kpt: 0.000637 acc_pose: 0.840451 loss: 0.000637 2022/09/14 02:42:01 - mmengine - INFO - Epoch(train) [57][100/293] lr: 5.000000e-04 eta: 5:20:59 time: 0.502699 data_time: 0.074039 memory: 9871 loss_kpt: 0.000642 acc_pose: 0.838168 loss: 0.000642 2022/09/14 02:42:26 - mmengine - INFO - Epoch(train) [57][150/293] lr: 5.000000e-04 eta: 5:20:49 time: 0.509052 data_time: 0.080954 memory: 9871 loss_kpt: 0.000632 acc_pose: 0.784345 loss: 0.000632 2022/09/14 02:42:51 - mmengine - INFO - Epoch(train) [57][200/293] lr: 5.000000e-04 eta: 5:20:37 time: 0.493169 data_time: 0.076580 memory: 9871 loss_kpt: 0.000637 acc_pose: 0.805568 loss: 0.000637 2022/09/14 02:43:16 - mmengine - INFO - Epoch(train) [57][250/293] lr: 5.000000e-04 eta: 5:20:24 time: 0.492059 data_time: 0.080034 memory: 9871 loss_kpt: 0.000646 acc_pose: 0.783265 loss: 0.000646 2022/09/14 02:43:37 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 02:43:37 - mmengine - INFO - Saving checkpoint at 57 epochs 2022/09/14 02:44:08 - mmengine - INFO - Epoch(train) [58][50/293] lr: 5.000000e-04 eta: 5:19:12 time: 0.555489 data_time: 0.105279 memory: 9871 loss_kpt: 0.000635 acc_pose: 0.788217 loss: 0.000635 2022/09/14 02:44:33 - mmengine - INFO - Epoch(train) [58][100/293] lr: 5.000000e-04 eta: 5:19:01 time: 0.508519 data_time: 0.079872 memory: 9871 loss_kpt: 0.000645 acc_pose: 0.796430 loss: 0.000645 2022/09/14 02:44:58 - mmengine - INFO - Epoch(train) [58][150/293] lr: 5.000000e-04 eta: 5:18:48 time: 0.494021 data_time: 0.072187 memory: 9871 loss_kpt: 0.000655 acc_pose: 0.812588 loss: 0.000655 2022/09/14 02:45:22 - mmengine - INFO - Epoch(train) [58][200/293] lr: 5.000000e-04 eta: 5:18:35 time: 0.486544 data_time: 0.076145 memory: 9871 loss_kpt: 0.000662 acc_pose: 0.827029 loss: 0.000662 2022/09/14 02:45:47 - mmengine - INFO - Epoch(train) [58][250/293] lr: 5.000000e-04 eta: 5:18:22 time: 0.495991 data_time: 0.081815 memory: 9871 loss_kpt: 0.000643 acc_pose: 0.848693 loss: 0.000643 2022/09/14 02:46:08 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 02:46:08 - mmengine - INFO - Saving checkpoint at 58 epochs 2022/09/14 02:46:15 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 02:46:37 - mmengine - INFO - Epoch(train) [59][50/293] lr: 5.000000e-04 eta: 5:17:05 time: 0.510029 data_time: 0.083895 memory: 9871 loss_kpt: 0.000646 acc_pose: 0.785916 loss: 0.000646 2022/09/14 02:47:02 - mmengine - INFO - Epoch(train) [59][100/293] lr: 5.000000e-04 eta: 5:16:53 time: 0.503919 data_time: 0.077020 memory: 9871 loss_kpt: 0.000633 acc_pose: 0.796115 loss: 0.000633 2022/09/14 02:47:26 - mmengine - INFO - Epoch(train) [59][150/293] lr: 5.000000e-04 eta: 5:16:39 time: 0.483020 data_time: 0.079354 memory: 9871 loss_kpt: 0.000641 acc_pose: 0.819477 loss: 0.000641 2022/09/14 02:47:51 - mmengine - INFO - Epoch(train) [59][200/293] lr: 5.000000e-04 eta: 5:16:26 time: 0.491759 data_time: 0.082123 memory: 9871 loss_kpt: 0.000645 acc_pose: 0.823354 loss: 0.000645 2022/09/14 02:48:16 - mmengine - INFO - Epoch(train) [59][250/293] lr: 5.000000e-04 eta: 5:16:13 time: 0.497988 data_time: 0.077220 memory: 9871 loss_kpt: 0.000636 acc_pose: 0.787475 loss: 0.000636 2022/09/14 02:48:37 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 02:48:37 - mmengine - INFO - Saving checkpoint at 59 epochs 2022/09/14 02:49:07 - mmengine - INFO - Epoch(train) [60][50/293] lr: 5.000000e-04 eta: 5:14:59 time: 0.527116 data_time: 0.090785 memory: 9871 loss_kpt: 0.000615 acc_pose: 0.826694 loss: 0.000615 2022/09/14 02:49:32 - mmengine - INFO - Epoch(train) [60][100/293] lr: 5.000000e-04 eta: 5:14:47 time: 0.498480 data_time: 0.075307 memory: 9871 loss_kpt: 0.000631 acc_pose: 0.846594 loss: 0.000631 2022/09/14 02:49:56 - mmengine - INFO - Epoch(train) [60][150/293] lr: 5.000000e-04 eta: 5:14:33 time: 0.488062 data_time: 0.076910 memory: 9871 loss_kpt: 0.000633 acc_pose: 0.789963 loss: 0.000633 2022/09/14 02:50:22 - mmengine - INFO - Epoch(train) [60][200/293] lr: 5.000000e-04 eta: 5:14:21 time: 0.502174 data_time: 0.073144 memory: 9871 loss_kpt: 0.000630 acc_pose: 0.834284 loss: 0.000630 2022/09/14 02:50:47 - mmengine - INFO - Epoch(train) [60][250/293] lr: 5.000000e-04 eta: 5:14:09 time: 0.506170 data_time: 0.078146 memory: 9871 loss_kpt: 0.000639 acc_pose: 0.827758 loss: 0.000639 2022/09/14 02:51:09 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 02:51:09 - mmengine - INFO - Saving checkpoint at 60 epochs 2022/09/14 02:51:19 - mmengine - INFO - Epoch(val) [60][50/407] eta: 0:00:48 time: 0.136594 data_time: 0.013080 memory: 9871 2022/09/14 02:51:25 - mmengine - INFO - Epoch(val) [60][100/407] eta: 0:00:40 time: 0.131608 data_time: 0.009537 memory: 920 2022/09/14 02:51:32 - mmengine - INFO - Epoch(val) [60][150/407] eta: 0:00:33 time: 0.130930 data_time: 0.008915 memory: 920 2022/09/14 02:51:38 - mmengine - INFO - Epoch(val) [60][200/407] eta: 0:00:26 time: 0.127782 data_time: 0.008207 memory: 920 2022/09/14 02:51:45 - mmengine - INFO - Epoch(val) [60][250/407] eta: 0:00:21 time: 0.134260 data_time: 0.011577 memory: 920 2022/09/14 02:51:51 - mmengine - INFO - Epoch(val) [60][300/407] eta: 0:00:14 time: 0.132083 data_time: 0.010515 memory: 920 2022/09/14 02:51:58 - mmengine - INFO - Epoch(val) [60][350/407] eta: 0:00:07 time: 0.131099 data_time: 0.009158 memory: 920 2022/09/14 02:52:04 - mmengine - INFO - Epoch(val) [60][400/407] eta: 0:00:00 time: 0.128268 data_time: 0.008089 memory: 920 2022/09/14 02:52:41 - mmengine - INFO - Evaluating CocoMetric... 2022/09/14 02:52:55 - mmengine - INFO - Epoch(val) [60][407/407] coco/AP: 0.726006 coco/AP .5: 0.892767 coco/AP .75: 0.794690 coco/AP (M): 0.688419 coco/AP (L): 0.795156 coco/AR: 0.779440 coco/AR .5: 0.931203 coco/AR .75: 0.841625 coco/AR (M): 0.735810 coco/AR (L): 0.841620 2022/09/14 02:52:55 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220914/udp_w32_256_v1/best_coco/AP_epoch_50.pth is removed 2022/09/14 02:52:58 - mmengine - INFO - The best checkpoint with 0.7260 coco/AP at 60 epoch is saved to best_coco/AP_epoch_60.pth. 2022/09/14 02:53:23 - mmengine - INFO - Epoch(train) [61][50/293] lr: 5.000000e-04 eta: 5:12:53 time: 0.501491 data_time: 0.083342 memory: 9871 loss_kpt: 0.000646 acc_pose: 0.802350 loss: 0.000646 2022/09/14 02:53:48 - mmengine - INFO - Epoch(train) [61][100/293] lr: 5.000000e-04 eta: 5:12:41 time: 0.508193 data_time: 0.077860 memory: 9871 loss_kpt: 0.000625 acc_pose: 0.831788 loss: 0.000625 2022/09/14 02:54:13 - mmengine - INFO - Epoch(train) [61][150/293] lr: 5.000000e-04 eta: 5:12:28 time: 0.490655 data_time: 0.074815 memory: 9871 loss_kpt: 0.000639 acc_pose: 0.858584 loss: 0.000639 2022/09/14 02:54:37 - mmengine - INFO - Epoch(train) [61][200/293] lr: 5.000000e-04 eta: 5:12:15 time: 0.495478 data_time: 0.070906 memory: 9871 loss_kpt: 0.000637 acc_pose: 0.806767 loss: 0.000637 2022/09/14 02:55:03 - mmengine - INFO - Epoch(train) [61][250/293] lr: 5.000000e-04 eta: 5:12:02 time: 0.502671 data_time: 0.075436 memory: 9871 loss_kpt: 0.000631 acc_pose: 0.829736 loss: 0.000631 2022/09/14 02:55:24 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 02:55:24 - mmengine - INFO - Saving checkpoint at 61 epochs 2022/09/14 02:55:54 - mmengine - INFO - Epoch(train) [62][50/293] lr: 5.000000e-04 eta: 5:10:48 time: 0.510463 data_time: 0.082380 memory: 9871 loss_kpt: 0.000634 acc_pose: 0.818424 loss: 0.000634 2022/09/14 02:56:19 - mmengine - INFO - Epoch(train) [62][100/293] lr: 5.000000e-04 eta: 5:10:34 time: 0.489702 data_time: 0.073323 memory: 9871 loss_kpt: 0.000625 acc_pose: 0.825347 loss: 0.000625 2022/09/14 02:56:32 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 02:56:44 - mmengine - INFO - Epoch(train) [62][150/293] lr: 5.000000e-04 eta: 5:10:21 time: 0.498869 data_time: 0.074072 memory: 9871 loss_kpt: 0.000630 acc_pose: 0.830785 loss: 0.000630 2022/09/14 02:57:09 - mmengine - INFO - Epoch(train) [62][200/293] lr: 5.000000e-04 eta: 5:10:08 time: 0.498763 data_time: 0.074227 memory: 9871 loss_kpt: 0.000640 acc_pose: 0.810520 loss: 0.000640 2022/09/14 02:57:34 - mmengine - INFO - Epoch(train) [62][250/293] lr: 5.000000e-04 eta: 5:09:56 time: 0.502672 data_time: 0.074230 memory: 9871 loss_kpt: 0.000625 acc_pose: 0.818788 loss: 0.000625 2022/09/14 02:57:55 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 02:57:55 - mmengine - INFO - Saving checkpoint at 62 epochs 2022/09/14 02:58:23 - mmengine - INFO - Epoch(train) [63][50/293] lr: 5.000000e-04 eta: 5:08:42 time: 0.509264 data_time: 0.078934 memory: 9871 loss_kpt: 0.000645 acc_pose: 0.753411 loss: 0.000645 2022/09/14 02:58:48 - mmengine - INFO - Epoch(train) [63][100/293] lr: 5.000000e-04 eta: 5:08:27 time: 0.488441 data_time: 0.074033 memory: 9871 loss_kpt: 0.000636 acc_pose: 0.781319 loss: 0.000636 2022/09/14 02:59:13 - mmengine - INFO - Epoch(train) [63][150/293] lr: 5.000000e-04 eta: 5:08:16 time: 0.510885 data_time: 0.079978 memory: 9871 loss_kpt: 0.000645 acc_pose: 0.808900 loss: 0.000645 2022/09/14 02:59:38 - mmengine - INFO - Epoch(train) [63][200/293] lr: 5.000000e-04 eta: 5:08:03 time: 0.501182 data_time: 0.082227 memory: 9871 loss_kpt: 0.000626 acc_pose: 0.796124 loss: 0.000626 2022/09/14 03:00:03 - mmengine - INFO - Epoch(train) [63][250/293] lr: 5.000000e-04 eta: 5:07:49 time: 0.491226 data_time: 0.075558 memory: 9871 loss_kpt: 0.000630 acc_pose: 0.761852 loss: 0.000630 2022/09/14 03:00:24 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 03:00:25 - mmengine - INFO - Saving checkpoint at 63 epochs 2022/09/14 03:00:53 - mmengine - INFO - Epoch(train) [64][50/293] lr: 5.000000e-04 eta: 5:06:36 time: 0.509722 data_time: 0.086836 memory: 9871 loss_kpt: 0.000636 acc_pose: 0.798395 loss: 0.000636 2022/09/14 03:01:18 - mmengine - INFO - Epoch(train) [64][100/293] lr: 5.000000e-04 eta: 5:06:22 time: 0.494058 data_time: 0.075420 memory: 9871 loss_kpt: 0.000640 acc_pose: 0.819518 loss: 0.000640 2022/09/14 03:01:43 - mmengine - INFO - Epoch(train) [64][150/293] lr: 5.000000e-04 eta: 5:06:09 time: 0.499828 data_time: 0.078371 memory: 9871 loss_kpt: 0.000633 acc_pose: 0.836954 loss: 0.000633 2022/09/14 03:02:08 - mmengine - INFO - Epoch(train) [64][200/293] lr: 5.000000e-04 eta: 5:05:56 time: 0.497440 data_time: 0.075644 memory: 9871 loss_kpt: 0.000635 acc_pose: 0.843540 loss: 0.000635 2022/09/14 03:02:33 - mmengine - INFO - Epoch(train) [64][250/293] lr: 5.000000e-04 eta: 5:05:42 time: 0.497282 data_time: 0.075845 memory: 9871 loss_kpt: 0.000633 acc_pose: 0.825097 loss: 0.000633 2022/09/14 03:02:54 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 03:02:54 - mmengine - INFO - Saving checkpoint at 64 epochs 2022/09/14 03:03:23 - mmengine - INFO - Epoch(train) [65][50/293] lr: 5.000000e-04 eta: 5:04:30 time: 0.515640 data_time: 0.083342 memory: 9871 loss_kpt: 0.000637 acc_pose: 0.798948 loss: 0.000637 2022/09/14 03:03:48 - mmengine - INFO - Epoch(train) [65][100/293] lr: 5.000000e-04 eta: 5:04:16 time: 0.490180 data_time: 0.076602 memory: 9871 loss_kpt: 0.000615 acc_pose: 0.835017 loss: 0.000615 2022/09/14 03:04:13 - mmengine - INFO - Epoch(train) [65][150/293] lr: 5.000000e-04 eta: 5:04:03 time: 0.500084 data_time: 0.075865 memory: 9871 loss_kpt: 0.000633 acc_pose: 0.775088 loss: 0.000633 2022/09/14 03:04:38 - mmengine - INFO - Epoch(train) [65][200/293] lr: 5.000000e-04 eta: 5:03:50 time: 0.501961 data_time: 0.074137 memory: 9871 loss_kpt: 0.000632 acc_pose: 0.794695 loss: 0.000632 2022/09/14 03:05:02 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 03:05:03 - mmengine - INFO - Epoch(train) [65][250/293] lr: 5.000000e-04 eta: 5:03:36 time: 0.501215 data_time: 0.075746 memory: 9871 loss_kpt: 0.000636 acc_pose: 0.872569 loss: 0.000636 2022/09/14 03:05:25 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 03:05:25 - mmengine - INFO - Saving checkpoint at 65 epochs 2022/09/14 03:05:53 - mmengine - INFO - Epoch(train) [66][50/293] lr: 5.000000e-04 eta: 5:02:24 time: 0.505544 data_time: 0.086854 memory: 9871 loss_kpt: 0.000631 acc_pose: 0.823222 loss: 0.000631 2022/09/14 03:06:18 - mmengine - INFO - Epoch(train) [66][100/293] lr: 5.000000e-04 eta: 5:02:11 time: 0.501886 data_time: 0.070057 memory: 9871 loss_kpt: 0.000637 acc_pose: 0.762227 loss: 0.000637 2022/09/14 03:06:43 - mmengine - INFO - Epoch(train) [66][150/293] lr: 5.000000e-04 eta: 5:01:57 time: 0.497831 data_time: 0.076848 memory: 9871 loss_kpt: 0.000627 acc_pose: 0.799376 loss: 0.000627 2022/09/14 03:07:08 - mmengine - INFO - Epoch(train) [66][200/293] lr: 5.000000e-04 eta: 5:01:44 time: 0.500043 data_time: 0.076741 memory: 9871 loss_kpt: 0.000635 acc_pose: 0.769495 loss: 0.000635 2022/09/14 03:07:34 - mmengine - INFO - Epoch(train) [66][250/293] lr: 5.000000e-04 eta: 5:01:31 time: 0.509469 data_time: 0.076364 memory: 9871 loss_kpt: 0.000615 acc_pose: 0.806449 loss: 0.000615 2022/09/14 03:07:55 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 03:07:55 - mmengine - INFO - Saving checkpoint at 66 epochs 2022/09/14 03:08:24 - mmengine - INFO - Epoch(train) [67][50/293] lr: 5.000000e-04 eta: 5:00:20 time: 0.506218 data_time: 0.083639 memory: 9871 loss_kpt: 0.000628 acc_pose: 0.797496 loss: 0.000628 2022/09/14 03:08:49 - mmengine - INFO - Epoch(train) [67][100/293] lr: 5.000000e-04 eta: 5:00:07 time: 0.502983 data_time: 0.080279 memory: 9871 loss_kpt: 0.000630 acc_pose: 0.820513 loss: 0.000630 2022/09/14 03:09:13 - mmengine - INFO - Epoch(train) [67][150/293] lr: 5.000000e-04 eta: 4:59:52 time: 0.492055 data_time: 0.071101 memory: 9871 loss_kpt: 0.000627 acc_pose: 0.849261 loss: 0.000627 2022/09/14 03:09:38 - mmengine - INFO - Epoch(train) [67][200/293] lr: 5.000000e-04 eta: 4:59:39 time: 0.500401 data_time: 0.073954 memory: 9871 loss_kpt: 0.000632 acc_pose: 0.833487 loss: 0.000632 2022/09/14 03:10:03 - mmengine - INFO - Epoch(train) [67][250/293] lr: 5.000000e-04 eta: 4:59:24 time: 0.490480 data_time: 0.075708 memory: 9871 loss_kpt: 0.000638 acc_pose: 0.768486 loss: 0.000638 2022/09/14 03:10:24 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 03:10:24 - mmengine - INFO - Saving checkpoint at 67 epochs 2022/09/14 03:10:53 - mmengine - INFO - Epoch(train) [68][50/293] lr: 5.000000e-04 eta: 4:58:14 time: 0.516923 data_time: 0.087135 memory: 9871 loss_kpt: 0.000632 acc_pose: 0.823506 loss: 0.000632 2022/09/14 03:11:18 - mmengine - INFO - Epoch(train) [68][100/293] lr: 5.000000e-04 eta: 4:58:00 time: 0.496382 data_time: 0.080973 memory: 9871 loss_kpt: 0.000625 acc_pose: 0.822275 loss: 0.000625 2022/09/14 03:11:42 - mmengine - INFO - Epoch(train) [68][150/293] lr: 5.000000e-04 eta: 4:57:46 time: 0.492642 data_time: 0.075341 memory: 9871 loss_kpt: 0.000613 acc_pose: 0.836726 loss: 0.000613 2022/09/14 03:12:07 - mmengine - INFO - Epoch(train) [68][200/293] lr: 5.000000e-04 eta: 4:57:31 time: 0.491249 data_time: 0.072680 memory: 9871 loss_kpt: 0.000633 acc_pose: 0.791222 loss: 0.000633 2022/09/14 03:12:32 - mmengine - INFO - Epoch(train) [68][250/293] lr: 5.000000e-04 eta: 4:57:17 time: 0.496872 data_time: 0.074766 memory: 9871 loss_kpt: 0.000633 acc_pose: 0.798538 loss: 0.000633 2022/09/14 03:12:54 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 03:12:54 - mmengine - INFO - Saving checkpoint at 68 epochs 2022/09/14 03:13:22 - mmengine - INFO - Epoch(train) [69][50/293] lr: 5.000000e-04 eta: 4:56:06 time: 0.503412 data_time: 0.080067 memory: 9871 loss_kpt: 0.000615 acc_pose: 0.819871 loss: 0.000615 2022/09/14 03:13:35 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 03:13:47 - mmengine - INFO - Epoch(train) [69][100/293] lr: 5.000000e-04 eta: 4:55:52 time: 0.495998 data_time: 0.076470 memory: 9871 loss_kpt: 0.000630 acc_pose: 0.832206 loss: 0.000630 2022/09/14 03:14:12 - mmengine - INFO - Epoch(train) [69][150/293] lr: 5.000000e-04 eta: 4:55:38 time: 0.497620 data_time: 0.077138 memory: 9871 loss_kpt: 0.000631 acc_pose: 0.797850 loss: 0.000631 2022/09/14 03:14:36 - mmengine - INFO - Epoch(train) [69][200/293] lr: 5.000000e-04 eta: 4:55:23 time: 0.494350 data_time: 0.079136 memory: 9871 loss_kpt: 0.000622 acc_pose: 0.789397 loss: 0.000622 2022/09/14 03:15:02 - mmengine - INFO - Epoch(train) [69][250/293] lr: 5.000000e-04 eta: 4:55:11 time: 0.511518 data_time: 0.082708 memory: 9871 loss_kpt: 0.000635 acc_pose: 0.785647 loss: 0.000635 2022/09/14 03:15:23 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 03:15:23 - mmengine - INFO - Saving checkpoint at 69 epochs 2022/09/14 03:15:53 - mmengine - INFO - Epoch(train) [70][50/293] lr: 5.000000e-04 eta: 4:54:03 time: 0.528509 data_time: 0.089441 memory: 9871 loss_kpt: 0.000620 acc_pose: 0.830120 loss: 0.000620 2022/09/14 03:16:18 - mmengine - INFO - Epoch(train) [70][100/293] lr: 5.000000e-04 eta: 4:53:50 time: 0.505102 data_time: 0.078084 memory: 9871 loss_kpt: 0.000632 acc_pose: 0.869620 loss: 0.000632 2022/09/14 03:16:43 - mmengine - INFO - Epoch(train) [70][150/293] lr: 5.000000e-04 eta: 4:53:35 time: 0.493672 data_time: 0.074471 memory: 9871 loss_kpt: 0.000620 acc_pose: 0.856692 loss: 0.000620 2022/09/14 03:17:07 - mmengine - INFO - Epoch(train) [70][200/293] lr: 5.000000e-04 eta: 4:53:21 time: 0.494739 data_time: 0.077527 memory: 9871 loss_kpt: 0.000641 acc_pose: 0.820836 loss: 0.000641 2022/09/14 03:17:32 - mmengine - INFO - Epoch(train) [70][250/293] lr: 5.000000e-04 eta: 4:53:06 time: 0.501305 data_time: 0.076200 memory: 9871 loss_kpt: 0.000643 acc_pose: 0.819986 loss: 0.000643 2022/09/14 03:17:54 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 03:17:54 - mmengine - INFO - Saving checkpoint at 70 epochs 2022/09/14 03:18:04 - mmengine - INFO - Epoch(val) [70][50/407] eta: 0:00:50 time: 0.140959 data_time: 0.015488 memory: 9871 2022/09/14 03:18:11 - mmengine - INFO - Epoch(val) [70][100/407] eta: 0:00:39 time: 0.127929 data_time: 0.008010 memory: 920 2022/09/14 03:18:17 - mmengine - INFO - Epoch(val) [70][150/407] eta: 0:00:33 time: 0.128735 data_time: 0.008377 memory: 920 2022/09/14 03:18:24 - mmengine - INFO - Epoch(val) [70][200/407] eta: 0:00:26 time: 0.129159 data_time: 0.008596 memory: 920 2022/09/14 03:18:30 - mmengine - INFO - Epoch(val) [70][250/407] eta: 0:00:20 time: 0.131140 data_time: 0.008888 memory: 920 2022/09/14 03:18:37 - mmengine - INFO - Epoch(val) [70][300/407] eta: 0:00:14 time: 0.135409 data_time: 0.012388 memory: 920 2022/09/14 03:18:44 - mmengine - INFO - Epoch(val) [70][350/407] eta: 0:00:07 time: 0.135531 data_time: 0.009055 memory: 920 2022/09/14 03:18:50 - mmengine - INFO - Epoch(val) [70][400/407] eta: 0:00:00 time: 0.131156 data_time: 0.010575 memory: 920 2022/09/14 03:19:27 - mmengine - INFO - Evaluating CocoMetric... 2022/09/14 03:19:41 - mmengine - INFO - Epoch(val) [70][407/407] coco/AP: 0.732284 coco/AP .5: 0.893193 coco/AP .75: 0.799185 coco/AP (M): 0.694455 coco/AP (L): 0.802544 coco/AR: 0.785249 coco/AR .5: 0.931203 coco/AR .75: 0.845718 coco/AR (M): 0.740290 coco/AR (L): 0.849907 2022/09/14 03:19:41 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220914/udp_w32_256_v1/best_coco/AP_epoch_60.pth is removed 2022/09/14 03:19:44 - mmengine - INFO - The best checkpoint with 0.7323 coco/AP at 70 epoch is saved to best_coco/AP_epoch_70.pth. 2022/09/14 03:20:09 - mmengine - INFO - Epoch(train) [71][50/293] lr: 5.000000e-04 eta: 4:51:58 time: 0.513377 data_time: 0.084418 memory: 9871 loss_kpt: 0.000608 acc_pose: 0.796996 loss: 0.000608 2022/09/14 03:20:34 - mmengine - INFO - Epoch(train) [71][100/293] lr: 5.000000e-04 eta: 4:51:44 time: 0.497001 data_time: 0.072189 memory: 9871 loss_kpt: 0.000621 acc_pose: 0.849063 loss: 0.000621 2022/09/14 03:20:59 - mmengine - INFO - Epoch(train) [71][150/293] lr: 5.000000e-04 eta: 4:51:30 time: 0.503431 data_time: 0.077882 memory: 9871 loss_kpt: 0.000634 acc_pose: 0.812958 loss: 0.000634 2022/09/14 03:21:25 - mmengine - INFO - Epoch(train) [71][200/293] lr: 5.000000e-04 eta: 4:51:16 time: 0.504174 data_time: 0.078099 memory: 9871 loss_kpt: 0.000627 acc_pose: 0.817868 loss: 0.000627 2022/09/14 03:21:49 - mmengine - INFO - Epoch(train) [71][250/293] lr: 5.000000e-04 eta: 4:51:01 time: 0.494491 data_time: 0.071204 memory: 9871 loss_kpt: 0.000627 acc_pose: 0.787395 loss: 0.000627 2022/09/14 03:22:11 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 03:22:11 - mmengine - INFO - Saving checkpoint at 71 epochs 2022/09/14 03:22:39 - mmengine - INFO - Epoch(train) [72][50/293] lr: 5.000000e-04 eta: 4:49:53 time: 0.503876 data_time: 0.081535 memory: 9871 loss_kpt: 0.000626 acc_pose: 0.842231 loss: 0.000626 2022/09/14 03:23:04 - mmengine - INFO - Epoch(train) [72][100/293] lr: 5.000000e-04 eta: 4:49:38 time: 0.496752 data_time: 0.076051 memory: 9871 loss_kpt: 0.000625 acc_pose: 0.805710 loss: 0.000625 2022/09/14 03:23:29 - mmengine - INFO - Epoch(train) [72][150/293] lr: 5.000000e-04 eta: 4:49:23 time: 0.491924 data_time: 0.070998 memory: 9871 loss_kpt: 0.000632 acc_pose: 0.800426 loss: 0.000632 2022/09/14 03:23:52 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 03:23:53 - mmengine - INFO - Epoch(train) [72][200/293] lr: 5.000000e-04 eta: 4:49:08 time: 0.493445 data_time: 0.074584 memory: 9871 loss_kpt: 0.000622 acc_pose: 0.798752 loss: 0.000622 2022/09/14 03:24:19 - mmengine - INFO - Epoch(train) [72][250/293] lr: 5.000000e-04 eta: 4:48:54 time: 0.508072 data_time: 0.085258 memory: 9871 loss_kpt: 0.000624 acc_pose: 0.837389 loss: 0.000624 2022/09/14 03:24:40 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 03:24:40 - mmengine - INFO - Saving checkpoint at 72 epochs 2022/09/14 03:25:10 - mmengine - INFO - Epoch(train) [73][50/293] lr: 5.000000e-04 eta: 4:47:49 time: 0.531332 data_time: 0.105381 memory: 9871 loss_kpt: 0.000615 acc_pose: 0.818304 loss: 0.000615 2022/09/14 03:25:36 - mmengine - INFO - Epoch(train) [73][100/293] lr: 5.000000e-04 eta: 4:47:36 time: 0.514946 data_time: 0.074779 memory: 9871 loss_kpt: 0.000613 acc_pose: 0.795004 loss: 0.000613 2022/09/14 03:26:01 - mmengine - INFO - Epoch(train) [73][150/293] lr: 5.000000e-04 eta: 4:47:21 time: 0.497885 data_time: 0.073201 memory: 9871 loss_kpt: 0.000608 acc_pose: 0.832739 loss: 0.000608 2022/09/14 03:26:27 - mmengine - INFO - Epoch(train) [73][200/293] lr: 5.000000e-04 eta: 4:47:08 time: 0.514992 data_time: 0.078682 memory: 9871 loss_kpt: 0.000620 acc_pose: 0.843968 loss: 0.000620 2022/09/14 03:26:51 - mmengine - INFO - Epoch(train) [73][250/293] lr: 5.000000e-04 eta: 4:46:53 time: 0.497262 data_time: 0.072308 memory: 9871 loss_kpt: 0.000640 acc_pose: 0.789254 loss: 0.000640 2022/09/14 03:27:13 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 03:27:13 - mmengine - INFO - Saving checkpoint at 73 epochs 2022/09/14 03:27:42 - mmengine - INFO - Epoch(train) [74][50/293] lr: 5.000000e-04 eta: 4:45:48 time: 0.520757 data_time: 0.086141 memory: 9871 loss_kpt: 0.000625 acc_pose: 0.827960 loss: 0.000625 2022/09/14 03:28:07 - mmengine - INFO - Epoch(train) [74][100/293] lr: 5.000000e-04 eta: 4:45:32 time: 0.492485 data_time: 0.075428 memory: 9871 loss_kpt: 0.000618 acc_pose: 0.834469 loss: 0.000618 2022/09/14 03:28:32 - mmengine - INFO - Epoch(train) [74][150/293] lr: 5.000000e-04 eta: 4:45:17 time: 0.499226 data_time: 0.073227 memory: 9871 loss_kpt: 0.000630 acc_pose: 0.788567 loss: 0.000630 2022/09/14 03:28:57 - mmengine - INFO - Epoch(train) [74][200/293] lr: 5.000000e-04 eta: 4:45:03 time: 0.507119 data_time: 0.082350 memory: 9871 loss_kpt: 0.000618 acc_pose: 0.842427 loss: 0.000618 2022/09/14 03:29:22 - mmengine - INFO - Epoch(train) [74][250/293] lr: 5.000000e-04 eta: 4:44:48 time: 0.499546 data_time: 0.078086 memory: 9871 loss_kpt: 0.000634 acc_pose: 0.830601 loss: 0.000634 2022/09/14 03:29:45 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 03:29:45 - mmengine - INFO - Saving checkpoint at 74 epochs 2022/09/14 03:30:13 - mmengine - INFO - Epoch(train) [75][50/293] lr: 5.000000e-04 eta: 4:43:42 time: 0.502081 data_time: 0.082701 memory: 9871 loss_kpt: 0.000614 acc_pose: 0.763986 loss: 0.000614 2022/09/14 03:30:38 - mmengine - INFO - Epoch(train) [75][100/293] lr: 5.000000e-04 eta: 4:43:27 time: 0.499302 data_time: 0.079112 memory: 9871 loss_kpt: 0.000616 acc_pose: 0.797524 loss: 0.000616 2022/09/14 03:31:03 - mmengine - INFO - Epoch(train) [75][150/293] lr: 5.000000e-04 eta: 4:43:11 time: 0.494791 data_time: 0.074074 memory: 9871 loss_kpt: 0.000622 acc_pose: 0.850077 loss: 0.000622 2022/09/14 03:31:28 - mmengine - INFO - Epoch(train) [75][200/293] lr: 5.000000e-04 eta: 4:42:57 time: 0.502592 data_time: 0.074431 memory: 9871 loss_kpt: 0.000611 acc_pose: 0.815639 loss: 0.000611 2022/09/14 03:31:53 - mmengine - INFO - Epoch(train) [75][250/293] lr: 5.000000e-04 eta: 4:42:42 time: 0.497208 data_time: 0.076433 memory: 9871 loss_kpt: 0.000611 acc_pose: 0.821731 loss: 0.000611 2022/09/14 03:32:15 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 03:32:15 - mmengine - INFO - Saving checkpoint at 75 epochs 2022/09/14 03:32:31 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 03:32:43 - mmengine - INFO - Epoch(train) [76][50/293] lr: 5.000000e-04 eta: 4:41:36 time: 0.508012 data_time: 0.080340 memory: 9871 loss_kpt: 0.000635 acc_pose: 0.745315 loss: 0.000635 2022/09/14 03:33:08 - mmengine - INFO - Epoch(train) [76][100/293] lr: 5.000000e-04 eta: 4:41:21 time: 0.501887 data_time: 0.080425 memory: 9871 loss_kpt: 0.000626 acc_pose: 0.789798 loss: 0.000626 2022/09/14 03:33:33 - mmengine - INFO - Epoch(train) [76][150/293] lr: 5.000000e-04 eta: 4:41:06 time: 0.493918 data_time: 0.079410 memory: 9871 loss_kpt: 0.000630 acc_pose: 0.754328 loss: 0.000630 2022/09/14 03:33:58 - mmengine - INFO - Epoch(train) [76][200/293] lr: 5.000000e-04 eta: 4:40:51 time: 0.504708 data_time: 0.075846 memory: 9871 loss_kpt: 0.000614 acc_pose: 0.796129 loss: 0.000614 2022/09/14 03:34:23 - mmengine - INFO - Epoch(train) [76][250/293] lr: 5.000000e-04 eta: 4:40:36 time: 0.501243 data_time: 0.074844 memory: 9871 loss_kpt: 0.000623 acc_pose: 0.823732 loss: 0.000623 2022/09/14 03:34:44 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 03:34:44 - mmengine - INFO - Saving checkpoint at 76 epochs 2022/09/14 03:35:14 - mmengine - INFO - Epoch(train) [77][50/293] lr: 5.000000e-04 eta: 4:39:33 time: 0.527873 data_time: 0.092239 memory: 9871 loss_kpt: 0.000638 acc_pose: 0.828891 loss: 0.000638 2022/09/14 03:35:38 - mmengine - INFO - Epoch(train) [77][100/293] lr: 5.000000e-04 eta: 4:39:17 time: 0.494732 data_time: 0.076154 memory: 9871 loss_kpt: 0.000622 acc_pose: 0.799335 loss: 0.000622 2022/09/14 03:36:04 - mmengine - INFO - Epoch(train) [77][150/293] lr: 5.000000e-04 eta: 4:39:03 time: 0.509950 data_time: 0.074156 memory: 9871 loss_kpt: 0.000624 acc_pose: 0.797139 loss: 0.000624 2022/09/14 03:36:29 - mmengine - INFO - Epoch(train) [77][200/293] lr: 5.000000e-04 eta: 4:38:48 time: 0.504714 data_time: 0.076084 memory: 9871 loss_kpt: 0.000620 acc_pose: 0.839136 loss: 0.000620 2022/09/14 03:36:54 - mmengine - INFO - Epoch(train) [77][250/293] lr: 5.000000e-04 eta: 4:38:32 time: 0.493001 data_time: 0.079280 memory: 9871 loss_kpt: 0.000613 acc_pose: 0.838691 loss: 0.000613 2022/09/14 03:37:15 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 03:37:15 - mmengine - INFO - Saving checkpoint at 77 epochs 2022/09/14 03:37:43 - mmengine - INFO - Epoch(train) [78][50/293] lr: 5.000000e-04 eta: 4:37:27 time: 0.495828 data_time: 0.079786 memory: 9871 loss_kpt: 0.000617 acc_pose: 0.789480 loss: 0.000617 2022/09/14 03:38:08 - mmengine - INFO - Epoch(train) [78][100/293] lr: 5.000000e-04 eta: 4:37:11 time: 0.500563 data_time: 0.080159 memory: 9871 loss_kpt: 0.000616 acc_pose: 0.812383 loss: 0.000616 2022/09/14 03:38:33 - mmengine - INFO - Epoch(train) [78][150/293] lr: 5.000000e-04 eta: 4:36:55 time: 0.485232 data_time: 0.073296 memory: 9871 loss_kpt: 0.000619 acc_pose: 0.816981 loss: 0.000619 2022/09/14 03:38:58 - mmengine - INFO - Epoch(train) [78][200/293] lr: 5.000000e-04 eta: 4:36:39 time: 0.496700 data_time: 0.076072 memory: 9871 loss_kpt: 0.000617 acc_pose: 0.805942 loss: 0.000617 2022/09/14 03:39:22 - mmengine - INFO - Epoch(train) [78][250/293] lr: 5.000000e-04 eta: 4:36:24 time: 0.497140 data_time: 0.075440 memory: 9871 loss_kpt: 0.000620 acc_pose: 0.774118 loss: 0.000620 2022/09/14 03:39:44 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 03:39:44 - mmengine - INFO - Saving checkpoint at 78 epochs 2022/09/14 03:40:13 - mmengine - INFO - Epoch(train) [79][50/293] lr: 5.000000e-04 eta: 4:35:20 time: 0.511323 data_time: 0.084009 memory: 9871 loss_kpt: 0.000613 acc_pose: 0.783962 loss: 0.000613 2022/09/14 03:40:37 - mmengine - INFO - Epoch(train) [79][100/293] lr: 5.000000e-04 eta: 4:35:04 time: 0.490468 data_time: 0.071704 memory: 9871 loss_kpt: 0.000612 acc_pose: 0.803686 loss: 0.000612 2022/09/14 03:41:00 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 03:41:02 - mmengine - INFO - Epoch(train) [79][150/293] lr: 5.000000e-04 eta: 4:34:48 time: 0.499077 data_time: 0.080277 memory: 9871 loss_kpt: 0.000606 acc_pose: 0.812413 loss: 0.000606 2022/09/14 03:41:27 - mmengine - INFO - Epoch(train) [79][200/293] lr: 5.000000e-04 eta: 4:34:33 time: 0.496888 data_time: 0.079861 memory: 9871 loss_kpt: 0.000622 acc_pose: 0.821734 loss: 0.000622 2022/09/14 03:41:52 - mmengine - INFO - Epoch(train) [79][250/293] lr: 5.000000e-04 eta: 4:34:17 time: 0.498107 data_time: 0.077242 memory: 9871 loss_kpt: 0.000610 acc_pose: 0.821552 loss: 0.000610 2022/09/14 03:42:13 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 03:42:13 - mmengine - INFO - Saving checkpoint at 79 epochs 2022/09/14 03:42:43 - mmengine - INFO - Epoch(train) [80][50/293] lr: 5.000000e-04 eta: 4:33:13 time: 0.504155 data_time: 0.079974 memory: 9871 loss_kpt: 0.000618 acc_pose: 0.869335 loss: 0.000618 2022/09/14 03:43:07 - mmengine - INFO - Epoch(train) [80][100/293] lr: 5.000000e-04 eta: 4:32:57 time: 0.491505 data_time: 0.074563 memory: 9871 loss_kpt: 0.000622 acc_pose: 0.800955 loss: 0.000622 2022/09/14 03:43:32 - mmengine - INFO - Epoch(train) [80][150/293] lr: 5.000000e-04 eta: 4:32:41 time: 0.498634 data_time: 0.077565 memory: 9871 loss_kpt: 0.000624 acc_pose: 0.791725 loss: 0.000624 2022/09/14 03:43:57 - mmengine - INFO - Epoch(train) [80][200/293] lr: 5.000000e-04 eta: 4:32:26 time: 0.498322 data_time: 0.083622 memory: 9871 loss_kpt: 0.000615 acc_pose: 0.816742 loss: 0.000615 2022/09/14 03:44:22 - mmengine - INFO - Epoch(train) [80][250/293] lr: 5.000000e-04 eta: 4:32:10 time: 0.497810 data_time: 0.074844 memory: 9871 loss_kpt: 0.000613 acc_pose: 0.856966 loss: 0.000613 2022/09/14 03:44:43 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 03:44:43 - mmengine - INFO - Saving checkpoint at 80 epochs 2022/09/14 03:44:53 - mmengine - INFO - Epoch(val) [80][50/407] eta: 0:00:48 time: 0.136100 data_time: 0.013038 memory: 9871 2022/09/14 03:45:00 - mmengine - INFO - Epoch(val) [80][100/407] eta: 0:00:40 time: 0.133406 data_time: 0.008917 memory: 920 2022/09/14 03:45:07 - mmengine - INFO - Epoch(val) [80][150/407] eta: 0:00:33 time: 0.131108 data_time: 0.008123 memory: 920 2022/09/14 03:45:13 - mmengine - INFO - Epoch(val) [80][200/407] eta: 0:00:27 time: 0.131404 data_time: 0.007681 memory: 920 2022/09/14 03:45:20 - mmengine - INFO - Epoch(val) [80][250/407] eta: 0:00:20 time: 0.130327 data_time: 0.008074 memory: 920 2022/09/14 03:45:26 - mmengine - INFO - Epoch(val) [80][300/407] eta: 0:00:14 time: 0.131388 data_time: 0.008746 memory: 920 2022/09/14 03:45:33 - mmengine - INFO - Epoch(val) [80][350/407] eta: 0:00:07 time: 0.128384 data_time: 0.008473 memory: 920 2022/09/14 03:45:39 - mmengine - INFO - Epoch(val) [80][400/407] eta: 0:00:00 time: 0.127152 data_time: 0.007961 memory: 920 2022/09/14 03:46:16 - mmengine - INFO - Evaluating CocoMetric... 2022/09/14 03:46:30 - mmengine - INFO - Epoch(val) [80][407/407] coco/AP: 0.735105 coco/AP .5: 0.897006 coco/AP .75: 0.804071 coco/AP (M): 0.698871 coco/AP (L): 0.803857 coco/AR: 0.787689 coco/AR .5: 0.936555 coco/AR .75: 0.850283 coco/AR (M): 0.744578 coco/AR (L): 0.850056 2022/09/14 03:46:30 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220914/udp_w32_256_v1/best_coco/AP_epoch_70.pth is removed 2022/09/14 03:46:32 - mmengine - INFO - The best checkpoint with 0.7351 coco/AP at 80 epoch is saved to best_coco/AP_epoch_80.pth. 2022/09/14 03:46:58 - mmengine - INFO - Epoch(train) [81][50/293] lr: 5.000000e-04 eta: 4:31:07 time: 0.508667 data_time: 0.083100 memory: 9871 loss_kpt: 0.000614 acc_pose: 0.852323 loss: 0.000614 2022/09/14 03:47:22 - mmengine - INFO - Epoch(train) [81][100/293] lr: 5.000000e-04 eta: 4:30:51 time: 0.494787 data_time: 0.073716 memory: 9871 loss_kpt: 0.000612 acc_pose: 0.810937 loss: 0.000612 2022/09/14 03:47:48 - mmengine - INFO - Epoch(train) [81][150/293] lr: 5.000000e-04 eta: 4:30:36 time: 0.501712 data_time: 0.079661 memory: 9871 loss_kpt: 0.000612 acc_pose: 0.797905 loss: 0.000612 2022/09/14 03:48:12 - mmengine - INFO - Epoch(train) [81][200/293] lr: 5.000000e-04 eta: 4:30:19 time: 0.485887 data_time: 0.072768 memory: 9871 loss_kpt: 0.000638 acc_pose: 0.822605 loss: 0.000638 2022/09/14 03:48:37 - mmengine - INFO - Epoch(train) [81][250/293] lr: 5.000000e-04 eta: 4:30:04 time: 0.505364 data_time: 0.079392 memory: 9871 loss_kpt: 0.000623 acc_pose: 0.832280 loss: 0.000623 2022/09/14 03:48:59 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 03:48:59 - mmengine - INFO - Saving checkpoint at 81 epochs 2022/09/14 03:49:29 - mmengine - INFO - Epoch(train) [82][50/293] lr: 5.000000e-04 eta: 4:29:03 time: 0.534090 data_time: 0.103373 memory: 9871 loss_kpt: 0.000616 acc_pose: 0.795687 loss: 0.000616 2022/09/14 03:49:54 - mmengine - INFO - Epoch(train) [82][100/293] lr: 5.000000e-04 eta: 4:28:48 time: 0.504363 data_time: 0.084996 memory: 9871 loss_kpt: 0.000608 acc_pose: 0.768392 loss: 0.000608 2022/09/14 03:50:18 - mmengine - INFO - Epoch(train) [82][150/293] lr: 5.000000e-04 eta: 4:28:31 time: 0.493398 data_time: 0.075543 memory: 9871 loss_kpt: 0.000616 acc_pose: 0.819755 loss: 0.000616 2022/09/14 03:50:43 - mmengine - INFO - Epoch(train) [82][200/293] lr: 5.000000e-04 eta: 4:28:15 time: 0.490790 data_time: 0.076775 memory: 9871 loss_kpt: 0.000624 acc_pose: 0.830352 loss: 0.000624 2022/09/14 03:51:08 - mmengine - INFO - Epoch(train) [82][250/293] lr: 5.000000e-04 eta: 4:27:59 time: 0.493899 data_time: 0.076845 memory: 9871 loss_kpt: 0.000607 acc_pose: 0.808272 loss: 0.000607 2022/09/14 03:51:16 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 03:51:29 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 03:51:29 - mmengine - INFO - Saving checkpoint at 82 epochs 2022/09/14 03:51:59 - mmengine - INFO - Epoch(train) [83][50/293] lr: 5.000000e-04 eta: 4:26:58 time: 0.522227 data_time: 0.083873 memory: 9871 loss_kpt: 0.000613 acc_pose: 0.828766 loss: 0.000613 2022/09/14 03:52:24 - mmengine - INFO - Epoch(train) [83][100/293] lr: 5.000000e-04 eta: 4:26:42 time: 0.508276 data_time: 0.073433 memory: 9871 loss_kpt: 0.000628 acc_pose: 0.855077 loss: 0.000628 2022/09/14 03:52:49 - mmengine - INFO - Epoch(train) [83][150/293] lr: 5.000000e-04 eta: 4:26:26 time: 0.498937 data_time: 0.077927 memory: 9871 loss_kpt: 0.000621 acc_pose: 0.827728 loss: 0.000621 2022/09/14 03:53:14 - mmengine - INFO - Epoch(train) [83][200/293] lr: 5.000000e-04 eta: 4:26:10 time: 0.495851 data_time: 0.072775 memory: 9871 loss_kpt: 0.000600 acc_pose: 0.802705 loss: 0.000600 2022/09/14 03:53:39 - mmengine - INFO - Epoch(train) [83][250/293] lr: 5.000000e-04 eta: 4:25:55 time: 0.502345 data_time: 0.071316 memory: 9871 loss_kpt: 0.000600 acc_pose: 0.815676 loss: 0.000600 2022/09/14 03:54:00 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 03:54:00 - mmengine - INFO - Saving checkpoint at 83 epochs 2022/09/14 03:54:29 - mmengine - INFO - Epoch(train) [84][50/293] lr: 5.000000e-04 eta: 4:24:53 time: 0.512180 data_time: 0.079002 memory: 9871 loss_kpt: 0.000604 acc_pose: 0.842928 loss: 0.000604 2022/09/14 03:54:54 - mmengine - INFO - Epoch(train) [84][100/293] lr: 5.000000e-04 eta: 4:24:37 time: 0.500429 data_time: 0.074255 memory: 9871 loss_kpt: 0.000604 acc_pose: 0.845796 loss: 0.000604 2022/09/14 03:55:19 - mmengine - INFO - Epoch(train) [84][150/293] lr: 5.000000e-04 eta: 4:24:21 time: 0.497848 data_time: 0.074671 memory: 9871 loss_kpt: 0.000602 acc_pose: 0.825325 loss: 0.000602 2022/09/14 03:55:44 - mmengine - INFO - Epoch(train) [84][200/293] lr: 5.000000e-04 eta: 4:24:05 time: 0.502487 data_time: 0.076725 memory: 9871 loss_kpt: 0.000614 acc_pose: 0.848409 loss: 0.000614 2022/09/14 03:56:09 - mmengine - INFO - Epoch(train) [84][250/293] lr: 5.000000e-04 eta: 4:23:50 time: 0.503978 data_time: 0.083080 memory: 9871 loss_kpt: 0.000622 acc_pose: 0.810692 loss: 0.000622 2022/09/14 03:56:30 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 03:56:30 - mmengine - INFO - Saving checkpoint at 84 epochs 2022/09/14 03:57:00 - mmengine - INFO - Epoch(train) [85][50/293] lr: 5.000000e-04 eta: 4:22:47 time: 0.497348 data_time: 0.080439 memory: 9871 loss_kpt: 0.000608 acc_pose: 0.862465 loss: 0.000608 2022/09/14 03:57:25 - mmengine - INFO - Epoch(train) [85][100/293] lr: 5.000000e-04 eta: 4:22:32 time: 0.503487 data_time: 0.070828 memory: 9871 loss_kpt: 0.000634 acc_pose: 0.797231 loss: 0.000634 2022/09/14 03:57:50 - mmengine - INFO - Epoch(train) [85][150/293] lr: 5.000000e-04 eta: 4:22:16 time: 0.504765 data_time: 0.076655 memory: 9871 loss_kpt: 0.000614 acc_pose: 0.855968 loss: 0.000614 2022/09/14 03:58:15 - mmengine - INFO - Epoch(train) [85][200/293] lr: 5.000000e-04 eta: 4:22:00 time: 0.497976 data_time: 0.073340 memory: 9871 loss_kpt: 0.000608 acc_pose: 0.850304 loss: 0.000608 2022/09/14 03:58:40 - mmengine - INFO - Epoch(train) [85][250/293] lr: 5.000000e-04 eta: 4:21:44 time: 0.506070 data_time: 0.082040 memory: 9871 loss_kpt: 0.000614 acc_pose: 0.813051 loss: 0.000614 2022/09/14 03:59:01 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 03:59:01 - mmengine - INFO - Saving checkpoint at 85 epochs 2022/09/14 03:59:30 - mmengine - INFO - Epoch(train) [86][50/293] lr: 5.000000e-04 eta: 4:20:43 time: 0.511493 data_time: 0.083318 memory: 9871 loss_kpt: 0.000595 acc_pose: 0.834529 loss: 0.000595 2022/09/14 03:59:53 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 03:59:55 - mmengine - INFO - Epoch(train) [86][100/293] lr: 5.000000e-04 eta: 4:20:28 time: 0.506752 data_time: 0.080441 memory: 9871 loss_kpt: 0.000624 acc_pose: 0.820154 loss: 0.000624 2022/09/14 04:00:20 - mmengine - INFO - Epoch(train) [86][150/293] lr: 5.000000e-04 eta: 4:20:12 time: 0.499351 data_time: 0.070328 memory: 9871 loss_kpt: 0.000605 acc_pose: 0.831265 loss: 0.000605 2022/09/14 04:00:46 - mmengine - INFO - Epoch(train) [86][200/293] lr: 5.000000e-04 eta: 4:19:56 time: 0.503962 data_time: 0.082215 memory: 9871 loss_kpt: 0.000612 acc_pose: 0.836633 loss: 0.000612 2022/09/14 04:01:11 - mmengine - INFO - Epoch(train) [86][250/293] lr: 5.000000e-04 eta: 4:19:40 time: 0.500295 data_time: 0.070750 memory: 9871 loss_kpt: 0.000601 acc_pose: 0.828201 loss: 0.000601 2022/09/14 04:01:32 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 04:01:32 - mmengine - INFO - Saving checkpoint at 86 epochs 2022/09/14 04:02:03 - mmengine - INFO - Epoch(train) [87][50/293] lr: 5.000000e-04 eta: 4:18:41 time: 0.538170 data_time: 0.099658 memory: 9871 loss_kpt: 0.000612 acc_pose: 0.825904 loss: 0.000612 2022/09/14 04:02:28 - mmengine - INFO - Epoch(train) [87][100/293] lr: 5.000000e-04 eta: 4:18:25 time: 0.502835 data_time: 0.074901 memory: 9871 loss_kpt: 0.000626 acc_pose: 0.798102 loss: 0.000626 2022/09/14 04:02:54 - mmengine - INFO - Epoch(train) [87][150/293] lr: 5.000000e-04 eta: 4:18:09 time: 0.502008 data_time: 0.076241 memory: 9871 loss_kpt: 0.000620 acc_pose: 0.805971 loss: 0.000620 2022/09/14 04:03:18 - mmengine - INFO - Epoch(train) [87][200/293] lr: 5.000000e-04 eta: 4:17:52 time: 0.494191 data_time: 0.071129 memory: 9871 loss_kpt: 0.000605 acc_pose: 0.869955 loss: 0.000605 2022/09/14 04:03:44 - mmengine - INFO - Epoch(train) [87][250/293] lr: 5.000000e-04 eta: 4:17:36 time: 0.506635 data_time: 0.074479 memory: 9871 loss_kpt: 0.000628 acc_pose: 0.786227 loss: 0.000628 2022/09/14 04:04:05 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 04:04:05 - mmengine - INFO - Saving checkpoint at 87 epochs 2022/09/14 04:04:34 - mmengine - INFO - Epoch(train) [88][50/293] lr: 5.000000e-04 eta: 4:16:36 time: 0.507053 data_time: 0.080719 memory: 9871 loss_kpt: 0.000616 acc_pose: 0.799506 loss: 0.000616 2022/09/14 04:04:58 - mmengine - INFO - Epoch(train) [88][100/293] lr: 5.000000e-04 eta: 4:16:19 time: 0.491316 data_time: 0.075670 memory: 9871 loss_kpt: 0.000596 acc_pose: 0.742824 loss: 0.000596 2022/09/14 04:05:24 - mmengine - INFO - Epoch(train) [88][150/293] lr: 5.000000e-04 eta: 4:16:03 time: 0.505707 data_time: 0.080751 memory: 9871 loss_kpt: 0.000615 acc_pose: 0.852840 loss: 0.000615 2022/09/14 04:05:49 - mmengine - INFO - Epoch(train) [88][200/293] lr: 5.000000e-04 eta: 4:15:47 time: 0.499043 data_time: 0.075432 memory: 9871 loss_kpt: 0.000617 acc_pose: 0.789556 loss: 0.000617 2022/09/14 04:06:14 - mmengine - INFO - Epoch(train) [88][250/293] lr: 5.000000e-04 eta: 4:15:31 time: 0.503681 data_time: 0.075023 memory: 9871 loss_kpt: 0.000603 acc_pose: 0.782516 loss: 0.000603 2022/09/14 04:06:35 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 04:06:35 - mmengine - INFO - Saving checkpoint at 88 epochs 2022/09/14 04:07:04 - mmengine - INFO - Epoch(train) [89][50/293] lr: 5.000000e-04 eta: 4:14:31 time: 0.516667 data_time: 0.078762 memory: 9871 loss_kpt: 0.000609 acc_pose: 0.871413 loss: 0.000609 2022/09/14 04:07:29 - mmengine - INFO - Epoch(train) [89][100/293] lr: 5.000000e-04 eta: 4:14:15 time: 0.496400 data_time: 0.074705 memory: 9871 loss_kpt: 0.000606 acc_pose: 0.810152 loss: 0.000606 2022/09/14 04:07:54 - mmengine - INFO - Epoch(train) [89][150/293] lr: 5.000000e-04 eta: 4:13:58 time: 0.499679 data_time: 0.077407 memory: 9871 loss_kpt: 0.000618 acc_pose: 0.813748 loss: 0.000618 2022/09/14 04:08:19 - mmengine - INFO - Epoch(train) [89][200/293] lr: 5.000000e-04 eta: 4:13:42 time: 0.501728 data_time: 0.071100 memory: 9871 loss_kpt: 0.000623 acc_pose: 0.793162 loss: 0.000623 2022/09/14 04:08:27 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 04:08:45 - mmengine - INFO - Epoch(train) [89][250/293] lr: 5.000000e-04 eta: 4:13:26 time: 0.514240 data_time: 0.085757 memory: 9871 loss_kpt: 0.000607 acc_pose: 0.864165 loss: 0.000607 2022/09/14 04:09:06 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 04:09:06 - mmengine - INFO - Saving checkpoint at 89 epochs 2022/09/14 04:09:36 - mmengine - INFO - Epoch(train) [90][50/293] lr: 5.000000e-04 eta: 4:12:27 time: 0.504116 data_time: 0.079725 memory: 9871 loss_kpt: 0.000600 acc_pose: 0.811951 loss: 0.000600 2022/09/14 04:10:01 - mmengine - INFO - Epoch(train) [90][100/293] lr: 5.000000e-04 eta: 4:12:10 time: 0.500869 data_time: 0.079612 memory: 9871 loss_kpt: 0.000614 acc_pose: 0.819639 loss: 0.000614 2022/09/14 04:10:26 - mmengine - INFO - Epoch(train) [90][150/293] lr: 5.000000e-04 eta: 4:11:54 time: 0.498220 data_time: 0.072236 memory: 9871 loss_kpt: 0.000613 acc_pose: 0.813612 loss: 0.000613 2022/09/14 04:10:51 - mmengine - INFO - Epoch(train) [90][200/293] lr: 5.000000e-04 eta: 4:11:37 time: 0.492981 data_time: 0.070211 memory: 9871 loss_kpt: 0.000608 acc_pose: 0.863784 loss: 0.000608 2022/09/14 04:11:16 - mmengine - INFO - Epoch(train) [90][250/293] lr: 5.000000e-04 eta: 4:11:20 time: 0.501756 data_time: 0.069950 memory: 9871 loss_kpt: 0.000602 acc_pose: 0.849016 loss: 0.000602 2022/09/14 04:11:37 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 04:11:37 - mmengine - INFO - Saving checkpoint at 90 epochs 2022/09/14 04:11:47 - mmengine - INFO - Epoch(val) [90][50/407] eta: 0:00:49 time: 0.139776 data_time: 0.013862 memory: 9871 2022/09/14 04:11:54 - mmengine - INFO - Epoch(val) [90][100/407] eta: 0:00:40 time: 0.131946 data_time: 0.008380 memory: 920 2022/09/14 04:12:00 - mmengine - INFO - Epoch(val) [90][150/407] eta: 0:00:34 time: 0.135961 data_time: 0.012310 memory: 920 2022/09/14 04:12:07 - mmengine - INFO - Epoch(val) [90][200/407] eta: 0:00:27 time: 0.131868 data_time: 0.008928 memory: 920 2022/09/14 04:12:14 - mmengine - INFO - Epoch(val) [90][250/407] eta: 0:00:20 time: 0.131780 data_time: 0.008844 memory: 920 2022/09/14 04:12:20 - mmengine - INFO - Epoch(val) [90][300/407] eta: 0:00:14 time: 0.132171 data_time: 0.008142 memory: 920 2022/09/14 04:12:27 - mmengine - INFO - Epoch(val) [90][350/407] eta: 0:00:07 time: 0.133019 data_time: 0.009140 memory: 920 2022/09/14 04:12:33 - mmengine - INFO - Epoch(val) [90][400/407] eta: 0:00:00 time: 0.127500 data_time: 0.008528 memory: 920 2022/09/14 04:13:11 - mmengine - INFO - Evaluating CocoMetric... 2022/09/14 04:13:25 - mmengine - INFO - Epoch(val) [90][407/407] coco/AP: 0.738349 coco/AP .5: 0.898789 coco/AP .75: 0.808795 coco/AP (M): 0.699247 coco/AP (L): 0.807311 coco/AR: 0.789751 coco/AR .5: 0.936241 coco/AR .75: 0.854219 coco/AR (M): 0.746190 coco/AR (L): 0.852843 2022/09/14 04:13:25 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220914/udp_w32_256_v1/best_coco/AP_epoch_80.pth is removed 2022/09/14 04:13:28 - mmengine - INFO - The best checkpoint with 0.7383 coco/AP at 90 epoch is saved to best_coco/AP_epoch_90.pth. 2022/09/14 04:13:53 - mmengine - INFO - Epoch(train) [91][50/293] lr: 5.000000e-04 eta: 4:10:21 time: 0.515013 data_time: 0.083216 memory: 9871 loss_kpt: 0.000610 acc_pose: 0.862840 loss: 0.000610 2022/09/14 04:14:18 - mmengine - INFO - Epoch(train) [91][100/293] lr: 5.000000e-04 eta: 4:10:05 time: 0.503214 data_time: 0.081339 memory: 9871 loss_kpt: 0.000609 acc_pose: 0.797238 loss: 0.000609 2022/09/14 04:14:43 - mmengine - INFO - Epoch(train) [91][150/293] lr: 5.000000e-04 eta: 4:09:48 time: 0.495968 data_time: 0.074952 memory: 9871 loss_kpt: 0.000604 acc_pose: 0.802042 loss: 0.000604 2022/09/14 04:15:09 - mmengine - INFO - Epoch(train) [91][200/293] lr: 5.000000e-04 eta: 4:09:32 time: 0.504842 data_time: 0.076795 memory: 9871 loss_kpt: 0.000613 acc_pose: 0.810297 loss: 0.000613 2022/09/14 04:15:34 - mmengine - INFO - Epoch(train) [91][250/293] lr: 5.000000e-04 eta: 4:09:16 time: 0.508831 data_time: 0.082122 memory: 9871 loss_kpt: 0.000621 acc_pose: 0.851342 loss: 0.000621 2022/09/14 04:15:55 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 04:15:55 - mmengine - INFO - Saving checkpoint at 91 epochs 2022/09/14 04:16:24 - mmengine - INFO - Epoch(train) [92][50/293] lr: 5.000000e-04 eta: 4:08:17 time: 0.512222 data_time: 0.080216 memory: 9871 loss_kpt: 0.000617 acc_pose: 0.850194 loss: 0.000617 2022/09/14 04:16:49 - mmengine - INFO - Epoch(train) [92][100/293] lr: 5.000000e-04 eta: 4:08:01 time: 0.499136 data_time: 0.084429 memory: 9871 loss_kpt: 0.000616 acc_pose: 0.787587 loss: 0.000616 2022/09/14 04:17:14 - mmengine - INFO - Epoch(train) [92][150/293] lr: 5.000000e-04 eta: 4:07:44 time: 0.499205 data_time: 0.075639 memory: 9871 loss_kpt: 0.000594 acc_pose: 0.796121 loss: 0.000594 2022/09/14 04:17:39 - mmengine - INFO - Epoch(train) [92][200/293] lr: 5.000000e-04 eta: 4:07:27 time: 0.504359 data_time: 0.077557 memory: 9871 loss_kpt: 0.000606 acc_pose: 0.818182 loss: 0.000606 2022/09/14 04:18:04 - mmengine - INFO - Epoch(train) [92][250/293] lr: 5.000000e-04 eta: 4:07:10 time: 0.498040 data_time: 0.071810 memory: 9871 loss_kpt: 0.000599 acc_pose: 0.787892 loss: 0.000599 2022/09/14 04:18:25 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 04:18:25 - mmengine - INFO - Saving checkpoint at 92 epochs 2022/09/14 04:18:51 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 04:18:54 - mmengine - INFO - Epoch(train) [93][50/293] lr: 5.000000e-04 eta: 4:06:12 time: 0.510945 data_time: 0.089340 memory: 9871 loss_kpt: 0.000603 acc_pose: 0.855147 loss: 0.000603 2022/09/14 04:19:19 - mmengine - INFO - Epoch(train) [93][100/293] lr: 5.000000e-04 eta: 4:05:55 time: 0.499120 data_time: 0.072201 memory: 9871 loss_kpt: 0.000617 acc_pose: 0.834160 loss: 0.000617 2022/09/14 04:19:44 - mmengine - INFO - Epoch(train) [93][150/293] lr: 5.000000e-04 eta: 4:05:38 time: 0.495292 data_time: 0.076912 memory: 9871 loss_kpt: 0.000604 acc_pose: 0.800744 loss: 0.000604 2022/09/14 04:20:09 - mmengine - INFO - Epoch(train) [93][200/293] lr: 5.000000e-04 eta: 4:05:21 time: 0.497114 data_time: 0.070867 memory: 9871 loss_kpt: 0.000592 acc_pose: 0.850413 loss: 0.000592 2022/09/14 04:20:33 - mmengine - INFO - Epoch(train) [93][250/293] lr: 5.000000e-04 eta: 4:05:04 time: 0.491025 data_time: 0.070487 memory: 9871 loss_kpt: 0.000600 acc_pose: 0.824199 loss: 0.000600 2022/09/14 04:20:55 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 04:20:55 - mmengine - INFO - Saving checkpoint at 93 epochs 2022/09/14 04:21:24 - mmengine - INFO - Epoch(train) [94][50/293] lr: 5.000000e-04 eta: 4:04:06 time: 0.511501 data_time: 0.083852 memory: 9871 loss_kpt: 0.000593 acc_pose: 0.827467 loss: 0.000593 2022/09/14 04:21:49 - mmengine - INFO - Epoch(train) [94][100/293] lr: 5.000000e-04 eta: 4:03:49 time: 0.501384 data_time: 0.085770 memory: 9871 loss_kpt: 0.000599 acc_pose: 0.811353 loss: 0.000599 2022/09/14 04:22:13 - mmengine - INFO - Epoch(train) [94][150/293] lr: 5.000000e-04 eta: 4:03:31 time: 0.486308 data_time: 0.076656 memory: 9871 loss_kpt: 0.000610 acc_pose: 0.856039 loss: 0.000610 2022/09/14 04:22:38 - mmengine - INFO - Epoch(train) [94][200/293] lr: 5.000000e-04 eta: 4:03:14 time: 0.491582 data_time: 0.073387 memory: 9871 loss_kpt: 0.000596 acc_pose: 0.803341 loss: 0.000596 2022/09/14 04:23:02 - mmengine - INFO - Epoch(train) [94][250/293] lr: 5.000000e-04 eta: 4:02:57 time: 0.494189 data_time: 0.077170 memory: 9871 loss_kpt: 0.000606 acc_pose: 0.720973 loss: 0.000606 2022/09/14 04:23:24 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 04:23:24 - mmengine - INFO - Saving checkpoint at 94 epochs 2022/09/14 04:23:53 - mmengine - INFO - Epoch(train) [95][50/293] lr: 5.000000e-04 eta: 4:02:00 time: 0.516205 data_time: 0.088299 memory: 9871 loss_kpt: 0.000599 acc_pose: 0.840611 loss: 0.000599 2022/09/14 04:24:18 - mmengine - INFO - Epoch(train) [95][100/293] lr: 5.000000e-04 eta: 4:01:43 time: 0.501121 data_time: 0.074195 memory: 9871 loss_kpt: 0.000595 acc_pose: 0.888995 loss: 0.000595 2022/09/14 04:24:43 - mmengine - INFO - Epoch(train) [95][150/293] lr: 5.000000e-04 eta: 4:01:25 time: 0.497196 data_time: 0.075865 memory: 9871 loss_kpt: 0.000614 acc_pose: 0.819489 loss: 0.000614 2022/09/14 04:25:08 - mmengine - INFO - Epoch(train) [95][200/293] lr: 5.000000e-04 eta: 4:01:08 time: 0.498281 data_time: 0.081179 memory: 9871 loss_kpt: 0.000600 acc_pose: 0.835003 loss: 0.000600 2022/09/14 04:25:33 - mmengine - INFO - Epoch(train) [95][250/293] lr: 5.000000e-04 eta: 4:00:51 time: 0.501828 data_time: 0.075802 memory: 9871 loss_kpt: 0.000611 acc_pose: 0.779476 loss: 0.000611 2022/09/14 04:25:55 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 04:25:55 - mmengine - INFO - Saving checkpoint at 95 epochs 2022/09/14 04:26:23 - mmengine - INFO - Epoch(train) [96][50/293] lr: 5.000000e-04 eta: 3:59:54 time: 0.503791 data_time: 0.082378 memory: 9871 loss_kpt: 0.000590 acc_pose: 0.866245 loss: 0.000590 2022/09/14 04:26:48 - mmengine - INFO - Epoch(train) [96][100/293] lr: 5.000000e-04 eta: 3:59:37 time: 0.496848 data_time: 0.075387 memory: 9871 loss_kpt: 0.000593 acc_pose: 0.806559 loss: 0.000593 2022/09/14 04:27:13 - mmengine - INFO - Epoch(train) [96][150/293] lr: 5.000000e-04 eta: 3:59:19 time: 0.495880 data_time: 0.075923 memory: 9871 loss_kpt: 0.000605 acc_pose: 0.841430 loss: 0.000605 2022/09/14 04:27:20 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 04:27:38 - mmengine - INFO - Epoch(train) [96][200/293] lr: 5.000000e-04 eta: 3:59:02 time: 0.500439 data_time: 0.074923 memory: 9871 loss_kpt: 0.000604 acc_pose: 0.806387 loss: 0.000604 2022/09/14 04:28:02 - mmengine - INFO - Epoch(train) [96][250/293] lr: 5.000000e-04 eta: 3:58:45 time: 0.495598 data_time: 0.079256 memory: 9871 loss_kpt: 0.000602 acc_pose: 0.785999 loss: 0.000602 2022/09/14 04:28:24 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 04:28:24 - mmengine - INFO - Saving checkpoint at 96 epochs 2022/09/14 04:28:53 - mmengine - INFO - Epoch(train) [97][50/293] lr: 5.000000e-04 eta: 3:57:48 time: 0.513404 data_time: 0.084034 memory: 9871 loss_kpt: 0.000604 acc_pose: 0.792962 loss: 0.000604 2022/09/14 04:29:18 - mmengine - INFO - Epoch(train) [97][100/293] lr: 5.000000e-04 eta: 3:57:31 time: 0.497632 data_time: 0.077626 memory: 9871 loss_kpt: 0.000597 acc_pose: 0.798149 loss: 0.000597 2022/09/14 04:29:42 - mmengine - INFO - Epoch(train) [97][150/293] lr: 5.000000e-04 eta: 3:57:13 time: 0.491725 data_time: 0.075962 memory: 9871 loss_kpt: 0.000597 acc_pose: 0.834420 loss: 0.000597 2022/09/14 04:30:07 - mmengine - INFO - Epoch(train) [97][200/293] lr: 5.000000e-04 eta: 3:56:56 time: 0.500993 data_time: 0.077392 memory: 9871 loss_kpt: 0.000603 acc_pose: 0.788986 loss: 0.000603 2022/09/14 04:30:32 - mmengine - INFO - Epoch(train) [97][250/293] lr: 5.000000e-04 eta: 3:56:39 time: 0.497270 data_time: 0.079117 memory: 9871 loss_kpt: 0.000603 acc_pose: 0.804310 loss: 0.000603 2022/09/14 04:30:54 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 04:30:54 - mmengine - INFO - Saving checkpoint at 97 epochs 2022/09/14 04:31:22 - mmengine - INFO - Epoch(train) [98][50/293] lr: 5.000000e-04 eta: 3:55:42 time: 0.510252 data_time: 0.080051 memory: 9871 loss_kpt: 0.000603 acc_pose: 0.777106 loss: 0.000603 2022/09/14 04:31:47 - mmengine - INFO - Epoch(train) [98][100/293] lr: 5.000000e-04 eta: 3:55:24 time: 0.488204 data_time: 0.075590 memory: 9871 loss_kpt: 0.000585 acc_pose: 0.858024 loss: 0.000585 2022/09/14 04:32:12 - mmengine - INFO - Epoch(train) [98][150/293] lr: 5.000000e-04 eta: 3:55:07 time: 0.499098 data_time: 0.075583 memory: 9871 loss_kpt: 0.000617 acc_pose: 0.849627 loss: 0.000617 2022/09/14 04:32:37 - mmengine - INFO - Epoch(train) [98][200/293] lr: 5.000000e-04 eta: 3:54:50 time: 0.501927 data_time: 0.077355 memory: 9871 loss_kpt: 0.000610 acc_pose: 0.847272 loss: 0.000610 2022/09/14 04:33:02 - mmengine - INFO - Epoch(train) [98][250/293] lr: 5.000000e-04 eta: 3:54:33 time: 0.502414 data_time: 0.080209 memory: 9871 loss_kpt: 0.000602 acc_pose: 0.800330 loss: 0.000602 2022/09/14 04:33:24 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 04:33:24 - mmengine - INFO - Saving checkpoint at 98 epochs 2022/09/14 04:33:53 - mmengine - INFO - Epoch(train) [99][50/293] lr: 5.000000e-04 eta: 3:53:37 time: 0.516880 data_time: 0.083632 memory: 9871 loss_kpt: 0.000611 acc_pose: 0.860405 loss: 0.000611 2022/09/14 04:34:18 - mmengine - INFO - Epoch(train) [99][100/293] lr: 5.000000e-04 eta: 3:53:20 time: 0.503318 data_time: 0.076318 memory: 9871 loss_kpt: 0.000590 acc_pose: 0.806365 loss: 0.000590 2022/09/14 04:34:43 - mmengine - INFO - Epoch(train) [99][150/293] lr: 5.000000e-04 eta: 3:53:03 time: 0.499826 data_time: 0.071106 memory: 9871 loss_kpt: 0.000602 acc_pose: 0.848084 loss: 0.000602 2022/09/14 04:35:08 - mmengine - INFO - Epoch(train) [99][200/293] lr: 5.000000e-04 eta: 3:52:46 time: 0.507417 data_time: 0.086858 memory: 9871 loss_kpt: 0.000592 acc_pose: 0.822479 loss: 0.000592 2022/09/14 04:35:34 - mmengine - INFO - Epoch(train) [99][250/293] lr: 5.000000e-04 eta: 3:52:29 time: 0.505499 data_time: 0.076024 memory: 9871 loss_kpt: 0.000600 acc_pose: 0.801722 loss: 0.000600 2022/09/14 04:35:52 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 04:35:55 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 04:35:55 - mmengine - INFO - Saving checkpoint at 99 epochs 2022/09/14 04:36:24 - mmengine - INFO - Epoch(train) [100][50/293] lr: 5.000000e-04 eta: 3:51:33 time: 0.511578 data_time: 0.084284 memory: 9871 loss_kpt: 0.000631 acc_pose: 0.835184 loss: 0.000631 2022/09/14 04:36:49 - mmengine - INFO - Epoch(train) [100][100/293] lr: 5.000000e-04 eta: 3:51:15 time: 0.492359 data_time: 0.077494 memory: 9871 loss_kpt: 0.000602 acc_pose: 0.816795 loss: 0.000602 2022/09/14 04:37:14 - mmengine - INFO - Epoch(train) [100][150/293] lr: 5.000000e-04 eta: 3:50:58 time: 0.505063 data_time: 0.080643 memory: 9871 loss_kpt: 0.000606 acc_pose: 0.908868 loss: 0.000606 2022/09/14 04:37:39 - mmengine - INFO - Epoch(train) [100][200/293] lr: 5.000000e-04 eta: 3:50:41 time: 0.500029 data_time: 0.079152 memory: 9871 loss_kpt: 0.000603 acc_pose: 0.824621 loss: 0.000603 2022/09/14 04:38:04 - mmengine - INFO - Epoch(train) [100][250/293] lr: 5.000000e-04 eta: 3:50:23 time: 0.494115 data_time: 0.074973 memory: 9871 loss_kpt: 0.000597 acc_pose: 0.796309 loss: 0.000597 2022/09/14 04:38:25 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 04:38:25 - mmengine - INFO - Saving checkpoint at 100 epochs 2022/09/14 04:38:35 - mmengine - INFO - Epoch(val) [100][50/407] eta: 0:00:50 time: 0.141216 data_time: 0.014431 memory: 9871 2022/09/14 04:38:42 - mmengine - INFO - Epoch(val) [100][100/407] eta: 0:00:42 time: 0.137936 data_time: 0.010500 memory: 920 2022/09/14 04:38:49 - mmengine - INFO - Epoch(val) [100][150/407] eta: 0:00:35 time: 0.136462 data_time: 0.008999 memory: 920 2022/09/14 04:38:56 - mmengine - INFO - Epoch(val) [100][200/407] eta: 0:00:28 time: 0.138466 data_time: 0.009622 memory: 920 2022/09/14 04:39:03 - mmengine - INFO - Epoch(val) [100][250/407] eta: 0:00:21 time: 0.135944 data_time: 0.009576 memory: 920 2022/09/14 04:39:10 - mmengine - INFO - Epoch(val) [100][300/407] eta: 0:00:14 time: 0.136162 data_time: 0.009467 memory: 920 2022/09/14 04:39:16 - mmengine - INFO - Epoch(val) [100][350/407] eta: 0:00:07 time: 0.135925 data_time: 0.009455 memory: 920 2022/09/14 04:39:23 - mmengine - INFO - Epoch(val) [100][400/407] eta: 0:00:00 time: 0.130359 data_time: 0.007923 memory: 920 2022/09/14 04:40:01 - mmengine - INFO - Evaluating CocoMetric... 2022/09/14 04:40:16 - mmengine - INFO - Epoch(val) [100][407/407] coco/AP: 0.738281 coco/AP .5: 0.895400 coco/AP .75: 0.803553 coco/AP (M): 0.698474 coco/AP (L): 0.810751 coco/AR: 0.790963 coco/AR .5: 0.936083 coco/AR .75: 0.849496 coco/AR (M): 0.744824 coco/AR (L): 0.857488 2022/09/14 04:40:41 - mmengine - INFO - Epoch(train) [101][50/293] lr: 5.000000e-04 eta: 3:49:27 time: 0.514261 data_time: 0.080924 memory: 9871 loss_kpt: 0.000593 acc_pose: 0.826740 loss: 0.000593 2022/09/14 04:41:06 - mmengine - INFO - Epoch(train) [101][100/293] lr: 5.000000e-04 eta: 3:49:10 time: 0.497044 data_time: 0.074093 memory: 9871 loss_kpt: 0.000602 acc_pose: 0.824473 loss: 0.000602 2022/09/14 04:41:31 - mmengine - INFO - Epoch(train) [101][150/293] lr: 5.000000e-04 eta: 3:48:53 time: 0.502460 data_time: 0.071785 memory: 9871 loss_kpt: 0.000588 acc_pose: 0.805458 loss: 0.000588 2022/09/14 04:41:56 - mmengine - INFO - Epoch(train) [101][200/293] lr: 5.000000e-04 eta: 3:48:35 time: 0.502191 data_time: 0.080811 memory: 9871 loss_kpt: 0.000605 acc_pose: 0.810959 loss: 0.000605 2022/09/14 04:42:21 - mmengine - INFO - Epoch(train) [101][250/293] lr: 5.000000e-04 eta: 3:48:18 time: 0.499345 data_time: 0.072685 memory: 9871 loss_kpt: 0.000604 acc_pose: 0.828171 loss: 0.000604 2022/09/14 04:42:43 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 04:42:43 - mmengine - INFO - Saving checkpoint at 101 epochs 2022/09/14 04:43:12 - mmengine - INFO - Epoch(train) [102][50/293] lr: 5.000000e-04 eta: 3:47:22 time: 0.511523 data_time: 0.084625 memory: 9871 loss_kpt: 0.000588 acc_pose: 0.824136 loss: 0.000588 2022/09/14 04:43:37 - mmengine - INFO - Epoch(train) [102][100/293] lr: 5.000000e-04 eta: 3:47:05 time: 0.499432 data_time: 0.073694 memory: 9871 loss_kpt: 0.000599 acc_pose: 0.847671 loss: 0.000599 2022/09/14 04:44:02 - mmengine - INFO - Epoch(train) [102][150/293] lr: 5.000000e-04 eta: 3:46:47 time: 0.498483 data_time: 0.072358 memory: 9871 loss_kpt: 0.000602 acc_pose: 0.862293 loss: 0.000602 2022/09/14 04:44:27 - mmengine - INFO - Epoch(train) [102][200/293] lr: 5.000000e-04 eta: 3:46:30 time: 0.500180 data_time: 0.073094 memory: 9871 loss_kpt: 0.000585 acc_pose: 0.794820 loss: 0.000585 2022/09/14 04:44:52 - mmengine - INFO - Epoch(train) [102][250/293] lr: 5.000000e-04 eta: 3:46:12 time: 0.507912 data_time: 0.081610 memory: 9871 loss_kpt: 0.000598 acc_pose: 0.816405 loss: 0.000598 2022/09/14 04:45:14 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 04:45:14 - mmengine - INFO - Saving checkpoint at 102 epochs 2022/09/14 04:45:42 - mmengine - INFO - Epoch(train) [103][50/293] lr: 5.000000e-04 eta: 3:45:17 time: 0.502836 data_time: 0.084757 memory: 9871 loss_kpt: 0.000592 acc_pose: 0.796954 loss: 0.000592 2022/09/14 04:46:07 - mmengine - INFO - Epoch(train) [103][100/293] lr: 5.000000e-04 eta: 3:45:00 time: 0.503205 data_time: 0.085710 memory: 9871 loss_kpt: 0.000594 acc_pose: 0.801183 loss: 0.000594 2022/09/14 04:46:14 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 04:46:32 - mmengine - INFO - Epoch(train) [103][150/293] lr: 5.000000e-04 eta: 3:44:42 time: 0.496915 data_time: 0.076493 memory: 9871 loss_kpt: 0.000596 acc_pose: 0.813233 loss: 0.000596 2022/09/14 04:46:57 - mmengine - INFO - Epoch(train) [103][200/293] lr: 5.000000e-04 eta: 3:44:24 time: 0.490850 data_time: 0.074186 memory: 9871 loss_kpt: 0.000606 acc_pose: 0.838591 loss: 0.000606 2022/09/14 04:47:21 - mmengine - INFO - Epoch(train) [103][250/293] lr: 5.000000e-04 eta: 3:44:06 time: 0.490029 data_time: 0.075503 memory: 9871 loss_kpt: 0.000592 acc_pose: 0.808961 loss: 0.000592 2022/09/14 04:47:42 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 04:47:42 - mmengine - INFO - Saving checkpoint at 103 epochs 2022/09/14 04:48:12 - mmengine - INFO - Epoch(train) [104][50/293] lr: 5.000000e-04 eta: 3:43:12 time: 0.528698 data_time: 0.108179 memory: 9871 loss_kpt: 0.000605 acc_pose: 0.787806 loss: 0.000605 2022/09/14 04:48:36 - mmengine - INFO - Epoch(train) [104][100/293] lr: 5.000000e-04 eta: 3:42:54 time: 0.491208 data_time: 0.077461 memory: 9871 loss_kpt: 0.000594 acc_pose: 0.815675 loss: 0.000594 2022/09/14 04:49:02 - mmengine - INFO - Epoch(train) [104][150/293] lr: 5.000000e-04 eta: 3:42:37 time: 0.513758 data_time: 0.073408 memory: 9871 loss_kpt: 0.000592 acc_pose: 0.825476 loss: 0.000592 2022/09/14 04:49:27 - mmengine - INFO - Epoch(train) [104][200/293] lr: 5.000000e-04 eta: 3:42:19 time: 0.491844 data_time: 0.076596 memory: 9871 loss_kpt: 0.000601 acc_pose: 0.866730 loss: 0.000601 2022/09/14 04:49:52 - mmengine - INFO - Epoch(train) [104][250/293] lr: 5.000000e-04 eta: 3:42:01 time: 0.507357 data_time: 0.074155 memory: 9871 loss_kpt: 0.000594 acc_pose: 0.771713 loss: 0.000594 2022/09/14 04:50:13 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 04:50:13 - mmengine - INFO - Saving checkpoint at 104 epochs 2022/09/14 04:50:42 - mmengine - INFO - Epoch(train) [105][50/293] lr: 5.000000e-04 eta: 3:41:07 time: 0.508307 data_time: 0.087477 memory: 9871 loss_kpt: 0.000599 acc_pose: 0.833348 loss: 0.000599 2022/09/14 04:51:07 - mmengine - INFO - Epoch(train) [105][100/293] lr: 5.000000e-04 eta: 3:40:49 time: 0.498476 data_time: 0.072302 memory: 9871 loss_kpt: 0.000593 acc_pose: 0.862786 loss: 0.000593 2022/09/14 04:51:32 - mmengine - INFO - Epoch(train) [105][150/293] lr: 5.000000e-04 eta: 3:40:31 time: 0.504500 data_time: 0.079103 memory: 9871 loss_kpt: 0.000583 acc_pose: 0.844061 loss: 0.000583 2022/09/14 04:51:57 - mmengine - INFO - Epoch(train) [105][200/293] lr: 5.000000e-04 eta: 3:40:13 time: 0.490446 data_time: 0.076230 memory: 9871 loss_kpt: 0.000582 acc_pose: 0.790877 loss: 0.000582 2022/09/14 04:52:22 - mmengine - INFO - Epoch(train) [105][250/293] lr: 5.000000e-04 eta: 3:39:56 time: 0.505202 data_time: 0.074191 memory: 9871 loss_kpt: 0.000594 acc_pose: 0.765377 loss: 0.000594 2022/09/14 04:52:44 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 04:52:44 - mmengine - INFO - Saving checkpoint at 105 epochs 2022/09/14 04:53:14 - mmengine - INFO - Epoch(train) [106][50/293] lr: 5.000000e-04 eta: 3:39:02 time: 0.529357 data_time: 0.102851 memory: 9871 loss_kpt: 0.000588 acc_pose: 0.806982 loss: 0.000588 2022/09/14 04:53:39 - mmengine - INFO - Epoch(train) [106][100/293] lr: 5.000000e-04 eta: 3:38:45 time: 0.501458 data_time: 0.080681 memory: 9871 loss_kpt: 0.000591 acc_pose: 0.800957 loss: 0.000591 2022/09/14 04:54:04 - mmengine - INFO - Epoch(train) [106][150/293] lr: 5.000000e-04 eta: 3:38:27 time: 0.504054 data_time: 0.079060 memory: 9871 loss_kpt: 0.000608 acc_pose: 0.805935 loss: 0.000608 2022/09/14 04:54:29 - mmengine - INFO - Epoch(train) [106][200/293] lr: 5.000000e-04 eta: 3:38:09 time: 0.498184 data_time: 0.076910 memory: 9871 loss_kpt: 0.000592 acc_pose: 0.833230 loss: 0.000592 2022/09/14 04:54:46 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 04:54:54 - mmengine - INFO - Epoch(train) [106][250/293] lr: 5.000000e-04 eta: 3:37:51 time: 0.499117 data_time: 0.072865 memory: 9871 loss_kpt: 0.000609 acc_pose: 0.832064 loss: 0.000609 2022/09/14 04:55:16 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 04:55:16 - mmengine - INFO - Saving checkpoint at 106 epochs 2022/09/14 04:55:44 - mmengine - INFO - Epoch(train) [107][50/293] lr: 5.000000e-04 eta: 3:36:57 time: 0.502827 data_time: 0.082584 memory: 9871 loss_kpt: 0.000610 acc_pose: 0.808249 loss: 0.000610 2022/09/14 04:56:09 - mmengine - INFO - Epoch(train) [107][100/293] lr: 5.000000e-04 eta: 3:36:39 time: 0.503329 data_time: 0.072303 memory: 9871 loss_kpt: 0.000603 acc_pose: 0.859927 loss: 0.000603 2022/09/14 04:56:35 - mmengine - INFO - Epoch(train) [107][150/293] lr: 5.000000e-04 eta: 3:36:22 time: 0.515335 data_time: 0.071266 memory: 9871 loss_kpt: 0.000596 acc_pose: 0.857926 loss: 0.000596 2022/09/14 04:57:00 - mmengine - INFO - Epoch(train) [107][200/293] lr: 5.000000e-04 eta: 3:36:04 time: 0.494968 data_time: 0.075565 memory: 9871 loss_kpt: 0.000612 acc_pose: 0.802618 loss: 0.000612 2022/09/14 04:57:25 - mmengine - INFO - Epoch(train) [107][250/293] lr: 5.000000e-04 eta: 3:35:46 time: 0.499878 data_time: 0.074577 memory: 9871 loss_kpt: 0.000580 acc_pose: 0.838533 loss: 0.000580 2022/09/14 04:57:46 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 04:57:46 - mmengine - INFO - Saving checkpoint at 107 epochs 2022/09/14 04:58:15 - mmengine - INFO - Epoch(train) [108][50/293] lr: 5.000000e-04 eta: 3:34:53 time: 0.513793 data_time: 0.083412 memory: 9871 loss_kpt: 0.000604 acc_pose: 0.788292 loss: 0.000604 2022/09/14 04:58:40 - mmengine - INFO - Epoch(train) [108][100/293] lr: 5.000000e-04 eta: 3:34:35 time: 0.507115 data_time: 0.077087 memory: 9871 loss_kpt: 0.000606 acc_pose: 0.817558 loss: 0.000606 2022/09/14 04:59:05 - mmengine - INFO - Epoch(train) [108][150/293] lr: 5.000000e-04 eta: 3:34:17 time: 0.494668 data_time: 0.076051 memory: 9871 loss_kpt: 0.000592 acc_pose: 0.850583 loss: 0.000592 2022/09/14 04:59:29 - mmengine - INFO - Epoch(train) [108][200/293] lr: 5.000000e-04 eta: 3:33:58 time: 0.493564 data_time: 0.076187 memory: 9871 loss_kpt: 0.000583 acc_pose: 0.842797 loss: 0.000583 2022/09/14 04:59:55 - mmengine - INFO - Epoch(train) [108][250/293] lr: 5.000000e-04 eta: 3:33:41 time: 0.504747 data_time: 0.084396 memory: 9871 loss_kpt: 0.000589 acc_pose: 0.849093 loss: 0.000589 2022/09/14 05:00:16 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 05:00:16 - mmengine - INFO - Saving checkpoint at 108 epochs 2022/09/14 05:00:45 - mmengine - INFO - Epoch(train) [109][50/293] lr: 5.000000e-04 eta: 3:32:47 time: 0.511300 data_time: 0.083097 memory: 9871 loss_kpt: 0.000586 acc_pose: 0.785433 loss: 0.000586 2022/09/14 05:01:10 - mmengine - INFO - Epoch(train) [109][100/293] lr: 5.000000e-04 eta: 3:32:29 time: 0.500323 data_time: 0.078840 memory: 9871 loss_kpt: 0.000598 acc_pose: 0.844197 loss: 0.000598 2022/09/14 05:01:35 - mmengine - INFO - Epoch(train) [109][150/293] lr: 5.000000e-04 eta: 3:32:11 time: 0.502024 data_time: 0.071408 memory: 9871 loss_kpt: 0.000603 acc_pose: 0.844223 loss: 0.000603 2022/09/14 05:02:00 - mmengine - INFO - Epoch(train) [109][200/293] lr: 5.000000e-04 eta: 3:31:54 time: 0.506192 data_time: 0.078391 memory: 9871 loss_kpt: 0.000585 acc_pose: 0.826025 loss: 0.000585 2022/09/14 05:02:25 - mmengine - INFO - Epoch(train) [109][250/293] lr: 5.000000e-04 eta: 3:31:35 time: 0.496908 data_time: 0.076980 memory: 9871 loss_kpt: 0.000594 acc_pose: 0.860146 loss: 0.000594 2022/09/14 05:02:47 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 05:02:47 - mmengine - INFO - Saving checkpoint at 109 epochs 2022/09/14 05:03:15 - mmengine - INFO - Epoch(train) [110][50/293] lr: 5.000000e-04 eta: 3:30:42 time: 0.507369 data_time: 0.088449 memory: 9871 loss_kpt: 0.000587 acc_pose: 0.874771 loss: 0.000587 2022/09/14 05:03:22 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 05:03:40 - mmengine - INFO - Epoch(train) [110][100/293] lr: 5.000000e-04 eta: 3:30:24 time: 0.492741 data_time: 0.074195 memory: 9871 loss_kpt: 0.000594 acc_pose: 0.799320 loss: 0.000594 2022/09/14 05:04:06 - mmengine - INFO - Epoch(train) [110][150/293] lr: 5.000000e-04 eta: 3:30:06 time: 0.510119 data_time: 0.076765 memory: 9871 loss_kpt: 0.000586 acc_pose: 0.808162 loss: 0.000586 2022/09/14 05:04:30 - mmengine - INFO - Epoch(train) [110][200/293] lr: 5.000000e-04 eta: 3:29:48 time: 0.496751 data_time: 0.080554 memory: 9871 loss_kpt: 0.000607 acc_pose: 0.830001 loss: 0.000607 2022/09/14 05:04:55 - mmengine - INFO - Epoch(train) [110][250/293] lr: 5.000000e-04 eta: 3:29:30 time: 0.497517 data_time: 0.076083 memory: 9871 loss_kpt: 0.000596 acc_pose: 0.819229 loss: 0.000596 2022/09/14 05:05:17 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 05:05:17 - mmengine - INFO - Saving checkpoint at 110 epochs 2022/09/14 05:05:27 - mmengine - INFO - Epoch(val) [110][50/407] eta: 0:00:49 time: 0.139666 data_time: 0.013637 memory: 9871 2022/09/14 05:05:34 - mmengine - INFO - Epoch(val) [110][100/407] eta: 0:00:40 time: 0.132164 data_time: 0.009070 memory: 920 2022/09/14 05:05:40 - mmengine - INFO - Epoch(val) [110][150/407] eta: 0:00:33 time: 0.131411 data_time: 0.008771 memory: 920 2022/09/14 05:05:47 - mmengine - INFO - Epoch(val) [110][200/407] eta: 0:00:27 time: 0.132464 data_time: 0.008593 memory: 920 2022/09/14 05:05:54 - mmengine - INFO - Epoch(val) [110][250/407] eta: 0:00:21 time: 0.134522 data_time: 0.009016 memory: 920 2022/09/14 05:06:00 - mmengine - INFO - Epoch(val) [110][300/407] eta: 0:00:13 time: 0.130190 data_time: 0.008613 memory: 920 2022/09/14 05:06:07 - mmengine - INFO - Epoch(val) [110][350/407] eta: 0:00:07 time: 0.131113 data_time: 0.008530 memory: 920 2022/09/14 05:06:13 - mmengine - INFO - Epoch(val) [110][400/407] eta: 0:00:00 time: 0.131155 data_time: 0.010279 memory: 920 2022/09/14 05:06:51 - mmengine - INFO - Evaluating CocoMetric... 2022/09/14 05:07:05 - mmengine - INFO - Epoch(val) [110][407/407] coco/AP: 0.740391 coco/AP .5: 0.898362 coco/AP .75: 0.807481 coco/AP (M): 0.703414 coco/AP (L): 0.809052 coco/AR: 0.793341 coco/AR .5: 0.937815 coco/AR .75: 0.852645 coco/AR (M): 0.750341 coco/AR (L): 0.855704 2022/09/14 05:07:05 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220914/udp_w32_256_v1/best_coco/AP_epoch_90.pth is removed 2022/09/14 05:07:07 - mmengine - INFO - The best checkpoint with 0.7404 coco/AP at 110 epoch is saved to best_coco/AP_epoch_110.pth. 2022/09/14 05:07:32 - mmengine - INFO - Epoch(train) [111][50/293] lr: 5.000000e-04 eta: 3:28:36 time: 0.495857 data_time: 0.080198 memory: 9871 loss_kpt: 0.000605 acc_pose: 0.757492 loss: 0.000605 2022/09/14 05:07:57 - mmengine - INFO - Epoch(train) [111][100/293] lr: 5.000000e-04 eta: 3:28:18 time: 0.501614 data_time: 0.072721 memory: 9871 loss_kpt: 0.000586 acc_pose: 0.818103 loss: 0.000586 2022/09/14 05:08:22 - mmengine - INFO - Epoch(train) [111][150/293] lr: 5.000000e-04 eta: 3:28:00 time: 0.500817 data_time: 0.076698 memory: 9871 loss_kpt: 0.000587 acc_pose: 0.813819 loss: 0.000587 2022/09/14 05:08:47 - mmengine - INFO - Epoch(train) [111][200/293] lr: 5.000000e-04 eta: 3:27:42 time: 0.499947 data_time: 0.074779 memory: 9871 loss_kpt: 0.000599 acc_pose: 0.795036 loss: 0.000599 2022/09/14 05:09:13 - mmengine - INFO - Epoch(train) [111][250/293] lr: 5.000000e-04 eta: 3:27:24 time: 0.505314 data_time: 0.071859 memory: 9871 loss_kpt: 0.000602 acc_pose: 0.809320 loss: 0.000602 2022/09/14 05:09:34 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 05:09:34 - mmengine - INFO - Saving checkpoint at 111 epochs 2022/09/14 05:10:03 - mmengine - INFO - Epoch(train) [112][50/293] lr: 5.000000e-04 eta: 3:26:32 time: 0.517519 data_time: 0.084787 memory: 9871 loss_kpt: 0.000592 acc_pose: 0.854236 loss: 0.000592 2022/09/14 05:10:28 - mmengine - INFO - Epoch(train) [112][100/293] lr: 5.000000e-04 eta: 3:26:14 time: 0.505632 data_time: 0.080517 memory: 9871 loss_kpt: 0.000577 acc_pose: 0.823178 loss: 0.000577 2022/09/14 05:10:53 - mmengine - INFO - Epoch(train) [112][150/293] lr: 5.000000e-04 eta: 3:25:55 time: 0.499813 data_time: 0.073111 memory: 9871 loss_kpt: 0.000584 acc_pose: 0.830535 loss: 0.000584 2022/09/14 05:11:18 - mmengine - INFO - Epoch(train) [112][200/293] lr: 5.000000e-04 eta: 3:25:37 time: 0.495474 data_time: 0.077173 memory: 9871 loss_kpt: 0.000602 acc_pose: 0.868110 loss: 0.000602 2022/09/14 05:11:42 - mmengine - INFO - Epoch(train) [112][250/293] lr: 5.000000e-04 eta: 3:25:18 time: 0.489310 data_time: 0.072882 memory: 9871 loss_kpt: 0.000590 acc_pose: 0.815286 loss: 0.000590 2022/09/14 05:12:04 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 05:12:04 - mmengine - INFO - Saving checkpoint at 112 epochs 2022/09/14 05:12:33 - mmengine - INFO - Epoch(train) [113][50/293] lr: 5.000000e-04 eta: 3:24:26 time: 0.512606 data_time: 0.083470 memory: 9871 loss_kpt: 0.000581 acc_pose: 0.829113 loss: 0.000581 2022/09/14 05:12:57 - mmengine - INFO - Epoch(train) [113][100/293] lr: 5.000000e-04 eta: 3:24:08 time: 0.496087 data_time: 0.085523 memory: 9871 loss_kpt: 0.000588 acc_pose: 0.802762 loss: 0.000588 2022/09/14 05:13:22 - mmengine - INFO - Epoch(train) [113][150/293] lr: 5.000000e-04 eta: 3:23:49 time: 0.496700 data_time: 0.075281 memory: 9871 loss_kpt: 0.000591 acc_pose: 0.791385 loss: 0.000591 2022/09/14 05:13:39 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 05:13:47 - mmengine - INFO - Epoch(train) [113][200/293] lr: 5.000000e-04 eta: 3:23:30 time: 0.488480 data_time: 0.075435 memory: 9871 loss_kpt: 0.000598 acc_pose: 0.819311 loss: 0.000598 2022/09/14 05:14:12 - mmengine - INFO - Epoch(train) [113][250/293] lr: 5.000000e-04 eta: 3:23:12 time: 0.498121 data_time: 0.070821 memory: 9871 loss_kpt: 0.000609 acc_pose: 0.878931 loss: 0.000609 2022/09/14 05:14:33 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 05:14:33 - mmengine - INFO - Saving checkpoint at 113 epochs 2022/09/14 05:15:01 - mmengine - INFO - Epoch(train) [114][50/293] lr: 5.000000e-04 eta: 3:22:20 time: 0.506983 data_time: 0.089850 memory: 9871 loss_kpt: 0.000586 acc_pose: 0.860970 loss: 0.000586 2022/09/14 05:15:25 - mmengine - INFO - Epoch(train) [114][100/293] lr: 5.000000e-04 eta: 3:22:01 time: 0.482444 data_time: 0.076257 memory: 9871 loss_kpt: 0.000597 acc_pose: 0.824978 loss: 0.000597 2022/09/14 05:15:50 - mmengine - INFO - Epoch(train) [114][150/293] lr: 5.000000e-04 eta: 3:21:42 time: 0.497816 data_time: 0.072723 memory: 9871 loss_kpt: 0.000584 acc_pose: 0.806154 loss: 0.000584 2022/09/14 05:16:15 - mmengine - INFO - Epoch(train) [114][200/293] lr: 5.000000e-04 eta: 3:21:24 time: 0.500828 data_time: 0.081907 memory: 9871 loss_kpt: 0.000592 acc_pose: 0.838737 loss: 0.000592 2022/09/14 05:16:40 - mmengine - INFO - Epoch(train) [114][250/293] lr: 5.000000e-04 eta: 3:21:05 time: 0.492605 data_time: 0.077389 memory: 9871 loss_kpt: 0.000591 acc_pose: 0.879283 loss: 0.000591 2022/09/14 05:17:01 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 05:17:01 - mmengine - INFO - Saving checkpoint at 114 epochs 2022/09/14 05:17:30 - mmengine - INFO - Epoch(train) [115][50/293] lr: 5.000000e-04 eta: 3:20:13 time: 0.507673 data_time: 0.087617 memory: 9871 loss_kpt: 0.000593 acc_pose: 0.834763 loss: 0.000593 2022/09/14 05:17:55 - mmengine - INFO - Epoch(train) [115][100/293] lr: 5.000000e-04 eta: 3:19:55 time: 0.496668 data_time: 0.073526 memory: 9871 loss_kpt: 0.000589 acc_pose: 0.811581 loss: 0.000589 2022/09/14 05:18:19 - mmengine - INFO - Epoch(train) [115][150/293] lr: 5.000000e-04 eta: 3:19:36 time: 0.490408 data_time: 0.079657 memory: 9871 loss_kpt: 0.000589 acc_pose: 0.766433 loss: 0.000589 2022/09/14 05:18:44 - mmengine - INFO - Epoch(train) [115][200/293] lr: 5.000000e-04 eta: 3:19:17 time: 0.499823 data_time: 0.074797 memory: 9871 loss_kpt: 0.000586 acc_pose: 0.819878 loss: 0.000586 2022/09/14 05:19:10 - mmengine - INFO - Epoch(train) [115][250/293] lr: 5.000000e-04 eta: 3:18:59 time: 0.506947 data_time: 0.082270 memory: 9871 loss_kpt: 0.000584 acc_pose: 0.838870 loss: 0.000584 2022/09/14 05:19:30 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 05:19:30 - mmengine - INFO - Saving checkpoint at 115 epochs 2022/09/14 05:20:00 - mmengine - INFO - Epoch(train) [116][50/293] lr: 5.000000e-04 eta: 3:18:08 time: 0.524714 data_time: 0.083385 memory: 9871 loss_kpt: 0.000592 acc_pose: 0.816375 loss: 0.000592 2022/09/14 05:20:25 - mmengine - INFO - Epoch(train) [116][100/293] lr: 5.000000e-04 eta: 3:17:50 time: 0.505525 data_time: 0.085464 memory: 9871 loss_kpt: 0.000586 acc_pose: 0.797319 loss: 0.000586 2022/09/14 05:20:50 - mmengine - INFO - Epoch(train) [116][150/293] lr: 5.000000e-04 eta: 3:17:31 time: 0.491755 data_time: 0.076724 memory: 9871 loss_kpt: 0.000586 acc_pose: 0.859380 loss: 0.000586 2022/09/14 05:21:15 - mmengine - INFO - Epoch(train) [116][200/293] lr: 5.000000e-04 eta: 3:17:13 time: 0.499139 data_time: 0.075930 memory: 9871 loss_kpt: 0.000578 acc_pose: 0.828670 loss: 0.000578 2022/09/14 05:21:39 - mmengine - INFO - Epoch(train) [116][250/293] lr: 5.000000e-04 eta: 3:16:54 time: 0.495380 data_time: 0.073071 memory: 9871 loss_kpt: 0.000586 acc_pose: 0.877993 loss: 0.000586 2022/09/14 05:22:01 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 05:22:01 - mmengine - INFO - Saving checkpoint at 116 epochs 2022/09/14 05:22:11 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 05:22:30 - mmengine - INFO - Epoch(train) [117][50/293] lr: 5.000000e-04 eta: 3:16:03 time: 0.521582 data_time: 0.090521 memory: 9871 loss_kpt: 0.000575 acc_pose: 0.830993 loss: 0.000575 2022/09/14 05:22:55 - mmengine - INFO - Epoch(train) [117][100/293] lr: 5.000000e-04 eta: 3:15:45 time: 0.501929 data_time: 0.072067 memory: 9871 loss_kpt: 0.000601 acc_pose: 0.844066 loss: 0.000601 2022/09/14 05:23:20 - mmengine - INFO - Epoch(train) [117][150/293] lr: 5.000000e-04 eta: 3:15:26 time: 0.491527 data_time: 0.071816 memory: 9871 loss_kpt: 0.000605 acc_pose: 0.831673 loss: 0.000605 2022/09/14 05:23:44 - mmengine - INFO - Epoch(train) [117][200/293] lr: 5.000000e-04 eta: 3:15:07 time: 0.495296 data_time: 0.071880 memory: 9871 loss_kpt: 0.000592 acc_pose: 0.811605 loss: 0.000592 2022/09/14 05:24:09 - mmengine - INFO - Epoch(train) [117][250/293] lr: 5.000000e-04 eta: 3:14:49 time: 0.498777 data_time: 0.076477 memory: 9871 loss_kpt: 0.000592 acc_pose: 0.802556 loss: 0.000592 2022/09/14 05:24:30 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 05:24:31 - mmengine - INFO - Saving checkpoint at 117 epochs 2022/09/14 05:25:01 - mmengine - INFO - Epoch(train) [118][50/293] lr: 5.000000e-04 eta: 3:13:58 time: 0.527334 data_time: 0.091439 memory: 9871 loss_kpt: 0.000572 acc_pose: 0.832777 loss: 0.000572 2022/09/14 05:25:26 - mmengine - INFO - Epoch(train) [118][100/293] lr: 5.000000e-04 eta: 3:13:39 time: 0.499445 data_time: 0.075505 memory: 9871 loss_kpt: 0.000593 acc_pose: 0.875017 loss: 0.000593 2022/09/14 05:25:51 - mmengine - INFO - Epoch(train) [118][150/293] lr: 5.000000e-04 eta: 3:13:21 time: 0.491250 data_time: 0.076454 memory: 9871 loss_kpt: 0.000580 acc_pose: 0.808807 loss: 0.000580 2022/09/14 05:26:16 - mmengine - INFO - Epoch(train) [118][200/293] lr: 5.000000e-04 eta: 3:13:02 time: 0.499595 data_time: 0.074650 memory: 9871 loss_kpt: 0.000602 acc_pose: 0.783378 loss: 0.000602 2022/09/14 05:26:41 - mmengine - INFO - Epoch(train) [118][250/293] lr: 5.000000e-04 eta: 3:12:43 time: 0.499844 data_time: 0.070245 memory: 9871 loss_kpt: 0.000595 acc_pose: 0.835873 loss: 0.000595 2022/09/14 05:27:02 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 05:27:02 - mmengine - INFO - Saving checkpoint at 118 epochs 2022/09/14 05:27:32 - mmengine - INFO - Epoch(train) [119][50/293] lr: 5.000000e-04 eta: 3:11:53 time: 0.528015 data_time: 0.106954 memory: 9871 loss_kpt: 0.000594 acc_pose: 0.859305 loss: 0.000594 2022/09/14 05:27:57 - mmengine - INFO - Epoch(train) [119][100/293] lr: 5.000000e-04 eta: 3:11:34 time: 0.494354 data_time: 0.076629 memory: 9871 loss_kpt: 0.000589 acc_pose: 0.838926 loss: 0.000589 2022/09/14 05:28:22 - mmengine - INFO - Epoch(train) [119][150/293] lr: 5.000000e-04 eta: 3:11:16 time: 0.502055 data_time: 0.080160 memory: 9871 loss_kpt: 0.000591 acc_pose: 0.813667 loss: 0.000591 2022/09/14 05:28:47 - mmengine - INFO - Epoch(train) [119][200/293] lr: 5.000000e-04 eta: 3:10:57 time: 0.500797 data_time: 0.075259 memory: 9871 loss_kpt: 0.000584 acc_pose: 0.825092 loss: 0.000584 2022/09/14 05:29:12 - mmengine - INFO - Epoch(train) [119][250/293] lr: 5.000000e-04 eta: 3:10:39 time: 0.503932 data_time: 0.079027 memory: 9871 loss_kpt: 0.000596 acc_pose: 0.843446 loss: 0.000596 2022/09/14 05:29:33 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 05:29:33 - mmengine - INFO - Saving checkpoint at 119 epochs 2022/09/14 05:30:03 - mmengine - INFO - Epoch(train) [120][50/293] lr: 5.000000e-04 eta: 3:09:48 time: 0.520914 data_time: 0.085824 memory: 9871 loss_kpt: 0.000588 acc_pose: 0.828656 loss: 0.000588 2022/09/14 05:30:28 - mmengine - INFO - Epoch(train) [120][100/293] lr: 5.000000e-04 eta: 3:09:30 time: 0.507189 data_time: 0.078794 memory: 9871 loss_kpt: 0.000606 acc_pose: 0.852607 loss: 0.000606 2022/09/14 05:30:44 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 05:30:53 - mmengine - INFO - Epoch(train) [120][150/293] lr: 5.000000e-04 eta: 3:09:11 time: 0.494642 data_time: 0.074097 memory: 9871 loss_kpt: 0.000580 acc_pose: 0.828182 loss: 0.000580 2022/09/14 05:31:18 - mmengine - INFO - Epoch(train) [120][200/293] lr: 5.000000e-04 eta: 3:08:52 time: 0.500087 data_time: 0.074770 memory: 9871 loss_kpt: 0.000578 acc_pose: 0.839647 loss: 0.000578 2022/09/14 05:31:43 - mmengine - INFO - Epoch(train) [120][250/293] lr: 5.000000e-04 eta: 3:08:34 time: 0.502661 data_time: 0.079728 memory: 9871 loss_kpt: 0.000599 acc_pose: 0.853414 loss: 0.000599 2022/09/14 05:32:04 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 05:32:04 - mmengine - INFO - Saving checkpoint at 120 epochs 2022/09/14 05:32:15 - mmengine - INFO - Epoch(val) [120][50/407] eta: 0:00:49 time: 0.139275 data_time: 0.013503 memory: 9871 2022/09/14 05:32:21 - mmengine - INFO - Epoch(val) [120][100/407] eta: 0:00:39 time: 0.129317 data_time: 0.008701 memory: 920 2022/09/14 05:32:28 - mmengine - INFO - Epoch(val) [120][150/407] eta: 0:00:33 time: 0.129928 data_time: 0.008858 memory: 920 2022/09/14 05:32:34 - mmengine - INFO - Epoch(val) [120][200/407] eta: 0:00:27 time: 0.131100 data_time: 0.009061 memory: 920 2022/09/14 05:32:41 - mmengine - INFO - Epoch(val) [120][250/407] eta: 0:00:21 time: 0.135707 data_time: 0.012761 memory: 920 2022/09/14 05:32:48 - mmengine - INFO - Epoch(val) [120][300/407] eta: 0:00:14 time: 0.132000 data_time: 0.011756 memory: 920 2022/09/14 05:32:54 - mmengine - INFO - Epoch(val) [120][350/407] eta: 0:00:07 time: 0.133022 data_time: 0.008800 memory: 920 2022/09/14 05:33:01 - mmengine - INFO - Epoch(val) [120][400/407] eta: 0:00:00 time: 0.126206 data_time: 0.007837 memory: 920 2022/09/14 05:33:37 - mmengine - INFO - Evaluating CocoMetric... 2022/09/14 05:33:51 - mmengine - INFO - Epoch(val) [120][407/407] coco/AP: 0.742308 coco/AP .5: 0.898377 coco/AP .75: 0.810525 coco/AP (M): 0.704085 coco/AP (L): 0.813296 coco/AR: 0.794049 coco/AR .5: 0.938445 coco/AR .75: 0.855164 coco/AR (M): 0.749795 coco/AR (L): 0.858268 2022/09/14 05:33:51 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220914/udp_w32_256_v1/best_coco/AP_epoch_110.pth is removed 2022/09/14 05:33:54 - mmengine - INFO - The best checkpoint with 0.7423 coco/AP at 120 epoch is saved to best_coco/AP_epoch_120.pth. 2022/09/14 05:34:19 - mmengine - INFO - Epoch(train) [121][50/293] lr: 5.000000e-04 eta: 3:07:43 time: 0.500272 data_time: 0.089271 memory: 9871 loss_kpt: 0.000591 acc_pose: 0.780037 loss: 0.000591 2022/09/14 05:34:44 - mmengine - INFO - Epoch(train) [121][100/293] lr: 5.000000e-04 eta: 3:07:24 time: 0.501128 data_time: 0.077650 memory: 9871 loss_kpt: 0.000578 acc_pose: 0.825287 loss: 0.000578 2022/09/14 05:35:09 - mmengine - INFO - Epoch(train) [121][150/293] lr: 5.000000e-04 eta: 3:07:05 time: 0.499446 data_time: 0.076367 memory: 9871 loss_kpt: 0.000586 acc_pose: 0.850406 loss: 0.000586 2022/09/14 05:35:34 - mmengine - INFO - Epoch(train) [121][200/293] lr: 5.000000e-04 eta: 3:06:47 time: 0.502633 data_time: 0.074415 memory: 9871 loss_kpt: 0.000586 acc_pose: 0.833948 loss: 0.000586 2022/09/14 05:35:59 - mmengine - INFO - Epoch(train) [121][250/293] lr: 5.000000e-04 eta: 3:06:28 time: 0.498109 data_time: 0.077066 memory: 9871 loss_kpt: 0.000603 acc_pose: 0.846015 loss: 0.000603 2022/09/14 05:36:20 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 05:36:20 - mmengine - INFO - Saving checkpoint at 121 epochs 2022/09/14 05:36:49 - mmengine - INFO - Epoch(train) [122][50/293] lr: 5.000000e-04 eta: 3:05:37 time: 0.500010 data_time: 0.080297 memory: 9871 loss_kpt: 0.000598 acc_pose: 0.823816 loss: 0.000598 2022/09/14 05:37:14 - mmengine - INFO - Epoch(train) [122][100/293] lr: 5.000000e-04 eta: 3:05:19 time: 0.515361 data_time: 0.080226 memory: 9871 loss_kpt: 0.000589 acc_pose: 0.814535 loss: 0.000589 2022/09/14 05:37:39 - mmengine - INFO - Epoch(train) [122][150/293] lr: 5.000000e-04 eta: 3:05:00 time: 0.499435 data_time: 0.077330 memory: 9871 loss_kpt: 0.000579 acc_pose: 0.816278 loss: 0.000579 2022/09/14 05:38:04 - mmengine - INFO - Epoch(train) [122][200/293] lr: 5.000000e-04 eta: 3:04:41 time: 0.492653 data_time: 0.076358 memory: 9871 loss_kpt: 0.000594 acc_pose: 0.833250 loss: 0.000594 2022/09/14 05:38:29 - mmengine - INFO - Epoch(train) [122][250/293] lr: 5.000000e-04 eta: 3:04:22 time: 0.493852 data_time: 0.081388 memory: 9871 loss_kpt: 0.000577 acc_pose: 0.810038 loss: 0.000577 2022/09/14 05:38:50 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 05:38:50 - mmengine - INFO - Saving checkpoint at 122 epochs 2022/09/14 05:39:18 - mmengine - INFO - Epoch(train) [123][50/293] lr: 5.000000e-04 eta: 3:03:31 time: 0.498222 data_time: 0.084601 memory: 9871 loss_kpt: 0.000590 acc_pose: 0.833381 loss: 0.000590 2022/09/14 05:39:43 - mmengine - INFO - Epoch(train) [123][100/293] lr: 5.000000e-04 eta: 3:03:13 time: 0.496168 data_time: 0.076181 memory: 9871 loss_kpt: 0.000572 acc_pose: 0.805768 loss: 0.000572 2022/09/14 05:40:08 - mmengine - INFO - Epoch(train) [123][150/293] lr: 5.000000e-04 eta: 3:02:54 time: 0.505782 data_time: 0.080657 memory: 9871 loss_kpt: 0.000582 acc_pose: 0.840565 loss: 0.000582 2022/09/14 05:40:33 - mmengine - INFO - Epoch(train) [123][200/293] lr: 5.000000e-04 eta: 3:02:35 time: 0.499934 data_time: 0.071842 memory: 9871 loss_kpt: 0.000581 acc_pose: 0.875830 loss: 0.000581 2022/09/14 05:40:57 - mmengine - INFO - Epoch(train) [123][250/293] lr: 5.000000e-04 eta: 3:02:16 time: 0.488761 data_time: 0.075997 memory: 9871 loss_kpt: 0.000589 acc_pose: 0.836238 loss: 0.000589 2022/09/14 05:40:59 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 05:41:18 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 05:41:18 - mmengine - INFO - Saving checkpoint at 123 epochs 2022/09/14 05:41:47 - mmengine - INFO - Epoch(train) [124][50/293] lr: 5.000000e-04 eta: 3:01:26 time: 0.507416 data_time: 0.081108 memory: 9871 loss_kpt: 0.000587 acc_pose: 0.801639 loss: 0.000587 2022/09/14 05:42:12 - mmengine - INFO - Epoch(train) [124][100/293] lr: 5.000000e-04 eta: 3:01:07 time: 0.497345 data_time: 0.078823 memory: 9871 loss_kpt: 0.000586 acc_pose: 0.810190 loss: 0.000586 2022/09/14 05:42:37 - mmengine - INFO - Epoch(train) [124][150/293] lr: 5.000000e-04 eta: 3:00:48 time: 0.501440 data_time: 0.073187 memory: 9871 loss_kpt: 0.000597 acc_pose: 0.867079 loss: 0.000597 2022/09/14 05:43:02 - mmengine - INFO - Epoch(train) [124][200/293] lr: 5.000000e-04 eta: 3:00:29 time: 0.496873 data_time: 0.076200 memory: 9871 loss_kpt: 0.000591 acc_pose: 0.852642 loss: 0.000591 2022/09/14 05:43:26 - mmengine - INFO - Epoch(train) [124][250/293] lr: 5.000000e-04 eta: 3:00:10 time: 0.490350 data_time: 0.071799 memory: 9871 loss_kpt: 0.000580 acc_pose: 0.824897 loss: 0.000580 2022/09/14 05:43:48 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 05:43:48 - mmengine - INFO - Saving checkpoint at 124 epochs 2022/09/14 05:44:17 - mmengine - INFO - Epoch(train) [125][50/293] lr: 5.000000e-04 eta: 2:59:20 time: 0.504339 data_time: 0.087000 memory: 9871 loss_kpt: 0.000584 acc_pose: 0.826238 loss: 0.000584 2022/09/14 05:44:41 - mmengine - INFO - Epoch(train) [125][100/293] lr: 5.000000e-04 eta: 2:59:01 time: 0.497042 data_time: 0.080684 memory: 9871 loss_kpt: 0.000568 acc_pose: 0.831851 loss: 0.000568 2022/09/14 05:45:06 - mmengine - INFO - Epoch(train) [125][150/293] lr: 5.000000e-04 eta: 2:58:42 time: 0.496562 data_time: 0.074724 memory: 9871 loss_kpt: 0.000575 acc_pose: 0.845690 loss: 0.000575 2022/09/14 05:45:31 - mmengine - INFO - Epoch(train) [125][200/293] lr: 5.000000e-04 eta: 2:58:23 time: 0.501477 data_time: 0.077865 memory: 9871 loss_kpt: 0.000588 acc_pose: 0.855272 loss: 0.000588 2022/09/14 05:45:57 - mmengine - INFO - Epoch(train) [125][250/293] lr: 5.000000e-04 eta: 2:58:04 time: 0.506261 data_time: 0.071304 memory: 9871 loss_kpt: 0.000602 acc_pose: 0.802304 loss: 0.000602 2022/09/14 05:46:18 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 05:46:18 - mmengine - INFO - Saving checkpoint at 125 epochs 2022/09/14 05:46:47 - mmengine - INFO - Epoch(train) [126][50/293] lr: 5.000000e-04 eta: 2:57:14 time: 0.506072 data_time: 0.087576 memory: 9871 loss_kpt: 0.000594 acc_pose: 0.838766 loss: 0.000594 2022/09/14 05:47:12 - mmengine - INFO - Epoch(train) [126][100/293] lr: 5.000000e-04 eta: 2:56:56 time: 0.503393 data_time: 0.072181 memory: 9871 loss_kpt: 0.000568 acc_pose: 0.811474 loss: 0.000568 2022/09/14 05:47:37 - mmengine - INFO - Epoch(train) [126][150/293] lr: 5.000000e-04 eta: 2:56:37 time: 0.506842 data_time: 0.080633 memory: 9871 loss_kpt: 0.000587 acc_pose: 0.843302 loss: 0.000587 2022/09/14 05:48:02 - mmengine - INFO - Epoch(train) [126][200/293] lr: 5.000000e-04 eta: 2:56:18 time: 0.497736 data_time: 0.076484 memory: 9871 loss_kpt: 0.000595 acc_pose: 0.810194 loss: 0.000595 2022/09/14 05:48:27 - mmengine - INFO - Epoch(train) [126][250/293] lr: 5.000000e-04 eta: 2:55:59 time: 0.495117 data_time: 0.077684 memory: 9871 loss_kpt: 0.000578 acc_pose: 0.869854 loss: 0.000578 2022/09/14 05:48:48 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 05:48:49 - mmengine - INFO - Saving checkpoint at 126 epochs 2022/09/14 05:49:19 - mmengine - INFO - Epoch(train) [127][50/293] lr: 5.000000e-04 eta: 2:55:09 time: 0.512198 data_time: 0.083821 memory: 9871 loss_kpt: 0.000587 acc_pose: 0.809949 loss: 0.000587 2022/09/14 05:49:35 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 05:49:44 - mmengine - INFO - Epoch(train) [127][100/293] lr: 5.000000e-04 eta: 2:54:50 time: 0.499164 data_time: 0.078053 memory: 9871 loss_kpt: 0.000576 acc_pose: 0.846268 loss: 0.000576 2022/09/14 05:50:09 - mmengine - INFO - Epoch(train) [127][150/293] lr: 5.000000e-04 eta: 2:54:32 time: 0.506991 data_time: 0.075728 memory: 9871 loss_kpt: 0.000576 acc_pose: 0.797250 loss: 0.000576 2022/09/14 05:50:33 - mmengine - INFO - Epoch(train) [127][200/293] lr: 5.000000e-04 eta: 2:54:12 time: 0.487751 data_time: 0.074585 memory: 9871 loss_kpt: 0.000580 acc_pose: 0.850508 loss: 0.000580 2022/09/14 05:50:59 - mmengine - INFO - Epoch(train) [127][250/293] lr: 5.000000e-04 eta: 2:53:53 time: 0.512968 data_time: 0.072555 memory: 9871 loss_kpt: 0.000577 acc_pose: 0.810306 loss: 0.000577 2022/09/14 05:51:20 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 05:51:20 - mmengine - INFO - Saving checkpoint at 127 epochs 2022/09/14 05:51:49 - mmengine - INFO - Epoch(train) [128][50/293] lr: 5.000000e-04 eta: 2:53:04 time: 0.506464 data_time: 0.081798 memory: 9871 loss_kpt: 0.000578 acc_pose: 0.843593 loss: 0.000578 2022/09/14 05:52:14 - mmengine - INFO - Epoch(train) [128][100/293] lr: 5.000000e-04 eta: 2:52:46 time: 0.516990 data_time: 0.082735 memory: 9871 loss_kpt: 0.000593 acc_pose: 0.839250 loss: 0.000593 2022/09/14 05:52:39 - mmengine - INFO - Epoch(train) [128][150/293] lr: 5.000000e-04 eta: 2:52:26 time: 0.493421 data_time: 0.074306 memory: 9871 loss_kpt: 0.000586 acc_pose: 0.819715 loss: 0.000586 2022/09/14 05:53:04 - mmengine - INFO - Epoch(train) [128][200/293] lr: 5.000000e-04 eta: 2:52:07 time: 0.498826 data_time: 0.080455 memory: 9871 loss_kpt: 0.000577 acc_pose: 0.870979 loss: 0.000577 2022/09/14 05:53:29 - mmengine - INFO - Epoch(train) [128][250/293] lr: 5.000000e-04 eta: 2:51:48 time: 0.501535 data_time: 0.078660 memory: 9871 loss_kpt: 0.000581 acc_pose: 0.810910 loss: 0.000581 2022/09/14 05:53:50 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 05:53:50 - mmengine - INFO - Saving checkpoint at 128 epochs 2022/09/14 05:54:20 - mmengine - INFO - Epoch(train) [129][50/293] lr: 5.000000e-04 eta: 2:51:00 time: 0.538584 data_time: 0.103860 memory: 9871 loss_kpt: 0.000572 acc_pose: 0.801044 loss: 0.000572 2022/09/14 05:54:46 - mmengine - INFO - Epoch(train) [129][100/293] lr: 5.000000e-04 eta: 2:50:41 time: 0.506973 data_time: 0.071864 memory: 9871 loss_kpt: 0.000599 acc_pose: 0.788402 loss: 0.000599 2022/09/14 05:55:11 - mmengine - INFO - Epoch(train) [129][150/293] lr: 5.000000e-04 eta: 2:50:23 time: 0.515134 data_time: 0.082205 memory: 9871 loss_kpt: 0.000582 acc_pose: 0.830912 loss: 0.000582 2022/09/14 05:55:36 - mmengine - INFO - Epoch(train) [129][200/293] lr: 5.000000e-04 eta: 2:50:03 time: 0.488774 data_time: 0.072610 memory: 9871 loss_kpt: 0.000596 acc_pose: 0.827448 loss: 0.000596 2022/09/14 05:56:01 - mmengine - INFO - Epoch(train) [129][250/293] lr: 5.000000e-04 eta: 2:49:44 time: 0.498809 data_time: 0.074726 memory: 9871 loss_kpt: 0.000582 acc_pose: 0.792840 loss: 0.000582 2022/09/14 05:56:23 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 05:56:23 - mmengine - INFO - Saving checkpoint at 129 epochs 2022/09/14 05:56:51 - mmengine - INFO - Epoch(train) [130][50/293] lr: 5.000000e-04 eta: 2:48:55 time: 0.511971 data_time: 0.082207 memory: 9871 loss_kpt: 0.000597 acc_pose: 0.790257 loss: 0.000597 2022/09/14 05:57:17 - mmengine - INFO - Epoch(train) [130][100/293] lr: 5.000000e-04 eta: 2:48:37 time: 0.516054 data_time: 0.078717 memory: 9871 loss_kpt: 0.000588 acc_pose: 0.820648 loss: 0.000588 2022/09/14 05:57:43 - mmengine - INFO - Epoch(train) [130][150/293] lr: 5.000000e-04 eta: 2:48:18 time: 0.513924 data_time: 0.077580 memory: 9871 loss_kpt: 0.000583 acc_pose: 0.841415 loss: 0.000583 2022/09/14 05:58:08 - mmengine - INFO - Epoch(train) [130][200/293] lr: 5.000000e-04 eta: 2:47:59 time: 0.504031 data_time: 0.070296 memory: 9871 loss_kpt: 0.000598 acc_pose: 0.830011 loss: 0.000598 2022/09/14 05:58:10 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 05:58:33 - mmengine - INFO - Epoch(train) [130][250/293] lr: 5.000000e-04 eta: 2:47:40 time: 0.504418 data_time: 0.072844 memory: 9871 loss_kpt: 0.000576 acc_pose: 0.808814 loss: 0.000576 2022/09/14 05:58:55 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 05:58:55 - mmengine - INFO - Saving checkpoint at 130 epochs 2022/09/14 05:59:05 - mmengine - INFO - Epoch(val) [130][50/407] eta: 0:00:50 time: 0.141757 data_time: 0.018278 memory: 9871 2022/09/14 05:59:12 - mmengine - INFO - Epoch(val) [130][100/407] eta: 0:00:41 time: 0.136616 data_time: 0.013397 memory: 920 2022/09/14 05:59:18 - mmengine - INFO - Epoch(val) [130][150/407] eta: 0:00:33 time: 0.129346 data_time: 0.008593 memory: 920 2022/09/14 05:59:25 - mmengine - INFO - Epoch(val) [130][200/407] eta: 0:00:26 time: 0.129233 data_time: 0.008123 memory: 920 2022/09/14 05:59:32 - mmengine - INFO - Epoch(val) [130][250/407] eta: 0:00:20 time: 0.133605 data_time: 0.008698 memory: 920 2022/09/14 05:59:38 - mmengine - INFO - Epoch(val) [130][300/407] eta: 0:00:13 time: 0.129687 data_time: 0.008362 memory: 920 2022/09/14 05:59:46 - mmengine - INFO - Epoch(val) [130][350/407] eta: 0:00:08 time: 0.156079 data_time: 0.035387 memory: 920 2022/09/14 05:59:55 - mmengine - INFO - Epoch(val) [130][400/407] eta: 0:00:01 time: 0.179010 data_time: 0.053200 memory: 920 2022/09/14 06:00:33 - mmengine - INFO - Evaluating CocoMetric... 2022/09/14 06:00:48 - mmengine - INFO - Epoch(val) [130][407/407] coco/AP: 0.744622 coco/AP .5: 0.897774 coco/AP .75: 0.813133 coco/AP (M): 0.708129 coco/AP (L): 0.813925 coco/AR: 0.797182 coco/AR .5: 0.937028 coco/AR .75: 0.859414 coco/AR (M): 0.754603 coco/AR (L): 0.858974 2022/09/14 06:00:48 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220914/udp_w32_256_v1/best_coco/AP_epoch_120.pth is removed 2022/09/14 06:00:50 - mmengine - INFO - The best checkpoint with 0.7446 coco/AP at 130 epoch is saved to best_coco/AP_epoch_130.pth. 2022/09/14 06:01:16 - mmengine - INFO - Epoch(train) [131][50/293] lr: 5.000000e-04 eta: 2:46:51 time: 0.518765 data_time: 0.078850 memory: 9871 loss_kpt: 0.000575 acc_pose: 0.831477 loss: 0.000575 2022/09/14 06:01:42 - mmengine - INFO - Epoch(train) [131][100/293] lr: 5.000000e-04 eta: 2:46:33 time: 0.520442 data_time: 0.076798 memory: 9871 loss_kpt: 0.000581 acc_pose: 0.828559 loss: 0.000581 2022/09/14 06:02:08 - mmengine - INFO - Epoch(train) [131][150/293] lr: 5.000000e-04 eta: 2:46:14 time: 0.507962 data_time: 0.080848 memory: 9871 loss_kpt: 0.000577 acc_pose: 0.817352 loss: 0.000577 2022/09/14 06:02:33 - mmengine - INFO - Epoch(train) [131][200/293] lr: 5.000000e-04 eta: 2:45:55 time: 0.503068 data_time: 0.079083 memory: 9871 loss_kpt: 0.000582 acc_pose: 0.825125 loss: 0.000582 2022/09/14 06:02:58 - mmengine - INFO - Epoch(train) [131][250/293] lr: 5.000000e-04 eta: 2:45:35 time: 0.496497 data_time: 0.076418 memory: 9871 loss_kpt: 0.000577 acc_pose: 0.807562 loss: 0.000577 2022/09/14 06:03:20 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 06:03:20 - mmengine - INFO - Saving checkpoint at 131 epochs 2022/09/14 06:03:48 - mmengine - INFO - Epoch(train) [132][50/293] lr: 5.000000e-04 eta: 2:44:47 time: 0.506754 data_time: 0.083449 memory: 9871 loss_kpt: 0.000571 acc_pose: 0.821251 loss: 0.000571 2022/09/14 06:04:14 - mmengine - INFO - Epoch(train) [132][100/293] lr: 5.000000e-04 eta: 2:44:28 time: 0.506723 data_time: 0.083914 memory: 9871 loss_kpt: 0.000589 acc_pose: 0.809222 loss: 0.000589 2022/09/14 06:04:41 - mmengine - INFO - Epoch(train) [132][150/293] lr: 5.000000e-04 eta: 2:44:10 time: 0.551122 data_time: 0.084102 memory: 9871 loss_kpt: 0.000585 acc_pose: 0.844731 loss: 0.000585 2022/09/14 06:05:08 - mmengine - INFO - Epoch(train) [132][200/293] lr: 5.000000e-04 eta: 2:43:52 time: 0.533771 data_time: 0.080718 memory: 9871 loss_kpt: 0.000565 acc_pose: 0.856642 loss: 0.000565 2022/09/14 06:05:33 - mmengine - INFO - Epoch(train) [132][250/293] lr: 5.000000e-04 eta: 2:43:32 time: 0.501137 data_time: 0.076492 memory: 9871 loss_kpt: 0.000583 acc_pose: 0.867707 loss: 0.000583 2022/09/14 06:05:54 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 06:05:54 - mmengine - INFO - Saving checkpoint at 132 epochs 2022/09/14 06:06:25 - mmengine - INFO - Epoch(train) [133][50/293] lr: 5.000000e-04 eta: 2:42:45 time: 0.528118 data_time: 0.094168 memory: 9871 loss_kpt: 0.000574 acc_pose: 0.829687 loss: 0.000574 2022/09/14 06:06:54 - mmengine - INFO - Epoch(train) [133][100/293] lr: 5.000000e-04 eta: 2:42:28 time: 0.588763 data_time: 0.082773 memory: 9871 loss_kpt: 0.000589 acc_pose: 0.820571 loss: 0.000589 2022/09/14 06:07:20 - mmengine - INFO - Epoch(train) [133][150/293] lr: 5.000000e-04 eta: 2:42:09 time: 0.510200 data_time: 0.082035 memory: 9871 loss_kpt: 0.000570 acc_pose: 0.769526 loss: 0.000570 2022/09/14 06:07:45 - mmengine - INFO - Epoch(train) [133][200/293] lr: 5.000000e-04 eta: 2:41:49 time: 0.501136 data_time: 0.077331 memory: 9871 loss_kpt: 0.000558 acc_pose: 0.868184 loss: 0.000558 2022/09/14 06:08:10 - mmengine - INFO - Epoch(train) [133][250/293] lr: 5.000000e-04 eta: 2:41:30 time: 0.496398 data_time: 0.077047 memory: 9871 loss_kpt: 0.000580 acc_pose: 0.789344 loss: 0.000580 2022/09/14 06:08:30 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 06:08:30 - mmengine - INFO - Saving checkpoint at 133 epochs 2022/09/14 06:08:50 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 06:09:00 - mmengine - INFO - Epoch(train) [134][50/293] lr: 5.000000e-04 eta: 2:40:42 time: 0.513316 data_time: 0.083610 memory: 9871 loss_kpt: 0.000575 acc_pose: 0.817696 loss: 0.000575 2022/09/14 06:09:25 - mmengine - INFO - Epoch(train) [134][100/293] lr: 5.000000e-04 eta: 2:40:23 time: 0.508411 data_time: 0.070910 memory: 9871 loss_kpt: 0.000574 acc_pose: 0.795765 loss: 0.000574 2022/09/14 06:09:50 - mmengine - INFO - Epoch(train) [134][150/293] lr: 5.000000e-04 eta: 2:40:03 time: 0.500408 data_time: 0.077980 memory: 9871 loss_kpt: 0.000579 acc_pose: 0.847670 loss: 0.000579 2022/09/14 06:10:16 - mmengine - INFO - Epoch(train) [134][200/293] lr: 5.000000e-04 eta: 2:39:45 time: 0.518439 data_time: 0.082310 memory: 9871 loss_kpt: 0.000592 acc_pose: 0.839255 loss: 0.000592 2022/09/14 06:10:42 - mmengine - INFO - Epoch(train) [134][250/293] lr: 5.000000e-04 eta: 2:39:26 time: 0.530184 data_time: 0.076370 memory: 9871 loss_kpt: 0.000581 acc_pose: 0.827411 loss: 0.000581 2022/09/14 06:11:04 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 06:11:04 - mmengine - INFO - Saving checkpoint at 134 epochs 2022/09/14 06:11:33 - mmengine - INFO - Epoch(train) [135][50/293] lr: 5.000000e-04 eta: 2:38:38 time: 0.516806 data_time: 0.078565 memory: 9871 loss_kpt: 0.000580 acc_pose: 0.845381 loss: 0.000580 2022/09/14 06:11:59 - mmengine - INFO - Epoch(train) [135][100/293] lr: 5.000000e-04 eta: 2:38:19 time: 0.512118 data_time: 0.073329 memory: 9871 loss_kpt: 0.000582 acc_pose: 0.813300 loss: 0.000582 2022/09/14 06:12:23 - mmengine - INFO - Epoch(train) [135][150/293] lr: 5.000000e-04 eta: 2:38:00 time: 0.494603 data_time: 0.077621 memory: 9871 loss_kpt: 0.000583 acc_pose: 0.818440 loss: 0.000583 2022/09/14 06:12:48 - mmengine - INFO - Epoch(train) [135][200/293] lr: 5.000000e-04 eta: 2:37:40 time: 0.496819 data_time: 0.072891 memory: 9871 loss_kpt: 0.000580 acc_pose: 0.824869 loss: 0.000580 2022/09/14 06:13:13 - mmengine - INFO - Epoch(train) [135][250/293] lr: 5.000000e-04 eta: 2:37:21 time: 0.498943 data_time: 0.074790 memory: 9871 loss_kpt: 0.000580 acc_pose: 0.828544 loss: 0.000580 2022/09/14 06:13:35 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 06:13:35 - mmengine - INFO - Saving checkpoint at 135 epochs 2022/09/14 06:14:03 - mmengine - INFO - Epoch(train) [136][50/293] lr: 5.000000e-04 eta: 2:36:33 time: 0.504475 data_time: 0.080514 memory: 9871 loss_kpt: 0.000584 acc_pose: 0.835010 loss: 0.000584 2022/09/14 06:14:29 - mmengine - INFO - Epoch(train) [136][100/293] lr: 5.000000e-04 eta: 2:36:13 time: 0.510000 data_time: 0.077032 memory: 9871 loss_kpt: 0.000566 acc_pose: 0.827809 loss: 0.000566 2022/09/14 06:14:54 - mmengine - INFO - Epoch(train) [136][150/293] lr: 5.000000e-04 eta: 2:35:54 time: 0.498749 data_time: 0.079496 memory: 9871 loss_kpt: 0.000576 acc_pose: 0.835473 loss: 0.000576 2022/09/14 06:15:19 - mmengine - INFO - Epoch(train) [136][200/293] lr: 5.000000e-04 eta: 2:35:34 time: 0.499240 data_time: 0.083745 memory: 9871 loss_kpt: 0.000568 acc_pose: 0.832049 loss: 0.000568 2022/09/14 06:15:44 - mmengine - INFO - Epoch(train) [136][250/293] lr: 5.000000e-04 eta: 2:35:15 time: 0.505961 data_time: 0.077948 memory: 9871 loss_kpt: 0.000576 acc_pose: 0.821856 loss: 0.000576 2022/09/14 06:16:08 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 06:16:08 - mmengine - INFO - Saving checkpoint at 136 epochs 2022/09/14 06:16:36 - mmengine - INFO - Epoch(train) [137][50/293] lr: 5.000000e-04 eta: 2:34:27 time: 0.508991 data_time: 0.091572 memory: 9871 loss_kpt: 0.000578 acc_pose: 0.821218 loss: 0.000578 2022/09/14 06:17:01 - mmengine - INFO - Epoch(train) [137][100/293] lr: 5.000000e-04 eta: 2:34:08 time: 0.499358 data_time: 0.079414 memory: 9871 loss_kpt: 0.000571 acc_pose: 0.847829 loss: 0.000571 2022/09/14 06:17:26 - mmengine - INFO - Epoch(train) [137][150/293] lr: 5.000000e-04 eta: 2:33:48 time: 0.493881 data_time: 0.077561 memory: 9871 loss_kpt: 0.000581 acc_pose: 0.838325 loss: 0.000581 2022/09/14 06:17:27 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 06:17:51 - mmengine - INFO - Epoch(train) [137][200/293] lr: 5.000000e-04 eta: 2:33:29 time: 0.508526 data_time: 0.081488 memory: 9871 loss_kpt: 0.000576 acc_pose: 0.825456 loss: 0.000576 2022/09/14 06:18:17 - mmengine - INFO - Epoch(train) [137][250/293] lr: 5.000000e-04 eta: 2:33:10 time: 0.509935 data_time: 0.087254 memory: 9871 loss_kpt: 0.000576 acc_pose: 0.866745 loss: 0.000576 2022/09/14 06:18:40 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 06:18:40 - mmengine - INFO - Saving checkpoint at 137 epochs 2022/09/14 06:19:09 - mmengine - INFO - Epoch(train) [138][50/293] lr: 5.000000e-04 eta: 2:32:22 time: 0.509908 data_time: 0.086840 memory: 9871 loss_kpt: 0.000589 acc_pose: 0.835759 loss: 0.000589 2022/09/14 06:19:34 - mmengine - INFO - Epoch(train) [138][100/293] lr: 5.000000e-04 eta: 2:32:03 time: 0.499258 data_time: 0.072235 memory: 9871 loss_kpt: 0.000573 acc_pose: 0.835774 loss: 0.000573 2022/09/14 06:19:58 - mmengine - INFO - Epoch(train) [138][150/293] lr: 5.000000e-04 eta: 2:31:43 time: 0.495775 data_time: 0.071347 memory: 9871 loss_kpt: 0.000587 acc_pose: 0.829632 loss: 0.000587 2022/09/14 06:20:23 - mmengine - INFO - Epoch(train) [138][200/293] lr: 5.000000e-04 eta: 2:31:23 time: 0.501075 data_time: 0.075212 memory: 9871 loss_kpt: 0.000583 acc_pose: 0.847353 loss: 0.000583 2022/09/14 06:20:48 - mmengine - INFO - Epoch(train) [138][250/293] lr: 5.000000e-04 eta: 2:31:04 time: 0.498205 data_time: 0.075724 memory: 9871 loss_kpt: 0.000589 acc_pose: 0.834969 loss: 0.000589 2022/09/14 06:21:09 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 06:21:09 - mmengine - INFO - Saving checkpoint at 138 epochs 2022/09/14 06:21:38 - mmengine - INFO - Epoch(train) [139][50/293] lr: 5.000000e-04 eta: 2:30:16 time: 0.505754 data_time: 0.085357 memory: 9871 loss_kpt: 0.000579 acc_pose: 0.829856 loss: 0.000579 2022/09/14 06:22:03 - mmengine - INFO - Epoch(train) [139][100/293] lr: 5.000000e-04 eta: 2:29:57 time: 0.499026 data_time: 0.071116 memory: 9871 loss_kpt: 0.000558 acc_pose: 0.792343 loss: 0.000558 2022/09/14 06:22:28 - mmengine - INFO - Epoch(train) [139][150/293] lr: 5.000000e-04 eta: 2:29:37 time: 0.501259 data_time: 0.071600 memory: 9871 loss_kpt: 0.000571 acc_pose: 0.862732 loss: 0.000571 2022/09/14 06:22:55 - mmengine - INFO - Epoch(train) [139][200/293] lr: 5.000000e-04 eta: 2:29:19 time: 0.537420 data_time: 0.078757 memory: 9871 loss_kpt: 0.000571 acc_pose: 0.846638 loss: 0.000571 2022/09/14 06:23:23 - mmengine - INFO - Epoch(train) [139][250/293] lr: 5.000000e-04 eta: 2:29:01 time: 0.576335 data_time: 0.077145 memory: 9871 loss_kpt: 0.000600 acc_pose: 0.778029 loss: 0.000600 2022/09/14 06:23:46 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 06:23:46 - mmengine - INFO - Saving checkpoint at 139 epochs 2022/09/14 06:24:14 - mmengine - INFO - Epoch(train) [140][50/293] lr: 5.000000e-04 eta: 2:28:14 time: 0.505144 data_time: 0.082185 memory: 9871 loss_kpt: 0.000578 acc_pose: 0.866185 loss: 0.000578 2022/09/14 06:24:40 - mmengine - INFO - Epoch(train) [140][100/293] lr: 5.000000e-04 eta: 2:27:54 time: 0.516444 data_time: 0.071684 memory: 9871 loss_kpt: 0.000583 acc_pose: 0.846152 loss: 0.000583 2022/09/14 06:25:05 - mmengine - INFO - Epoch(train) [140][150/293] lr: 5.000000e-04 eta: 2:27:35 time: 0.499894 data_time: 0.078288 memory: 9871 loss_kpt: 0.000584 acc_pose: 0.830036 loss: 0.000584 2022/09/14 06:25:30 - mmengine - INFO - Epoch(train) [140][200/293] lr: 5.000000e-04 eta: 2:27:15 time: 0.504348 data_time: 0.083211 memory: 9871 loss_kpt: 0.000576 acc_pose: 0.806757 loss: 0.000576 2022/09/14 06:25:55 - mmengine - INFO - Epoch(train) [140][250/293] lr: 5.000000e-04 eta: 2:26:55 time: 0.491481 data_time: 0.070745 memory: 9871 loss_kpt: 0.000578 acc_pose: 0.775039 loss: 0.000578 2022/09/14 06:26:06 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 06:26:16 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 06:26:16 - mmengine - INFO - Saving checkpoint at 140 epochs 2022/09/14 06:26:26 - mmengine - INFO - Epoch(val) [140][50/407] eta: 0:00:49 time: 0.138288 data_time: 0.014147 memory: 9871 2022/09/14 06:26:33 - mmengine - INFO - Epoch(val) [140][100/407] eta: 0:00:41 time: 0.136226 data_time: 0.008686 memory: 920 2022/09/14 06:26:40 - mmengine - INFO - Epoch(val) [140][150/407] eta: 0:00:33 time: 0.129684 data_time: 0.008597 memory: 920 2022/09/14 06:26:46 - mmengine - INFO - Epoch(val) [140][200/407] eta: 0:00:27 time: 0.132410 data_time: 0.010928 memory: 920 2022/09/14 06:26:53 - mmengine - INFO - Epoch(val) [140][250/407] eta: 0:00:20 time: 0.130450 data_time: 0.008807 memory: 920 2022/09/14 06:26:59 - mmengine - INFO - Epoch(val) [140][300/407] eta: 0:00:13 time: 0.130266 data_time: 0.008270 memory: 920 2022/09/14 06:27:06 - mmengine - INFO - Epoch(val) [140][350/407] eta: 0:00:07 time: 0.130969 data_time: 0.009448 memory: 920 2022/09/14 06:27:12 - mmengine - INFO - Epoch(val) [140][400/407] eta: 0:00:00 time: 0.127183 data_time: 0.007725 memory: 920 2022/09/14 06:27:49 - mmengine - INFO - Evaluating CocoMetric... 2022/09/14 06:28:03 - mmengine - INFO - Epoch(val) [140][407/407] coco/AP: 0.746282 coco/AP .5: 0.897896 coco/AP .75: 0.815860 coco/AP (M): 0.710790 coco/AP (L): 0.814910 coco/AR: 0.799496 coco/AR .5: 0.938445 coco/AR .75: 0.862563 coco/AR (M): 0.757034 coco/AR (L): 0.860832 2022/09/14 06:28:03 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220914/udp_w32_256_v1/best_coco/AP_epoch_130.pth is removed 2022/09/14 06:28:06 - mmengine - INFO - The best checkpoint with 0.7463 coco/AP at 140 epoch is saved to best_coco/AP_epoch_140.pth. 2022/09/14 06:28:32 - mmengine - INFO - Epoch(train) [141][50/293] lr: 5.000000e-04 eta: 2:26:09 time: 0.520394 data_time: 0.078471 memory: 9871 loss_kpt: 0.000557 acc_pose: 0.871285 loss: 0.000557 2022/09/14 06:28:57 - mmengine - INFO - Epoch(train) [141][100/293] lr: 5.000000e-04 eta: 2:25:49 time: 0.502058 data_time: 0.072835 memory: 9871 loss_kpt: 0.000580 acc_pose: 0.841371 loss: 0.000580 2022/09/14 06:29:22 - mmengine - INFO - Epoch(train) [141][150/293] lr: 5.000000e-04 eta: 2:25:29 time: 0.501180 data_time: 0.075864 memory: 9871 loss_kpt: 0.000573 acc_pose: 0.814279 loss: 0.000573 2022/09/14 06:29:47 - mmengine - INFO - Epoch(train) [141][200/293] lr: 5.000000e-04 eta: 2:25:10 time: 0.501609 data_time: 0.075627 memory: 9871 loss_kpt: 0.000588 acc_pose: 0.802210 loss: 0.000588 2022/09/14 06:30:12 - mmengine - INFO - Epoch(train) [141][250/293] lr: 5.000000e-04 eta: 2:24:50 time: 0.503526 data_time: 0.070512 memory: 9871 loss_kpt: 0.000583 acc_pose: 0.861627 loss: 0.000583 2022/09/14 06:30:34 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 06:30:34 - mmengine - INFO - Saving checkpoint at 141 epochs 2022/09/14 06:31:03 - mmengine - INFO - Epoch(train) [142][50/293] lr: 5.000000e-04 eta: 2:24:03 time: 0.515465 data_time: 0.086359 memory: 9871 loss_kpt: 0.000563 acc_pose: 0.837730 loss: 0.000563 2022/09/14 06:31:28 - mmengine - INFO - Epoch(train) [142][100/293] lr: 5.000000e-04 eta: 2:23:43 time: 0.495220 data_time: 0.076851 memory: 9871 loss_kpt: 0.000565 acc_pose: 0.872007 loss: 0.000565 2022/09/14 06:31:53 - mmengine - INFO - Epoch(train) [142][150/293] lr: 5.000000e-04 eta: 2:23:24 time: 0.500701 data_time: 0.085604 memory: 9871 loss_kpt: 0.000576 acc_pose: 0.792557 loss: 0.000576 2022/09/14 06:32:18 - mmengine - INFO - Epoch(train) [142][200/293] lr: 5.000000e-04 eta: 2:23:04 time: 0.497967 data_time: 0.077482 memory: 9871 loss_kpt: 0.000575 acc_pose: 0.831146 loss: 0.000575 2022/09/14 06:32:43 - mmengine - INFO - Epoch(train) [142][250/293] lr: 5.000000e-04 eta: 2:22:44 time: 0.499904 data_time: 0.079730 memory: 9871 loss_kpt: 0.000572 acc_pose: 0.848970 loss: 0.000572 2022/09/14 06:33:05 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 06:33:05 - mmengine - INFO - Saving checkpoint at 142 epochs 2022/09/14 06:33:34 - mmengine - INFO - Epoch(train) [143][50/293] lr: 5.000000e-04 eta: 2:21:58 time: 0.513993 data_time: 0.082354 memory: 9871 loss_kpt: 0.000585 acc_pose: 0.837875 loss: 0.000585 2022/09/14 06:33:59 - mmengine - INFO - Epoch(train) [143][100/293] lr: 5.000000e-04 eta: 2:21:38 time: 0.508255 data_time: 0.083338 memory: 9871 loss_kpt: 0.000575 acc_pose: 0.835586 loss: 0.000575 2022/09/14 06:34:24 - mmengine - INFO - Epoch(train) [143][150/293] lr: 5.000000e-04 eta: 2:21:18 time: 0.496462 data_time: 0.076748 memory: 9871 loss_kpt: 0.000569 acc_pose: 0.845716 loss: 0.000569 2022/09/14 06:34:49 - mmengine - INFO - Epoch(train) [143][200/293] lr: 5.000000e-04 eta: 2:20:59 time: 0.507461 data_time: 0.087246 memory: 9871 loss_kpt: 0.000585 acc_pose: 0.792838 loss: 0.000585 2022/09/14 06:35:14 - mmengine - INFO - Epoch(train) [143][250/293] lr: 5.000000e-04 eta: 2:20:39 time: 0.496261 data_time: 0.077416 memory: 9871 loss_kpt: 0.000576 acc_pose: 0.818340 loss: 0.000576 2022/09/14 06:35:35 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 06:35:35 - mmengine - INFO - Saving checkpoint at 143 epochs 2022/09/14 06:36:03 - mmengine - INFO - Epoch(train) [144][50/293] lr: 5.000000e-04 eta: 2:19:52 time: 0.498065 data_time: 0.081540 memory: 9871 loss_kpt: 0.000570 acc_pose: 0.846431 loss: 0.000570 2022/09/14 06:36:28 - mmengine - INFO - Epoch(train) [144][100/293] lr: 5.000000e-04 eta: 2:19:32 time: 0.501538 data_time: 0.077109 memory: 9871 loss_kpt: 0.000572 acc_pose: 0.843639 loss: 0.000572 2022/09/14 06:36:29 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 06:36:53 - mmengine - INFO - Epoch(train) [144][150/293] lr: 5.000000e-04 eta: 2:19:12 time: 0.499588 data_time: 0.078954 memory: 9871 loss_kpt: 0.000576 acc_pose: 0.821483 loss: 0.000576 2022/09/14 06:37:19 - mmengine - INFO - Epoch(train) [144][200/293] lr: 5.000000e-04 eta: 2:18:53 time: 0.505600 data_time: 0.088223 memory: 9871 loss_kpt: 0.000569 acc_pose: 0.832806 loss: 0.000569 2022/09/14 06:37:44 - mmengine - INFO - Epoch(train) [144][250/293] lr: 5.000000e-04 eta: 2:18:33 time: 0.501840 data_time: 0.075950 memory: 9871 loss_kpt: 0.000581 acc_pose: 0.850840 loss: 0.000581 2022/09/14 06:38:05 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 06:38:05 - mmengine - INFO - Saving checkpoint at 144 epochs 2022/09/14 06:38:33 - mmengine - INFO - Epoch(train) [145][50/293] lr: 5.000000e-04 eta: 2:17:47 time: 0.511658 data_time: 0.080597 memory: 9871 loss_kpt: 0.000575 acc_pose: 0.834802 loss: 0.000575 2022/09/14 06:38:59 - mmengine - INFO - Epoch(train) [145][100/293] lr: 5.000000e-04 eta: 2:17:27 time: 0.503754 data_time: 0.075298 memory: 9871 loss_kpt: 0.000587 acc_pose: 0.840425 loss: 0.000587 2022/09/14 06:39:23 - mmengine - INFO - Epoch(train) [145][150/293] lr: 5.000000e-04 eta: 2:17:07 time: 0.495525 data_time: 0.075346 memory: 9871 loss_kpt: 0.000574 acc_pose: 0.879753 loss: 0.000574 2022/09/14 06:39:49 - mmengine - INFO - Epoch(train) [145][200/293] lr: 5.000000e-04 eta: 2:16:47 time: 0.504587 data_time: 0.081334 memory: 9871 loss_kpt: 0.000575 acc_pose: 0.856877 loss: 0.000575 2022/09/14 06:40:13 - mmengine - INFO - Epoch(train) [145][250/293] lr: 5.000000e-04 eta: 2:16:27 time: 0.494607 data_time: 0.076018 memory: 9871 loss_kpt: 0.000574 acc_pose: 0.802227 loss: 0.000574 2022/09/14 06:40:34 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 06:40:34 - mmengine - INFO - Saving checkpoint at 145 epochs 2022/09/14 06:41:03 - mmengine - INFO - Epoch(train) [146][50/293] lr: 5.000000e-04 eta: 2:15:41 time: 0.504181 data_time: 0.080200 memory: 9871 loss_kpt: 0.000571 acc_pose: 0.821534 loss: 0.000571 2022/09/14 06:41:28 - mmengine - INFO - Epoch(train) [146][100/293] lr: 5.000000e-04 eta: 2:15:21 time: 0.500231 data_time: 0.074981 memory: 9871 loss_kpt: 0.000555 acc_pose: 0.851623 loss: 0.000555 2022/09/14 06:41:54 - mmengine - INFO - Epoch(train) [146][150/293] lr: 5.000000e-04 eta: 2:15:01 time: 0.511052 data_time: 0.078876 memory: 9871 loss_kpt: 0.000578 acc_pose: 0.824585 loss: 0.000578 2022/09/14 06:42:19 - mmengine - INFO - Epoch(train) [146][200/293] lr: 5.000000e-04 eta: 2:14:41 time: 0.499291 data_time: 0.083440 memory: 9871 loss_kpt: 0.000565 acc_pose: 0.832421 loss: 0.000565 2022/09/14 06:42:43 - mmengine - INFO - Epoch(train) [146][250/293] lr: 5.000000e-04 eta: 2:14:21 time: 0.485318 data_time: 0.074098 memory: 9871 loss_kpt: 0.000581 acc_pose: 0.826212 loss: 0.000581 2022/09/14 06:43:04 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 06:43:04 - mmengine - INFO - Saving checkpoint at 146 epochs 2022/09/14 06:43:33 - mmengine - INFO - Epoch(train) [147][50/293] lr: 5.000000e-04 eta: 2:13:35 time: 0.505320 data_time: 0.084451 memory: 9871 loss_kpt: 0.000572 acc_pose: 0.826889 loss: 0.000572 2022/09/14 06:43:57 - mmengine - INFO - Epoch(train) [147][100/293] lr: 5.000000e-04 eta: 2:13:15 time: 0.496669 data_time: 0.073691 memory: 9871 loss_kpt: 0.000574 acc_pose: 0.885845 loss: 0.000574 2022/09/14 06:44:23 - mmengine - INFO - Epoch(train) [147][150/293] lr: 5.000000e-04 eta: 2:12:55 time: 0.510140 data_time: 0.081466 memory: 9871 loss_kpt: 0.000571 acc_pose: 0.857005 loss: 0.000571 2022/09/14 06:44:48 - mmengine - INFO - Epoch(train) [147][200/293] lr: 5.000000e-04 eta: 2:12:35 time: 0.499858 data_time: 0.071571 memory: 9871 loss_kpt: 0.000571 acc_pose: 0.836083 loss: 0.000571 2022/09/14 06:44:59 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 06:45:12 - mmengine - INFO - Epoch(train) [147][250/293] lr: 5.000000e-04 eta: 2:12:15 time: 0.491158 data_time: 0.076797 memory: 9871 loss_kpt: 0.000567 acc_pose: 0.800785 loss: 0.000567 2022/09/14 06:45:34 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 06:45:34 - mmengine - INFO - Saving checkpoint at 147 epochs 2022/09/14 06:46:03 - mmengine - INFO - Epoch(train) [148][50/293] lr: 5.000000e-04 eta: 2:11:29 time: 0.510547 data_time: 0.083994 memory: 9871 loss_kpt: 0.000565 acc_pose: 0.824924 loss: 0.000565 2022/09/14 06:46:28 - mmengine - INFO - Epoch(train) [148][100/293] lr: 5.000000e-04 eta: 2:11:10 time: 0.509238 data_time: 0.084180 memory: 9871 loss_kpt: 0.000567 acc_pose: 0.829119 loss: 0.000567 2022/09/14 06:46:53 - mmengine - INFO - Epoch(train) [148][150/293] lr: 5.000000e-04 eta: 2:10:50 time: 0.499556 data_time: 0.081472 memory: 9871 loss_kpt: 0.000580 acc_pose: 0.824228 loss: 0.000580 2022/09/14 06:47:18 - mmengine - INFO - Epoch(train) [148][200/293] lr: 5.000000e-04 eta: 2:10:30 time: 0.492353 data_time: 0.071039 memory: 9871 loss_kpt: 0.000585 acc_pose: 0.789116 loss: 0.000585 2022/09/14 06:47:43 - mmengine - INFO - Epoch(train) [148][250/293] lr: 5.000000e-04 eta: 2:10:10 time: 0.498912 data_time: 0.078658 memory: 9871 loss_kpt: 0.000572 acc_pose: 0.851055 loss: 0.000572 2022/09/14 06:48:04 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 06:48:04 - mmengine - INFO - Saving checkpoint at 148 epochs 2022/09/14 06:48:32 - mmengine - INFO - Epoch(train) [149][50/293] lr: 5.000000e-04 eta: 2:09:24 time: 0.511145 data_time: 0.080905 memory: 9871 loss_kpt: 0.000579 acc_pose: 0.862949 loss: 0.000579 2022/09/14 06:48:57 - mmengine - INFO - Epoch(train) [149][100/293] lr: 5.000000e-04 eta: 2:09:04 time: 0.497090 data_time: 0.077392 memory: 9871 loss_kpt: 0.000567 acc_pose: 0.830630 loss: 0.000567 2022/09/14 06:49:22 - mmengine - INFO - Epoch(train) [149][150/293] lr: 5.000000e-04 eta: 2:08:44 time: 0.497089 data_time: 0.073961 memory: 9871 loss_kpt: 0.000574 acc_pose: 0.841959 loss: 0.000574 2022/09/14 06:49:47 - mmengine - INFO - Epoch(train) [149][200/293] lr: 5.000000e-04 eta: 2:08:24 time: 0.499002 data_time: 0.077662 memory: 9871 loss_kpt: 0.000564 acc_pose: 0.829689 loss: 0.000564 2022/09/14 06:50:12 - mmengine - INFO - Epoch(train) [149][250/293] lr: 5.000000e-04 eta: 2:08:04 time: 0.491936 data_time: 0.070434 memory: 9871 loss_kpt: 0.000565 acc_pose: 0.819569 loss: 0.000565 2022/09/14 06:50:33 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 06:50:33 - mmengine - INFO - Saving checkpoint at 149 epochs 2022/09/14 06:51:03 - mmengine - INFO - Epoch(train) [150][50/293] lr: 5.000000e-04 eta: 2:07:18 time: 0.511795 data_time: 0.078682 memory: 9871 loss_kpt: 0.000573 acc_pose: 0.844705 loss: 0.000573 2022/09/14 06:51:28 - mmengine - INFO - Epoch(train) [150][100/293] lr: 5.000000e-04 eta: 2:06:58 time: 0.496051 data_time: 0.073144 memory: 9871 loss_kpt: 0.000572 acc_pose: 0.772041 loss: 0.000572 2022/09/14 06:51:53 - mmengine - INFO - Epoch(train) [150][150/293] lr: 5.000000e-04 eta: 2:06:38 time: 0.499450 data_time: 0.073388 memory: 9871 loss_kpt: 0.000574 acc_pose: 0.803752 loss: 0.000574 2022/09/14 06:52:18 - mmengine - INFO - Epoch(train) [150][200/293] lr: 5.000000e-04 eta: 2:06:18 time: 0.503747 data_time: 0.075667 memory: 9871 loss_kpt: 0.000572 acc_pose: 0.807472 loss: 0.000572 2022/09/14 06:52:43 - mmengine - INFO - Epoch(train) [150][250/293] lr: 5.000000e-04 eta: 2:05:58 time: 0.505483 data_time: 0.076116 memory: 9871 loss_kpt: 0.000575 acc_pose: 0.846191 loss: 0.000575 2022/09/14 06:53:04 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 06:53:04 - mmengine - INFO - Saving checkpoint at 150 epochs 2022/09/14 06:53:14 - mmengine - INFO - Epoch(val) [150][50/407] eta: 0:00:48 time: 0.137063 data_time: 0.014211 memory: 9871 2022/09/14 06:53:21 - mmengine - INFO - Epoch(val) [150][100/407] eta: 0:00:40 time: 0.132891 data_time: 0.008522 memory: 920 2022/09/14 06:53:28 - mmengine - INFO - Epoch(val) [150][150/407] eta: 0:00:33 time: 0.132037 data_time: 0.009222 memory: 920 2022/09/14 06:53:34 - mmengine - INFO - Epoch(val) [150][200/407] eta: 0:00:27 time: 0.131709 data_time: 0.008771 memory: 920 2022/09/14 06:53:41 - mmengine - INFO - Epoch(val) [150][250/407] eta: 0:00:20 time: 0.129044 data_time: 0.008385 memory: 920 2022/09/14 06:53:47 - mmengine - INFO - Epoch(val) [150][300/407] eta: 0:00:13 time: 0.130515 data_time: 0.008855 memory: 920 2022/09/14 06:53:54 - mmengine - INFO - Epoch(val) [150][350/407] eta: 0:00:07 time: 0.130430 data_time: 0.008720 memory: 920 2022/09/14 06:54:00 - mmengine - INFO - Epoch(val) [150][400/407] eta: 0:00:00 time: 0.127383 data_time: 0.007864 memory: 920 2022/09/14 06:54:37 - mmengine - INFO - Evaluating CocoMetric... 2022/09/14 06:54:51 - mmengine - INFO - Epoch(val) [150][407/407] coco/AP: 0.747550 coco/AP .5: 0.899070 coco/AP .75: 0.816668 coco/AP (M): 0.706857 coco/AP (L): 0.820184 coco/AR: 0.799528 coco/AR .5: 0.939547 coco/AR .75: 0.861461 coco/AR (M): 0.753483 coco/AR (L): 0.865812 2022/09/14 06:54:52 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220914/udp_w32_256_v1/best_coco/AP_epoch_140.pth is removed 2022/09/14 06:54:54 - mmengine - INFO - The best checkpoint with 0.7475 coco/AP at 150 epoch is saved to best_coco/AP_epoch_150.pth. 2022/09/14 06:55:20 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 06:55:20 - mmengine - INFO - Epoch(train) [151][50/293] lr: 5.000000e-04 eta: 2:05:12 time: 0.512289 data_time: 0.084639 memory: 9871 loss_kpt: 0.000566 acc_pose: 0.816516 loss: 0.000566 2022/09/14 06:55:45 - mmengine - INFO - Epoch(train) [151][100/293] lr: 5.000000e-04 eta: 2:04:52 time: 0.503398 data_time: 0.075915 memory: 9871 loss_kpt: 0.000575 acc_pose: 0.843697 loss: 0.000575 2022/09/14 06:56:10 - mmengine - INFO - Epoch(train) [151][150/293] lr: 5.000000e-04 eta: 2:04:32 time: 0.496005 data_time: 0.076820 memory: 9871 loss_kpt: 0.000573 acc_pose: 0.849407 loss: 0.000573 2022/09/14 06:56:35 - mmengine - INFO - Epoch(train) [151][200/293] lr: 5.000000e-04 eta: 2:04:12 time: 0.508634 data_time: 0.085452 memory: 9871 loss_kpt: 0.000588 acc_pose: 0.841210 loss: 0.000588 2022/09/14 06:57:00 - mmengine - INFO - Epoch(train) [151][250/293] lr: 5.000000e-04 eta: 2:03:52 time: 0.499335 data_time: 0.077128 memory: 9871 loss_kpt: 0.000583 acc_pose: 0.830194 loss: 0.000583 2022/09/14 06:57:21 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 06:57:21 - mmengine - INFO - Saving checkpoint at 151 epochs 2022/09/14 06:57:50 - mmengine - INFO - Epoch(train) [152][50/293] lr: 5.000000e-04 eta: 2:03:07 time: 0.527402 data_time: 0.081559 memory: 9871 loss_kpt: 0.000561 acc_pose: 0.808816 loss: 0.000561 2022/09/14 06:58:14 - mmengine - INFO - Epoch(train) [152][100/293] lr: 5.000000e-04 eta: 2:02:47 time: 0.487285 data_time: 0.073393 memory: 9871 loss_kpt: 0.000565 acc_pose: 0.872184 loss: 0.000565 2022/09/14 06:58:39 - mmengine - INFO - Epoch(train) [152][150/293] lr: 5.000000e-04 eta: 2:02:27 time: 0.497146 data_time: 0.073573 memory: 9871 loss_kpt: 0.000581 acc_pose: 0.827490 loss: 0.000581 2022/09/14 06:59:04 - mmengine - INFO - Epoch(train) [152][200/293] lr: 5.000000e-04 eta: 2:02:07 time: 0.491417 data_time: 0.076850 memory: 9871 loss_kpt: 0.000569 acc_pose: 0.844212 loss: 0.000569 2022/09/14 06:59:29 - mmengine - INFO - Epoch(train) [152][250/293] lr: 5.000000e-04 eta: 2:01:47 time: 0.498436 data_time: 0.078773 memory: 9871 loss_kpt: 0.000573 acc_pose: 0.879465 loss: 0.000573 2022/09/14 06:59:50 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 06:59:50 - mmengine - INFO - Saving checkpoint at 152 epochs 2022/09/14 07:00:19 - mmengine - INFO - Epoch(train) [153][50/293] lr: 5.000000e-04 eta: 2:01:01 time: 0.515942 data_time: 0.084150 memory: 9871 loss_kpt: 0.000563 acc_pose: 0.862150 loss: 0.000563 2022/09/14 07:00:43 - mmengine - INFO - Epoch(train) [153][100/293] lr: 5.000000e-04 eta: 2:00:41 time: 0.488123 data_time: 0.077328 memory: 9871 loss_kpt: 0.000571 acc_pose: 0.809936 loss: 0.000571 2022/09/14 07:01:09 - mmengine - INFO - Epoch(train) [153][150/293] lr: 5.000000e-04 eta: 2:00:21 time: 0.513830 data_time: 0.077234 memory: 9871 loss_kpt: 0.000564 acc_pose: 0.854606 loss: 0.000564 2022/09/14 07:01:34 - mmengine - INFO - Epoch(train) [153][200/293] lr: 5.000000e-04 eta: 2:00:01 time: 0.503287 data_time: 0.075425 memory: 9871 loss_kpt: 0.000576 acc_pose: 0.828482 loss: 0.000576 2022/09/14 07:01:59 - mmengine - INFO - Epoch(train) [153][250/293] lr: 5.000000e-04 eta: 1:59:41 time: 0.494889 data_time: 0.081800 memory: 9871 loss_kpt: 0.000580 acc_pose: 0.833761 loss: 0.000580 2022/09/14 07:02:20 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 07:02:20 - mmengine - INFO - Saving checkpoint at 153 epochs 2022/09/14 07:02:49 - mmengine - INFO - Epoch(train) [154][50/293] lr: 5.000000e-04 eta: 1:58:56 time: 0.512760 data_time: 0.083374 memory: 9871 loss_kpt: 0.000560 acc_pose: 0.852434 loss: 0.000560 2022/09/14 07:03:14 - mmengine - INFO - Epoch(train) [154][100/293] lr: 5.000000e-04 eta: 1:58:36 time: 0.504790 data_time: 0.079818 memory: 9871 loss_kpt: 0.000572 acc_pose: 0.866636 loss: 0.000572 2022/09/14 07:03:39 - mmengine - INFO - Epoch(train) [154][150/293] lr: 5.000000e-04 eta: 1:58:16 time: 0.495337 data_time: 0.071486 memory: 9871 loss_kpt: 0.000567 acc_pose: 0.838260 loss: 0.000567 2022/09/14 07:03:49 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 07:04:04 - mmengine - INFO - Epoch(train) [154][200/293] lr: 5.000000e-04 eta: 1:57:55 time: 0.504915 data_time: 0.081185 memory: 9871 loss_kpt: 0.000570 acc_pose: 0.865950 loss: 0.000570 2022/09/14 07:04:29 - mmengine - INFO - Epoch(train) [154][250/293] lr: 5.000000e-04 eta: 1:57:35 time: 0.494550 data_time: 0.076640 memory: 9871 loss_kpt: 0.000572 acc_pose: 0.856876 loss: 0.000572 2022/09/14 07:04:49 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 07:04:49 - mmengine - INFO - Saving checkpoint at 154 epochs 2022/09/14 07:05:19 - mmengine - INFO - Epoch(train) [155][50/293] lr: 5.000000e-04 eta: 1:56:50 time: 0.525816 data_time: 0.102158 memory: 9871 loss_kpt: 0.000585 acc_pose: 0.830475 loss: 0.000585 2022/09/14 07:05:44 - mmengine - INFO - Epoch(train) [155][100/293] lr: 5.000000e-04 eta: 1:56:30 time: 0.496263 data_time: 0.076490 memory: 9871 loss_kpt: 0.000556 acc_pose: 0.818367 loss: 0.000556 2022/09/14 07:06:09 - mmengine - INFO - Epoch(train) [155][150/293] lr: 5.000000e-04 eta: 1:56:10 time: 0.498227 data_time: 0.077766 memory: 9871 loss_kpt: 0.000570 acc_pose: 0.794570 loss: 0.000570 2022/09/14 07:06:34 - mmengine - INFO - Epoch(train) [155][200/293] lr: 5.000000e-04 eta: 1:55:50 time: 0.506503 data_time: 0.082358 memory: 9871 loss_kpt: 0.000579 acc_pose: 0.837941 loss: 0.000579 2022/09/14 07:06:59 - mmengine - INFO - Epoch(train) [155][250/293] lr: 5.000000e-04 eta: 1:55:30 time: 0.511649 data_time: 0.077826 memory: 9871 loss_kpt: 0.000568 acc_pose: 0.885327 loss: 0.000568 2022/09/14 07:07:20 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 07:07:20 - mmengine - INFO - Saving checkpoint at 155 epochs 2022/09/14 07:07:49 - mmengine - INFO - Epoch(train) [156][50/293] lr: 5.000000e-04 eta: 1:54:45 time: 0.507635 data_time: 0.087137 memory: 9871 loss_kpt: 0.000586 acc_pose: 0.842766 loss: 0.000586 2022/09/14 07:08:14 - mmengine - INFO - Epoch(train) [156][100/293] lr: 5.000000e-04 eta: 1:54:25 time: 0.499472 data_time: 0.077238 memory: 9871 loss_kpt: 0.000563 acc_pose: 0.844341 loss: 0.000563 2022/09/14 07:08:39 - mmengine - INFO - Epoch(train) [156][150/293] lr: 5.000000e-04 eta: 1:54:05 time: 0.503703 data_time: 0.072870 memory: 9871 loss_kpt: 0.000565 acc_pose: 0.810930 loss: 0.000565 2022/09/14 07:09:04 - mmengine - INFO - Epoch(train) [156][200/293] lr: 5.000000e-04 eta: 1:53:44 time: 0.495057 data_time: 0.072568 memory: 9871 loss_kpt: 0.000564 acc_pose: 0.869585 loss: 0.000564 2022/09/14 07:09:29 - mmengine - INFO - Epoch(train) [156][250/293] lr: 5.000000e-04 eta: 1:53:24 time: 0.492741 data_time: 0.072044 memory: 9871 loss_kpt: 0.000560 acc_pose: 0.863778 loss: 0.000560 2022/09/14 07:09:50 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 07:09:50 - mmengine - INFO - Saving checkpoint at 156 epochs 2022/09/14 07:10:19 - mmengine - INFO - Epoch(train) [157][50/293] lr: 5.000000e-04 eta: 1:52:39 time: 0.512347 data_time: 0.088239 memory: 9871 loss_kpt: 0.000563 acc_pose: 0.860161 loss: 0.000563 2022/09/14 07:10:43 - mmengine - INFO - Epoch(train) [157][100/293] lr: 5.000000e-04 eta: 1:52:19 time: 0.492827 data_time: 0.076093 memory: 9871 loss_kpt: 0.000558 acc_pose: 0.861342 loss: 0.000558 2022/09/14 07:11:08 - mmengine - INFO - Epoch(train) [157][150/293] lr: 5.000000e-04 eta: 1:51:59 time: 0.504708 data_time: 0.073399 memory: 9871 loss_kpt: 0.000559 acc_pose: 0.877256 loss: 0.000559 2022/09/14 07:11:34 - mmengine - INFO - Epoch(train) [157][200/293] lr: 5.000000e-04 eta: 1:51:39 time: 0.503633 data_time: 0.081346 memory: 9871 loss_kpt: 0.000578 acc_pose: 0.834113 loss: 0.000578 2022/09/14 07:11:58 - mmengine - INFO - Epoch(train) [157][250/293] lr: 5.000000e-04 eta: 1:51:18 time: 0.488632 data_time: 0.076237 memory: 9871 loss_kpt: 0.000565 acc_pose: 0.836593 loss: 0.000565 2022/09/14 07:12:19 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 07:12:20 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 07:12:20 - mmengine - INFO - Saving checkpoint at 157 epochs 2022/09/14 07:12:48 - mmengine - INFO - Epoch(train) [158][50/293] lr: 5.000000e-04 eta: 1:50:33 time: 0.503711 data_time: 0.085484 memory: 9871 loss_kpt: 0.000560 acc_pose: 0.860431 loss: 0.000560 2022/09/14 07:13:12 - mmengine - INFO - Epoch(train) [158][100/293] lr: 5.000000e-04 eta: 1:50:13 time: 0.494279 data_time: 0.075662 memory: 9871 loss_kpt: 0.000562 acc_pose: 0.833998 loss: 0.000562 2022/09/14 07:13:38 - mmengine - INFO - Epoch(train) [158][150/293] lr: 5.000000e-04 eta: 1:49:53 time: 0.503603 data_time: 0.075502 memory: 9871 loss_kpt: 0.000572 acc_pose: 0.850103 loss: 0.000572 2022/09/14 07:14:03 - mmengine - INFO - Epoch(train) [158][200/293] lr: 5.000000e-04 eta: 1:49:33 time: 0.502670 data_time: 0.076307 memory: 9871 loss_kpt: 0.000571 acc_pose: 0.816845 loss: 0.000571 2022/09/14 07:14:28 - mmengine - INFO - Epoch(train) [158][250/293] lr: 5.000000e-04 eta: 1:49:13 time: 0.507281 data_time: 0.077425 memory: 9871 loss_kpt: 0.000560 acc_pose: 0.826638 loss: 0.000560 2022/09/14 07:14:49 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 07:14:49 - mmengine - INFO - Saving checkpoint at 158 epochs 2022/09/14 07:15:18 - mmengine - INFO - Epoch(train) [159][50/293] lr: 5.000000e-04 eta: 1:48:28 time: 0.503781 data_time: 0.081296 memory: 9871 loss_kpt: 0.000555 acc_pose: 0.845390 loss: 0.000555 2022/09/14 07:15:43 - mmengine - INFO - Epoch(train) [159][100/293] lr: 5.000000e-04 eta: 1:48:08 time: 0.511908 data_time: 0.072159 memory: 9871 loss_kpt: 0.000565 acc_pose: 0.842859 loss: 0.000565 2022/09/14 07:16:08 - mmengine - INFO - Epoch(train) [159][150/293] lr: 5.000000e-04 eta: 1:47:47 time: 0.490353 data_time: 0.071676 memory: 9871 loss_kpt: 0.000555 acc_pose: 0.857774 loss: 0.000555 2022/09/14 07:16:34 - mmengine - INFO - Epoch(train) [159][200/293] lr: 5.000000e-04 eta: 1:47:27 time: 0.514100 data_time: 0.077889 memory: 9871 loss_kpt: 0.000556 acc_pose: 0.821192 loss: 0.000556 2022/09/14 07:16:59 - mmengine - INFO - Epoch(train) [159][250/293] lr: 5.000000e-04 eta: 1:47:07 time: 0.501208 data_time: 0.079177 memory: 9871 loss_kpt: 0.000567 acc_pose: 0.830735 loss: 0.000567 2022/09/14 07:17:20 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 07:17:20 - mmengine - INFO - Saving checkpoint at 159 epochs 2022/09/14 07:17:48 - mmengine - INFO - Epoch(train) [160][50/293] lr: 5.000000e-04 eta: 1:46:22 time: 0.507938 data_time: 0.088652 memory: 9871 loss_kpt: 0.000566 acc_pose: 0.873436 loss: 0.000566 2022/09/14 07:18:13 - mmengine - INFO - Epoch(train) [160][100/293] lr: 5.000000e-04 eta: 1:46:02 time: 0.503172 data_time: 0.070744 memory: 9871 loss_kpt: 0.000565 acc_pose: 0.880181 loss: 0.000565 2022/09/14 07:18:38 - mmengine - INFO - Epoch(train) [160][150/293] lr: 5.000000e-04 eta: 1:45:42 time: 0.491498 data_time: 0.080379 memory: 9871 loss_kpt: 0.000564 acc_pose: 0.833228 loss: 0.000564 2022/09/14 07:19:03 - mmengine - INFO - Epoch(train) [160][200/293] lr: 5.000000e-04 eta: 1:45:22 time: 0.501438 data_time: 0.076135 memory: 9871 loss_kpt: 0.000567 acc_pose: 0.829700 loss: 0.000567 2022/09/14 07:19:28 - mmengine - INFO - Epoch(train) [160][250/293] lr: 5.000000e-04 eta: 1:45:01 time: 0.504986 data_time: 0.072532 memory: 9871 loss_kpt: 0.000580 acc_pose: 0.824812 loss: 0.000580 2022/09/14 07:19:50 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 07:19:50 - mmengine - INFO - Saving checkpoint at 160 epochs 2022/09/14 07:20:00 - mmengine - INFO - Epoch(val) [160][50/407] eta: 0:00:49 time: 0.139180 data_time: 0.015000 memory: 9871 2022/09/14 07:20:07 - mmengine - INFO - Epoch(val) [160][100/407] eta: 0:00:40 time: 0.131517 data_time: 0.009069 memory: 920 2022/09/14 07:20:13 - mmengine - INFO - Epoch(val) [160][150/407] eta: 0:00:33 time: 0.130037 data_time: 0.009519 memory: 920 2022/09/14 07:20:20 - mmengine - INFO - Epoch(val) [160][200/407] eta: 0:00:27 time: 0.131046 data_time: 0.008412 memory: 920 2022/09/14 07:20:27 - mmengine - INFO - Epoch(val) [160][250/407] eta: 0:00:21 time: 0.135375 data_time: 0.009459 memory: 920 2022/09/14 07:20:33 - mmengine - INFO - Epoch(val) [160][300/407] eta: 0:00:14 time: 0.134040 data_time: 0.012194 memory: 920 2022/09/14 07:20:40 - mmengine - INFO - Epoch(val) [160][350/407] eta: 0:00:07 time: 0.129583 data_time: 0.008039 memory: 920 2022/09/14 07:20:46 - mmengine - INFO - Epoch(val) [160][400/407] eta: 0:00:00 time: 0.125896 data_time: 0.007546 memory: 920 2022/09/14 07:21:23 - mmengine - INFO - Evaluating CocoMetric... 2022/09/14 07:21:37 - mmengine - INFO - Epoch(val) [160][407/407] coco/AP: 0.748148 coco/AP .5: 0.901847 coco/AP .75: 0.817983 coco/AP (M): 0.711297 coco/AP (L): 0.817634 coco/AR: 0.800756 coco/AR .5: 0.940649 coco/AR .75: 0.863508 coco/AR (M): 0.757635 coco/AR (L): 0.863211 2022/09/14 07:21:37 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220914/udp_w32_256_v1/best_coco/AP_epoch_150.pth is removed 2022/09/14 07:21:40 - mmengine - INFO - The best checkpoint with 0.7481 coco/AP at 160 epoch is saved to best_coco/AP_epoch_160.pth. 2022/09/14 07:22:06 - mmengine - INFO - Epoch(train) [161][50/293] lr: 5.000000e-04 eta: 1:44:17 time: 0.516147 data_time: 0.080172 memory: 9871 loss_kpt: 0.000562 acc_pose: 0.861761 loss: 0.000562 2022/09/14 07:22:30 - mmengine - INFO - Epoch(train) [161][100/293] lr: 5.000000e-04 eta: 1:43:57 time: 0.495609 data_time: 0.081588 memory: 9871 loss_kpt: 0.000560 acc_pose: 0.835986 loss: 0.000560 2022/09/14 07:22:40 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 07:22:55 - mmengine - INFO - Epoch(train) [161][150/293] lr: 5.000000e-04 eta: 1:43:36 time: 0.484295 data_time: 0.072684 memory: 9871 loss_kpt: 0.000565 acc_pose: 0.807882 loss: 0.000565 2022/09/14 07:23:20 - mmengine - INFO - Epoch(train) [161][200/293] lr: 5.000000e-04 eta: 1:43:16 time: 0.507056 data_time: 0.076370 memory: 9871 loss_kpt: 0.000578 acc_pose: 0.864753 loss: 0.000578 2022/09/14 07:23:46 - mmengine - INFO - Epoch(train) [161][250/293] lr: 5.000000e-04 eta: 1:42:56 time: 0.514346 data_time: 0.082765 memory: 9871 loss_kpt: 0.000565 acc_pose: 0.856679 loss: 0.000565 2022/09/14 07:24:07 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 07:24:07 - mmengine - INFO - Saving checkpoint at 161 epochs 2022/09/14 07:24:36 - mmengine - INFO - Epoch(train) [162][50/293] lr: 5.000000e-04 eta: 1:42:12 time: 0.517132 data_time: 0.088483 memory: 9871 loss_kpt: 0.000579 acc_pose: 0.823505 loss: 0.000579 2022/09/14 07:25:01 - mmengine - INFO - Epoch(train) [162][100/293] lr: 5.000000e-04 eta: 1:41:51 time: 0.500085 data_time: 0.077616 memory: 9871 loss_kpt: 0.000562 acc_pose: 0.842083 loss: 0.000562 2022/09/14 07:25:25 - mmengine - INFO - Epoch(train) [162][150/293] lr: 5.000000e-04 eta: 1:41:31 time: 0.494608 data_time: 0.077856 memory: 9871 loss_kpt: 0.000564 acc_pose: 0.853061 loss: 0.000564 2022/09/14 07:25:51 - mmengine - INFO - Epoch(train) [162][200/293] lr: 5.000000e-04 eta: 1:41:10 time: 0.501046 data_time: 0.074681 memory: 9871 loss_kpt: 0.000564 acc_pose: 0.847836 loss: 0.000564 2022/09/14 07:26:15 - mmengine - INFO - Epoch(train) [162][250/293] lr: 5.000000e-04 eta: 1:40:50 time: 0.493678 data_time: 0.071027 memory: 9871 loss_kpt: 0.000574 acc_pose: 0.881046 loss: 0.000574 2022/09/14 07:26:37 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 07:26:37 - mmengine - INFO - Saving checkpoint at 162 epochs 2022/09/14 07:27:05 - mmengine - INFO - Epoch(train) [163][50/293] lr: 5.000000e-04 eta: 1:40:06 time: 0.504952 data_time: 0.086453 memory: 9871 loss_kpt: 0.000559 acc_pose: 0.795765 loss: 0.000559 2022/09/14 07:27:30 - mmengine - INFO - Epoch(train) [163][100/293] lr: 5.000000e-04 eta: 1:39:45 time: 0.494993 data_time: 0.079209 memory: 9871 loss_kpt: 0.000558 acc_pose: 0.809678 loss: 0.000558 2022/09/14 07:27:55 - mmengine - INFO - Epoch(train) [163][150/293] lr: 5.000000e-04 eta: 1:39:25 time: 0.502045 data_time: 0.075797 memory: 9871 loss_kpt: 0.000558 acc_pose: 0.851175 loss: 0.000558 2022/09/14 07:28:20 - mmengine - INFO - Epoch(train) [163][200/293] lr: 5.000000e-04 eta: 1:39:05 time: 0.503942 data_time: 0.076385 memory: 9871 loss_kpt: 0.000560 acc_pose: 0.859625 loss: 0.000560 2022/09/14 07:28:45 - mmengine - INFO - Epoch(train) [163][250/293] lr: 5.000000e-04 eta: 1:38:44 time: 0.504041 data_time: 0.070919 memory: 9871 loss_kpt: 0.000577 acc_pose: 0.818130 loss: 0.000577 2022/09/14 07:29:07 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 07:29:07 - mmengine - INFO - Saving checkpoint at 163 epochs 2022/09/14 07:29:36 - mmengine - INFO - Epoch(train) [164][50/293] lr: 5.000000e-04 eta: 1:38:00 time: 0.501956 data_time: 0.081286 memory: 9871 loss_kpt: 0.000559 acc_pose: 0.854471 loss: 0.000559 2022/09/14 07:30:01 - mmengine - INFO - Epoch(train) [164][100/293] lr: 5.000000e-04 eta: 1:37:40 time: 0.498752 data_time: 0.079584 memory: 9871 loss_kpt: 0.000564 acc_pose: 0.800195 loss: 0.000564 2022/09/14 07:30:26 - mmengine - INFO - Epoch(train) [164][150/293] lr: 5.000000e-04 eta: 1:37:19 time: 0.503231 data_time: 0.077915 memory: 9871 loss_kpt: 0.000570 acc_pose: 0.861478 loss: 0.000570 2022/09/14 07:30:52 - mmengine - INFO - Epoch(train) [164][200/293] lr: 5.000000e-04 eta: 1:36:59 time: 0.513985 data_time: 0.075550 memory: 9871 loss_kpt: 0.000575 acc_pose: 0.847962 loss: 0.000575 2022/09/14 07:31:12 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 07:31:17 - mmengine - INFO - Epoch(train) [164][250/293] lr: 5.000000e-04 eta: 1:36:39 time: 0.495532 data_time: 0.076011 memory: 9871 loss_kpt: 0.000561 acc_pose: 0.850659 loss: 0.000561 2022/09/14 07:31:38 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 07:31:38 - mmengine - INFO - Saving checkpoint at 164 epochs 2022/09/14 07:32:07 - mmengine - INFO - Epoch(train) [165][50/293] lr: 5.000000e-04 eta: 1:35:55 time: 0.509744 data_time: 0.087888 memory: 9871 loss_kpt: 0.000563 acc_pose: 0.870656 loss: 0.000563 2022/09/14 07:32:32 - mmengine - INFO - Epoch(train) [165][100/293] lr: 5.000000e-04 eta: 1:35:34 time: 0.502590 data_time: 0.074823 memory: 9871 loss_kpt: 0.000561 acc_pose: 0.853759 loss: 0.000561 2022/09/14 07:32:56 - mmengine - INFO - Epoch(train) [165][150/293] lr: 5.000000e-04 eta: 1:35:14 time: 0.494782 data_time: 0.072850 memory: 9871 loss_kpt: 0.000560 acc_pose: 0.806091 loss: 0.000560 2022/09/14 07:33:22 - mmengine - INFO - Epoch(train) [165][200/293] lr: 5.000000e-04 eta: 1:34:53 time: 0.502648 data_time: 0.078136 memory: 9871 loss_kpt: 0.000573 acc_pose: 0.848033 loss: 0.000573 2022/09/14 07:33:46 - mmengine - INFO - Epoch(train) [165][250/293] lr: 5.000000e-04 eta: 1:34:33 time: 0.490639 data_time: 0.074552 memory: 9871 loss_kpt: 0.000567 acc_pose: 0.833731 loss: 0.000567 2022/09/14 07:34:07 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 07:34:07 - mmengine - INFO - Saving checkpoint at 165 epochs 2022/09/14 07:34:36 - mmengine - INFO - Epoch(train) [166][50/293] lr: 5.000000e-04 eta: 1:33:49 time: 0.515645 data_time: 0.082640 memory: 9871 loss_kpt: 0.000570 acc_pose: 0.849764 loss: 0.000570 2022/09/14 07:35:01 - mmengine - INFO - Epoch(train) [166][100/293] lr: 5.000000e-04 eta: 1:33:28 time: 0.498554 data_time: 0.076234 memory: 9871 loss_kpt: 0.000562 acc_pose: 0.817966 loss: 0.000562 2022/09/14 07:35:26 - mmengine - INFO - Epoch(train) [166][150/293] lr: 5.000000e-04 eta: 1:33:08 time: 0.497505 data_time: 0.075887 memory: 9871 loss_kpt: 0.000551 acc_pose: 0.838011 loss: 0.000551 2022/09/14 07:35:51 - mmengine - INFO - Epoch(train) [166][200/293] lr: 5.000000e-04 eta: 1:32:48 time: 0.508411 data_time: 0.080917 memory: 9871 loss_kpt: 0.000576 acc_pose: 0.814501 loss: 0.000576 2022/09/14 07:36:17 - mmengine - INFO - Epoch(train) [166][250/293] lr: 5.000000e-04 eta: 1:32:27 time: 0.506460 data_time: 0.081249 memory: 9871 loss_kpt: 0.000562 acc_pose: 0.844941 loss: 0.000562 2022/09/14 07:36:38 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 07:36:38 - mmengine - INFO - Saving checkpoint at 166 epochs 2022/09/14 07:37:09 - mmengine - INFO - Epoch(train) [167][50/293] lr: 5.000000e-04 eta: 1:31:44 time: 0.515269 data_time: 0.095113 memory: 9871 loss_kpt: 0.000564 acc_pose: 0.858749 loss: 0.000564 2022/09/14 07:37:33 - mmengine - INFO - Epoch(train) [167][100/293] lr: 5.000000e-04 eta: 1:31:23 time: 0.485689 data_time: 0.073376 memory: 9871 loss_kpt: 0.000568 acc_pose: 0.800703 loss: 0.000568 2022/09/14 07:37:58 - mmengine - INFO - Epoch(train) [167][150/293] lr: 5.000000e-04 eta: 1:31:02 time: 0.504472 data_time: 0.078909 memory: 9871 loss_kpt: 0.000565 acc_pose: 0.838493 loss: 0.000565 2022/09/14 07:38:24 - mmengine - INFO - Epoch(train) [167][200/293] lr: 5.000000e-04 eta: 1:30:42 time: 0.513556 data_time: 0.076079 memory: 9871 loss_kpt: 0.000553 acc_pose: 0.862523 loss: 0.000553 2022/09/14 07:38:49 - mmengine - INFO - Epoch(train) [167][250/293] lr: 5.000000e-04 eta: 1:30:22 time: 0.510449 data_time: 0.082140 memory: 9871 loss_kpt: 0.000566 acc_pose: 0.771935 loss: 0.000566 2022/09/14 07:39:11 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 07:39:11 - mmengine - INFO - Saving checkpoint at 167 epochs 2022/09/14 07:39:40 - mmengine - INFO - Epoch(train) [168][50/293] lr: 5.000000e-04 eta: 1:29:38 time: 0.516460 data_time: 0.082206 memory: 9871 loss_kpt: 0.000568 acc_pose: 0.820056 loss: 0.000568 2022/09/14 07:39:49 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 07:40:05 - mmengine - INFO - Epoch(train) [168][100/293] lr: 5.000000e-04 eta: 1:29:18 time: 0.492724 data_time: 0.079640 memory: 9871 loss_kpt: 0.000553 acc_pose: 0.865415 loss: 0.000553 2022/09/14 07:40:30 - mmengine - INFO - Epoch(train) [168][150/293] lr: 5.000000e-04 eta: 1:28:57 time: 0.515278 data_time: 0.081085 memory: 9871 loss_kpt: 0.000558 acc_pose: 0.823357 loss: 0.000558 2022/09/14 07:40:55 - mmengine - INFO - Epoch(train) [168][200/293] lr: 5.000000e-04 eta: 1:28:37 time: 0.494719 data_time: 0.081965 memory: 9871 loss_kpt: 0.000573 acc_pose: 0.810106 loss: 0.000573 2022/09/14 07:41:20 - mmengine - INFO - Epoch(train) [168][250/293] lr: 5.000000e-04 eta: 1:28:16 time: 0.498033 data_time: 0.072618 memory: 9871 loss_kpt: 0.000566 acc_pose: 0.795461 loss: 0.000566 2022/09/14 07:41:41 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 07:41:41 - mmengine - INFO - Saving checkpoint at 168 epochs 2022/09/14 07:42:09 - mmengine - INFO - Epoch(train) [169][50/293] lr: 5.000000e-04 eta: 1:27:33 time: 0.506781 data_time: 0.088671 memory: 9871 loss_kpt: 0.000567 acc_pose: 0.858830 loss: 0.000567 2022/09/14 07:42:35 - mmengine - INFO - Epoch(train) [169][100/293] lr: 5.000000e-04 eta: 1:27:12 time: 0.502375 data_time: 0.076917 memory: 9871 loss_kpt: 0.000575 acc_pose: 0.777142 loss: 0.000575 2022/09/14 07:43:00 - mmengine - INFO - Epoch(train) [169][150/293] lr: 5.000000e-04 eta: 1:26:52 time: 0.502676 data_time: 0.072458 memory: 9871 loss_kpt: 0.000560 acc_pose: 0.839145 loss: 0.000560 2022/09/14 07:43:25 - mmengine - INFO - Epoch(train) [169][200/293] lr: 5.000000e-04 eta: 1:26:31 time: 0.508453 data_time: 0.080893 memory: 9871 loss_kpt: 0.000556 acc_pose: 0.836830 loss: 0.000556 2022/09/14 07:43:50 - mmengine - INFO - Epoch(train) [169][250/293] lr: 5.000000e-04 eta: 1:26:11 time: 0.499162 data_time: 0.077330 memory: 9871 loss_kpt: 0.000567 acc_pose: 0.860125 loss: 0.000567 2022/09/14 07:44:11 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 07:44:11 - mmengine - INFO - Saving checkpoint at 169 epochs 2022/09/14 07:44:40 - mmengine - INFO - Epoch(train) [170][50/293] lr: 5.000000e-04 eta: 1:25:27 time: 0.512997 data_time: 0.086226 memory: 9871 loss_kpt: 0.000563 acc_pose: 0.876033 loss: 0.000563 2022/09/14 07:45:05 - mmengine - INFO - Epoch(train) [170][100/293] lr: 5.000000e-04 eta: 1:25:07 time: 0.499559 data_time: 0.076731 memory: 9871 loss_kpt: 0.000555 acc_pose: 0.840139 loss: 0.000555 2022/09/14 07:45:30 - mmengine - INFO - Epoch(train) [170][150/293] lr: 5.000000e-04 eta: 1:24:46 time: 0.506958 data_time: 0.076242 memory: 9871 loss_kpt: 0.000556 acc_pose: 0.830119 loss: 0.000556 2022/09/14 07:45:55 - mmengine - INFO - Epoch(train) [170][200/293] lr: 5.000000e-04 eta: 1:24:25 time: 0.492259 data_time: 0.076894 memory: 9871 loss_kpt: 0.000560 acc_pose: 0.859826 loss: 0.000560 2022/09/14 07:46:20 - mmengine - INFO - Epoch(train) [170][250/293] lr: 5.000000e-04 eta: 1:24:05 time: 0.499375 data_time: 0.074499 memory: 9871 loss_kpt: 0.000566 acc_pose: 0.877099 loss: 0.000566 2022/09/14 07:46:41 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 07:46:41 - mmengine - INFO - Saving checkpoint at 170 epochs 2022/09/14 07:46:51 - mmengine - INFO - Epoch(val) [170][50/407] eta: 0:00:48 time: 0.135279 data_time: 0.013257 memory: 9871 2022/09/14 07:46:58 - mmengine - INFO - Epoch(val) [170][100/407] eta: 0:00:41 time: 0.134887 data_time: 0.014809 memory: 920 2022/09/14 07:47:04 - mmengine - INFO - Epoch(val) [170][150/407] eta: 0:00:34 time: 0.133085 data_time: 0.008713 memory: 920 2022/09/14 07:47:11 - mmengine - INFO - Epoch(val) [170][200/407] eta: 0:00:27 time: 0.131665 data_time: 0.009506 memory: 920 2022/09/14 07:47:17 - mmengine - INFO - Epoch(val) [170][250/407] eta: 0:00:20 time: 0.128457 data_time: 0.008180 memory: 920 2022/09/14 07:47:24 - mmengine - INFO - Epoch(val) [170][300/407] eta: 0:00:14 time: 0.132759 data_time: 0.008357 memory: 920 2022/09/14 07:47:30 - mmengine - INFO - Epoch(val) [170][350/407] eta: 0:00:07 time: 0.128823 data_time: 0.009385 memory: 920 2022/09/14 07:47:37 - mmengine - INFO - Epoch(val) [170][400/407] eta: 0:00:00 time: 0.129038 data_time: 0.010494 memory: 920 2022/09/14 07:48:14 - mmengine - INFO - Evaluating CocoMetric... 2022/09/14 07:48:28 - mmengine - INFO - Epoch(val) [170][407/407] coco/AP: 0.751018 coco/AP .5: 0.903591 coco/AP .75: 0.820462 coco/AP (M): 0.713719 coco/AP (L): 0.818822 coco/AR: 0.802739 coco/AR .5: 0.941908 coco/AR .75: 0.865397 coco/AR (M): 0.760339 coco/AR (L): 0.864177 2022/09/14 07:48:28 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220914/udp_w32_256_v1/best_coco/AP_epoch_160.pth is removed 2022/09/14 07:48:30 - mmengine - INFO - The best checkpoint with 0.7510 coco/AP at 170 epoch is saved to best_coco/AP_epoch_170.pth. 2022/09/14 07:48:56 - mmengine - INFO - Epoch(train) [171][50/293] lr: 5.000000e-05 eta: 1:23:21 time: 0.504880 data_time: 0.084297 memory: 9871 loss_kpt: 0.000559 acc_pose: 0.828468 loss: 0.000559 2022/09/14 07:49:20 - mmengine - INFO - Epoch(train) [171][100/293] lr: 5.000000e-05 eta: 1:23:01 time: 0.496540 data_time: 0.075027 memory: 9871 loss_kpt: 0.000542 acc_pose: 0.861242 loss: 0.000542 2022/09/14 07:49:46 - mmengine - INFO - Epoch(train) [171][150/293] lr: 5.000000e-05 eta: 1:22:40 time: 0.508582 data_time: 0.072414 memory: 9871 loss_kpt: 0.000544 acc_pose: 0.844621 loss: 0.000544 2022/09/14 07:50:06 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 07:50:11 - mmengine - INFO - Epoch(train) [171][200/293] lr: 5.000000e-05 eta: 1:22:20 time: 0.499788 data_time: 0.076422 memory: 9871 loss_kpt: 0.000562 acc_pose: 0.871395 loss: 0.000562 2022/09/14 07:50:35 - mmengine - INFO - Epoch(train) [171][250/293] lr: 5.000000e-05 eta: 1:21:59 time: 0.487687 data_time: 0.079841 memory: 9871 loss_kpt: 0.000548 acc_pose: 0.871815 loss: 0.000548 2022/09/14 07:50:57 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 07:50:57 - mmengine - INFO - Saving checkpoint at 171 epochs 2022/09/14 07:51:25 - mmengine - INFO - Epoch(train) [172][50/293] lr: 5.000000e-05 eta: 1:21:16 time: 0.503501 data_time: 0.083857 memory: 9871 loss_kpt: 0.000544 acc_pose: 0.812268 loss: 0.000544 2022/09/14 07:51:50 - mmengine - INFO - Epoch(train) [172][100/293] lr: 5.000000e-05 eta: 1:20:55 time: 0.502828 data_time: 0.077312 memory: 9871 loss_kpt: 0.000546 acc_pose: 0.868726 loss: 0.000546 2022/09/14 07:52:16 - mmengine - INFO - Epoch(train) [172][150/293] lr: 5.000000e-05 eta: 1:20:35 time: 0.511238 data_time: 0.075851 memory: 9871 loss_kpt: 0.000539 acc_pose: 0.858319 loss: 0.000539 2022/09/14 07:52:41 - mmengine - INFO - Epoch(train) [172][200/293] lr: 5.000000e-05 eta: 1:20:14 time: 0.503363 data_time: 0.075840 memory: 9871 loss_kpt: 0.000537 acc_pose: 0.827688 loss: 0.000537 2022/09/14 07:53:06 - mmengine - INFO - Epoch(train) [172][250/293] lr: 5.000000e-05 eta: 1:19:53 time: 0.493699 data_time: 0.078270 memory: 9871 loss_kpt: 0.000551 acc_pose: 0.795187 loss: 0.000551 2022/09/14 07:53:27 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 07:53:27 - mmengine - INFO - Saving checkpoint at 172 epochs 2022/09/14 07:53:55 - mmengine - INFO - Epoch(train) [173][50/293] lr: 5.000000e-05 eta: 1:19:10 time: 0.499702 data_time: 0.081686 memory: 9871 loss_kpt: 0.000536 acc_pose: 0.839116 loss: 0.000536 2022/09/14 07:54:20 - mmengine - INFO - Epoch(train) [173][100/293] lr: 5.000000e-05 eta: 1:18:49 time: 0.498374 data_time: 0.070428 memory: 9871 loss_kpt: 0.000533 acc_pose: 0.839394 loss: 0.000533 2022/09/14 07:54:45 - mmengine - INFO - Epoch(train) [173][150/293] lr: 5.000000e-05 eta: 1:18:29 time: 0.510973 data_time: 0.077354 memory: 9871 loss_kpt: 0.000539 acc_pose: 0.830815 loss: 0.000539 2022/09/14 07:55:10 - mmengine - INFO - Epoch(train) [173][200/293] lr: 5.000000e-05 eta: 1:18:08 time: 0.500910 data_time: 0.071047 memory: 9871 loss_kpt: 0.000538 acc_pose: 0.876214 loss: 0.000538 2022/09/14 07:55:35 - mmengine - INFO - Epoch(train) [173][250/293] lr: 5.000000e-05 eta: 1:17:48 time: 0.494706 data_time: 0.076397 memory: 9871 loss_kpt: 0.000533 acc_pose: 0.871205 loss: 0.000533 2022/09/14 07:55:56 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 07:55:56 - mmengine - INFO - Saving checkpoint at 173 epochs 2022/09/14 07:56:25 - mmengine - INFO - Epoch(train) [174][50/293] lr: 5.000000e-05 eta: 1:17:05 time: 0.508973 data_time: 0.083601 memory: 9871 loss_kpt: 0.000525 acc_pose: 0.864685 loss: 0.000525 2022/09/14 07:56:50 - mmengine - INFO - Epoch(train) [174][100/293] lr: 5.000000e-05 eta: 1:16:44 time: 0.495487 data_time: 0.080180 memory: 9871 loss_kpt: 0.000546 acc_pose: 0.857530 loss: 0.000546 2022/09/14 07:57:15 - mmengine - INFO - Epoch(train) [174][150/293] lr: 5.000000e-05 eta: 1:16:23 time: 0.507556 data_time: 0.078236 memory: 9871 loss_kpt: 0.000539 acc_pose: 0.845216 loss: 0.000539 2022/09/14 07:57:40 - mmengine - INFO - Epoch(train) [174][200/293] lr: 5.000000e-05 eta: 1:16:03 time: 0.494605 data_time: 0.076052 memory: 9871 loss_kpt: 0.000542 acc_pose: 0.856532 loss: 0.000542 2022/09/14 07:58:05 - mmengine - INFO - Epoch(train) [174][250/293] lr: 5.000000e-05 eta: 1:15:42 time: 0.495751 data_time: 0.076392 memory: 9871 loss_kpt: 0.000547 acc_pose: 0.827164 loss: 0.000547 2022/09/14 07:58:26 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 07:58:26 - mmengine - INFO - Saving checkpoint at 174 epochs 2022/09/14 07:58:38 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 07:58:54 - mmengine - INFO - Epoch(train) [175][50/293] lr: 5.000000e-05 eta: 1:14:59 time: 0.502795 data_time: 0.083187 memory: 9871 loss_kpt: 0.000526 acc_pose: 0.872958 loss: 0.000526 2022/09/14 07:59:20 - mmengine - INFO - Epoch(train) [175][100/293] lr: 5.000000e-05 eta: 1:14:38 time: 0.506381 data_time: 0.077707 memory: 9871 loss_kpt: 0.000531 acc_pose: 0.843424 loss: 0.000531 2022/09/14 07:59:45 - mmengine - INFO - Epoch(train) [175][150/293] lr: 5.000000e-05 eta: 1:14:18 time: 0.500769 data_time: 0.073221 memory: 9871 loss_kpt: 0.000524 acc_pose: 0.845794 loss: 0.000524 2022/09/14 08:00:10 - mmengine - INFO - Epoch(train) [175][200/293] lr: 5.000000e-05 eta: 1:13:57 time: 0.502169 data_time: 0.071870 memory: 9871 loss_kpt: 0.000534 acc_pose: 0.882659 loss: 0.000534 2022/09/14 08:00:35 - mmengine - INFO - Epoch(train) [175][250/293] lr: 5.000000e-05 eta: 1:13:36 time: 0.497213 data_time: 0.077350 memory: 9871 loss_kpt: 0.000531 acc_pose: 0.850800 loss: 0.000531 2022/09/14 08:00:55 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 08:00:55 - mmengine - INFO - Saving checkpoint at 175 epochs 2022/09/14 08:01:23 - mmengine - INFO - Epoch(train) [176][50/293] lr: 5.000000e-05 eta: 1:12:53 time: 0.506270 data_time: 0.090328 memory: 9871 loss_kpt: 0.000530 acc_pose: 0.853519 loss: 0.000530 2022/09/14 08:01:49 - mmengine - INFO - Epoch(train) [176][100/293] lr: 5.000000e-05 eta: 1:12:33 time: 0.507903 data_time: 0.081359 memory: 9871 loss_kpt: 0.000536 acc_pose: 0.872331 loss: 0.000536 2022/09/14 08:02:13 - mmengine - INFO - Epoch(train) [176][150/293] lr: 5.000000e-05 eta: 1:12:12 time: 0.489144 data_time: 0.072088 memory: 9871 loss_kpt: 0.000560 acc_pose: 0.850642 loss: 0.000560 2022/09/14 08:02:38 - mmengine - INFO - Epoch(train) [176][200/293] lr: 5.000000e-05 eta: 1:11:51 time: 0.489935 data_time: 0.076411 memory: 9871 loss_kpt: 0.000522 acc_pose: 0.845493 loss: 0.000522 2022/09/14 08:03:03 - mmengine - INFO - Epoch(train) [176][250/293] lr: 5.000000e-05 eta: 1:11:30 time: 0.494310 data_time: 0.073551 memory: 9871 loss_kpt: 0.000520 acc_pose: 0.850220 loss: 0.000520 2022/09/14 08:03:24 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 08:03:24 - mmengine - INFO - Saving checkpoint at 176 epochs 2022/09/14 08:03:53 - mmengine - INFO - Epoch(train) [177][50/293] lr: 5.000000e-05 eta: 1:10:48 time: 0.513973 data_time: 0.088894 memory: 9871 loss_kpt: 0.000534 acc_pose: 0.836635 loss: 0.000534 2022/09/14 08:04:18 - mmengine - INFO - Epoch(train) [177][100/293] lr: 5.000000e-05 eta: 1:10:27 time: 0.495164 data_time: 0.074617 memory: 9871 loss_kpt: 0.000538 acc_pose: 0.893618 loss: 0.000538 2022/09/14 08:04:43 - mmengine - INFO - Epoch(train) [177][150/293] lr: 5.000000e-05 eta: 1:10:06 time: 0.500590 data_time: 0.076250 memory: 9871 loss_kpt: 0.000522 acc_pose: 0.851728 loss: 0.000522 2022/09/14 08:05:08 - mmengine - INFO - Epoch(train) [177][200/293] lr: 5.000000e-05 eta: 1:09:45 time: 0.502296 data_time: 0.078282 memory: 9871 loss_kpt: 0.000529 acc_pose: 0.877210 loss: 0.000529 2022/09/14 08:05:33 - mmengine - INFO - Epoch(train) [177][250/293] lr: 5.000000e-05 eta: 1:09:25 time: 0.503312 data_time: 0.075670 memory: 9871 loss_kpt: 0.000542 acc_pose: 0.832757 loss: 0.000542 2022/09/14 08:05:54 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 08:05:54 - mmengine - INFO - Saving checkpoint at 177 epochs 2022/09/14 08:06:23 - mmengine - INFO - Epoch(train) [178][50/293] lr: 5.000000e-05 eta: 1:08:42 time: 0.506808 data_time: 0.080380 memory: 9871 loss_kpt: 0.000526 acc_pose: 0.875799 loss: 0.000526 2022/09/14 08:06:48 - mmengine - INFO - Epoch(train) [178][100/293] lr: 5.000000e-05 eta: 1:08:21 time: 0.499305 data_time: 0.075578 memory: 9871 loss_kpt: 0.000516 acc_pose: 0.868629 loss: 0.000516 2022/09/14 08:07:07 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 08:07:13 - mmengine - INFO - Epoch(train) [178][150/293] lr: 5.000000e-05 eta: 1:08:00 time: 0.498758 data_time: 0.076028 memory: 9871 loss_kpt: 0.000528 acc_pose: 0.857892 loss: 0.000528 2022/09/14 08:07:37 - mmengine - INFO - Epoch(train) [178][200/293] lr: 5.000000e-05 eta: 1:07:40 time: 0.491725 data_time: 0.075053 memory: 9871 loss_kpt: 0.000535 acc_pose: 0.831020 loss: 0.000535 2022/09/14 08:08:02 - mmengine - INFO - Epoch(train) [178][250/293] lr: 5.000000e-05 eta: 1:07:19 time: 0.500864 data_time: 0.083123 memory: 9871 loss_kpt: 0.000539 acc_pose: 0.812143 loss: 0.000539 2022/09/14 08:08:23 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 08:08:23 - mmengine - INFO - Saving checkpoint at 178 epochs 2022/09/14 08:08:54 - mmengine - INFO - Epoch(train) [179][50/293] lr: 5.000000e-05 eta: 1:06:36 time: 0.516670 data_time: 0.088039 memory: 9871 loss_kpt: 0.000532 acc_pose: 0.812386 loss: 0.000532 2022/09/14 08:09:19 - mmengine - INFO - Epoch(train) [179][100/293] lr: 5.000000e-05 eta: 1:06:16 time: 0.498937 data_time: 0.075990 memory: 9871 loss_kpt: 0.000533 acc_pose: 0.893447 loss: 0.000533 2022/09/14 08:09:44 - mmengine - INFO - Epoch(train) [179][150/293] lr: 5.000000e-05 eta: 1:05:55 time: 0.501364 data_time: 0.076383 memory: 9871 loss_kpt: 0.000526 acc_pose: 0.882729 loss: 0.000526 2022/09/14 08:10:08 - mmengine - INFO - Epoch(train) [179][200/293] lr: 5.000000e-05 eta: 1:05:34 time: 0.492651 data_time: 0.072292 memory: 9871 loss_kpt: 0.000534 acc_pose: 0.859085 loss: 0.000534 2022/09/14 08:10:33 - mmengine - INFO - Epoch(train) [179][250/293] lr: 5.000000e-05 eta: 1:05:13 time: 0.501892 data_time: 0.074529 memory: 9871 loss_kpt: 0.000525 acc_pose: 0.868316 loss: 0.000525 2022/09/14 08:10:55 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 08:10:55 - mmengine - INFO - Saving checkpoint at 179 epochs 2022/09/14 08:11:24 - mmengine - INFO - Epoch(train) [180][50/293] lr: 5.000000e-05 eta: 1:04:31 time: 0.505309 data_time: 0.082828 memory: 9871 loss_kpt: 0.000527 acc_pose: 0.835012 loss: 0.000527 2022/09/14 08:11:50 - mmengine - INFO - Epoch(train) [180][100/293] lr: 5.000000e-05 eta: 1:04:10 time: 0.504125 data_time: 0.076386 memory: 9871 loss_kpt: 0.000538 acc_pose: 0.876617 loss: 0.000538 2022/09/14 08:12:15 - mmengine - INFO - Epoch(train) [180][150/293] lr: 5.000000e-05 eta: 1:03:49 time: 0.508280 data_time: 0.074323 memory: 9871 loss_kpt: 0.000529 acc_pose: 0.771229 loss: 0.000529 2022/09/14 08:12:40 - mmengine - INFO - Epoch(train) [180][200/293] lr: 5.000000e-05 eta: 1:03:28 time: 0.492046 data_time: 0.074975 memory: 9871 loss_kpt: 0.000521 acc_pose: 0.826773 loss: 0.000521 2022/09/14 08:13:05 - mmengine - INFO - Epoch(train) [180][250/293] lr: 5.000000e-05 eta: 1:03:07 time: 0.505500 data_time: 0.079929 memory: 9871 loss_kpt: 0.000540 acc_pose: 0.788417 loss: 0.000540 2022/09/14 08:13:27 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 08:13:27 - mmengine - INFO - Saving checkpoint at 180 epochs 2022/09/14 08:13:37 - mmengine - INFO - Epoch(val) [180][50/407] eta: 0:00:51 time: 0.143180 data_time: 0.018935 memory: 9871 2022/09/14 08:13:44 - mmengine - INFO - Epoch(val) [180][100/407] eta: 0:00:40 time: 0.132103 data_time: 0.008657 memory: 920 2022/09/14 08:13:50 - mmengine - INFO - Epoch(val) [180][150/407] eta: 0:00:32 time: 0.128340 data_time: 0.007985 memory: 920 2022/09/14 08:13:57 - mmengine - INFO - Epoch(val) [180][200/407] eta: 0:00:26 time: 0.130359 data_time: 0.008405 memory: 920 2022/09/14 08:14:03 - mmengine - INFO - Epoch(val) [180][250/407] eta: 0:00:21 time: 0.135166 data_time: 0.010946 memory: 920 2022/09/14 08:14:10 - mmengine - INFO - Epoch(val) [180][300/407] eta: 0:00:13 time: 0.128975 data_time: 0.008608 memory: 920 2022/09/14 08:14:16 - mmengine - INFO - Epoch(val) [180][350/407] eta: 0:00:07 time: 0.128522 data_time: 0.008845 memory: 920 2022/09/14 08:14:22 - mmengine - INFO - Epoch(val) [180][400/407] eta: 0:00:00 time: 0.124783 data_time: 0.007414 memory: 920 2022/09/14 08:14:59 - mmengine - INFO - Evaluating CocoMetric... 2022/09/14 08:15:14 - mmengine - INFO - Epoch(val) [180][407/407] coco/AP: 0.760041 coco/AP .5: 0.906164 coco/AP .75: 0.825632 coco/AP (M): 0.722778 coco/AP (L): 0.829353 coco/AR: 0.810343 coco/AR .5: 0.942853 coco/AR .75: 0.869962 coco/AR (M): 0.767768 coco/AR (L): 0.872501 2022/09/14 08:15:14 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220914/udp_w32_256_v1/best_coco/AP_epoch_170.pth is removed 2022/09/14 08:15:16 - mmengine - INFO - The best checkpoint with 0.7600 coco/AP at 180 epoch is saved to best_coco/AP_epoch_180.pth. 2022/09/14 08:15:42 - mmengine - INFO - Epoch(train) [181][50/293] lr: 5.000000e-05 eta: 1:02:25 time: 0.511060 data_time: 0.082314 memory: 9871 loss_kpt: 0.000536 acc_pose: 0.873431 loss: 0.000536 2022/09/14 08:16:06 - mmengine - INFO - Epoch(train) [181][100/293] lr: 5.000000e-05 eta: 1:02:04 time: 0.492970 data_time: 0.074602 memory: 9871 loss_kpt: 0.000530 acc_pose: 0.871015 loss: 0.000530 2022/09/14 08:16:32 - mmengine - INFO - Epoch(train) [181][150/293] lr: 5.000000e-05 eta: 1:01:43 time: 0.504208 data_time: 0.082086 memory: 9871 loss_kpt: 0.000532 acc_pose: 0.858755 loss: 0.000532 2022/09/14 08:16:56 - mmengine - INFO - Epoch(train) [181][200/293] lr: 5.000000e-05 eta: 1:01:23 time: 0.491785 data_time: 0.076392 memory: 9871 loss_kpt: 0.000536 acc_pose: 0.867042 loss: 0.000536 2022/09/14 08:17:21 - mmengine - INFO - Epoch(train) [181][250/293] lr: 5.000000e-05 eta: 1:01:02 time: 0.499849 data_time: 0.077310 memory: 9871 loss_kpt: 0.000522 acc_pose: 0.831458 loss: 0.000522 2022/09/14 08:17:26 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 08:17:43 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 08:17:43 - mmengine - INFO - Saving checkpoint at 181 epochs 2022/09/14 08:18:12 - mmengine - INFO - Epoch(train) [182][50/293] lr: 5.000000e-05 eta: 1:00:20 time: 0.510683 data_time: 0.086910 memory: 9871 loss_kpt: 0.000534 acc_pose: 0.869476 loss: 0.000534 2022/09/14 08:18:37 - mmengine - INFO - Epoch(train) [182][100/293] lr: 5.000000e-05 eta: 0:59:59 time: 0.497506 data_time: 0.076239 memory: 9871 loss_kpt: 0.000542 acc_pose: 0.809545 loss: 0.000542 2022/09/14 08:19:02 - mmengine - INFO - Epoch(train) [182][150/293] lr: 5.000000e-05 eta: 0:59:38 time: 0.501370 data_time: 0.073269 memory: 9871 loss_kpt: 0.000534 acc_pose: 0.870310 loss: 0.000534 2022/09/14 08:19:27 - mmengine - INFO - Epoch(train) [182][200/293] lr: 5.000000e-05 eta: 0:59:17 time: 0.500864 data_time: 0.079098 memory: 9871 loss_kpt: 0.000532 acc_pose: 0.828829 loss: 0.000532 2022/09/14 08:19:51 - mmengine - INFO - Epoch(train) [182][250/293] lr: 5.000000e-05 eta: 0:58:56 time: 0.493864 data_time: 0.076862 memory: 9871 loss_kpt: 0.000527 acc_pose: 0.879553 loss: 0.000527 2022/09/14 08:20:13 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 08:20:13 - mmengine - INFO - Saving checkpoint at 182 epochs 2022/09/14 08:20:43 - mmengine - INFO - Epoch(train) [183][50/293] lr: 5.000000e-05 eta: 0:58:14 time: 0.515609 data_time: 0.082644 memory: 9871 loss_kpt: 0.000533 acc_pose: 0.850243 loss: 0.000533 2022/09/14 08:21:08 - mmengine - INFO - Epoch(train) [183][100/293] lr: 5.000000e-05 eta: 0:57:53 time: 0.501714 data_time: 0.077075 memory: 9871 loss_kpt: 0.000519 acc_pose: 0.857174 loss: 0.000519 2022/09/14 08:21:33 - mmengine - INFO - Epoch(train) [183][150/293] lr: 5.000000e-05 eta: 0:57:32 time: 0.494606 data_time: 0.072734 memory: 9871 loss_kpt: 0.000530 acc_pose: 0.862246 loss: 0.000530 2022/09/14 08:21:58 - mmengine - INFO - Epoch(train) [183][200/293] lr: 5.000000e-05 eta: 0:57:11 time: 0.493066 data_time: 0.075841 memory: 9871 loss_kpt: 0.000531 acc_pose: 0.839743 loss: 0.000531 2022/09/14 08:22:23 - mmengine - INFO - Epoch(train) [183][250/293] lr: 5.000000e-05 eta: 0:56:50 time: 0.506591 data_time: 0.085995 memory: 9871 loss_kpt: 0.000525 acc_pose: 0.847180 loss: 0.000525 2022/09/14 08:22:44 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 08:22:44 - mmengine - INFO - Saving checkpoint at 183 epochs 2022/09/14 08:23:13 - mmengine - INFO - Epoch(train) [184][50/293] lr: 5.000000e-05 eta: 0:56:08 time: 0.512532 data_time: 0.086356 memory: 9871 loss_kpt: 0.000527 acc_pose: 0.854323 loss: 0.000527 2022/09/14 08:23:38 - mmengine - INFO - Epoch(train) [184][100/293] lr: 5.000000e-05 eta: 0:55:47 time: 0.505037 data_time: 0.081713 memory: 9871 loss_kpt: 0.000529 acc_pose: 0.833315 loss: 0.000529 2022/09/14 08:24:03 - mmengine - INFO - Epoch(train) [184][150/293] lr: 5.000000e-05 eta: 0:55:27 time: 0.496178 data_time: 0.076165 memory: 9871 loss_kpt: 0.000532 acc_pose: 0.830250 loss: 0.000532 2022/09/14 08:24:28 - mmengine - INFO - Epoch(train) [184][200/293] lr: 5.000000e-05 eta: 0:55:06 time: 0.499354 data_time: 0.077282 memory: 9871 loss_kpt: 0.000532 acc_pose: 0.853018 loss: 0.000532 2022/09/14 08:24:53 - mmengine - INFO - Epoch(train) [184][250/293] lr: 5.000000e-05 eta: 0:54:45 time: 0.508629 data_time: 0.081115 memory: 9871 loss_kpt: 0.000528 acc_pose: 0.872480 loss: 0.000528 2022/09/14 08:25:15 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 08:25:15 - mmengine - INFO - Saving checkpoint at 184 epochs 2022/09/14 08:25:43 - mmengine - INFO - Epoch(train) [185][50/293] lr: 5.000000e-05 eta: 0:54:03 time: 0.504720 data_time: 0.084647 memory: 9871 loss_kpt: 0.000539 acc_pose: 0.886759 loss: 0.000539 2022/09/14 08:26:03 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 08:26:09 - mmengine - INFO - Epoch(train) [185][100/293] lr: 5.000000e-05 eta: 0:53:42 time: 0.507057 data_time: 0.072898 memory: 9871 loss_kpt: 0.000510 acc_pose: 0.889540 loss: 0.000510 2022/09/14 08:26:34 - mmengine - INFO - Epoch(train) [185][150/293] lr: 5.000000e-05 eta: 0:53:21 time: 0.501713 data_time: 0.078658 memory: 9871 loss_kpt: 0.000524 acc_pose: 0.876477 loss: 0.000524 2022/09/14 08:26:58 - mmengine - INFO - Epoch(train) [185][200/293] lr: 5.000000e-05 eta: 0:53:00 time: 0.496162 data_time: 0.073329 memory: 9871 loss_kpt: 0.000539 acc_pose: 0.833895 loss: 0.000539 2022/09/14 08:27:23 - mmengine - INFO - Epoch(train) [185][250/293] lr: 5.000000e-05 eta: 0:52:39 time: 0.486444 data_time: 0.071983 memory: 9871 loss_kpt: 0.000540 acc_pose: 0.889577 loss: 0.000540 2022/09/14 08:27:44 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 08:27:44 - mmengine - INFO - Saving checkpoint at 185 epochs 2022/09/14 08:28:12 - mmengine - INFO - Epoch(train) [186][50/293] lr: 5.000000e-05 eta: 0:51:57 time: 0.503292 data_time: 0.081546 memory: 9871 loss_kpt: 0.000522 acc_pose: 0.858099 loss: 0.000522 2022/09/14 08:28:37 - mmengine - INFO - Epoch(train) [186][100/293] lr: 5.000000e-05 eta: 0:51:36 time: 0.501286 data_time: 0.076071 memory: 9871 loss_kpt: 0.000535 acc_pose: 0.886827 loss: 0.000535 2022/09/14 08:29:02 - mmengine - INFO - Epoch(train) [186][150/293] lr: 5.000000e-05 eta: 0:51:15 time: 0.502236 data_time: 0.078863 memory: 9871 loss_kpt: 0.000531 acc_pose: 0.842259 loss: 0.000531 2022/09/14 08:29:27 - mmengine - INFO - Epoch(train) [186][200/293] lr: 5.000000e-05 eta: 0:50:54 time: 0.492224 data_time: 0.077376 memory: 9871 loss_kpt: 0.000527 acc_pose: 0.870995 loss: 0.000527 2022/09/14 08:29:52 - mmengine - INFO - Epoch(train) [186][250/293] lr: 5.000000e-05 eta: 0:50:33 time: 0.497978 data_time: 0.078153 memory: 9871 loss_kpt: 0.000537 acc_pose: 0.882191 loss: 0.000537 2022/09/14 08:30:13 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 08:30:13 - mmengine - INFO - Saving checkpoint at 186 epochs 2022/09/14 08:30:42 - mmengine - INFO - Epoch(train) [187][50/293] lr: 5.000000e-05 eta: 0:49:52 time: 0.511044 data_time: 0.083977 memory: 9871 loss_kpt: 0.000545 acc_pose: 0.891488 loss: 0.000545 2022/09/14 08:31:07 - mmengine - INFO - Epoch(train) [187][100/293] lr: 5.000000e-05 eta: 0:49:31 time: 0.502643 data_time: 0.081399 memory: 9871 loss_kpt: 0.000520 acc_pose: 0.847440 loss: 0.000520 2022/09/14 08:31:32 - mmengine - INFO - Epoch(train) [187][150/293] lr: 5.000000e-05 eta: 0:49:10 time: 0.496069 data_time: 0.073389 memory: 9871 loss_kpt: 0.000528 acc_pose: 0.841085 loss: 0.000528 2022/09/14 08:31:57 - mmengine - INFO - Epoch(train) [187][200/293] lr: 5.000000e-05 eta: 0:48:49 time: 0.493158 data_time: 0.075994 memory: 9871 loss_kpt: 0.000524 acc_pose: 0.884291 loss: 0.000524 2022/09/14 08:32:22 - mmengine - INFO - Epoch(train) [187][250/293] lr: 5.000000e-05 eta: 0:48:28 time: 0.501947 data_time: 0.076088 memory: 9871 loss_kpt: 0.000516 acc_pose: 0.850745 loss: 0.000516 2022/09/14 08:32:43 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 08:32:43 - mmengine - INFO - Saving checkpoint at 187 epochs 2022/09/14 08:33:11 - mmengine - INFO - Epoch(train) [188][50/293] lr: 5.000000e-05 eta: 0:47:46 time: 0.504402 data_time: 0.078325 memory: 9871 loss_kpt: 0.000517 acc_pose: 0.861866 loss: 0.000517 2022/09/14 08:33:36 - mmengine - INFO - Epoch(train) [188][100/293] lr: 5.000000e-05 eta: 0:47:25 time: 0.500353 data_time: 0.077672 memory: 9871 loss_kpt: 0.000528 acc_pose: 0.876851 loss: 0.000528 2022/09/14 08:34:01 - mmengine - INFO - Epoch(train) [188][150/293] lr: 5.000000e-05 eta: 0:47:04 time: 0.501243 data_time: 0.077441 memory: 9871 loss_kpt: 0.000524 acc_pose: 0.827824 loss: 0.000524 2022/09/14 08:34:27 - mmengine - INFO - Epoch(train) [188][200/293] lr: 5.000000e-05 eta: 0:46:43 time: 0.513530 data_time: 0.079967 memory: 9871 loss_kpt: 0.000531 acc_pose: 0.782877 loss: 0.000531 2022/09/14 08:34:32 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 08:34:52 - mmengine - INFO - Epoch(train) [188][250/293] lr: 5.000000e-05 eta: 0:46:22 time: 0.493658 data_time: 0.076023 memory: 9871 loss_kpt: 0.000523 acc_pose: 0.846309 loss: 0.000523 2022/09/14 08:35:12 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 08:35:13 - mmengine - INFO - Saving checkpoint at 188 epochs 2022/09/14 08:35:41 - mmengine - INFO - Epoch(train) [189][50/293] lr: 5.000000e-05 eta: 0:45:40 time: 0.508074 data_time: 0.083747 memory: 9871 loss_kpt: 0.000520 acc_pose: 0.864856 loss: 0.000520 2022/09/14 08:36:06 - mmengine - INFO - Epoch(train) [189][100/293] lr: 5.000000e-05 eta: 0:45:19 time: 0.498169 data_time: 0.076916 memory: 9871 loss_kpt: 0.000516 acc_pose: 0.877675 loss: 0.000516 2022/09/14 08:36:31 - mmengine - INFO - Epoch(train) [189][150/293] lr: 5.000000e-05 eta: 0:44:58 time: 0.497473 data_time: 0.074767 memory: 9871 loss_kpt: 0.000527 acc_pose: 0.830495 loss: 0.000527 2022/09/14 08:36:56 - mmengine - INFO - Epoch(train) [189][200/293] lr: 5.000000e-05 eta: 0:44:37 time: 0.497121 data_time: 0.076997 memory: 9871 loss_kpt: 0.000520 acc_pose: 0.851639 loss: 0.000520 2022/09/14 08:37:21 - mmengine - INFO - Epoch(train) [189][250/293] lr: 5.000000e-05 eta: 0:44:16 time: 0.508387 data_time: 0.080838 memory: 9871 loss_kpt: 0.000526 acc_pose: 0.858783 loss: 0.000526 2022/09/14 08:37:43 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 08:37:43 - mmengine - INFO - Saving checkpoint at 189 epochs 2022/09/14 08:38:11 - mmengine - INFO - Epoch(train) [190][50/293] lr: 5.000000e-05 eta: 0:43:35 time: 0.503985 data_time: 0.079425 memory: 9871 loss_kpt: 0.000527 acc_pose: 0.852236 loss: 0.000527 2022/09/14 08:38:37 - mmengine - INFO - Epoch(train) [190][100/293] lr: 5.000000e-05 eta: 0:43:14 time: 0.508610 data_time: 0.082997 memory: 9871 loss_kpt: 0.000520 acc_pose: 0.897780 loss: 0.000520 2022/09/14 08:39:02 - mmengine - INFO - Epoch(train) [190][150/293] lr: 5.000000e-05 eta: 0:42:53 time: 0.498117 data_time: 0.072439 memory: 9871 loss_kpt: 0.000533 acc_pose: 0.862482 loss: 0.000533 2022/09/14 08:39:27 - mmengine - INFO - Epoch(train) [190][200/293] lr: 5.000000e-05 eta: 0:42:32 time: 0.499133 data_time: 0.073868 memory: 9871 loss_kpt: 0.000516 acc_pose: 0.855663 loss: 0.000516 2022/09/14 08:39:52 - mmengine - INFO - Epoch(train) [190][250/293] lr: 5.000000e-05 eta: 0:42:11 time: 0.505120 data_time: 0.074857 memory: 9871 loss_kpt: 0.000515 acc_pose: 0.856001 loss: 0.000515 2022/09/14 08:40:13 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 08:40:13 - mmengine - INFO - Saving checkpoint at 190 epochs 2022/09/14 08:40:24 - mmengine - INFO - Epoch(val) [190][50/407] eta: 0:00:49 time: 0.139660 data_time: 0.015299 memory: 9871 2022/09/14 08:40:30 - mmengine - INFO - Epoch(val) [190][100/407] eta: 0:00:39 time: 0.130214 data_time: 0.008832 memory: 920 2022/09/14 08:40:37 - mmengine - INFO - Epoch(val) [190][150/407] eta: 0:00:33 time: 0.132219 data_time: 0.008149 memory: 920 2022/09/14 08:40:43 - mmengine - INFO - Epoch(val) [190][200/407] eta: 0:00:27 time: 0.130952 data_time: 0.008372 memory: 920 2022/09/14 08:40:50 - mmengine - INFO - Epoch(val) [190][250/407] eta: 0:00:20 time: 0.132291 data_time: 0.011980 memory: 920 2022/09/14 08:40:56 - mmengine - INFO - Epoch(val) [190][300/407] eta: 0:00:13 time: 0.129477 data_time: 0.009176 memory: 920 2022/09/14 08:41:03 - mmengine - INFO - Epoch(val) [190][350/407] eta: 0:00:07 time: 0.129037 data_time: 0.007962 memory: 920 2022/09/14 08:41:09 - mmengine - INFO - Epoch(val) [190][400/407] eta: 0:00:00 time: 0.129407 data_time: 0.008310 memory: 920 2022/09/14 08:41:46 - mmengine - INFO - Evaluating CocoMetric... 2022/09/14 08:42:00 - mmengine - INFO - Epoch(val) [190][407/407] coco/AP: 0.761634 coco/AP .5: 0.906787 coco/AP .75: 0.829390 coco/AP (M): 0.723774 coco/AP (L): 0.830527 coco/AR: 0.810390 coco/AR .5: 0.942223 coco/AR .75: 0.871379 coco/AR (M): 0.767659 coco/AR (L): 0.872984 2022/09/14 08:42:01 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220914/udp_w32_256_v1/best_coco/AP_epoch_180.pth is removed 2022/09/14 08:42:03 - mmengine - INFO - The best checkpoint with 0.7616 coco/AP at 190 epoch is saved to best_coco/AP_epoch_190.pth. 2022/09/14 08:42:29 - mmengine - INFO - Epoch(train) [191][50/293] lr: 5.000000e-05 eta: 0:41:29 time: 0.514862 data_time: 0.082266 memory: 9871 loss_kpt: 0.000525 acc_pose: 0.848333 loss: 0.000525 2022/09/14 08:42:54 - mmengine - INFO - Epoch(train) [191][100/293] lr: 5.000000e-05 eta: 0:41:08 time: 0.496194 data_time: 0.078865 memory: 9871 loss_kpt: 0.000524 acc_pose: 0.847612 loss: 0.000524 2022/09/14 08:43:19 - mmengine - INFO - Epoch(train) [191][150/293] lr: 5.000000e-05 eta: 0:40:47 time: 0.497303 data_time: 0.076550 memory: 9871 loss_kpt: 0.000527 acc_pose: 0.871007 loss: 0.000527 2022/09/14 08:43:43 - mmengine - INFO - Epoch(train) [191][200/293] lr: 5.000000e-05 eta: 0:40:26 time: 0.491871 data_time: 0.070969 memory: 9871 loss_kpt: 0.000528 acc_pose: 0.817745 loss: 0.000528 2022/09/14 08:44:08 - mmengine - INFO - Epoch(train) [191][250/293] lr: 5.000000e-05 eta: 0:40:05 time: 0.495927 data_time: 0.076976 memory: 9871 loss_kpt: 0.000526 acc_pose: 0.889410 loss: 0.000526 2022/09/14 08:44:30 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 08:44:30 - mmengine - INFO - Saving checkpoint at 191 epochs 2022/09/14 08:44:52 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 08:44:59 - mmengine - INFO - Epoch(train) [192][50/293] lr: 5.000000e-05 eta: 0:39:24 time: 0.517604 data_time: 0.084018 memory: 9871 loss_kpt: 0.000515 acc_pose: 0.844705 loss: 0.000515 2022/09/14 08:45:24 - mmengine - INFO - Epoch(train) [192][100/293] lr: 5.000000e-05 eta: 0:39:03 time: 0.510008 data_time: 0.079416 memory: 9871 loss_kpt: 0.000531 acc_pose: 0.863680 loss: 0.000531 2022/09/14 08:45:49 - mmengine - INFO - Epoch(train) [192][150/293] lr: 5.000000e-05 eta: 0:38:42 time: 0.500995 data_time: 0.078055 memory: 9871 loss_kpt: 0.000528 acc_pose: 0.832391 loss: 0.000528 2022/09/14 08:46:15 - mmengine - INFO - Epoch(train) [192][200/293] lr: 5.000000e-05 eta: 0:38:20 time: 0.504518 data_time: 0.083384 memory: 9871 loss_kpt: 0.000524 acc_pose: 0.862806 loss: 0.000524 2022/09/14 08:46:39 - mmengine - INFO - Epoch(train) [192][250/293] lr: 5.000000e-05 eta: 0:37:59 time: 0.497725 data_time: 0.076398 memory: 9871 loss_kpt: 0.000518 acc_pose: 0.858595 loss: 0.000518 2022/09/14 08:47:01 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 08:47:01 - mmengine - INFO - Saving checkpoint at 192 epochs 2022/09/14 08:47:30 - mmengine - INFO - Epoch(train) [193][50/293] lr: 5.000000e-05 eta: 0:37:18 time: 0.521238 data_time: 0.107937 memory: 9871 loss_kpt: 0.000503 acc_pose: 0.890563 loss: 0.000503 2022/09/14 08:47:55 - mmengine - INFO - Epoch(train) [193][100/293] lr: 5.000000e-05 eta: 0:36:57 time: 0.497819 data_time: 0.082825 memory: 9871 loss_kpt: 0.000524 acc_pose: 0.906048 loss: 0.000524 2022/09/14 08:48:20 - mmengine - INFO - Epoch(train) [193][150/293] lr: 5.000000e-05 eta: 0:36:36 time: 0.501996 data_time: 0.076590 memory: 9871 loss_kpt: 0.000522 acc_pose: 0.888372 loss: 0.000522 2022/09/14 08:48:46 - mmengine - INFO - Epoch(train) [193][200/293] lr: 5.000000e-05 eta: 0:36:15 time: 0.501163 data_time: 0.074724 memory: 9871 loss_kpt: 0.000521 acc_pose: 0.871908 loss: 0.000521 2022/09/14 08:49:10 - mmengine - INFO - Epoch(train) [193][250/293] lr: 5.000000e-05 eta: 0:35:54 time: 0.495558 data_time: 0.077355 memory: 9871 loss_kpt: 0.000524 acc_pose: 0.851139 loss: 0.000524 2022/09/14 08:49:32 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 08:49:32 - mmengine - INFO - Saving checkpoint at 193 epochs 2022/09/14 08:50:02 - mmengine - INFO - Epoch(train) [194][50/293] lr: 5.000000e-05 eta: 0:35:13 time: 0.533461 data_time: 0.099913 memory: 9871 loss_kpt: 0.000525 acc_pose: 0.878465 loss: 0.000525 2022/09/14 08:50:26 - mmengine - INFO - Epoch(train) [194][100/293] lr: 5.000000e-05 eta: 0:34:52 time: 0.497736 data_time: 0.082662 memory: 9871 loss_kpt: 0.000535 acc_pose: 0.810863 loss: 0.000535 2022/09/14 08:50:52 - mmengine - INFO - Epoch(train) [194][150/293] lr: 5.000000e-05 eta: 0:34:30 time: 0.503286 data_time: 0.075226 memory: 9871 loss_kpt: 0.000506 acc_pose: 0.865798 loss: 0.000506 2022/09/14 08:51:17 - mmengine - INFO - Epoch(train) [194][200/293] lr: 5.000000e-05 eta: 0:34:09 time: 0.499510 data_time: 0.073555 memory: 9871 loss_kpt: 0.000531 acc_pose: 0.839054 loss: 0.000531 2022/09/14 08:51:42 - mmengine - INFO - Epoch(train) [194][250/293] lr: 5.000000e-05 eta: 0:33:48 time: 0.499766 data_time: 0.075965 memory: 9871 loss_kpt: 0.000519 acc_pose: 0.877559 loss: 0.000519 2022/09/14 08:52:04 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 08:52:04 - mmengine - INFO - Saving checkpoint at 194 epochs 2022/09/14 08:52:32 - mmengine - INFO - Epoch(train) [195][50/293] lr: 5.000000e-05 eta: 0:33:07 time: 0.504189 data_time: 0.079158 memory: 9871 loss_kpt: 0.000531 acc_pose: 0.857405 loss: 0.000531 2022/09/14 08:52:57 - mmengine - INFO - Epoch(train) [195][100/293] lr: 5.000000e-05 eta: 0:32:46 time: 0.501605 data_time: 0.071106 memory: 9871 loss_kpt: 0.000514 acc_pose: 0.894588 loss: 0.000514 2022/09/14 08:53:22 - mmengine - INFO - Epoch(train) [195][150/293] lr: 5.000000e-05 eta: 0:32:25 time: 0.498409 data_time: 0.077115 memory: 9871 loss_kpt: 0.000514 acc_pose: 0.851308 loss: 0.000514 2022/09/14 08:53:27 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 08:53:48 - mmengine - INFO - Epoch(train) [195][200/293] lr: 5.000000e-05 eta: 0:32:04 time: 0.508160 data_time: 0.076076 memory: 9871 loss_kpt: 0.000513 acc_pose: 0.864980 loss: 0.000513 2022/09/14 08:54:13 - mmengine - INFO - Epoch(train) [195][250/293] lr: 5.000000e-05 eta: 0:31:43 time: 0.500187 data_time: 0.072520 memory: 9871 loss_kpt: 0.000522 acc_pose: 0.839256 loss: 0.000522 2022/09/14 08:54:33 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 08:54:33 - mmengine - INFO - Saving checkpoint at 195 epochs 2022/09/14 08:55:02 - mmengine - INFO - Epoch(train) [196][50/293] lr: 5.000000e-05 eta: 0:31:02 time: 0.515364 data_time: 0.076299 memory: 9871 loss_kpt: 0.000527 acc_pose: 0.853557 loss: 0.000527 2022/09/14 08:55:27 - mmengine - INFO - Epoch(train) [196][100/293] lr: 5.000000e-05 eta: 0:30:40 time: 0.501008 data_time: 0.075770 memory: 9871 loss_kpt: 0.000524 acc_pose: 0.899683 loss: 0.000524 2022/09/14 08:55:53 - mmengine - INFO - Epoch(train) [196][150/293] lr: 5.000000e-05 eta: 0:30:19 time: 0.508790 data_time: 0.079806 memory: 9871 loss_kpt: 0.000506 acc_pose: 0.855708 loss: 0.000506 2022/09/14 08:56:18 - mmengine - INFO - Epoch(train) [196][200/293] lr: 5.000000e-05 eta: 0:29:58 time: 0.495058 data_time: 0.083101 memory: 9871 loss_kpt: 0.000526 acc_pose: 0.866650 loss: 0.000526 2022/09/14 08:56:42 - mmengine - INFO - Epoch(train) [196][250/293] lr: 5.000000e-05 eta: 0:29:37 time: 0.486121 data_time: 0.071482 memory: 9871 loss_kpt: 0.000524 acc_pose: 0.876977 loss: 0.000524 2022/09/14 08:57:04 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 08:57:04 - mmengine - INFO - Saving checkpoint at 196 epochs 2022/09/14 08:57:33 - mmengine - INFO - Epoch(train) [197][50/293] lr: 5.000000e-05 eta: 0:28:56 time: 0.512856 data_time: 0.081854 memory: 9871 loss_kpt: 0.000522 acc_pose: 0.839547 loss: 0.000522 2022/09/14 08:57:58 - mmengine - INFO - Epoch(train) [197][100/293] lr: 5.000000e-05 eta: 0:28:35 time: 0.504214 data_time: 0.081339 memory: 9871 loss_kpt: 0.000517 acc_pose: 0.885135 loss: 0.000517 2022/09/14 08:58:23 - mmengine - INFO - Epoch(train) [197][150/293] lr: 5.000000e-05 eta: 0:28:14 time: 0.501985 data_time: 0.082401 memory: 9871 loss_kpt: 0.000529 acc_pose: 0.893177 loss: 0.000529 2022/09/14 08:58:48 - mmengine - INFO - Epoch(train) [197][200/293] lr: 5.000000e-05 eta: 0:27:52 time: 0.502893 data_time: 0.078139 memory: 9871 loss_kpt: 0.000514 acc_pose: 0.875027 loss: 0.000514 2022/09/14 08:59:13 - mmengine - INFO - Epoch(train) [197][250/293] lr: 5.000000e-05 eta: 0:27:31 time: 0.497832 data_time: 0.074308 memory: 9871 loss_kpt: 0.000513 acc_pose: 0.894963 loss: 0.000513 2022/09/14 08:59:34 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 08:59:34 - mmengine - INFO - Saving checkpoint at 197 epochs 2022/09/14 09:00:03 - mmengine - INFO - Epoch(train) [198][50/293] lr: 5.000000e-05 eta: 0:26:50 time: 0.508557 data_time: 0.086114 memory: 9871 loss_kpt: 0.000521 acc_pose: 0.850909 loss: 0.000521 2022/09/14 09:00:28 - mmengine - INFO - Epoch(train) [198][100/293] lr: 5.000000e-05 eta: 0:26:29 time: 0.505681 data_time: 0.076400 memory: 9871 loss_kpt: 0.000521 acc_pose: 0.859245 loss: 0.000521 2022/09/14 09:00:53 - mmengine - INFO - Epoch(train) [198][150/293] lr: 5.000000e-05 eta: 0:26:08 time: 0.505299 data_time: 0.076147 memory: 9871 loss_kpt: 0.000518 acc_pose: 0.862477 loss: 0.000518 2022/09/14 09:01:18 - mmengine - INFO - Epoch(train) [198][200/293] lr: 5.000000e-05 eta: 0:25:47 time: 0.505070 data_time: 0.081420 memory: 9871 loss_kpt: 0.000515 acc_pose: 0.869332 loss: 0.000515 2022/09/14 09:01:43 - mmengine - INFO - Epoch(train) [198][250/293] lr: 5.000000e-05 eta: 0:25:26 time: 0.495203 data_time: 0.071804 memory: 9871 loss_kpt: 0.000510 acc_pose: 0.857930 loss: 0.000510 2022/09/14 09:01:58 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 09:02:05 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 09:02:05 - mmengine - INFO - Saving checkpoint at 198 epochs 2022/09/14 09:02:33 - mmengine - INFO - Epoch(train) [199][50/293] lr: 5.000000e-05 eta: 0:24:45 time: 0.509732 data_time: 0.083665 memory: 9871 loss_kpt: 0.000520 acc_pose: 0.878579 loss: 0.000520 2022/09/14 09:02:58 - mmengine - INFO - Epoch(train) [199][100/293] lr: 5.000000e-05 eta: 0:24:24 time: 0.496742 data_time: 0.071698 memory: 9871 loss_kpt: 0.000521 acc_pose: 0.872647 loss: 0.000521 2022/09/14 09:03:23 - mmengine - INFO - Epoch(train) [199][150/293] lr: 5.000000e-05 eta: 0:24:02 time: 0.492747 data_time: 0.076537 memory: 9871 loss_kpt: 0.000525 acc_pose: 0.851669 loss: 0.000525 2022/09/14 09:03:48 - mmengine - INFO - Epoch(train) [199][200/293] lr: 5.000000e-05 eta: 0:23:41 time: 0.501443 data_time: 0.075291 memory: 9871 loss_kpt: 0.000525 acc_pose: 0.829081 loss: 0.000525 2022/09/14 09:04:13 - mmengine - INFO - Epoch(train) [199][250/293] lr: 5.000000e-05 eta: 0:23:20 time: 0.504545 data_time: 0.081609 memory: 9871 loss_kpt: 0.000516 acc_pose: 0.832793 loss: 0.000516 2022/09/14 09:04:35 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 09:04:35 - mmengine - INFO - Saving checkpoint at 199 epochs 2022/09/14 09:05:03 - mmengine - INFO - Epoch(train) [200][50/293] lr: 5.000000e-05 eta: 0:22:39 time: 0.510560 data_time: 0.090235 memory: 9871 loss_kpt: 0.000516 acc_pose: 0.866461 loss: 0.000516 2022/09/14 09:05:29 - mmengine - INFO - Epoch(train) [200][100/293] lr: 5.000000e-05 eta: 0:22:18 time: 0.504708 data_time: 0.073266 memory: 9871 loss_kpt: 0.000530 acc_pose: 0.839251 loss: 0.000530 2022/09/14 09:05:53 - mmengine - INFO - Epoch(train) [200][150/293] lr: 5.000000e-05 eta: 0:21:57 time: 0.491694 data_time: 0.071115 memory: 9871 loss_kpt: 0.000521 acc_pose: 0.853314 loss: 0.000521 2022/09/14 09:06:18 - mmengine - INFO - Epoch(train) [200][200/293] lr: 5.000000e-05 eta: 0:21:36 time: 0.505775 data_time: 0.076260 memory: 9871 loss_kpt: 0.000520 acc_pose: 0.866160 loss: 0.000520 2022/09/14 09:06:43 - mmengine - INFO - Epoch(train) [200][250/293] lr: 5.000000e-05 eta: 0:21:14 time: 0.496168 data_time: 0.071622 memory: 9871 loss_kpt: 0.000515 acc_pose: 0.820488 loss: 0.000515 2022/09/14 09:07:05 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 09:07:05 - mmengine - INFO - Saving checkpoint at 200 epochs 2022/09/14 09:07:15 - mmengine - INFO - Epoch(val) [200][50/407] eta: 0:00:48 time: 0.136927 data_time: 0.013659 memory: 9871 2022/09/14 09:07:22 - mmengine - INFO - Epoch(val) [200][100/407] eta: 0:00:39 time: 0.129020 data_time: 0.008667 memory: 920 2022/09/14 09:07:28 - mmengine - INFO - Epoch(val) [200][150/407] eta: 0:00:33 time: 0.130897 data_time: 0.007983 memory: 920 2022/09/14 09:07:35 - mmengine - INFO - Epoch(val) [200][200/407] eta: 0:00:26 time: 0.129769 data_time: 0.008987 memory: 920 2022/09/14 09:07:42 - mmengine - INFO - Epoch(val) [200][250/407] eta: 0:00:21 time: 0.138478 data_time: 0.010266 memory: 920 2022/09/14 09:07:49 - mmengine - INFO - Epoch(val) [200][300/407] eta: 0:00:14 time: 0.135269 data_time: 0.008972 memory: 920 2022/09/14 09:07:55 - mmengine - INFO - Epoch(val) [200][350/407] eta: 0:00:07 time: 0.132213 data_time: 0.008262 memory: 920 2022/09/14 09:08:02 - mmengine - INFO - Epoch(val) [200][400/407] eta: 0:00:00 time: 0.128316 data_time: 0.008496 memory: 920 2022/09/14 09:08:39 - mmengine - INFO - Evaluating CocoMetric... 2022/09/14 09:08:53 - mmengine - INFO - Epoch(val) [200][407/407] coco/AP: 0.760346 coco/AP .5: 0.906593 coco/AP .75: 0.826290 coco/AP (M): 0.721369 coco/AP (L): 0.830677 coco/AR: 0.809761 coco/AR .5: 0.942695 coco/AR .75: 0.869175 coco/AR (M): 0.766430 coco/AR (L): 0.872798 2022/09/14 09:09:19 - mmengine - INFO - Epoch(train) [201][50/293] lr: 5.000000e-06 eta: 0:20:34 time: 0.517659 data_time: 0.086073 memory: 9871 loss_kpt: 0.000516 acc_pose: 0.870809 loss: 0.000516 2022/09/14 09:09:44 - mmengine - INFO - Epoch(train) [201][100/293] lr: 5.000000e-06 eta: 0:20:13 time: 0.502621 data_time: 0.076468 memory: 9871 loss_kpt: 0.000521 acc_pose: 0.833956 loss: 0.000521 2022/09/14 09:10:10 - mmengine - INFO - Epoch(train) [201][150/293] lr: 5.000000e-06 eta: 0:19:51 time: 0.510604 data_time: 0.073330 memory: 9871 loss_kpt: 0.000513 acc_pose: 0.868871 loss: 0.000513 2022/09/14 09:10:35 - mmengine - INFO - Epoch(train) [201][200/293] lr: 5.000000e-06 eta: 0:19:30 time: 0.504383 data_time: 0.077463 memory: 9871 loss_kpt: 0.000526 acc_pose: 0.880970 loss: 0.000526 2022/09/14 09:11:00 - mmengine - INFO - Epoch(train) [201][250/293] lr: 5.000000e-06 eta: 0:19:09 time: 0.499262 data_time: 0.079997 memory: 9871 loss_kpt: 0.000524 acc_pose: 0.878879 loss: 0.000524 2022/09/14 09:11:21 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 09:11:21 - mmengine - INFO - Saving checkpoint at 201 epochs 2022/09/14 09:11:50 - mmengine - INFO - Epoch(train) [202][50/293] lr: 5.000000e-06 eta: 0:18:28 time: 0.518788 data_time: 0.087987 memory: 9871 loss_kpt: 0.000523 acc_pose: 0.852415 loss: 0.000523 2022/09/14 09:12:15 - mmengine - INFO - Epoch(train) [202][100/293] lr: 5.000000e-06 eta: 0:18:07 time: 0.492415 data_time: 0.074890 memory: 9871 loss_kpt: 0.000519 acc_pose: 0.842462 loss: 0.000519 2022/09/14 09:12:18 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 09:12:40 - mmengine - INFO - Epoch(train) [202][150/293] lr: 5.000000e-06 eta: 0:17:46 time: 0.493880 data_time: 0.075003 memory: 9871 loss_kpt: 0.000524 acc_pose: 0.890260 loss: 0.000524 2022/09/14 09:13:05 - mmengine - INFO - Epoch(train) [202][200/293] lr: 5.000000e-06 eta: 0:17:24 time: 0.506591 data_time: 0.081893 memory: 9871 loss_kpt: 0.000528 acc_pose: 0.856497 loss: 0.000528 2022/09/14 09:13:30 - mmengine - INFO - Epoch(train) [202][250/293] lr: 5.000000e-06 eta: 0:17:03 time: 0.504042 data_time: 0.078555 memory: 9871 loss_kpt: 0.000523 acc_pose: 0.867792 loss: 0.000523 2022/09/14 09:13:52 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 09:13:52 - mmengine - INFO - Saving checkpoint at 202 epochs 2022/09/14 09:14:21 - mmengine - INFO - Epoch(train) [203][50/293] lr: 5.000000e-06 eta: 0:16:23 time: 0.512366 data_time: 0.085046 memory: 9871 loss_kpt: 0.000527 acc_pose: 0.809088 loss: 0.000527 2022/09/14 09:14:46 - mmengine - INFO - Epoch(train) [203][100/293] lr: 5.000000e-06 eta: 0:16:01 time: 0.499852 data_time: 0.075116 memory: 9871 loss_kpt: 0.000510 acc_pose: 0.855204 loss: 0.000510 2022/09/14 09:15:11 - mmengine - INFO - Epoch(train) [203][150/293] lr: 5.000000e-06 eta: 0:15:40 time: 0.507038 data_time: 0.075851 memory: 9871 loss_kpt: 0.000521 acc_pose: 0.881069 loss: 0.000521 2022/09/14 09:15:36 - mmengine - INFO - Epoch(train) [203][200/293] lr: 5.000000e-06 eta: 0:15:19 time: 0.506243 data_time: 0.078220 memory: 9871 loss_kpt: 0.000524 acc_pose: 0.843822 loss: 0.000524 2022/09/14 09:16:02 - mmengine - INFO - Epoch(train) [203][250/293] lr: 5.000000e-06 eta: 0:14:58 time: 0.506905 data_time: 0.074580 memory: 9871 loss_kpt: 0.000522 acc_pose: 0.883431 loss: 0.000522 2022/09/14 09:16:23 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 09:16:23 - mmengine - INFO - Saving checkpoint at 203 epochs 2022/09/14 09:16:53 - mmengine - INFO - Epoch(train) [204][50/293] lr: 5.000000e-06 eta: 0:14:17 time: 0.541867 data_time: 0.107005 memory: 9871 loss_kpt: 0.000514 acc_pose: 0.885814 loss: 0.000514 2022/09/14 09:17:18 - mmengine - INFO - Epoch(train) [204][100/293] lr: 5.000000e-06 eta: 0:13:56 time: 0.501932 data_time: 0.077208 memory: 9871 loss_kpt: 0.000525 acc_pose: 0.904025 loss: 0.000525 2022/09/14 09:17:44 - mmengine - INFO - Epoch(train) [204][150/293] lr: 5.000000e-06 eta: 0:13:35 time: 0.505502 data_time: 0.076218 memory: 9871 loss_kpt: 0.000504 acc_pose: 0.819053 loss: 0.000504 2022/09/14 09:18:09 - mmengine - INFO - Epoch(train) [204][200/293] lr: 5.000000e-06 eta: 0:13:13 time: 0.500120 data_time: 0.071697 memory: 9871 loss_kpt: 0.000530 acc_pose: 0.837930 loss: 0.000530 2022/09/14 09:18:34 - mmengine - INFO - Epoch(train) [204][250/293] lr: 5.000000e-06 eta: 0:12:52 time: 0.499675 data_time: 0.075116 memory: 9871 loss_kpt: 0.000513 acc_pose: 0.862304 loss: 0.000513 2022/09/14 09:18:55 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 09:18:55 - mmengine - INFO - Saving checkpoint at 204 epochs 2022/09/14 09:19:24 - mmengine - INFO - Epoch(train) [205][50/293] lr: 5.000000e-06 eta: 0:12:12 time: 0.508246 data_time: 0.082517 memory: 9871 loss_kpt: 0.000522 acc_pose: 0.871653 loss: 0.000522 2022/09/14 09:19:49 - mmengine - INFO - Epoch(train) [205][100/293] lr: 5.000000e-06 eta: 0:11:50 time: 0.506666 data_time: 0.078927 memory: 9871 loss_kpt: 0.000519 acc_pose: 0.882166 loss: 0.000519 2022/09/14 09:20:14 - mmengine - INFO - Epoch(train) [205][150/293] lr: 5.000000e-06 eta: 0:11:29 time: 0.496474 data_time: 0.076731 memory: 9871 loss_kpt: 0.000518 acc_pose: 0.839204 loss: 0.000518 2022/09/14 09:20:39 - mmengine - INFO - Epoch(train) [205][200/293] lr: 5.000000e-06 eta: 0:11:08 time: 0.501520 data_time: 0.075141 memory: 9871 loss_kpt: 0.000506 acc_pose: 0.897632 loss: 0.000506 2022/09/14 09:20:53 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 09:21:03 - mmengine - INFO - Epoch(train) [205][250/293] lr: 5.000000e-06 eta: 0:10:46 time: 0.490341 data_time: 0.076699 memory: 9871 loss_kpt: 0.000531 acc_pose: 0.855447 loss: 0.000531 2022/09/14 09:21:25 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 09:21:25 - mmengine - INFO - Saving checkpoint at 205 epochs 2022/09/14 09:21:53 - mmengine - INFO - Epoch(train) [206][50/293] lr: 5.000000e-06 eta: 0:10:06 time: 0.511142 data_time: 0.084380 memory: 9871 loss_kpt: 0.000516 acc_pose: 0.876003 loss: 0.000516 2022/09/14 09:22:19 - mmengine - INFO - Epoch(train) [206][100/293] lr: 5.000000e-06 eta: 0:09:45 time: 0.507412 data_time: 0.080350 memory: 9871 loss_kpt: 0.000531 acc_pose: 0.879425 loss: 0.000531 2022/09/14 09:22:44 - mmengine - INFO - Epoch(train) [206][150/293] lr: 5.000000e-06 eta: 0:09:23 time: 0.509150 data_time: 0.079151 memory: 9871 loss_kpt: 0.000516 acc_pose: 0.805270 loss: 0.000516 2022/09/14 09:23:10 - mmengine - INFO - Epoch(train) [206][200/293] lr: 5.000000e-06 eta: 0:09:02 time: 0.507565 data_time: 0.075606 memory: 9871 loss_kpt: 0.000516 acc_pose: 0.865177 loss: 0.000516 2022/09/14 09:23:34 - mmengine - INFO - Epoch(train) [206][250/293] lr: 5.000000e-06 eta: 0:08:41 time: 0.491580 data_time: 0.075067 memory: 9871 loss_kpt: 0.000505 acc_pose: 0.899128 loss: 0.000505 2022/09/14 09:23:55 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 09:23:55 - mmengine - INFO - Saving checkpoint at 206 epochs 2022/09/14 09:24:25 - mmengine - INFO - Epoch(train) [207][50/293] lr: 5.000000e-06 eta: 0:08:00 time: 0.530544 data_time: 0.104717 memory: 9871 loss_kpt: 0.000519 acc_pose: 0.851473 loss: 0.000519 2022/09/14 09:24:50 - mmengine - INFO - Epoch(train) [207][100/293] lr: 5.000000e-06 eta: 0:07:39 time: 0.496747 data_time: 0.077105 memory: 9871 loss_kpt: 0.000522 acc_pose: 0.861821 loss: 0.000522 2022/09/14 09:25:15 - mmengine - INFO - Epoch(train) [207][150/293] lr: 5.000000e-06 eta: 0:07:18 time: 0.504744 data_time: 0.076278 memory: 9871 loss_kpt: 0.000515 acc_pose: 0.893629 loss: 0.000515 2022/09/14 09:25:40 - mmengine - INFO - Epoch(train) [207][200/293] lr: 5.000000e-06 eta: 0:06:56 time: 0.485687 data_time: 0.077315 memory: 9871 loss_kpt: 0.000508 acc_pose: 0.859947 loss: 0.000508 2022/09/14 09:26:04 - mmengine - INFO - Epoch(train) [207][250/293] lr: 5.000000e-06 eta: 0:06:35 time: 0.490284 data_time: 0.074608 memory: 9871 loss_kpt: 0.000525 acc_pose: 0.860558 loss: 0.000525 2022/09/14 09:26:26 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 09:26:26 - mmengine - INFO - Saving checkpoint at 207 epochs 2022/09/14 09:26:56 - mmengine - INFO - Epoch(train) [208][50/293] lr: 5.000000e-06 eta: 0:05:55 time: 0.515419 data_time: 0.086773 memory: 9871 loss_kpt: 0.000518 acc_pose: 0.860575 loss: 0.000518 2022/09/14 09:27:22 - mmengine - INFO - Epoch(train) [208][100/293] lr: 5.000000e-06 eta: 0:05:33 time: 0.508660 data_time: 0.077113 memory: 9871 loss_kpt: 0.000522 acc_pose: 0.825390 loss: 0.000522 2022/09/14 09:27:47 - mmengine - INFO - Epoch(train) [208][150/293] lr: 5.000000e-06 eta: 0:05:12 time: 0.501305 data_time: 0.085204 memory: 9871 loss_kpt: 0.000509 acc_pose: 0.904264 loss: 0.000509 2022/09/14 09:28:12 - mmengine - INFO - Epoch(train) [208][200/293] lr: 5.000000e-06 eta: 0:04:51 time: 0.495796 data_time: 0.075651 memory: 9871 loss_kpt: 0.000511 acc_pose: 0.882675 loss: 0.000511 2022/09/14 09:28:36 - mmengine - INFO - Epoch(train) [208][250/293] lr: 5.000000e-06 eta: 0:04:29 time: 0.498873 data_time: 0.073087 memory: 9871 loss_kpt: 0.000519 acc_pose: 0.863179 loss: 0.000519 2022/09/14 09:28:58 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 09:28:58 - mmengine - INFO - Saving checkpoint at 208 epochs 2022/09/14 09:29:27 - mmengine - INFO - Epoch(train) [209][50/293] lr: 5.000000e-06 eta: 0:03:49 time: 0.510789 data_time: 0.084919 memory: 9871 loss_kpt: 0.000515 acc_pose: 0.840958 loss: 0.000515 2022/09/14 09:29:30 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 09:29:52 - mmengine - INFO - Epoch(train) [209][100/293] lr: 5.000000e-06 eta: 0:03:28 time: 0.513359 data_time: 0.080472 memory: 9871 loss_kpt: 0.000512 acc_pose: 0.869923 loss: 0.000512 2022/09/14 09:30:18 - mmengine - INFO - Epoch(train) [209][150/293] lr: 5.000000e-06 eta: 0:03:06 time: 0.508102 data_time: 0.073101 memory: 9871 loss_kpt: 0.000512 acc_pose: 0.872660 loss: 0.000512 2022/09/14 09:30:43 - mmengine - INFO - Epoch(train) [209][200/293] lr: 5.000000e-06 eta: 0:02:45 time: 0.499631 data_time: 0.080185 memory: 9871 loss_kpt: 0.000514 acc_pose: 0.867306 loss: 0.000514 2022/09/14 09:31:08 - mmengine - INFO - Epoch(train) [209][250/293] lr: 5.000000e-06 eta: 0:02:24 time: 0.503810 data_time: 0.075738 memory: 9871 loss_kpt: 0.000519 acc_pose: 0.875676 loss: 0.000519 2022/09/14 09:31:29 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 09:31:29 - mmengine - INFO - Saving checkpoint at 209 epochs 2022/09/14 09:31:58 - mmengine - INFO - Epoch(train) [210][50/293] lr: 5.000000e-06 eta: 0:01:44 time: 0.504521 data_time: 0.085814 memory: 9871 loss_kpt: 0.000519 acc_pose: 0.879056 loss: 0.000519 2022/09/14 09:32:23 - mmengine - INFO - Epoch(train) [210][100/293] lr: 5.000000e-06 eta: 0:01:22 time: 0.500948 data_time: 0.071956 memory: 9871 loss_kpt: 0.000515 acc_pose: 0.868890 loss: 0.000515 2022/09/14 09:32:48 - mmengine - INFO - Epoch(train) [210][150/293] lr: 5.000000e-06 eta: 0:01:01 time: 0.499507 data_time: 0.079976 memory: 9871 loss_kpt: 0.000518 acc_pose: 0.859312 loss: 0.000518 2022/09/14 09:33:13 - mmengine - INFO - Epoch(train) [210][200/293] lr: 5.000000e-06 eta: 0:00:39 time: 0.509008 data_time: 0.075546 memory: 9871 loss_kpt: 0.000518 acc_pose: 0.839901 loss: 0.000518 2022/09/14 09:33:38 - mmengine - INFO - Epoch(train) [210][250/293] lr: 5.000000e-06 eta: 0:00:18 time: 0.498811 data_time: 0.077265 memory: 9871 loss_kpt: 0.000519 acc_pose: 0.883033 loss: 0.000519 2022/09/14 09:34:00 - mmengine - INFO - Exp name: td-hm_hrnet-w32_udp-8xb64-210e_coco-256x192_20220914_001047 2022/09/14 09:34:00 - mmengine - INFO - Saving checkpoint at 210 epochs 2022/09/14 09:34:10 - mmengine - INFO - Epoch(val) [210][50/407] eta: 0:00:49 time: 0.138351 data_time: 0.014250 memory: 9871 2022/09/14 09:34:17 - mmengine - INFO - Epoch(val) [210][100/407] eta: 0:00:41 time: 0.134869 data_time: 0.013181 memory: 920 2022/09/14 09:34:23 - mmengine - INFO - Epoch(val) [210][150/407] eta: 0:00:33 time: 0.129848 data_time: 0.008334 memory: 920 2022/09/14 09:34:30 - mmengine - INFO - Epoch(val) [210][200/407] eta: 0:00:27 time: 0.131285 data_time: 0.009158 memory: 920 2022/09/14 09:34:36 - mmengine - INFO - Epoch(val) [210][250/407] eta: 0:00:20 time: 0.131046 data_time: 0.008462 memory: 920 2022/09/14 09:34:43 - mmengine - INFO - Epoch(val) [210][300/407] eta: 0:00:14 time: 0.131254 data_time: 0.008118 memory: 920 2022/09/14 09:34:50 - mmengine - INFO - Epoch(val) [210][350/407] eta: 0:00:07 time: 0.132234 data_time: 0.009058 memory: 920 2022/09/14 09:34:56 - mmengine - INFO - Epoch(val) [210][400/407] eta: 0:00:00 time: 0.127807 data_time: 0.008132 memory: 920 2022/09/14 09:35:33 - mmengine - INFO - Evaluating CocoMetric... 2022/09/14 09:35:47 - mmengine - INFO - Epoch(val) [210][407/407] coco/AP: 0.760670 coco/AP .5: 0.906310 coco/AP .75: 0.826089 coco/AP (M): 0.721984 coco/AP (L): 0.830647 coco/AR: 0.810139 coco/AR .5: 0.941751 coco/AR .75: 0.869962 coco/AR (M): 0.766621 coco/AR (L): 0.872947