2022/09/14 00:20:44 - 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: 491545548 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 00:20:46 - 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), type='AmpOptimWrapper', loss_scale='dynamic') param_scheduler = [ dict( type='LinearLR', begin=0, end=500, start_factor=0.001, by_epoch=False), dict( type='MultiStepLR', begin=0, end=210, milestones=[170, 200], gamma=0.1, by_epoch=True) ] auto_scale_lr = dict(base_batch_size=512) codec = dict( type='MSRAHeatmap', input_size=(192, 256), heatmap_size=(48, 64), sigma=2) model = dict( type='TopdownPoseEstimator', data_preprocessor=dict( type='PoseDataPreprocessor', mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], bgr_to_rgb=True), backbone=dict( type='HRNet', in_channels=3, extra=dict( stage1=dict( num_modules=1, num_branches=1, block='BOTTLENECK', num_blocks=(4, ), num_channels=(64, )), stage2=dict( num_modules=1, num_branches=2, block='BASIC', num_blocks=(4, 4), num_channels=(32, 64)), stage3=dict( num_modules=4, num_branches=3, block='BASIC', num_blocks=(4, 4, 4), num_channels=(32, 64, 128)), stage4=dict( num_modules=3, num_branches=4, block='BASIC', num_blocks=(4, 4, 4, 4), num_channels=(32, 64, 128, 256))), init_cfg=dict( type='Pretrained', checkpoint= 'https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w32-36af842e.pth' )), head=dict( type='HeatmapHead', in_channels=32, out_channels=17, deconv_out_channels=None, loss=dict(type='KeypointMSELoss', use_target_weight=True), decoder=dict( type='MSRAHeatmap', input_size=(192, 256), heatmap_size=(48, 64), sigma=2)), test_cfg=dict(flip_test=True, flip_mode='heatmap', shift_heatmap=True)) dataset_type = 'CocoDataset' data_mode = 'topdown' data_root = 'data/coco/' train_pipeline = [ dict( type='LoadImage', file_client_args=dict( backend='petrel', path_mapping=dict({ './data/': 's3://openmmlab/datasets/detection/', 'data/': 's3://openmmlab/datasets/detection/' }))), dict(type='GetBBoxCenterScale'), dict(type='RandomFlip', direction='horizontal'), dict(type='RandomHalfBody'), dict(type='RandomBBoxTransform'), dict(type='TopdownAffine', input_size=(192, 256)), dict( type='GenerateTarget', target_type='heatmap', encoder=dict( type='MSRAHeatmap', input_size=(192, 256), heatmap_size=(48, 64), sigma=2)), dict(type='PackPoseInputs') ] test_pipeline = [ dict( type='LoadImage', file_client_args=dict( backend='petrel', path_mapping=dict({ './data/': 's3://openmmlab/datasets/detection/', 'data/': 's3://openmmlab/datasets/detection/' }))), dict(type='GetBBoxCenterScale'), dict(type='TopdownAffine', input_size=(192, 256)), dict(type='PackPoseInputs') ] train_dataloader = dict( batch_size=64, num_workers=2, persistent_workers=True, sampler=dict(type='DefaultSampler', shuffle=True), dataset=dict( type='CocoDataset', data_root='data/coco/', data_mode='topdown', ann_file='annotations/person_keypoints_train2017.json', data_prefix=dict(img='train2017/'), pipeline=[ dict( type='LoadImage', file_client_args=dict( backend='petrel', path_mapping=dict({ './data/': 's3://openmmlab/datasets/detection/', 'data/': 's3://openmmlab/datasets/detection/' }))), dict(type='GetBBoxCenterScale'), dict(type='RandomFlip', direction='horizontal'), dict(type='RandomHalfBody'), dict(type='RandomBBoxTransform'), dict(type='TopdownAffine', input_size=(192, 256)), dict( type='GenerateTarget', target_type='heatmap', encoder=dict( type='MSRAHeatmap', input_size=(192, 256), heatmap_size=(48, 64), sigma=2)), dict(type='PackPoseInputs') ])) val_dataloader = dict( batch_size=32, num_workers=2, persistent_workers=True, drop_last=False, sampler=dict(type='DefaultSampler', shuffle=False, round_up=False), dataset=dict( type='CocoDataset', data_root='data/coco/', data_mode='topdown', ann_file='annotations/person_keypoints_val2017.json', bbox_file= 'data/coco/person_detection_results/COCO_val2017_detections_AP_H_56_person.json', data_prefix=dict(img='val2017/'), test_mode=True, pipeline=[ dict( type='LoadImage', file_client_args=dict( backend='petrel', path_mapping=dict({ './data/': 's3://openmmlab/datasets/detection/', 'data/': 's3://openmmlab/datasets/detection/' }))), dict(type='GetBBoxCenterScale'), dict(type='TopdownAffine', input_size=(192, 256)), dict(type='PackPoseInputs') ])) test_dataloader = dict( batch_size=32, num_workers=2, persistent_workers=True, drop_last=False, sampler=dict(type='DefaultSampler', shuffle=False, round_up=False), dataset=dict( type='CocoDataset', data_root='data/coco/', data_mode='topdown', ann_file='annotations/person_keypoints_val2017.json', bbox_file= 'data/coco/person_detection_results/COCO_val2017_detections_AP_H_56_person.json', data_prefix=dict(img='val2017/'), test_mode=True, pipeline=[ dict( type='LoadImage', file_client_args=dict( backend='petrel', path_mapping=dict({ './data/': 's3://openmmlab/datasets/detection/', 'data/': 's3://openmmlab/datasets/detection/' }))), dict(type='GetBBoxCenterScale'), dict(type='TopdownAffine', input_size=(192, 256)), dict(type='PackPoseInputs') ])) val_evaluator = dict( type='CocoMetric', ann_file='data/coco/annotations/person_keypoints_val2017.json') test_evaluator = dict( type='CocoMetric', ann_file='data/coco/annotations/person_keypoints_val2017.json') launcher = 'slurm' work_dir = '/mnt/lustre/liqikai/work_dirs/20220914/hrnet_fp16/' 2022/09/14 00:21:23 - 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 00:21:23 - 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 00:21:23 - 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 00:21:23 - 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 00:21:23 - 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 00:21:23 - 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 00:21:23 - 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 00:21:23 - 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 00:21:27 - 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 00:21:30 - 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 00:21:32 - 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 00:21:32 - 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 00:21:47 - mmengine - INFO - Checkpoints will be saved to /mnt/lustre/liqikai/work_dirs/20220914/hrnet_fp16 by HardDiskBackend. 2022/09/14 00:22:22 - mmengine - INFO - Epoch(train) [1][50/293] lr: 4.954910e-05 eta: 12:00:05 time: 0.702759 data_time: 0.248313 memory: 5387 loss_kpt: 0.002203 acc_pose: 0.164161 loss: 0.002203 2022/09/14 00:22:47 - mmengine - INFO - Epoch(train) [1][100/293] lr: 9.959920e-05 eta: 10:17:52 time: 0.504213 data_time: 0.084457 memory: 5387 loss_kpt: 0.001893 acc_pose: 0.362384 loss: 0.001893 2022/09/14 00:23:12 - mmengine - INFO - Epoch(train) [1][150/293] lr: 1.496493e-04 eta: 9:40:29 time: 0.495342 data_time: 0.082435 memory: 5387 loss_kpt: 0.001620 acc_pose: 0.438119 loss: 0.001620 2022/09/14 00:23:37 - mmengine - INFO - Epoch(train) [1][200/293] lr: 1.996994e-04 eta: 9:19:37 time: 0.487651 data_time: 0.077048 memory: 5387 loss_kpt: 0.001437 acc_pose: 0.495695 loss: 0.001437 2022/09/14 00:24:01 - mmengine - INFO - Epoch(train) [1][250/293] lr: 2.497495e-04 eta: 9:06:20 time: 0.484649 data_time: 0.072942 memory: 5387 loss_kpt: 0.001320 acc_pose: 0.573596 loss: 0.001320 2022/09/14 00:24:22 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 00:24:22 - mmengine - INFO - Saving checkpoint at 1 epochs 2022/09/14 00:24:56 - mmengine - INFO - Epoch(train) [2][50/293] lr: 3.428427e-04 eta: 7:52:53 time: 0.506530 data_time: 0.090161 memory: 5387 loss_kpt: 0.001199 acc_pose: 0.655863 loss: 0.001199 2022/09/14 00:25:22 - mmengine - INFO - Epoch(train) [2][100/293] lr: 3.928928e-04 eta: 7:58:07 time: 0.506971 data_time: 0.075282 memory: 5387 loss_kpt: 0.001169 acc_pose: 0.576164 loss: 0.001169 2022/09/14 00:25:47 - mmengine - INFO - Epoch(train) [2][150/293] lr: 4.429429e-04 eta: 8:01:00 time: 0.497763 data_time: 0.075682 memory: 5387 loss_kpt: 0.001143 acc_pose: 0.630383 loss: 0.001143 2022/09/14 00:26:11 - mmengine - INFO - Epoch(train) [2][200/293] lr: 4.929930e-04 eta: 8:02:27 time: 0.490368 data_time: 0.079796 memory: 5387 loss_kpt: 0.001114 acc_pose: 0.677286 loss: 0.001114 2022/09/14 00:26:36 - mmengine - INFO - Epoch(train) [2][250/293] lr: 5.000000e-04 eta: 8:03:32 time: 0.490037 data_time: 0.075412 memory: 5387 loss_kpt: 0.001105 acc_pose: 0.688195 loss: 0.001105 2022/09/14 00:26:57 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 00:26:57 - mmengine - INFO - Saving checkpoint at 2 epochs 2022/09/14 00:27:26 - mmengine - INFO - Epoch(train) [3][50/293] lr: 5.000000e-04 eta: 7:32:30 time: 0.505128 data_time: 0.083761 memory: 5387 loss_kpt: 0.001052 acc_pose: 0.675647 loss: 0.001052 2022/09/14 00:27:51 - mmengine - INFO - Epoch(train) [3][100/293] lr: 5.000000e-04 eta: 7:36:15 time: 0.501548 data_time: 0.084396 memory: 5387 loss_kpt: 0.001025 acc_pose: 0.687441 loss: 0.001025 2022/09/14 00:28:17 - mmengine - INFO - Epoch(train) [3][150/293] lr: 5.000000e-04 eta: 7:39:47 time: 0.506882 data_time: 0.081726 memory: 5387 loss_kpt: 0.001008 acc_pose: 0.597816 loss: 0.001008 2022/09/14 00:28:42 - mmengine - INFO - Epoch(train) [3][200/293] lr: 5.000000e-04 eta: 7:42:23 time: 0.499953 data_time: 0.073395 memory: 5387 loss_kpt: 0.001027 acc_pose: 0.613185 loss: 0.001027 2022/09/14 00:29:07 - mmengine - INFO - Epoch(train) [3][250/293] lr: 5.000000e-04 eta: 7:44:24 time: 0.496434 data_time: 0.078939 memory: 5387 loss_kpt: 0.001000 acc_pose: 0.667079 loss: 0.001000 2022/09/14 00:29:28 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 00:29:28 - mmengine - INFO - Saving checkpoint at 3 epochs 2022/09/14 00:29:58 - mmengine - INFO - Epoch(train) [4][50/293] lr: 5.000000e-04 eta: 7:24:57 time: 0.509101 data_time: 0.088141 memory: 5387 loss_kpt: 0.000990 acc_pose: 0.668237 loss: 0.000990 2022/09/14 00:30:22 - mmengine - INFO - Epoch(train) [4][100/293] lr: 5.000000e-04 eta: 7:27:22 time: 0.494636 data_time: 0.076309 memory: 5387 loss_kpt: 0.000972 acc_pose: 0.688407 loss: 0.000972 2022/09/14 00:30:32 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 00:30:47 - mmengine - INFO - Epoch(train) [4][150/293] lr: 5.000000e-04 eta: 7:29:41 time: 0.498058 data_time: 0.080079 memory: 5387 loss_kpt: 0.000962 acc_pose: 0.675795 loss: 0.000962 2022/09/14 00:31:12 - mmengine - INFO - Epoch(train) [4][200/293] lr: 5.000000e-04 eta: 7:31:48 time: 0.499305 data_time: 0.076523 memory: 5387 loss_kpt: 0.000953 acc_pose: 0.655505 loss: 0.000953 2022/09/14 00:31:38 - mmengine - INFO - Epoch(train) [4][250/293] lr: 5.000000e-04 eta: 7:33:58 time: 0.505305 data_time: 0.084891 memory: 5387 loss_kpt: 0.000963 acc_pose: 0.713357 loss: 0.000963 2022/09/14 00:31:59 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 00:31:59 - mmengine - INFO - Saving checkpoint at 4 epochs 2022/09/14 00:32:34 - mmengine - INFO - Epoch(train) [5][50/293] lr: 5.000000e-04 eta: 7:20:46 time: 0.534739 data_time: 0.097798 memory: 5387 loss_kpt: 0.000937 acc_pose: 0.619785 loss: 0.000937 2022/09/14 00:33:00 - mmengine - INFO - Epoch(train) [5][100/293] lr: 5.000000e-04 eta: 7:23:01 time: 0.504774 data_time: 0.080437 memory: 5387 loss_kpt: 0.000927 acc_pose: 0.718665 loss: 0.000927 2022/09/14 00:33:24 - mmengine - INFO - Epoch(train) [5][150/293] lr: 5.000000e-04 eta: 7:24:48 time: 0.497884 data_time: 0.074144 memory: 5387 loss_kpt: 0.000911 acc_pose: 0.720250 loss: 0.000911 2022/09/14 00:33:49 - mmengine - INFO - Epoch(train) [5][200/293] lr: 5.000000e-04 eta: 7:26:22 time: 0.496257 data_time: 0.079302 memory: 5387 loss_kpt: 0.000934 acc_pose: 0.678721 loss: 0.000934 2022/09/14 00:34:14 - mmengine - INFO - Epoch(train) [5][250/293] lr: 5.000000e-04 eta: 7:27:41 time: 0.493263 data_time: 0.071465 memory: 5387 loss_kpt: 0.000924 acc_pose: 0.740751 loss: 0.000924 2022/09/14 00:34:35 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 00:34:35 - mmengine - INFO - Saving checkpoint at 5 epochs 2022/09/14 00:35:06 - mmengine - INFO - Epoch(train) [6][50/293] lr: 5.000000e-04 eta: 7:17:06 time: 0.531561 data_time: 0.091164 memory: 5387 loss_kpt: 0.000902 acc_pose: 0.685967 loss: 0.000902 2022/09/14 00:35:31 - mmengine - INFO - Epoch(train) [6][100/293] lr: 5.000000e-04 eta: 7:18:31 time: 0.492589 data_time: 0.071267 memory: 5387 loss_kpt: 0.000896 acc_pose: 0.662333 loss: 0.000896 2022/09/14 00:35:55 - mmengine - INFO - Epoch(train) [6][150/293] lr: 5.000000e-04 eta: 7:19:51 time: 0.494140 data_time: 0.078212 memory: 5387 loss_kpt: 0.000902 acc_pose: 0.697627 loss: 0.000902 2022/09/14 00:36:20 - mmengine - INFO - Epoch(train) [6][200/293] lr: 5.000000e-04 eta: 7:21:18 time: 0.500933 data_time: 0.071575 memory: 5387 loss_kpt: 0.000916 acc_pose: 0.753488 loss: 0.000916 2022/09/14 00:36:46 - mmengine - INFO - Epoch(train) [6][250/293] lr: 5.000000e-04 eta: 7:23:09 time: 0.518743 data_time: 0.077486 memory: 5387 loss_kpt: 0.000888 acc_pose: 0.694245 loss: 0.000888 2022/09/14 00:37:08 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 00:37:08 - mmengine - INFO - Saving checkpoint at 6 epochs 2022/09/14 00:37:38 - mmengine - INFO - Epoch(train) [7][50/293] lr: 5.000000e-04 eta: 7:13:44 time: 0.509575 data_time: 0.084226 memory: 5387 loss_kpt: 0.000891 acc_pose: 0.772764 loss: 0.000891 2022/09/14 00:38:03 - mmengine - INFO - Epoch(train) [7][100/293] lr: 5.000000e-04 eta: 7:15:02 time: 0.497613 data_time: 0.078476 memory: 5387 loss_kpt: 0.000892 acc_pose: 0.719181 loss: 0.000892 2022/09/14 00:38:28 - mmengine - INFO - Epoch(train) [7][150/293] lr: 5.000000e-04 eta: 7:16:16 time: 0.499307 data_time: 0.081994 memory: 5387 loss_kpt: 0.000861 acc_pose: 0.735206 loss: 0.000861 2022/09/14 00:38:53 - mmengine - INFO - Epoch(train) [7][200/293] lr: 5.000000e-04 eta: 7:17:20 time: 0.495656 data_time: 0.077443 memory: 5387 loss_kpt: 0.000863 acc_pose: 0.794287 loss: 0.000863 2022/09/14 00:39:14 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 00:39:18 - mmengine - INFO - Epoch(train) [7][250/293] lr: 5.000000e-04 eta: 7:18:34 time: 0.505262 data_time: 0.078128 memory: 5387 loss_kpt: 0.000880 acc_pose: 0.753774 loss: 0.000880 2022/09/14 00:39:40 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 00:39:40 - mmengine - INFO - Saving checkpoint at 7 epochs 2022/09/14 00:40:10 - mmengine - INFO - Epoch(train) [8][50/293] lr: 5.000000e-04 eta: 7:10:41 time: 0.516318 data_time: 0.088361 memory: 5387 loss_kpt: 0.000858 acc_pose: 0.723540 loss: 0.000858 2022/09/14 00:40:35 - mmengine - INFO - Epoch(train) [8][100/293] lr: 5.000000e-04 eta: 7:11:46 time: 0.497907 data_time: 0.073375 memory: 5387 loss_kpt: 0.000866 acc_pose: 0.691978 loss: 0.000866 2022/09/14 00:41:00 - mmengine - INFO - Epoch(train) [8][150/293] lr: 5.000000e-04 eta: 7:12:52 time: 0.501492 data_time: 0.074536 memory: 5387 loss_kpt: 0.000859 acc_pose: 0.686823 loss: 0.000859 2022/09/14 00:41:26 - mmengine - INFO - Epoch(train) [8][200/293] lr: 5.000000e-04 eta: 7:14:14 time: 0.516665 data_time: 0.079850 memory: 5387 loss_kpt: 0.000870 acc_pose: 0.764026 loss: 0.000870 2022/09/14 00:41:51 - mmengine - INFO - Epoch(train) [8][250/293] lr: 5.000000e-04 eta: 7:15:18 time: 0.506133 data_time: 0.075029 memory: 5387 loss_kpt: 0.000849 acc_pose: 0.720758 loss: 0.000849 2022/09/14 00:42:12 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 00:42:12 - mmengine - INFO - Saving checkpoint at 8 epochs 2022/09/14 00:42:43 - mmengine - INFO - Epoch(train) [9][50/293] lr: 5.000000e-04 eta: 7:08:31 time: 0.523797 data_time: 0.088686 memory: 5387 loss_kpt: 0.000841 acc_pose: 0.722131 loss: 0.000841 2022/09/14 00:43:08 - mmengine - INFO - Epoch(train) [9][100/293] lr: 5.000000e-04 eta: 7:09:33 time: 0.504241 data_time: 0.075921 memory: 5387 loss_kpt: 0.000852 acc_pose: 0.730525 loss: 0.000852 2022/09/14 00:43:33 - mmengine - INFO - Epoch(train) [9][150/293] lr: 5.000000e-04 eta: 7:10:30 time: 0.502835 data_time: 0.071818 memory: 5387 loss_kpt: 0.000840 acc_pose: 0.694035 loss: 0.000840 2022/09/14 00:43:58 - mmengine - INFO - Epoch(train) [9][200/293] lr: 5.000000e-04 eta: 7:11:18 time: 0.498141 data_time: 0.075740 memory: 5387 loss_kpt: 0.000839 acc_pose: 0.662270 loss: 0.000839 2022/09/14 00:44:23 - mmengine - INFO - Epoch(train) [9][250/293] lr: 5.000000e-04 eta: 7:11:58 time: 0.493275 data_time: 0.080948 memory: 5387 loss_kpt: 0.000842 acc_pose: 0.733525 loss: 0.000842 2022/09/14 00:44:44 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 00:44:44 - mmengine - INFO - Saving checkpoint at 9 epochs 2022/09/14 00:45:14 - mmengine - INFO - Epoch(train) [10][50/293] lr: 5.000000e-04 eta: 7:05:40 time: 0.510225 data_time: 0.084125 memory: 5387 loss_kpt: 0.000842 acc_pose: 0.793590 loss: 0.000842 2022/09/14 00:45:39 - mmengine - INFO - Epoch(train) [10][100/293] lr: 5.000000e-04 eta: 7:06:18 time: 0.488837 data_time: 0.075624 memory: 5387 loss_kpt: 0.000830 acc_pose: 0.731392 loss: 0.000830 2022/09/14 00:46:04 - mmengine - INFO - Epoch(train) [10][150/293] lr: 5.000000e-04 eta: 7:07:08 time: 0.503305 data_time: 0.074880 memory: 5387 loss_kpt: 0.000817 acc_pose: 0.663927 loss: 0.000817 2022/09/14 00:46:29 - mmengine - INFO - Epoch(train) [10][200/293] lr: 5.000000e-04 eta: 7:07:59 time: 0.506558 data_time: 0.078434 memory: 5387 loss_kpt: 0.000823 acc_pose: 0.727930 loss: 0.000823 2022/09/14 00:46:54 - mmengine - INFO - Epoch(train) [10][250/293] lr: 5.000000e-04 eta: 7:08:39 time: 0.498405 data_time: 0.072762 memory: 5387 loss_kpt: 0.000817 acc_pose: 0.769153 loss: 0.000817 2022/09/14 00:47:16 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 00:47:16 - mmengine - INFO - Saving checkpoint at 10 epochs 2022/09/14 00:47:32 - mmengine - INFO - Epoch(val) [10][50/407] eta: 0:01:09 time: 0.195220 data_time: 0.085498 memory: 5387 2022/09/14 00:47:38 - mmengine - INFO - Epoch(val) [10][100/407] eta: 0:00:35 time: 0.116096 data_time: 0.009796 memory: 920 2022/09/14 00:47:43 - mmengine - INFO - Epoch(val) [10][150/407] eta: 0:00:30 time: 0.117052 data_time: 0.009391 memory: 920 2022/09/14 00:47:49 - mmengine - INFO - Epoch(val) [10][200/407] eta: 0:00:23 time: 0.114591 data_time: 0.008961 memory: 920 2022/09/14 00:47:55 - mmengine - INFO - Epoch(val) [10][250/407] eta: 0:00:18 time: 0.114764 data_time: 0.008599 memory: 920 2022/09/14 00:48:01 - mmengine - INFO - Epoch(val) [10][300/407] eta: 0:00:13 time: 0.123257 data_time: 0.016494 memory: 920 2022/09/14 00:48:07 - mmengine - INFO - Epoch(val) [10][350/407] eta: 0:00:06 time: 0.117733 data_time: 0.009258 memory: 920 2022/09/14 00:48:13 - mmengine - INFO - Epoch(val) [10][400/407] eta: 0:00:00 time: 0.113816 data_time: 0.008589 memory: 920 2022/09/14 00:48:49 - mmengine - INFO - Evaluating CocoMetric... 2022/09/14 00:49:03 - mmengine - INFO - Epoch(val) [10][407/407] coco/AP: 0.648533 coco/AP .5: 0.866241 coco/AP .75: 0.718355 coco/AP (M): 0.616639 coco/AP (L): 0.711533 coco/AR: 0.711681 coco/AR .5: 0.909950 coco/AR .75: 0.779125 coco/AR (M): 0.669899 coco/AR (L): 0.771795 2022/09/14 00:49:06 - mmengine - INFO - The best checkpoint with 0.6485 coco/AP at 10 epoch is saved to best_coco/AP_epoch_10.pth. 2022/09/14 00:49:31 - mmengine - INFO - Epoch(train) [11][50/293] lr: 5.000000e-04 eta: 7:02:54 time: 0.506819 data_time: 0.077878 memory: 5387 loss_kpt: 0.000816 acc_pose: 0.721160 loss: 0.000816 2022/09/14 00:49:42 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 00:49:57 - mmengine - INFO - Epoch(train) [11][100/293] lr: 5.000000e-04 eta: 7:03:43 time: 0.506614 data_time: 0.076354 memory: 5387 loss_kpt: 0.000819 acc_pose: 0.778659 loss: 0.000819 2022/09/14 00:50:22 - mmengine - INFO - Epoch(train) [11][150/293] lr: 5.000000e-04 eta: 7:04:33 time: 0.509599 data_time: 0.074123 memory: 5387 loss_kpt: 0.000804 acc_pose: 0.744896 loss: 0.000804 2022/09/14 00:50:48 - mmengine - INFO - Epoch(train) [11][200/293] lr: 5.000000e-04 eta: 7:05:27 time: 0.516858 data_time: 0.074756 memory: 5387 loss_kpt: 0.000827 acc_pose: 0.750345 loss: 0.000827 2022/09/14 00:51:13 - mmengine - INFO - Epoch(train) [11][250/293] lr: 5.000000e-04 eta: 7:05:58 time: 0.494985 data_time: 0.074270 memory: 5387 loss_kpt: 0.000814 acc_pose: 0.771218 loss: 0.000814 2022/09/14 00:51:35 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 00:51:35 - mmengine - INFO - Saving checkpoint at 11 epochs 2022/09/14 00:52:05 - mmengine - INFO - Epoch(train) [12][50/293] lr: 5.000000e-04 eta: 7:00:57 time: 0.522750 data_time: 0.087168 memory: 5387 loss_kpt: 0.000828 acc_pose: 0.757322 loss: 0.000828 2022/09/14 00:52:31 - mmengine - INFO - Epoch(train) [12][100/293] lr: 5.000000e-04 eta: 7:01:47 time: 0.515642 data_time: 0.077094 memory: 5387 loss_kpt: 0.000819 acc_pose: 0.779102 loss: 0.000819 2022/09/14 00:52:56 - mmengine - INFO - Epoch(train) [12][150/293] lr: 5.000000e-04 eta: 7:02:20 time: 0.498097 data_time: 0.077681 memory: 5387 loss_kpt: 0.000809 acc_pose: 0.720149 loss: 0.000809 2022/09/14 00:53:21 - mmengine - INFO - Epoch(train) [12][200/293] lr: 5.000000e-04 eta: 7:03:01 time: 0.509736 data_time: 0.072866 memory: 5387 loss_kpt: 0.000811 acc_pose: 0.742453 loss: 0.000811 2022/09/14 00:53:46 - mmengine - INFO - Epoch(train) [12][250/293] lr: 5.000000e-04 eta: 7:03:29 time: 0.495991 data_time: 0.081715 memory: 5387 loss_kpt: 0.000803 acc_pose: 0.745190 loss: 0.000803 2022/09/14 00:54:08 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 00:54:08 - mmengine - INFO - Saving checkpoint at 12 epochs 2022/09/14 00:54:38 - mmengine - INFO - Epoch(train) [13][50/293] lr: 5.000000e-04 eta: 6:58:54 time: 0.525704 data_time: 0.086098 memory: 5387 loss_kpt: 0.000806 acc_pose: 0.754147 loss: 0.000806 2022/09/14 00:55:04 - mmengine - INFO - Epoch(train) [13][100/293] lr: 5.000000e-04 eta: 6:59:35 time: 0.511897 data_time: 0.075967 memory: 5387 loss_kpt: 0.000814 acc_pose: 0.790688 loss: 0.000814 2022/09/14 00:55:29 - mmengine - INFO - Epoch(train) [13][150/293] lr: 5.000000e-04 eta: 7:00:08 time: 0.504752 data_time: 0.075358 memory: 5387 loss_kpt: 0.000796 acc_pose: 0.767112 loss: 0.000796 2022/09/14 00:55:54 - mmengine - INFO - Epoch(train) [13][200/293] lr: 5.000000e-04 eta: 7:00:33 time: 0.494875 data_time: 0.081271 memory: 5387 loss_kpt: 0.000807 acc_pose: 0.757213 loss: 0.000807 2022/09/14 00:56:20 - mmengine - INFO - Epoch(train) [13][250/293] lr: 5.000000e-04 eta: 7:01:11 time: 0.514863 data_time: 0.072182 memory: 5387 loss_kpt: 0.000800 acc_pose: 0.813810 loss: 0.000800 2022/09/14 00:56:41 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 00:56:41 - mmengine - INFO - Saving checkpoint at 13 epochs 2022/09/14 00:57:12 - mmengine - INFO - Epoch(train) [14][50/293] lr: 5.000000e-04 eta: 6:56:53 time: 0.522297 data_time: 0.087737 memory: 5387 loss_kpt: 0.000805 acc_pose: 0.764189 loss: 0.000805 2022/09/14 00:57:37 - mmengine - INFO - Epoch(train) [14][100/293] lr: 5.000000e-04 eta: 6:57:25 time: 0.507720 data_time: 0.081030 memory: 5387 loss_kpt: 0.000784 acc_pose: 0.813295 loss: 0.000784 2022/09/14 00:58:02 - mmengine - INFO - Epoch(train) [14][150/293] lr: 5.000000e-04 eta: 6:57:52 time: 0.500612 data_time: 0.074234 memory: 5387 loss_kpt: 0.000785 acc_pose: 0.775891 loss: 0.000785 2022/09/14 00:58:23 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 00:58:28 - mmengine - INFO - Epoch(train) [14][200/293] lr: 5.000000e-04 eta: 6:58:20 time: 0.505198 data_time: 0.083591 memory: 5387 loss_kpt: 0.000800 acc_pose: 0.709151 loss: 0.000800 2022/09/14 00:58:53 - mmengine - INFO - Epoch(train) [14][250/293] lr: 5.000000e-04 eta: 6:58:45 time: 0.502036 data_time: 0.076823 memory: 5387 loss_kpt: 0.000786 acc_pose: 0.762210 loss: 0.000786 2022/09/14 00:59:15 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 00:59:15 - mmengine - INFO - Saving checkpoint at 14 epochs 2022/09/14 00:59:45 - mmengine - INFO - Epoch(train) [15][50/293] lr: 5.000000e-04 eta: 6:54:39 time: 0.516072 data_time: 0.082447 memory: 5387 loss_kpt: 0.000787 acc_pose: 0.789787 loss: 0.000787 2022/09/14 01:00:10 - mmengine - INFO - Epoch(train) [15][100/293] lr: 5.000000e-04 eta: 6:55:08 time: 0.509040 data_time: 0.082762 memory: 5387 loss_kpt: 0.000783 acc_pose: 0.778437 loss: 0.000783 2022/09/14 01:00:35 - mmengine - INFO - Epoch(train) [15][150/293] lr: 5.000000e-04 eta: 6:55:30 time: 0.499411 data_time: 0.074590 memory: 5387 loss_kpt: 0.000801 acc_pose: 0.799286 loss: 0.000801 2022/09/14 01:01:00 - mmengine - INFO - Epoch(train) [15][200/293] lr: 5.000000e-04 eta: 6:55:46 time: 0.492149 data_time: 0.082193 memory: 5387 loss_kpt: 0.000780 acc_pose: 0.839599 loss: 0.000780 2022/09/14 01:01:25 - mmengine - INFO - Epoch(train) [15][250/293] lr: 5.000000e-04 eta: 6:56:13 time: 0.509802 data_time: 0.080733 memory: 5387 loss_kpt: 0.000782 acc_pose: 0.710767 loss: 0.000782 2022/09/14 01:01:46 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 01:01:46 - mmengine - INFO - Saving checkpoint at 15 epochs 2022/09/14 01:02:17 - mmengine - INFO - Epoch(train) [16][50/293] lr: 5.000000e-04 eta: 6:52:25 time: 0.519860 data_time: 0.087399 memory: 5387 loss_kpt: 0.000801 acc_pose: 0.752604 loss: 0.000801 2022/09/14 01:02:42 - mmengine - INFO - Epoch(train) [16][100/293] lr: 5.000000e-04 eta: 6:52:48 time: 0.503527 data_time: 0.072820 memory: 5387 loss_kpt: 0.000782 acc_pose: 0.760087 loss: 0.000782 2022/09/14 01:03:07 - mmengine - INFO - Epoch(train) [16][150/293] lr: 5.000000e-04 eta: 6:53:08 time: 0.500987 data_time: 0.076054 memory: 5387 loss_kpt: 0.000776 acc_pose: 0.697737 loss: 0.000776 2022/09/14 01:03:32 - mmengine - INFO - Epoch(train) [16][200/293] lr: 5.000000e-04 eta: 6:53:26 time: 0.500373 data_time: 0.080208 memory: 5387 loss_kpt: 0.000780 acc_pose: 0.747494 loss: 0.000780 2022/09/14 01:03:57 - mmengine - INFO - Epoch(train) [16][250/293] lr: 5.000000e-04 eta: 6:53:49 time: 0.507482 data_time: 0.077384 memory: 5387 loss_kpt: 0.000795 acc_pose: 0.734423 loss: 0.000795 2022/09/14 01:04:19 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 01:04:19 - mmengine - INFO - Saving checkpoint at 16 epochs 2022/09/14 01:04:53 - mmengine - INFO - Epoch(train) [17][50/293] lr: 5.000000e-04 eta: 6:50:22 time: 0.534206 data_time: 0.087920 memory: 5387 loss_kpt: 0.000785 acc_pose: 0.747154 loss: 0.000785 2022/09/14 01:05:19 - mmengine - INFO - Epoch(train) [17][100/293] lr: 5.000000e-04 eta: 6:50:47 time: 0.513710 data_time: 0.081623 memory: 5387 loss_kpt: 0.000768 acc_pose: 0.745201 loss: 0.000768 2022/09/14 01:05:45 - mmengine - INFO - Epoch(train) [17][150/293] lr: 5.000000e-04 eta: 6:51:10 time: 0.509569 data_time: 0.076873 memory: 5387 loss_kpt: 0.000774 acc_pose: 0.739013 loss: 0.000774 2022/09/14 01:06:10 - mmengine - INFO - Epoch(train) [17][200/293] lr: 5.000000e-04 eta: 6:51:28 time: 0.505049 data_time: 0.081608 memory: 5387 loss_kpt: 0.000777 acc_pose: 0.766042 loss: 0.000777 2022/09/14 01:06:35 - mmengine - INFO - Epoch(train) [17][250/293] lr: 5.000000e-04 eta: 6:51:45 time: 0.502802 data_time: 0.078140 memory: 5387 loss_kpt: 0.000784 acc_pose: 0.706496 loss: 0.000784 2022/09/14 01:06:56 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 01:06:56 - mmengine - INFO - Saving checkpoint at 17 epochs 2022/09/14 01:07:10 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 01:07:27 - mmengine - INFO - Epoch(train) [18][50/293] lr: 5.000000e-04 eta: 6:48:25 time: 0.528422 data_time: 0.090482 memory: 5387 loss_kpt: 0.000767 acc_pose: 0.765471 loss: 0.000767 2022/09/14 01:07:52 - mmengine - INFO - Epoch(train) [18][100/293] lr: 5.000000e-04 eta: 6:48:47 time: 0.511848 data_time: 0.073480 memory: 5387 loss_kpt: 0.000760 acc_pose: 0.795871 loss: 0.000760 2022/09/14 01:08:18 - mmengine - INFO - Epoch(train) [18][150/293] lr: 5.000000e-04 eta: 6:49:07 time: 0.511063 data_time: 0.084237 memory: 5387 loss_kpt: 0.000775 acc_pose: 0.778486 loss: 0.000775 2022/09/14 01:08:43 - mmengine - INFO - Epoch(train) [18][200/293] lr: 5.000000e-04 eta: 6:49:21 time: 0.501130 data_time: 0.082343 memory: 5387 loss_kpt: 0.000781 acc_pose: 0.732199 loss: 0.000781 2022/09/14 01:09:08 - mmengine - INFO - Epoch(train) [18][250/293] lr: 5.000000e-04 eta: 6:49:31 time: 0.494021 data_time: 0.075140 memory: 5387 loss_kpt: 0.000764 acc_pose: 0.753601 loss: 0.000764 2022/09/14 01:09:30 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 01:09:30 - mmengine - INFO - Saving checkpoint at 18 epochs 2022/09/14 01:10:00 - mmengine - INFO - Epoch(train) [19][50/293] lr: 5.000000e-04 eta: 6:46:17 time: 0.520832 data_time: 0.087315 memory: 5387 loss_kpt: 0.000756 acc_pose: 0.786957 loss: 0.000756 2022/09/14 01:10:25 - mmengine - INFO - Epoch(train) [19][100/293] lr: 5.000000e-04 eta: 6:46:27 time: 0.495546 data_time: 0.081801 memory: 5387 loss_kpt: 0.000770 acc_pose: 0.775991 loss: 0.000770 2022/09/14 01:10:50 - mmengine - INFO - Epoch(train) [19][150/293] lr: 5.000000e-04 eta: 6:46:45 time: 0.510736 data_time: 0.076503 memory: 5387 loss_kpt: 0.000777 acc_pose: 0.790047 loss: 0.000777 2022/09/14 01:11:16 - mmengine - INFO - Epoch(train) [19][200/293] lr: 5.000000e-04 eta: 6:47:03 time: 0.512434 data_time: 0.076208 memory: 5387 loss_kpt: 0.000767 acc_pose: 0.813196 loss: 0.000767 2022/09/14 01:11:41 - mmengine - INFO - Epoch(train) [19][250/293] lr: 5.000000e-04 eta: 6:47:16 time: 0.504204 data_time: 0.078870 memory: 5387 loss_kpt: 0.000766 acc_pose: 0.785783 loss: 0.000766 2022/09/14 01:12:03 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 01:12:03 - mmengine - INFO - Saving checkpoint at 19 epochs 2022/09/14 01:12:33 - mmengine - INFO - Epoch(train) [20][50/293] lr: 5.000000e-04 eta: 6:44:10 time: 0.520420 data_time: 0.088756 memory: 5387 loss_kpt: 0.000779 acc_pose: 0.771949 loss: 0.000779 2022/09/14 01:12:59 - mmengine - INFO - Epoch(train) [20][100/293] lr: 5.000000e-04 eta: 6:44:24 time: 0.505349 data_time: 0.081012 memory: 5387 loss_kpt: 0.000758 acc_pose: 0.773901 loss: 0.000758 2022/09/14 01:13:24 - mmengine - INFO - Epoch(train) [20][150/293] lr: 5.000000e-04 eta: 6:44:39 time: 0.509128 data_time: 0.088982 memory: 5387 loss_kpt: 0.000752 acc_pose: 0.762609 loss: 0.000752 2022/09/14 01:13:50 - mmengine - INFO - Epoch(train) [20][200/293] lr: 5.000000e-04 eta: 6:44:54 time: 0.512229 data_time: 0.075496 memory: 5387 loss_kpt: 0.000751 acc_pose: 0.730352 loss: 0.000751 2022/09/14 01:14:15 - mmengine - INFO - Epoch(train) [20][250/293] lr: 5.000000e-04 eta: 6:45:10 time: 0.514177 data_time: 0.079240 memory: 5387 loss_kpt: 0.000775 acc_pose: 0.801216 loss: 0.000775 2022/09/14 01:14:37 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 01:14:37 - mmengine - INFO - Saving checkpoint at 20 epochs 2022/09/14 01:14:48 - mmengine - INFO - Epoch(val) [20][50/407] eta: 0:00:43 time: 0.121476 data_time: 0.013936 memory: 5387 2022/09/14 01:14:54 - mmengine - INFO - Epoch(val) [20][100/407] eta: 0:00:36 time: 0.119885 data_time: 0.012161 memory: 920 2022/09/14 01:15:00 - mmengine - INFO - Epoch(val) [20][150/407] eta: 0:00:29 time: 0.114455 data_time: 0.009282 memory: 920 2022/09/14 01:15:05 - mmengine - INFO - Epoch(val) [20][200/407] eta: 0:00:23 time: 0.115591 data_time: 0.009445 memory: 920 2022/09/14 01:15:11 - mmengine - INFO - Epoch(val) [20][250/407] eta: 0:00:18 time: 0.115102 data_time: 0.009041 memory: 920 2022/09/14 01:15:17 - mmengine - INFO - Epoch(val) [20][300/407] eta: 0:00:12 time: 0.115759 data_time: 0.008818 memory: 920 2022/09/14 01:15:23 - mmengine - INFO - Epoch(val) [20][350/407] eta: 0:00:06 time: 0.120663 data_time: 0.011683 memory: 920 2022/09/14 01:15:29 - mmengine - INFO - Epoch(val) [20][400/407] eta: 0:00:00 time: 0.110718 data_time: 0.007304 memory: 920 2022/09/14 01:16:06 - mmengine - INFO - Evaluating CocoMetric... 2022/09/14 01:16:20 - mmengine - INFO - Epoch(val) [20][407/407] coco/AP: 0.681044 coco/AP .5: 0.878689 coco/AP .75: 0.757483 coco/AP (M): 0.644479 coco/AP (L): 0.747913 coco/AR: 0.741373 coco/AR .5: 0.920655 coco/AR .75: 0.810453 coco/AR (M): 0.696886 coco/AR (L): 0.804905 2022/09/14 01:16:20 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220914/hrnet_fp16/best_coco/AP_epoch_10.pth is removed 2022/09/14 01:16:23 - mmengine - INFO - The best checkpoint with 0.6810 coco/AP at 20 epoch is saved to best_coco/AP_epoch_20.pth. 2022/09/14 01:16:49 - mmengine - INFO - Epoch(train) [21][50/293] lr: 5.000000e-04 eta: 6:42:09 time: 0.512630 data_time: 0.085254 memory: 5387 loss_kpt: 0.000762 acc_pose: 0.796740 loss: 0.000762 2022/09/14 01:17:14 - mmengine - INFO - Epoch(train) [21][100/293] lr: 5.000000e-04 eta: 6:42:18 time: 0.499135 data_time: 0.078536 memory: 5387 loss_kpt: 0.000760 acc_pose: 0.763620 loss: 0.000760 2022/09/14 01:17:33 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 01:17:38 - mmengine - INFO - Epoch(train) [21][150/293] lr: 5.000000e-04 eta: 6:42:23 time: 0.493522 data_time: 0.076654 memory: 5387 loss_kpt: 0.000745 acc_pose: 0.762974 loss: 0.000745 2022/09/14 01:18:03 - mmengine - INFO - Epoch(train) [21][200/293] lr: 5.000000e-04 eta: 6:42:32 time: 0.502239 data_time: 0.083911 memory: 5387 loss_kpt: 0.000755 acc_pose: 0.768879 loss: 0.000755 2022/09/14 01:18:29 - mmengine - INFO - Epoch(train) [21][250/293] lr: 5.000000e-04 eta: 6:42:41 time: 0.503086 data_time: 0.078684 memory: 5387 loss_kpt: 0.000747 acc_pose: 0.706144 loss: 0.000747 2022/09/14 01:18:50 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 01:18:50 - mmengine - INFO - Saving checkpoint at 21 epochs 2022/09/14 01:19:21 - mmengine - INFO - Epoch(train) [22][50/293] lr: 5.000000e-04 eta: 6:39:55 time: 0.528260 data_time: 0.097351 memory: 5387 loss_kpt: 0.000758 acc_pose: 0.745441 loss: 0.000758 2022/09/14 01:19:46 - mmengine - INFO - Epoch(train) [22][100/293] lr: 5.000000e-04 eta: 6:40:03 time: 0.502167 data_time: 0.079559 memory: 5387 loss_kpt: 0.000742 acc_pose: 0.777450 loss: 0.000742 2022/09/14 01:20:11 - mmengine - INFO - Epoch(train) [22][150/293] lr: 5.000000e-04 eta: 6:40:13 time: 0.505959 data_time: 0.080089 memory: 5387 loss_kpt: 0.000760 acc_pose: 0.757225 loss: 0.000760 2022/09/14 01:20:36 - mmengine - INFO - Epoch(train) [22][200/293] lr: 5.000000e-04 eta: 6:40:21 time: 0.502735 data_time: 0.079339 memory: 5387 loss_kpt: 0.000753 acc_pose: 0.710410 loss: 0.000753 2022/09/14 01:21:02 - mmengine - INFO - Epoch(train) [22][250/293] lr: 5.000000e-04 eta: 6:40:29 time: 0.504048 data_time: 0.074786 memory: 5387 loss_kpt: 0.000760 acc_pose: 0.784759 loss: 0.000760 2022/09/14 01:21:23 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 01:21:23 - mmengine - INFO - Saving checkpoint at 22 epochs 2022/09/14 01:21:53 - mmengine - INFO - Epoch(train) [23][50/293] lr: 5.000000e-04 eta: 6:37:43 time: 0.515568 data_time: 0.083393 memory: 5387 loss_kpt: 0.000760 acc_pose: 0.747230 loss: 0.000760 2022/09/14 01:22:19 - mmengine - INFO - Epoch(train) [23][100/293] lr: 5.000000e-04 eta: 6:37:56 time: 0.515559 data_time: 0.079765 memory: 5387 loss_kpt: 0.000747 acc_pose: 0.764716 loss: 0.000747 2022/09/14 01:22:45 - mmengine - INFO - Epoch(train) [23][150/293] lr: 5.000000e-04 eta: 6:38:09 time: 0.517102 data_time: 0.078452 memory: 5387 loss_kpt: 0.000731 acc_pose: 0.739675 loss: 0.000731 2022/09/14 01:23:10 - mmengine - INFO - Epoch(train) [23][200/293] lr: 5.000000e-04 eta: 6:38:13 time: 0.497575 data_time: 0.080000 memory: 5387 loss_kpt: 0.000741 acc_pose: 0.804820 loss: 0.000741 2022/09/14 01:23:35 - mmengine - INFO - Epoch(train) [23][250/293] lr: 5.000000e-04 eta: 6:38:22 time: 0.510613 data_time: 0.083936 memory: 5387 loss_kpt: 0.000742 acc_pose: 0.774499 loss: 0.000742 2022/09/14 01:23:57 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 01:23:57 - mmengine - INFO - Saving checkpoint at 23 epochs 2022/09/14 01:24:28 - mmengine - INFO - Epoch(train) [24][50/293] lr: 5.000000e-04 eta: 6:35:46 time: 0.524979 data_time: 0.082553 memory: 5387 loss_kpt: 0.000743 acc_pose: 0.839962 loss: 0.000743 2022/09/14 01:24:53 - mmengine - INFO - Epoch(train) [24][100/293] lr: 5.000000e-04 eta: 6:35:54 time: 0.507940 data_time: 0.079483 memory: 5387 loss_kpt: 0.000757 acc_pose: 0.789533 loss: 0.000757 2022/09/14 01:25:18 - mmengine - INFO - Epoch(train) [24][150/293] lr: 5.000000e-04 eta: 6:35:59 time: 0.501329 data_time: 0.076260 memory: 5387 loss_kpt: 0.000740 acc_pose: 0.760597 loss: 0.000740 2022/09/14 01:25:43 - mmengine - INFO - Epoch(train) [24][200/293] lr: 5.000000e-04 eta: 6:36:03 time: 0.501940 data_time: 0.084065 memory: 5387 loss_kpt: 0.000749 acc_pose: 0.785177 loss: 0.000749 2022/09/14 01:26:09 - mmengine - INFO - Epoch(train) [24][250/293] lr: 5.000000e-04 eta: 6:36:08 time: 0.501935 data_time: 0.078908 memory: 5387 loss_kpt: 0.000736 acc_pose: 0.763698 loss: 0.000736 2022/09/14 01:26:14 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 01:26:30 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 01:26:30 - mmengine - INFO - Saving checkpoint at 24 epochs 2022/09/14 01:27:01 - mmengine - INFO - Epoch(train) [25][50/293] lr: 5.000000e-04 eta: 6:33:39 time: 0.530028 data_time: 0.085774 memory: 5387 loss_kpt: 0.000745 acc_pose: 0.722471 loss: 0.000745 2022/09/14 01:27:26 - mmengine - INFO - Epoch(train) [25][100/293] lr: 5.000000e-04 eta: 6:33:42 time: 0.498005 data_time: 0.076592 memory: 5387 loss_kpt: 0.000740 acc_pose: 0.783865 loss: 0.000740 2022/09/14 01:27:51 - mmengine - INFO - Epoch(train) [25][150/293] lr: 5.000000e-04 eta: 6:33:46 time: 0.501367 data_time: 0.076072 memory: 5387 loss_kpt: 0.000720 acc_pose: 0.730695 loss: 0.000720 2022/09/14 01:28:16 - mmengine - INFO - Epoch(train) [25][200/293] lr: 5.000000e-04 eta: 6:33:50 time: 0.503474 data_time: 0.081191 memory: 5387 loss_kpt: 0.000733 acc_pose: 0.733958 loss: 0.000733 2022/09/14 01:28:42 - mmengine - INFO - Epoch(train) [25][250/293] lr: 5.000000e-04 eta: 6:33:59 time: 0.517646 data_time: 0.080122 memory: 5387 loss_kpt: 0.000757 acc_pose: 0.848885 loss: 0.000757 2022/09/14 01:29:04 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 01:29:04 - mmengine - INFO - Saving checkpoint at 25 epochs 2022/09/14 01:29:35 - mmengine - INFO - Epoch(train) [26][50/293] lr: 5.000000e-04 eta: 6:31:32 time: 0.521164 data_time: 0.092098 memory: 5387 loss_kpt: 0.000742 acc_pose: 0.759969 loss: 0.000742 2022/09/14 01:30:00 - mmengine - INFO - Epoch(train) [26][100/293] lr: 5.000000e-04 eta: 6:31:35 time: 0.500717 data_time: 0.076827 memory: 5387 loss_kpt: 0.000740 acc_pose: 0.776218 loss: 0.000740 2022/09/14 01:30:25 - mmengine - INFO - Epoch(train) [26][150/293] lr: 5.000000e-04 eta: 6:31:36 time: 0.497687 data_time: 0.078941 memory: 5387 loss_kpt: 0.000732 acc_pose: 0.803162 loss: 0.000732 2022/09/14 01:30:50 - mmengine - INFO - Epoch(train) [26][200/293] lr: 5.000000e-04 eta: 6:31:40 time: 0.507400 data_time: 0.082417 memory: 5387 loss_kpt: 0.000729 acc_pose: 0.806407 loss: 0.000729 2022/09/14 01:31:16 - mmengine - INFO - Epoch(train) [26][250/293] lr: 5.000000e-04 eta: 6:31:46 time: 0.512548 data_time: 0.073784 memory: 5387 loss_kpt: 0.000727 acc_pose: 0.759248 loss: 0.000727 2022/09/14 01:31:37 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 01:31:37 - mmengine - INFO - Saving checkpoint at 26 epochs 2022/09/14 01:32:08 - mmengine - INFO - Epoch(train) [27][50/293] lr: 5.000000e-04 eta: 6:29:28 time: 0.531848 data_time: 0.091223 memory: 5387 loss_kpt: 0.000718 acc_pose: 0.784450 loss: 0.000718 2022/09/14 01:32:34 - mmengine - INFO - Epoch(train) [27][100/293] lr: 5.000000e-04 eta: 6:29:32 time: 0.507667 data_time: 0.077971 memory: 5387 loss_kpt: 0.000741 acc_pose: 0.696041 loss: 0.000741 2022/09/14 01:32:59 - mmengine - INFO - Epoch(train) [27][150/293] lr: 5.000000e-04 eta: 6:29:34 time: 0.503977 data_time: 0.077382 memory: 5387 loss_kpt: 0.000728 acc_pose: 0.785782 loss: 0.000728 2022/09/14 01:33:24 - mmengine - INFO - Epoch(train) [27][200/293] lr: 5.000000e-04 eta: 6:29:35 time: 0.501272 data_time: 0.077665 memory: 5387 loss_kpt: 0.000747 acc_pose: 0.784013 loss: 0.000747 2022/09/14 01:33:49 - mmengine - INFO - Epoch(train) [27][250/293] lr: 5.000000e-04 eta: 6:29:37 time: 0.505223 data_time: 0.077263 memory: 5387 loss_kpt: 0.000744 acc_pose: 0.762430 loss: 0.000744 2022/09/14 01:34:11 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 01:34:11 - mmengine - INFO - Saving checkpoint at 27 epochs 2022/09/14 01:34:41 - mmengine - INFO - Epoch(train) [28][50/293] lr: 5.000000e-04 eta: 6:27:18 time: 0.516703 data_time: 0.087212 memory: 5387 loss_kpt: 0.000731 acc_pose: 0.787918 loss: 0.000731 2022/09/14 01:35:01 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 01:35:06 - mmengine - INFO - Epoch(train) [28][100/293] lr: 5.000000e-04 eta: 6:27:19 time: 0.501590 data_time: 0.073592 memory: 5387 loss_kpt: 0.000735 acc_pose: 0.796889 loss: 0.000735 2022/09/14 01:35:31 - mmengine - INFO - Epoch(train) [28][150/293] lr: 5.000000e-04 eta: 6:27:21 time: 0.504236 data_time: 0.077028 memory: 5387 loss_kpt: 0.000748 acc_pose: 0.795365 loss: 0.000748 2022/09/14 01:35:57 - mmengine - INFO - Epoch(train) [28][200/293] lr: 5.000000e-04 eta: 6:27:22 time: 0.504908 data_time: 0.081235 memory: 5387 loss_kpt: 0.000733 acc_pose: 0.799811 loss: 0.000733 2022/09/14 01:36:22 - mmengine - INFO - Epoch(train) [28][250/293] lr: 5.000000e-04 eta: 6:27:23 time: 0.503680 data_time: 0.077941 memory: 5387 loss_kpt: 0.000724 acc_pose: 0.714725 loss: 0.000724 2022/09/14 01:36:43 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 01:36:43 - mmengine - INFO - Saving checkpoint at 28 epochs 2022/09/14 01:37:13 - mmengine - INFO - Epoch(train) [29][50/293] lr: 5.000000e-04 eta: 6:25:06 time: 0.512151 data_time: 0.082578 memory: 5387 loss_kpt: 0.000730 acc_pose: 0.818508 loss: 0.000730 2022/09/14 01:37:39 - mmengine - INFO - Epoch(train) [29][100/293] lr: 5.000000e-04 eta: 6:25:11 time: 0.518534 data_time: 0.072643 memory: 5387 loss_kpt: 0.000725 acc_pose: 0.803996 loss: 0.000725 2022/09/14 01:38:04 - mmengine - INFO - Epoch(train) [29][150/293] lr: 5.000000e-04 eta: 6:25:12 time: 0.503954 data_time: 0.077270 memory: 5387 loss_kpt: 0.000742 acc_pose: 0.758006 loss: 0.000742 2022/09/14 01:38:30 - mmengine - INFO - Epoch(train) [29][200/293] lr: 5.000000e-04 eta: 6:25:13 time: 0.507042 data_time: 0.078166 memory: 5387 loss_kpt: 0.000727 acc_pose: 0.779554 loss: 0.000727 2022/09/14 01:38:56 - mmengine - INFO - Epoch(train) [29][250/293] lr: 5.000000e-04 eta: 6:25:16 time: 0.514430 data_time: 0.080653 memory: 5387 loss_kpt: 0.000711 acc_pose: 0.789271 loss: 0.000711 2022/09/14 01:39:17 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 01:39:17 - mmengine - INFO - Saving checkpoint at 29 epochs 2022/09/14 01:39:47 - mmengine - INFO - Epoch(train) [30][50/293] lr: 5.000000e-04 eta: 6:23:06 time: 0.519214 data_time: 0.084126 memory: 5387 loss_kpt: 0.000722 acc_pose: 0.834880 loss: 0.000722 2022/09/14 01:40:13 - mmengine - INFO - Epoch(train) [30][100/293] lr: 5.000000e-04 eta: 6:23:06 time: 0.505997 data_time: 0.082604 memory: 5387 loss_kpt: 0.000736 acc_pose: 0.831619 loss: 0.000736 2022/09/14 01:40:38 - mmengine - INFO - Epoch(train) [30][150/293] lr: 5.000000e-04 eta: 6:23:07 time: 0.507991 data_time: 0.076660 memory: 5387 loss_kpt: 0.000736 acc_pose: 0.812685 loss: 0.000736 2022/09/14 01:41:04 - mmengine - INFO - Epoch(train) [30][200/293] lr: 5.000000e-04 eta: 6:23:11 time: 0.518974 data_time: 0.074321 memory: 5387 loss_kpt: 0.000726 acc_pose: 0.802126 loss: 0.000726 2022/09/14 01:41:30 - mmengine - INFO - Epoch(train) [30][250/293] lr: 5.000000e-04 eta: 6:23:12 time: 0.511463 data_time: 0.085077 memory: 5387 loss_kpt: 0.000736 acc_pose: 0.741359 loss: 0.000736 2022/09/14 01:41:51 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 01:41:51 - mmengine - INFO - Saving checkpoint at 30 epochs 2022/09/14 01:42:02 - mmengine - INFO - Epoch(val) [30][50/407] eta: 0:00:42 time: 0.120289 data_time: 0.013745 memory: 5387 2022/09/14 01:42:08 - mmengine - INFO - Epoch(val) [30][100/407] eta: 0:00:35 time: 0.116319 data_time: 0.008692 memory: 920 2022/09/14 01:42:13 - mmengine - INFO - Epoch(val) [30][150/407] eta: 0:00:30 time: 0.117337 data_time: 0.010879 memory: 920 2022/09/14 01:42:19 - mmengine - INFO - Epoch(val) [30][200/407] eta: 0:00:24 time: 0.119158 data_time: 0.012869 memory: 920 2022/09/14 01:42:25 - mmengine - INFO - Epoch(val) [30][250/407] eta: 0:00:18 time: 0.120320 data_time: 0.011937 memory: 920 2022/09/14 01:42:31 - mmengine - INFO - Epoch(val) [30][300/407] eta: 0:00:12 time: 0.116180 data_time: 0.009650 memory: 920 2022/09/14 01:42:37 - mmengine - INFO - Epoch(val) [30][350/407] eta: 0:00:06 time: 0.116283 data_time: 0.008928 memory: 920 2022/09/14 01:42:43 - mmengine - INFO - Epoch(val) [30][400/407] eta: 0:00:00 time: 0.110225 data_time: 0.007871 memory: 920 2022/09/14 01:43:19 - mmengine - INFO - Evaluating CocoMetric... 2022/09/14 01:43:33 - mmengine - INFO - Epoch(val) [30][407/407] coco/AP: 0.696864 coco/AP .5: 0.885004 coco/AP .75: 0.774427 coco/AP (M): 0.662887 coco/AP (L): 0.760987 coco/AR: 0.753747 coco/AR .5: 0.923646 coco/AR .75: 0.822261 coco/AR (M): 0.712264 coco/AR (L): 0.813935 2022/09/14 01:43:33 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220914/hrnet_fp16/best_coco/AP_epoch_20.pth is removed 2022/09/14 01:43:36 - mmengine - INFO - The best checkpoint with 0.6969 coco/AP at 30 epoch is saved to best_coco/AP_epoch_30.pth. 2022/09/14 01:44:02 - mmengine - INFO - Epoch(train) [31][50/293] lr: 5.000000e-04 eta: 6:21:03 time: 0.514501 data_time: 0.083001 memory: 5387 loss_kpt: 0.000727 acc_pose: 0.840433 loss: 0.000727 2022/09/14 01:44:27 - mmengine - INFO - Epoch(train) [31][100/293] lr: 5.000000e-04 eta: 6:21:03 time: 0.504507 data_time: 0.077115 memory: 5387 loss_kpt: 0.000708 acc_pose: 0.757941 loss: 0.000708 2022/09/14 01:44:52 - mmengine - INFO - Epoch(train) [31][150/293] lr: 5.000000e-04 eta: 6:21:03 time: 0.509497 data_time: 0.075272 memory: 5387 loss_kpt: 0.000716 acc_pose: 0.775548 loss: 0.000716 2022/09/14 01:45:18 - mmengine - INFO - Epoch(train) [31][200/293] lr: 5.000000e-04 eta: 6:21:02 time: 0.506111 data_time: 0.079857 memory: 5387 loss_kpt: 0.000731 acc_pose: 0.739647 loss: 0.000731 2022/09/14 01:45:23 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 01:45:43 - mmengine - INFO - Epoch(train) [31][250/293] lr: 5.000000e-04 eta: 6:21:01 time: 0.506672 data_time: 0.076132 memory: 5387 loss_kpt: 0.000730 acc_pose: 0.832763 loss: 0.000730 2022/09/14 01:46:04 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 01:46:04 - mmengine - INFO - Saving checkpoint at 31 epochs 2022/09/14 01:46:34 - mmengine - INFO - Epoch(train) [32][50/293] lr: 5.000000e-04 eta: 6:18:55 time: 0.511067 data_time: 0.084461 memory: 5387 loss_kpt: 0.000719 acc_pose: 0.761713 loss: 0.000719 2022/09/14 01:46:59 - mmengine - INFO - Epoch(train) [32][100/293] lr: 5.000000e-04 eta: 6:18:53 time: 0.504055 data_time: 0.078420 memory: 5387 loss_kpt: 0.000729 acc_pose: 0.776074 loss: 0.000729 2022/09/14 01:47:25 - mmengine - INFO - Epoch(train) [32][150/293] lr: 5.000000e-04 eta: 6:18:51 time: 0.503554 data_time: 0.074962 memory: 5387 loss_kpt: 0.000733 acc_pose: 0.790708 loss: 0.000733 2022/09/14 01:47:50 - mmengine - INFO - Epoch(train) [32][200/293] lr: 5.000000e-04 eta: 6:18:52 time: 0.514311 data_time: 0.086259 memory: 5387 loss_kpt: 0.000726 acc_pose: 0.800052 loss: 0.000726 2022/09/14 01:48:16 - mmengine - INFO - Epoch(train) [32][250/293] lr: 5.000000e-04 eta: 6:18:50 time: 0.507606 data_time: 0.077282 memory: 5387 loss_kpt: 0.000720 acc_pose: 0.745125 loss: 0.000720 2022/09/14 01:48:38 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 01:48:38 - mmengine - INFO - Saving checkpoint at 32 epochs 2022/09/14 01:49:07 - mmengine - INFO - Epoch(train) [33][50/293] lr: 5.000000e-04 eta: 6:16:48 time: 0.514815 data_time: 0.091945 memory: 5387 loss_kpt: 0.000723 acc_pose: 0.776159 loss: 0.000723 2022/09/14 01:49:32 - mmengine - INFO - Epoch(train) [33][100/293] lr: 5.000000e-04 eta: 6:16:45 time: 0.500090 data_time: 0.072046 memory: 5387 loss_kpt: 0.000717 acc_pose: 0.820209 loss: 0.000717 2022/09/14 01:49:58 - mmengine - INFO - Epoch(train) [33][150/293] lr: 5.000000e-04 eta: 6:16:45 time: 0.513719 data_time: 0.079594 memory: 5387 loss_kpt: 0.000722 acc_pose: 0.765847 loss: 0.000722 2022/09/14 01:50:24 - mmengine - INFO - Epoch(train) [33][200/293] lr: 5.000000e-04 eta: 6:16:43 time: 0.508432 data_time: 0.077895 memory: 5387 loss_kpt: 0.000704 acc_pose: 0.764957 loss: 0.000704 2022/09/14 01:50:49 - mmengine - INFO - Epoch(train) [33][250/293] lr: 5.000000e-04 eta: 6:16:39 time: 0.502674 data_time: 0.082239 memory: 5387 loss_kpt: 0.000708 acc_pose: 0.816241 loss: 0.000708 2022/09/14 01:51:10 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 01:51:10 - mmengine - INFO - Saving checkpoint at 33 epochs 2022/09/14 01:51:43 - mmengine - INFO - Epoch(train) [34][50/293] lr: 5.000000e-04 eta: 6:14:44 time: 0.527221 data_time: 0.097022 memory: 5387 loss_kpt: 0.000717 acc_pose: 0.755404 loss: 0.000717 2022/09/14 01:52:08 - mmengine - INFO - Epoch(train) [34][100/293] lr: 5.000000e-04 eta: 6:14:42 time: 0.508953 data_time: 0.076915 memory: 5387 loss_kpt: 0.000720 acc_pose: 0.813709 loss: 0.000720 2022/09/14 01:52:33 - mmengine - INFO - Epoch(train) [34][150/293] lr: 5.000000e-04 eta: 6:14:38 time: 0.504227 data_time: 0.077741 memory: 5387 loss_kpt: 0.000723 acc_pose: 0.807790 loss: 0.000723 2022/09/14 01:52:59 - mmengine - INFO - Epoch(train) [34][200/293] lr: 5.000000e-04 eta: 6:14:35 time: 0.503589 data_time: 0.079051 memory: 5387 loss_kpt: 0.000714 acc_pose: 0.819759 loss: 0.000714 2022/09/14 01:53:23 - mmengine - INFO - Epoch(train) [34][250/293] lr: 5.000000e-04 eta: 6:14:29 time: 0.498271 data_time: 0.078154 memory: 5387 loss_kpt: 0.000726 acc_pose: 0.773217 loss: 0.000726 2022/09/14 01:53:45 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 01:53:45 - mmengine - INFO - Saving checkpoint at 34 epochs 2022/09/14 01:54:09 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 01:54:16 - mmengine - INFO - Epoch(train) [35][50/293] lr: 5.000000e-04 eta: 6:12:35 time: 0.523294 data_time: 0.087772 memory: 5387 loss_kpt: 0.000706 acc_pose: 0.815662 loss: 0.000706 2022/09/14 01:54:41 - mmengine - INFO - Epoch(train) [35][100/293] lr: 5.000000e-04 eta: 6:12:34 time: 0.513197 data_time: 0.073840 memory: 5387 loss_kpt: 0.000699 acc_pose: 0.833033 loss: 0.000699 2022/09/14 01:55:07 - mmengine - INFO - Epoch(train) [35][150/293] lr: 5.000000e-04 eta: 6:12:34 time: 0.520290 data_time: 0.090431 memory: 5387 loss_kpt: 0.000718 acc_pose: 0.776542 loss: 0.000718 2022/09/14 01:55:33 - mmengine - INFO - Epoch(train) [35][200/293] lr: 5.000000e-04 eta: 6:12:31 time: 0.509394 data_time: 0.075825 memory: 5387 loss_kpt: 0.000701 acc_pose: 0.833981 loss: 0.000701 2022/09/14 01:55:58 - mmengine - INFO - Epoch(train) [35][250/293] lr: 5.000000e-04 eta: 6:12:25 time: 0.498316 data_time: 0.083845 memory: 5387 loss_kpt: 0.000710 acc_pose: 0.827250 loss: 0.000710 2022/09/14 01:56:19 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 01:56:19 - mmengine - INFO - Saving checkpoint at 35 epochs 2022/09/14 01:56:53 - mmengine - INFO - Epoch(train) [36][50/293] lr: 5.000000e-04 eta: 6:10:30 time: 0.510318 data_time: 0.085540 memory: 5387 loss_kpt: 0.000712 acc_pose: 0.762467 loss: 0.000712 2022/09/14 01:57:18 - mmengine - INFO - Epoch(train) [36][100/293] lr: 5.000000e-04 eta: 6:10:27 time: 0.510480 data_time: 0.077233 memory: 5387 loss_kpt: 0.000708 acc_pose: 0.799704 loss: 0.000708 2022/09/14 01:57:44 - mmengine - INFO - Epoch(train) [36][150/293] lr: 5.000000e-04 eta: 6:10:25 time: 0.511094 data_time: 0.083792 memory: 5387 loss_kpt: 0.000712 acc_pose: 0.800061 loss: 0.000712 2022/09/14 01:58:09 - mmengine - INFO - Epoch(train) [36][200/293] lr: 5.000000e-04 eta: 6:10:19 time: 0.501953 data_time: 0.077230 memory: 5387 loss_kpt: 0.000715 acc_pose: 0.776950 loss: 0.000715 2022/09/14 01:58:34 - mmengine - INFO - Epoch(train) [36][250/293] lr: 5.000000e-04 eta: 6:10:14 time: 0.503213 data_time: 0.074309 memory: 5387 loss_kpt: 0.000715 acc_pose: 0.783337 loss: 0.000715 2022/09/14 01:58:55 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 01:58:55 - mmengine - INFO - Saving checkpoint at 36 epochs 2022/09/14 01:59:25 - mmengine - INFO - Epoch(train) [37][50/293] lr: 5.000000e-04 eta: 6:08:22 time: 0.512496 data_time: 0.083120 memory: 5387 loss_kpt: 0.000683 acc_pose: 0.778807 loss: 0.000683 2022/09/14 01:59:51 - mmengine - INFO - Epoch(train) [37][100/293] lr: 5.000000e-04 eta: 6:08:21 time: 0.518229 data_time: 0.083125 memory: 5387 loss_kpt: 0.000704 acc_pose: 0.808318 loss: 0.000704 2022/09/14 02:00:16 - mmengine - INFO - Epoch(train) [37][150/293] lr: 5.000000e-04 eta: 6:08:15 time: 0.502408 data_time: 0.079940 memory: 5387 loss_kpt: 0.000711 acc_pose: 0.742081 loss: 0.000711 2022/09/14 02:00:43 - mmengine - INFO - Epoch(train) [37][200/293] lr: 5.000000e-04 eta: 6:08:17 time: 0.534234 data_time: 0.079039 memory: 5387 loss_kpt: 0.000722 acc_pose: 0.820230 loss: 0.000722 2022/09/14 02:01:09 - mmengine - INFO - Epoch(train) [37][250/293] lr: 5.000000e-04 eta: 6:08:13 time: 0.510318 data_time: 0.077922 memory: 5387 loss_kpt: 0.000714 acc_pose: 0.768962 loss: 0.000714 2022/09/14 02:01:30 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 02:01:30 - mmengine - INFO - Saving checkpoint at 37 epochs 2022/09/14 02:02:00 - mmengine - INFO - Epoch(train) [38][50/293] lr: 5.000000e-04 eta: 6:06:23 time: 0.510726 data_time: 0.081650 memory: 5387 loss_kpt: 0.000708 acc_pose: 0.858951 loss: 0.000708 2022/09/14 02:02:25 - mmengine - INFO - Epoch(train) [38][100/293] lr: 5.000000e-04 eta: 6:06:18 time: 0.507949 data_time: 0.084717 memory: 5387 loss_kpt: 0.000701 acc_pose: 0.794783 loss: 0.000701 2022/09/14 02:02:50 - mmengine - INFO - Epoch(train) [38][150/293] lr: 5.000000e-04 eta: 6:06:12 time: 0.501428 data_time: 0.073870 memory: 5387 loss_kpt: 0.000722 acc_pose: 0.746861 loss: 0.000722 2022/09/14 02:02:55 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 02:03:16 - mmengine - INFO - Epoch(train) [38][200/293] lr: 5.000000e-04 eta: 6:06:06 time: 0.506830 data_time: 0.078375 memory: 5387 loss_kpt: 0.000707 acc_pose: 0.749022 loss: 0.000707 2022/09/14 02:03:41 - mmengine - INFO - Epoch(train) [38][250/293] lr: 5.000000e-04 eta: 6:06:01 time: 0.508429 data_time: 0.077847 memory: 5387 loss_kpt: 0.000716 acc_pose: 0.813419 loss: 0.000716 2022/09/14 02:04:03 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 02:04:03 - mmengine - INFO - Saving checkpoint at 38 epochs 2022/09/14 02:04:34 - mmengine - INFO - Epoch(train) [39][50/293] lr: 5.000000e-04 eta: 6:04:14 time: 0.512307 data_time: 0.083136 memory: 5387 loss_kpt: 0.000712 acc_pose: 0.782446 loss: 0.000712 2022/09/14 02:04:59 - mmengine - INFO - Epoch(train) [39][100/293] lr: 5.000000e-04 eta: 6:04:08 time: 0.505066 data_time: 0.075054 memory: 5387 loss_kpt: 0.000710 acc_pose: 0.721511 loss: 0.000710 2022/09/14 02:05:24 - mmengine - INFO - Epoch(train) [39][150/293] lr: 5.000000e-04 eta: 6:04:03 time: 0.508813 data_time: 0.080788 memory: 5387 loss_kpt: 0.000693 acc_pose: 0.798778 loss: 0.000693 2022/09/14 02:05:50 - mmengine - INFO - Epoch(train) [39][200/293] lr: 5.000000e-04 eta: 6:03:59 time: 0.513920 data_time: 0.075888 memory: 5387 loss_kpt: 0.000707 acc_pose: 0.838497 loss: 0.000707 2022/09/14 02:06:15 - mmengine - INFO - Epoch(train) [39][250/293] lr: 5.000000e-04 eta: 6:03:53 time: 0.509440 data_time: 0.078878 memory: 5387 loss_kpt: 0.000704 acc_pose: 0.815098 loss: 0.000704 2022/09/14 02:06:37 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 02:06:37 - mmengine - INFO - Saving checkpoint at 39 epochs 2022/09/14 02:07:08 - mmengine - INFO - Epoch(train) [40][50/293] lr: 5.000000e-04 eta: 6:02:12 time: 0.533110 data_time: 0.090908 memory: 5387 loss_kpt: 0.000712 acc_pose: 0.785619 loss: 0.000712 2022/09/14 02:07:33 - mmengine - INFO - Epoch(train) [40][100/293] lr: 5.000000e-04 eta: 6:02:05 time: 0.498074 data_time: 0.076316 memory: 5387 loss_kpt: 0.000699 acc_pose: 0.761327 loss: 0.000699 2022/09/14 02:07:58 - mmengine - INFO - Epoch(train) [40][150/293] lr: 5.000000e-04 eta: 6:01:59 time: 0.508661 data_time: 0.078611 memory: 5387 loss_kpt: 0.000705 acc_pose: 0.781740 loss: 0.000705 2022/09/14 02:08:24 - mmengine - INFO - Epoch(train) [40][200/293] lr: 5.000000e-04 eta: 6:01:54 time: 0.512123 data_time: 0.077831 memory: 5387 loss_kpt: 0.000708 acc_pose: 0.816605 loss: 0.000708 2022/09/14 02:08:49 - mmengine - INFO - Epoch(train) [40][250/293] lr: 5.000000e-04 eta: 6:01:47 time: 0.506502 data_time: 0.074551 memory: 5387 loss_kpt: 0.000711 acc_pose: 0.826447 loss: 0.000711 2022/09/14 02:09:11 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 02:09:11 - mmengine - INFO - Saving checkpoint at 40 epochs 2022/09/14 02:09:23 - mmengine - INFO - Epoch(val) [40][50/407] eta: 0:00:42 time: 0.118648 data_time: 0.013475 memory: 5387 2022/09/14 02:09:29 - mmengine - INFO - Epoch(val) [40][100/407] eta: 0:00:36 time: 0.119860 data_time: 0.012492 memory: 920 2022/09/14 02:09:35 - mmengine - INFO - Epoch(val) [40][150/407] eta: 0:00:30 time: 0.117643 data_time: 0.008960 memory: 920 2022/09/14 02:09:41 - mmengine - INFO - Epoch(val) [40][200/407] eta: 0:00:24 time: 0.116341 data_time: 0.009618 memory: 920 2022/09/14 02:09:47 - mmengine - INFO - Epoch(val) [40][250/407] eta: 0:00:18 time: 0.115235 data_time: 0.009509 memory: 920 2022/09/14 02:09:53 - mmengine - INFO - Epoch(val) [40][300/407] eta: 0:00:13 time: 0.121666 data_time: 0.015159 memory: 920 2022/09/14 02:09:59 - mmengine - INFO - Epoch(val) [40][350/407] eta: 0:00:06 time: 0.115846 data_time: 0.008942 memory: 920 2022/09/14 02:10:04 - mmengine - INFO - Epoch(val) [40][400/407] eta: 0:00:00 time: 0.112602 data_time: 0.010951 memory: 920 2022/09/14 02:10:42 - mmengine - INFO - Evaluating CocoMetric... 2022/09/14 02:10:56 - mmengine - INFO - Epoch(val) [40][407/407] coco/AP: 0.706121 coco/AP .5: 0.890463 coco/AP .75: 0.780861 coco/AP (M): 0.671774 coco/AP (L): 0.770745 coco/AR: 0.763492 coco/AR .5: 0.930416 coco/AR .75: 0.832021 coco/AR (M): 0.721497 coco/AR (L): 0.823597 2022/09/14 02:10:56 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220914/hrnet_fp16/best_coco/AP_epoch_30.pth is removed 2022/09/14 02:10:59 - mmengine - INFO - The best checkpoint with 0.7061 coco/AP at 40 epoch is saved to best_coco/AP_epoch_40.pth. 2022/09/14 02:11:25 - mmengine - INFO - Epoch(train) [41][50/293] lr: 5.000000e-04 eta: 6:00:06 time: 0.522402 data_time: 0.080271 memory: 5387 loss_kpt: 0.000705 acc_pose: 0.773376 loss: 0.000705 2022/09/14 02:11:51 - mmengine - INFO - Epoch(train) [41][100/293] lr: 5.000000e-04 eta: 6:00:01 time: 0.513698 data_time: 0.079216 memory: 5387 loss_kpt: 0.000689 acc_pose: 0.796450 loss: 0.000689 2022/09/14 02:12:16 - mmengine - INFO - Epoch(train) [41][150/293] lr: 5.000000e-04 eta: 5:59:55 time: 0.510552 data_time: 0.077862 memory: 5387 loss_kpt: 0.000696 acc_pose: 0.783954 loss: 0.000696 2022/09/14 02:12:41 - mmengine - INFO - Epoch(train) [41][200/293] lr: 5.000000e-04 eta: 5:59:48 time: 0.505011 data_time: 0.074717 memory: 5387 loss_kpt: 0.000698 acc_pose: 0.760237 loss: 0.000698 2022/09/14 02:13:07 - mmengine - INFO - Epoch(train) [41][250/293] lr: 5.000000e-04 eta: 5:59:42 time: 0.510672 data_time: 0.084146 memory: 5387 loss_kpt: 0.000707 acc_pose: 0.750063 loss: 0.000707 2022/09/14 02:13:22 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 02:13:29 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 02:13:29 - mmengine - INFO - Saving checkpoint at 41 epochs 2022/09/14 02:13:59 - mmengine - INFO - Epoch(train) [42][50/293] lr: 5.000000e-04 eta: 5:58:00 time: 0.511158 data_time: 0.083077 memory: 5387 loss_kpt: 0.000682 acc_pose: 0.848710 loss: 0.000682 2022/09/14 02:14:24 - mmengine - INFO - Epoch(train) [42][100/293] lr: 5.000000e-04 eta: 5:57:52 time: 0.502570 data_time: 0.080049 memory: 5387 loss_kpt: 0.000701 acc_pose: 0.836553 loss: 0.000701 2022/09/14 02:14:49 - mmengine - INFO - Epoch(train) [42][150/293] lr: 5.000000e-04 eta: 5:57:47 time: 0.514660 data_time: 0.073143 memory: 5387 loss_kpt: 0.000698 acc_pose: 0.768564 loss: 0.000698 2022/09/14 02:15:15 - mmengine - INFO - Epoch(train) [42][200/293] lr: 5.000000e-04 eta: 5:57:39 time: 0.506022 data_time: 0.071090 memory: 5387 loss_kpt: 0.000684 acc_pose: 0.779518 loss: 0.000684 2022/09/14 02:15:40 - mmengine - INFO - Epoch(train) [42][250/293] lr: 5.000000e-04 eta: 5:57:31 time: 0.502835 data_time: 0.074414 memory: 5387 loss_kpt: 0.000694 acc_pose: 0.814042 loss: 0.000694 2022/09/14 02:16:01 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 02:16:01 - mmengine - INFO - Saving checkpoint at 42 epochs 2022/09/14 02:16:32 - mmengine - INFO - Epoch(train) [43][50/293] lr: 5.000000e-04 eta: 5:55:54 time: 0.523777 data_time: 0.084380 memory: 5387 loss_kpt: 0.000703 acc_pose: 0.808649 loss: 0.000703 2022/09/14 02:16:57 - mmengine - INFO - Epoch(train) [43][100/293] lr: 5.000000e-04 eta: 5:55:47 time: 0.508220 data_time: 0.074960 memory: 5387 loss_kpt: 0.000697 acc_pose: 0.842248 loss: 0.000697 2022/09/14 02:17:23 - mmengine - INFO - Epoch(train) [43][150/293] lr: 5.000000e-04 eta: 5:55:41 time: 0.514824 data_time: 0.071639 memory: 5387 loss_kpt: 0.000698 acc_pose: 0.813885 loss: 0.000698 2022/09/14 02:17:48 - mmengine - INFO - Epoch(train) [43][200/293] lr: 5.000000e-04 eta: 5:55:34 time: 0.508407 data_time: 0.076658 memory: 5387 loss_kpt: 0.000701 acc_pose: 0.764812 loss: 0.000701 2022/09/14 02:18:13 - mmengine - INFO - Epoch(train) [43][250/293] lr: 5.000000e-04 eta: 5:55:26 time: 0.507572 data_time: 0.081835 memory: 5387 loss_kpt: 0.000694 acc_pose: 0.813956 loss: 0.000694 2022/09/14 02:18:35 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 02:18:35 - mmengine - INFO - Saving checkpoint at 43 epochs 2022/09/14 02:19:05 - mmengine - INFO - Epoch(train) [44][50/293] lr: 5.000000e-04 eta: 5:53:48 time: 0.513753 data_time: 0.087323 memory: 5387 loss_kpt: 0.000707 acc_pose: 0.775278 loss: 0.000707 2022/09/14 02:19:31 - mmengine - INFO - Epoch(train) [44][100/293] lr: 5.000000e-04 eta: 5:53:42 time: 0.515829 data_time: 0.079019 memory: 5387 loss_kpt: 0.000703 acc_pose: 0.824914 loss: 0.000703 2022/09/14 02:19:56 - mmengine - INFO - Epoch(train) [44][150/293] lr: 5.000000e-04 eta: 5:53:34 time: 0.506799 data_time: 0.080553 memory: 5387 loss_kpt: 0.000694 acc_pose: 0.795419 loss: 0.000694 2022/09/14 02:20:21 - mmengine - INFO - Epoch(train) [44][200/293] lr: 5.000000e-04 eta: 5:53:25 time: 0.499061 data_time: 0.078406 memory: 5387 loss_kpt: 0.000697 acc_pose: 0.838004 loss: 0.000697 2022/09/14 02:20:47 - mmengine - INFO - Epoch(train) [44][250/293] lr: 5.000000e-04 eta: 5:53:17 time: 0.508550 data_time: 0.078668 memory: 5387 loss_kpt: 0.000685 acc_pose: 0.807487 loss: 0.000685 2022/09/14 02:21:08 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 02:21:08 - mmengine - INFO - Saving checkpoint at 44 epochs 2022/09/14 02:21:38 - mmengine - INFO - Epoch(train) [45][50/293] lr: 5.000000e-04 eta: 5:51:40 time: 0.508365 data_time: 0.082851 memory: 5387 loss_kpt: 0.000699 acc_pose: 0.818078 loss: 0.000699 2022/09/14 02:22:03 - mmengine - INFO - Epoch(train) [45][100/293] lr: 5.000000e-04 eta: 5:51:32 time: 0.508196 data_time: 0.079168 memory: 5387 loss_kpt: 0.000689 acc_pose: 0.796505 loss: 0.000689 2022/09/14 02:22:07 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 02:22:28 - mmengine - INFO - Epoch(train) [45][150/293] lr: 5.000000e-04 eta: 5:51:22 time: 0.498860 data_time: 0.080148 memory: 5387 loss_kpt: 0.000702 acc_pose: 0.782061 loss: 0.000702 2022/09/14 02:22:54 - mmengine - INFO - Epoch(train) [45][200/293] lr: 5.000000e-04 eta: 5:51:14 time: 0.506149 data_time: 0.080848 memory: 5387 loss_kpt: 0.000696 acc_pose: 0.797274 loss: 0.000696 2022/09/14 02:23:19 - mmengine - INFO - Epoch(train) [45][250/293] lr: 5.000000e-04 eta: 5:51:04 time: 0.501257 data_time: 0.083360 memory: 5387 loss_kpt: 0.000707 acc_pose: 0.815073 loss: 0.000707 2022/09/14 02:23:40 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 02:23:40 - mmengine - INFO - Saving checkpoint at 45 epochs 2022/09/14 02:24:10 - mmengine - INFO - Epoch(train) [46][50/293] lr: 5.000000e-04 eta: 5:49:29 time: 0.508558 data_time: 0.086303 memory: 5387 loss_kpt: 0.000696 acc_pose: 0.776691 loss: 0.000696 2022/09/14 02:24:35 - mmengine - INFO - Epoch(train) [46][100/293] lr: 5.000000e-04 eta: 5:49:21 time: 0.512603 data_time: 0.078722 memory: 5387 loss_kpt: 0.000697 acc_pose: 0.834481 loss: 0.000697 2022/09/14 02:25:01 - mmengine - INFO - Epoch(train) [46][150/293] lr: 5.000000e-04 eta: 5:49:13 time: 0.511809 data_time: 0.081472 memory: 5387 loss_kpt: 0.000701 acc_pose: 0.779371 loss: 0.000701 2022/09/14 02:25:26 - mmengine - INFO - Epoch(train) [46][200/293] lr: 5.000000e-04 eta: 5:49:04 time: 0.505748 data_time: 0.073452 memory: 5387 loss_kpt: 0.000705 acc_pose: 0.796779 loss: 0.000705 2022/09/14 02:25:51 - mmengine - INFO - Epoch(train) [46][250/293] lr: 5.000000e-04 eta: 5:48:54 time: 0.500516 data_time: 0.076851 memory: 5387 loss_kpt: 0.000681 acc_pose: 0.819448 loss: 0.000681 2022/09/14 02:26:13 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 02:26:13 - mmengine - INFO - Saving checkpoint at 46 epochs 2022/09/14 02:26:42 - mmengine - INFO - Epoch(train) [47][50/293] lr: 5.000000e-04 eta: 5:47:20 time: 0.507754 data_time: 0.082063 memory: 5387 loss_kpt: 0.000686 acc_pose: 0.762309 loss: 0.000686 2022/09/14 02:27:08 - mmengine - INFO - Epoch(train) [47][100/293] lr: 5.000000e-04 eta: 5:47:14 time: 0.520529 data_time: 0.077588 memory: 5387 loss_kpt: 0.000682 acc_pose: 0.809876 loss: 0.000682 2022/09/14 02:27:33 - mmengine - INFO - Epoch(train) [47][150/293] lr: 5.000000e-04 eta: 5:47:02 time: 0.493663 data_time: 0.079649 memory: 5387 loss_kpt: 0.000688 acc_pose: 0.796941 loss: 0.000688 2022/09/14 02:27:58 - mmengine - INFO - Epoch(train) [47][200/293] lr: 5.000000e-04 eta: 5:46:53 time: 0.502844 data_time: 0.071749 memory: 5387 loss_kpt: 0.000697 acc_pose: 0.787052 loss: 0.000697 2022/09/14 02:28:23 - mmengine - INFO - Epoch(train) [47][250/293] lr: 5.000000e-04 eta: 5:46:43 time: 0.502190 data_time: 0.075478 memory: 5387 loss_kpt: 0.000690 acc_pose: 0.781460 loss: 0.000690 2022/09/14 02:28:45 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 02:28:45 - mmengine - INFO - Saving checkpoint at 47 epochs 2022/09/14 02:29:15 - mmengine - INFO - Epoch(train) [48][50/293] lr: 5.000000e-04 eta: 5:45:11 time: 0.510743 data_time: 0.089158 memory: 5387 loss_kpt: 0.000692 acc_pose: 0.765954 loss: 0.000692 2022/09/14 02:29:41 - mmengine - INFO - Epoch(train) [48][100/293] lr: 5.000000e-04 eta: 5:45:02 time: 0.513291 data_time: 0.075101 memory: 5387 loss_kpt: 0.000690 acc_pose: 0.847202 loss: 0.000690 2022/09/14 02:30:05 - mmengine - INFO - Epoch(train) [48][150/293] lr: 5.000000e-04 eta: 5:44:51 time: 0.496262 data_time: 0.081367 memory: 5387 loss_kpt: 0.000681 acc_pose: 0.768620 loss: 0.000681 2022/09/14 02:30:31 - mmengine - INFO - Epoch(train) [48][200/293] lr: 5.000000e-04 eta: 5:44:41 time: 0.504109 data_time: 0.071021 memory: 5387 loss_kpt: 0.000684 acc_pose: 0.727223 loss: 0.000684 2022/09/14 02:30:45 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 02:30:56 - mmengine - INFO - Epoch(train) [48][250/293] lr: 5.000000e-04 eta: 5:44:33 time: 0.511314 data_time: 0.080403 memory: 5387 loss_kpt: 0.000697 acc_pose: 0.803500 loss: 0.000697 2022/09/14 02:31:18 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 02:31:18 - mmengine - INFO - Saving checkpoint at 48 epochs 2022/09/14 02:31:48 - mmengine - INFO - Epoch(train) [49][50/293] lr: 5.000000e-04 eta: 5:43:04 time: 0.523533 data_time: 0.083112 memory: 5387 loss_kpt: 0.000689 acc_pose: 0.857112 loss: 0.000689 2022/09/14 02:32:13 - mmengine - INFO - Epoch(train) [49][100/293] lr: 5.000000e-04 eta: 5:42:54 time: 0.505114 data_time: 0.075125 memory: 5387 loss_kpt: 0.000690 acc_pose: 0.783524 loss: 0.000690 2022/09/14 02:32:39 - mmengine - INFO - Epoch(train) [49][150/293] lr: 5.000000e-04 eta: 5:42:46 time: 0.511952 data_time: 0.081997 memory: 5387 loss_kpt: 0.000698 acc_pose: 0.794318 loss: 0.000698 2022/09/14 02:33:05 - mmengine - INFO - Epoch(train) [49][200/293] lr: 5.000000e-04 eta: 5:42:37 time: 0.516589 data_time: 0.075969 memory: 5387 loss_kpt: 0.000681 acc_pose: 0.830812 loss: 0.000681 2022/09/14 02:33:30 - mmengine - INFO - Epoch(train) [49][250/293] lr: 5.000000e-04 eta: 5:42:27 time: 0.501187 data_time: 0.084918 memory: 5387 loss_kpt: 0.000680 acc_pose: 0.808781 loss: 0.000680 2022/09/14 02:33:51 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 02:33:51 - mmengine - INFO - Saving checkpoint at 49 epochs 2022/09/14 02:34:21 - mmengine - INFO - Epoch(train) [50][50/293] lr: 5.000000e-04 eta: 5:40:57 time: 0.511122 data_time: 0.083822 memory: 5387 loss_kpt: 0.000670 acc_pose: 0.826984 loss: 0.000670 2022/09/14 02:34:47 - mmengine - INFO - Epoch(train) [50][100/293] lr: 5.000000e-04 eta: 5:40:50 time: 0.519930 data_time: 0.078387 memory: 5387 loss_kpt: 0.000679 acc_pose: 0.820187 loss: 0.000679 2022/09/14 02:35:12 - mmengine - INFO - Epoch(train) [50][150/293] lr: 5.000000e-04 eta: 5:40:38 time: 0.494796 data_time: 0.073333 memory: 5387 loss_kpt: 0.000685 acc_pose: 0.807742 loss: 0.000685 2022/09/14 02:35:37 - mmengine - INFO - Epoch(train) [50][200/293] lr: 5.000000e-04 eta: 5:40:28 time: 0.509592 data_time: 0.072128 memory: 5387 loss_kpt: 0.000682 acc_pose: 0.814572 loss: 0.000682 2022/09/14 02:36:03 - mmengine - INFO - Epoch(train) [50][250/293] lr: 5.000000e-04 eta: 5:40:17 time: 0.502400 data_time: 0.084636 memory: 5387 loss_kpt: 0.000683 acc_pose: 0.804448 loss: 0.000683 2022/09/14 02:36:24 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 02:36:24 - mmengine - INFO - Saving checkpoint at 50 epochs 2022/09/14 02:36:34 - mmengine - INFO - Epoch(val) [50][50/407] eta: 0:00:44 time: 0.124748 data_time: 0.014596 memory: 5387 2022/09/14 02:36:41 - mmengine - INFO - Epoch(val) [50][100/407] eta: 0:00:37 time: 0.123516 data_time: 0.014729 memory: 920 2022/09/14 02:36:47 - mmengine - INFO - Epoch(val) [50][150/407] eta: 0:00:31 time: 0.122047 data_time: 0.009759 memory: 920 2022/09/14 02:36:53 - mmengine - INFO - Epoch(val) [50][200/407] eta: 0:00:23 time: 0.115806 data_time: 0.008919 memory: 920 2022/09/14 02:36:58 - mmengine - INFO - Epoch(val) [50][250/407] eta: 0:00:18 time: 0.115442 data_time: 0.009276 memory: 920 2022/09/14 02:37:04 - mmengine - INFO - Epoch(val) [50][300/407] eta: 0:00:12 time: 0.118522 data_time: 0.010477 memory: 920 2022/09/14 02:37:10 - mmengine - INFO - Epoch(val) [50][350/407] eta: 0:00:06 time: 0.116209 data_time: 0.009618 memory: 920 2022/09/14 02:37:16 - mmengine - INFO - Epoch(val) [50][400/407] eta: 0:00:00 time: 0.111022 data_time: 0.007893 memory: 920 2022/09/14 02:37:53 - mmengine - INFO - Evaluating CocoMetric... 2022/09/14 02:38:07 - mmengine - INFO - Epoch(val) [50][407/407] coco/AP: 0.713626 coco/AP .5: 0.893806 coco/AP .75: 0.789820 coco/AP (M): 0.679796 coco/AP (L): 0.777929 coco/AR: 0.769600 coco/AR .5: 0.933249 coco/AR .75: 0.838319 coco/AR (M): 0.728107 coco/AR (L): 0.829246 2022/09/14 02:38:07 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220914/hrnet_fp16/best_coco/AP_epoch_40.pth is removed 2022/09/14 02:38:09 - mmengine - INFO - The best checkpoint with 0.7136 coco/AP at 50 epoch is saved to best_coco/AP_epoch_50.pth. 2022/09/14 02:38:35 - mmengine - INFO - Epoch(train) [51][50/293] lr: 5.000000e-04 eta: 5:38:50 time: 0.515132 data_time: 0.083831 memory: 5387 loss_kpt: 0.000680 acc_pose: 0.813547 loss: 0.000680 2022/09/14 02:39:01 - mmengine - INFO - Epoch(train) [51][100/293] lr: 5.000000e-04 eta: 5:38:40 time: 0.508627 data_time: 0.078625 memory: 5387 loss_kpt: 0.000704 acc_pose: 0.814596 loss: 0.000704 2022/09/14 02:39:26 - mmengine - INFO - Epoch(train) [51][150/293] lr: 5.000000e-04 eta: 5:38:28 time: 0.499745 data_time: 0.076342 memory: 5387 loss_kpt: 0.000685 acc_pose: 0.791963 loss: 0.000685 2022/09/14 02:39:50 - mmengine - INFO - Epoch(train) [51][200/293] lr: 5.000000e-04 eta: 5:38:16 time: 0.493095 data_time: 0.071207 memory: 5387 loss_kpt: 0.000690 acc_pose: 0.747467 loss: 0.000690 2022/09/14 02:40:16 - mmengine - INFO - Epoch(train) [51][250/293] lr: 5.000000e-04 eta: 5:38:06 time: 0.511973 data_time: 0.089336 memory: 5387 loss_kpt: 0.000677 acc_pose: 0.780481 loss: 0.000677 2022/09/14 02:40:37 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 02:40:37 - mmengine - INFO - Saving checkpoint at 51 epochs 2022/09/14 02:41:08 - mmengine - INFO - Epoch(train) [52][50/293] lr: 5.000000e-04 eta: 5:36:41 time: 0.519072 data_time: 0.083709 memory: 5387 loss_kpt: 0.000684 acc_pose: 0.785658 loss: 0.000684 2022/09/14 02:41:11 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 02:41:33 - mmengine - INFO - Epoch(train) [52][100/293] lr: 5.000000e-04 eta: 5:36:32 time: 0.516380 data_time: 0.089572 memory: 5387 loss_kpt: 0.000667 acc_pose: 0.807409 loss: 0.000667 2022/09/14 02:41:59 - mmengine - INFO - Epoch(train) [52][150/293] lr: 5.000000e-04 eta: 5:36:21 time: 0.503133 data_time: 0.078957 memory: 5387 loss_kpt: 0.000684 acc_pose: 0.733819 loss: 0.000684 2022/09/14 02:42:24 - mmengine - INFO - Epoch(train) [52][200/293] lr: 5.000000e-04 eta: 5:36:09 time: 0.501074 data_time: 0.074633 memory: 5387 loss_kpt: 0.000683 acc_pose: 0.822626 loss: 0.000683 2022/09/14 02:42:48 - mmengine - INFO - Epoch(train) [52][250/293] lr: 5.000000e-04 eta: 5:35:57 time: 0.495375 data_time: 0.075463 memory: 5387 loss_kpt: 0.000688 acc_pose: 0.762606 loss: 0.000688 2022/09/14 02:43:10 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 02:43:10 - mmengine - INFO - Saving checkpoint at 52 epochs 2022/09/14 02:43:41 - mmengine - INFO - Epoch(train) [53][50/293] lr: 5.000000e-04 eta: 5:34:32 time: 0.515213 data_time: 0.092356 memory: 5387 loss_kpt: 0.000672 acc_pose: 0.808738 loss: 0.000672 2022/09/14 02:44:06 - mmengine - INFO - Epoch(train) [53][100/293] lr: 5.000000e-04 eta: 5:34:22 time: 0.510584 data_time: 0.083064 memory: 5387 loss_kpt: 0.000681 acc_pose: 0.794594 loss: 0.000681 2022/09/14 02:44:31 - mmengine - INFO - Epoch(train) [53][150/293] lr: 5.000000e-04 eta: 5:34:09 time: 0.498375 data_time: 0.083448 memory: 5387 loss_kpt: 0.000694 acc_pose: 0.806216 loss: 0.000694 2022/09/14 02:44:56 - mmengine - INFO - Epoch(train) [53][200/293] lr: 5.000000e-04 eta: 5:33:57 time: 0.499797 data_time: 0.073171 memory: 5387 loss_kpt: 0.000668 acc_pose: 0.756175 loss: 0.000668 2022/09/14 02:45:21 - mmengine - INFO - Epoch(train) [53][250/293] lr: 5.000000e-04 eta: 5:33:45 time: 0.497810 data_time: 0.076942 memory: 5387 loss_kpt: 0.000681 acc_pose: 0.830283 loss: 0.000681 2022/09/14 02:45:43 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 02:45:43 - mmengine - INFO - Saving checkpoint at 53 epochs 2022/09/14 02:46:12 - mmengine - INFO - Epoch(train) [54][50/293] lr: 5.000000e-04 eta: 5:32:21 time: 0.510811 data_time: 0.089369 memory: 5387 loss_kpt: 0.000675 acc_pose: 0.808880 loss: 0.000675 2022/09/14 02:46:38 - mmengine - INFO - Epoch(train) [54][100/293] lr: 5.000000e-04 eta: 5:32:10 time: 0.507960 data_time: 0.078917 memory: 5387 loss_kpt: 0.000679 acc_pose: 0.809109 loss: 0.000679 2022/09/14 02:47:03 - mmengine - INFO - Epoch(train) [54][150/293] lr: 5.000000e-04 eta: 5:31:59 time: 0.509446 data_time: 0.078854 memory: 5387 loss_kpt: 0.000681 acc_pose: 0.829197 loss: 0.000681 2022/09/14 02:47:29 - mmengine - INFO - Epoch(train) [54][200/293] lr: 5.000000e-04 eta: 5:31:48 time: 0.508789 data_time: 0.076007 memory: 5387 loss_kpt: 0.000686 acc_pose: 0.786306 loss: 0.000686 2022/09/14 02:47:54 - mmengine - INFO - Epoch(train) [54][250/293] lr: 5.000000e-04 eta: 5:31:37 time: 0.505523 data_time: 0.079055 memory: 5387 loss_kpt: 0.000689 acc_pose: 0.811646 loss: 0.000689 2022/09/14 02:48:15 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 02:48:15 - mmengine - INFO - Saving checkpoint at 54 epochs 2022/09/14 02:48:46 - mmengine - INFO - Epoch(train) [55][50/293] lr: 5.000000e-04 eta: 5:30:14 time: 0.513094 data_time: 0.089728 memory: 5387 loss_kpt: 0.000668 acc_pose: 0.818408 loss: 0.000668 2022/09/14 02:49:11 - mmengine - INFO - Epoch(train) [55][100/293] lr: 5.000000e-04 eta: 5:30:02 time: 0.505063 data_time: 0.077024 memory: 5387 loss_kpt: 0.000683 acc_pose: 0.815561 loss: 0.000683 2022/09/14 02:49:36 - mmengine - INFO - Epoch(train) [55][150/293] lr: 5.000000e-04 eta: 5:29:50 time: 0.502162 data_time: 0.082273 memory: 5387 loss_kpt: 0.000662 acc_pose: 0.763974 loss: 0.000662 2022/09/14 02:49:50 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 02:50:02 - mmengine - INFO - Epoch(train) [55][200/293] lr: 5.000000e-04 eta: 5:29:40 time: 0.515267 data_time: 0.078913 memory: 5387 loss_kpt: 0.000666 acc_pose: 0.810227 loss: 0.000666 2022/09/14 02:50:27 - mmengine - INFO - Epoch(train) [55][250/293] lr: 5.000000e-04 eta: 5:29:28 time: 0.503209 data_time: 0.075014 memory: 5387 loss_kpt: 0.000680 acc_pose: 0.768973 loss: 0.000680 2022/09/14 02:50:48 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 02:50:48 - mmengine - INFO - Saving checkpoint at 55 epochs 2022/09/14 02:51:18 - mmengine - INFO - Epoch(train) [56][50/293] lr: 5.000000e-04 eta: 5:28:07 time: 0.520713 data_time: 0.085876 memory: 5387 loss_kpt: 0.000667 acc_pose: 0.811673 loss: 0.000667 2022/09/14 02:51:44 - mmengine - INFO - Epoch(train) [56][100/293] lr: 5.000000e-04 eta: 5:27:56 time: 0.511799 data_time: 0.078653 memory: 5387 loss_kpt: 0.000664 acc_pose: 0.827674 loss: 0.000664 2022/09/14 02:52:10 - mmengine - INFO - Epoch(train) [56][150/293] lr: 5.000000e-04 eta: 5:27:46 time: 0.513887 data_time: 0.081754 memory: 5387 loss_kpt: 0.000672 acc_pose: 0.739667 loss: 0.000672 2022/09/14 02:52:35 - mmengine - INFO - Epoch(train) [56][200/293] lr: 5.000000e-04 eta: 5:27:33 time: 0.502597 data_time: 0.078263 memory: 5387 loss_kpt: 0.000661 acc_pose: 0.794219 loss: 0.000661 2022/09/14 02:53:00 - mmengine - INFO - Epoch(train) [56][250/293] lr: 5.000000e-04 eta: 5:27:21 time: 0.500484 data_time: 0.077902 memory: 5387 loss_kpt: 0.000673 acc_pose: 0.833916 loss: 0.000673 2022/09/14 02:53:22 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 02:53:22 - mmengine - INFO - Saving checkpoint at 56 epochs 2022/09/14 02:53:51 - mmengine - INFO - Epoch(train) [57][50/293] lr: 5.000000e-04 eta: 5:25:59 time: 0.505767 data_time: 0.080790 memory: 5387 loss_kpt: 0.000662 acc_pose: 0.837482 loss: 0.000662 2022/09/14 02:54:16 - mmengine - INFO - Epoch(train) [57][100/293] lr: 5.000000e-04 eta: 5:25:45 time: 0.491957 data_time: 0.071745 memory: 5387 loss_kpt: 0.000678 acc_pose: 0.855636 loss: 0.000678 2022/09/14 02:54:41 - mmengine - INFO - Epoch(train) [57][150/293] lr: 5.000000e-04 eta: 5:25:33 time: 0.502559 data_time: 0.075062 memory: 5387 loss_kpt: 0.000674 acc_pose: 0.809352 loss: 0.000674 2022/09/14 02:55:06 - mmengine - INFO - Epoch(train) [57][200/293] lr: 5.000000e-04 eta: 5:25:21 time: 0.511320 data_time: 0.082846 memory: 5387 loss_kpt: 0.000676 acc_pose: 0.787897 loss: 0.000676 2022/09/14 02:55:32 - mmengine - INFO - Epoch(train) [57][250/293] lr: 5.000000e-04 eta: 5:25:09 time: 0.507204 data_time: 0.077255 memory: 5387 loss_kpt: 0.000676 acc_pose: 0.824139 loss: 0.000676 2022/09/14 02:55:53 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 02:55:53 - mmengine - INFO - Saving checkpoint at 57 epochs 2022/09/14 02:56:23 - mmengine - INFO - Epoch(train) [58][50/293] lr: 5.000000e-04 eta: 5:23:48 time: 0.504821 data_time: 0.088470 memory: 5387 loss_kpt: 0.000678 acc_pose: 0.749040 loss: 0.000678 2022/09/14 02:56:48 - mmengine - INFO - Epoch(train) [58][100/293] lr: 5.000000e-04 eta: 5:23:36 time: 0.502519 data_time: 0.078187 memory: 5387 loss_kpt: 0.000660 acc_pose: 0.821834 loss: 0.000660 2022/09/14 02:57:13 - mmengine - INFO - Epoch(train) [58][150/293] lr: 5.000000e-04 eta: 5:23:24 time: 0.506688 data_time: 0.081400 memory: 5387 loss_kpt: 0.000668 acc_pose: 0.813340 loss: 0.000668 2022/09/14 02:57:38 - mmengine - INFO - Epoch(train) [58][200/293] lr: 5.000000e-04 eta: 5:23:11 time: 0.500546 data_time: 0.075428 memory: 5387 loss_kpt: 0.000675 acc_pose: 0.822227 loss: 0.000675 2022/09/14 02:58:03 - mmengine - INFO - Epoch(train) [58][250/293] lr: 5.000000e-04 eta: 5:22:58 time: 0.507553 data_time: 0.080034 memory: 5387 loss_kpt: 0.000654 acc_pose: 0.847852 loss: 0.000654 2022/09/14 02:58:25 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 02:58:25 - mmengine - INFO - Saving checkpoint at 58 epochs 2022/09/14 02:58:33 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 02:58:55 - mmengine - INFO - Epoch(train) [59][50/293] lr: 5.000000e-04 eta: 5:21:39 time: 0.511527 data_time: 0.083364 memory: 5387 loss_kpt: 0.000670 acc_pose: 0.803387 loss: 0.000670 2022/09/14 02:59:21 - mmengine - INFO - Epoch(train) [59][100/293] lr: 5.000000e-04 eta: 5:21:28 time: 0.512151 data_time: 0.085845 memory: 5387 loss_kpt: 0.000677 acc_pose: 0.815147 loss: 0.000677 2022/09/14 02:59:46 - mmengine - INFO - Epoch(train) [59][150/293] lr: 5.000000e-04 eta: 5:21:14 time: 0.497706 data_time: 0.075722 memory: 5387 loss_kpt: 0.000658 acc_pose: 0.784490 loss: 0.000658 2022/09/14 03:00:11 - mmengine - INFO - Epoch(train) [59][200/293] lr: 5.000000e-04 eta: 5:21:02 time: 0.509300 data_time: 0.073599 memory: 5387 loss_kpt: 0.000676 acc_pose: 0.832487 loss: 0.000676 2022/09/14 03:00:36 - mmengine - INFO - Epoch(train) [59][250/293] lr: 5.000000e-04 eta: 5:20:48 time: 0.495600 data_time: 0.077306 memory: 5387 loss_kpt: 0.000686 acc_pose: 0.827258 loss: 0.000686 2022/09/14 03:00:57 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 03:00:57 - mmengine - INFO - Saving checkpoint at 59 epochs 2022/09/14 03:01:27 - mmengine - INFO - Epoch(train) [60][50/293] lr: 5.000000e-04 eta: 5:19:31 time: 0.514571 data_time: 0.085238 memory: 5387 loss_kpt: 0.000672 acc_pose: 0.807979 loss: 0.000672 2022/09/14 03:01:52 - mmengine - INFO - Epoch(train) [60][100/293] lr: 5.000000e-04 eta: 5:19:18 time: 0.503484 data_time: 0.077363 memory: 5387 loss_kpt: 0.000663 acc_pose: 0.802549 loss: 0.000663 2022/09/14 03:02:17 - mmengine - INFO - Epoch(train) [60][150/293] lr: 5.000000e-04 eta: 5:19:05 time: 0.505542 data_time: 0.080733 memory: 5387 loss_kpt: 0.000669 acc_pose: 0.789298 loss: 0.000669 2022/09/14 03:02:43 - mmengine - INFO - Epoch(train) [60][200/293] lr: 5.000000e-04 eta: 5:18:52 time: 0.503919 data_time: 0.072578 memory: 5387 loss_kpt: 0.000664 acc_pose: 0.799931 loss: 0.000664 2022/09/14 03:03:08 - mmengine - INFO - Epoch(train) [60][250/293] lr: 5.000000e-04 eta: 5:18:38 time: 0.498376 data_time: 0.079394 memory: 5387 loss_kpt: 0.000673 acc_pose: 0.787857 loss: 0.000673 2022/09/14 03:03:29 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 03:03:29 - mmengine - INFO - Saving checkpoint at 60 epochs 2022/09/14 03:03:41 - mmengine - INFO - Epoch(val) [60][50/407] eta: 0:00:42 time: 0.119282 data_time: 0.013667 memory: 5387 2022/09/14 03:03:47 - mmengine - INFO - Epoch(val) [60][100/407] eta: 0:00:35 time: 0.116462 data_time: 0.009094 memory: 920 2022/09/14 03:03:53 - mmengine - INFO - Epoch(val) [60][150/407] eta: 0:00:30 time: 0.118243 data_time: 0.012495 memory: 920 2022/09/14 03:03:58 - mmengine - INFO - Epoch(val) [60][200/407] eta: 0:00:23 time: 0.114897 data_time: 0.009993 memory: 920 2022/09/14 03:04:04 - mmengine - INFO - Epoch(val) [60][250/407] eta: 0:00:18 time: 0.118852 data_time: 0.008729 memory: 920 2022/09/14 03:04:10 - mmengine - INFO - Epoch(val) [60][300/407] eta: 0:00:12 time: 0.114357 data_time: 0.008794 memory: 920 2022/09/14 03:04:16 - mmengine - INFO - Epoch(val) [60][350/407] eta: 0:00:06 time: 0.115098 data_time: 0.008732 memory: 920 2022/09/14 03:04:21 - mmengine - INFO - Epoch(val) [60][400/407] eta: 0:00:00 time: 0.110384 data_time: 0.007341 memory: 920 2022/09/14 03:04:58 - mmengine - INFO - Evaluating CocoMetric... 2022/09/14 03:05:12 - mmengine - INFO - Epoch(val) [60][407/407] coco/AP: 0.713112 coco/AP .5: 0.892342 coco/AP .75: 0.785069 coco/AP (M): 0.676903 coco/AP (L): 0.779576 coco/AR: 0.770057 coco/AR .5: 0.931045 coco/AR .75: 0.833753 coco/AR (M): 0.726441 coco/AR (L): 0.832330 2022/09/14 03:05:39 - mmengine - INFO - Epoch(train) [61][50/293] lr: 5.000000e-04 eta: 5:17:24 time: 0.535376 data_time: 0.084110 memory: 5387 loss_kpt: 0.000671 acc_pose: 0.793427 loss: 0.000671 2022/09/14 03:06:05 - mmengine - INFO - Epoch(train) [61][100/293] lr: 5.000000e-04 eta: 5:17:12 time: 0.513031 data_time: 0.077116 memory: 5387 loss_kpt: 0.000681 acc_pose: 0.746750 loss: 0.000681 2022/09/14 03:06:30 - mmengine - INFO - Epoch(train) [61][150/293] lr: 5.000000e-04 eta: 5:16:59 time: 0.505061 data_time: 0.076522 memory: 5387 loss_kpt: 0.000668 acc_pose: 0.811440 loss: 0.000668 2022/09/14 03:06:55 - mmengine - INFO - Epoch(train) [61][200/293] lr: 5.000000e-04 eta: 5:16:47 time: 0.508590 data_time: 0.077986 memory: 5387 loss_kpt: 0.000661 acc_pose: 0.826204 loss: 0.000661 2022/09/14 03:07:21 - mmengine - INFO - Epoch(train) [61][250/293] lr: 5.000000e-04 eta: 5:16:34 time: 0.506492 data_time: 0.079697 memory: 5387 loss_kpt: 0.000666 acc_pose: 0.822061 loss: 0.000666 2022/09/14 03:07:42 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 03:07:42 - mmengine - INFO - Saving checkpoint at 61 epochs 2022/09/14 03:08:12 - mmengine - INFO - Epoch(train) [62][50/293] lr: 5.000000e-04 eta: 5:15:17 time: 0.512959 data_time: 0.084033 memory: 5387 loss_kpt: 0.000669 acc_pose: 0.838904 loss: 0.000669 2022/09/14 03:08:38 - mmengine - INFO - Epoch(train) [62][100/293] lr: 5.000000e-04 eta: 5:15:05 time: 0.513583 data_time: 0.079740 memory: 5387 loss_kpt: 0.000653 acc_pose: 0.840440 loss: 0.000653 2022/09/14 03:08:51 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 03:09:03 - mmengine - INFO - Epoch(train) [62][150/293] lr: 5.000000e-04 eta: 5:14:53 time: 0.511563 data_time: 0.076327 memory: 5387 loss_kpt: 0.000684 acc_pose: 0.887150 loss: 0.000684 2022/09/14 03:09:29 - mmengine - INFO - Epoch(train) [62][200/293] lr: 5.000000e-04 eta: 5:14:40 time: 0.508590 data_time: 0.077513 memory: 5387 loss_kpt: 0.000664 acc_pose: 0.825731 loss: 0.000664 2022/09/14 03:09:54 - mmengine - INFO - Epoch(train) [62][250/293] lr: 5.000000e-04 eta: 5:14:27 time: 0.505623 data_time: 0.078176 memory: 5387 loss_kpt: 0.000682 acc_pose: 0.771912 loss: 0.000682 2022/09/14 03:10:16 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 03:10:16 - mmengine - INFO - Saving checkpoint at 62 epochs 2022/09/14 03:10:46 - mmengine - INFO - Epoch(train) [63][50/293] lr: 5.000000e-04 eta: 5:13:12 time: 0.519017 data_time: 0.095774 memory: 5387 loss_kpt: 0.000676 acc_pose: 0.846258 loss: 0.000676 2022/09/14 03:11:11 - mmengine - INFO - Epoch(train) [63][100/293] lr: 5.000000e-04 eta: 5:12:59 time: 0.504515 data_time: 0.078892 memory: 5387 loss_kpt: 0.000664 acc_pose: 0.814587 loss: 0.000664 2022/09/14 03:11:37 - mmengine - INFO - Epoch(train) [63][150/293] lr: 5.000000e-04 eta: 5:12:46 time: 0.512567 data_time: 0.080149 memory: 5387 loss_kpt: 0.000666 acc_pose: 0.827586 loss: 0.000666 2022/09/14 03:12:02 - mmengine - INFO - Epoch(train) [63][200/293] lr: 5.000000e-04 eta: 5:12:32 time: 0.498548 data_time: 0.073752 memory: 5387 loss_kpt: 0.000659 acc_pose: 0.852103 loss: 0.000659 2022/09/14 03:12:27 - mmengine - INFO - Epoch(train) [63][250/293] lr: 5.000000e-04 eta: 5:12:19 time: 0.510615 data_time: 0.077385 memory: 5387 loss_kpt: 0.000652 acc_pose: 0.787372 loss: 0.000652 2022/09/14 03:12:49 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 03:12:49 - mmengine - INFO - Saving checkpoint at 63 epochs 2022/09/14 03:13:20 - mmengine - INFO - Epoch(train) [64][50/293] lr: 5.000000e-04 eta: 5:11:06 time: 0.528045 data_time: 0.090786 memory: 5387 loss_kpt: 0.000655 acc_pose: 0.798763 loss: 0.000655 2022/09/14 03:13:45 - mmengine - INFO - Epoch(train) [64][100/293] lr: 5.000000e-04 eta: 5:10:53 time: 0.507888 data_time: 0.078569 memory: 5387 loss_kpt: 0.000656 acc_pose: 0.827365 loss: 0.000656 2022/09/14 03:14:10 - mmengine - INFO - Epoch(train) [64][150/293] lr: 5.000000e-04 eta: 5:10:40 time: 0.508138 data_time: 0.082551 memory: 5387 loss_kpt: 0.000656 acc_pose: 0.782174 loss: 0.000656 2022/09/14 03:14:37 - mmengine - INFO - Epoch(train) [64][200/293] lr: 5.000000e-04 eta: 5:10:28 time: 0.521924 data_time: 0.073642 memory: 5387 loss_kpt: 0.000666 acc_pose: 0.799687 loss: 0.000666 2022/09/14 03:15:02 - mmengine - INFO - Epoch(train) [64][250/293] lr: 5.000000e-04 eta: 5:10:14 time: 0.498946 data_time: 0.090102 memory: 5387 loss_kpt: 0.000665 acc_pose: 0.818527 loss: 0.000665 2022/09/14 03:15:23 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 03:15:23 - mmengine - INFO - Saving checkpoint at 64 epochs 2022/09/14 03:15:54 - mmengine - INFO - Epoch(train) [65][50/293] lr: 5.000000e-04 eta: 5:09:01 time: 0.521401 data_time: 0.090085 memory: 5387 loss_kpt: 0.000662 acc_pose: 0.792569 loss: 0.000662 2022/09/14 03:16:19 - mmengine - INFO - Epoch(train) [65][100/293] lr: 5.000000e-04 eta: 5:08:48 time: 0.508823 data_time: 0.075893 memory: 5387 loss_kpt: 0.000661 acc_pose: 0.789383 loss: 0.000661 2022/09/14 03:16:44 - mmengine - INFO - Epoch(train) [65][150/293] lr: 5.000000e-04 eta: 5:08:33 time: 0.496762 data_time: 0.080542 memory: 5387 loss_kpt: 0.000674 acc_pose: 0.798787 loss: 0.000674 2022/09/14 03:17:10 - mmengine - INFO - Epoch(train) [65][200/293] lr: 5.000000e-04 eta: 5:08:21 time: 0.514843 data_time: 0.079849 memory: 5387 loss_kpt: 0.000658 acc_pose: 0.819264 loss: 0.000658 2022/09/14 03:17:34 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 03:17:35 - mmengine - INFO - Epoch(train) [65][250/293] lr: 5.000000e-04 eta: 5:08:07 time: 0.504892 data_time: 0.076542 memory: 5387 loss_kpt: 0.000668 acc_pose: 0.765635 loss: 0.000668 2022/09/14 03:17:56 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 03:17:56 - mmengine - INFO - Saving checkpoint at 65 epochs 2022/09/14 03:18:26 - mmengine - INFO - Epoch(train) [66][50/293] lr: 5.000000e-04 eta: 5:06:53 time: 0.511077 data_time: 0.080500 memory: 5387 loss_kpt: 0.000670 acc_pose: 0.759562 loss: 0.000670 2022/09/14 03:18:52 - mmengine - INFO - Epoch(train) [66][100/293] lr: 5.000000e-04 eta: 5:06:40 time: 0.511680 data_time: 0.076127 memory: 5387 loss_kpt: 0.000654 acc_pose: 0.811542 loss: 0.000654 2022/09/14 03:19:17 - mmengine - INFO - Epoch(train) [66][150/293] lr: 5.000000e-04 eta: 5:06:27 time: 0.509271 data_time: 0.084687 memory: 5387 loss_kpt: 0.000669 acc_pose: 0.846792 loss: 0.000669 2022/09/14 03:19:42 - mmengine - INFO - Epoch(train) [66][200/293] lr: 5.000000e-04 eta: 5:06:13 time: 0.504433 data_time: 0.072381 memory: 5387 loss_kpt: 0.000672 acc_pose: 0.776393 loss: 0.000672 2022/09/14 03:20:08 - mmengine - INFO - Epoch(train) [66][250/293] lr: 5.000000e-04 eta: 5:05:59 time: 0.512190 data_time: 0.077674 memory: 5387 loss_kpt: 0.000668 acc_pose: 0.793706 loss: 0.000668 2022/09/14 03:20:30 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 03:20:30 - mmengine - INFO - Saving checkpoint at 66 epochs 2022/09/14 03:21:06 - mmengine - INFO - Epoch(train) [67][50/293] lr: 5.000000e-04 eta: 5:04:50 time: 0.545132 data_time: 0.108939 memory: 5387 loss_kpt: 0.000661 acc_pose: 0.813894 loss: 0.000661 2022/09/14 03:21:31 - mmengine - INFO - Epoch(train) [67][100/293] lr: 5.000000e-04 eta: 5:04:37 time: 0.508083 data_time: 0.078519 memory: 5387 loss_kpt: 0.000668 acc_pose: 0.830226 loss: 0.000668 2022/09/14 03:21:57 - mmengine - INFO - Epoch(train) [67][150/293] lr: 5.000000e-04 eta: 5:04:23 time: 0.510789 data_time: 0.075844 memory: 5387 loss_kpt: 0.000675 acc_pose: 0.794632 loss: 0.000675 2022/09/14 03:22:22 - mmengine - INFO - Epoch(train) [67][200/293] lr: 5.000000e-04 eta: 5:04:09 time: 0.505165 data_time: 0.075693 memory: 5387 loss_kpt: 0.000661 acc_pose: 0.824644 loss: 0.000661 2022/09/14 03:22:47 - mmengine - INFO - Epoch(train) [67][250/293] lr: 5.000000e-04 eta: 5:03:55 time: 0.509516 data_time: 0.075146 memory: 5387 loss_kpt: 0.000663 acc_pose: 0.793807 loss: 0.000663 2022/09/14 03:23:09 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 03:23:09 - mmengine - INFO - Saving checkpoint at 67 epochs 2022/09/14 03:23:39 - mmengine - INFO - Epoch(train) [68][50/293] lr: 5.000000e-04 eta: 5:02:45 time: 0.522517 data_time: 0.083253 memory: 5387 loss_kpt: 0.000657 acc_pose: 0.820538 loss: 0.000657 2022/09/14 03:24:05 - mmengine - INFO - Epoch(train) [68][100/293] lr: 5.000000e-04 eta: 5:02:31 time: 0.511139 data_time: 0.077694 memory: 5387 loss_kpt: 0.000663 acc_pose: 0.856783 loss: 0.000663 2022/09/14 03:24:30 - mmengine - INFO - Epoch(train) [68][150/293] lr: 5.000000e-04 eta: 5:02:16 time: 0.501297 data_time: 0.073125 memory: 5387 loss_kpt: 0.000671 acc_pose: 0.814345 loss: 0.000671 2022/09/14 03:24:55 - mmengine - INFO - Epoch(train) [68][200/293] lr: 5.000000e-04 eta: 5:02:03 time: 0.508837 data_time: 0.077639 memory: 5387 loss_kpt: 0.000657 acc_pose: 0.827453 loss: 0.000657 2022/09/14 03:25:21 - mmengine - INFO - Epoch(train) [68][250/293] lr: 5.000000e-04 eta: 5:01:49 time: 0.511590 data_time: 0.082468 memory: 5387 loss_kpt: 0.000672 acc_pose: 0.751360 loss: 0.000672 2022/09/14 03:25:43 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 03:25:43 - mmengine - INFO - Saving checkpoint at 68 epochs 2022/09/14 03:26:14 - mmengine - INFO - Epoch(train) [69][50/293] lr: 5.000000e-04 eta: 5:00:39 time: 0.529868 data_time: 0.089640 memory: 5387 loss_kpt: 0.000677 acc_pose: 0.828263 loss: 0.000677 2022/09/14 03:26:27 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 03:26:39 - mmengine - INFO - Epoch(train) [69][100/293] lr: 5.000000e-04 eta: 5:00:25 time: 0.501254 data_time: 0.081050 memory: 5387 loss_kpt: 0.000649 acc_pose: 0.800429 loss: 0.000649 2022/09/14 03:27:05 - mmengine - INFO - Epoch(train) [69][150/293] lr: 5.000000e-04 eta: 5:00:11 time: 0.509670 data_time: 0.080428 memory: 5387 loss_kpt: 0.000658 acc_pose: 0.830343 loss: 0.000658 2022/09/14 03:27:30 - mmengine - INFO - Epoch(train) [69][200/293] lr: 5.000000e-04 eta: 4:59:56 time: 0.502995 data_time: 0.073678 memory: 5387 loss_kpt: 0.000659 acc_pose: 0.803382 loss: 0.000659 2022/09/14 03:27:55 - mmengine - INFO - Epoch(train) [69][250/293] lr: 5.000000e-04 eta: 4:59:41 time: 0.502598 data_time: 0.076658 memory: 5387 loss_kpt: 0.000666 acc_pose: 0.794330 loss: 0.000666 2022/09/14 03:28:16 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 03:28:16 - mmengine - INFO - Saving checkpoint at 69 epochs 2022/09/14 03:28:46 - mmengine - INFO - Epoch(train) [70][50/293] lr: 5.000000e-04 eta: 4:58:31 time: 0.514272 data_time: 0.086999 memory: 5387 loss_kpt: 0.000659 acc_pose: 0.773146 loss: 0.000659 2022/09/14 03:29:12 - mmengine - INFO - Epoch(train) [70][100/293] lr: 5.000000e-04 eta: 4:58:18 time: 0.518641 data_time: 0.079998 memory: 5387 loss_kpt: 0.000669 acc_pose: 0.827327 loss: 0.000669 2022/09/14 03:29:37 - mmengine - INFO - Epoch(train) [70][150/293] lr: 5.000000e-04 eta: 4:58:02 time: 0.496711 data_time: 0.076377 memory: 5387 loss_kpt: 0.000658 acc_pose: 0.813903 loss: 0.000658 2022/09/14 03:30:03 - mmengine - INFO - Epoch(train) [70][200/293] lr: 5.000000e-04 eta: 4:57:49 time: 0.517119 data_time: 0.073384 memory: 5387 loss_kpt: 0.000656 acc_pose: 0.828156 loss: 0.000656 2022/09/14 03:30:29 - mmengine - INFO - Epoch(train) [70][250/293] lr: 5.000000e-04 eta: 4:57:35 time: 0.509434 data_time: 0.083629 memory: 5387 loss_kpt: 0.000668 acc_pose: 0.816518 loss: 0.000668 2022/09/14 03:30:51 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 03:30:51 - mmengine - INFO - Saving checkpoint at 70 epochs 2022/09/14 03:31:02 - mmengine - INFO - Epoch(val) [70][50/407] eta: 0:00:44 time: 0.125331 data_time: 0.017209 memory: 5387 2022/09/14 03:31:08 - mmengine - INFO - Epoch(val) [70][100/407] eta: 0:00:37 time: 0.121167 data_time: 0.009947 memory: 920 2022/09/14 03:31:14 - mmengine - INFO - Epoch(val) [70][150/407] eta: 0:00:31 time: 0.122050 data_time: 0.009098 memory: 920 2022/09/14 03:31:20 - mmengine - INFO - Epoch(val) [70][200/407] eta: 0:00:24 time: 0.118444 data_time: 0.009171 memory: 920 2022/09/14 03:31:26 - mmengine - INFO - Epoch(val) [70][250/407] eta: 0:00:18 time: 0.118565 data_time: 0.009379 memory: 920 2022/09/14 03:31:32 - mmengine - INFO - Epoch(val) [70][300/407] eta: 0:00:12 time: 0.120255 data_time: 0.010410 memory: 920 2022/09/14 03:31:38 - mmengine - INFO - Epoch(val) [70][350/407] eta: 0:00:07 time: 0.130876 data_time: 0.022444 memory: 920 2022/09/14 03:31:44 - mmengine - INFO - Epoch(val) [70][400/407] eta: 0:00:00 time: 0.108885 data_time: 0.006843 memory: 920 2022/09/14 03:32:21 - mmengine - INFO - Evaluating CocoMetric... 2022/09/14 03:32:35 - mmengine - INFO - Epoch(val) [70][407/407] coco/AP: 0.720384 coco/AP .5: 0.895353 coco/AP .75: 0.795869 coco/AP (M): 0.686982 coco/AP (L): 0.784604 coco/AR: 0.776354 coco/AR .5: 0.934666 coco/AR .75: 0.843986 coco/AR (M): 0.734171 coco/AR (L): 0.836715 2022/09/14 03:32:36 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220914/hrnet_fp16/best_coco/AP_epoch_50.pth is removed 2022/09/14 03:32:38 - mmengine - INFO - The best checkpoint with 0.7204 coco/AP at 70 epoch is saved to best_coco/AP_epoch_70.pth. 2022/09/14 03:33:04 - mmengine - INFO - Epoch(train) [71][50/293] lr: 5.000000e-04 eta: 4:56:25 time: 0.519011 data_time: 0.085337 memory: 5387 loss_kpt: 0.000651 acc_pose: 0.830416 loss: 0.000651 2022/09/14 03:33:30 - mmengine - INFO - Epoch(train) [71][100/293] lr: 5.000000e-04 eta: 4:56:12 time: 0.514288 data_time: 0.076200 memory: 5387 loss_kpt: 0.000661 acc_pose: 0.857238 loss: 0.000661 2022/09/14 03:33:56 - mmengine - INFO - Epoch(train) [71][150/293] lr: 5.000000e-04 eta: 4:55:58 time: 0.511083 data_time: 0.078203 memory: 5387 loss_kpt: 0.000652 acc_pose: 0.797777 loss: 0.000652 2022/09/14 03:34:20 - mmengine - INFO - Epoch(train) [71][200/293] lr: 5.000000e-04 eta: 4:55:42 time: 0.492557 data_time: 0.076661 memory: 5387 loss_kpt: 0.000663 acc_pose: 0.819834 loss: 0.000663 2022/09/14 03:34:46 - mmengine - INFO - Epoch(train) [71][250/293] lr: 5.000000e-04 eta: 4:55:27 time: 0.503904 data_time: 0.081139 memory: 5387 loss_kpt: 0.000659 acc_pose: 0.809283 loss: 0.000659 2022/09/14 03:35:07 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 03:35:07 - mmengine - INFO - Saving checkpoint at 71 epochs 2022/09/14 03:35:37 - mmengine - INFO - Epoch(train) [72][50/293] lr: 5.000000e-04 eta: 4:54:17 time: 0.513454 data_time: 0.081748 memory: 5387 loss_kpt: 0.000663 acc_pose: 0.786044 loss: 0.000663 2022/09/14 03:36:02 - mmengine - INFO - Epoch(train) [72][100/293] lr: 5.000000e-04 eta: 4:54:03 time: 0.504928 data_time: 0.083792 memory: 5387 loss_kpt: 0.000665 acc_pose: 0.848146 loss: 0.000665 2022/09/14 03:36:27 - mmengine - INFO - Epoch(train) [72][150/293] lr: 5.000000e-04 eta: 4:53:48 time: 0.503677 data_time: 0.079175 memory: 5387 loss_kpt: 0.000674 acc_pose: 0.789124 loss: 0.000674 2022/09/14 03:36:51 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 03:36:53 - mmengine - INFO - Epoch(train) [72][200/293] lr: 5.000000e-04 eta: 4:53:34 time: 0.519583 data_time: 0.078309 memory: 5387 loss_kpt: 0.000654 acc_pose: 0.832958 loss: 0.000654 2022/09/14 03:37:18 - mmengine - INFO - Epoch(train) [72][250/293] lr: 5.000000e-04 eta: 4:53:19 time: 0.507618 data_time: 0.078119 memory: 5387 loss_kpt: 0.000652 acc_pose: 0.818688 loss: 0.000652 2022/09/14 03:37:40 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 03:37:41 - mmengine - INFO - Saving checkpoint at 72 epochs 2022/09/14 03:38:11 - mmengine - INFO - Epoch(train) [73][50/293] lr: 5.000000e-04 eta: 4:52:11 time: 0.519267 data_time: 0.083895 memory: 5387 loss_kpt: 0.000652 acc_pose: 0.796063 loss: 0.000652 2022/09/14 03:38:37 - mmengine - INFO - Epoch(train) [73][100/293] lr: 5.000000e-04 eta: 4:51:57 time: 0.517380 data_time: 0.072665 memory: 5387 loss_kpt: 0.000656 acc_pose: 0.825681 loss: 0.000656 2022/09/14 03:39:02 - mmengine - INFO - Epoch(train) [73][150/293] lr: 5.000000e-04 eta: 4:51:42 time: 0.504751 data_time: 0.078672 memory: 5387 loss_kpt: 0.000665 acc_pose: 0.841411 loss: 0.000665 2022/09/14 03:39:27 - mmengine - INFO - Epoch(train) [73][200/293] lr: 5.000000e-04 eta: 4:51:28 time: 0.510758 data_time: 0.077744 memory: 5387 loss_kpt: 0.000657 acc_pose: 0.836175 loss: 0.000657 2022/09/14 03:39:53 - mmengine - INFO - Epoch(train) [73][250/293] lr: 5.000000e-04 eta: 4:51:12 time: 0.501199 data_time: 0.080322 memory: 5387 loss_kpt: 0.000655 acc_pose: 0.801477 loss: 0.000655 2022/09/14 03:40:14 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 03:40:14 - mmengine - INFO - Saving checkpoint at 73 epochs 2022/09/14 03:40:45 - mmengine - INFO - Epoch(train) [74][50/293] lr: 5.000000e-04 eta: 4:50:05 time: 0.516902 data_time: 0.087910 memory: 5387 loss_kpt: 0.000668 acc_pose: 0.803883 loss: 0.000668 2022/09/14 03:41:10 - mmengine - INFO - Epoch(train) [74][100/293] lr: 5.000000e-04 eta: 4:49:49 time: 0.502062 data_time: 0.073769 memory: 5387 loss_kpt: 0.000651 acc_pose: 0.817065 loss: 0.000651 2022/09/14 03:41:35 - mmengine - INFO - Epoch(train) [74][150/293] lr: 5.000000e-04 eta: 4:49:35 time: 0.509984 data_time: 0.076666 memory: 5387 loss_kpt: 0.000659 acc_pose: 0.833889 loss: 0.000659 2022/09/14 03:42:00 - mmengine - INFO - Epoch(train) [74][200/293] lr: 5.000000e-04 eta: 4:49:19 time: 0.505039 data_time: 0.080738 memory: 5387 loss_kpt: 0.000656 acc_pose: 0.817619 loss: 0.000656 2022/09/14 03:42:26 - mmengine - INFO - Epoch(train) [74][250/293] lr: 5.000000e-04 eta: 4:49:04 time: 0.500712 data_time: 0.077985 memory: 5387 loss_kpt: 0.000666 acc_pose: 0.838324 loss: 0.000666 2022/09/14 03:42:47 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 03:42:47 - mmengine - INFO - Saving checkpoint at 74 epochs 2022/09/14 03:43:18 - mmengine - INFO - Epoch(train) [75][50/293] lr: 5.000000e-04 eta: 4:47:57 time: 0.522589 data_time: 0.084351 memory: 5387 loss_kpt: 0.000661 acc_pose: 0.775584 loss: 0.000661 2022/09/14 03:43:43 - mmengine - INFO - Epoch(train) [75][100/293] lr: 5.000000e-04 eta: 4:47:41 time: 0.498739 data_time: 0.073167 memory: 5387 loss_kpt: 0.000672 acc_pose: 0.804601 loss: 0.000672 2022/09/14 03:44:08 - mmengine - INFO - Epoch(train) [75][150/293] lr: 5.000000e-04 eta: 4:47:27 time: 0.510936 data_time: 0.074851 memory: 5387 loss_kpt: 0.000645 acc_pose: 0.821667 loss: 0.000645 2022/09/14 03:44:33 - mmengine - INFO - Epoch(train) [75][200/293] lr: 5.000000e-04 eta: 4:47:11 time: 0.499371 data_time: 0.077576 memory: 5387 loss_kpt: 0.000644 acc_pose: 0.876917 loss: 0.000644 2022/09/14 03:44:58 - mmengine - INFO - Epoch(train) [75][250/293] lr: 5.000000e-04 eta: 4:46:55 time: 0.503919 data_time: 0.081670 memory: 5387 loss_kpt: 0.000661 acc_pose: 0.787977 loss: 0.000661 2022/09/14 03:45:20 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 03:45:20 - mmengine - INFO - Saving checkpoint at 75 epochs 2022/09/14 03:45:38 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 03:45:51 - mmengine - INFO - Epoch(train) [76][50/293] lr: 5.000000e-04 eta: 4:45:50 time: 0.533563 data_time: 0.082801 memory: 5387 loss_kpt: 0.000638 acc_pose: 0.827954 loss: 0.000638 2022/09/14 03:46:17 - mmengine - INFO - Epoch(train) [76][100/293] lr: 5.000000e-04 eta: 4:45:36 time: 0.514723 data_time: 0.076775 memory: 5387 loss_kpt: 0.000666 acc_pose: 0.816683 loss: 0.000666 2022/09/14 03:46:42 - mmengine - INFO - Epoch(train) [76][150/293] lr: 5.000000e-04 eta: 4:45:21 time: 0.509287 data_time: 0.088113 memory: 5387 loss_kpt: 0.000662 acc_pose: 0.829576 loss: 0.000662 2022/09/14 03:47:07 - mmengine - INFO - Epoch(train) [76][200/293] lr: 5.000000e-04 eta: 4:45:05 time: 0.507210 data_time: 0.080069 memory: 5387 loss_kpt: 0.000660 acc_pose: 0.837774 loss: 0.000660 2022/09/14 03:47:33 - mmengine - INFO - Epoch(train) [76][250/293] lr: 5.000000e-04 eta: 4:44:50 time: 0.508772 data_time: 0.079318 memory: 5387 loss_kpt: 0.000655 acc_pose: 0.745092 loss: 0.000655 2022/09/14 03:47:55 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 03:47:55 - mmengine - INFO - Saving checkpoint at 76 epochs 2022/09/14 03:48:26 - mmengine - INFO - Epoch(train) [77][50/293] lr: 5.000000e-04 eta: 4:43:45 time: 0.528072 data_time: 0.089303 memory: 5387 loss_kpt: 0.000655 acc_pose: 0.726106 loss: 0.000655 2022/09/14 03:48:51 - mmengine - INFO - Epoch(train) [77][100/293] lr: 5.000000e-04 eta: 4:43:29 time: 0.502769 data_time: 0.073866 memory: 5387 loss_kpt: 0.000654 acc_pose: 0.749795 loss: 0.000654 2022/09/14 03:49:17 - mmengine - INFO - Epoch(train) [77][150/293] lr: 5.000000e-04 eta: 4:43:14 time: 0.512623 data_time: 0.077745 memory: 5387 loss_kpt: 0.000652 acc_pose: 0.797838 loss: 0.000652 2022/09/14 03:49:43 - mmengine - INFO - Epoch(train) [77][200/293] lr: 5.000000e-04 eta: 4:43:00 time: 0.516748 data_time: 0.079443 memory: 5387 loss_kpt: 0.000658 acc_pose: 0.827896 loss: 0.000658 2022/09/14 03:50:08 - mmengine - INFO - Epoch(train) [77][250/293] lr: 5.000000e-04 eta: 4:42:44 time: 0.505434 data_time: 0.076266 memory: 5387 loss_kpt: 0.000645 acc_pose: 0.833488 loss: 0.000645 2022/09/14 03:50:29 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 03:50:29 - mmengine - INFO - Saving checkpoint at 77 epochs 2022/09/14 03:51:00 - mmengine - INFO - Epoch(train) [78][50/293] lr: 5.000000e-04 eta: 4:41:39 time: 0.518228 data_time: 0.092183 memory: 5387 loss_kpt: 0.000644 acc_pose: 0.806111 loss: 0.000644 2022/09/14 03:51:25 - mmengine - INFO - Epoch(train) [78][100/293] lr: 5.000000e-04 eta: 4:41:24 time: 0.512505 data_time: 0.076846 memory: 5387 loss_kpt: 0.000646 acc_pose: 0.822999 loss: 0.000646 2022/09/14 03:51:51 - mmengine - INFO - Epoch(train) [78][150/293] lr: 5.000000e-04 eta: 4:41:08 time: 0.500362 data_time: 0.082617 memory: 5387 loss_kpt: 0.000648 acc_pose: 0.806756 loss: 0.000648 2022/09/14 03:52:16 - mmengine - INFO - Epoch(train) [78][200/293] lr: 5.000000e-04 eta: 4:40:52 time: 0.500950 data_time: 0.071939 memory: 5387 loss_kpt: 0.000650 acc_pose: 0.794842 loss: 0.000650 2022/09/14 03:52:41 - mmengine - INFO - Epoch(train) [78][250/293] lr: 5.000000e-04 eta: 4:40:37 time: 0.512444 data_time: 0.076777 memory: 5387 loss_kpt: 0.000637 acc_pose: 0.843905 loss: 0.000637 2022/09/14 03:53:03 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 03:53:03 - mmengine - INFO - Saving checkpoint at 78 epochs 2022/09/14 03:53:37 - mmengine - INFO - Epoch(train) [79][50/293] lr: 5.000000e-04 eta: 4:39:33 time: 0.530072 data_time: 0.090127 memory: 5387 loss_kpt: 0.000655 acc_pose: 0.816577 loss: 0.000655 2022/09/14 03:54:03 - mmengine - INFO - Epoch(train) [79][100/293] lr: 5.000000e-04 eta: 4:39:18 time: 0.518773 data_time: 0.077155 memory: 5387 loss_kpt: 0.000657 acc_pose: 0.847328 loss: 0.000657 2022/09/14 03:54:26 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 03:54:28 - mmengine - INFO - Epoch(train) [79][150/293] lr: 5.000000e-04 eta: 4:39:03 time: 0.509066 data_time: 0.077579 memory: 5387 loss_kpt: 0.000652 acc_pose: 0.750960 loss: 0.000652 2022/09/14 03:54:53 - mmengine - INFO - Epoch(train) [79][200/293] lr: 5.000000e-04 eta: 4:38:46 time: 0.500359 data_time: 0.076573 memory: 5387 loss_kpt: 0.000667 acc_pose: 0.788115 loss: 0.000667 2022/09/14 03:55:19 - mmengine - INFO - Epoch(train) [79][250/293] lr: 5.000000e-04 eta: 4:38:31 time: 0.511975 data_time: 0.074483 memory: 5387 loss_kpt: 0.000637 acc_pose: 0.845822 loss: 0.000637 2022/09/14 03:55:41 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 03:55:41 - mmengine - INFO - Saving checkpoint at 79 epochs 2022/09/14 03:56:11 - mmengine - INFO - Epoch(train) [80][50/293] lr: 5.000000e-04 eta: 4:37:26 time: 0.516619 data_time: 0.081789 memory: 5387 loss_kpt: 0.000666 acc_pose: 0.773437 loss: 0.000666 2022/09/14 03:56:36 - mmengine - INFO - Epoch(train) [80][100/293] lr: 5.000000e-04 eta: 4:37:11 time: 0.507105 data_time: 0.073749 memory: 5387 loss_kpt: 0.000648 acc_pose: 0.855279 loss: 0.000648 2022/09/14 03:57:02 - mmengine - INFO - Epoch(train) [80][150/293] lr: 5.000000e-04 eta: 4:36:55 time: 0.512391 data_time: 0.084412 memory: 5387 loss_kpt: 0.000623 acc_pose: 0.848578 loss: 0.000623 2022/09/14 03:57:28 - mmengine - INFO - Epoch(train) [80][200/293] lr: 5.000000e-04 eta: 4:36:40 time: 0.518633 data_time: 0.075045 memory: 5387 loss_kpt: 0.000655 acc_pose: 0.786078 loss: 0.000655 2022/09/14 03:57:53 - mmengine - INFO - Epoch(train) [80][250/293] lr: 5.000000e-04 eta: 4:36:24 time: 0.502870 data_time: 0.075999 memory: 5387 loss_kpt: 0.000648 acc_pose: 0.857791 loss: 0.000648 2022/09/14 03:58:15 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 03:58:15 - mmengine - INFO - Saving checkpoint at 80 epochs 2022/09/14 03:58:26 - mmengine - INFO - Epoch(val) [80][50/407] eta: 0:00:45 time: 0.126405 data_time: 0.015541 memory: 5387 2022/09/14 03:58:32 - mmengine - INFO - Epoch(val) [80][100/407] eta: 0:00:38 time: 0.124068 data_time: 0.016259 memory: 920 2022/09/14 03:58:38 - mmengine - INFO - Epoch(val) [80][150/407] eta: 0:00:29 time: 0.116638 data_time: 0.009181 memory: 920 2022/09/14 03:58:44 - mmengine - INFO - Epoch(val) [80][200/407] eta: 0:00:25 time: 0.124365 data_time: 0.013353 memory: 920 2022/09/14 03:58:50 - mmengine - INFO - Epoch(val) [80][250/407] eta: 0:00:18 time: 0.118986 data_time: 0.009508 memory: 920 2022/09/14 03:58:56 - mmengine - INFO - Epoch(val) [80][300/407] eta: 0:00:12 time: 0.117031 data_time: 0.009406 memory: 920 2022/09/14 03:59:02 - mmengine - INFO - Epoch(val) [80][350/407] eta: 0:00:06 time: 0.119625 data_time: 0.010597 memory: 920 2022/09/14 03:59:07 - mmengine - INFO - Epoch(val) [80][400/407] eta: 0:00:00 time: 0.110813 data_time: 0.007691 memory: 920 2022/09/14 03:59:45 - mmengine - INFO - Evaluating CocoMetric... 2022/09/14 03:59:59 - mmengine - INFO - Epoch(val) [80][407/407] coco/AP: 0.723693 coco/AP .5: 0.896595 coco/AP .75: 0.798525 coco/AP (M): 0.689824 coco/AP (L): 0.787297 coco/AR: 0.780038 coco/AR .5: 0.936713 coco/AR .75: 0.846820 coco/AR (M): 0.738787 coco/AR (L): 0.839242 2022/09/14 03:59:59 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220914/hrnet_fp16/best_coco/AP_epoch_70.pth is removed 2022/09/14 04:00:02 - mmengine - INFO - The best checkpoint with 0.7237 coco/AP at 80 epoch is saved to best_coco/AP_epoch_80.pth. 2022/09/14 04:00:28 - mmengine - INFO - Epoch(train) [81][50/293] lr: 5.000000e-04 eta: 4:35:20 time: 0.512438 data_time: 0.087561 memory: 5387 loss_kpt: 0.000644 acc_pose: 0.783823 loss: 0.000644 2022/09/14 04:00:53 - mmengine - INFO - Epoch(train) [81][100/293] lr: 5.000000e-04 eta: 4:35:04 time: 0.508172 data_time: 0.076526 memory: 5387 loss_kpt: 0.000669 acc_pose: 0.779055 loss: 0.000669 2022/09/14 04:01:18 - mmengine - INFO - Epoch(train) [81][150/293] lr: 5.000000e-04 eta: 4:34:48 time: 0.503317 data_time: 0.072124 memory: 5387 loss_kpt: 0.000660 acc_pose: 0.831819 loss: 0.000660 2022/09/14 04:01:44 - mmengine - INFO - Epoch(train) [81][200/293] lr: 5.000000e-04 eta: 4:34:33 time: 0.516241 data_time: 0.084064 memory: 5387 loss_kpt: 0.000657 acc_pose: 0.818897 loss: 0.000657 2022/09/14 04:02:09 - mmengine - INFO - Epoch(train) [81][250/293] lr: 5.000000e-04 eta: 4:34:16 time: 0.501415 data_time: 0.073854 memory: 5387 loss_kpt: 0.000633 acc_pose: 0.848850 loss: 0.000633 2022/09/14 04:02:31 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 04:02:31 - mmengine - INFO - Saving checkpoint at 81 epochs 2022/09/14 04:03:01 - mmengine - INFO - Epoch(train) [82][50/293] lr: 5.000000e-04 eta: 4:33:12 time: 0.513296 data_time: 0.085227 memory: 5387 loss_kpt: 0.000655 acc_pose: 0.797242 loss: 0.000655 2022/09/14 04:03:26 - mmengine - INFO - Epoch(train) [82][100/293] lr: 5.000000e-04 eta: 4:32:56 time: 0.498052 data_time: 0.077476 memory: 5387 loss_kpt: 0.000658 acc_pose: 0.824997 loss: 0.000658 2022/09/14 04:03:52 - mmengine - INFO - Epoch(train) [82][150/293] lr: 5.000000e-04 eta: 4:32:41 time: 0.518478 data_time: 0.076723 memory: 5387 loss_kpt: 0.000655 acc_pose: 0.826476 loss: 0.000655 2022/09/14 04:04:17 - mmengine - INFO - Epoch(train) [82][200/293] lr: 5.000000e-04 eta: 4:32:24 time: 0.505697 data_time: 0.080447 memory: 5387 loss_kpt: 0.000642 acc_pose: 0.773449 loss: 0.000642 2022/09/14 04:04:43 - mmengine - INFO - Epoch(train) [82][250/293] lr: 5.000000e-04 eta: 4:32:09 time: 0.517576 data_time: 0.076659 memory: 5387 loss_kpt: 0.000653 acc_pose: 0.706703 loss: 0.000653 2022/09/14 04:04:52 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 04:05:05 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 04:05:05 - mmengine - INFO - Saving checkpoint at 82 epochs 2022/09/14 04:05:36 - mmengine - INFO - Epoch(train) [83][50/293] lr: 5.000000e-04 eta: 4:31:06 time: 0.516647 data_time: 0.088810 memory: 5387 loss_kpt: 0.000642 acc_pose: 0.844515 loss: 0.000642 2022/09/14 04:06:01 - mmengine - INFO - Epoch(train) [83][100/293] lr: 5.000000e-04 eta: 4:30:50 time: 0.506752 data_time: 0.073819 memory: 5387 loss_kpt: 0.000650 acc_pose: 0.822877 loss: 0.000650 2022/09/14 04:06:27 - mmengine - INFO - Epoch(train) [83][150/293] lr: 5.000000e-04 eta: 4:30:34 time: 0.513664 data_time: 0.078308 memory: 5387 loss_kpt: 0.000645 acc_pose: 0.827489 loss: 0.000645 2022/09/14 04:06:53 - mmengine - INFO - Epoch(train) [83][200/293] lr: 5.000000e-04 eta: 4:30:18 time: 0.510968 data_time: 0.080929 memory: 5387 loss_kpt: 0.000654 acc_pose: 0.809295 loss: 0.000654 2022/09/14 04:07:18 - mmengine - INFO - Epoch(train) [83][250/293] lr: 5.000000e-04 eta: 4:30:02 time: 0.505704 data_time: 0.082804 memory: 5387 loss_kpt: 0.000647 acc_pose: 0.844078 loss: 0.000647 2022/09/14 04:07:40 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 04:07:40 - mmengine - INFO - Saving checkpoint at 83 epochs 2022/09/14 04:08:10 - mmengine - INFO - Epoch(train) [84][50/293] lr: 5.000000e-04 eta: 4:29:00 time: 0.520560 data_time: 0.088412 memory: 5387 loss_kpt: 0.000645 acc_pose: 0.829389 loss: 0.000645 2022/09/14 04:08:35 - mmengine - INFO - Epoch(train) [84][100/293] lr: 5.000000e-04 eta: 4:28:43 time: 0.505607 data_time: 0.075706 memory: 5387 loss_kpt: 0.000643 acc_pose: 0.861293 loss: 0.000643 2022/09/14 04:09:01 - mmengine - INFO - Epoch(train) [84][150/293] lr: 5.000000e-04 eta: 4:28:27 time: 0.505600 data_time: 0.084560 memory: 5387 loss_kpt: 0.000639 acc_pose: 0.728657 loss: 0.000639 2022/09/14 04:09:26 - mmengine - INFO - Epoch(train) [84][200/293] lr: 5.000000e-04 eta: 4:28:11 time: 0.507790 data_time: 0.075996 memory: 5387 loss_kpt: 0.000650 acc_pose: 0.765893 loss: 0.000650 2022/09/14 04:09:52 - mmengine - INFO - Epoch(train) [84][250/293] lr: 5.000000e-04 eta: 4:27:55 time: 0.514071 data_time: 0.076889 memory: 5387 loss_kpt: 0.000647 acc_pose: 0.781474 loss: 0.000647 2022/09/14 04:10:13 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 04:10:13 - mmengine - INFO - Saving checkpoint at 84 epochs 2022/09/14 04:10:43 - mmengine - INFO - Epoch(train) [85][50/293] lr: 5.000000e-04 eta: 4:26:52 time: 0.509723 data_time: 0.080623 memory: 5387 loss_kpt: 0.000647 acc_pose: 0.789784 loss: 0.000647 2022/09/14 04:11:09 - mmengine - INFO - Epoch(train) [85][100/293] lr: 5.000000e-04 eta: 4:26:37 time: 0.513655 data_time: 0.078802 memory: 5387 loss_kpt: 0.000649 acc_pose: 0.822599 loss: 0.000649 2022/09/14 04:11:35 - mmengine - INFO - Epoch(train) [85][150/293] lr: 5.000000e-04 eta: 4:26:20 time: 0.508200 data_time: 0.077722 memory: 5387 loss_kpt: 0.000657 acc_pose: 0.809234 loss: 0.000657 2022/09/14 04:12:00 - mmengine - INFO - Epoch(train) [85][200/293] lr: 5.000000e-04 eta: 4:26:04 time: 0.507259 data_time: 0.081909 memory: 5387 loss_kpt: 0.000651 acc_pose: 0.815139 loss: 0.000651 2022/09/14 04:12:26 - mmengine - INFO - Epoch(train) [85][250/293] lr: 5.000000e-04 eta: 4:25:48 time: 0.514657 data_time: 0.074454 memory: 5387 loss_kpt: 0.000645 acc_pose: 0.832012 loss: 0.000645 2022/09/14 04:12:47 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 04:12:47 - mmengine - INFO - Saving checkpoint at 85 epochs 2022/09/14 04:13:18 - mmengine - INFO - Epoch(train) [86][50/293] lr: 5.000000e-04 eta: 4:24:46 time: 0.516467 data_time: 0.086217 memory: 5387 loss_kpt: 0.000626 acc_pose: 0.823680 loss: 0.000626 2022/09/14 04:13:41 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 04:13:44 - mmengine - INFO - Epoch(train) [86][100/293] lr: 5.000000e-04 eta: 4:24:31 time: 0.517708 data_time: 0.079160 memory: 5387 loss_kpt: 0.000636 acc_pose: 0.834617 loss: 0.000636 2022/09/14 04:14:09 - mmengine - INFO - Epoch(train) [86][150/293] lr: 5.000000e-04 eta: 4:24:15 time: 0.515794 data_time: 0.078830 memory: 5387 loss_kpt: 0.000644 acc_pose: 0.851708 loss: 0.000644 2022/09/14 04:14:34 - mmengine - INFO - Epoch(train) [86][200/293] lr: 5.000000e-04 eta: 4:23:58 time: 0.500486 data_time: 0.078805 memory: 5387 loss_kpt: 0.000637 acc_pose: 0.811933 loss: 0.000637 2022/09/14 04:15:00 - mmengine - INFO - Epoch(train) [86][250/293] lr: 5.000000e-04 eta: 4:23:42 time: 0.517815 data_time: 0.082550 memory: 5387 loss_kpt: 0.000650 acc_pose: 0.790807 loss: 0.000650 2022/09/14 04:15:22 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 04:15:22 - mmengine - INFO - Saving checkpoint at 86 epochs 2022/09/14 04:15:52 - mmengine - INFO - Epoch(train) [87][50/293] lr: 5.000000e-04 eta: 4:22:41 time: 0.523689 data_time: 0.081715 memory: 5387 loss_kpt: 0.000636 acc_pose: 0.806182 loss: 0.000636 2022/09/14 04:16:18 - mmengine - INFO - Epoch(train) [87][100/293] lr: 5.000000e-04 eta: 4:22:26 time: 0.525125 data_time: 0.083784 memory: 5387 loss_kpt: 0.000660 acc_pose: 0.816789 loss: 0.000660 2022/09/14 04:16:44 - mmengine - INFO - Epoch(train) [87][150/293] lr: 5.000000e-04 eta: 4:22:09 time: 0.510100 data_time: 0.080614 memory: 5387 loss_kpt: 0.000632 acc_pose: 0.832172 loss: 0.000632 2022/09/14 04:17:10 - mmengine - INFO - Epoch(train) [87][200/293] lr: 5.000000e-04 eta: 4:21:53 time: 0.514300 data_time: 0.080707 memory: 5387 loss_kpt: 0.000629 acc_pose: 0.831150 loss: 0.000629 2022/09/14 04:17:35 - mmengine - INFO - Epoch(train) [87][250/293] lr: 5.000000e-04 eta: 4:21:36 time: 0.499702 data_time: 0.079274 memory: 5387 loss_kpt: 0.000635 acc_pose: 0.811183 loss: 0.000635 2022/09/14 04:17:57 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 04:17:57 - mmengine - INFO - Saving checkpoint at 87 epochs 2022/09/14 04:18:28 - mmengine - INFO - Epoch(train) [88][50/293] lr: 5.000000e-04 eta: 4:20:36 time: 0.529139 data_time: 0.099067 memory: 5387 loss_kpt: 0.000638 acc_pose: 0.803612 loss: 0.000638 2022/09/14 04:18:53 - mmengine - INFO - Epoch(train) [88][100/293] lr: 5.000000e-04 eta: 4:20:19 time: 0.501984 data_time: 0.080439 memory: 5387 loss_kpt: 0.000643 acc_pose: 0.780828 loss: 0.000643 2022/09/14 04:19:18 - mmengine - INFO - Epoch(train) [88][150/293] lr: 5.000000e-04 eta: 4:20:02 time: 0.504294 data_time: 0.077559 memory: 5387 loss_kpt: 0.000632 acc_pose: 0.859163 loss: 0.000632 2022/09/14 04:19:44 - mmengine - INFO - Epoch(train) [88][200/293] lr: 5.000000e-04 eta: 4:19:46 time: 0.509012 data_time: 0.076125 memory: 5387 loss_kpt: 0.000645 acc_pose: 0.822449 loss: 0.000645 2022/09/14 04:20:09 - mmengine - INFO - Epoch(train) [88][250/293] lr: 5.000000e-04 eta: 4:19:30 time: 0.516485 data_time: 0.076637 memory: 5387 loss_kpt: 0.000646 acc_pose: 0.806493 loss: 0.000646 2022/09/14 04:20:31 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 04:20:31 - mmengine - INFO - Saving checkpoint at 88 epochs 2022/09/14 04:21:02 - mmengine - INFO - Epoch(train) [89][50/293] lr: 5.000000e-04 eta: 4:18:30 time: 0.527178 data_time: 0.091251 memory: 5387 loss_kpt: 0.000637 acc_pose: 0.810283 loss: 0.000637 2022/09/14 04:21:28 - mmengine - INFO - Epoch(train) [89][100/293] lr: 5.000000e-04 eta: 4:18:13 time: 0.510175 data_time: 0.084313 memory: 5387 loss_kpt: 0.000639 acc_pose: 0.806832 loss: 0.000639 2022/09/14 04:21:53 - mmengine - INFO - Epoch(train) [89][150/293] lr: 5.000000e-04 eta: 4:17:56 time: 0.506632 data_time: 0.074283 memory: 5387 loss_kpt: 0.000650 acc_pose: 0.811622 loss: 0.000650 2022/09/14 04:22:18 - mmengine - INFO - Epoch(train) [89][200/293] lr: 5.000000e-04 eta: 4:17:40 time: 0.508143 data_time: 0.075446 memory: 5387 loss_kpt: 0.000638 acc_pose: 0.792649 loss: 0.000638 2022/09/14 04:22:27 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 04:22:44 - mmengine - INFO - Epoch(train) [89][250/293] lr: 5.000000e-04 eta: 4:17:23 time: 0.504445 data_time: 0.078716 memory: 5387 loss_kpt: 0.000644 acc_pose: 0.821612 loss: 0.000644 2022/09/14 04:23:05 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 04:23:05 - mmengine - INFO - Saving checkpoint at 89 epochs 2022/09/14 04:23:36 - mmengine - INFO - Epoch(train) [90][50/293] lr: 5.000000e-04 eta: 4:16:23 time: 0.527795 data_time: 0.089646 memory: 5387 loss_kpt: 0.000644 acc_pose: 0.775077 loss: 0.000644 2022/09/14 04:24:02 - mmengine - INFO - Epoch(train) [90][100/293] lr: 5.000000e-04 eta: 4:16:07 time: 0.514704 data_time: 0.073851 memory: 5387 loss_kpt: 0.000633 acc_pose: 0.828138 loss: 0.000633 2022/09/14 04:24:27 - mmengine - INFO - Epoch(train) [90][150/293] lr: 5.000000e-04 eta: 4:15:50 time: 0.506164 data_time: 0.080026 memory: 5387 loss_kpt: 0.000648 acc_pose: 0.811765 loss: 0.000648 2022/09/14 04:24:52 - mmengine - INFO - Epoch(train) [90][200/293] lr: 5.000000e-04 eta: 4:15:32 time: 0.498463 data_time: 0.079907 memory: 5387 loss_kpt: 0.000635 acc_pose: 0.848122 loss: 0.000635 2022/09/14 04:25:18 - mmengine - INFO - Epoch(train) [90][250/293] lr: 5.000000e-04 eta: 4:15:16 time: 0.514696 data_time: 0.078856 memory: 5387 loss_kpt: 0.000639 acc_pose: 0.847389 loss: 0.000639 2022/09/14 04:25:40 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 04:25:40 - mmengine - INFO - Saving checkpoint at 90 epochs 2022/09/14 04:25:51 - mmengine - INFO - Epoch(val) [90][50/407] eta: 0:00:44 time: 0.125522 data_time: 0.017557 memory: 5387 2022/09/14 04:25:57 - mmengine - INFO - Epoch(val) [90][100/407] eta: 0:00:35 time: 0.117034 data_time: 0.010732 memory: 920 2022/09/14 04:26:03 - mmengine - INFO - Epoch(val) [90][150/407] eta: 0:00:29 time: 0.115869 data_time: 0.009087 memory: 920 2022/09/14 04:26:09 - mmengine - INFO - Epoch(val) [90][200/407] eta: 0:00:23 time: 0.114304 data_time: 0.008912 memory: 920 2022/09/14 04:26:14 - mmengine - INFO - Epoch(val) [90][250/407] eta: 0:00:18 time: 0.114691 data_time: 0.009065 memory: 920 2022/09/14 04:26:20 - mmengine - INFO - Epoch(val) [90][300/407] eta: 0:00:12 time: 0.113997 data_time: 0.008623 memory: 920 2022/09/14 04:26:26 - mmengine - INFO - Epoch(val) [90][350/407] eta: 0:00:06 time: 0.121243 data_time: 0.009374 memory: 920 2022/09/14 04:26:32 - mmengine - INFO - Epoch(val) [90][400/407] eta: 0:00:00 time: 0.110776 data_time: 0.007795 memory: 920 2022/09/14 04:27:08 - mmengine - INFO - Evaluating CocoMetric... 2022/09/14 04:27:22 - mmengine - INFO - Epoch(val) [90][407/407] coco/AP: 0.725762 coco/AP .5: 0.895876 coco/AP .75: 0.799976 coco/AP (M): 0.690195 coco/AP (L): 0.792667 coco/AR: 0.781533 coco/AR .5: 0.934351 coco/AR .75: 0.847764 coco/AR (M): 0.739252 coco/AR (L): 0.842289 2022/09/14 04:27:22 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220914/hrnet_fp16/best_coco/AP_epoch_80.pth is removed 2022/09/14 04:27:25 - mmengine - INFO - The best checkpoint with 0.7258 coco/AP at 90 epoch is saved to best_coco/AP_epoch_90.pth. 2022/09/14 04:27:51 - mmengine - INFO - Epoch(train) [91][50/293] lr: 5.000000e-04 eta: 4:14:16 time: 0.511436 data_time: 0.085036 memory: 5387 loss_kpt: 0.000640 acc_pose: 0.797203 loss: 0.000640 2022/09/14 04:28:16 - mmengine - INFO - Epoch(train) [91][100/293] lr: 5.000000e-04 eta: 4:13:59 time: 0.512957 data_time: 0.075397 memory: 5387 loss_kpt: 0.000642 acc_pose: 0.767507 loss: 0.000642 2022/09/14 04:28:43 - mmengine - INFO - Epoch(train) [91][150/293] lr: 5.000000e-04 eta: 4:13:43 time: 0.525656 data_time: 0.081608 memory: 5387 loss_kpt: 0.000641 acc_pose: 0.851357 loss: 0.000641 2022/09/14 04:29:08 - mmengine - INFO - Epoch(train) [91][200/293] lr: 5.000000e-04 eta: 4:13:26 time: 0.503579 data_time: 0.077260 memory: 5387 loss_kpt: 0.000650 acc_pose: 0.756474 loss: 0.000650 2022/09/14 04:29:33 - mmengine - INFO - Epoch(train) [91][250/293] lr: 5.000000e-04 eta: 4:13:09 time: 0.505018 data_time: 0.076535 memory: 5387 loss_kpt: 0.000643 acc_pose: 0.801042 loss: 0.000643 2022/09/14 04:29:55 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 04:29:55 - mmengine - INFO - Saving checkpoint at 91 epochs 2022/09/14 04:30:25 - mmengine - INFO - Epoch(train) [92][50/293] lr: 5.000000e-04 eta: 4:12:10 time: 0.519384 data_time: 0.087488 memory: 5387 loss_kpt: 0.000647 acc_pose: 0.786670 loss: 0.000647 2022/09/14 04:30:51 - mmengine - INFO - Epoch(train) [92][100/293] lr: 5.000000e-04 eta: 4:11:53 time: 0.511900 data_time: 0.082561 memory: 5387 loss_kpt: 0.000635 acc_pose: 0.828840 loss: 0.000635 2022/09/14 04:31:16 - mmengine - INFO - Epoch(train) [92][150/293] lr: 5.000000e-04 eta: 4:11:36 time: 0.506526 data_time: 0.087386 memory: 5387 loss_kpt: 0.000622 acc_pose: 0.846929 loss: 0.000622 2022/09/14 04:31:42 - mmengine - INFO - Epoch(train) [92][200/293] lr: 5.000000e-04 eta: 4:11:19 time: 0.511184 data_time: 0.075722 memory: 5387 loss_kpt: 0.000635 acc_pose: 0.799623 loss: 0.000635 2022/09/14 04:32:07 - mmengine - INFO - Epoch(train) [92][250/293] lr: 5.000000e-04 eta: 4:11:01 time: 0.495923 data_time: 0.077875 memory: 5387 loss_kpt: 0.000640 acc_pose: 0.797955 loss: 0.000640 2022/09/14 04:32:28 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 04:32:28 - mmengine - INFO - Saving checkpoint at 92 epochs 2022/09/14 04:32:56 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 04:32:59 - mmengine - INFO - Epoch(train) [93][50/293] lr: 5.000000e-04 eta: 4:10:03 time: 0.528601 data_time: 0.091398 memory: 5387 loss_kpt: 0.000642 acc_pose: 0.815904 loss: 0.000642 2022/09/14 04:33:24 - mmengine - INFO - Epoch(train) [93][100/293] lr: 5.000000e-04 eta: 4:09:46 time: 0.510687 data_time: 0.074612 memory: 5387 loss_kpt: 0.000641 acc_pose: 0.809879 loss: 0.000641 2022/09/14 04:33:50 - mmengine - INFO - Epoch(train) [93][150/293] lr: 5.000000e-04 eta: 4:09:29 time: 0.512259 data_time: 0.081655 memory: 5387 loss_kpt: 0.000642 acc_pose: 0.833934 loss: 0.000642 2022/09/14 04:34:15 - mmengine - INFO - Epoch(train) [93][200/293] lr: 5.000000e-04 eta: 4:09:12 time: 0.507665 data_time: 0.082204 memory: 5387 loss_kpt: 0.000639 acc_pose: 0.835088 loss: 0.000639 2022/09/14 04:34:40 - mmengine - INFO - Epoch(train) [93][250/293] lr: 5.000000e-04 eta: 4:08:54 time: 0.498648 data_time: 0.078542 memory: 5387 loss_kpt: 0.000632 acc_pose: 0.854802 loss: 0.000632 2022/09/14 04:35:01 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 04:35:01 - mmengine - INFO - Saving checkpoint at 93 epochs 2022/09/14 04:35:31 - mmengine - INFO - Epoch(train) [94][50/293] lr: 5.000000e-04 eta: 4:07:55 time: 0.506961 data_time: 0.089426 memory: 5387 loss_kpt: 0.000635 acc_pose: 0.847025 loss: 0.000635 2022/09/14 04:35:56 - mmengine - INFO - Epoch(train) [94][100/293] lr: 5.000000e-04 eta: 4:07:37 time: 0.503233 data_time: 0.073835 memory: 5387 loss_kpt: 0.000622 acc_pose: 0.835834 loss: 0.000622 2022/09/14 04:36:21 - mmengine - INFO - Epoch(train) [94][150/293] lr: 5.000000e-04 eta: 4:07:20 time: 0.500424 data_time: 0.081640 memory: 5387 loss_kpt: 0.000648 acc_pose: 0.838525 loss: 0.000648 2022/09/14 04:36:46 - mmengine - INFO - Epoch(train) [94][200/293] lr: 5.000000e-04 eta: 4:07:01 time: 0.489296 data_time: 0.078328 memory: 5387 loss_kpt: 0.000638 acc_pose: 0.766770 loss: 0.000638 2022/09/14 04:37:11 - mmengine - INFO - Epoch(train) [94][250/293] lr: 5.000000e-04 eta: 4:06:44 time: 0.508146 data_time: 0.078700 memory: 5387 loss_kpt: 0.000637 acc_pose: 0.793110 loss: 0.000637 2022/09/14 04:37:33 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 04:37:33 - mmengine - INFO - Saving checkpoint at 94 epochs 2022/09/14 04:38:04 - mmengine - INFO - Epoch(train) [95][50/293] lr: 5.000000e-04 eta: 4:05:47 time: 0.536949 data_time: 0.088914 memory: 5387 loss_kpt: 0.000642 acc_pose: 0.846567 loss: 0.000642 2022/09/14 04:38:29 - mmengine - INFO - Epoch(train) [95][100/293] lr: 5.000000e-04 eta: 4:05:30 time: 0.508614 data_time: 0.079653 memory: 5387 loss_kpt: 0.000636 acc_pose: 0.824289 loss: 0.000636 2022/09/14 04:38:54 - mmengine - INFO - Epoch(train) [95][150/293] lr: 5.000000e-04 eta: 4:05:12 time: 0.502989 data_time: 0.079396 memory: 5387 loss_kpt: 0.000632 acc_pose: 0.816914 loss: 0.000632 2022/09/14 04:39:20 - mmengine - INFO - Epoch(train) [95][200/293] lr: 5.000000e-04 eta: 4:04:55 time: 0.503614 data_time: 0.085091 memory: 5387 loss_kpt: 0.000628 acc_pose: 0.800617 loss: 0.000628 2022/09/14 04:39:45 - mmengine - INFO - Epoch(train) [95][250/293] lr: 5.000000e-04 eta: 4:04:38 time: 0.509236 data_time: 0.075265 memory: 5387 loss_kpt: 0.000630 acc_pose: 0.829042 loss: 0.000630 2022/09/14 04:40:07 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 04:40:07 - mmengine - INFO - Saving checkpoint at 95 epochs 2022/09/14 04:40:37 - mmengine - INFO - Epoch(train) [96][50/293] lr: 5.000000e-04 eta: 4:03:40 time: 0.519873 data_time: 0.082742 memory: 5387 loss_kpt: 0.000636 acc_pose: 0.817857 loss: 0.000636 2022/09/14 04:41:02 - mmengine - INFO - Epoch(train) [96][100/293] lr: 5.000000e-04 eta: 4:03:22 time: 0.500593 data_time: 0.080497 memory: 5387 loss_kpt: 0.000636 acc_pose: 0.805556 loss: 0.000636 2022/09/14 04:41:28 - mmengine - INFO - Epoch(train) [96][150/293] lr: 5.000000e-04 eta: 4:03:04 time: 0.505646 data_time: 0.083347 memory: 5387 loss_kpt: 0.000631 acc_pose: 0.859805 loss: 0.000631 2022/09/14 04:41:35 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 04:41:53 - mmengine - INFO - Epoch(train) [96][200/293] lr: 5.000000e-04 eta: 4:02:47 time: 0.512247 data_time: 0.075266 memory: 5387 loss_kpt: 0.000637 acc_pose: 0.771451 loss: 0.000637 2022/09/14 04:42:18 - mmengine - INFO - Epoch(train) [96][250/293] lr: 5.000000e-04 eta: 4:02:30 time: 0.504623 data_time: 0.079243 memory: 5387 loss_kpt: 0.000632 acc_pose: 0.808910 loss: 0.000632 2022/09/14 04:42:40 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 04:42:40 - mmengine - INFO - Saving checkpoint at 96 epochs 2022/09/14 04:43:11 - mmengine - INFO - Epoch(train) [97][50/293] lr: 5.000000e-04 eta: 4:01:32 time: 0.518713 data_time: 0.089717 memory: 5387 loss_kpt: 0.000633 acc_pose: 0.819266 loss: 0.000633 2022/09/14 04:43:36 - mmengine - INFO - Epoch(train) [97][100/293] lr: 5.000000e-04 eta: 4:01:15 time: 0.515019 data_time: 0.078085 memory: 5387 loss_kpt: 0.000625 acc_pose: 0.823452 loss: 0.000625 2022/09/14 04:44:02 - mmengine - INFO - Epoch(train) [97][150/293] lr: 5.000000e-04 eta: 4:00:58 time: 0.508130 data_time: 0.078276 memory: 5387 loss_kpt: 0.000632 acc_pose: 0.856506 loss: 0.000632 2022/09/14 04:44:27 - mmengine - INFO - Epoch(train) [97][200/293] lr: 5.000000e-04 eta: 4:00:40 time: 0.504419 data_time: 0.083501 memory: 5387 loss_kpt: 0.000641 acc_pose: 0.796494 loss: 0.000641 2022/09/14 04:44:53 - mmengine - INFO - Epoch(train) [97][250/293] lr: 5.000000e-04 eta: 4:00:23 time: 0.513088 data_time: 0.084142 memory: 5387 loss_kpt: 0.000636 acc_pose: 0.809997 loss: 0.000636 2022/09/14 04:45:15 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 04:45:15 - mmengine - INFO - Saving checkpoint at 97 epochs 2022/09/14 04:45:46 - mmengine - INFO - Epoch(train) [98][50/293] lr: 5.000000e-04 eta: 3:59:26 time: 0.527297 data_time: 0.084732 memory: 5387 loss_kpt: 0.000624 acc_pose: 0.813571 loss: 0.000624 2022/09/14 04:46:11 - mmengine - INFO - Epoch(train) [98][100/293] lr: 5.000000e-04 eta: 3:59:09 time: 0.509202 data_time: 0.079658 memory: 5387 loss_kpt: 0.000640 acc_pose: 0.835784 loss: 0.000640 2022/09/14 04:46:36 - mmengine - INFO - Epoch(train) [98][150/293] lr: 5.000000e-04 eta: 3:58:51 time: 0.506406 data_time: 0.087759 memory: 5387 loss_kpt: 0.000644 acc_pose: 0.824192 loss: 0.000644 2022/09/14 04:47:02 - mmengine - INFO - Epoch(train) [98][200/293] lr: 5.000000e-04 eta: 3:58:34 time: 0.519790 data_time: 0.074915 memory: 5387 loss_kpt: 0.000635 acc_pose: 0.794366 loss: 0.000635 2022/09/14 04:47:28 - mmengine - INFO - Epoch(train) [98][250/293] lr: 5.000000e-04 eta: 3:58:16 time: 0.503997 data_time: 0.079595 memory: 5387 loss_kpt: 0.000639 acc_pose: 0.825219 loss: 0.000639 2022/09/14 04:47:49 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 04:47:49 - mmengine - INFO - Saving checkpoint at 98 epochs 2022/09/14 04:48:20 - mmengine - INFO - Epoch(train) [99][50/293] lr: 5.000000e-04 eta: 3:57:20 time: 0.527553 data_time: 0.088264 memory: 5387 loss_kpt: 0.000634 acc_pose: 0.796513 loss: 0.000634 2022/09/14 04:48:46 - mmengine - INFO - Epoch(train) [99][100/293] lr: 5.000000e-04 eta: 3:57:03 time: 0.514894 data_time: 0.089517 memory: 5387 loss_kpt: 0.000639 acc_pose: 0.809605 loss: 0.000639 2022/09/14 04:49:11 - mmengine - INFO - Epoch(train) [99][150/293] lr: 5.000000e-04 eta: 3:56:45 time: 0.507369 data_time: 0.072832 memory: 5387 loss_kpt: 0.000641 acc_pose: 0.822701 loss: 0.000641 2022/09/14 04:49:36 - mmengine - INFO - Epoch(train) [99][200/293] lr: 5.000000e-04 eta: 3:56:27 time: 0.497569 data_time: 0.077829 memory: 5387 loss_kpt: 0.000634 acc_pose: 0.771086 loss: 0.000634 2022/09/14 04:50:02 - mmengine - INFO - Epoch(train) [99][250/293] lr: 5.000000e-04 eta: 3:56:09 time: 0.511807 data_time: 0.076984 memory: 5387 loss_kpt: 0.000630 acc_pose: 0.832664 loss: 0.000630 2022/09/14 04:50:21 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 04:50:24 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 04:50:24 - mmengine - INFO - Saving checkpoint at 99 epochs 2022/09/14 04:50:55 - mmengine - INFO - Epoch(train) [100][50/293] lr: 5.000000e-04 eta: 3:55:13 time: 0.526670 data_time: 0.084103 memory: 5387 loss_kpt: 0.000631 acc_pose: 0.858884 loss: 0.000631 2022/09/14 04:51:20 - mmengine - INFO - Epoch(train) [100][100/293] lr: 5.000000e-04 eta: 3:54:56 time: 0.512738 data_time: 0.081057 memory: 5387 loss_kpt: 0.000626 acc_pose: 0.814524 loss: 0.000626 2022/09/14 04:51:47 - mmengine - INFO - Epoch(train) [100][150/293] lr: 5.000000e-04 eta: 3:54:39 time: 0.524450 data_time: 0.090936 memory: 5387 loss_kpt: 0.000633 acc_pose: 0.840657 loss: 0.000633 2022/09/14 04:52:12 - mmengine - INFO - Epoch(train) [100][200/293] lr: 5.000000e-04 eta: 3:54:21 time: 0.507506 data_time: 0.075070 memory: 5387 loss_kpt: 0.000640 acc_pose: 0.781342 loss: 0.000640 2022/09/14 04:52:37 - mmengine - INFO - Epoch(train) [100][250/293] lr: 5.000000e-04 eta: 3:54:03 time: 0.505362 data_time: 0.077749 memory: 5387 loss_kpt: 0.000637 acc_pose: 0.836311 loss: 0.000637 2022/09/14 04:52:59 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 04:52:59 - mmengine - INFO - Saving checkpoint at 100 epochs 2022/09/14 04:53:09 - mmengine - INFO - Epoch(val) [100][50/407] eta: 0:00:44 time: 0.123452 data_time: 0.015369 memory: 5387 2022/09/14 04:53:15 - mmengine - INFO - Epoch(val) [100][100/407] eta: 0:00:36 time: 0.118271 data_time: 0.010688 memory: 920 2022/09/14 04:53:21 - mmengine - INFO - Epoch(val) [100][150/407] eta: 0:00:29 time: 0.115810 data_time: 0.010209 memory: 920 2022/09/14 04:53:27 - mmengine - INFO - Epoch(val) [100][200/407] eta: 0:00:24 time: 0.120376 data_time: 0.014448 memory: 920 2022/09/14 04:53:33 - mmengine - INFO - Epoch(val) [100][250/407] eta: 0:00:18 time: 0.115289 data_time: 0.009614 memory: 920 2022/09/14 04:53:39 - mmengine - INFO - Epoch(val) [100][300/407] eta: 0:00:12 time: 0.119927 data_time: 0.013011 memory: 920 2022/09/14 04:53:45 - mmengine - INFO - Epoch(val) [100][350/407] eta: 0:00:07 time: 0.128119 data_time: 0.017075 memory: 920 2022/09/14 04:53:51 - mmengine - INFO - Epoch(val) [100][400/407] eta: 0:00:00 time: 0.112300 data_time: 0.008135 memory: 920 2022/09/14 04:54:28 - mmengine - INFO - Evaluating CocoMetric... 2022/09/14 04:54:41 - mmengine - INFO - Epoch(val) [100][407/407] coco/AP: 0.726791 coco/AP .5: 0.895469 coco/AP .75: 0.800590 coco/AP (M): 0.691689 coco/AP (L): 0.794302 coco/AR: 0.782352 coco/AR .5: 0.935296 coco/AR .75: 0.847135 coco/AR (M): 0.739552 coco/AR (L): 0.843961 2022/09/14 04:54:42 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220914/hrnet_fp16/best_coco/AP_epoch_90.pth is removed 2022/09/14 04:54:45 - mmengine - INFO - The best checkpoint with 0.7268 coco/AP at 100 epoch is saved to best_coco/AP_epoch_100.pth. 2022/09/14 04:55:11 - mmengine - INFO - Epoch(train) [101][50/293] lr: 5.000000e-04 eta: 3:53:07 time: 0.523443 data_time: 0.088472 memory: 5387 loss_kpt: 0.000639 acc_pose: 0.813635 loss: 0.000639 2022/09/14 04:55:36 - mmengine - INFO - Epoch(train) [101][100/293] lr: 5.000000e-04 eta: 3:52:49 time: 0.501528 data_time: 0.078717 memory: 5387 loss_kpt: 0.000635 acc_pose: 0.852098 loss: 0.000635 2022/09/14 04:56:02 - mmengine - INFO - Epoch(train) [101][150/293] lr: 5.000000e-04 eta: 3:52:32 time: 0.511047 data_time: 0.076922 memory: 5387 loss_kpt: 0.000632 acc_pose: 0.856367 loss: 0.000632 2022/09/14 04:56:27 - mmengine - INFO - Epoch(train) [101][200/293] lr: 5.000000e-04 eta: 3:52:14 time: 0.503949 data_time: 0.078666 memory: 5387 loss_kpt: 0.000635 acc_pose: 0.834349 loss: 0.000635 2022/09/14 04:56:52 - mmengine - INFO - Epoch(train) [101][250/293] lr: 5.000000e-04 eta: 3:51:56 time: 0.508164 data_time: 0.078902 memory: 5387 loss_kpt: 0.000627 acc_pose: 0.814952 loss: 0.000627 2022/09/14 04:57:14 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 04:57:14 - mmengine - INFO - Saving checkpoint at 101 epochs 2022/09/14 04:57:44 - mmengine - INFO - Epoch(train) [102][50/293] lr: 5.000000e-04 eta: 3:51:00 time: 0.519320 data_time: 0.085374 memory: 5387 loss_kpt: 0.000642 acc_pose: 0.834138 loss: 0.000642 2022/09/14 04:58:10 - mmengine - INFO - Epoch(train) [102][100/293] lr: 5.000000e-04 eta: 3:50:42 time: 0.506158 data_time: 0.079346 memory: 5387 loss_kpt: 0.000624 acc_pose: 0.837005 loss: 0.000624 2022/09/14 04:58:36 - mmengine - INFO - Epoch(train) [102][150/293] lr: 5.000000e-04 eta: 3:50:25 time: 0.530712 data_time: 0.077985 memory: 5387 loss_kpt: 0.000633 acc_pose: 0.780105 loss: 0.000633 2022/09/14 04:59:01 - mmengine - INFO - Epoch(train) [102][200/293] lr: 5.000000e-04 eta: 3:50:07 time: 0.497231 data_time: 0.072597 memory: 5387 loss_kpt: 0.000627 acc_pose: 0.839664 loss: 0.000627 2022/09/14 04:59:27 - mmengine - INFO - Epoch(train) [102][250/293] lr: 5.000000e-04 eta: 3:49:49 time: 0.507471 data_time: 0.083915 memory: 5387 loss_kpt: 0.000639 acc_pose: 0.775708 loss: 0.000639 2022/09/14 04:59:48 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 04:59:48 - mmengine - INFO - Saving checkpoint at 102 epochs 2022/09/14 05:00:19 - mmengine - INFO - Epoch(train) [103][50/293] lr: 5.000000e-04 eta: 3:48:53 time: 0.526623 data_time: 0.091461 memory: 5387 loss_kpt: 0.000619 acc_pose: 0.860473 loss: 0.000619 2022/09/14 05:00:45 - mmengine - INFO - Epoch(train) [103][100/293] lr: 5.000000e-04 eta: 3:48:36 time: 0.511470 data_time: 0.074336 memory: 5387 loss_kpt: 0.000635 acc_pose: 0.865619 loss: 0.000635 2022/09/14 05:00:52 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 05:01:10 - mmengine - INFO - Epoch(train) [103][150/293] lr: 5.000000e-04 eta: 3:48:18 time: 0.509289 data_time: 0.079329 memory: 5387 loss_kpt: 0.000628 acc_pose: 0.814455 loss: 0.000628 2022/09/14 05:01:36 - mmengine - INFO - Epoch(train) [103][200/293] lr: 5.000000e-04 eta: 3:48:00 time: 0.505874 data_time: 0.079913 memory: 5387 loss_kpt: 0.000627 acc_pose: 0.834158 loss: 0.000627 2022/09/14 05:02:01 - mmengine - INFO - Epoch(train) [103][250/293] lr: 5.000000e-04 eta: 3:47:42 time: 0.509116 data_time: 0.076752 memory: 5387 loss_kpt: 0.000631 acc_pose: 0.848837 loss: 0.000631 2022/09/14 05:02:22 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 05:02:22 - mmengine - INFO - Saving checkpoint at 103 epochs 2022/09/14 05:02:53 - mmengine - INFO - Epoch(train) [104][50/293] lr: 5.000000e-04 eta: 3:46:47 time: 0.522181 data_time: 0.090879 memory: 5387 loss_kpt: 0.000639 acc_pose: 0.817990 loss: 0.000639 2022/09/14 05:03:19 - mmengine - INFO - Epoch(train) [104][100/293] lr: 5.000000e-04 eta: 3:46:29 time: 0.505964 data_time: 0.076025 memory: 5387 loss_kpt: 0.000638 acc_pose: 0.811047 loss: 0.000638 2022/09/14 05:03:44 - mmengine - INFO - Epoch(train) [104][150/293] lr: 5.000000e-04 eta: 3:46:11 time: 0.507887 data_time: 0.074300 memory: 5387 loss_kpt: 0.000631 acc_pose: 0.812397 loss: 0.000631 2022/09/14 05:04:09 - mmengine - INFO - Epoch(train) [104][200/293] lr: 5.000000e-04 eta: 3:45:52 time: 0.499490 data_time: 0.083165 memory: 5387 loss_kpt: 0.000631 acc_pose: 0.852146 loss: 0.000631 2022/09/14 05:04:35 - mmengine - INFO - Epoch(train) [104][250/293] lr: 5.000000e-04 eta: 3:45:34 time: 0.512461 data_time: 0.079236 memory: 5387 loss_kpt: 0.000620 acc_pose: 0.820742 loss: 0.000620 2022/09/14 05:04:56 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 05:04:56 - mmengine - INFO - Saving checkpoint at 104 epochs 2022/09/14 05:05:27 - mmengine - INFO - Epoch(train) [105][50/293] lr: 5.000000e-04 eta: 3:44:39 time: 0.516582 data_time: 0.090792 memory: 5387 loss_kpt: 0.000626 acc_pose: 0.808326 loss: 0.000626 2022/09/14 05:05:53 - mmengine - INFO - Epoch(train) [105][100/293] lr: 5.000000e-04 eta: 3:44:21 time: 0.517649 data_time: 0.078250 memory: 5387 loss_kpt: 0.000622 acc_pose: 0.784093 loss: 0.000622 2022/09/14 05:06:18 - mmengine - INFO - Epoch(train) [105][150/293] lr: 5.000000e-04 eta: 3:44:04 time: 0.511418 data_time: 0.074694 memory: 5387 loss_kpt: 0.000628 acc_pose: 0.851390 loss: 0.000628 2022/09/14 05:06:44 - mmengine - INFO - Epoch(train) [105][200/293] lr: 5.000000e-04 eta: 3:43:46 time: 0.513145 data_time: 0.079540 memory: 5387 loss_kpt: 0.000608 acc_pose: 0.846683 loss: 0.000608 2022/09/14 05:07:09 - mmengine - INFO - Epoch(train) [105][250/293] lr: 5.000000e-04 eta: 3:43:28 time: 0.509803 data_time: 0.077040 memory: 5387 loss_kpt: 0.000629 acc_pose: 0.804443 loss: 0.000629 2022/09/14 05:07:31 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 05:07:31 - mmengine - INFO - Saving checkpoint at 105 epochs 2022/09/14 05:08:01 - mmengine - INFO - Epoch(train) [106][50/293] lr: 5.000000e-04 eta: 3:42:33 time: 0.515102 data_time: 0.084182 memory: 5387 loss_kpt: 0.000628 acc_pose: 0.808115 loss: 0.000628 2022/09/14 05:08:27 - mmengine - INFO - Epoch(train) [106][100/293] lr: 5.000000e-04 eta: 3:42:15 time: 0.515326 data_time: 0.078350 memory: 5387 loss_kpt: 0.000637 acc_pose: 0.784735 loss: 0.000637 2022/09/14 05:08:52 - mmengine - INFO - Epoch(train) [106][150/293] lr: 5.000000e-04 eta: 3:41:57 time: 0.503305 data_time: 0.078223 memory: 5387 loss_kpt: 0.000630 acc_pose: 0.843867 loss: 0.000630 2022/09/14 05:09:17 - mmengine - INFO - Epoch(train) [106][200/293] lr: 5.000000e-04 eta: 3:41:38 time: 0.507823 data_time: 0.077649 memory: 5387 loss_kpt: 0.000634 acc_pose: 0.865364 loss: 0.000634 2022/09/14 05:09:36 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 05:09:43 - mmengine - INFO - Epoch(train) [106][250/293] lr: 5.000000e-04 eta: 3:41:20 time: 0.510050 data_time: 0.084145 memory: 5387 loss_kpt: 0.000634 acc_pose: 0.810371 loss: 0.000634 2022/09/14 05:10:04 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 05:10:04 - mmengine - INFO - Saving checkpoint at 106 epochs 2022/09/14 05:10:35 - mmengine - INFO - Epoch(train) [107][50/293] lr: 5.000000e-04 eta: 3:40:25 time: 0.516900 data_time: 0.092219 memory: 5387 loss_kpt: 0.000627 acc_pose: 0.797162 loss: 0.000627 2022/09/14 05:11:00 - mmengine - INFO - Epoch(train) [107][100/293] lr: 5.000000e-04 eta: 3:40:07 time: 0.507287 data_time: 0.073480 memory: 5387 loss_kpt: 0.000636 acc_pose: 0.806138 loss: 0.000636 2022/09/14 05:11:25 - mmengine - INFO - Epoch(train) [107][150/293] lr: 5.000000e-04 eta: 3:39:49 time: 0.506363 data_time: 0.084233 memory: 5387 loss_kpt: 0.000625 acc_pose: 0.840225 loss: 0.000625 2022/09/14 05:11:51 - mmengine - INFO - Epoch(train) [107][200/293] lr: 5.000000e-04 eta: 3:39:31 time: 0.512485 data_time: 0.081262 memory: 5387 loss_kpt: 0.000633 acc_pose: 0.814866 loss: 0.000633 2022/09/14 05:12:17 - mmengine - INFO - Epoch(train) [107][250/293] lr: 5.000000e-04 eta: 3:39:13 time: 0.518197 data_time: 0.073908 memory: 5387 loss_kpt: 0.000624 acc_pose: 0.817585 loss: 0.000624 2022/09/14 05:12:39 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 05:12:39 - mmengine - INFO - Saving checkpoint at 107 epochs 2022/09/14 05:13:09 - mmengine - INFO - Epoch(train) [108][50/293] lr: 5.000000e-04 eta: 3:38:19 time: 0.520224 data_time: 0.093123 memory: 5387 loss_kpt: 0.000637 acc_pose: 0.794219 loss: 0.000637 2022/09/14 05:13:34 - mmengine - INFO - Epoch(train) [108][100/293] lr: 5.000000e-04 eta: 3:38:01 time: 0.510843 data_time: 0.076058 memory: 5387 loss_kpt: 0.000632 acc_pose: 0.829550 loss: 0.000632 2022/09/14 05:14:00 - mmengine - INFO - Epoch(train) [108][150/293] lr: 5.000000e-04 eta: 3:37:42 time: 0.505853 data_time: 0.078695 memory: 5387 loss_kpt: 0.000627 acc_pose: 0.842788 loss: 0.000627 2022/09/14 05:14:25 - mmengine - INFO - Epoch(train) [108][200/293] lr: 5.000000e-04 eta: 3:37:24 time: 0.512203 data_time: 0.082574 memory: 5387 loss_kpt: 0.000627 acc_pose: 0.779408 loss: 0.000627 2022/09/14 05:14:51 - mmengine - INFO - Epoch(train) [108][250/293] lr: 5.000000e-04 eta: 3:37:06 time: 0.509670 data_time: 0.074845 memory: 5387 loss_kpt: 0.000620 acc_pose: 0.794660 loss: 0.000620 2022/09/14 05:15:12 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 05:15:12 - mmengine - INFO - Saving checkpoint at 108 epochs 2022/09/14 05:15:43 - mmengine - INFO - Epoch(train) [109][50/293] lr: 5.000000e-04 eta: 3:36:13 time: 0.536442 data_time: 0.095516 memory: 5387 loss_kpt: 0.000612 acc_pose: 0.829840 loss: 0.000612 2022/09/14 05:16:09 - mmengine - INFO - Epoch(train) [109][100/293] lr: 5.000000e-04 eta: 3:35:55 time: 0.513672 data_time: 0.080894 memory: 5387 loss_kpt: 0.000613 acc_pose: 0.820063 loss: 0.000613 2022/09/14 05:16:35 - mmengine - INFO - Epoch(train) [109][150/293] lr: 5.000000e-04 eta: 3:35:37 time: 0.511225 data_time: 0.077109 memory: 5387 loss_kpt: 0.000633 acc_pose: 0.782507 loss: 0.000633 2022/09/14 05:17:00 - mmengine - INFO - Epoch(train) [109][200/293] lr: 5.000000e-04 eta: 3:35:18 time: 0.499742 data_time: 0.075396 memory: 5387 loss_kpt: 0.000627 acc_pose: 0.830319 loss: 0.000627 2022/09/14 05:17:25 - mmengine - INFO - Epoch(train) [109][250/293] lr: 5.000000e-04 eta: 3:35:00 time: 0.512867 data_time: 0.081401 memory: 5387 loss_kpt: 0.000621 acc_pose: 0.830014 loss: 0.000621 2022/09/14 05:17:47 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 05:17:47 - mmengine - INFO - Saving checkpoint at 109 epochs 2022/09/14 05:18:17 - mmengine - INFO - Epoch(train) [110][50/293] lr: 5.000000e-04 eta: 3:34:06 time: 0.516443 data_time: 0.081029 memory: 5387 loss_kpt: 0.000620 acc_pose: 0.805523 loss: 0.000620 2022/09/14 05:18:24 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 05:18:43 - mmengine - INFO - Epoch(train) [110][100/293] lr: 5.000000e-04 eta: 3:33:47 time: 0.503158 data_time: 0.079161 memory: 5387 loss_kpt: 0.000614 acc_pose: 0.830629 loss: 0.000614 2022/09/14 05:19:08 - mmengine - INFO - Epoch(train) [110][150/293] lr: 5.000000e-04 eta: 3:33:29 time: 0.512655 data_time: 0.076697 memory: 5387 loss_kpt: 0.000637 acc_pose: 0.828462 loss: 0.000637 2022/09/14 05:19:33 - mmengine - INFO - Epoch(train) [110][200/293] lr: 5.000000e-04 eta: 3:33:10 time: 0.504195 data_time: 0.075517 memory: 5387 loss_kpt: 0.000612 acc_pose: 0.832918 loss: 0.000612 2022/09/14 05:19:58 - mmengine - INFO - Epoch(train) [110][250/293] lr: 5.000000e-04 eta: 3:32:52 time: 0.499949 data_time: 0.072817 memory: 5387 loss_kpt: 0.000627 acc_pose: 0.822922 loss: 0.000627 2022/09/14 05:20:20 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 05:20:20 - mmengine - INFO - Saving checkpoint at 110 epochs 2022/09/14 05:20:31 - mmengine - INFO - Epoch(val) [110][50/407] eta: 0:00:43 time: 0.122228 data_time: 0.014688 memory: 5387 2022/09/14 05:20:37 - mmengine - INFO - Epoch(val) [110][100/407] eta: 0:00:37 time: 0.120871 data_time: 0.013544 memory: 920 2022/09/14 05:20:42 - mmengine - INFO - Epoch(val) [110][150/407] eta: 0:00:29 time: 0.114997 data_time: 0.010068 memory: 920 2022/09/14 05:20:48 - mmengine - INFO - Epoch(val) [110][200/407] eta: 0:00:24 time: 0.117496 data_time: 0.012072 memory: 920 2022/09/14 05:20:54 - mmengine - INFO - Epoch(val) [110][250/407] eta: 0:00:18 time: 0.116059 data_time: 0.009277 memory: 920 2022/09/14 05:21:00 - mmengine - INFO - Epoch(val) [110][300/407] eta: 0:00:12 time: 0.116098 data_time: 0.009209 memory: 920 2022/09/14 05:21:06 - mmengine - INFO - Epoch(val) [110][350/407] eta: 0:00:06 time: 0.114171 data_time: 0.009234 memory: 920 2022/09/14 05:21:11 - mmengine - INFO - Epoch(val) [110][400/407] eta: 0:00:00 time: 0.112481 data_time: 0.008287 memory: 920 2022/09/14 05:21:47 - mmengine - INFO - Evaluating CocoMetric... 2022/09/14 05:22:01 - mmengine - INFO - Epoch(val) [110][407/407] coco/AP: 0.727613 coco/AP .5: 0.896737 coco/AP .75: 0.800539 coco/AP (M): 0.692454 coco/AP (L): 0.795411 coco/AR: 0.783737 coco/AR .5: 0.937972 coco/AR .75: 0.848394 coco/AR (M): 0.741546 coco/AR (L): 0.844593 2022/09/14 05:22:02 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220914/hrnet_fp16/best_coco/AP_epoch_100.pth is removed 2022/09/14 05:22:06 - mmengine - INFO - The best checkpoint with 0.7276 coco/AP at 110 epoch is saved to best_coco/AP_epoch_110.pth. 2022/09/14 05:22:31 - mmengine - INFO - Epoch(train) [111][50/293] lr: 5.000000e-04 eta: 3:31:58 time: 0.515621 data_time: 0.083030 memory: 5387 loss_kpt: 0.000621 acc_pose: 0.840812 loss: 0.000621 2022/09/14 05:22:57 - mmengine - INFO - Epoch(train) [111][100/293] lr: 5.000000e-04 eta: 3:31:40 time: 0.513735 data_time: 0.075497 memory: 5387 loss_kpt: 0.000614 acc_pose: 0.865018 loss: 0.000614 2022/09/14 05:23:23 - mmengine - INFO - Epoch(train) [111][150/293] lr: 5.000000e-04 eta: 3:31:21 time: 0.510627 data_time: 0.076875 memory: 5387 loss_kpt: 0.000611 acc_pose: 0.867512 loss: 0.000611 2022/09/14 05:23:48 - mmengine - INFO - Epoch(train) [111][200/293] lr: 5.000000e-04 eta: 3:31:03 time: 0.509972 data_time: 0.077183 memory: 5387 loss_kpt: 0.000630 acc_pose: 0.815605 loss: 0.000630 2022/09/14 05:24:14 - mmengine - INFO - Epoch(train) [111][250/293] lr: 5.000000e-04 eta: 3:30:44 time: 0.509998 data_time: 0.076745 memory: 5387 loss_kpt: 0.000620 acc_pose: 0.843090 loss: 0.000620 2022/09/14 05:24:36 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 05:24:36 - mmengine - INFO - Saving checkpoint at 111 epochs 2022/09/14 05:25:06 - mmengine - INFO - Epoch(train) [112][50/293] lr: 5.000000e-04 eta: 3:29:51 time: 0.526362 data_time: 0.092470 memory: 5387 loss_kpt: 0.000613 acc_pose: 0.806504 loss: 0.000613 2022/09/14 05:25:32 - mmengine - INFO - Epoch(train) [112][100/293] lr: 5.000000e-04 eta: 3:29:33 time: 0.510227 data_time: 0.080993 memory: 5387 loss_kpt: 0.000618 acc_pose: 0.817908 loss: 0.000618 2022/09/14 05:25:58 - mmengine - INFO - Epoch(train) [112][150/293] lr: 5.000000e-04 eta: 3:29:15 time: 0.514371 data_time: 0.074822 memory: 5387 loss_kpt: 0.000628 acc_pose: 0.857683 loss: 0.000628 2022/09/14 05:26:23 - mmengine - INFO - Epoch(train) [112][200/293] lr: 5.000000e-04 eta: 3:28:56 time: 0.500960 data_time: 0.079334 memory: 5387 loss_kpt: 0.000628 acc_pose: 0.825062 loss: 0.000628 2022/09/14 05:26:48 - mmengine - INFO - Epoch(train) [112][250/293] lr: 5.000000e-04 eta: 3:28:37 time: 0.508977 data_time: 0.077907 memory: 5387 loss_kpt: 0.000622 acc_pose: 0.784272 loss: 0.000622 2022/09/14 05:27:09 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 05:27:09 - mmengine - INFO - Saving checkpoint at 112 epochs 2022/09/14 05:27:40 - mmengine - INFO - Epoch(train) [113][50/293] lr: 5.000000e-04 eta: 3:27:44 time: 0.520808 data_time: 0.084786 memory: 5387 loss_kpt: 0.000632 acc_pose: 0.833970 loss: 0.000632 2022/09/14 05:28:05 - mmengine - INFO - Epoch(train) [113][100/293] lr: 5.000000e-04 eta: 3:27:26 time: 0.516182 data_time: 0.082596 memory: 5387 loss_kpt: 0.000612 acc_pose: 0.844431 loss: 0.000612 2022/09/14 05:28:31 - mmengine - INFO - Epoch(train) [113][150/293] lr: 5.000000e-04 eta: 3:27:07 time: 0.505492 data_time: 0.077468 memory: 5387 loss_kpt: 0.000615 acc_pose: 0.843989 loss: 0.000615 2022/09/14 05:28:48 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 05:28:56 - mmengine - INFO - Epoch(train) [113][200/293] lr: 5.000000e-04 eta: 3:26:49 time: 0.506266 data_time: 0.078023 memory: 5387 loss_kpt: 0.000633 acc_pose: 0.816770 loss: 0.000633 2022/09/14 05:29:21 - mmengine - INFO - Epoch(train) [113][250/293] lr: 5.000000e-04 eta: 3:26:30 time: 0.505369 data_time: 0.073864 memory: 5387 loss_kpt: 0.000621 acc_pose: 0.796287 loss: 0.000621 2022/09/14 05:29:43 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 05:29:43 - mmengine - INFO - Saving checkpoint at 113 epochs 2022/09/14 05:30:13 - mmengine - INFO - Epoch(train) [114][50/293] lr: 5.000000e-04 eta: 3:25:37 time: 0.521146 data_time: 0.083271 memory: 5387 loss_kpt: 0.000623 acc_pose: 0.813666 loss: 0.000623 2022/09/14 05:30:40 - mmengine - INFO - Epoch(train) [114][100/293] lr: 5.000000e-04 eta: 3:25:19 time: 0.523949 data_time: 0.080552 memory: 5387 loss_kpt: 0.000623 acc_pose: 0.786523 loss: 0.000623 2022/09/14 05:31:05 - mmengine - INFO - Epoch(train) [114][150/293] lr: 5.000000e-04 eta: 3:25:01 time: 0.508786 data_time: 0.077858 memory: 5387 loss_kpt: 0.000621 acc_pose: 0.848427 loss: 0.000621 2022/09/14 05:31:31 - mmengine - INFO - Epoch(train) [114][200/293] lr: 5.000000e-04 eta: 3:24:42 time: 0.510575 data_time: 0.077118 memory: 5387 loss_kpt: 0.000618 acc_pose: 0.840655 loss: 0.000618 2022/09/14 05:31:56 - mmengine - INFO - Epoch(train) [114][250/293] lr: 5.000000e-04 eta: 3:24:23 time: 0.511173 data_time: 0.081588 memory: 5387 loss_kpt: 0.000610 acc_pose: 0.788674 loss: 0.000610 2022/09/14 05:32:18 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 05:32:18 - mmengine - INFO - Saving checkpoint at 114 epochs 2022/09/14 05:32:48 - mmengine - INFO - Epoch(train) [115][50/293] lr: 5.000000e-04 eta: 3:23:31 time: 0.519271 data_time: 0.087875 memory: 5387 loss_kpt: 0.000621 acc_pose: 0.826351 loss: 0.000621 2022/09/14 05:33:14 - mmengine - INFO - Epoch(train) [115][100/293] lr: 5.000000e-04 eta: 3:23:12 time: 0.508874 data_time: 0.083025 memory: 5387 loss_kpt: 0.000619 acc_pose: 0.823442 loss: 0.000619 2022/09/14 05:33:39 - mmengine - INFO - Epoch(train) [115][150/293] lr: 5.000000e-04 eta: 3:22:53 time: 0.507981 data_time: 0.077268 memory: 5387 loss_kpt: 0.000617 acc_pose: 0.844691 loss: 0.000617 2022/09/14 05:34:04 - mmengine - INFO - Epoch(train) [115][200/293] lr: 5.000000e-04 eta: 3:22:34 time: 0.501342 data_time: 0.076641 memory: 5387 loss_kpt: 0.000621 acc_pose: 0.835696 loss: 0.000621 2022/09/14 05:34:30 - mmengine - INFO - Epoch(train) [115][250/293] lr: 5.000000e-04 eta: 3:22:16 time: 0.515063 data_time: 0.081582 memory: 5387 loss_kpt: 0.000617 acc_pose: 0.810726 loss: 0.000617 2022/09/14 05:34:52 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 05:34:52 - mmengine - INFO - Saving checkpoint at 115 epochs 2022/09/14 05:35:22 - mmengine - INFO - Epoch(train) [116][50/293] lr: 5.000000e-04 eta: 3:21:23 time: 0.518506 data_time: 0.088199 memory: 5387 loss_kpt: 0.000632 acc_pose: 0.797147 loss: 0.000632 2022/09/14 05:35:47 - mmengine - INFO - Epoch(train) [116][100/293] lr: 5.000000e-04 eta: 3:21:05 time: 0.509585 data_time: 0.079514 memory: 5387 loss_kpt: 0.000608 acc_pose: 0.812170 loss: 0.000608 2022/09/14 05:36:13 - mmengine - INFO - Epoch(train) [116][150/293] lr: 5.000000e-04 eta: 3:20:46 time: 0.511333 data_time: 0.076971 memory: 5387 loss_kpt: 0.000620 acc_pose: 0.825642 loss: 0.000620 2022/09/14 05:36:39 - mmengine - INFO - Epoch(train) [116][200/293] lr: 5.000000e-04 eta: 3:20:28 time: 0.520037 data_time: 0.083800 memory: 5387 loss_kpt: 0.000624 acc_pose: 0.856678 loss: 0.000624 2022/09/14 05:37:04 - mmengine - INFO - Epoch(train) [116][250/293] lr: 5.000000e-04 eta: 3:20:09 time: 0.504233 data_time: 0.076368 memory: 5387 loss_kpt: 0.000614 acc_pose: 0.847650 loss: 0.000614 2022/09/14 05:37:26 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 05:37:26 - mmengine - INFO - Saving checkpoint at 116 epochs 2022/09/14 05:37:37 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 05:37:56 - mmengine - INFO - Epoch(train) [117][50/293] lr: 5.000000e-04 eta: 3:19:17 time: 0.519890 data_time: 0.083766 memory: 5387 loss_kpt: 0.000620 acc_pose: 0.814259 loss: 0.000620 2022/09/14 05:38:22 - mmengine - INFO - Epoch(train) [117][100/293] lr: 5.000000e-04 eta: 3:18:58 time: 0.502604 data_time: 0.078692 memory: 5387 loss_kpt: 0.000614 acc_pose: 0.818199 loss: 0.000614 2022/09/14 05:38:47 - mmengine - INFO - Epoch(train) [117][150/293] lr: 5.000000e-04 eta: 3:18:39 time: 0.510020 data_time: 0.076561 memory: 5387 loss_kpt: 0.000620 acc_pose: 0.833772 loss: 0.000620 2022/09/14 05:39:13 - mmengine - INFO - Epoch(train) [117][200/293] lr: 5.000000e-04 eta: 3:18:20 time: 0.516311 data_time: 0.073436 memory: 5387 loss_kpt: 0.000608 acc_pose: 0.806042 loss: 0.000608 2022/09/14 05:39:38 - mmengine - INFO - Epoch(train) [117][250/293] lr: 5.000000e-04 eta: 3:18:01 time: 0.507099 data_time: 0.089099 memory: 5387 loss_kpt: 0.000620 acc_pose: 0.813997 loss: 0.000620 2022/09/14 05:40:00 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 05:40:00 - mmengine - INFO - Saving checkpoint at 117 epochs 2022/09/14 05:40:30 - mmengine - INFO - Epoch(train) [118][50/293] lr: 5.000000e-04 eta: 3:17:09 time: 0.512212 data_time: 0.086241 memory: 5387 loss_kpt: 0.000618 acc_pose: 0.824312 loss: 0.000618 2022/09/14 05:40:56 - mmengine - INFO - Epoch(train) [118][100/293] lr: 5.000000e-04 eta: 3:16:50 time: 0.507254 data_time: 0.079068 memory: 5387 loss_kpt: 0.000620 acc_pose: 0.810596 loss: 0.000620 2022/09/14 05:41:22 - mmengine - INFO - Epoch(train) [118][150/293] lr: 5.000000e-04 eta: 3:16:32 time: 0.517576 data_time: 0.081870 memory: 5387 loss_kpt: 0.000603 acc_pose: 0.835754 loss: 0.000603 2022/09/14 05:41:47 - mmengine - INFO - Epoch(train) [118][200/293] lr: 5.000000e-04 eta: 3:16:13 time: 0.507655 data_time: 0.077509 memory: 5387 loss_kpt: 0.000620 acc_pose: 0.870512 loss: 0.000620 2022/09/14 05:42:12 - mmengine - INFO - Epoch(train) [118][250/293] lr: 5.000000e-04 eta: 3:15:54 time: 0.500715 data_time: 0.072646 memory: 5387 loss_kpt: 0.000634 acc_pose: 0.836503 loss: 0.000634 2022/09/14 05:42:33 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 05:42:33 - mmengine - INFO - Saving checkpoint at 118 epochs 2022/09/14 05:43:04 - mmengine - INFO - Epoch(train) [119][50/293] lr: 5.000000e-04 eta: 3:15:02 time: 0.517155 data_time: 0.086247 memory: 5387 loss_kpt: 0.000621 acc_pose: 0.819189 loss: 0.000621 2022/09/14 05:43:30 - mmengine - INFO - Epoch(train) [119][100/293] lr: 5.000000e-04 eta: 3:14:43 time: 0.513762 data_time: 0.083218 memory: 5387 loss_kpt: 0.000637 acc_pose: 0.815624 loss: 0.000637 2022/09/14 05:43:55 - mmengine - INFO - Epoch(train) [119][150/293] lr: 5.000000e-04 eta: 3:14:24 time: 0.500531 data_time: 0.074797 memory: 5387 loss_kpt: 0.000617 acc_pose: 0.824703 loss: 0.000617 2022/09/14 05:44:20 - mmengine - INFO - Epoch(train) [119][200/293] lr: 5.000000e-04 eta: 3:14:05 time: 0.502267 data_time: 0.081406 memory: 5387 loss_kpt: 0.000639 acc_pose: 0.834011 loss: 0.000639 2022/09/14 05:44:45 - mmengine - INFO - Epoch(train) [119][250/293] lr: 5.000000e-04 eta: 3:13:46 time: 0.507570 data_time: 0.076194 memory: 5387 loss_kpt: 0.000610 acc_pose: 0.828911 loss: 0.000610 2022/09/14 05:45:07 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 05:45:07 - mmengine - INFO - Saving checkpoint at 119 epochs 2022/09/14 05:45:36 - mmengine - INFO - Epoch(train) [120][50/293] lr: 5.000000e-04 eta: 3:12:54 time: 0.510674 data_time: 0.080875 memory: 5387 loss_kpt: 0.000624 acc_pose: 0.825748 loss: 0.000624 2022/09/14 05:46:01 - mmengine - INFO - Epoch(train) [120][100/293] lr: 5.000000e-04 eta: 3:12:35 time: 0.498361 data_time: 0.077212 memory: 5387 loss_kpt: 0.000623 acc_pose: 0.823299 loss: 0.000623 2022/09/14 05:46:18 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 05:46:27 - mmengine - INFO - Epoch(train) [120][150/293] lr: 5.000000e-04 eta: 3:12:16 time: 0.515737 data_time: 0.082180 memory: 5387 loss_kpt: 0.000617 acc_pose: 0.792421 loss: 0.000617 2022/09/14 05:46:52 - mmengine - INFO - Epoch(train) [120][200/293] lr: 5.000000e-04 eta: 3:11:57 time: 0.498894 data_time: 0.086348 memory: 5387 loss_kpt: 0.000617 acc_pose: 0.807815 loss: 0.000617 2022/09/14 05:47:17 - mmengine - INFO - Epoch(train) [120][250/293] lr: 5.000000e-04 eta: 3:11:37 time: 0.498528 data_time: 0.073508 memory: 5387 loss_kpt: 0.000641 acc_pose: 0.827812 loss: 0.000641 2022/09/14 05:47:39 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 05:47:39 - mmengine - INFO - Saving checkpoint at 120 epochs 2022/09/14 05:47:50 - mmengine - INFO - Epoch(val) [120][50/407] eta: 0:00:44 time: 0.125850 data_time: 0.018257 memory: 5387 2022/09/14 05:47:56 - mmengine - INFO - Epoch(val) [120][100/407] eta: 0:00:35 time: 0.116714 data_time: 0.010206 memory: 920 2022/09/14 05:48:02 - mmengine - INFO - Epoch(val) [120][150/407] eta: 0:00:30 time: 0.119494 data_time: 0.012711 memory: 920 2022/09/14 05:48:07 - mmengine - INFO - Epoch(val) [120][200/407] eta: 0:00:23 time: 0.115558 data_time: 0.009054 memory: 920 2022/09/14 05:48:13 - mmengine - INFO - Epoch(val) [120][250/407] eta: 0:00:17 time: 0.114015 data_time: 0.008695 memory: 920 2022/09/14 05:48:19 - mmengine - INFO - Epoch(val) [120][300/407] eta: 0:00:12 time: 0.119555 data_time: 0.013208 memory: 920 2022/09/14 05:48:25 - mmengine - INFO - Epoch(val) [120][350/407] eta: 0:00:06 time: 0.122114 data_time: 0.010027 memory: 920 2022/09/14 05:48:31 - mmengine - INFO - Epoch(val) [120][400/407] eta: 0:00:00 time: 0.111953 data_time: 0.008577 memory: 920 2022/09/14 05:49:08 - mmengine - INFO - Evaluating CocoMetric... 2022/09/14 05:49:22 - mmengine - INFO - Epoch(val) [120][407/407] coco/AP: 0.729803 coco/AP .5: 0.895719 coco/AP .75: 0.805885 coco/AP (M): 0.691386 coco/AP (L): 0.798834 coco/AR: 0.784241 coco/AR .5: 0.932620 coco/AR .75: 0.853117 coco/AR (M): 0.739634 coco/AR (L): 0.848421 2022/09/14 05:49:22 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220914/hrnet_fp16/best_coco/AP_epoch_110.pth is removed 2022/09/14 05:49:25 - mmengine - INFO - The best checkpoint with 0.7298 coco/AP at 120 epoch is saved to best_coco/AP_epoch_120.pth. 2022/09/14 05:49:51 - mmengine - INFO - Epoch(train) [121][50/293] lr: 5.000000e-04 eta: 3:10:46 time: 0.517315 data_time: 0.085411 memory: 5387 loss_kpt: 0.000614 acc_pose: 0.810287 loss: 0.000614 2022/09/14 05:50:16 - mmengine - INFO - Epoch(train) [121][100/293] lr: 5.000000e-04 eta: 3:10:27 time: 0.507084 data_time: 0.076082 memory: 5387 loss_kpt: 0.000618 acc_pose: 0.819638 loss: 0.000618 2022/09/14 05:50:42 - mmengine - INFO - Epoch(train) [121][150/293] lr: 5.000000e-04 eta: 3:10:08 time: 0.510540 data_time: 0.078383 memory: 5387 loss_kpt: 0.000615 acc_pose: 0.859760 loss: 0.000615 2022/09/14 05:51:08 - mmengine - INFO - Epoch(train) [121][200/293] lr: 5.000000e-04 eta: 3:09:49 time: 0.519554 data_time: 0.082529 memory: 5387 loss_kpt: 0.000610 acc_pose: 0.886564 loss: 0.000610 2022/09/14 05:51:33 - mmengine - INFO - Epoch(train) [121][250/293] lr: 5.000000e-04 eta: 3:09:30 time: 0.504597 data_time: 0.071397 memory: 5387 loss_kpt: 0.000614 acc_pose: 0.859625 loss: 0.000614 2022/09/14 05:51:54 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 05:51:54 - mmengine - INFO - Saving checkpoint at 121 epochs 2022/09/14 05:52:25 - mmengine - INFO - Epoch(train) [122][50/293] lr: 5.000000e-04 eta: 3:08:39 time: 0.523947 data_time: 0.088063 memory: 5387 loss_kpt: 0.000615 acc_pose: 0.915563 loss: 0.000615 2022/09/14 05:52:50 - mmengine - INFO - Epoch(train) [122][100/293] lr: 5.000000e-04 eta: 3:08:20 time: 0.507649 data_time: 0.079290 memory: 5387 loss_kpt: 0.000623 acc_pose: 0.832710 loss: 0.000623 2022/09/14 05:53:15 - mmengine - INFO - Epoch(train) [122][150/293] lr: 5.000000e-04 eta: 3:08:01 time: 0.508875 data_time: 0.075005 memory: 5387 loss_kpt: 0.000626 acc_pose: 0.849734 loss: 0.000626 2022/09/14 05:53:40 - mmengine - INFO - Epoch(train) [122][200/293] lr: 5.000000e-04 eta: 3:07:41 time: 0.499136 data_time: 0.074558 memory: 5387 loss_kpt: 0.000615 acc_pose: 0.821320 loss: 0.000615 2022/09/14 05:54:06 - mmengine - INFO - Epoch(train) [122][250/293] lr: 5.000000e-04 eta: 3:07:23 time: 0.519073 data_time: 0.077036 memory: 5387 loss_kpt: 0.000618 acc_pose: 0.803800 loss: 0.000618 2022/09/14 05:54:28 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 05:54:28 - mmengine - INFO - Saving checkpoint at 122 epochs 2022/09/14 05:54:58 - mmengine - INFO - Epoch(train) [123][50/293] lr: 5.000000e-04 eta: 3:06:31 time: 0.512880 data_time: 0.089021 memory: 5387 loss_kpt: 0.000610 acc_pose: 0.791858 loss: 0.000610 2022/09/14 05:55:22 - mmengine - INFO - Epoch(train) [123][100/293] lr: 5.000000e-04 eta: 3:06:12 time: 0.496481 data_time: 0.074233 memory: 5387 loss_kpt: 0.000621 acc_pose: 0.852261 loss: 0.000621 2022/09/14 05:55:48 - mmengine - INFO - Epoch(train) [123][150/293] lr: 5.000000e-04 eta: 3:05:53 time: 0.501966 data_time: 0.078885 memory: 5387 loss_kpt: 0.000617 acc_pose: 0.847754 loss: 0.000617 2022/09/14 05:56:13 - mmengine - INFO - Epoch(train) [123][200/293] lr: 5.000000e-04 eta: 3:05:33 time: 0.507831 data_time: 0.076578 memory: 5387 loss_kpt: 0.000617 acc_pose: 0.804080 loss: 0.000617 2022/09/14 05:56:38 - mmengine - INFO - Epoch(train) [123][250/293] lr: 5.000000e-04 eta: 3:05:14 time: 0.509687 data_time: 0.076421 memory: 5387 loss_kpt: 0.000624 acc_pose: 0.801231 loss: 0.000624 2022/09/14 05:56:41 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 05:57:00 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 05:57:00 - mmengine - INFO - Saving checkpoint at 123 epochs 2022/09/14 05:57:30 - mmengine - INFO - Epoch(train) [124][50/293] lr: 5.000000e-04 eta: 3:04:23 time: 0.513895 data_time: 0.088151 memory: 5387 loss_kpt: 0.000614 acc_pose: 0.834219 loss: 0.000614 2022/09/14 05:57:55 - mmengine - INFO - Epoch(train) [124][100/293] lr: 5.000000e-04 eta: 3:04:04 time: 0.508901 data_time: 0.073133 memory: 5387 loss_kpt: 0.000622 acc_pose: 0.836251 loss: 0.000622 2022/09/14 05:58:20 - mmengine - INFO - Epoch(train) [124][150/293] lr: 5.000000e-04 eta: 3:03:45 time: 0.503570 data_time: 0.080997 memory: 5387 loss_kpt: 0.000612 acc_pose: 0.827426 loss: 0.000612 2022/09/14 05:58:46 - mmengine - INFO - Epoch(train) [124][200/293] lr: 5.000000e-04 eta: 3:03:26 time: 0.506142 data_time: 0.081086 memory: 5387 loss_kpt: 0.000619 acc_pose: 0.827845 loss: 0.000619 2022/09/14 05:59:11 - mmengine - INFO - Epoch(train) [124][250/293] lr: 5.000000e-04 eta: 3:03:06 time: 0.508805 data_time: 0.078768 memory: 5387 loss_kpt: 0.000615 acc_pose: 0.852927 loss: 0.000615 2022/09/14 05:59:33 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 05:59:33 - mmengine - INFO - Saving checkpoint at 124 epochs 2022/09/14 06:00:06 - mmengine - INFO - Epoch(train) [125][50/293] lr: 5.000000e-04 eta: 3:02:17 time: 0.548734 data_time: 0.088753 memory: 5387 loss_kpt: 0.000629 acc_pose: 0.773640 loss: 0.000629 2022/09/14 06:00:31 - mmengine - INFO - Epoch(train) [125][100/293] lr: 5.000000e-04 eta: 3:01:58 time: 0.503370 data_time: 0.084476 memory: 5387 loss_kpt: 0.000626 acc_pose: 0.874557 loss: 0.000626 2022/09/14 06:00:56 - mmengine - INFO - Epoch(train) [125][150/293] lr: 5.000000e-04 eta: 3:01:38 time: 0.510973 data_time: 0.083805 memory: 5387 loss_kpt: 0.000615 acc_pose: 0.791213 loss: 0.000615 2022/09/14 06:01:22 - mmengine - INFO - Epoch(train) [125][200/293] lr: 5.000000e-04 eta: 3:01:19 time: 0.512947 data_time: 0.086624 memory: 5387 loss_kpt: 0.000624 acc_pose: 0.883218 loss: 0.000624 2022/09/14 06:01:48 - mmengine - INFO - Epoch(train) [125][250/293] lr: 5.000000e-04 eta: 3:01:01 time: 0.531930 data_time: 0.082623 memory: 5387 loss_kpt: 0.000623 acc_pose: 0.823551 loss: 0.000623 2022/09/14 06:02:17 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 06:02:17 - mmengine - INFO - Saving checkpoint at 125 epochs 2022/09/14 06:02:47 - mmengine - INFO - Epoch(train) [126][50/293] lr: 5.000000e-04 eta: 3:00:10 time: 0.509863 data_time: 0.089071 memory: 5387 loss_kpt: 0.000619 acc_pose: 0.826041 loss: 0.000619 2022/09/14 06:03:12 - mmengine - INFO - Epoch(train) [126][100/293] lr: 5.000000e-04 eta: 2:59:51 time: 0.506501 data_time: 0.078484 memory: 5387 loss_kpt: 0.000619 acc_pose: 0.818039 loss: 0.000619 2022/09/14 06:03:38 - mmengine - INFO - Epoch(train) [126][150/293] lr: 5.000000e-04 eta: 2:59:32 time: 0.523045 data_time: 0.081577 memory: 5387 loss_kpt: 0.000601 acc_pose: 0.840685 loss: 0.000601 2022/09/14 06:04:03 - mmengine - INFO - Epoch(train) [126][200/293] lr: 5.000000e-04 eta: 2:59:13 time: 0.502773 data_time: 0.079432 memory: 5387 loss_kpt: 0.000609 acc_pose: 0.830790 loss: 0.000609 2022/09/14 06:04:28 - mmengine - INFO - Epoch(train) [126][250/293] lr: 5.000000e-04 eta: 2:58:53 time: 0.503397 data_time: 0.075624 memory: 5387 loss_kpt: 0.000618 acc_pose: 0.858117 loss: 0.000618 2022/09/14 06:04:50 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 06:04:50 - mmengine - INFO - Saving checkpoint at 126 epochs 2022/09/14 06:05:21 - mmengine - INFO - Epoch(train) [127][50/293] lr: 5.000000e-04 eta: 2:58:03 time: 0.525563 data_time: 0.089660 memory: 5387 loss_kpt: 0.000620 acc_pose: 0.853324 loss: 0.000620 2022/09/14 06:05:37 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 06:05:46 - mmengine - INFO - Epoch(train) [127][100/293] lr: 5.000000e-04 eta: 2:57:44 time: 0.504836 data_time: 0.073355 memory: 5387 loss_kpt: 0.000613 acc_pose: 0.851333 loss: 0.000613 2022/09/14 06:06:13 - mmengine - INFO - Epoch(train) [127][150/293] lr: 5.000000e-04 eta: 2:57:25 time: 0.531457 data_time: 0.074739 memory: 5387 loss_kpt: 0.000612 acc_pose: 0.868422 loss: 0.000612 2022/09/14 06:06:38 - mmengine - INFO - Epoch(train) [127][200/293] lr: 5.000000e-04 eta: 2:57:06 time: 0.509193 data_time: 0.081712 memory: 5387 loss_kpt: 0.000608 acc_pose: 0.800724 loss: 0.000608 2022/09/14 06:07:04 - mmengine - INFO - Epoch(train) [127][250/293] lr: 5.000000e-04 eta: 2:56:47 time: 0.518504 data_time: 0.077390 memory: 5387 loss_kpt: 0.000609 acc_pose: 0.832904 loss: 0.000609 2022/09/14 06:07:25 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 06:07:25 - mmengine - INFO - Saving checkpoint at 127 epochs 2022/09/14 06:07:55 - mmengine - INFO - Epoch(train) [128][50/293] lr: 5.000000e-04 eta: 2:55:56 time: 0.507926 data_time: 0.077728 memory: 5387 loss_kpt: 0.000610 acc_pose: 0.830822 loss: 0.000610 2022/09/14 06:08:20 - mmengine - INFO - Epoch(train) [128][100/293] lr: 5.000000e-04 eta: 2:55:37 time: 0.502870 data_time: 0.075222 memory: 5387 loss_kpt: 0.000624 acc_pose: 0.797412 loss: 0.000624 2022/09/14 06:08:45 - mmengine - INFO - Epoch(train) [128][150/293] lr: 5.000000e-04 eta: 2:55:17 time: 0.491964 data_time: 0.077353 memory: 5387 loss_kpt: 0.000625 acc_pose: 0.807930 loss: 0.000625 2022/09/14 06:09:11 - mmengine - INFO - Epoch(train) [128][200/293] lr: 5.000000e-04 eta: 2:54:58 time: 0.528538 data_time: 0.071538 memory: 5387 loss_kpt: 0.000630 acc_pose: 0.811143 loss: 0.000630 2022/09/14 06:09:36 - mmengine - INFO - Epoch(train) [128][250/293] lr: 5.000000e-04 eta: 2:54:39 time: 0.502696 data_time: 0.077068 memory: 5387 loss_kpt: 0.000616 acc_pose: 0.788039 loss: 0.000616 2022/09/14 06:09:57 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 06:09:57 - mmengine - INFO - Saving checkpoint at 128 epochs 2022/09/14 06:10:34 - mmengine - INFO - Epoch(train) [129][50/293] lr: 5.000000e-04 eta: 2:53:50 time: 0.546318 data_time: 0.093101 memory: 5387 loss_kpt: 0.000604 acc_pose: 0.776333 loss: 0.000604 2022/09/14 06:11:01 - mmengine - INFO - Epoch(train) [129][100/293] lr: 5.000000e-04 eta: 2:53:31 time: 0.536482 data_time: 0.077191 memory: 5387 loss_kpt: 0.000612 acc_pose: 0.882110 loss: 0.000612 2022/09/14 06:11:27 - mmengine - INFO - Epoch(train) [129][150/293] lr: 5.000000e-04 eta: 2:53:12 time: 0.515894 data_time: 0.072883 memory: 5387 loss_kpt: 0.000612 acc_pose: 0.842375 loss: 0.000612 2022/09/14 06:11:53 - mmengine - INFO - Epoch(train) [129][200/293] lr: 5.000000e-04 eta: 2:52:53 time: 0.513850 data_time: 0.084297 memory: 5387 loss_kpt: 0.000617 acc_pose: 0.832990 loss: 0.000617 2022/09/14 06:12:18 - mmengine - INFO - Epoch(train) [129][250/293] lr: 5.000000e-04 eta: 2:52:33 time: 0.506055 data_time: 0.077946 memory: 5387 loss_kpt: 0.000626 acc_pose: 0.826824 loss: 0.000626 2022/09/14 06:12:40 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 06:12:40 - mmengine - INFO - Saving checkpoint at 129 epochs 2022/09/14 06:13:10 - mmengine - INFO - Epoch(train) [130][50/293] lr: 5.000000e-04 eta: 2:51:44 time: 0.516358 data_time: 0.090874 memory: 5387 loss_kpt: 0.000626 acc_pose: 0.790844 loss: 0.000626 2022/09/14 06:13:36 - mmengine - INFO - Epoch(train) [130][100/293] lr: 5.000000e-04 eta: 2:51:24 time: 0.522533 data_time: 0.075828 memory: 5387 loss_kpt: 0.000627 acc_pose: 0.805737 loss: 0.000627 2022/09/14 06:14:02 - mmengine - INFO - Epoch(train) [130][150/293] lr: 5.000000e-04 eta: 2:51:05 time: 0.502737 data_time: 0.077162 memory: 5387 loss_kpt: 0.000618 acc_pose: 0.829881 loss: 0.000618 2022/09/14 06:14:29 - mmengine - INFO - Epoch(train) [130][200/293] lr: 5.000000e-04 eta: 2:50:47 time: 0.548735 data_time: 0.078731 memory: 5387 loss_kpt: 0.000622 acc_pose: 0.834074 loss: 0.000622 2022/09/14 06:14:30 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 06:14:55 - mmengine - INFO - Epoch(train) [130][250/293] lr: 5.000000e-04 eta: 2:50:27 time: 0.513735 data_time: 0.085650 memory: 5387 loss_kpt: 0.000612 acc_pose: 0.832535 loss: 0.000612 2022/09/14 06:15:17 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 06:15:17 - mmengine - INFO - Saving checkpoint at 130 epochs 2022/09/14 06:15:28 - mmengine - INFO - Epoch(val) [130][50/407] eta: 0:00:43 time: 0.123241 data_time: 0.016159 memory: 5387 2022/09/14 06:15:34 - mmengine - INFO - Epoch(val) [130][100/407] eta: 0:00:35 time: 0.116060 data_time: 0.009152 memory: 920 2022/09/14 06:15:40 - mmengine - INFO - Epoch(val) [130][150/407] eta: 0:00:29 time: 0.116587 data_time: 0.009606 memory: 920 2022/09/14 06:15:46 - mmengine - INFO - Epoch(val) [130][200/407] eta: 0:00:24 time: 0.117606 data_time: 0.009575 memory: 920 2022/09/14 06:15:51 - mmengine - INFO - Epoch(val) [130][250/407] eta: 0:00:18 time: 0.116805 data_time: 0.011059 memory: 920 2022/09/14 06:15:58 - mmengine - INFO - Epoch(val) [130][300/407] eta: 0:00:13 time: 0.123888 data_time: 0.013738 memory: 920 2022/09/14 06:16:04 - mmengine - INFO - Epoch(val) [130][350/407] eta: 0:00:06 time: 0.120583 data_time: 0.012406 memory: 920 2022/09/14 06:16:09 - mmengine - INFO - Epoch(val) [130][400/407] eta: 0:00:00 time: 0.111524 data_time: 0.007910 memory: 920 2022/09/14 06:16:46 - mmengine - INFO - Evaluating CocoMetric... 2022/09/14 06:17:00 - mmengine - INFO - Epoch(val) [130][407/407] coco/AP: 0.731132 coco/AP .5: 0.902169 coco/AP .75: 0.803004 coco/AP (M): 0.696402 coco/AP (L): 0.794993 coco/AR: 0.786839 coco/AR .5: 0.940963 coco/AR .75: 0.851543 coco/AR (M): 0.745534 coco/AR (L): 0.846451 2022/09/14 06:17:00 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220914/hrnet_fp16/best_coco/AP_epoch_120.pth is removed 2022/09/14 06:17:03 - mmengine - INFO - The best checkpoint with 0.7311 coco/AP at 130 epoch is saved to best_coco/AP_epoch_130.pth. 2022/09/14 06:17:28 - mmengine - INFO - Epoch(train) [131][50/293] lr: 5.000000e-04 eta: 2:49:38 time: 0.512512 data_time: 0.082675 memory: 5387 loss_kpt: 0.000612 acc_pose: 0.841059 loss: 0.000612 2022/09/14 06:17:54 - mmengine - INFO - Epoch(train) [131][100/293] lr: 5.000000e-04 eta: 2:49:18 time: 0.517702 data_time: 0.081978 memory: 5387 loss_kpt: 0.000623 acc_pose: 0.845111 loss: 0.000623 2022/09/14 06:18:19 - mmengine - INFO - Epoch(train) [131][150/293] lr: 5.000000e-04 eta: 2:48:59 time: 0.500935 data_time: 0.073058 memory: 5387 loss_kpt: 0.000604 acc_pose: 0.826069 loss: 0.000604 2022/09/14 06:18:44 - mmengine - INFO - Epoch(train) [131][200/293] lr: 5.000000e-04 eta: 2:48:39 time: 0.501570 data_time: 0.080424 memory: 5387 loss_kpt: 0.000614 acc_pose: 0.879765 loss: 0.000614 2022/09/14 06:19:10 - mmengine - INFO - Epoch(train) [131][250/293] lr: 5.000000e-04 eta: 2:48:19 time: 0.514153 data_time: 0.080485 memory: 5387 loss_kpt: 0.000602 acc_pose: 0.816957 loss: 0.000602 2022/09/14 06:19:31 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 06:19:31 - mmengine - INFO - Saving checkpoint at 131 epochs 2022/09/14 06:20:01 - mmengine - INFO - Epoch(train) [132][50/293] lr: 5.000000e-04 eta: 2:47:30 time: 0.514406 data_time: 0.082170 memory: 5387 loss_kpt: 0.000624 acc_pose: 0.810611 loss: 0.000624 2022/09/14 06:20:30 - mmengine - INFO - Epoch(train) [132][100/293] lr: 5.000000e-04 eta: 2:47:12 time: 0.570456 data_time: 0.076519 memory: 5387 loss_kpt: 0.000612 acc_pose: 0.825495 loss: 0.000612 2022/09/14 06:20:55 - mmengine - INFO - Epoch(train) [132][150/293] lr: 5.000000e-04 eta: 2:46:53 time: 0.500414 data_time: 0.077583 memory: 5387 loss_kpt: 0.000605 acc_pose: 0.797002 loss: 0.000605 2022/09/14 06:21:20 - mmengine - INFO - Epoch(train) [132][200/293] lr: 5.000000e-04 eta: 2:46:33 time: 0.505177 data_time: 0.082251 memory: 5387 loss_kpt: 0.000620 acc_pose: 0.792078 loss: 0.000620 2022/09/14 06:21:45 - mmengine - INFO - Epoch(train) [132][250/293] lr: 5.000000e-04 eta: 2:46:13 time: 0.503697 data_time: 0.073428 memory: 5387 loss_kpt: 0.000623 acc_pose: 0.852779 loss: 0.000623 2022/09/14 06:22:07 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 06:22:07 - mmengine - INFO - Saving checkpoint at 132 epochs 2022/09/14 06:22:59 - mmengine - INFO - Epoch(train) [133][50/293] lr: 5.000000e-04 eta: 2:45:26 time: 0.577190 data_time: 0.109894 memory: 5387 loss_kpt: 0.000602 acc_pose: 0.819977 loss: 0.000602 2022/09/14 06:23:25 - mmengine - INFO - Epoch(train) [133][100/293] lr: 5.000000e-04 eta: 2:45:07 time: 0.527096 data_time: 0.075214 memory: 5387 loss_kpt: 0.000613 acc_pose: 0.854985 loss: 0.000613 2022/09/14 06:23:51 - mmengine - INFO - Epoch(train) [133][150/293] lr: 5.000000e-04 eta: 2:44:47 time: 0.510242 data_time: 0.076001 memory: 5387 loss_kpt: 0.000620 acc_pose: 0.829997 loss: 0.000620 2022/09/14 06:24:16 - mmengine - INFO - Epoch(train) [133][200/293] lr: 5.000000e-04 eta: 2:44:27 time: 0.493231 data_time: 0.077365 memory: 5387 loss_kpt: 0.000625 acc_pose: 0.875100 loss: 0.000625 2022/09/14 06:24:42 - mmengine - INFO - Epoch(train) [133][250/293] lr: 5.000000e-04 eta: 2:44:08 time: 0.522375 data_time: 0.077359 memory: 5387 loss_kpt: 0.000587 acc_pose: 0.863702 loss: 0.000587 2022/09/14 06:25:04 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 06:25:04 - mmengine - INFO - Saving checkpoint at 133 epochs 2022/09/14 06:25:24 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 06:25:34 - mmengine - INFO - Epoch(train) [134][50/293] lr: 5.000000e-04 eta: 2:43:19 time: 0.511705 data_time: 0.082538 memory: 5387 loss_kpt: 0.000605 acc_pose: 0.865837 loss: 0.000605 2022/09/14 06:25:59 - mmengine - INFO - Epoch(train) [134][100/293] lr: 5.000000e-04 eta: 2:42:59 time: 0.504204 data_time: 0.072882 memory: 5387 loss_kpt: 0.000616 acc_pose: 0.849160 loss: 0.000616 2022/09/14 06:26:24 - mmengine - INFO - Epoch(train) [134][150/293] lr: 5.000000e-04 eta: 2:42:39 time: 0.495371 data_time: 0.078417 memory: 5387 loss_kpt: 0.000609 acc_pose: 0.858442 loss: 0.000609 2022/09/14 06:26:49 - mmengine - INFO - Epoch(train) [134][200/293] lr: 5.000000e-04 eta: 2:42:19 time: 0.496643 data_time: 0.072340 memory: 5387 loss_kpt: 0.000624 acc_pose: 0.842227 loss: 0.000624 2022/09/14 06:27:14 - mmengine - INFO - Epoch(train) [134][250/293] lr: 5.000000e-04 eta: 2:41:59 time: 0.512558 data_time: 0.075362 memory: 5387 loss_kpt: 0.000617 acc_pose: 0.790161 loss: 0.000617 2022/09/14 06:27:36 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 06:27:36 - mmengine - INFO - Saving checkpoint at 134 epochs 2022/09/14 06:28:06 - mmengine - INFO - Epoch(train) [135][50/293] lr: 5.000000e-04 eta: 2:41:10 time: 0.516359 data_time: 0.086387 memory: 5387 loss_kpt: 0.000613 acc_pose: 0.811577 loss: 0.000613 2022/09/14 06:28:32 - mmengine - INFO - Epoch(train) [135][100/293] lr: 5.000000e-04 eta: 2:40:51 time: 0.509844 data_time: 0.082965 memory: 5387 loss_kpt: 0.000610 acc_pose: 0.848764 loss: 0.000610 2022/09/14 06:28:57 - mmengine - INFO - Epoch(train) [135][150/293] lr: 5.000000e-04 eta: 2:40:31 time: 0.497915 data_time: 0.078768 memory: 5387 loss_kpt: 0.000606 acc_pose: 0.830833 loss: 0.000606 2022/09/14 06:29:22 - mmengine - INFO - Epoch(train) [135][200/293] lr: 5.000000e-04 eta: 2:40:11 time: 0.499507 data_time: 0.073434 memory: 5387 loss_kpt: 0.000609 acc_pose: 0.823971 loss: 0.000609 2022/09/14 06:29:47 - mmengine - INFO - Epoch(train) [135][250/293] lr: 5.000000e-04 eta: 2:39:51 time: 0.500653 data_time: 0.076138 memory: 5387 loss_kpt: 0.000626 acc_pose: 0.835150 loss: 0.000626 2022/09/14 06:30:08 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 06:30:08 - mmengine - INFO - Saving checkpoint at 135 epochs 2022/09/14 06:30:38 - mmengine - INFO - Epoch(train) [136][50/293] lr: 5.000000e-04 eta: 2:39:02 time: 0.516150 data_time: 0.088387 memory: 5387 loss_kpt: 0.000606 acc_pose: 0.791056 loss: 0.000606 2022/09/14 06:31:04 - mmengine - INFO - Epoch(train) [136][100/293] lr: 5.000000e-04 eta: 2:38:42 time: 0.503879 data_time: 0.075271 memory: 5387 loss_kpt: 0.000617 acc_pose: 0.855625 loss: 0.000617 2022/09/14 06:31:29 - mmengine - INFO - Epoch(train) [136][150/293] lr: 5.000000e-04 eta: 2:38:22 time: 0.499296 data_time: 0.076300 memory: 5387 loss_kpt: 0.000605 acc_pose: 0.836551 loss: 0.000605 2022/09/14 06:31:54 - mmengine - INFO - Epoch(train) [136][200/293] lr: 5.000000e-04 eta: 2:38:02 time: 0.505019 data_time: 0.073506 memory: 5387 loss_kpt: 0.000616 acc_pose: 0.842807 loss: 0.000616 2022/09/14 06:32:18 - mmengine - INFO - Epoch(train) [136][250/293] lr: 5.000000e-04 eta: 2:37:42 time: 0.493270 data_time: 0.071150 memory: 5387 loss_kpt: 0.000607 acc_pose: 0.815376 loss: 0.000607 2022/09/14 06:32:41 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 06:32:41 - mmengine - INFO - Saving checkpoint at 136 epochs 2022/09/14 06:33:11 - mmengine - INFO - Epoch(train) [137][50/293] lr: 5.000000e-04 eta: 2:36:53 time: 0.508645 data_time: 0.087157 memory: 5387 loss_kpt: 0.000615 acc_pose: 0.855677 loss: 0.000615 2022/09/14 06:33:35 - mmengine - INFO - Epoch(train) [137][100/293] lr: 5.000000e-04 eta: 2:36:33 time: 0.494467 data_time: 0.080160 memory: 5387 loss_kpt: 0.000611 acc_pose: 0.839328 loss: 0.000611 2022/09/14 06:34:01 - mmengine - INFO - Epoch(train) [137][150/293] lr: 5.000000e-04 eta: 2:36:14 time: 0.512256 data_time: 0.073379 memory: 5387 loss_kpt: 0.000619 acc_pose: 0.865174 loss: 0.000619 2022/09/14 06:34:02 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 06:34:26 - mmengine - INFO - Epoch(train) [137][200/293] lr: 5.000000e-04 eta: 2:35:54 time: 0.507332 data_time: 0.080770 memory: 5387 loss_kpt: 0.000616 acc_pose: 0.832309 loss: 0.000616 2022/09/14 06:34:52 - mmengine - INFO - Epoch(train) [137][250/293] lr: 5.000000e-04 eta: 2:35:34 time: 0.505799 data_time: 0.075736 memory: 5387 loss_kpt: 0.000610 acc_pose: 0.847736 loss: 0.000610 2022/09/14 06:35:13 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 06:35:13 - mmengine - INFO - Saving checkpoint at 137 epochs 2022/09/14 06:35:42 - mmengine - INFO - Epoch(train) [138][50/293] lr: 5.000000e-04 eta: 2:34:45 time: 0.511940 data_time: 0.085472 memory: 5387 loss_kpt: 0.000606 acc_pose: 0.815630 loss: 0.000606 2022/09/14 06:36:08 - mmengine - INFO - Epoch(train) [138][100/293] lr: 5.000000e-04 eta: 2:34:25 time: 0.501740 data_time: 0.079542 memory: 5387 loss_kpt: 0.000601 acc_pose: 0.848298 loss: 0.000601 2022/09/14 06:36:33 - mmengine - INFO - Epoch(train) [138][150/293] lr: 5.000000e-04 eta: 2:34:05 time: 0.499817 data_time: 0.079049 memory: 5387 loss_kpt: 0.000615 acc_pose: 0.844755 loss: 0.000615 2022/09/14 06:36:58 - mmengine - INFO - Epoch(train) [138][200/293] lr: 5.000000e-04 eta: 2:33:46 time: 0.517277 data_time: 0.077071 memory: 5387 loss_kpt: 0.000610 acc_pose: 0.841822 loss: 0.000610 2022/09/14 06:37:23 - mmengine - INFO - Epoch(train) [138][250/293] lr: 5.000000e-04 eta: 2:33:26 time: 0.501452 data_time: 0.078515 memory: 5387 loss_kpt: 0.000615 acc_pose: 0.821215 loss: 0.000615 2022/09/14 06:37:45 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 06:37:45 - mmengine - INFO - Saving checkpoint at 138 epochs 2022/09/14 06:38:14 - mmengine - INFO - Epoch(train) [139][50/293] lr: 5.000000e-04 eta: 2:32:37 time: 0.502712 data_time: 0.086546 memory: 5387 loss_kpt: 0.000608 acc_pose: 0.869497 loss: 0.000608 2022/09/14 06:38:40 - mmengine - INFO - Epoch(train) [139][100/293] lr: 5.000000e-04 eta: 2:32:17 time: 0.506642 data_time: 0.079274 memory: 5387 loss_kpt: 0.000613 acc_pose: 0.837035 loss: 0.000613 2022/09/14 06:39:05 - mmengine - INFO - Epoch(train) [139][150/293] lr: 5.000000e-04 eta: 2:31:57 time: 0.507036 data_time: 0.073328 memory: 5387 loss_kpt: 0.000605 acc_pose: 0.815515 loss: 0.000605 2022/09/14 06:39:30 - mmengine - INFO - Epoch(train) [139][200/293] lr: 5.000000e-04 eta: 2:31:37 time: 0.501147 data_time: 0.083454 memory: 5387 loss_kpt: 0.000617 acc_pose: 0.839698 loss: 0.000617 2022/09/14 06:39:55 - mmengine - INFO - Epoch(train) [139][250/293] lr: 5.000000e-04 eta: 2:31:17 time: 0.499815 data_time: 0.080914 memory: 5387 loss_kpt: 0.000611 acc_pose: 0.841595 loss: 0.000611 2022/09/14 06:40:17 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 06:40:17 - mmengine - INFO - Saving checkpoint at 139 epochs 2022/09/14 06:40:47 - mmengine - INFO - Epoch(train) [140][50/293] lr: 5.000000e-04 eta: 2:30:29 time: 0.510509 data_time: 0.082028 memory: 5387 loss_kpt: 0.000610 acc_pose: 0.838143 loss: 0.000610 2022/09/14 06:41:13 - mmengine - INFO - Epoch(train) [140][100/293] lr: 5.000000e-04 eta: 2:30:09 time: 0.510331 data_time: 0.078416 memory: 5387 loss_kpt: 0.000617 acc_pose: 0.842581 loss: 0.000617 2022/09/14 06:41:38 - mmengine - INFO - Epoch(train) [140][150/293] lr: 5.000000e-04 eta: 2:29:49 time: 0.503252 data_time: 0.075074 memory: 5387 loss_kpt: 0.000609 acc_pose: 0.845174 loss: 0.000609 2022/09/14 06:42:03 - mmengine - INFO - Epoch(train) [140][200/293] lr: 5.000000e-04 eta: 2:29:29 time: 0.500734 data_time: 0.077500 memory: 5387 loss_kpt: 0.000596 acc_pose: 0.848870 loss: 0.000596 2022/09/14 06:42:28 - mmengine - INFO - Epoch(train) [140][250/293] lr: 5.000000e-04 eta: 2:29:09 time: 0.502690 data_time: 0.079111 memory: 5387 loss_kpt: 0.000609 acc_pose: 0.841208 loss: 0.000609 2022/09/14 06:42:40 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 06:42:49 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 06:42:49 - mmengine - INFO - Saving checkpoint at 140 epochs 2022/09/14 06:43:00 - mmengine - INFO - Epoch(val) [140][50/407] eta: 0:00:43 time: 0.122938 data_time: 0.017153 memory: 5387 2022/09/14 06:43:05 - mmengine - INFO - Epoch(val) [140][100/407] eta: 0:00:35 time: 0.116010 data_time: 0.009283 memory: 920 2022/09/14 06:43:11 - mmengine - INFO - Epoch(val) [140][150/407] eta: 0:00:29 time: 0.114155 data_time: 0.009492 memory: 920 2022/09/14 06:43:17 - mmengine - INFO - Epoch(val) [140][200/407] eta: 0:00:25 time: 0.120893 data_time: 0.014473 memory: 920 2022/09/14 06:43:23 - mmengine - INFO - Epoch(val) [140][250/407] eta: 0:00:18 time: 0.114848 data_time: 0.009283 memory: 920 2022/09/14 06:43:29 - mmengine - INFO - Epoch(val) [140][300/407] eta: 0:00:12 time: 0.118974 data_time: 0.012271 memory: 920 2022/09/14 06:43:35 - mmengine - INFO - Epoch(val) [140][350/407] eta: 0:00:06 time: 0.117850 data_time: 0.011363 memory: 920 2022/09/14 06:43:40 - mmengine - INFO - Epoch(val) [140][400/407] eta: 0:00:00 time: 0.111414 data_time: 0.007863 memory: 920 2022/09/14 06:44:17 - mmengine - INFO - Evaluating CocoMetric... 2022/09/14 06:44:30 - mmengine - INFO - Epoch(val) [140][407/407] coco/AP: 0.732987 coco/AP .5: 0.897714 coco/AP .75: 0.808241 coco/AP (M): 0.696338 coco/AP (L): 0.800518 coco/AR: 0.788004 coco/AR .5: 0.938130 coco/AR .75: 0.855321 coco/AR (M): 0.744359 coco/AR (L): 0.851208 2022/09/14 06:44:30 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220914/hrnet_fp16/best_coco/AP_epoch_130.pth is removed 2022/09/14 06:44:34 - mmengine - INFO - The best checkpoint with 0.7330 coco/AP at 140 epoch is saved to best_coco/AP_epoch_140.pth. 2022/09/14 06:44:59 - mmengine - INFO - Epoch(train) [141][50/293] lr: 5.000000e-04 eta: 2:28:21 time: 0.512584 data_time: 0.082403 memory: 5387 loss_kpt: 0.000612 acc_pose: 0.801572 loss: 0.000612 2022/09/14 06:45:25 - mmengine - INFO - Epoch(train) [141][100/293] lr: 5.000000e-04 eta: 2:28:01 time: 0.513643 data_time: 0.080866 memory: 5387 loss_kpt: 0.000605 acc_pose: 0.830915 loss: 0.000605 2022/09/14 06:45:50 - mmengine - INFO - Epoch(train) [141][150/293] lr: 5.000000e-04 eta: 2:27:41 time: 0.500469 data_time: 0.076934 memory: 5387 loss_kpt: 0.000604 acc_pose: 0.828277 loss: 0.000604 2022/09/14 06:46:15 - mmengine - INFO - Epoch(train) [141][200/293] lr: 5.000000e-04 eta: 2:27:21 time: 0.509041 data_time: 0.082157 memory: 5387 loss_kpt: 0.000611 acc_pose: 0.816530 loss: 0.000611 2022/09/14 06:46:40 - mmengine - INFO - Epoch(train) [141][250/293] lr: 5.000000e-04 eta: 2:27:01 time: 0.491249 data_time: 0.076650 memory: 5387 loss_kpt: 0.000617 acc_pose: 0.870336 loss: 0.000617 2022/09/14 06:47:01 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 06:47:01 - mmengine - INFO - Saving checkpoint at 141 epochs 2022/09/14 06:47:33 - mmengine - INFO - Epoch(train) [142][50/293] lr: 5.000000e-04 eta: 2:26:13 time: 0.510676 data_time: 0.080218 memory: 5387 loss_kpt: 0.000614 acc_pose: 0.874766 loss: 0.000614 2022/09/14 06:47:59 - mmengine - INFO - Epoch(train) [142][100/293] lr: 5.000000e-04 eta: 2:25:53 time: 0.511657 data_time: 0.083569 memory: 5387 loss_kpt: 0.000611 acc_pose: 0.845841 loss: 0.000611 2022/09/14 06:48:24 - mmengine - INFO - Epoch(train) [142][150/293] lr: 5.000000e-04 eta: 2:25:33 time: 0.505079 data_time: 0.070281 memory: 5387 loss_kpt: 0.000619 acc_pose: 0.801897 loss: 0.000619 2022/09/14 06:48:50 - mmengine - INFO - Epoch(train) [142][200/293] lr: 5.000000e-04 eta: 2:25:13 time: 0.516036 data_time: 0.074436 memory: 5387 loss_kpt: 0.000607 acc_pose: 0.867401 loss: 0.000607 2022/09/14 06:49:15 - mmengine - INFO - Epoch(train) [142][250/293] lr: 5.000000e-04 eta: 2:24:53 time: 0.494313 data_time: 0.077518 memory: 5387 loss_kpt: 0.000601 acc_pose: 0.805892 loss: 0.000601 2022/09/14 06:49:36 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 06:49:36 - mmengine - INFO - Saving checkpoint at 142 epochs 2022/09/14 06:50:06 - mmengine - INFO - Epoch(train) [143][50/293] lr: 5.000000e-04 eta: 2:24:05 time: 0.516382 data_time: 0.091789 memory: 5387 loss_kpt: 0.000617 acc_pose: 0.814107 loss: 0.000617 2022/09/14 06:50:32 - mmengine - INFO - Epoch(train) [143][100/293] lr: 5.000000e-04 eta: 2:23:45 time: 0.506844 data_time: 0.081420 memory: 5387 loss_kpt: 0.000615 acc_pose: 0.836300 loss: 0.000615 2022/09/14 06:50:57 - mmengine - INFO - Epoch(train) [143][150/293] lr: 5.000000e-04 eta: 2:23:25 time: 0.502993 data_time: 0.075263 memory: 5387 loss_kpt: 0.000608 acc_pose: 0.813587 loss: 0.000608 2022/09/14 06:51:21 - mmengine - INFO - Epoch(train) [143][200/293] lr: 5.000000e-04 eta: 2:23:05 time: 0.492477 data_time: 0.072350 memory: 5387 loss_kpt: 0.000593 acc_pose: 0.855402 loss: 0.000593 2022/09/14 06:51:47 - mmengine - INFO - Epoch(train) [143][250/293] lr: 5.000000e-04 eta: 2:22:45 time: 0.509681 data_time: 0.076846 memory: 5387 loss_kpt: 0.000607 acc_pose: 0.856064 loss: 0.000607 2022/09/14 06:52:09 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 06:52:09 - mmengine - INFO - Saving checkpoint at 143 epochs 2022/09/14 06:52:39 - mmengine - INFO - Epoch(train) [144][50/293] lr: 5.000000e-04 eta: 2:21:57 time: 0.514825 data_time: 0.085396 memory: 5387 loss_kpt: 0.000613 acc_pose: 0.880903 loss: 0.000613 2022/09/14 06:53:04 - mmengine - INFO - Epoch(train) [144][100/293] lr: 5.000000e-04 eta: 2:21:37 time: 0.507606 data_time: 0.072869 memory: 5387 loss_kpt: 0.000600 acc_pose: 0.842777 loss: 0.000600 2022/09/14 06:53:05 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 06:53:30 - mmengine - INFO - Epoch(train) [144][150/293] lr: 5.000000e-04 eta: 2:21:17 time: 0.507906 data_time: 0.076889 memory: 5387 loss_kpt: 0.000599 acc_pose: 0.908574 loss: 0.000599 2022/09/14 06:53:55 - mmengine - INFO - Epoch(train) [144][200/293] lr: 5.000000e-04 eta: 2:20:57 time: 0.513349 data_time: 0.078372 memory: 5387 loss_kpt: 0.000612 acc_pose: 0.838036 loss: 0.000612 2022/09/14 06:54:21 - mmengine - INFO - Epoch(train) [144][250/293] lr: 5.000000e-04 eta: 2:20:37 time: 0.506835 data_time: 0.077548 memory: 5387 loss_kpt: 0.000605 acc_pose: 0.844026 loss: 0.000605 2022/09/14 06:54:43 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 06:54:43 - mmengine - INFO - Saving checkpoint at 144 epochs 2022/09/14 06:55:13 - mmengine - INFO - Epoch(train) [145][50/293] lr: 5.000000e-04 eta: 2:19:50 time: 0.519254 data_time: 0.086942 memory: 5387 loss_kpt: 0.000613 acc_pose: 0.786214 loss: 0.000613 2022/09/14 06:55:39 - mmengine - INFO - Epoch(train) [145][100/293] lr: 5.000000e-04 eta: 2:19:30 time: 0.517142 data_time: 0.074365 memory: 5387 loss_kpt: 0.000596 acc_pose: 0.818174 loss: 0.000596 2022/09/14 06:56:04 - mmengine - INFO - Epoch(train) [145][150/293] lr: 5.000000e-04 eta: 2:19:10 time: 0.504251 data_time: 0.078605 memory: 5387 loss_kpt: 0.000613 acc_pose: 0.845744 loss: 0.000613 2022/09/14 06:56:29 - mmengine - INFO - Epoch(train) [145][200/293] lr: 5.000000e-04 eta: 2:18:50 time: 0.499974 data_time: 0.076116 memory: 5387 loss_kpt: 0.000610 acc_pose: 0.814165 loss: 0.000610 2022/09/14 06:56:55 - mmengine - INFO - Epoch(train) [145][250/293] lr: 5.000000e-04 eta: 2:18:30 time: 0.509882 data_time: 0.081891 memory: 5387 loss_kpt: 0.000609 acc_pose: 0.850082 loss: 0.000609 2022/09/14 06:57:17 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 06:57:17 - mmengine - INFO - Saving checkpoint at 145 epochs 2022/09/14 06:57:46 - mmengine - INFO - Epoch(train) [146][50/293] lr: 5.000000e-04 eta: 2:17:43 time: 0.515558 data_time: 0.082843 memory: 5387 loss_kpt: 0.000602 acc_pose: 0.803073 loss: 0.000602 2022/09/14 06:58:12 - mmengine - INFO - Epoch(train) [146][100/293] lr: 5.000000e-04 eta: 2:17:22 time: 0.501368 data_time: 0.078937 memory: 5387 loss_kpt: 0.000604 acc_pose: 0.876330 loss: 0.000604 2022/09/14 06:58:37 - mmengine - INFO - Epoch(train) [146][150/293] lr: 5.000000e-04 eta: 2:17:02 time: 0.512368 data_time: 0.076480 memory: 5387 loss_kpt: 0.000603 acc_pose: 0.814360 loss: 0.000603 2022/09/14 06:59:02 - mmengine - INFO - Epoch(train) [146][200/293] lr: 5.000000e-04 eta: 2:16:42 time: 0.500980 data_time: 0.082357 memory: 5387 loss_kpt: 0.000610 acc_pose: 0.826573 loss: 0.000610 2022/09/14 06:59:28 - mmengine - INFO - Epoch(train) [146][250/293] lr: 5.000000e-04 eta: 2:16:22 time: 0.507413 data_time: 0.077385 memory: 5387 loss_kpt: 0.000604 acc_pose: 0.799641 loss: 0.000604 2022/09/14 06:59:49 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 06:59:49 - mmengine - INFO - Saving checkpoint at 146 epochs 2022/09/14 07:00:19 - mmengine - INFO - Epoch(train) [147][50/293] lr: 5.000000e-04 eta: 2:15:35 time: 0.506181 data_time: 0.085764 memory: 5387 loss_kpt: 0.000620 acc_pose: 0.848939 loss: 0.000620 2022/09/14 07:00:45 - mmengine - INFO - Epoch(train) [147][100/293] lr: 5.000000e-04 eta: 2:15:15 time: 0.511235 data_time: 0.077459 memory: 5387 loss_kpt: 0.000598 acc_pose: 0.838592 loss: 0.000598 2022/09/14 07:01:10 - mmengine - INFO - Epoch(train) [147][150/293] lr: 5.000000e-04 eta: 2:14:54 time: 0.504761 data_time: 0.075651 memory: 5387 loss_kpt: 0.000617 acc_pose: 0.841348 loss: 0.000617 2022/09/14 07:01:35 - mmengine - INFO - Epoch(train) [147][200/293] lr: 5.000000e-04 eta: 2:14:34 time: 0.496068 data_time: 0.075561 memory: 5387 loss_kpt: 0.000610 acc_pose: 0.852623 loss: 0.000610 2022/09/14 07:01:46 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 07:02:00 - mmengine - INFO - Epoch(train) [147][250/293] lr: 5.000000e-04 eta: 2:14:14 time: 0.507952 data_time: 0.074654 memory: 5387 loss_kpt: 0.000614 acc_pose: 0.858431 loss: 0.000614 2022/09/14 07:02:22 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 07:02:22 - mmengine - INFO - Saving checkpoint at 147 epochs 2022/09/14 07:02:52 - mmengine - INFO - Epoch(train) [148][50/293] lr: 5.000000e-04 eta: 2:13:27 time: 0.524754 data_time: 0.083457 memory: 5387 loss_kpt: 0.000619 acc_pose: 0.843717 loss: 0.000619 2022/09/14 07:03:17 - mmengine - INFO - Epoch(train) [148][100/293] lr: 5.000000e-04 eta: 2:13:07 time: 0.499465 data_time: 0.074830 memory: 5387 loss_kpt: 0.000603 acc_pose: 0.884963 loss: 0.000603 2022/09/14 07:03:43 - mmengine - INFO - Epoch(train) [148][150/293] lr: 5.000000e-04 eta: 2:12:46 time: 0.502018 data_time: 0.078423 memory: 5387 loss_kpt: 0.000619 acc_pose: 0.821420 loss: 0.000619 2022/09/14 07:04:08 - mmengine - INFO - Epoch(train) [148][200/293] lr: 5.000000e-04 eta: 2:12:26 time: 0.509433 data_time: 0.071654 memory: 5387 loss_kpt: 0.000605 acc_pose: 0.812139 loss: 0.000605 2022/09/14 07:04:33 - mmengine - INFO - Epoch(train) [148][250/293] lr: 5.000000e-04 eta: 2:12:06 time: 0.500872 data_time: 0.078819 memory: 5387 loss_kpt: 0.000618 acc_pose: 0.805531 loss: 0.000618 2022/09/14 07:04:55 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 07:04:55 - mmengine - INFO - Saving checkpoint at 148 epochs 2022/09/14 07:05:25 - mmengine - INFO - Epoch(train) [149][50/293] lr: 5.000000e-04 eta: 2:11:19 time: 0.502923 data_time: 0.080938 memory: 5387 loss_kpt: 0.000603 acc_pose: 0.847943 loss: 0.000603 2022/09/14 07:05:50 - mmengine - INFO - Epoch(train) [149][100/293] lr: 5.000000e-04 eta: 2:10:59 time: 0.498894 data_time: 0.080499 memory: 5387 loss_kpt: 0.000593 acc_pose: 0.853720 loss: 0.000593 2022/09/14 07:06:15 - mmengine - INFO - Epoch(train) [149][150/293] lr: 5.000000e-04 eta: 2:10:38 time: 0.508254 data_time: 0.073668 memory: 5387 loss_kpt: 0.000608 acc_pose: 0.852938 loss: 0.000608 2022/09/14 07:06:41 - mmengine - INFO - Epoch(train) [149][200/293] lr: 5.000000e-04 eta: 2:10:18 time: 0.511340 data_time: 0.081766 memory: 5387 loss_kpt: 0.000593 acc_pose: 0.858696 loss: 0.000593 2022/09/14 07:07:06 - mmengine - INFO - Epoch(train) [149][250/293] lr: 5.000000e-04 eta: 2:09:58 time: 0.500817 data_time: 0.076337 memory: 5387 loss_kpt: 0.000600 acc_pose: 0.839730 loss: 0.000600 2022/09/14 07:07:27 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 07:07:27 - mmengine - INFO - Saving checkpoint at 149 epochs 2022/09/14 07:07:58 - mmengine - INFO - Epoch(train) [150][50/293] lr: 5.000000e-04 eta: 2:09:11 time: 0.517651 data_time: 0.081924 memory: 5387 loss_kpt: 0.000600 acc_pose: 0.824826 loss: 0.000600 2022/09/14 07:08:23 - mmengine - INFO - Epoch(train) [150][100/293] lr: 5.000000e-04 eta: 2:08:51 time: 0.501200 data_time: 0.076930 memory: 5387 loss_kpt: 0.000590 acc_pose: 0.807597 loss: 0.000590 2022/09/14 07:08:49 - mmengine - INFO - Epoch(train) [150][150/293] lr: 5.000000e-04 eta: 2:08:31 time: 0.514715 data_time: 0.079405 memory: 5387 loss_kpt: 0.000614 acc_pose: 0.858010 loss: 0.000614 2022/09/14 07:09:13 - mmengine - INFO - Epoch(train) [150][200/293] lr: 5.000000e-04 eta: 2:08:10 time: 0.493717 data_time: 0.075114 memory: 5387 loss_kpt: 0.000606 acc_pose: 0.791057 loss: 0.000606 2022/09/14 07:09:38 - mmengine - INFO - Epoch(train) [150][250/293] lr: 5.000000e-04 eta: 2:07:50 time: 0.504866 data_time: 0.076844 memory: 5387 loss_kpt: 0.000612 acc_pose: 0.861268 loss: 0.000612 2022/09/14 07:10:00 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 07:10:00 - mmengine - INFO - Saving checkpoint at 150 epochs 2022/09/14 07:10:10 - mmengine - INFO - Epoch(val) [150][50/407] eta: 0:00:43 time: 0.121611 data_time: 0.015629 memory: 5387 2022/09/14 07:10:16 - mmengine - INFO - Epoch(val) [150][100/407] eta: 0:00:36 time: 0.117746 data_time: 0.012035 memory: 920 2022/09/14 07:10:22 - mmengine - INFO - Epoch(val) [150][150/407] eta: 0:00:30 time: 0.119780 data_time: 0.012724 memory: 920 2022/09/14 07:10:28 - mmengine - INFO - Epoch(val) [150][200/407] eta: 0:00:23 time: 0.114552 data_time: 0.009468 memory: 920 2022/09/14 07:10:33 - mmengine - INFO - Epoch(val) [150][250/407] eta: 0:00:17 time: 0.113200 data_time: 0.008502 memory: 920 2022/09/14 07:10:39 - mmengine - INFO - Epoch(val) [150][300/407] eta: 0:00:12 time: 0.116627 data_time: 0.009977 memory: 920 2022/09/14 07:10:45 - mmengine - INFO - Epoch(val) [150][350/407] eta: 0:00:06 time: 0.120594 data_time: 0.013858 memory: 920 2022/09/14 07:10:51 - mmengine - INFO - Epoch(val) [150][400/407] eta: 0:00:00 time: 0.110676 data_time: 0.007544 memory: 920 2022/09/14 07:11:27 - mmengine - INFO - Evaluating CocoMetric... 2022/09/14 07:11:41 - mmengine - INFO - Epoch(val) [150][407/407] coco/AP: 0.734950 coco/AP .5: 0.898821 coco/AP .75: 0.808834 coco/AP (M): 0.699161 coco/AP (L): 0.802316 coco/AR: 0.789751 coco/AR .5: 0.937972 coco/AR .75: 0.856738 coco/AR (M): 0.746818 coco/AR (L): 0.851542 2022/09/14 07:11:41 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220914/hrnet_fp16/best_coco/AP_epoch_140.pth is removed 2022/09/14 07:11:44 - mmengine - INFO - The best checkpoint with 0.7350 coco/AP at 150 epoch is saved to best_coco/AP_epoch_150.pth. 2022/09/14 07:12:09 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 07:12:09 - mmengine - INFO - Epoch(train) [151][50/293] lr: 5.000000e-04 eta: 2:07:03 time: 0.504004 data_time: 0.082653 memory: 5387 loss_kpt: 0.000610 acc_pose: 0.835455 loss: 0.000610 2022/09/14 07:12:34 - mmengine - INFO - Epoch(train) [151][100/293] lr: 5.000000e-04 eta: 2:06:43 time: 0.503253 data_time: 0.079629 memory: 5387 loss_kpt: 0.000597 acc_pose: 0.853368 loss: 0.000597 2022/09/14 07:12:59 - mmengine - INFO - Epoch(train) [151][150/293] lr: 5.000000e-04 eta: 2:06:22 time: 0.492478 data_time: 0.072463 memory: 5387 loss_kpt: 0.000599 acc_pose: 0.865738 loss: 0.000599 2022/09/14 07:13:24 - mmengine - INFO - Epoch(train) [151][200/293] lr: 5.000000e-04 eta: 2:06:02 time: 0.495504 data_time: 0.079802 memory: 5387 loss_kpt: 0.000615 acc_pose: 0.836320 loss: 0.000615 2022/09/14 07:13:49 - mmengine - INFO - Epoch(train) [151][250/293] lr: 5.000000e-04 eta: 2:05:41 time: 0.507780 data_time: 0.076862 memory: 5387 loss_kpt: 0.000608 acc_pose: 0.843388 loss: 0.000608 2022/09/14 07:14:11 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 07:14:11 - mmengine - INFO - Saving checkpoint at 151 epochs 2022/09/14 07:14:40 - mmengine - INFO - Epoch(train) [152][50/293] lr: 5.000000e-04 eta: 2:04:55 time: 0.507625 data_time: 0.080308 memory: 5387 loss_kpt: 0.000617 acc_pose: 0.811323 loss: 0.000617 2022/09/14 07:15:06 - mmengine - INFO - Epoch(train) [152][100/293] lr: 5.000000e-04 eta: 2:04:35 time: 0.510975 data_time: 0.077010 memory: 5387 loss_kpt: 0.000586 acc_pose: 0.818849 loss: 0.000586 2022/09/14 07:15:31 - mmengine - INFO - Epoch(train) [152][150/293] lr: 5.000000e-04 eta: 2:04:14 time: 0.498924 data_time: 0.082275 memory: 5387 loss_kpt: 0.000596 acc_pose: 0.829961 loss: 0.000596 2022/09/14 07:15:56 - mmengine - INFO - Epoch(train) [152][200/293] lr: 5.000000e-04 eta: 2:03:54 time: 0.497021 data_time: 0.080484 memory: 5387 loss_kpt: 0.000603 acc_pose: 0.861762 loss: 0.000603 2022/09/14 07:16:20 - mmengine - INFO - Epoch(train) [152][250/293] lr: 5.000000e-04 eta: 2:03:33 time: 0.495331 data_time: 0.072483 memory: 5387 loss_kpt: 0.000602 acc_pose: 0.844156 loss: 0.000602 2022/09/14 07:16:42 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 07:16:42 - mmengine - INFO - Saving checkpoint at 152 epochs 2022/09/14 07:17:13 - mmengine - INFO - Epoch(train) [153][50/293] lr: 5.000000e-04 eta: 2:02:47 time: 0.522447 data_time: 0.081978 memory: 5387 loss_kpt: 0.000599 acc_pose: 0.865791 loss: 0.000599 2022/09/14 07:17:38 - mmengine - INFO - Epoch(train) [153][100/293] lr: 5.000000e-04 eta: 2:02:27 time: 0.504233 data_time: 0.073523 memory: 5387 loss_kpt: 0.000595 acc_pose: 0.832176 loss: 0.000595 2022/09/14 07:18:03 - mmengine - INFO - Epoch(train) [153][150/293] lr: 5.000000e-04 eta: 2:02:06 time: 0.497023 data_time: 0.073326 memory: 5387 loss_kpt: 0.000597 acc_pose: 0.843327 loss: 0.000597 2022/09/14 07:18:28 - mmengine - INFO - Epoch(train) [153][200/293] lr: 5.000000e-04 eta: 2:01:46 time: 0.498984 data_time: 0.077937 memory: 5387 loss_kpt: 0.000609 acc_pose: 0.842906 loss: 0.000609 2022/09/14 07:18:52 - mmengine - INFO - Epoch(train) [153][250/293] lr: 5.000000e-04 eta: 2:01:25 time: 0.497727 data_time: 0.072683 memory: 5387 loss_kpt: 0.000605 acc_pose: 0.815676 loss: 0.000605 2022/09/14 07:19:14 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 07:19:14 - mmengine - INFO - Saving checkpoint at 153 epochs 2022/09/14 07:19:44 - mmengine - INFO - Epoch(train) [154][50/293] lr: 5.000000e-04 eta: 2:00:39 time: 0.511313 data_time: 0.083521 memory: 5387 loss_kpt: 0.000594 acc_pose: 0.795465 loss: 0.000594 2022/09/14 07:20:09 - mmengine - INFO - Epoch(train) [154][100/293] lr: 5.000000e-04 eta: 2:00:19 time: 0.504584 data_time: 0.080108 memory: 5387 loss_kpt: 0.000608 acc_pose: 0.814384 loss: 0.000608 2022/09/14 07:20:35 - mmengine - INFO - Epoch(train) [154][150/293] lr: 5.000000e-04 eta: 1:59:58 time: 0.507370 data_time: 0.073292 memory: 5387 loss_kpt: 0.000612 acc_pose: 0.821673 loss: 0.000612 2022/09/14 07:20:46 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 07:21:00 - mmengine - INFO - Epoch(train) [154][200/293] lr: 5.000000e-04 eta: 1:59:38 time: 0.505234 data_time: 0.073725 memory: 5387 loss_kpt: 0.000590 acc_pose: 0.845154 loss: 0.000590 2022/09/14 07:21:25 - mmengine - INFO - Epoch(train) [154][250/293] lr: 5.000000e-04 eta: 1:59:17 time: 0.499210 data_time: 0.076595 memory: 5387 loss_kpt: 0.000602 acc_pose: 0.846493 loss: 0.000602 2022/09/14 07:21:46 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 07:21:46 - mmengine - INFO - Saving checkpoint at 154 epochs 2022/09/14 07:22:17 - mmengine - INFO - Epoch(train) [155][50/293] lr: 5.000000e-04 eta: 1:58:31 time: 0.520923 data_time: 0.084481 memory: 5387 loss_kpt: 0.000607 acc_pose: 0.840759 loss: 0.000607 2022/09/14 07:22:42 - mmengine - INFO - Epoch(train) [155][100/293] lr: 5.000000e-04 eta: 1:58:11 time: 0.501015 data_time: 0.084046 memory: 5387 loss_kpt: 0.000600 acc_pose: 0.840925 loss: 0.000600 2022/09/14 07:23:07 - mmengine - INFO - Epoch(train) [155][150/293] lr: 5.000000e-04 eta: 1:57:51 time: 0.510268 data_time: 0.072993 memory: 5387 loss_kpt: 0.000591 acc_pose: 0.844634 loss: 0.000591 2022/09/14 07:23:32 - mmengine - INFO - Epoch(train) [155][200/293] lr: 5.000000e-04 eta: 1:57:30 time: 0.497331 data_time: 0.073528 memory: 5387 loss_kpt: 0.000610 acc_pose: 0.856739 loss: 0.000610 2022/09/14 07:23:57 - mmengine - INFO - Epoch(train) [155][250/293] lr: 5.000000e-04 eta: 1:57:09 time: 0.506120 data_time: 0.080300 memory: 5387 loss_kpt: 0.000610 acc_pose: 0.868130 loss: 0.000610 2022/09/14 07:24:19 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 07:24:19 - mmengine - INFO - Saving checkpoint at 155 epochs 2022/09/14 07:24:49 - mmengine - INFO - Epoch(train) [156][50/293] lr: 5.000000e-04 eta: 1:56:24 time: 0.514924 data_time: 0.083493 memory: 5387 loss_kpt: 0.000599 acc_pose: 0.836725 loss: 0.000599 2022/09/14 07:25:14 - mmengine - INFO - Epoch(train) [156][100/293] lr: 5.000000e-04 eta: 1:56:03 time: 0.502569 data_time: 0.084771 memory: 5387 loss_kpt: 0.000612 acc_pose: 0.783139 loss: 0.000612 2022/09/14 07:25:40 - mmengine - INFO - Epoch(train) [156][150/293] lr: 5.000000e-04 eta: 1:55:43 time: 0.509962 data_time: 0.078293 memory: 5387 loss_kpt: 0.000595 acc_pose: 0.847886 loss: 0.000595 2022/09/14 07:26:05 - mmengine - INFO - Epoch(train) [156][200/293] lr: 5.000000e-04 eta: 1:55:22 time: 0.507190 data_time: 0.082019 memory: 5387 loss_kpt: 0.000602 acc_pose: 0.810652 loss: 0.000602 2022/09/14 07:26:30 - mmengine - INFO - Epoch(train) [156][250/293] lr: 5.000000e-04 eta: 1:55:02 time: 0.504317 data_time: 0.072525 memory: 5387 loss_kpt: 0.000600 acc_pose: 0.812994 loss: 0.000600 2022/09/14 07:26:51 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 07:26:51 - mmengine - INFO - Saving checkpoint at 156 epochs 2022/09/14 07:27:23 - mmengine - INFO - Epoch(train) [157][50/293] lr: 5.000000e-04 eta: 1:54:16 time: 0.523546 data_time: 0.081452 memory: 5387 loss_kpt: 0.000603 acc_pose: 0.856282 loss: 0.000603 2022/09/14 07:27:49 - mmengine - INFO - Epoch(train) [157][100/293] lr: 5.000000e-04 eta: 1:53:56 time: 0.523424 data_time: 0.078914 memory: 5387 loss_kpt: 0.000595 acc_pose: 0.815324 loss: 0.000595 2022/09/14 07:28:14 - mmengine - INFO - Epoch(train) [157][150/293] lr: 5.000000e-04 eta: 1:53:36 time: 0.510481 data_time: 0.077402 memory: 5387 loss_kpt: 0.000592 acc_pose: 0.859012 loss: 0.000592 2022/09/14 07:28:40 - mmengine - INFO - Epoch(train) [157][200/293] lr: 5.000000e-04 eta: 1:53:15 time: 0.512072 data_time: 0.081263 memory: 5387 loss_kpt: 0.000599 acc_pose: 0.821982 loss: 0.000599 2022/09/14 07:29:05 - mmengine - INFO - Epoch(train) [157][250/293] lr: 5.000000e-04 eta: 1:52:55 time: 0.501268 data_time: 0.076697 memory: 5387 loss_kpt: 0.000611 acc_pose: 0.849954 loss: 0.000611 2022/09/14 07:29:26 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 07:29:26 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 07:29:26 - mmengine - INFO - Saving checkpoint at 157 epochs 2022/09/14 07:29:56 - mmengine - INFO - Epoch(train) [158][50/293] lr: 5.000000e-04 eta: 1:52:09 time: 0.515799 data_time: 0.083380 memory: 5387 loss_kpt: 0.000589 acc_pose: 0.848457 loss: 0.000589 2022/09/14 07:30:21 - mmengine - INFO - Epoch(train) [158][100/293] lr: 5.000000e-04 eta: 1:51:49 time: 0.506260 data_time: 0.076625 memory: 5387 loss_kpt: 0.000610 acc_pose: 0.842729 loss: 0.000610 2022/09/14 07:30:47 - mmengine - INFO - Epoch(train) [158][150/293] lr: 5.000000e-04 eta: 1:51:28 time: 0.506971 data_time: 0.082323 memory: 5387 loss_kpt: 0.000591 acc_pose: 0.807750 loss: 0.000591 2022/09/14 07:31:11 - mmengine - INFO - Epoch(train) [158][200/293] lr: 5.000000e-04 eta: 1:51:07 time: 0.493885 data_time: 0.072359 memory: 5387 loss_kpt: 0.000600 acc_pose: 0.851995 loss: 0.000600 2022/09/14 07:31:36 - mmengine - INFO - Epoch(train) [158][250/293] lr: 5.000000e-04 eta: 1:50:47 time: 0.501772 data_time: 0.078431 memory: 5387 loss_kpt: 0.000604 acc_pose: 0.854578 loss: 0.000604 2022/09/14 07:31:58 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 07:31:58 - mmengine - INFO - Saving checkpoint at 158 epochs 2022/09/14 07:32:31 - mmengine - INFO - Epoch(train) [159][50/293] lr: 5.000000e-04 eta: 1:50:02 time: 0.525025 data_time: 0.093245 memory: 5387 loss_kpt: 0.000582 acc_pose: 0.830971 loss: 0.000582 2022/09/14 07:32:56 - mmengine - INFO - Epoch(train) [159][100/293] lr: 5.000000e-04 eta: 1:49:41 time: 0.501219 data_time: 0.072091 memory: 5387 loss_kpt: 0.000595 acc_pose: 0.876754 loss: 0.000595 2022/09/14 07:33:21 - mmengine - INFO - Epoch(train) [159][150/293] lr: 5.000000e-04 eta: 1:49:20 time: 0.492937 data_time: 0.076300 memory: 5387 loss_kpt: 0.000594 acc_pose: 0.788037 loss: 0.000594 2022/09/14 07:33:46 - mmengine - INFO - Epoch(train) [159][200/293] lr: 5.000000e-04 eta: 1:49:00 time: 0.504860 data_time: 0.080251 memory: 5387 loss_kpt: 0.000603 acc_pose: 0.795660 loss: 0.000603 2022/09/14 07:34:11 - mmengine - INFO - Epoch(train) [159][250/293] lr: 5.000000e-04 eta: 1:48:39 time: 0.495298 data_time: 0.073449 memory: 5387 loss_kpt: 0.000604 acc_pose: 0.825529 loss: 0.000604 2022/09/14 07:34:32 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 07:34:32 - mmengine - INFO - Saving checkpoint at 159 epochs 2022/09/14 07:35:03 - mmengine - INFO - Epoch(train) [160][50/293] lr: 5.000000e-04 eta: 1:47:54 time: 0.523793 data_time: 0.080447 memory: 5387 loss_kpt: 0.000596 acc_pose: 0.831545 loss: 0.000596 2022/09/14 07:35:28 - mmengine - INFO - Epoch(train) [160][100/293] lr: 5.000000e-04 eta: 1:47:33 time: 0.505744 data_time: 0.071809 memory: 5387 loss_kpt: 0.000618 acc_pose: 0.807796 loss: 0.000618 2022/09/14 07:35:54 - mmengine - INFO - Epoch(train) [160][150/293] lr: 5.000000e-04 eta: 1:47:13 time: 0.504008 data_time: 0.083251 memory: 5387 loss_kpt: 0.000612 acc_pose: 0.862410 loss: 0.000612 2022/09/14 07:36:19 - mmengine - INFO - Epoch(train) [160][200/293] lr: 5.000000e-04 eta: 1:46:52 time: 0.507368 data_time: 0.077182 memory: 5387 loss_kpt: 0.000600 acc_pose: 0.851630 loss: 0.000600 2022/09/14 07:36:44 - mmengine - INFO - Epoch(train) [160][250/293] lr: 5.000000e-04 eta: 1:46:31 time: 0.506600 data_time: 0.075488 memory: 5387 loss_kpt: 0.000610 acc_pose: 0.849567 loss: 0.000610 2022/09/14 07:37:05 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 07:37:05 - mmengine - INFO - Saving checkpoint at 160 epochs 2022/09/14 07:37:16 - mmengine - INFO - Epoch(val) [160][50/407] eta: 0:00:43 time: 0.123020 data_time: 0.014120 memory: 5387 2022/09/14 07:37:22 - mmengine - INFO - Epoch(val) [160][100/407] eta: 0:00:35 time: 0.116159 data_time: 0.009876 memory: 920 2022/09/14 07:37:28 - mmengine - INFO - Epoch(val) [160][150/407] eta: 0:00:28 time: 0.112792 data_time: 0.008479 memory: 920 2022/09/14 07:37:33 - mmengine - INFO - Epoch(val) [160][200/407] eta: 0:00:24 time: 0.118139 data_time: 0.009963 memory: 920 2022/09/14 07:37:39 - mmengine - INFO - Epoch(val) [160][250/407] eta: 0:00:17 time: 0.113514 data_time: 0.009601 memory: 920 2022/09/14 07:37:45 - mmengine - INFO - Epoch(val) [160][300/407] eta: 0:00:12 time: 0.114856 data_time: 0.009762 memory: 920 2022/09/14 07:37:51 - mmengine - INFO - Epoch(val) [160][350/407] eta: 0:00:06 time: 0.116469 data_time: 0.009950 memory: 920 2022/09/14 07:37:56 - mmengine - INFO - Epoch(val) [160][400/407] eta: 0:00:00 time: 0.109894 data_time: 0.007736 memory: 920 2022/09/14 07:38:33 - mmengine - INFO - Evaluating CocoMetric... 2022/09/14 07:38:47 - mmengine - INFO - Epoch(val) [160][407/407] coco/AP: 0.736391 coco/AP .5: 0.899723 coco/AP .75: 0.812013 coco/AP (M): 0.701363 coco/AP (L): 0.801954 coco/AR: 0.789657 coco/AR .5: 0.938602 coco/AR .75: 0.856108 coco/AR (M): 0.748129 coco/AR (L): 0.850130 2022/09/14 07:38:47 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220914/hrnet_fp16/best_coco/AP_epoch_150.pth is removed 2022/09/14 07:38:50 - mmengine - INFO - The best checkpoint with 0.7364 coco/AP at 160 epoch is saved to best_coco/AP_epoch_160.pth. 2022/09/14 07:39:15 - mmengine - INFO - Epoch(train) [161][50/293] lr: 5.000000e-04 eta: 1:45:46 time: 0.511435 data_time: 0.086685 memory: 5387 loss_kpt: 0.000610 acc_pose: 0.844320 loss: 0.000610 2022/09/14 07:39:41 - mmengine - INFO - Epoch(train) [161][100/293] lr: 5.000000e-04 eta: 1:45:26 time: 0.508919 data_time: 0.082941 memory: 5387 loss_kpt: 0.000592 acc_pose: 0.798932 loss: 0.000592 2022/09/14 07:39:51 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 07:40:06 - mmengine - INFO - Epoch(train) [161][150/293] lr: 5.000000e-04 eta: 1:45:05 time: 0.506953 data_time: 0.077146 memory: 5387 loss_kpt: 0.000604 acc_pose: 0.835933 loss: 0.000604 2022/09/14 07:40:31 - mmengine - INFO - Epoch(train) [161][200/293] lr: 5.000000e-04 eta: 1:44:44 time: 0.496206 data_time: 0.076155 memory: 5387 loss_kpt: 0.000604 acc_pose: 0.835240 loss: 0.000604 2022/09/14 07:40:55 - mmengine - INFO - Epoch(train) [161][250/293] lr: 5.000000e-04 eta: 1:44:23 time: 0.491087 data_time: 0.074292 memory: 5387 loss_kpt: 0.000607 acc_pose: 0.853596 loss: 0.000607 2022/09/14 07:41:17 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 07:41:17 - mmengine - INFO - Saving checkpoint at 161 epochs 2022/09/14 07:41:47 - mmengine - INFO - Epoch(train) [162][50/293] lr: 5.000000e-04 eta: 1:43:38 time: 0.520456 data_time: 0.094986 memory: 5387 loss_kpt: 0.000597 acc_pose: 0.861549 loss: 0.000597 2022/09/14 07:42:13 - mmengine - INFO - Epoch(train) [162][100/293] lr: 5.000000e-04 eta: 1:43:18 time: 0.524426 data_time: 0.079779 memory: 5387 loss_kpt: 0.000584 acc_pose: 0.855826 loss: 0.000584 2022/09/14 07:42:39 - mmengine - INFO - Epoch(train) [162][150/293] lr: 5.000000e-04 eta: 1:42:57 time: 0.507172 data_time: 0.077503 memory: 5387 loss_kpt: 0.000598 acc_pose: 0.835458 loss: 0.000598 2022/09/14 07:43:04 - mmengine - INFO - Epoch(train) [162][200/293] lr: 5.000000e-04 eta: 1:42:37 time: 0.502099 data_time: 0.074085 memory: 5387 loss_kpt: 0.000598 acc_pose: 0.852526 loss: 0.000598 2022/09/14 07:43:29 - mmengine - INFO - Epoch(train) [162][250/293] lr: 5.000000e-04 eta: 1:42:16 time: 0.504265 data_time: 0.079447 memory: 5387 loss_kpt: 0.000589 acc_pose: 0.877116 loss: 0.000589 2022/09/14 07:43:51 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 07:43:51 - mmengine - INFO - Saving checkpoint at 162 epochs 2022/09/14 07:44:21 - mmengine - INFO - Epoch(train) [163][50/293] lr: 5.000000e-04 eta: 1:41:31 time: 0.504310 data_time: 0.081493 memory: 5387 loss_kpt: 0.000606 acc_pose: 0.848709 loss: 0.000606 2022/09/14 07:44:46 - mmengine - INFO - Epoch(train) [163][100/293] lr: 5.000000e-04 eta: 1:41:10 time: 0.507005 data_time: 0.077410 memory: 5387 loss_kpt: 0.000593 acc_pose: 0.859929 loss: 0.000593 2022/09/14 07:45:11 - mmengine - INFO - Epoch(train) [163][150/293] lr: 5.000000e-04 eta: 1:40:50 time: 0.509618 data_time: 0.077385 memory: 5387 loss_kpt: 0.000598 acc_pose: 0.829402 loss: 0.000598 2022/09/14 07:45:36 - mmengine - INFO - Epoch(train) [163][200/293] lr: 5.000000e-04 eta: 1:40:29 time: 0.496958 data_time: 0.077200 memory: 5387 loss_kpt: 0.000589 acc_pose: 0.834632 loss: 0.000589 2022/09/14 07:46:02 - mmengine - INFO - Epoch(train) [163][250/293] lr: 5.000000e-04 eta: 1:40:08 time: 0.509424 data_time: 0.080401 memory: 5387 loss_kpt: 0.000592 acc_pose: 0.841834 loss: 0.000592 2022/09/14 07:46:23 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 07:46:23 - mmengine - INFO - Saving checkpoint at 163 epochs 2022/09/14 07:46:53 - mmengine - INFO - Epoch(train) [164][50/293] lr: 5.000000e-04 eta: 1:39:24 time: 0.521518 data_time: 0.082128 memory: 5387 loss_kpt: 0.000598 acc_pose: 0.817377 loss: 0.000598 2022/09/14 07:47:18 - mmengine - INFO - Epoch(train) [164][100/293] lr: 5.000000e-04 eta: 1:39:03 time: 0.500343 data_time: 0.073285 memory: 5387 loss_kpt: 0.000584 acc_pose: 0.895799 loss: 0.000584 2022/09/14 07:47:44 - mmengine - INFO - Epoch(train) [164][150/293] lr: 5.000000e-04 eta: 1:38:42 time: 0.504393 data_time: 0.077002 memory: 5387 loss_kpt: 0.000598 acc_pose: 0.827016 loss: 0.000598 2022/09/14 07:48:08 - mmengine - INFO - Epoch(train) [164][200/293] lr: 5.000000e-04 eta: 1:38:21 time: 0.494487 data_time: 0.072857 memory: 5387 loss_kpt: 0.000591 acc_pose: 0.855828 loss: 0.000591 2022/09/14 07:48:29 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 07:48:33 - mmengine - INFO - Epoch(train) [164][250/293] lr: 5.000000e-04 eta: 1:38:00 time: 0.498114 data_time: 0.088928 memory: 5387 loss_kpt: 0.000602 acc_pose: 0.849662 loss: 0.000602 2022/09/14 07:48:55 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 07:48:55 - mmengine - INFO - Saving checkpoint at 164 epochs 2022/09/14 07:49:25 - mmengine - INFO - Epoch(train) [165][50/293] lr: 5.000000e-04 eta: 1:37:16 time: 0.507846 data_time: 0.084526 memory: 5387 loss_kpt: 0.000593 acc_pose: 0.829909 loss: 0.000593 2022/09/14 07:49:50 - mmengine - INFO - Epoch(train) [165][100/293] lr: 5.000000e-04 eta: 1:36:55 time: 0.507024 data_time: 0.077825 memory: 5387 loss_kpt: 0.000603 acc_pose: 0.816943 loss: 0.000603 2022/09/14 07:50:16 - mmengine - INFO - Epoch(train) [165][150/293] lr: 5.000000e-04 eta: 1:36:34 time: 0.509867 data_time: 0.078625 memory: 5387 loss_kpt: 0.000602 acc_pose: 0.829393 loss: 0.000602 2022/09/14 07:50:41 - mmengine - INFO - Epoch(train) [165][200/293] lr: 5.000000e-04 eta: 1:36:13 time: 0.502482 data_time: 0.081541 memory: 5387 loss_kpt: 0.000591 acc_pose: 0.844989 loss: 0.000591 2022/09/14 07:51:06 - mmengine - INFO - Epoch(train) [165][250/293] lr: 5.000000e-04 eta: 1:35:53 time: 0.506295 data_time: 0.071825 memory: 5387 loss_kpt: 0.000607 acc_pose: 0.820375 loss: 0.000607 2022/09/14 07:51:27 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 07:51:27 - mmengine - INFO - Saving checkpoint at 165 epochs 2022/09/14 07:51:57 - mmengine - INFO - Epoch(train) [166][50/293] lr: 5.000000e-04 eta: 1:35:08 time: 0.513902 data_time: 0.085765 memory: 5387 loss_kpt: 0.000591 acc_pose: 0.881288 loss: 0.000591 2022/09/14 07:52:23 - mmengine - INFO - Epoch(train) [166][100/293] lr: 5.000000e-04 eta: 1:34:48 time: 0.515601 data_time: 0.076540 memory: 5387 loss_kpt: 0.000608 acc_pose: 0.872589 loss: 0.000608 2022/09/14 07:52:48 - mmengine - INFO - Epoch(train) [166][150/293] lr: 5.000000e-04 eta: 1:34:27 time: 0.501273 data_time: 0.076058 memory: 5387 loss_kpt: 0.000613 acc_pose: 0.868853 loss: 0.000613 2022/09/14 07:53:14 - mmengine - INFO - Epoch(train) [166][200/293] lr: 5.000000e-04 eta: 1:34:06 time: 0.516313 data_time: 0.078594 memory: 5387 loss_kpt: 0.000607 acc_pose: 0.873534 loss: 0.000607 2022/09/14 07:53:39 - mmengine - INFO - Epoch(train) [166][250/293] lr: 5.000000e-04 eta: 1:33:45 time: 0.503093 data_time: 0.085063 memory: 5387 loss_kpt: 0.000596 acc_pose: 0.860180 loss: 0.000596 2022/09/14 07:54:00 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 07:54:00 - mmengine - INFO - Saving checkpoint at 166 epochs 2022/09/14 07:54:29 - mmengine - INFO - Epoch(train) [167][50/293] lr: 5.000000e-04 eta: 1:33:01 time: 0.505707 data_time: 0.080441 memory: 5387 loss_kpt: 0.000591 acc_pose: 0.814541 loss: 0.000591 2022/09/14 07:54:54 - mmengine - INFO - Epoch(train) [167][100/293] lr: 5.000000e-04 eta: 1:32:40 time: 0.503723 data_time: 0.080169 memory: 5387 loss_kpt: 0.000590 acc_pose: 0.854333 loss: 0.000590 2022/09/14 07:55:20 - mmengine - INFO - Epoch(train) [167][150/293] lr: 5.000000e-04 eta: 1:32:19 time: 0.504635 data_time: 0.080094 memory: 5387 loss_kpt: 0.000592 acc_pose: 0.841391 loss: 0.000592 2022/09/14 07:55:45 - mmengine - INFO - Epoch(train) [167][200/293] lr: 5.000000e-04 eta: 1:31:58 time: 0.502235 data_time: 0.076465 memory: 5387 loss_kpt: 0.000597 acc_pose: 0.868358 loss: 0.000597 2022/09/14 07:56:10 - mmengine - INFO - Epoch(train) [167][250/293] lr: 5.000000e-04 eta: 1:31:37 time: 0.499483 data_time: 0.072741 memory: 5387 loss_kpt: 0.000612 acc_pose: 0.813655 loss: 0.000612 2022/09/14 07:56:31 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 07:56:31 - mmengine - INFO - Saving checkpoint at 167 epochs 2022/09/14 07:57:00 - mmengine - INFO - Epoch(train) [168][50/293] lr: 5.000000e-04 eta: 1:30:53 time: 0.503358 data_time: 0.087215 memory: 5387 loss_kpt: 0.000600 acc_pose: 0.826849 loss: 0.000600 2022/09/14 07:57:10 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 07:57:25 - mmengine - INFO - Epoch(train) [168][100/293] lr: 5.000000e-04 eta: 1:30:32 time: 0.503934 data_time: 0.071394 memory: 5387 loss_kpt: 0.000605 acc_pose: 0.802253 loss: 0.000605 2022/09/14 07:57:51 - mmengine - INFO - Epoch(train) [168][150/293] lr: 5.000000e-04 eta: 1:30:11 time: 0.507266 data_time: 0.075703 memory: 5387 loss_kpt: 0.000583 acc_pose: 0.831601 loss: 0.000583 2022/09/14 07:58:16 - mmengine - INFO - Epoch(train) [168][200/293] lr: 5.000000e-04 eta: 1:29:51 time: 0.507376 data_time: 0.076956 memory: 5387 loss_kpt: 0.000579 acc_pose: 0.839560 loss: 0.000579 2022/09/14 07:58:41 - mmengine - INFO - Epoch(train) [168][250/293] lr: 5.000000e-04 eta: 1:29:30 time: 0.494309 data_time: 0.076191 memory: 5387 loss_kpt: 0.000607 acc_pose: 0.827675 loss: 0.000607 2022/09/14 07:59:02 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 07:59:02 - mmengine - INFO - Saving checkpoint at 168 epochs 2022/09/14 07:59:33 - mmengine - INFO - Epoch(train) [169][50/293] lr: 5.000000e-04 eta: 1:28:46 time: 0.520645 data_time: 0.082088 memory: 5387 loss_kpt: 0.000592 acc_pose: 0.852067 loss: 0.000592 2022/09/14 07:59:58 - mmengine - INFO - Epoch(train) [169][100/293] lr: 5.000000e-04 eta: 1:28:25 time: 0.505798 data_time: 0.079427 memory: 5387 loss_kpt: 0.000601 acc_pose: 0.847490 loss: 0.000601 2022/09/14 08:00:23 - mmengine - INFO - Epoch(train) [169][150/293] lr: 5.000000e-04 eta: 1:28:04 time: 0.505093 data_time: 0.072326 memory: 5387 loss_kpt: 0.000592 acc_pose: 0.869701 loss: 0.000592 2022/09/14 08:00:48 - mmengine - INFO - Epoch(train) [169][200/293] lr: 5.000000e-04 eta: 1:27:43 time: 0.494896 data_time: 0.077318 memory: 5387 loss_kpt: 0.000604 acc_pose: 0.810752 loss: 0.000604 2022/09/14 08:01:13 - mmengine - INFO - Epoch(train) [169][250/293] lr: 5.000000e-04 eta: 1:27:22 time: 0.497841 data_time: 0.081922 memory: 5387 loss_kpt: 0.000604 acc_pose: 0.794118 loss: 0.000604 2022/09/14 08:01:34 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 08:01:34 - mmengine - INFO - Saving checkpoint at 169 epochs 2022/09/14 08:02:04 - mmengine - INFO - Epoch(train) [170][50/293] lr: 5.000000e-04 eta: 1:26:38 time: 0.503951 data_time: 0.083979 memory: 5387 loss_kpt: 0.000604 acc_pose: 0.799159 loss: 0.000604 2022/09/14 08:02:28 - mmengine - INFO - Epoch(train) [170][100/293] lr: 5.000000e-04 eta: 1:26:17 time: 0.485694 data_time: 0.076834 memory: 5387 loss_kpt: 0.000583 acc_pose: 0.835111 loss: 0.000583 2022/09/14 08:02:54 - mmengine - INFO - Epoch(train) [170][150/293] lr: 5.000000e-04 eta: 1:25:56 time: 0.505062 data_time: 0.076709 memory: 5387 loss_kpt: 0.000596 acc_pose: 0.864553 loss: 0.000596 2022/09/14 08:03:19 - mmengine - INFO - Epoch(train) [170][200/293] lr: 5.000000e-04 eta: 1:25:35 time: 0.503263 data_time: 0.075488 memory: 5387 loss_kpt: 0.000591 acc_pose: 0.845718 loss: 0.000591 2022/09/14 08:03:44 - mmengine - INFO - Epoch(train) [170][250/293] lr: 5.000000e-04 eta: 1:25:14 time: 0.500522 data_time: 0.073765 memory: 5387 loss_kpt: 0.000585 acc_pose: 0.855603 loss: 0.000585 2022/09/14 08:04:05 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 08:04:05 - mmengine - INFO - Saving checkpoint at 170 epochs 2022/09/14 08:04:15 - mmengine - INFO - Epoch(val) [170][50/407] eta: 0:00:45 time: 0.126135 data_time: 0.014842 memory: 5387 2022/09/14 08:04:21 - mmengine - INFO - Epoch(val) [170][100/407] eta: 0:00:34 time: 0.113660 data_time: 0.008473 memory: 920 2022/09/14 08:04:27 - mmengine - INFO - Epoch(val) [170][150/407] eta: 0:00:29 time: 0.115818 data_time: 0.009313 memory: 920 2022/09/14 08:04:32 - mmengine - INFO - Epoch(val) [170][200/407] eta: 0:00:23 time: 0.112929 data_time: 0.008210 memory: 920 2022/09/14 08:04:38 - mmengine - INFO - Epoch(val) [170][250/407] eta: 0:00:18 time: 0.116805 data_time: 0.009029 memory: 920 2022/09/14 08:04:44 - mmengine - INFO - Epoch(val) [170][300/407] eta: 0:00:12 time: 0.119052 data_time: 0.011722 memory: 920 2022/09/14 08:04:50 - mmengine - INFO - Epoch(val) [170][350/407] eta: 0:00:06 time: 0.114238 data_time: 0.008966 memory: 920 2022/09/14 08:04:55 - mmengine - INFO - Epoch(val) [170][400/407] eta: 0:00:00 time: 0.109723 data_time: 0.007471 memory: 920 2022/09/14 08:05:32 - mmengine - INFO - Evaluating CocoMetric... 2022/09/14 08:05:46 - mmengine - INFO - Epoch(val) [170][407/407] coco/AP: 0.734225 coco/AP .5: 0.899963 coco/AP .75: 0.808662 coco/AP (M): 0.697678 coco/AP (L): 0.801934 coco/AR: 0.789153 coco/AR .5: 0.939861 coco/AR .75: 0.855164 coco/AR (M): 0.746080 coco/AR (L): 0.851282 2022/09/14 08:06:12 - mmengine - INFO - Epoch(train) [171][50/293] lr: 5.000000e-05 eta: 1:24:30 time: 0.518299 data_time: 0.079260 memory: 5387 loss_kpt: 0.000589 acc_pose: 0.839810 loss: 0.000589 2022/09/14 08:06:37 - mmengine - INFO - Epoch(train) [171][100/293] lr: 5.000000e-05 eta: 1:24:09 time: 0.503034 data_time: 0.071026 memory: 5387 loss_kpt: 0.000584 acc_pose: 0.845525 loss: 0.000584 2022/09/14 08:07:03 - mmengine - INFO - Epoch(train) [171][150/293] lr: 5.000000e-05 eta: 1:23:48 time: 0.508145 data_time: 0.082565 memory: 5387 loss_kpt: 0.000577 acc_pose: 0.853467 loss: 0.000577 2022/09/14 08:07:23 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 08:07:28 - mmengine - INFO - Epoch(train) [171][200/293] lr: 5.000000e-05 eta: 1:23:27 time: 0.496122 data_time: 0.071009 memory: 5387 loss_kpt: 0.000579 acc_pose: 0.815896 loss: 0.000579 2022/09/14 08:07:53 - mmengine - INFO - Epoch(train) [171][250/293] lr: 5.000000e-05 eta: 1:23:06 time: 0.505830 data_time: 0.076940 memory: 5387 loss_kpt: 0.000575 acc_pose: 0.839756 loss: 0.000575 2022/09/14 08:08:14 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 08:08:14 - mmengine - INFO - Saving checkpoint at 171 epochs 2022/09/14 08:08:44 - mmengine - INFO - Epoch(train) [172][50/293] lr: 5.000000e-05 eta: 1:22:22 time: 0.507667 data_time: 0.079118 memory: 5387 loss_kpt: 0.000582 acc_pose: 0.873460 loss: 0.000582 2022/09/14 08:09:09 - mmengine - INFO - Epoch(train) [172][100/293] lr: 5.000000e-05 eta: 1:22:02 time: 0.505957 data_time: 0.083320 memory: 5387 loss_kpt: 0.000567 acc_pose: 0.868393 loss: 0.000567 2022/09/14 08:09:35 - mmengine - INFO - Epoch(train) [172][150/293] lr: 5.000000e-05 eta: 1:21:41 time: 0.504133 data_time: 0.081857 memory: 5387 loss_kpt: 0.000582 acc_pose: 0.866362 loss: 0.000582 2022/09/14 08:10:00 - mmengine - INFO - Epoch(train) [172][200/293] lr: 5.000000e-05 eta: 1:21:20 time: 0.502298 data_time: 0.073912 memory: 5387 loss_kpt: 0.000564 acc_pose: 0.881888 loss: 0.000564 2022/09/14 08:10:25 - mmengine - INFO - Epoch(train) [172][250/293] lr: 5.000000e-05 eta: 1:20:59 time: 0.499679 data_time: 0.077017 memory: 5387 loss_kpt: 0.000582 acc_pose: 0.804384 loss: 0.000582 2022/09/14 08:10:47 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 08:10:47 - mmengine - INFO - Saving checkpoint at 172 epochs 2022/09/14 08:11:17 - mmengine - INFO - Epoch(train) [173][50/293] lr: 5.000000e-05 eta: 1:20:15 time: 0.513013 data_time: 0.094093 memory: 5387 loss_kpt: 0.000563 acc_pose: 0.882795 loss: 0.000563 2022/09/14 08:11:42 - mmengine - INFO - Epoch(train) [173][100/293] lr: 5.000000e-05 eta: 1:19:54 time: 0.500382 data_time: 0.075386 memory: 5387 loss_kpt: 0.000570 acc_pose: 0.855813 loss: 0.000570 2022/09/14 08:12:07 - mmengine - INFO - Epoch(train) [173][150/293] lr: 5.000000e-05 eta: 1:19:33 time: 0.509970 data_time: 0.075831 memory: 5387 loss_kpt: 0.000577 acc_pose: 0.813266 loss: 0.000577 2022/09/14 08:12:33 - mmengine - INFO - Epoch(train) [173][200/293] lr: 5.000000e-05 eta: 1:19:12 time: 0.508479 data_time: 0.079572 memory: 5387 loss_kpt: 0.000576 acc_pose: 0.868801 loss: 0.000576 2022/09/14 08:12:58 - mmengine - INFO - Epoch(train) [173][250/293] lr: 5.000000e-05 eta: 1:18:51 time: 0.499606 data_time: 0.072038 memory: 5387 loss_kpt: 0.000567 acc_pose: 0.810915 loss: 0.000567 2022/09/14 08:13:19 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 08:13:19 - mmengine - INFO - Saving checkpoint at 173 epochs 2022/09/14 08:13:50 - mmengine - INFO - Epoch(train) [174][50/293] lr: 5.000000e-05 eta: 1:18:08 time: 0.516462 data_time: 0.097836 memory: 5387 loss_kpt: 0.000590 acc_pose: 0.834438 loss: 0.000590 2022/09/14 08:14:15 - mmengine - INFO - Epoch(train) [174][100/293] lr: 5.000000e-05 eta: 1:17:47 time: 0.505575 data_time: 0.070321 memory: 5387 loss_kpt: 0.000575 acc_pose: 0.894624 loss: 0.000575 2022/09/14 08:14:40 - mmengine - INFO - Epoch(train) [174][150/293] lr: 5.000000e-05 eta: 1:17:25 time: 0.496054 data_time: 0.073330 memory: 5387 loss_kpt: 0.000567 acc_pose: 0.844921 loss: 0.000567 2022/09/14 08:15:05 - mmengine - INFO - Epoch(train) [174][200/293] lr: 5.000000e-05 eta: 1:17:04 time: 0.501447 data_time: 0.071107 memory: 5387 loss_kpt: 0.000576 acc_pose: 0.761436 loss: 0.000576 2022/09/14 08:15:30 - mmengine - INFO - Epoch(train) [174][250/293] lr: 5.000000e-05 eta: 1:16:43 time: 0.501279 data_time: 0.078077 memory: 5387 loss_kpt: 0.000571 acc_pose: 0.863690 loss: 0.000571 2022/09/14 08:15:51 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 08:15:51 - mmengine - INFO - Saving checkpoint at 174 epochs 2022/09/14 08:16:07 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 08:16:23 - mmengine - INFO - Epoch(train) [175][50/293] lr: 5.000000e-05 eta: 1:16:00 time: 0.517873 data_time: 0.086442 memory: 5387 loss_kpt: 0.000559 acc_pose: 0.859927 loss: 0.000559 2022/09/14 08:16:48 - mmengine - INFO - Epoch(train) [175][100/293] lr: 5.000000e-05 eta: 1:15:39 time: 0.499646 data_time: 0.074075 memory: 5387 loss_kpt: 0.000565 acc_pose: 0.842684 loss: 0.000565 2022/09/14 08:17:14 - mmengine - INFO - Epoch(train) [175][150/293] lr: 5.000000e-05 eta: 1:15:18 time: 0.510779 data_time: 0.075862 memory: 5387 loss_kpt: 0.000578 acc_pose: 0.836158 loss: 0.000578 2022/09/14 08:17:39 - mmengine - INFO - Epoch(train) [175][200/293] lr: 5.000000e-05 eta: 1:14:57 time: 0.497855 data_time: 0.072853 memory: 5387 loss_kpt: 0.000565 acc_pose: 0.841011 loss: 0.000565 2022/09/14 08:18:04 - mmengine - INFO - Epoch(train) [175][250/293] lr: 5.000000e-05 eta: 1:14:36 time: 0.504142 data_time: 0.072585 memory: 5387 loss_kpt: 0.000554 acc_pose: 0.844585 loss: 0.000554 2022/09/14 08:18:26 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 08:18:26 - mmengine - INFO - Saving checkpoint at 175 epochs 2022/09/14 08:18:57 - mmengine - INFO - Epoch(train) [176][50/293] lr: 5.000000e-05 eta: 1:13:53 time: 0.511451 data_time: 0.090608 memory: 5387 loss_kpt: 0.000560 acc_pose: 0.859812 loss: 0.000560 2022/09/14 08:19:22 - mmengine - INFO - Epoch(train) [176][100/293] lr: 5.000000e-05 eta: 1:13:31 time: 0.506591 data_time: 0.077440 memory: 5387 loss_kpt: 0.000565 acc_pose: 0.804338 loss: 0.000565 2022/09/14 08:19:48 - mmengine - INFO - Epoch(train) [176][150/293] lr: 5.000000e-05 eta: 1:13:10 time: 0.503284 data_time: 0.075904 memory: 5387 loss_kpt: 0.000572 acc_pose: 0.821997 loss: 0.000572 2022/09/14 08:20:13 - mmengine - INFO - Epoch(train) [176][200/293] lr: 5.000000e-05 eta: 1:12:49 time: 0.497122 data_time: 0.076699 memory: 5387 loss_kpt: 0.000562 acc_pose: 0.865265 loss: 0.000562 2022/09/14 08:20:37 - mmengine - INFO - Epoch(train) [176][250/293] lr: 5.000000e-05 eta: 1:12:28 time: 0.498518 data_time: 0.071151 memory: 5387 loss_kpt: 0.000565 acc_pose: 0.850439 loss: 0.000565 2022/09/14 08:20:59 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 08:20:59 - mmengine - INFO - Saving checkpoint at 176 epochs 2022/09/14 08:21:29 - mmengine - INFO - Epoch(train) [177][50/293] lr: 5.000000e-05 eta: 1:11:45 time: 0.515051 data_time: 0.089429 memory: 5387 loss_kpt: 0.000575 acc_pose: 0.885297 loss: 0.000575 2022/09/14 08:21:55 - mmengine - INFO - Epoch(train) [177][100/293] lr: 5.000000e-05 eta: 1:11:24 time: 0.510169 data_time: 0.076084 memory: 5387 loss_kpt: 0.000569 acc_pose: 0.870420 loss: 0.000569 2022/09/14 08:22:20 - mmengine - INFO - Epoch(train) [177][150/293] lr: 5.000000e-05 eta: 1:11:03 time: 0.506455 data_time: 0.074412 memory: 5387 loss_kpt: 0.000556 acc_pose: 0.845977 loss: 0.000556 2022/09/14 08:22:45 - mmengine - INFO - Epoch(train) [177][200/293] lr: 5.000000e-05 eta: 1:10:42 time: 0.496134 data_time: 0.077810 memory: 5387 loss_kpt: 0.000549 acc_pose: 0.880421 loss: 0.000549 2022/09/14 08:23:10 - mmengine - INFO - Epoch(train) [177][250/293] lr: 5.000000e-05 eta: 1:10:21 time: 0.503794 data_time: 0.074746 memory: 5387 loss_kpt: 0.000566 acc_pose: 0.841569 loss: 0.000566 2022/09/14 08:23:32 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 08:23:32 - mmengine - INFO - Saving checkpoint at 177 epochs 2022/09/14 08:24:02 - mmengine - INFO - Epoch(train) [178][50/293] lr: 5.000000e-05 eta: 1:09:38 time: 0.522275 data_time: 0.081422 memory: 5387 loss_kpt: 0.000566 acc_pose: 0.831316 loss: 0.000566 2022/09/14 08:24:27 - mmengine - INFO - Epoch(train) [178][100/293] lr: 5.000000e-05 eta: 1:09:17 time: 0.496241 data_time: 0.080092 memory: 5387 loss_kpt: 0.000569 acc_pose: 0.827644 loss: 0.000569 2022/09/14 08:24:47 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 08:24:52 - mmengine - INFO - Epoch(train) [178][150/293] lr: 5.000000e-05 eta: 1:08:55 time: 0.501671 data_time: 0.072469 memory: 5387 loss_kpt: 0.000566 acc_pose: 0.828060 loss: 0.000566 2022/09/14 08:25:17 - mmengine - INFO - Epoch(train) [178][200/293] lr: 5.000000e-05 eta: 1:08:34 time: 0.509828 data_time: 0.078358 memory: 5387 loss_kpt: 0.000573 acc_pose: 0.855661 loss: 0.000573 2022/09/14 08:25:43 - mmengine - INFO - Epoch(train) [178][250/293] lr: 5.000000e-05 eta: 1:08:13 time: 0.503458 data_time: 0.077560 memory: 5387 loss_kpt: 0.000561 acc_pose: 0.812215 loss: 0.000561 2022/09/14 08:26:04 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 08:26:04 - mmengine - INFO - Saving checkpoint at 178 epochs 2022/09/14 08:26:36 - mmengine - INFO - Epoch(train) [179][50/293] lr: 5.000000e-05 eta: 1:07:30 time: 0.515759 data_time: 0.088194 memory: 5387 loss_kpt: 0.000563 acc_pose: 0.845755 loss: 0.000563 2022/09/14 08:27:02 - mmengine - INFO - Epoch(train) [179][100/293] lr: 5.000000e-05 eta: 1:07:09 time: 0.504628 data_time: 0.078691 memory: 5387 loss_kpt: 0.000557 acc_pose: 0.873284 loss: 0.000557 2022/09/14 08:27:27 - mmengine - INFO - Epoch(train) [179][150/293] lr: 5.000000e-05 eta: 1:06:48 time: 0.510915 data_time: 0.074544 memory: 5387 loss_kpt: 0.000575 acc_pose: 0.847829 loss: 0.000575 2022/09/14 08:27:52 - mmengine - INFO - Epoch(train) [179][200/293] lr: 5.000000e-05 eta: 1:06:27 time: 0.497196 data_time: 0.076973 memory: 5387 loss_kpt: 0.000565 acc_pose: 0.902200 loss: 0.000565 2022/09/14 08:28:17 - mmengine - INFO - Epoch(train) [179][250/293] lr: 5.000000e-05 eta: 1:06:06 time: 0.503003 data_time: 0.076965 memory: 5387 loss_kpt: 0.000573 acc_pose: 0.841569 loss: 0.000573 2022/09/14 08:28:38 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 08:28:38 - mmengine - INFO - Saving checkpoint at 179 epochs 2022/09/14 08:29:08 - mmengine - INFO - Epoch(train) [180][50/293] lr: 5.000000e-05 eta: 1:05:23 time: 0.519176 data_time: 0.095913 memory: 5387 loss_kpt: 0.000564 acc_pose: 0.864381 loss: 0.000564 2022/09/14 08:29:34 - mmengine - INFO - Epoch(train) [180][100/293] lr: 5.000000e-05 eta: 1:05:02 time: 0.507483 data_time: 0.078104 memory: 5387 loss_kpt: 0.000573 acc_pose: 0.848949 loss: 0.000573 2022/09/14 08:29:59 - mmengine - INFO - Epoch(train) [180][150/293] lr: 5.000000e-05 eta: 1:04:41 time: 0.496668 data_time: 0.078873 memory: 5387 loss_kpt: 0.000574 acc_pose: 0.880801 loss: 0.000574 2022/09/14 08:30:24 - mmengine - INFO - Epoch(train) [180][200/293] lr: 5.000000e-05 eta: 1:04:19 time: 0.502830 data_time: 0.077055 memory: 5387 loss_kpt: 0.000557 acc_pose: 0.849503 loss: 0.000557 2022/09/14 08:30:49 - mmengine - INFO - Epoch(train) [180][250/293] lr: 5.000000e-05 eta: 1:03:58 time: 0.493136 data_time: 0.072138 memory: 5387 loss_kpt: 0.000566 acc_pose: 0.873961 loss: 0.000566 2022/09/14 08:31:10 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 08:31:10 - mmengine - INFO - Saving checkpoint at 180 epochs 2022/09/14 08:31:21 - mmengine - INFO - Epoch(val) [180][50/407] eta: 0:00:42 time: 0.120028 data_time: 0.013681 memory: 5387 2022/09/14 08:31:27 - mmengine - INFO - Epoch(val) [180][100/407] eta: 0:00:35 time: 0.116735 data_time: 0.010801 memory: 920 2022/09/14 08:31:32 - mmengine - INFO - Epoch(val) [180][150/407] eta: 0:00:29 time: 0.115775 data_time: 0.008528 memory: 920 2022/09/14 08:31:38 - mmengine - INFO - Epoch(val) [180][200/407] eta: 0:00:23 time: 0.112585 data_time: 0.008105 memory: 920 2022/09/14 08:31:44 - mmengine - INFO - Epoch(val) [180][250/407] eta: 0:00:17 time: 0.113713 data_time: 0.008718 memory: 920 2022/09/14 08:31:50 - mmengine - INFO - Epoch(val) [180][300/407] eta: 0:00:12 time: 0.117576 data_time: 0.011753 memory: 920 2022/09/14 08:31:55 - mmengine - INFO - Epoch(val) [180][350/407] eta: 0:00:06 time: 0.114500 data_time: 0.009148 memory: 920 2022/09/14 08:32:01 - mmengine - INFO - Epoch(val) [180][400/407] eta: 0:00:00 time: 0.109947 data_time: 0.008030 memory: 920 2022/09/14 08:32:38 - mmengine - INFO - Evaluating CocoMetric... 2022/09/14 08:32:51 - mmengine - INFO - Epoch(val) [180][407/407] coco/AP: 0.745893 coco/AP .5: 0.906713 coco/AP .75: 0.819447 coco/AP (M): 0.709743 coco/AP (L): 0.812524 coco/AR: 0.798473 coco/AR .5: 0.944112 coco/AR .75: 0.862406 coco/AR (M): 0.755258 coco/AR (L): 0.860758 2022/09/14 08:32:52 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220914/hrnet_fp16/best_coco/AP_epoch_160.pth is removed 2022/09/14 08:32:55 - mmengine - INFO - The best checkpoint with 0.7459 coco/AP at 180 epoch is saved to best_coco/AP_epoch_180.pth. 2022/09/14 08:33:20 - mmengine - INFO - Epoch(train) [181][50/293] lr: 5.000000e-05 eta: 1:03:15 time: 0.504896 data_time: 0.083135 memory: 5387 loss_kpt: 0.000549 acc_pose: 0.856211 loss: 0.000549 2022/09/14 08:33:46 - mmengine - INFO - Epoch(train) [181][100/293] lr: 5.000000e-05 eta: 1:02:54 time: 0.511743 data_time: 0.074802 memory: 5387 loss_kpt: 0.000558 acc_pose: 0.908876 loss: 0.000558 2022/09/14 08:34:11 - mmengine - INFO - Epoch(train) [181][150/293] lr: 5.000000e-05 eta: 1:02:33 time: 0.505035 data_time: 0.078364 memory: 5387 loss_kpt: 0.000565 acc_pose: 0.876038 loss: 0.000565 2022/09/14 08:34:36 - mmengine - INFO - Epoch(train) [181][200/293] lr: 5.000000e-05 eta: 1:02:12 time: 0.500422 data_time: 0.074248 memory: 5387 loss_kpt: 0.000568 acc_pose: 0.778790 loss: 0.000568 2022/09/14 08:35:01 - mmengine - INFO - Epoch(train) [181][250/293] lr: 5.000000e-05 eta: 1:01:51 time: 0.498461 data_time: 0.083473 memory: 5387 loss_kpt: 0.000566 acc_pose: 0.855502 loss: 0.000566 2022/09/14 08:35:06 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 08:35:22 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 08:35:22 - mmengine - INFO - Saving checkpoint at 181 epochs 2022/09/14 08:35:52 - mmengine - INFO - Epoch(train) [182][50/293] lr: 5.000000e-05 eta: 1:01:08 time: 0.505578 data_time: 0.084159 memory: 5387 loss_kpt: 0.000564 acc_pose: 0.838627 loss: 0.000564 2022/09/14 08:36:17 - mmengine - INFO - Epoch(train) [182][100/293] lr: 5.000000e-05 eta: 1:00:47 time: 0.500562 data_time: 0.082639 memory: 5387 loss_kpt: 0.000557 acc_pose: 0.877510 loss: 0.000557 2022/09/14 08:36:42 - mmengine - INFO - Epoch(train) [182][150/293] lr: 5.000000e-05 eta: 1:00:26 time: 0.508101 data_time: 0.075319 memory: 5387 loss_kpt: 0.000556 acc_pose: 0.817624 loss: 0.000556 2022/09/14 08:37:07 - mmengine - INFO - Epoch(train) [182][200/293] lr: 5.000000e-05 eta: 1:00:04 time: 0.503836 data_time: 0.078239 memory: 5387 loss_kpt: 0.000551 acc_pose: 0.828941 loss: 0.000551 2022/09/14 08:37:32 - mmengine - INFO - Epoch(train) [182][250/293] lr: 5.000000e-05 eta: 0:59:43 time: 0.491954 data_time: 0.070738 memory: 5387 loss_kpt: 0.000565 acc_pose: 0.827058 loss: 0.000565 2022/09/14 08:37:53 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 08:37:53 - mmengine - INFO - Saving checkpoint at 182 epochs 2022/09/14 08:38:24 - mmengine - INFO - Epoch(train) [183][50/293] lr: 5.000000e-05 eta: 0:59:00 time: 0.515799 data_time: 0.082607 memory: 5387 loss_kpt: 0.000571 acc_pose: 0.850336 loss: 0.000571 2022/09/14 08:38:49 - mmengine - INFO - Epoch(train) [183][100/293] lr: 5.000000e-05 eta: 0:58:39 time: 0.509719 data_time: 0.083132 memory: 5387 loss_kpt: 0.000549 acc_pose: 0.827388 loss: 0.000549 2022/09/14 08:39:15 - mmengine - INFO - Epoch(train) [183][150/293] lr: 5.000000e-05 eta: 0:58:18 time: 0.511502 data_time: 0.074890 memory: 5387 loss_kpt: 0.000573 acc_pose: 0.869155 loss: 0.000573 2022/09/14 08:39:40 - mmengine - INFO - Epoch(train) [183][200/293] lr: 5.000000e-05 eta: 0:57:57 time: 0.500120 data_time: 0.073526 memory: 5387 loss_kpt: 0.000560 acc_pose: 0.823487 loss: 0.000560 2022/09/14 08:40:04 - mmengine - INFO - Epoch(train) [183][250/293] lr: 5.000000e-05 eta: 0:57:36 time: 0.494955 data_time: 0.072917 memory: 5387 loss_kpt: 0.000570 acc_pose: 0.833194 loss: 0.000570 2022/09/14 08:40:26 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 08:40:26 - mmengine - INFO - Saving checkpoint at 183 epochs 2022/09/14 08:40:56 - mmengine - INFO - Epoch(train) [184][50/293] lr: 5.000000e-05 eta: 0:56:53 time: 0.512436 data_time: 0.082632 memory: 5387 loss_kpt: 0.000562 acc_pose: 0.878627 loss: 0.000562 2022/09/14 08:41:22 - mmengine - INFO - Epoch(train) [184][100/293] lr: 5.000000e-05 eta: 0:56:32 time: 0.508226 data_time: 0.074342 memory: 5387 loss_kpt: 0.000565 acc_pose: 0.832167 loss: 0.000565 2022/09/14 08:41:47 - mmengine - INFO - Epoch(train) [184][150/293] lr: 5.000000e-05 eta: 0:56:11 time: 0.497736 data_time: 0.076602 memory: 5387 loss_kpt: 0.000579 acc_pose: 0.836298 loss: 0.000579 2022/09/14 08:42:11 - mmengine - INFO - Epoch(train) [184][200/293] lr: 5.000000e-05 eta: 0:55:49 time: 0.494598 data_time: 0.078758 memory: 5387 loss_kpt: 0.000557 acc_pose: 0.823058 loss: 0.000557 2022/09/14 08:42:36 - mmengine - INFO - Epoch(train) [184][250/293] lr: 5.000000e-05 eta: 0:55:28 time: 0.497418 data_time: 0.073455 memory: 5387 loss_kpt: 0.000570 acc_pose: 0.854741 loss: 0.000570 2022/09/14 08:42:58 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 08:42:58 - mmengine - INFO - Saving checkpoint at 184 epochs 2022/09/14 08:43:28 - mmengine - INFO - Epoch(train) [185][50/293] lr: 5.000000e-05 eta: 0:54:46 time: 0.520792 data_time: 0.084784 memory: 5387 loss_kpt: 0.000578 acc_pose: 0.853787 loss: 0.000578 2022/09/14 08:43:48 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 08:43:54 - mmengine - INFO - Epoch(train) [185][100/293] lr: 5.000000e-05 eta: 0:54:24 time: 0.502251 data_time: 0.077488 memory: 5387 loss_kpt: 0.000574 acc_pose: 0.861018 loss: 0.000574 2022/09/14 08:44:17 - mmengine - INFO - Epoch(train) [185][150/293] lr: 5.000000e-05 eta: 0:54:03 time: 0.479220 data_time: 0.071210 memory: 5387 loss_kpt: 0.000557 acc_pose: 0.852629 loss: 0.000557 2022/09/14 08:44:42 - mmengine - INFO - Epoch(train) [185][200/293] lr: 5.000000e-05 eta: 0:53:42 time: 0.495860 data_time: 0.086881 memory: 5387 loss_kpt: 0.000563 acc_pose: 0.871552 loss: 0.000563 2022/09/14 08:45:08 - mmengine - INFO - Epoch(train) [185][250/293] lr: 5.000000e-05 eta: 0:53:20 time: 0.509765 data_time: 0.074471 memory: 5387 loss_kpt: 0.000556 acc_pose: 0.847940 loss: 0.000556 2022/09/14 08:45:29 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 08:45:29 - mmengine - INFO - Saving checkpoint at 185 epochs 2022/09/14 08:46:00 - mmengine - INFO - Epoch(train) [186][50/293] lr: 5.000000e-05 eta: 0:52:38 time: 0.516402 data_time: 0.086918 memory: 5387 loss_kpt: 0.000559 acc_pose: 0.874580 loss: 0.000559 2022/09/14 08:46:26 - mmengine - INFO - Epoch(train) [186][100/293] lr: 5.000000e-05 eta: 0:52:17 time: 0.510180 data_time: 0.081272 memory: 5387 loss_kpt: 0.000561 acc_pose: 0.852385 loss: 0.000561 2022/09/14 08:46:51 - mmengine - INFO - Epoch(train) [186][150/293] lr: 5.000000e-05 eta: 0:51:56 time: 0.499701 data_time: 0.074605 memory: 5387 loss_kpt: 0.000561 acc_pose: 0.854706 loss: 0.000561 2022/09/14 08:47:16 - mmengine - INFO - Epoch(train) [186][200/293] lr: 5.000000e-05 eta: 0:51:34 time: 0.498695 data_time: 0.078225 memory: 5387 loss_kpt: 0.000573 acc_pose: 0.829220 loss: 0.000573 2022/09/14 08:47:41 - mmengine - INFO - Epoch(train) [186][250/293] lr: 5.000000e-05 eta: 0:51:13 time: 0.503293 data_time: 0.078254 memory: 5387 loss_kpt: 0.000556 acc_pose: 0.837023 loss: 0.000556 2022/09/14 08:48:03 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 08:48:03 - mmengine - INFO - Saving checkpoint at 186 epochs 2022/09/14 08:48:32 - mmengine - INFO - Epoch(train) [187][50/293] lr: 5.000000e-05 eta: 0:50:31 time: 0.508192 data_time: 0.082327 memory: 5387 loss_kpt: 0.000553 acc_pose: 0.841348 loss: 0.000553 2022/09/14 08:48:58 - mmengine - INFO - Epoch(train) [187][100/293] lr: 5.000000e-05 eta: 0:50:09 time: 0.502453 data_time: 0.081431 memory: 5387 loss_kpt: 0.000565 acc_pose: 0.815011 loss: 0.000565 2022/09/14 08:49:23 - mmengine - INFO - Epoch(train) [187][150/293] lr: 5.000000e-05 eta: 0:49:48 time: 0.500676 data_time: 0.076757 memory: 5387 loss_kpt: 0.000569 acc_pose: 0.844765 loss: 0.000569 2022/09/14 08:49:48 - mmengine - INFO - Epoch(train) [187][200/293] lr: 5.000000e-05 eta: 0:49:27 time: 0.496654 data_time: 0.076244 memory: 5387 loss_kpt: 0.000558 acc_pose: 0.836491 loss: 0.000558 2022/09/14 08:50:13 - mmengine - INFO - Epoch(train) [187][250/293] lr: 5.000000e-05 eta: 0:49:06 time: 0.506642 data_time: 0.076089 memory: 5387 loss_kpt: 0.000554 acc_pose: 0.871322 loss: 0.000554 2022/09/14 08:50:34 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 08:50:34 - mmengine - INFO - Saving checkpoint at 187 epochs 2022/09/14 08:51:04 - mmengine - INFO - Epoch(train) [188][50/293] lr: 5.000000e-05 eta: 0:48:23 time: 0.509204 data_time: 0.083184 memory: 5387 loss_kpt: 0.000550 acc_pose: 0.855528 loss: 0.000550 2022/09/14 08:51:29 - mmengine - INFO - Epoch(train) [188][100/293] lr: 5.000000e-05 eta: 0:48:02 time: 0.498922 data_time: 0.076284 memory: 5387 loss_kpt: 0.000565 acc_pose: 0.844124 loss: 0.000565 2022/09/14 08:51:55 - mmengine - INFO - Epoch(train) [188][150/293] lr: 5.000000e-05 eta: 0:47:41 time: 0.512104 data_time: 0.073743 memory: 5387 loss_kpt: 0.000562 acc_pose: 0.843945 loss: 0.000562 2022/09/14 08:52:20 - mmengine - INFO - Epoch(train) [188][200/293] lr: 5.000000e-05 eta: 0:47:19 time: 0.498585 data_time: 0.077158 memory: 5387 loss_kpt: 0.000559 acc_pose: 0.833040 loss: 0.000559 2022/09/14 08:52:24 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 08:52:45 - mmengine - INFO - Epoch(train) [188][250/293] lr: 5.000000e-05 eta: 0:46:58 time: 0.501320 data_time: 0.081997 memory: 5387 loss_kpt: 0.000564 acc_pose: 0.877555 loss: 0.000564 2022/09/14 08:53:06 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 08:53:06 - mmengine - INFO - Saving checkpoint at 188 epochs 2022/09/14 08:53:36 - mmengine - INFO - Epoch(train) [189][50/293] lr: 5.000000e-05 eta: 0:46:16 time: 0.516379 data_time: 0.099034 memory: 5387 loss_kpt: 0.000563 acc_pose: 0.823942 loss: 0.000563 2022/09/14 08:54:01 - mmengine - INFO - Epoch(train) [189][100/293] lr: 5.000000e-05 eta: 0:45:55 time: 0.503976 data_time: 0.073385 memory: 5387 loss_kpt: 0.000551 acc_pose: 0.834050 loss: 0.000551 2022/09/14 08:54:26 - mmengine - INFO - Epoch(train) [189][150/293] lr: 5.000000e-05 eta: 0:45:33 time: 0.494749 data_time: 0.077138 memory: 5387 loss_kpt: 0.000561 acc_pose: 0.872340 loss: 0.000561 2022/09/14 08:54:51 - mmengine - INFO - Epoch(train) [189][200/293] lr: 5.000000e-05 eta: 0:45:12 time: 0.492888 data_time: 0.073133 memory: 5387 loss_kpt: 0.000566 acc_pose: 0.865839 loss: 0.000566 2022/09/14 08:55:16 - mmengine - INFO - Epoch(train) [189][250/293] lr: 5.000000e-05 eta: 0:44:51 time: 0.503116 data_time: 0.078511 memory: 5387 loss_kpt: 0.000567 acc_pose: 0.898721 loss: 0.000567 2022/09/14 08:55:38 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 08:55:38 - mmengine - INFO - Saving checkpoint at 189 epochs 2022/09/14 08:56:07 - mmengine - INFO - Epoch(train) [190][50/293] lr: 5.000000e-05 eta: 0:44:09 time: 0.506027 data_time: 0.085191 memory: 5387 loss_kpt: 0.000567 acc_pose: 0.824767 loss: 0.000567 2022/09/14 08:56:33 - mmengine - INFO - Epoch(train) [190][100/293] lr: 5.000000e-05 eta: 0:43:47 time: 0.523451 data_time: 0.077324 memory: 5387 loss_kpt: 0.000558 acc_pose: 0.847389 loss: 0.000558 2022/09/14 08:56:59 - mmengine - INFO - Epoch(train) [190][150/293] lr: 5.000000e-05 eta: 0:43:26 time: 0.504899 data_time: 0.080013 memory: 5387 loss_kpt: 0.000564 acc_pose: 0.806575 loss: 0.000564 2022/09/14 08:57:23 - mmengine - INFO - Epoch(train) [190][200/293] lr: 5.000000e-05 eta: 0:43:05 time: 0.493506 data_time: 0.074717 memory: 5387 loss_kpt: 0.000563 acc_pose: 0.837998 loss: 0.000563 2022/09/14 08:57:47 - mmengine - INFO - Epoch(train) [190][250/293] lr: 5.000000e-05 eta: 0:42:43 time: 0.483284 data_time: 0.074400 memory: 5387 loss_kpt: 0.000556 acc_pose: 0.861830 loss: 0.000556 2022/09/14 08:58:09 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 08:58:09 - mmengine - INFO - Saving checkpoint at 190 epochs 2022/09/14 08:58:20 - mmengine - INFO - Epoch(val) [190][50/407] eta: 0:00:44 time: 0.124771 data_time: 0.017057 memory: 5387 2022/09/14 08:58:25 - mmengine - INFO - Epoch(val) [190][100/407] eta: 0:00:35 time: 0.115078 data_time: 0.009222 memory: 920 2022/09/14 08:58:31 - mmengine - INFO - Epoch(val) [190][150/407] eta: 0:00:30 time: 0.117813 data_time: 0.011324 memory: 920 2022/09/14 08:58:37 - mmengine - INFO - Epoch(val) [190][200/407] eta: 0:00:24 time: 0.119687 data_time: 0.013570 memory: 920 2022/09/14 08:58:43 - mmengine - INFO - Epoch(val) [190][250/407] eta: 0:00:17 time: 0.113421 data_time: 0.008467 memory: 920 2022/09/14 08:58:49 - mmengine - INFO - Epoch(val) [190][300/407] eta: 0:00:12 time: 0.119158 data_time: 0.012909 memory: 920 2022/09/14 08:58:55 - mmengine - INFO - Epoch(val) [190][350/407] eta: 0:00:06 time: 0.119523 data_time: 0.010034 memory: 920 2022/09/14 08:59:00 - mmengine - INFO - Epoch(val) [190][400/407] eta: 0:00:00 time: 0.110417 data_time: 0.008015 memory: 920 2022/09/14 08:59:37 - mmengine - INFO - Evaluating CocoMetric... 2022/09/14 08:59:51 - mmengine - INFO - Epoch(val) [190][407/407] coco/AP: 0.746825 coco/AP .5: 0.906028 coco/AP .75: 0.821250 coco/AP (M): 0.710693 coco/AP (L): 0.814335 coco/AR: 0.800299 coco/AR .5: 0.944899 coco/AR .75: 0.867286 coco/AR (M): 0.757662 coco/AR (L): 0.861910 2022/09/14 08:59:51 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220914/hrnet_fp16/best_coco/AP_epoch_180.pth is removed 2022/09/14 08:59:54 - mmengine - INFO - The best checkpoint with 0.7468 coco/AP at 190 epoch is saved to best_coco/AP_epoch_190.pth. 2022/09/14 09:00:19 - mmengine - INFO - Epoch(train) [191][50/293] lr: 5.000000e-05 eta: 0:42:01 time: 0.508726 data_time: 0.082508 memory: 5387 loss_kpt: 0.000556 acc_pose: 0.845131 loss: 0.000556 2022/09/14 09:00:44 - mmengine - INFO - Epoch(train) [191][100/293] lr: 5.000000e-05 eta: 0:41:40 time: 0.501130 data_time: 0.076718 memory: 5387 loss_kpt: 0.000566 acc_pose: 0.848443 loss: 0.000566 2022/09/14 09:01:10 - mmengine - INFO - Epoch(train) [191][150/293] lr: 5.000000e-05 eta: 0:41:19 time: 0.508372 data_time: 0.075557 memory: 5387 loss_kpt: 0.000549 acc_pose: 0.867079 loss: 0.000549 2022/09/14 09:01:35 - mmengine - INFO - Epoch(train) [191][200/293] lr: 5.000000e-05 eta: 0:40:57 time: 0.505016 data_time: 0.078375 memory: 5387 loss_kpt: 0.000561 acc_pose: 0.837714 loss: 0.000561 2022/09/14 09:02:01 - mmengine - INFO - Epoch(train) [191][250/293] lr: 5.000000e-05 eta: 0:40:36 time: 0.514276 data_time: 0.078754 memory: 5387 loss_kpt: 0.000566 acc_pose: 0.859311 loss: 0.000566 2022/09/14 09:02:22 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 09:02:22 - mmengine - INFO - Saving checkpoint at 191 epochs 2022/09/14 09:02:45 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 09:02:52 - mmengine - INFO - Epoch(train) [192][50/293] lr: 5.000000e-05 eta: 0:39:54 time: 0.509052 data_time: 0.087233 memory: 5387 loss_kpt: 0.000557 acc_pose: 0.851719 loss: 0.000557 2022/09/14 09:03:17 - mmengine - INFO - Epoch(train) [192][100/293] lr: 5.000000e-05 eta: 0:39:33 time: 0.504637 data_time: 0.077358 memory: 5387 loss_kpt: 0.000554 acc_pose: 0.871182 loss: 0.000554 2022/09/14 09:03:42 - mmengine - INFO - Epoch(train) [192][150/293] lr: 5.000000e-05 eta: 0:39:11 time: 0.505566 data_time: 0.086933 memory: 5387 loss_kpt: 0.000551 acc_pose: 0.869828 loss: 0.000551 2022/09/14 09:04:07 - mmengine - INFO - Epoch(train) [192][200/293] lr: 5.000000e-05 eta: 0:38:50 time: 0.502614 data_time: 0.077574 memory: 5387 loss_kpt: 0.000559 acc_pose: 0.875306 loss: 0.000559 2022/09/14 09:04:32 - mmengine - INFO - Epoch(train) [192][250/293] lr: 5.000000e-05 eta: 0:38:29 time: 0.499098 data_time: 0.074008 memory: 5387 loss_kpt: 0.000561 acc_pose: 0.871204 loss: 0.000561 2022/09/14 09:04:53 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 09:04:53 - mmengine - INFO - Saving checkpoint at 192 epochs 2022/09/14 09:05:24 - mmengine - INFO - Epoch(train) [193][50/293] lr: 5.000000e-05 eta: 0:37:47 time: 0.508882 data_time: 0.080793 memory: 5387 loss_kpt: 0.000567 acc_pose: 0.887812 loss: 0.000567 2022/09/14 09:05:49 - mmengine - INFO - Epoch(train) [193][100/293] lr: 5.000000e-05 eta: 0:37:25 time: 0.503194 data_time: 0.081469 memory: 5387 loss_kpt: 0.000562 acc_pose: 0.895657 loss: 0.000562 2022/09/14 09:06:14 - mmengine - INFO - Epoch(train) [193][150/293] lr: 5.000000e-05 eta: 0:37:04 time: 0.501073 data_time: 0.074463 memory: 5387 loss_kpt: 0.000562 acc_pose: 0.859450 loss: 0.000562 2022/09/14 09:06:39 - mmengine - INFO - Epoch(train) [193][200/293] lr: 5.000000e-05 eta: 0:36:43 time: 0.502210 data_time: 0.078799 memory: 5387 loss_kpt: 0.000562 acc_pose: 0.803768 loss: 0.000562 2022/09/14 09:07:04 - mmengine - INFO - Epoch(train) [193][250/293] lr: 5.000000e-05 eta: 0:36:21 time: 0.501153 data_time: 0.078991 memory: 5387 loss_kpt: 0.000558 acc_pose: 0.872364 loss: 0.000558 2022/09/14 09:07:25 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 09:07:25 - mmengine - INFO - Saving checkpoint at 193 epochs 2022/09/14 09:07:55 - mmengine - INFO - Epoch(train) [194][50/293] lr: 5.000000e-05 eta: 0:35:40 time: 0.512737 data_time: 0.090466 memory: 5387 loss_kpt: 0.000557 acc_pose: 0.838007 loss: 0.000557 2022/09/14 09:08:20 - mmengine - INFO - Epoch(train) [194][100/293] lr: 5.000000e-05 eta: 0:35:18 time: 0.501595 data_time: 0.078119 memory: 5387 loss_kpt: 0.000555 acc_pose: 0.839734 loss: 0.000555 2022/09/14 09:08:44 - mmengine - INFO - Epoch(train) [194][150/293] lr: 5.000000e-05 eta: 0:34:57 time: 0.494213 data_time: 0.073929 memory: 5387 loss_kpt: 0.000552 acc_pose: 0.840752 loss: 0.000552 2022/09/14 09:09:10 - mmengine - INFO - Epoch(train) [194][200/293] lr: 5.000000e-05 eta: 0:34:35 time: 0.506218 data_time: 0.080788 memory: 5387 loss_kpt: 0.000552 acc_pose: 0.877723 loss: 0.000552 2022/09/14 09:09:35 - mmengine - INFO - Epoch(train) [194][250/293] lr: 5.000000e-05 eta: 0:34:14 time: 0.500361 data_time: 0.074645 memory: 5387 loss_kpt: 0.000558 acc_pose: 0.869178 loss: 0.000558 2022/09/14 09:09:56 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 09:09:56 - mmengine - INFO - Saving checkpoint at 194 epochs 2022/09/14 09:10:26 - mmengine - INFO - Epoch(train) [195][50/293] lr: 5.000000e-05 eta: 0:33:32 time: 0.506248 data_time: 0.081833 memory: 5387 loss_kpt: 0.000556 acc_pose: 0.864004 loss: 0.000556 2022/09/14 09:10:51 - mmengine - INFO - Epoch(train) [195][100/293] lr: 5.000000e-05 eta: 0:33:11 time: 0.497076 data_time: 0.071120 memory: 5387 loss_kpt: 0.000569 acc_pose: 0.834721 loss: 0.000569 2022/09/14 09:11:16 - mmengine - INFO - Epoch(train) [195][150/293] lr: 5.000000e-05 eta: 0:32:49 time: 0.501095 data_time: 0.085750 memory: 5387 loss_kpt: 0.000555 acc_pose: 0.846548 loss: 0.000555 2022/09/14 09:11:20 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 09:11:41 - mmengine - INFO - Epoch(train) [195][200/293] lr: 5.000000e-05 eta: 0:32:28 time: 0.499256 data_time: 0.077747 memory: 5387 loss_kpt: 0.000556 acc_pose: 0.818109 loss: 0.000556 2022/09/14 09:12:06 - mmengine - INFO - Epoch(train) [195][250/293] lr: 5.000000e-05 eta: 0:32:06 time: 0.498813 data_time: 0.079796 memory: 5387 loss_kpt: 0.000568 acc_pose: 0.851928 loss: 0.000568 2022/09/14 09:12:26 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 09:12:26 - mmengine - INFO - Saving checkpoint at 195 epochs 2022/09/14 09:12:57 - mmengine - INFO - Epoch(train) [196][50/293] lr: 5.000000e-05 eta: 0:31:25 time: 0.516394 data_time: 0.090605 memory: 5387 loss_kpt: 0.000558 acc_pose: 0.922722 loss: 0.000558 2022/09/14 09:13:21 - mmengine - INFO - Epoch(train) [196][100/293] lr: 5.000000e-05 eta: 0:31:04 time: 0.497309 data_time: 0.073849 memory: 5387 loss_kpt: 0.000567 acc_pose: 0.822470 loss: 0.000567 2022/09/14 09:13:47 - mmengine - INFO - Epoch(train) [196][150/293] lr: 5.000000e-05 eta: 0:30:42 time: 0.505378 data_time: 0.077434 memory: 5387 loss_kpt: 0.000557 acc_pose: 0.798969 loss: 0.000557 2022/09/14 09:14:12 - mmengine - INFO - Epoch(train) [196][200/293] lr: 5.000000e-05 eta: 0:30:21 time: 0.500348 data_time: 0.075645 memory: 5387 loss_kpt: 0.000565 acc_pose: 0.885616 loss: 0.000565 2022/09/14 09:14:37 - mmengine - INFO - Epoch(train) [196][250/293] lr: 5.000000e-05 eta: 0:29:59 time: 0.500580 data_time: 0.078711 memory: 5387 loss_kpt: 0.000560 acc_pose: 0.826905 loss: 0.000560 2022/09/14 09:14:58 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 09:14:58 - mmengine - INFO - Saving checkpoint at 196 epochs 2022/09/14 09:15:29 - mmengine - INFO - Epoch(train) [197][50/293] lr: 5.000000e-05 eta: 0:29:18 time: 0.511359 data_time: 0.083468 memory: 5387 loss_kpt: 0.000559 acc_pose: 0.875527 loss: 0.000559 2022/09/14 09:15:54 - mmengine - INFO - Epoch(train) [197][100/293] lr: 5.000000e-05 eta: 0:28:56 time: 0.509952 data_time: 0.076979 memory: 5387 loss_kpt: 0.000562 acc_pose: 0.843945 loss: 0.000562 2022/09/14 09:16:19 - mmengine - INFO - Epoch(train) [197][150/293] lr: 5.000000e-05 eta: 0:28:35 time: 0.501097 data_time: 0.081374 memory: 5387 loss_kpt: 0.000561 acc_pose: 0.883170 loss: 0.000561 2022/09/14 09:16:44 - mmengine - INFO - Epoch(train) [197][200/293] lr: 5.000000e-05 eta: 0:28:13 time: 0.496084 data_time: 0.076849 memory: 5387 loss_kpt: 0.000554 acc_pose: 0.871793 loss: 0.000554 2022/09/14 09:17:09 - mmengine - INFO - Epoch(train) [197][250/293] lr: 5.000000e-05 eta: 0:27:52 time: 0.498547 data_time: 0.076456 memory: 5387 loss_kpt: 0.000564 acc_pose: 0.867256 loss: 0.000564 2022/09/14 09:17:30 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 09:17:30 - mmengine - INFO - Saving checkpoint at 197 epochs 2022/09/14 09:18:00 - mmengine - INFO - Epoch(train) [198][50/293] lr: 5.000000e-05 eta: 0:27:11 time: 0.506887 data_time: 0.089889 memory: 5387 loss_kpt: 0.000562 acc_pose: 0.873108 loss: 0.000562 2022/09/14 09:18:25 - mmengine - INFO - Epoch(train) [198][100/293] lr: 5.000000e-05 eta: 0:26:49 time: 0.499111 data_time: 0.076301 memory: 5387 loss_kpt: 0.000573 acc_pose: 0.875114 loss: 0.000573 2022/09/14 09:18:50 - mmengine - INFO - Epoch(train) [198][150/293] lr: 5.000000e-05 eta: 0:26:28 time: 0.503133 data_time: 0.075784 memory: 5387 loss_kpt: 0.000555 acc_pose: 0.843110 loss: 0.000555 2022/09/14 09:19:16 - mmengine - INFO - Epoch(train) [198][200/293] lr: 5.000000e-05 eta: 0:26:06 time: 0.517050 data_time: 0.082877 memory: 5387 loss_kpt: 0.000558 acc_pose: 0.860331 loss: 0.000558 2022/09/14 09:19:41 - mmengine - INFO - Epoch(train) [198][250/293] lr: 5.000000e-05 eta: 0:25:45 time: 0.508249 data_time: 0.077531 memory: 5387 loss_kpt: 0.000555 acc_pose: 0.892060 loss: 0.000555 2022/09/14 09:19:56 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 09:20:03 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 09:20:03 - mmengine - INFO - Saving checkpoint at 198 epochs 2022/09/14 09:20:33 - mmengine - INFO - Epoch(train) [199][50/293] lr: 5.000000e-05 eta: 0:25:03 time: 0.507632 data_time: 0.084118 memory: 5387 loss_kpt: 0.000549 acc_pose: 0.883621 loss: 0.000549 2022/09/14 09:20:57 - mmengine - INFO - Epoch(train) [199][100/293] lr: 5.000000e-05 eta: 0:24:42 time: 0.499155 data_time: 0.072937 memory: 5387 loss_kpt: 0.000549 acc_pose: 0.809692 loss: 0.000549 2022/09/14 09:21:23 - mmengine - INFO - Epoch(train) [199][150/293] lr: 5.000000e-05 eta: 0:24:20 time: 0.501788 data_time: 0.076364 memory: 5387 loss_kpt: 0.000555 acc_pose: 0.881904 loss: 0.000555 2022/09/14 09:21:47 - mmengine - INFO - Epoch(train) [199][200/293] lr: 5.000000e-05 eta: 0:23:59 time: 0.492696 data_time: 0.080411 memory: 5387 loss_kpt: 0.000557 acc_pose: 0.891101 loss: 0.000557 2022/09/14 09:22:12 - mmengine - INFO - Epoch(train) [199][250/293] lr: 5.000000e-05 eta: 0:23:37 time: 0.501602 data_time: 0.076785 memory: 5387 loss_kpt: 0.000559 acc_pose: 0.877299 loss: 0.000559 2022/09/14 09:22:34 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 09:22:34 - mmengine - INFO - Saving checkpoint at 199 epochs 2022/09/14 09:23:04 - mmengine - INFO - Epoch(train) [200][50/293] lr: 5.000000e-05 eta: 0:22:56 time: 0.523593 data_time: 0.085324 memory: 5387 loss_kpt: 0.000557 acc_pose: 0.855085 loss: 0.000557 2022/09/14 09:23:29 - mmengine - INFO - Epoch(train) [200][100/293] lr: 5.000000e-05 eta: 0:22:35 time: 0.490329 data_time: 0.073937 memory: 5387 loss_kpt: 0.000565 acc_pose: 0.880484 loss: 0.000565 2022/09/14 09:23:55 - mmengine - INFO - Epoch(train) [200][150/293] lr: 5.000000e-05 eta: 0:22:13 time: 0.510599 data_time: 0.078414 memory: 5387 loss_kpt: 0.000558 acc_pose: 0.851301 loss: 0.000558 2022/09/14 09:24:20 - mmengine - INFO - Epoch(train) [200][200/293] lr: 5.000000e-05 eta: 0:21:52 time: 0.502245 data_time: 0.072831 memory: 5387 loss_kpt: 0.000545 acc_pose: 0.858968 loss: 0.000545 2022/09/14 09:24:45 - mmengine - INFO - Epoch(train) [200][250/293] lr: 5.000000e-05 eta: 0:21:30 time: 0.507253 data_time: 0.090851 memory: 5387 loss_kpt: 0.000558 acc_pose: 0.820020 loss: 0.000558 2022/09/14 09:25:07 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 09:25:07 - mmengine - INFO - Saving checkpoint at 200 epochs 2022/09/14 09:25:17 - mmengine - INFO - Epoch(val) [200][50/407] eta: 0:00:43 time: 0.120617 data_time: 0.014511 memory: 5387 2022/09/14 09:25:23 - mmengine - INFO - Epoch(val) [200][100/407] eta: 0:00:35 time: 0.116262 data_time: 0.010350 memory: 920 2022/09/14 09:25:29 - mmengine - INFO - Epoch(val) [200][150/407] eta: 0:00:28 time: 0.112528 data_time: 0.008209 memory: 920 2022/09/14 09:25:35 - mmengine - INFO - Epoch(val) [200][200/407] eta: 0:00:24 time: 0.118674 data_time: 0.013135 memory: 920 2022/09/14 09:25:40 - mmengine - INFO - Epoch(val) [200][250/407] eta: 0:00:18 time: 0.115312 data_time: 0.009014 memory: 920 2022/09/14 09:25:46 - mmengine - INFO - Epoch(val) [200][300/407] eta: 0:00:12 time: 0.114294 data_time: 0.009899 memory: 920 2022/09/14 09:25:52 - mmengine - INFO - Epoch(val) [200][350/407] eta: 0:00:06 time: 0.113860 data_time: 0.009284 memory: 920 2022/09/14 09:25:57 - mmengine - INFO - Epoch(val) [200][400/407] eta: 0:00:00 time: 0.115232 data_time: 0.011951 memory: 920 2022/09/14 09:26:34 - mmengine - INFO - Evaluating CocoMetric... 2022/09/14 09:26:47 - mmengine - INFO - Epoch(val) [200][407/407] coco/AP: 0.747505 coco/AP .5: 0.906478 coco/AP .75: 0.820889 coco/AP (M): 0.711386 coco/AP (L): 0.815805 coco/AR: 0.800409 coco/AR .5: 0.944270 coco/AR .75: 0.864452 coco/AR (M): 0.757361 coco/AR (L): 0.862913 2022/09/14 09:26:47 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220914/hrnet_fp16/best_coco/AP_epoch_190.pth is removed 2022/09/14 09:26:51 - mmengine - INFO - The best checkpoint with 0.7475 coco/AP at 200 epoch is saved to best_coco/AP_epoch_200.pth. 2022/09/14 09:27:15 - mmengine - INFO - Epoch(train) [201][50/293] lr: 5.000000e-06 eta: 0:20:49 time: 0.496375 data_time: 0.077835 memory: 5387 loss_kpt: 0.000564 acc_pose: 0.840650 loss: 0.000564 2022/09/14 09:27:42 - mmengine - INFO - Epoch(train) [201][100/293] lr: 5.000000e-06 eta: 0:20:27 time: 0.525093 data_time: 0.086753 memory: 5387 loss_kpt: 0.000558 acc_pose: 0.887636 loss: 0.000558 2022/09/14 09:28:06 - mmengine - INFO - Epoch(train) [201][150/293] lr: 5.000000e-06 eta: 0:20:06 time: 0.496815 data_time: 0.077021 memory: 5387 loss_kpt: 0.000561 acc_pose: 0.831580 loss: 0.000561 2022/09/14 09:28:31 - mmengine - INFO - Epoch(train) [201][200/293] lr: 5.000000e-06 eta: 0:19:44 time: 0.492219 data_time: 0.081073 memory: 5387 loss_kpt: 0.000552 acc_pose: 0.864078 loss: 0.000552 2022/09/14 09:28:56 - mmengine - INFO - Epoch(train) [201][250/293] lr: 5.000000e-06 eta: 0:19:23 time: 0.491163 data_time: 0.073626 memory: 5387 loss_kpt: 0.000546 acc_pose: 0.882559 loss: 0.000546 2022/09/14 09:29:17 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 09:29:17 - mmengine - INFO - Saving checkpoint at 201 epochs 2022/09/14 09:29:48 - mmengine - INFO - Epoch(train) [202][50/293] lr: 5.000000e-06 eta: 0:18:42 time: 0.509960 data_time: 0.090692 memory: 5387 loss_kpt: 0.000535 acc_pose: 0.881212 loss: 0.000535 2022/09/14 09:30:12 - mmengine - INFO - Epoch(train) [202][100/293] lr: 5.000000e-06 eta: 0:18:20 time: 0.493862 data_time: 0.078046 memory: 5387 loss_kpt: 0.000549 acc_pose: 0.823479 loss: 0.000549 2022/09/14 09:30:16 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 09:30:37 - mmengine - INFO - Epoch(train) [202][150/293] lr: 5.000000e-06 eta: 0:17:59 time: 0.502641 data_time: 0.075292 memory: 5387 loss_kpt: 0.000549 acc_pose: 0.894629 loss: 0.000549 2022/09/14 09:31:02 - mmengine - INFO - Epoch(train) [202][200/293] lr: 5.000000e-06 eta: 0:17:37 time: 0.500668 data_time: 0.076057 memory: 5387 loss_kpt: 0.000568 acc_pose: 0.873135 loss: 0.000568 2022/09/14 09:31:27 - mmengine - INFO - Epoch(train) [202][250/293] lr: 5.000000e-06 eta: 0:17:16 time: 0.500093 data_time: 0.080109 memory: 5387 loss_kpt: 0.000534 acc_pose: 0.912601 loss: 0.000534 2022/09/14 09:31:49 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 09:31:49 - mmengine - INFO - Saving checkpoint at 202 epochs 2022/09/14 09:32:18 - mmengine - INFO - Epoch(train) [203][50/293] lr: 5.000000e-06 eta: 0:16:35 time: 0.502522 data_time: 0.079641 memory: 5387 loss_kpt: 0.000555 acc_pose: 0.785820 loss: 0.000555 2022/09/14 09:32:43 - mmengine - INFO - Epoch(train) [203][100/293] lr: 5.000000e-06 eta: 0:16:13 time: 0.496113 data_time: 0.076467 memory: 5387 loss_kpt: 0.000552 acc_pose: 0.824589 loss: 0.000552 2022/09/14 09:33:08 - mmengine - INFO - Epoch(train) [203][150/293] lr: 5.000000e-06 eta: 0:15:51 time: 0.499582 data_time: 0.078196 memory: 5387 loss_kpt: 0.000554 acc_pose: 0.862802 loss: 0.000554 2022/09/14 09:33:33 - mmengine - INFO - Epoch(train) [203][200/293] lr: 5.000000e-06 eta: 0:15:30 time: 0.505475 data_time: 0.074803 memory: 5387 loss_kpt: 0.000558 acc_pose: 0.882311 loss: 0.000558 2022/09/14 09:33:58 - mmengine - INFO - Epoch(train) [203][250/293] lr: 5.000000e-06 eta: 0:15:08 time: 0.492751 data_time: 0.078800 memory: 5387 loss_kpt: 0.000542 acc_pose: 0.841224 loss: 0.000542 2022/09/14 09:34:19 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 09:34:19 - mmengine - INFO - Saving checkpoint at 203 epochs 2022/09/14 09:34:50 - mmengine - INFO - Epoch(train) [204][50/293] lr: 5.000000e-06 eta: 0:14:27 time: 0.514460 data_time: 0.087352 memory: 5387 loss_kpt: 0.000569 acc_pose: 0.816233 loss: 0.000569 2022/09/14 09:35:14 - mmengine - INFO - Epoch(train) [204][100/293] lr: 5.000000e-06 eta: 0:14:06 time: 0.495688 data_time: 0.073899 memory: 5387 loss_kpt: 0.000556 acc_pose: 0.819574 loss: 0.000556 2022/09/14 09:35:40 - mmengine - INFO - Epoch(train) [204][150/293] lr: 5.000000e-06 eta: 0:13:44 time: 0.506008 data_time: 0.074628 memory: 5387 loss_kpt: 0.000560 acc_pose: 0.812635 loss: 0.000560 2022/09/14 09:36:05 - mmengine - INFO - Epoch(train) [204][200/293] lr: 5.000000e-06 eta: 0:13:23 time: 0.514821 data_time: 0.077319 memory: 5387 loss_kpt: 0.000549 acc_pose: 0.875750 loss: 0.000549 2022/09/14 09:36:31 - mmengine - INFO - Epoch(train) [204][250/293] lr: 5.000000e-06 eta: 0:13:01 time: 0.510676 data_time: 0.079137 memory: 5387 loss_kpt: 0.000558 acc_pose: 0.882748 loss: 0.000558 2022/09/14 09:36:52 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 09:36:52 - mmengine - INFO - Saving checkpoint at 204 epochs 2022/09/14 09:37:22 - mmengine - INFO - Epoch(train) [205][50/293] lr: 5.000000e-06 eta: 0:12:20 time: 0.506878 data_time: 0.078969 memory: 5387 loss_kpt: 0.000569 acc_pose: 0.854600 loss: 0.000569 2022/09/14 09:37:47 - mmengine - INFO - Epoch(train) [205][100/293] lr: 5.000000e-06 eta: 0:11:59 time: 0.496165 data_time: 0.078931 memory: 5387 loss_kpt: 0.000547 acc_pose: 0.823118 loss: 0.000547 2022/09/14 09:38:12 - mmengine - INFO - Epoch(train) [205][150/293] lr: 5.000000e-06 eta: 0:11:37 time: 0.502447 data_time: 0.072353 memory: 5387 loss_kpt: 0.000572 acc_pose: 0.876014 loss: 0.000572 2022/09/14 09:38:37 - mmengine - INFO - Epoch(train) [205][200/293] lr: 5.000000e-06 eta: 0:11:16 time: 0.507391 data_time: 0.079876 memory: 5387 loss_kpt: 0.000545 acc_pose: 0.862290 loss: 0.000545 2022/09/14 09:38:51 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 09:39:02 - mmengine - INFO - Epoch(train) [205][250/293] lr: 5.000000e-06 eta: 0:10:54 time: 0.498469 data_time: 0.072793 memory: 5387 loss_kpt: 0.000553 acc_pose: 0.871034 loss: 0.000553 2022/09/14 09:39:23 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 09:39:23 - mmengine - INFO - Saving checkpoint at 205 epochs 2022/09/14 09:39:54 - mmengine - INFO - Epoch(train) [206][50/293] lr: 5.000000e-06 eta: 0:10:13 time: 0.509841 data_time: 0.088731 memory: 5387 loss_kpt: 0.000550 acc_pose: 0.837394 loss: 0.000550 2022/09/14 09:40:19 - mmengine - INFO - Epoch(train) [206][100/293] lr: 5.000000e-06 eta: 0:09:52 time: 0.498801 data_time: 0.076985 memory: 5387 loss_kpt: 0.000563 acc_pose: 0.871790 loss: 0.000563 2022/09/14 09:40:44 - mmengine - INFO - Epoch(train) [206][150/293] lr: 5.000000e-06 eta: 0:09:30 time: 0.505974 data_time: 0.080337 memory: 5387 loss_kpt: 0.000550 acc_pose: 0.874021 loss: 0.000550 2022/09/14 09:41:09 - mmengine - INFO - Epoch(train) [206][200/293] lr: 5.000000e-06 eta: 0:09:08 time: 0.493749 data_time: 0.072563 memory: 5387 loss_kpt: 0.000544 acc_pose: 0.846457 loss: 0.000544 2022/09/14 09:41:34 - mmengine - INFO - Epoch(train) [206][250/293] lr: 5.000000e-06 eta: 0:08:47 time: 0.499458 data_time: 0.084140 memory: 5387 loss_kpt: 0.000564 acc_pose: 0.913783 loss: 0.000564 2022/09/14 09:41:55 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 09:41:55 - mmengine - INFO - Saving checkpoint at 206 epochs 2022/09/14 09:42:25 - mmengine - INFO - Epoch(train) [207][50/293] lr: 5.000000e-06 eta: 0:08:06 time: 0.510633 data_time: 0.079926 memory: 5387 loss_kpt: 0.000558 acc_pose: 0.827834 loss: 0.000558 2022/09/14 09:42:50 - mmengine - INFO - Epoch(train) [207][100/293] lr: 5.000000e-06 eta: 0:07:44 time: 0.499109 data_time: 0.080962 memory: 5387 loss_kpt: 0.000549 acc_pose: 0.862776 loss: 0.000549 2022/09/14 09:43:16 - mmengine - INFO - Epoch(train) [207][150/293] lr: 5.000000e-06 eta: 0:07:23 time: 0.507178 data_time: 0.074787 memory: 5387 loss_kpt: 0.000551 acc_pose: 0.841456 loss: 0.000551 2022/09/14 09:43:40 - mmengine - INFO - Epoch(train) [207][200/293] lr: 5.000000e-06 eta: 0:07:01 time: 0.487749 data_time: 0.075994 memory: 5387 loss_kpt: 0.000560 acc_pose: 0.865474 loss: 0.000560 2022/09/14 09:44:05 - mmengine - INFO - Epoch(train) [207][250/293] lr: 5.000000e-06 eta: 0:06:40 time: 0.501655 data_time: 0.076160 memory: 5387 loss_kpt: 0.000552 acc_pose: 0.876022 loss: 0.000552 2022/09/14 09:44:26 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 09:44:27 - mmengine - INFO - Saving checkpoint at 207 epochs 2022/09/14 09:44:57 - mmengine - INFO - Epoch(train) [208][50/293] lr: 5.000000e-06 eta: 0:05:59 time: 0.523045 data_time: 0.092101 memory: 5387 loss_kpt: 0.000552 acc_pose: 0.897571 loss: 0.000552 2022/09/14 09:45:23 - mmengine - INFO - Epoch(train) [208][100/293] lr: 5.000000e-06 eta: 0:05:37 time: 0.510063 data_time: 0.079775 memory: 5387 loss_kpt: 0.000545 acc_pose: 0.867445 loss: 0.000545 2022/09/14 09:45:48 - mmengine - INFO - Epoch(train) [208][150/293] lr: 5.000000e-06 eta: 0:05:16 time: 0.505253 data_time: 0.076602 memory: 5387 loss_kpt: 0.000571 acc_pose: 0.870256 loss: 0.000571 2022/09/14 09:46:13 - mmengine - INFO - Epoch(train) [208][200/293] lr: 5.000000e-06 eta: 0:04:54 time: 0.502568 data_time: 0.073082 memory: 5387 loss_kpt: 0.000559 acc_pose: 0.864659 loss: 0.000559 2022/09/14 09:46:39 - mmengine - INFO - Epoch(train) [208][250/293] lr: 5.000000e-06 eta: 0:04:32 time: 0.508600 data_time: 0.079116 memory: 5387 loss_kpt: 0.000548 acc_pose: 0.910324 loss: 0.000548 2022/09/14 09:46:59 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 09:46:59 - mmengine - INFO - Saving checkpoint at 208 epochs 2022/09/14 09:47:29 - mmengine - INFO - Epoch(train) [209][50/293] lr: 5.000000e-06 eta: 0:03:52 time: 0.514410 data_time: 0.090123 memory: 5387 loss_kpt: 0.000553 acc_pose: 0.828677 loss: 0.000553 2022/09/14 09:47:32 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 09:47:55 - mmengine - INFO - Epoch(train) [209][100/293] lr: 5.000000e-06 eta: 0:03:30 time: 0.500359 data_time: 0.076306 memory: 5387 loss_kpt: 0.000566 acc_pose: 0.858624 loss: 0.000566 2022/09/14 09:48:20 - mmengine - INFO - Epoch(train) [209][150/293] lr: 5.000000e-06 eta: 0:03:09 time: 0.519012 data_time: 0.077693 memory: 5387 loss_kpt: 0.000554 acc_pose: 0.846859 loss: 0.000554 2022/09/14 09:48:46 - mmengine - INFO - Epoch(train) [209][200/293] lr: 5.000000e-06 eta: 0:02:47 time: 0.510291 data_time: 0.076288 memory: 5387 loss_kpt: 0.000556 acc_pose: 0.830411 loss: 0.000556 2022/09/14 09:49:11 - mmengine - INFO - Epoch(train) [209][250/293] lr: 5.000000e-06 eta: 0:02:25 time: 0.498099 data_time: 0.071803 memory: 5387 loss_kpt: 0.000550 acc_pose: 0.846747 loss: 0.000550 2022/09/14 09:49:33 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 09:49:33 - mmengine - INFO - Saving checkpoint at 209 epochs 2022/09/14 09:50:03 - mmengine - INFO - Epoch(train) [210][50/293] lr: 5.000000e-06 eta: 0:01:45 time: 0.502585 data_time: 0.082449 memory: 5387 loss_kpt: 0.000551 acc_pose: 0.760224 loss: 0.000551 2022/09/14 09:50:28 - mmengine - INFO - Epoch(train) [210][100/293] lr: 5.000000e-06 eta: 0:01:23 time: 0.509926 data_time: 0.079042 memory: 5387 loss_kpt: 0.000544 acc_pose: 0.843561 loss: 0.000544 2022/09/14 09:50:54 - mmengine - INFO - Epoch(train) [210][150/293] lr: 5.000000e-06 eta: 0:01:02 time: 0.509869 data_time: 0.071810 memory: 5387 loss_kpt: 0.000551 acc_pose: 0.834052 loss: 0.000551 2022/09/14 09:51:19 - mmengine - INFO - Epoch(train) [210][200/293] lr: 5.000000e-06 eta: 0:00:40 time: 0.509146 data_time: 0.078303 memory: 5387 loss_kpt: 0.000547 acc_pose: 0.866031 loss: 0.000547 2022/09/14 09:51:44 - mmengine - INFO - Epoch(train) [210][250/293] lr: 5.000000e-06 eta: 0:00:18 time: 0.498059 data_time: 0.079208 memory: 5387 loss_kpt: 0.000552 acc_pose: 0.868602 loss: 0.000552 2022/09/14 09:52:05 - mmengine - INFO - Exp name: td-hm_hrnet-w32_fp16-8xb64-210e_coco-256x192_20220914_002034 2022/09/14 09:52:05 - mmengine - INFO - Saving checkpoint at 210 epochs 2022/09/14 09:52:16 - mmengine - INFO - Epoch(val) [210][50/407] eta: 0:00:43 time: 0.122361 data_time: 0.014714 memory: 5387 2022/09/14 09:52:22 - mmengine - INFO - Epoch(val) [210][100/407] eta: 0:00:36 time: 0.119015 data_time: 0.010871 memory: 920 2022/09/14 09:52:28 - mmengine - INFO - Epoch(val) [210][150/407] eta: 0:00:31 time: 0.122590 data_time: 0.009726 memory: 920 2022/09/14 09:52:34 - mmengine - INFO - Epoch(val) [210][200/407] eta: 0:00:24 time: 0.117988 data_time: 0.009715 memory: 920 2022/09/14 09:52:40 - mmengine - INFO - Epoch(val) [210][250/407] eta: 0:00:18 time: 0.118841 data_time: 0.009708 memory: 920 2022/09/14 09:52:46 - mmengine - INFO - Epoch(val) [210][300/407] eta: 0:00:12 time: 0.120063 data_time: 0.010018 memory: 920 2022/09/14 09:52:52 - mmengine - INFO - Epoch(val) [210][350/407] eta: 0:00:06 time: 0.119447 data_time: 0.011012 memory: 920 2022/09/14 09:52:58 - mmengine - INFO - Epoch(val) [210][400/407] eta: 0:00:00 time: 0.109526 data_time: 0.007362 memory: 920 2022/09/14 09:53:35 - mmengine - INFO - Evaluating CocoMetric... 2022/09/14 09:53:49 - mmengine - INFO - Epoch(val) [210][407/407] coco/AP: 0.748912 coco/AP .5: 0.907057 coco/AP .75: 0.822150 coco/AP (M): 0.711816 coco/AP (L): 0.817159 coco/AR: 0.801795 coco/AR .5: 0.945529 coco/AR .75: 0.866026 coco/AR (M): 0.759028 coco/AR (L): 0.863805 2022/09/14 09:53:49 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220914/hrnet_fp16/best_coco/AP_epoch_200.pth is removed 2022/09/14 09:53:52 - mmengine - INFO - The best checkpoint with 0.7489 coco/AP at 210 epoch is saved to best_coco/AP_epoch_210.pth.