2022/09/14 15:24:08 - 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: 1320352793 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 15:24:10 - mmengine - INFO - Config: default_scope = 'mmpose' default_hooks = dict( timer=dict(type='IterTimerHook'), logger=dict(type='LoggerHook', interval=50), param_scheduler=dict(type='ParamSchedulerHook'), checkpoint=dict( type='CheckpointHook', interval=1, save_best='coco/AP', rule='greater', max_keep_ckpts=1), sampler_seed=dict(type='DistSamplerSeedHook'), visualization=dict(type='PoseVisualizationHook', enable=False)) custom_hooks = [dict(type='SyncBuffersHook')] env_cfg = dict( cudnn_benchmark=False, mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0), dist_cfg=dict(backend='nccl')) vis_backends = [dict(type='LocalVisBackend')] visualizer = dict( type='PoseLocalVisualizer', vis_backends=[dict(type='LocalVisBackend')], name='visualizer') log_processor = dict( type='LogProcessor', window_size=50, by_epoch=True, num_digits=6) log_level = 'INFO' load_from = None resume = False file_client_args = dict( backend='petrel', path_mapping=dict({ './data/': 's3://openmmlab/datasets/detection/', 'data/': 's3://openmmlab/datasets/detection/' })) train_cfg = dict(by_epoch=True, max_epochs=210, val_interval=10) val_cfg = dict() test_cfg = dict() optim_wrapper = dict(optimizer=dict(type='Adam', lr=0.0005)) param_scheduler = [ dict( type='LinearLR', begin=0, end=500, start_factor=0.001, by_epoch=False), dict( type='MultiStepLR', begin=0, end=210, milestones=[170, 200], gamma=0.1, by_epoch=True) ] auto_scale_lr = dict(base_batch_size=512) codec = dict( type='MSRAHeatmap', input_size=(288, 384), heatmap_size=(72, 96), sigma=3) 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=(48, 96)), stage3=dict( num_modules=4, num_branches=3, block='BASIC', num_blocks=(4, 4, 4), num_channels=(48, 96, 192)), stage4=dict( num_modules=3, num_branches=4, block='BASIC', num_blocks=(4, 4, 4, 4), num_channels=(48, 96, 192, 384))), init_cfg=dict( type='Pretrained', checkpoint= 'https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth' )), head=dict( type='HeatmapHead', in_channels=48, out_channels=17, deconv_out_channels=None, loss=dict(type='KeypointMSELoss', use_target_weight=True), decoder=dict( type='MSRAHeatmap', input_size=(288, 384), heatmap_size=(72, 96), sigma=3)), test_cfg=dict(flip_test=True, flip_mode='heatmap', shift_heatmap=True)) dataset_type = 'CocoDataset' data_mode = 'topdown' data_root = 'data/coco/' train_pipeline = [ dict( type='LoadImage', file_client_args=dict( backend='petrel', path_mapping=dict({ './data/': 's3://openmmlab/datasets/detection/', 'data/': 's3://openmmlab/datasets/detection/' }))), dict(type='GetBBoxCenterScale'), dict(type='RandomFlip', direction='horizontal'), dict(type='RandomHalfBody'), dict(type='RandomBBoxTransform'), dict(type='TopdownAffine', input_size=(288, 384)), dict( type='GenerateTarget', target_type='heatmap', encoder=dict( type='MSRAHeatmap', input_size=(288, 384), heatmap_size=(72, 96), sigma=3)), dict(type='PackPoseInputs') ] test_pipeline = [ dict( type='LoadImage', file_client_args=dict( backend='petrel', path_mapping=dict({ './data/': 's3://openmmlab/datasets/detection/', 'data/': 's3://openmmlab/datasets/detection/' }))), dict(type='GetBBoxCenterScale'), dict(type='TopdownAffine', input_size=(288, 384)), dict(type='PackPoseInputs') ] train_dataloader = dict( batch_size=32, num_workers=2, persistent_workers=True, sampler=dict(type='DefaultSampler', shuffle=True), dataset=dict( type='CocoDataset', data_root='data/coco/', data_mode='topdown', ann_file='annotations/person_keypoints_train2017.json', data_prefix=dict(img='train2017/'), pipeline=[ dict( type='LoadImage', file_client_args=dict( backend='petrel', path_mapping=dict({ './data/': 's3://openmmlab/datasets/detection/', 'data/': 's3://openmmlab/datasets/detection/' }))), dict(type='GetBBoxCenterScale'), dict(type='RandomFlip', direction='horizontal'), dict(type='RandomHalfBody'), dict(type='RandomBBoxTransform'), dict(type='TopdownAffine', input_size=(288, 384)), dict( type='GenerateTarget', target_type='heatmap', encoder=dict( type='MSRAHeatmap', input_size=(288, 384), heatmap_size=(72, 96), sigma=3)), dict(type='PackPoseInputs') ])) val_dataloader = dict( batch_size=32, num_workers=2, persistent_workers=True, drop_last=False, sampler=dict(type='DefaultSampler', shuffle=False, round_up=False), dataset=dict( type='CocoDataset', data_root='data/coco/', data_mode='topdown', ann_file='annotations/person_keypoints_val2017.json', bbox_file= 'data/coco/person_detection_results/COCO_val2017_detections_AP_H_56_person.json', data_prefix=dict(img='val2017/'), test_mode=True, pipeline=[ dict( type='LoadImage', file_client_args=dict( backend='petrel', path_mapping=dict({ './data/': 's3://openmmlab/datasets/detection/', 'data/': 's3://openmmlab/datasets/detection/' }))), dict(type='GetBBoxCenterScale'), dict(type='TopdownAffine', input_size=(288, 384)), dict(type='PackPoseInputs') ])) test_dataloader = dict( batch_size=32, num_workers=2, persistent_workers=True, drop_last=False, sampler=dict(type='DefaultSampler', shuffle=False, round_up=False), dataset=dict( type='CocoDataset', data_root='data/coco/', data_mode='topdown', ann_file='annotations/person_keypoints_val2017.json', bbox_file= 'data/coco/person_detection_results/COCO_val2017_detections_AP_H_56_person.json', data_prefix=dict(img='val2017/'), test_mode=True, pipeline=[ dict( type='LoadImage', file_client_args=dict( backend='petrel', path_mapping=dict({ './data/': 's3://openmmlab/datasets/detection/', 'data/': 's3://openmmlab/datasets/detection/' }))), dict(type='GetBBoxCenterScale'), dict(type='TopdownAffine', input_size=(288, 384)), dict(type='PackPoseInputs') ])) val_evaluator = dict( type='CocoMetric', ann_file='data/coco/annotations/person_keypoints_val2017.json') test_evaluator = dict( type='CocoMetric', ann_file='data/coco/annotations/person_keypoints_val2017.json') launcher = 'slurm' work_dir = '/mnt/lustre/liqikai/work_dirs/20220914/hrnet_w48_384/' 2022/09/14 15:24:46 - 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 15:24:46 - 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 15:24:46 - 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 15:24:46 - 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 15:24:46 - 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 15:24:46 - 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 15:24:46 - 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 15:24:46 - 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 15:24:49 - 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 15:24:52 - 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 15:24:53 - 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 15:24:53 - 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_w48-8ef0771d.pth backbone.bn1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.bn1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.bn2.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.bn2.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.layer1.0.conv1.weight - torch.Size([64, 64, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.layer1.0.bn1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.layer1.0.bn1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.layer1.0.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.layer1.0.bn2.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.layer1.0.bn2.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.layer1.0.conv3.weight - torch.Size([256, 64, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.layer1.0.bn3.weight - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.layer1.0.bn3.bias - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.layer1.0.downsample.0.weight - torch.Size([256, 64, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.layer1.0.downsample.1.weight - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.layer1.0.downsample.1.bias - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.layer1.1.conv1.weight - torch.Size([64, 256, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.layer1.1.bn1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.layer1.1.bn1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.layer1.1.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.layer1.1.bn2.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.layer1.1.bn2.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.layer1.1.conv3.weight - torch.Size([256, 64, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.layer1.1.bn3.weight - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.layer1.1.bn3.bias - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.layer1.2.conv1.weight - torch.Size([64, 256, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.layer1.2.bn1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.layer1.2.bn1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.layer1.2.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.layer1.2.bn2.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.layer1.2.bn2.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.layer1.2.conv3.weight - torch.Size([256, 64, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.layer1.2.bn3.weight - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.layer1.2.bn3.bias - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.layer1.3.conv1.weight - torch.Size([64, 256, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.layer1.3.bn1.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.layer1.3.bn1.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.layer1.3.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.layer1.3.bn2.weight - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.layer1.3.bn2.bias - torch.Size([64]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.layer1.3.conv3.weight - torch.Size([256, 64, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.layer1.3.bn3.weight - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.layer1.3.bn3.bias - torch.Size([256]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.transition1.0.0.weight - torch.Size([48, 256, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.transition1.0.1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.transition1.0.1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.transition1.1.0.0.weight - torch.Size([96, 256, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.transition1.1.0.1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.transition1.1.0.1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.branches.0.0.conv1.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.branches.0.0.bn1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.branches.0.0.bn1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.branches.0.0.conv2.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.branches.0.0.bn2.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.branches.0.0.bn2.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.branches.0.1.conv1.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.branches.0.1.bn1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.branches.0.1.bn1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.branches.0.1.conv2.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.branches.0.1.bn2.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.branches.0.1.bn2.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.branches.0.2.conv1.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.branches.0.2.bn1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.branches.0.2.bn1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.branches.0.2.conv2.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.branches.0.2.bn2.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.branches.0.2.bn2.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.branches.0.3.conv1.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.branches.0.3.bn1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.branches.0.3.bn1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.branches.0.3.conv2.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.branches.0.3.bn2.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.branches.0.3.bn2.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.branches.1.0.conv1.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.branches.1.0.bn1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.branches.1.0.bn1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.branches.1.0.conv2.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.branches.1.0.bn2.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.branches.1.0.bn2.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.branches.1.1.conv1.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.branches.1.1.bn1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.branches.1.1.bn1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.branches.1.1.conv2.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.branches.1.1.bn2.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.branches.1.1.bn2.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.branches.1.2.conv1.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.branches.1.2.bn1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.branches.1.2.bn1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.branches.1.2.conv2.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.branches.1.2.bn2.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.branches.1.2.bn2.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.branches.1.3.conv1.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.branches.1.3.bn1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.branches.1.3.bn1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.branches.1.3.conv2.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.branches.1.3.bn2.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.branches.1.3.bn2.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.fuse_layers.0.1.0.weight - torch.Size([48, 96, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.fuse_layers.0.1.1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.fuse_layers.0.1.1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.fuse_layers.1.0.0.0.weight - torch.Size([96, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.fuse_layers.1.0.0.1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage2.0.fuse_layers.1.0.0.1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.transition2.2.0.0.weight - torch.Size([192, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.transition2.2.0.1.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.transition2.2.0.1.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.0.0.conv1.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.0.0.bn1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.0.0.bn1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.0.0.conv2.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.0.0.bn2.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.0.0.bn2.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.0.1.conv1.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.0.1.bn1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.0.1.bn1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.0.1.conv2.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.0.1.bn2.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.0.1.bn2.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.0.2.conv1.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.0.2.bn1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.0.2.bn1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.0.2.conv2.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.0.2.bn2.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.0.2.bn2.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.0.3.conv1.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.0.3.bn1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.0.3.bn1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.0.3.conv2.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.0.3.bn2.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.0.3.bn2.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.1.0.conv1.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.1.0.bn1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.1.0.bn1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.1.0.conv2.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.1.0.bn2.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.1.0.bn2.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.1.1.conv1.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.1.1.bn1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.1.1.bn1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.1.1.conv2.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.1.1.bn2.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.1.1.bn2.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.1.2.conv1.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.1.2.bn1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.1.2.bn1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.1.2.conv2.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.1.2.bn2.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.1.2.bn2.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.1.3.conv1.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.1.3.bn1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.1.3.bn1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.1.3.conv2.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.1.3.bn2.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.1.3.bn2.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.2.0.conv1.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.2.0.bn1.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.2.0.bn1.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.2.0.conv2.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.2.0.bn2.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.2.0.bn2.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.2.1.conv1.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.2.1.bn1.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.2.1.bn1.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.2.1.conv2.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.2.1.bn2.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.2.1.bn2.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.2.2.conv1.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.2.2.bn1.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.2.2.bn1.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.2.2.conv2.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.2.2.bn2.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.2.2.bn2.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.2.3.conv1.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.2.3.bn1.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.2.3.bn1.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.2.3.conv2.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.2.3.bn2.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.branches.2.3.bn2.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.fuse_layers.0.1.0.weight - torch.Size([48, 96, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.fuse_layers.0.1.1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.fuse_layers.0.1.1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.fuse_layers.0.2.0.weight - torch.Size([48, 192, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.fuse_layers.0.2.1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.fuse_layers.0.2.1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.fuse_layers.1.0.0.0.weight - torch.Size([96, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.fuse_layers.1.0.0.1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.fuse_layers.1.0.0.1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.fuse_layers.1.2.0.weight - torch.Size([96, 192, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.fuse_layers.1.2.1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.fuse_layers.1.2.1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.fuse_layers.2.0.0.0.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.fuse_layers.2.0.0.1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.fuse_layers.2.0.0.1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.fuse_layers.2.0.1.0.weight - torch.Size([192, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.fuse_layers.2.0.1.1.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.fuse_layers.2.0.1.1.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.fuse_layers.2.1.0.0.weight - torch.Size([192, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.fuse_layers.2.1.0.1.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.0.fuse_layers.2.1.0.1.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.0.0.conv1.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.0.0.bn1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.0.0.bn1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.0.0.conv2.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.0.0.bn2.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.0.0.bn2.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.0.1.conv1.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.0.1.bn1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.0.1.bn1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.0.1.conv2.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.0.1.bn2.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.0.1.bn2.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.0.2.conv1.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.0.2.bn1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.0.2.bn1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.0.2.conv2.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.0.2.bn2.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.0.2.bn2.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.0.3.conv1.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.0.3.bn1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.0.3.bn1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.0.3.conv2.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.0.3.bn2.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.0.3.bn2.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.1.0.conv1.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.1.0.bn1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.1.0.bn1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.1.0.conv2.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.1.0.bn2.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.1.0.bn2.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.1.1.conv1.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.1.1.bn1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.1.1.bn1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.1.1.conv2.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.1.1.bn2.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.1.1.bn2.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.1.2.conv1.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.1.2.bn1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.1.2.bn1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.1.2.conv2.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.1.2.bn2.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.1.2.bn2.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.1.3.conv1.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.1.3.bn1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.1.3.bn1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.1.3.conv2.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.1.3.bn2.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.1.3.bn2.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.2.0.conv1.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.2.0.bn1.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.2.0.bn1.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.2.0.conv2.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.2.0.bn2.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.2.0.bn2.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.2.1.conv1.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.2.1.bn1.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.2.1.bn1.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.2.1.conv2.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.2.1.bn2.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.2.1.bn2.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.2.2.conv1.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.2.2.bn1.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.2.2.bn1.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.2.2.conv2.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.2.2.bn2.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.2.2.bn2.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.2.3.conv1.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.2.3.bn1.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.2.3.bn1.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.2.3.conv2.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.2.3.bn2.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.branches.2.3.bn2.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.fuse_layers.0.1.0.weight - torch.Size([48, 96, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.fuse_layers.0.1.1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.fuse_layers.0.1.1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.fuse_layers.0.2.0.weight - torch.Size([48, 192, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.fuse_layers.0.2.1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.fuse_layers.0.2.1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.fuse_layers.1.0.0.0.weight - torch.Size([96, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.fuse_layers.1.0.0.1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.fuse_layers.1.0.0.1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.fuse_layers.1.2.0.weight - torch.Size([96, 192, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.fuse_layers.1.2.1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.fuse_layers.1.2.1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.fuse_layers.2.0.0.0.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.fuse_layers.2.0.0.1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.fuse_layers.2.0.0.1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.fuse_layers.2.0.1.0.weight - torch.Size([192, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.fuse_layers.2.0.1.1.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.fuse_layers.2.0.1.1.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.fuse_layers.2.1.0.0.weight - torch.Size([192, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.fuse_layers.2.1.0.1.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.1.fuse_layers.2.1.0.1.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.0.0.conv1.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.0.0.bn1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.0.0.bn1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.0.0.conv2.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.0.0.bn2.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.0.0.bn2.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.0.1.conv1.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.0.1.bn1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.0.1.bn1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.0.1.conv2.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.0.1.bn2.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.0.1.bn2.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.0.2.conv1.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.0.2.bn1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.0.2.bn1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.0.2.conv2.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.0.2.bn2.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.0.2.bn2.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.0.3.conv1.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.0.3.bn1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.0.3.bn1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.0.3.conv2.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.0.3.bn2.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.0.3.bn2.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.1.0.conv1.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.1.0.bn1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.1.0.bn1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.1.0.conv2.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.1.0.bn2.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.1.0.bn2.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.1.1.conv1.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.1.1.bn1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.1.1.bn1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.1.1.conv2.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.1.1.bn2.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.1.1.bn2.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.1.2.conv1.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.1.2.bn1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.1.2.bn1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.1.2.conv2.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.1.2.bn2.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.1.2.bn2.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.1.3.conv1.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.1.3.bn1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.1.3.bn1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.1.3.conv2.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.1.3.bn2.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.1.3.bn2.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.2.0.conv1.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.2.0.bn1.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.2.0.bn1.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.2.0.conv2.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.2.0.bn2.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.2.0.bn2.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.2.1.conv1.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.2.1.bn1.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.2.1.bn1.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.2.1.conv2.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.2.1.bn2.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.2.1.bn2.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.2.2.conv1.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.2.2.bn1.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.2.2.bn1.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.2.2.conv2.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.2.2.bn2.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.2.2.bn2.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.2.3.conv1.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.2.3.bn1.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.2.3.bn1.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.2.3.conv2.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.2.3.bn2.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.branches.2.3.bn2.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.fuse_layers.0.1.0.weight - torch.Size([48, 96, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.fuse_layers.0.1.1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.fuse_layers.0.1.1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.fuse_layers.0.2.0.weight - torch.Size([48, 192, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.fuse_layers.0.2.1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.fuse_layers.0.2.1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.fuse_layers.1.0.0.0.weight - torch.Size([96, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.fuse_layers.1.0.0.1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.fuse_layers.1.0.0.1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.fuse_layers.1.2.0.weight - torch.Size([96, 192, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.fuse_layers.1.2.1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.fuse_layers.1.2.1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.fuse_layers.2.0.0.0.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.fuse_layers.2.0.0.1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.fuse_layers.2.0.0.1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.fuse_layers.2.0.1.0.weight - torch.Size([192, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.fuse_layers.2.0.1.1.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.fuse_layers.2.0.1.1.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.fuse_layers.2.1.0.0.weight - torch.Size([192, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.fuse_layers.2.1.0.1.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.2.fuse_layers.2.1.0.1.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.0.0.conv1.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.0.0.bn1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.0.0.bn1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.0.0.conv2.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.0.0.bn2.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.0.0.bn2.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.0.1.conv1.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.0.1.bn1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.0.1.bn1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.0.1.conv2.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.0.1.bn2.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.0.1.bn2.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.0.2.conv1.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.0.2.bn1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.0.2.bn1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.0.2.conv2.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.0.2.bn2.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.0.2.bn2.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.0.3.conv1.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.0.3.bn1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.0.3.bn1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.0.3.conv2.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.0.3.bn2.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.0.3.bn2.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.1.0.conv1.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.1.0.bn1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.1.0.bn1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.1.0.conv2.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.1.0.bn2.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.1.0.bn2.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.1.1.conv1.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.1.1.bn1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.1.1.bn1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.1.1.conv2.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.1.1.bn2.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.1.1.bn2.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.1.2.conv1.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.1.2.bn1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.1.2.bn1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.1.2.conv2.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.1.2.bn2.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.1.2.bn2.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.1.3.conv1.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.1.3.bn1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.1.3.bn1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.1.3.conv2.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.1.3.bn2.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.1.3.bn2.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.2.0.conv1.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.2.0.bn1.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.2.0.bn1.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.2.0.conv2.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.2.0.bn2.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.2.0.bn2.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.2.1.conv1.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.2.1.bn1.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.2.1.bn1.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.2.1.conv2.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.2.1.bn2.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.2.1.bn2.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.2.2.conv1.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.2.2.bn1.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.2.2.bn1.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.2.2.conv2.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.2.2.bn2.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.2.2.bn2.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.2.3.conv1.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.2.3.bn1.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.2.3.bn1.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.2.3.conv2.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.2.3.bn2.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.branches.2.3.bn2.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.fuse_layers.0.1.0.weight - torch.Size([48, 96, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.fuse_layers.0.1.1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.fuse_layers.0.1.1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.fuse_layers.0.2.0.weight - torch.Size([48, 192, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.fuse_layers.0.2.1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.fuse_layers.0.2.1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.fuse_layers.1.0.0.0.weight - torch.Size([96, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.fuse_layers.1.0.0.1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.fuse_layers.1.0.0.1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.fuse_layers.1.2.0.weight - torch.Size([96, 192, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.fuse_layers.1.2.1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.fuse_layers.1.2.1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.fuse_layers.2.0.0.0.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.fuse_layers.2.0.0.1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.fuse_layers.2.0.0.1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.fuse_layers.2.0.1.0.weight - torch.Size([192, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.fuse_layers.2.0.1.1.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.fuse_layers.2.0.1.1.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.fuse_layers.2.1.0.0.weight - torch.Size([192, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.fuse_layers.2.1.0.1.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage3.3.fuse_layers.2.1.0.1.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.transition3.3.0.0.weight - torch.Size([384, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.transition3.3.0.1.weight - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.transition3.3.0.1.bias - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.0.0.conv1.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.0.0.bn1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.0.0.bn1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.0.0.conv2.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.0.0.bn2.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.0.0.bn2.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.0.1.conv1.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.0.1.bn1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.0.1.bn1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.0.1.conv2.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.0.1.bn2.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.0.1.bn2.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.0.2.conv1.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.0.2.bn1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.0.2.bn1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.0.2.conv2.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.0.2.bn2.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.0.2.bn2.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.0.3.conv1.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.0.3.bn1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.0.3.bn1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.0.3.conv2.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.0.3.bn2.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.0.3.bn2.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.1.0.conv1.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.1.0.bn1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.1.0.bn1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.1.0.conv2.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.1.0.bn2.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.1.0.bn2.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.1.1.conv1.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.1.1.bn1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.1.1.bn1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.1.1.conv2.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.1.1.bn2.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.1.1.bn2.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.1.2.conv1.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.1.2.bn1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.1.2.bn1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.1.2.conv2.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.1.2.bn2.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.1.2.bn2.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.1.3.conv1.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.1.3.bn1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.1.3.bn1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.1.3.conv2.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.1.3.bn2.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.1.3.bn2.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.2.0.conv1.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.2.0.bn1.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.2.0.bn1.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.2.0.conv2.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.2.0.bn2.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.2.0.bn2.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.2.1.conv1.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.2.1.bn1.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.2.1.bn1.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.2.1.conv2.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.2.1.bn2.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.2.1.bn2.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.2.2.conv1.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.2.2.bn1.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.2.2.bn1.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.2.2.conv2.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.2.2.bn2.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.2.2.bn2.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.2.3.conv1.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.2.3.bn1.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.2.3.bn1.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.2.3.conv2.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.2.3.bn2.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.2.3.bn2.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.3.0.conv1.weight - torch.Size([384, 384, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.3.0.bn1.weight - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.3.0.bn1.bias - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.3.0.conv2.weight - torch.Size([384, 384, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.3.0.bn2.weight - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.3.0.bn2.bias - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.3.1.conv1.weight - torch.Size([384, 384, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.3.1.bn1.weight - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.3.1.bn1.bias - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.3.1.conv2.weight - torch.Size([384, 384, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.3.1.bn2.weight - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.3.1.bn2.bias - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.3.2.conv1.weight - torch.Size([384, 384, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.3.2.bn1.weight - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.3.2.bn1.bias - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.3.2.conv2.weight - torch.Size([384, 384, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.3.2.bn2.weight - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.3.2.bn2.bias - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.3.3.conv1.weight - torch.Size([384, 384, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.3.3.bn1.weight - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.3.3.bn1.bias - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.3.3.conv2.weight - torch.Size([384, 384, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.3.3.bn2.weight - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.branches.3.3.bn2.bias - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.fuse_layers.0.1.0.weight - torch.Size([48, 96, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.fuse_layers.0.1.1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.fuse_layers.0.1.1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.fuse_layers.0.2.0.weight - torch.Size([48, 192, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.fuse_layers.0.2.1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.fuse_layers.0.2.1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.fuse_layers.0.3.0.weight - torch.Size([48, 384, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.fuse_layers.0.3.1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.fuse_layers.0.3.1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.fuse_layers.1.0.0.0.weight - torch.Size([96, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.fuse_layers.1.0.0.1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.fuse_layers.1.0.0.1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.fuse_layers.1.2.0.weight - torch.Size([96, 192, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.fuse_layers.1.2.1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.fuse_layers.1.2.1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.fuse_layers.1.3.0.weight - torch.Size([96, 384, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.fuse_layers.1.3.1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.fuse_layers.1.3.1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.fuse_layers.2.0.0.0.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.fuse_layers.2.0.0.1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.fuse_layers.2.0.0.1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.fuse_layers.2.0.1.0.weight - torch.Size([192, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.fuse_layers.2.0.1.1.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.fuse_layers.2.0.1.1.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.fuse_layers.2.1.0.0.weight - torch.Size([192, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.fuse_layers.2.1.0.1.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.fuse_layers.2.1.0.1.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.fuse_layers.2.3.0.weight - torch.Size([192, 384, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.fuse_layers.2.3.1.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.fuse_layers.2.3.1.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.fuse_layers.3.0.0.0.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.fuse_layers.3.0.0.1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.fuse_layers.3.0.0.1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.fuse_layers.3.0.1.0.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.fuse_layers.3.0.1.1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.fuse_layers.3.0.1.1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.fuse_layers.3.0.2.0.weight - torch.Size([384, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.fuse_layers.3.0.2.1.weight - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.fuse_layers.3.0.2.1.bias - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.fuse_layers.3.1.0.0.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.fuse_layers.3.1.0.1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.fuse_layers.3.1.0.1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.fuse_layers.3.1.1.0.weight - torch.Size([384, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.fuse_layers.3.1.1.1.weight - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.fuse_layers.3.1.1.1.bias - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.fuse_layers.3.2.0.0.weight - torch.Size([384, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.fuse_layers.3.2.0.1.weight - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.0.fuse_layers.3.2.0.1.bias - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.0.0.conv1.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.0.0.bn1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.0.0.bn1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.0.0.conv2.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.0.0.bn2.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.0.0.bn2.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.0.1.conv1.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.0.1.bn1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.0.1.bn1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.0.1.conv2.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.0.1.bn2.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.0.1.bn2.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.0.2.conv1.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.0.2.bn1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.0.2.bn1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.0.2.conv2.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.0.2.bn2.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.0.2.bn2.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.0.3.conv1.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.0.3.bn1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.0.3.bn1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.0.3.conv2.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.0.3.bn2.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.0.3.bn2.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.1.0.conv1.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.1.0.bn1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.1.0.bn1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.1.0.conv2.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.1.0.bn2.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.1.0.bn2.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.1.1.conv1.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.1.1.bn1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.1.1.bn1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.1.1.conv2.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.1.1.bn2.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.1.1.bn2.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.1.2.conv1.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.1.2.bn1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.1.2.bn1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.1.2.conv2.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.1.2.bn2.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.1.2.bn2.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.1.3.conv1.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.1.3.bn1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.1.3.bn1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.1.3.conv2.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.1.3.bn2.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.1.3.bn2.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.2.0.conv1.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.2.0.bn1.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.2.0.bn1.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.2.0.conv2.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.2.0.bn2.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.2.0.bn2.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.2.1.conv1.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.2.1.bn1.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.2.1.bn1.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.2.1.conv2.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.2.1.bn2.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.2.1.bn2.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.2.2.conv1.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.2.2.bn1.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.2.2.bn1.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.2.2.conv2.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.2.2.bn2.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.2.2.bn2.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.2.3.conv1.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.2.3.bn1.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.2.3.bn1.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.2.3.conv2.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.2.3.bn2.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.2.3.bn2.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.3.0.conv1.weight - torch.Size([384, 384, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.3.0.bn1.weight - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.3.0.bn1.bias - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.3.0.conv2.weight - torch.Size([384, 384, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.3.0.bn2.weight - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.3.0.bn2.bias - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.3.1.conv1.weight - torch.Size([384, 384, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.3.1.bn1.weight - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.3.1.bn1.bias - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.3.1.conv2.weight - torch.Size([384, 384, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.3.1.bn2.weight - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.3.1.bn2.bias - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.3.2.conv1.weight - torch.Size([384, 384, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.3.2.bn1.weight - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.3.2.bn1.bias - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.3.2.conv2.weight - torch.Size([384, 384, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.3.2.bn2.weight - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.3.2.bn2.bias - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.3.3.conv1.weight - torch.Size([384, 384, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.3.3.bn1.weight - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.3.3.bn1.bias - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.3.3.conv2.weight - torch.Size([384, 384, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.3.3.bn2.weight - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.branches.3.3.bn2.bias - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.fuse_layers.0.1.0.weight - torch.Size([48, 96, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.fuse_layers.0.1.1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.fuse_layers.0.1.1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.fuse_layers.0.2.0.weight - torch.Size([48, 192, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.fuse_layers.0.2.1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.fuse_layers.0.2.1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.fuse_layers.0.3.0.weight - torch.Size([48, 384, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.fuse_layers.0.3.1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.fuse_layers.0.3.1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.fuse_layers.1.0.0.0.weight - torch.Size([96, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.fuse_layers.1.0.0.1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.fuse_layers.1.0.0.1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.fuse_layers.1.2.0.weight - torch.Size([96, 192, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.fuse_layers.1.2.1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.fuse_layers.1.2.1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.fuse_layers.1.3.0.weight - torch.Size([96, 384, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.fuse_layers.1.3.1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.fuse_layers.1.3.1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.fuse_layers.2.0.0.0.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.fuse_layers.2.0.0.1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.fuse_layers.2.0.0.1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.fuse_layers.2.0.1.0.weight - torch.Size([192, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.fuse_layers.2.0.1.1.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.fuse_layers.2.0.1.1.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.fuse_layers.2.1.0.0.weight - torch.Size([192, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.fuse_layers.2.1.0.1.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.fuse_layers.2.1.0.1.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.fuse_layers.2.3.0.weight - torch.Size([192, 384, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.fuse_layers.2.3.1.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.fuse_layers.2.3.1.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.fuse_layers.3.0.0.0.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.fuse_layers.3.0.0.1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.fuse_layers.3.0.0.1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.fuse_layers.3.0.1.0.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.fuse_layers.3.0.1.1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.fuse_layers.3.0.1.1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.fuse_layers.3.0.2.0.weight - torch.Size([384, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.fuse_layers.3.0.2.1.weight - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.fuse_layers.3.0.2.1.bias - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.fuse_layers.3.1.0.0.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.fuse_layers.3.1.0.1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.fuse_layers.3.1.0.1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.fuse_layers.3.1.1.0.weight - torch.Size([384, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.fuse_layers.3.1.1.1.weight - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.fuse_layers.3.1.1.1.bias - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.fuse_layers.3.2.0.0.weight - torch.Size([384, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.fuse_layers.3.2.0.1.weight - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.1.fuse_layers.3.2.0.1.bias - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.0.0.conv1.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.0.0.bn1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.0.0.bn1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.0.0.conv2.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.0.0.bn2.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.0.0.bn2.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.0.1.conv1.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.0.1.bn1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.0.1.bn1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.0.1.conv2.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.0.1.bn2.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.0.1.bn2.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.0.2.conv1.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.0.2.bn1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.0.2.bn1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.0.2.conv2.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.0.2.bn2.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.0.2.bn2.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.0.3.conv1.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.0.3.bn1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.0.3.bn1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.0.3.conv2.weight - torch.Size([48, 48, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.0.3.bn2.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.0.3.bn2.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.1.0.conv1.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.1.0.bn1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.1.0.bn1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.1.0.conv2.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.1.0.bn2.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.1.0.bn2.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.1.1.conv1.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.1.1.bn1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.1.1.bn1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.1.1.conv2.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.1.1.bn2.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.1.1.bn2.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.1.2.conv1.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.1.2.bn1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.1.2.bn1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.1.2.conv2.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.1.2.bn2.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.1.2.bn2.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.1.3.conv1.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.1.3.bn1.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.1.3.bn1.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.1.3.conv2.weight - torch.Size([96, 96, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.1.3.bn2.weight - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.1.3.bn2.bias - torch.Size([96]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.2.0.conv1.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.2.0.bn1.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.2.0.bn1.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.2.0.conv2.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.2.0.bn2.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.2.0.bn2.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.2.1.conv1.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.2.1.bn1.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.2.1.bn1.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.2.1.conv2.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.2.1.bn2.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.2.1.bn2.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.2.2.conv1.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.2.2.bn1.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.2.2.bn1.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.2.2.conv2.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.2.2.bn2.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.2.2.bn2.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.2.3.conv1.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.2.3.bn1.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.2.3.bn1.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.2.3.conv2.weight - torch.Size([192, 192, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.2.3.bn2.weight - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.2.3.bn2.bias - torch.Size([192]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.3.0.conv1.weight - torch.Size([384, 384, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.3.0.bn1.weight - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.3.0.bn1.bias - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.3.0.conv2.weight - torch.Size([384, 384, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.3.0.bn2.weight - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.3.0.bn2.bias - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.3.1.conv1.weight - torch.Size([384, 384, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.3.1.bn1.weight - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.3.1.bn1.bias - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.3.1.conv2.weight - torch.Size([384, 384, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.3.1.bn2.weight - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.3.1.bn2.bias - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.3.2.conv1.weight - torch.Size([384, 384, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.3.2.bn1.weight - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.3.2.bn1.bias - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.3.2.conv2.weight - torch.Size([384, 384, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.3.2.bn2.weight - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.3.2.bn2.bias - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.3.3.conv1.weight - torch.Size([384, 384, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.3.3.bn1.weight - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.3.3.bn1.bias - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.3.3.conv2.weight - torch.Size([384, 384, 3, 3]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.3.3.bn2.weight - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.branches.3.3.bn2.bias - torch.Size([384]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.fuse_layers.0.1.0.weight - torch.Size([48, 96, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.fuse_layers.0.1.1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.fuse_layers.0.1.1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.fuse_layers.0.2.0.weight - torch.Size([48, 192, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.fuse_layers.0.2.1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.fuse_layers.0.2.1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.fuse_layers.0.3.0.weight - torch.Size([48, 384, 1, 1]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.fuse_layers.0.3.1.weight - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth backbone.stage4.2.fuse_layers.0.3.1.bias - torch.Size([48]): PretrainedInit: load from https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth head.final_layer.weight - torch.Size([17, 48, 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 15:25:07 - mmengine - INFO - Checkpoints will be saved to /mnt/lustre/liqikai/work_dirs/20220914/hrnet_w48_384 by HardDiskBackend. 2022/09/14 15:26:42 - mmengine - INFO - Epoch(train) [1][50/586] lr: 4.954910e-05 eta: 2 days, 16:54:14 time: 1.899472 data_time: 0.302130 memory: 15239 loss_kpt: 0.002209 acc_pose: 0.177438 loss: 0.002209 2022/09/14 15:27:26 - mmengine - INFO - Epoch(train) [1][100/586] lr: 9.959920e-05 eta: 1 day, 23:32:02 time: 0.883918 data_time: 0.104775 memory: 15239 loss_kpt: 0.001826 acc_pose: 0.369458 loss: 0.001826 2022/09/14 15:28:01 - mmengine - INFO - Epoch(train) [1][150/586] lr: 1.496493e-04 eta: 1 day, 15:39:34 time: 0.701471 data_time: 0.053588 memory: 15239 loss_kpt: 0.001465 acc_pose: 0.566668 loss: 0.001465 2022/09/14 15:28:38 - mmengine - INFO - Epoch(train) [1][200/586] lr: 1.996994e-04 eta: 1 day, 12:05:30 time: 0.745323 data_time: 0.027843 memory: 15239 loss_kpt: 0.001329 acc_pose: 0.471619 loss: 0.001329 2022/09/14 15:29:15 - mmengine - INFO - Epoch(train) [1][250/586] lr: 2.497495e-04 eta: 1 day, 9:53:41 time: 0.737694 data_time: 0.206663 memory: 15239 loss_kpt: 0.001233 acc_pose: 0.642485 loss: 0.001233 2022/09/14 15:29:44 - mmengine - INFO - Epoch(train) [1][300/586] lr: 2.997996e-04 eta: 1 day, 7:30:58 time: 0.577508 data_time: 0.047498 memory: 15239 loss_kpt: 0.001198 acc_pose: 0.561305 loss: 0.001198 2022/09/14 15:30:15 - mmengine - INFO - Epoch(train) [1][350/586] lr: 3.498497e-04 eta: 1 day, 6:00:31 time: 0.617298 data_time: 0.045806 memory: 15239 loss_kpt: 0.001179 acc_pose: 0.634500 loss: 0.001179 2022/09/14 15:30:40 - mmengine - INFO - Epoch(train) [1][400/586] lr: 3.998998e-04 eta: 1 day, 4:22:48 time: 0.500836 data_time: 0.028039 memory: 15239 loss_kpt: 0.001151 acc_pose: 0.623301 loss: 0.001151 2022/09/14 15:31:13 - mmengine - INFO - Epoch(train) [1][450/586] lr: 4.499499e-04 eta: 1 day, 3:41:34 time: 0.654418 data_time: 0.029997 memory: 15239 loss_kpt: 0.001112 acc_pose: 0.609896 loss: 0.001112 2022/09/14 15:31:48 - mmengine - INFO - Epoch(train) [1][500/586] lr: 5.000000e-04 eta: 1 day, 3:19:52 time: 0.710184 data_time: 0.040515 memory: 15239 loss_kpt: 0.001114 acc_pose: 0.644648 loss: 0.001114 2022/09/14 15:32:18 - mmengine - INFO - Epoch(train) [1][550/586] lr: 5.000000e-04 eta: 1 day, 2:38:51 time: 0.585475 data_time: 0.049227 memory: 15239 loss_kpt: 0.001097 acc_pose: 0.594093 loss: 0.001097 2022/09/14 15:32:38 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 15:32:38 - mmengine - INFO - Saving checkpoint at 1 epochs 2022/09/14 15:33:09 - mmengine - INFO - Epoch(train) [2][50/586] lr: 5.000000e-04 eta: 1 day, 0:17:34 time: 0.473069 data_time: 0.032835 memory: 15239 loss_kpt: 0.001110 acc_pose: 0.676893 loss: 0.001110 2022/09/14 15:33:32 - mmengine - INFO - Epoch(train) [2][100/586] lr: 5.000000e-04 eta: 23:39:01 time: 0.459040 data_time: 0.025424 memory: 15239 loss_kpt: 0.001075 acc_pose: 0.635890 loss: 0.001075 2022/09/14 15:33:55 - mmengine - INFO - Epoch(train) [2][150/586] lr: 5.000000e-04 eta: 23:07:03 time: 0.469058 data_time: 0.025874 memory: 15239 loss_kpt: 0.001060 acc_pose: 0.683363 loss: 0.001060 2022/09/14 15:34:18 - mmengine - INFO - Epoch(train) [2][200/586] lr: 5.000000e-04 eta: 22:38:22 time: 0.463535 data_time: 0.024755 memory: 15239 loss_kpt: 0.000999 acc_pose: 0.678459 loss: 0.000999 2022/09/14 15:34:41 - mmengine - INFO - Epoch(train) [2][250/586] lr: 5.000000e-04 eta: 22:13:19 time: 0.465431 data_time: 0.028006 memory: 15239 loss_kpt: 0.000975 acc_pose: 0.728413 loss: 0.000975 2022/09/14 15:35:05 - mmengine - INFO - Epoch(train) [2][300/586] lr: 5.000000e-04 eta: 21:51:16 time: 0.467486 data_time: 0.026156 memory: 15239 loss_kpt: 0.001023 acc_pose: 0.637236 loss: 0.001023 2022/09/14 15:35:28 - mmengine - INFO - Epoch(train) [2][350/586] lr: 5.000000e-04 eta: 21:31:41 time: 0.468804 data_time: 0.026939 memory: 15239 loss_kpt: 0.000973 acc_pose: 0.757182 loss: 0.000973 2022/09/14 15:35:52 - mmengine - INFO - Epoch(train) [2][400/586] lr: 5.000000e-04 eta: 21:13:57 time: 0.467839 data_time: 0.029402 memory: 15239 loss_kpt: 0.001002 acc_pose: 0.713318 loss: 0.001002 2022/09/14 15:35:58 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 15:36:15 - mmengine - INFO - Epoch(train) [2][450/586] lr: 5.000000e-04 eta: 20:58:32 time: 0.474322 data_time: 0.025788 memory: 15239 loss_kpt: 0.000981 acc_pose: 0.660801 loss: 0.000981 2022/09/14 15:36:39 - mmengine - INFO - Epoch(train) [2][500/586] lr: 5.000000e-04 eta: 20:43:32 time: 0.464084 data_time: 0.025938 memory: 15239 loss_kpt: 0.000945 acc_pose: 0.753576 loss: 0.000945 2022/09/14 15:37:02 - mmengine - INFO - Epoch(train) [2][550/586] lr: 5.000000e-04 eta: 20:30:48 time: 0.475150 data_time: 0.026293 memory: 15239 loss_kpt: 0.000987 acc_pose: 0.607479 loss: 0.000987 2022/09/14 15:37:19 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 15:37:19 - mmengine - INFO - Saving checkpoint at 2 epochs 2022/09/14 15:37:49 - mmengine - INFO - Epoch(train) [3][50/586] lr: 5.000000e-04 eta: 19:43:09 time: 0.478573 data_time: 0.033681 memory: 15239 loss_kpt: 0.000947 acc_pose: 0.657368 loss: 0.000947 2022/09/14 15:38:13 - mmengine - INFO - Epoch(train) [3][100/586] lr: 5.000000e-04 eta: 19:33:27 time: 0.467322 data_time: 0.025811 memory: 15239 loss_kpt: 0.000928 acc_pose: 0.628540 loss: 0.000928 2022/09/14 15:38:36 - mmengine - INFO - Epoch(train) [3][150/586] lr: 5.000000e-04 eta: 19:23:53 time: 0.459764 data_time: 0.025416 memory: 15239 loss_kpt: 0.000923 acc_pose: 0.681713 loss: 0.000923 2022/09/14 15:38:59 - mmengine - INFO - Epoch(train) [3][200/586] lr: 5.000000e-04 eta: 19:15:52 time: 0.471559 data_time: 0.031237 memory: 15239 loss_kpt: 0.000909 acc_pose: 0.719865 loss: 0.000909 2022/09/14 15:39:23 - mmengine - INFO - Epoch(train) [3][250/586] lr: 5.000000e-04 eta: 19:07:56 time: 0.465222 data_time: 0.028075 memory: 15239 loss_kpt: 0.000924 acc_pose: 0.699159 loss: 0.000924 2022/09/14 15:39:46 - mmengine - INFO - Epoch(train) [3][300/586] lr: 5.000000e-04 eta: 19:00:59 time: 0.472245 data_time: 0.033248 memory: 15239 loss_kpt: 0.000878 acc_pose: 0.789796 loss: 0.000878 2022/09/14 15:40:10 - mmengine - INFO - Epoch(train) [3][350/586] lr: 5.000000e-04 eta: 18:54:29 time: 0.472254 data_time: 0.036417 memory: 15239 loss_kpt: 0.000938 acc_pose: 0.759324 loss: 0.000938 2022/09/14 15:40:33 - mmengine - INFO - Epoch(train) [3][400/586] lr: 5.000000e-04 eta: 18:48:03 time: 0.467447 data_time: 0.026771 memory: 15239 loss_kpt: 0.000899 acc_pose: 0.676063 loss: 0.000899 2022/09/14 15:40:56 - mmengine - INFO - Epoch(train) [3][450/586] lr: 5.000000e-04 eta: 18:41:48 time: 0.464593 data_time: 0.026885 memory: 15239 loss_kpt: 0.000906 acc_pose: 0.699938 loss: 0.000906 2022/09/14 15:41:20 - mmengine - INFO - Epoch(train) [3][500/586] lr: 5.000000e-04 eta: 18:36:20 time: 0.471542 data_time: 0.026056 memory: 15239 loss_kpt: 0.000934 acc_pose: 0.673092 loss: 0.000934 2022/09/14 15:41:44 - mmengine - INFO - Epoch(train) [3][550/586] lr: 5.000000e-04 eta: 18:31:06 time: 0.470415 data_time: 0.025728 memory: 15239 loss_kpt: 0.000905 acc_pose: 0.711587 loss: 0.000905 2022/09/14 15:42:01 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 15:42:01 - mmengine - INFO - Saving checkpoint at 3 epochs 2022/09/14 15:42:31 - mmengine - INFO - Epoch(train) [4][50/586] lr: 5.000000e-04 eta: 18:03:41 time: 0.468503 data_time: 0.029546 memory: 15239 loss_kpt: 0.000905 acc_pose: 0.655327 loss: 0.000905 2022/09/14 15:42:54 - mmengine - INFO - Epoch(train) [4][100/586] lr: 5.000000e-04 eta: 17:59:32 time: 0.468032 data_time: 0.026517 memory: 15239 loss_kpt: 0.000909 acc_pose: 0.677526 loss: 0.000909 2022/09/14 15:43:17 - mmengine - INFO - Epoch(train) [4][150/586] lr: 5.000000e-04 eta: 17:55:21 time: 0.463827 data_time: 0.026244 memory: 15239 loss_kpt: 0.000866 acc_pose: 0.725582 loss: 0.000866 2022/09/14 15:43:41 - mmengine - INFO - Epoch(train) [4][200/586] lr: 5.000000e-04 eta: 17:51:36 time: 0.468308 data_time: 0.026262 memory: 15239 loss_kpt: 0.000847 acc_pose: 0.646253 loss: 0.000847 2022/09/14 15:44:00 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 15:44:04 - mmengine - INFO - Epoch(train) [4][250/586] lr: 5.000000e-04 eta: 17:48:02 time: 0.468987 data_time: 0.027496 memory: 15239 loss_kpt: 0.000881 acc_pose: 0.730286 loss: 0.000881 2022/09/14 15:44:27 - mmengine - INFO - Epoch(train) [4][300/586] lr: 5.000000e-04 eta: 17:44:05 time: 0.457682 data_time: 0.025383 memory: 15239 loss_kpt: 0.000878 acc_pose: 0.743083 loss: 0.000878 2022/09/14 15:44:50 - mmengine - INFO - Epoch(train) [4][350/586] lr: 5.000000e-04 eta: 17:40:28 time: 0.461081 data_time: 0.025142 memory: 15239 loss_kpt: 0.000866 acc_pose: 0.687650 loss: 0.000866 2022/09/14 15:45:14 - mmengine - INFO - Epoch(train) [4][400/586] lr: 5.000000e-04 eta: 17:37:51 time: 0.479578 data_time: 0.026393 memory: 15239 loss_kpt: 0.000879 acc_pose: 0.662168 loss: 0.000879 2022/09/14 15:45:38 - mmengine - INFO - Epoch(train) [4][450/586] lr: 5.000000e-04 eta: 17:35:01 time: 0.472349 data_time: 0.026323 memory: 15239 loss_kpt: 0.000891 acc_pose: 0.724236 loss: 0.000891 2022/09/14 15:46:01 - mmengine - INFO - Epoch(train) [4][500/586] lr: 5.000000e-04 eta: 17:31:52 time: 0.462786 data_time: 0.024941 memory: 15239 loss_kpt: 0.000849 acc_pose: 0.677932 loss: 0.000849 2022/09/14 15:46:25 - mmengine - INFO - Epoch(train) [4][550/586] lr: 5.000000e-04 eta: 17:29:26 time: 0.476675 data_time: 0.029893 memory: 15239 loss_kpt: 0.000848 acc_pose: 0.721191 loss: 0.000848 2022/09/14 15:46:41 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 15:46:41 - mmengine - INFO - Saving checkpoint at 4 epochs 2022/09/14 15:47:12 - mmengine - INFO - Epoch(train) [5][50/586] lr: 5.000000e-04 eta: 17:10:55 time: 0.474128 data_time: 0.044108 memory: 15239 loss_kpt: 0.000861 acc_pose: 0.672446 loss: 0.000861 2022/09/14 15:47:36 - mmengine - INFO - Epoch(train) [5][100/586] lr: 5.000000e-04 eta: 17:09:09 time: 0.479831 data_time: 0.030768 memory: 15239 loss_kpt: 0.000849 acc_pose: 0.656996 loss: 0.000849 2022/09/14 15:47:59 - mmengine - INFO - Epoch(train) [5][150/586] lr: 5.000000e-04 eta: 17:06:50 time: 0.464972 data_time: 0.030790 memory: 15239 loss_kpt: 0.000838 acc_pose: 0.720870 loss: 0.000838 2022/09/14 15:48:22 - mmengine - INFO - Epoch(train) [5][200/586] lr: 5.000000e-04 eta: 17:04:31 time: 0.463181 data_time: 0.031461 memory: 15239 loss_kpt: 0.000834 acc_pose: 0.676307 loss: 0.000834 2022/09/14 15:48:46 - mmengine - INFO - Epoch(train) [5][250/586] lr: 5.000000e-04 eta: 17:03:03 time: 0.483079 data_time: 0.026013 memory: 15239 loss_kpt: 0.000823 acc_pose: 0.741283 loss: 0.000823 2022/09/14 15:49:10 - mmengine - INFO - Epoch(train) [5][300/586] lr: 5.000000e-04 eta: 17:00:50 time: 0.462614 data_time: 0.027033 memory: 15239 loss_kpt: 0.000829 acc_pose: 0.695315 loss: 0.000829 2022/09/14 15:49:33 - mmengine - INFO - Epoch(train) [5][350/586] lr: 5.000000e-04 eta: 16:58:58 time: 0.469694 data_time: 0.025754 memory: 15239 loss_kpt: 0.000817 acc_pose: 0.758709 loss: 0.000817 2022/09/14 15:49:57 - mmengine - INFO - Epoch(train) [5][400/586] lr: 5.000000e-04 eta: 16:57:34 time: 0.481190 data_time: 0.025582 memory: 15239 loss_kpt: 0.000802 acc_pose: 0.683163 loss: 0.000802 2022/09/14 15:50:23 - mmengine - INFO - Epoch(train) [5][450/586] lr: 5.000000e-04 eta: 16:57:18 time: 0.511698 data_time: 0.033144 memory: 15239 loss_kpt: 0.000818 acc_pose: 0.682492 loss: 0.000818 2022/09/14 15:50:47 - mmengine - INFO - Epoch(train) [5][500/586] lr: 5.000000e-04 eta: 16:56:15 time: 0.490108 data_time: 0.039052 memory: 15239 loss_kpt: 0.000827 acc_pose: 0.741445 loss: 0.000827 2022/09/14 15:51:12 - mmengine - INFO - Epoch(train) [5][550/586] lr: 5.000000e-04 eta: 16:55:13 time: 0.489186 data_time: 0.029034 memory: 15239 loss_kpt: 0.000842 acc_pose: 0.747502 loss: 0.000842 2022/09/14 15:51:29 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 15:51:29 - mmengine - INFO - Saving checkpoint at 5 epochs 2022/09/14 15:51:59 - mmengine - INFO - Epoch(train) [6][50/586] lr: 5.000000e-04 eta: 16:41:08 time: 0.474465 data_time: 0.035141 memory: 15239 loss_kpt: 0.000833 acc_pose: 0.755611 loss: 0.000833 2022/09/14 15:52:08 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 15:52:23 - mmengine - INFO - Epoch(train) [6][100/586] lr: 5.000000e-04 eta: 16:39:50 time: 0.473316 data_time: 0.030182 memory: 15239 loss_kpt: 0.000815 acc_pose: 0.664664 loss: 0.000815 2022/09/14 15:52:46 - mmengine - INFO - Epoch(train) [6][150/586] lr: 5.000000e-04 eta: 16:38:02 time: 0.457028 data_time: 0.026991 memory: 15239 loss_kpt: 0.000789 acc_pose: 0.714558 loss: 0.000789 2022/09/14 15:53:09 - mmengine - INFO - Epoch(train) [6][200/586] lr: 5.000000e-04 eta: 16:36:32 time: 0.465567 data_time: 0.025330 memory: 15239 loss_kpt: 0.000803 acc_pose: 0.780189 loss: 0.000803 2022/09/14 15:53:33 - mmengine - INFO - Epoch(train) [6][250/586] lr: 5.000000e-04 eta: 16:35:25 time: 0.475933 data_time: 0.025869 memory: 15239 loss_kpt: 0.000828 acc_pose: 0.783985 loss: 0.000828 2022/09/14 15:53:56 - mmengine - INFO - Epoch(train) [6][300/586] lr: 5.000000e-04 eta: 16:33:50 time: 0.460487 data_time: 0.025779 memory: 15239 loss_kpt: 0.000794 acc_pose: 0.762756 loss: 0.000794 2022/09/14 15:54:19 - mmengine - INFO - Epoch(train) [6][350/586] lr: 5.000000e-04 eta: 16:32:28 time: 0.466561 data_time: 0.025294 memory: 15239 loss_kpt: 0.000794 acc_pose: 0.714341 loss: 0.000794 2022/09/14 15:54:43 - mmengine - INFO - Epoch(train) [6][400/586] lr: 5.000000e-04 eta: 16:31:23 time: 0.474343 data_time: 0.025630 memory: 15239 loss_kpt: 0.000845 acc_pose: 0.796070 loss: 0.000845 2022/09/14 15:55:07 - mmengine - INFO - Epoch(train) [6][450/586] lr: 5.000000e-04 eta: 16:30:16 time: 0.473421 data_time: 0.026525 memory: 15239 loss_kpt: 0.000820 acc_pose: 0.775738 loss: 0.000820 2022/09/14 15:55:30 - mmengine - INFO - Epoch(train) [6][500/586] lr: 5.000000e-04 eta: 16:28:48 time: 0.460282 data_time: 0.029250 memory: 15239 loss_kpt: 0.000805 acc_pose: 0.806990 loss: 0.000805 2022/09/14 15:55:53 - mmengine - INFO - Epoch(train) [6][550/586] lr: 5.000000e-04 eta: 16:27:49 time: 0.476063 data_time: 0.026339 memory: 15239 loss_kpt: 0.000804 acc_pose: 0.836588 loss: 0.000804 2022/09/14 15:56:10 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 15:56:10 - mmengine - INFO - Saving checkpoint at 6 epochs 2022/09/14 15:56:40 - mmengine - INFO - Epoch(train) [7][50/586] lr: 5.000000e-04 eta: 16:16:20 time: 0.466636 data_time: 0.034854 memory: 15239 loss_kpt: 0.000802 acc_pose: 0.675417 loss: 0.000802 2022/09/14 15:57:04 - mmengine - INFO - Epoch(train) [7][100/586] lr: 5.000000e-04 eta: 16:15:38 time: 0.479347 data_time: 0.032578 memory: 15239 loss_kpt: 0.000781 acc_pose: 0.749710 loss: 0.000781 2022/09/14 15:57:28 - mmengine - INFO - Epoch(train) [7][150/586] lr: 5.000000e-04 eta: 16:14:38 time: 0.468198 data_time: 0.025907 memory: 15239 loss_kpt: 0.000814 acc_pose: 0.667716 loss: 0.000814 2022/09/14 15:57:51 - mmengine - INFO - Epoch(train) [7][200/586] lr: 5.000000e-04 eta: 16:13:23 time: 0.458522 data_time: 0.025812 memory: 15239 loss_kpt: 0.000788 acc_pose: 0.766374 loss: 0.000788 2022/09/14 15:58:15 - mmengine - INFO - Epoch(train) [7][250/586] lr: 5.000000e-04 eta: 16:12:40 time: 0.477672 data_time: 0.030347 memory: 15239 loss_kpt: 0.000802 acc_pose: 0.737778 loss: 0.000802 2022/09/14 15:58:38 - mmengine - INFO - Epoch(train) [7][300/586] lr: 5.000000e-04 eta: 16:11:51 time: 0.473288 data_time: 0.026147 memory: 15239 loss_kpt: 0.000819 acc_pose: 0.719686 loss: 0.000819 2022/09/14 15:59:01 - mmengine - INFO - Epoch(train) [7][350/586] lr: 5.000000e-04 eta: 16:10:43 time: 0.461123 data_time: 0.026482 memory: 15239 loss_kpt: 0.000781 acc_pose: 0.730060 loss: 0.000781 2022/09/14 15:59:25 - mmengine - INFO - Epoch(train) [7][400/586] lr: 5.000000e-04 eta: 16:09:56 time: 0.473408 data_time: 0.027299 memory: 15239 loss_kpt: 0.000811 acc_pose: 0.813137 loss: 0.000811 2022/09/14 15:59:48 - mmengine - INFO - Epoch(train) [7][450/586] lr: 5.000000e-04 eta: 16:08:59 time: 0.467093 data_time: 0.027104 memory: 15239 loss_kpt: 0.000806 acc_pose: 0.739542 loss: 0.000806 2022/09/14 16:00:04 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 16:00:11 - mmengine - INFO - Epoch(train) [7][500/586] lr: 5.000000e-04 eta: 16:07:51 time: 0.458984 data_time: 0.025906 memory: 15239 loss_kpt: 0.000806 acc_pose: 0.756636 loss: 0.000806 2022/09/14 16:00:35 - mmengine - INFO - Epoch(train) [7][550/586] lr: 5.000000e-04 eta: 16:07:14 time: 0.479114 data_time: 0.025684 memory: 15239 loss_kpt: 0.000770 acc_pose: 0.796700 loss: 0.000770 2022/09/14 16:00:52 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 16:00:52 - mmengine - INFO - Saving checkpoint at 7 epochs 2022/09/14 16:01:22 - mmengine - INFO - Epoch(train) [8][50/586] lr: 5.000000e-04 eta: 15:57:47 time: 0.472166 data_time: 0.041865 memory: 15239 loss_kpt: 0.000776 acc_pose: 0.742022 loss: 0.000776 2022/09/14 16:01:46 - mmengine - INFO - Epoch(train) [8][100/586] lr: 5.000000e-04 eta: 15:57:10 time: 0.474208 data_time: 0.026863 memory: 15239 loss_kpt: 0.000774 acc_pose: 0.765144 loss: 0.000774 2022/09/14 16:02:09 - mmengine - INFO - Epoch(train) [8][150/586] lr: 5.000000e-04 eta: 15:56:24 time: 0.467564 data_time: 0.025337 memory: 15239 loss_kpt: 0.000788 acc_pose: 0.814715 loss: 0.000788 2022/09/14 16:02:33 - mmengine - INFO - Epoch(train) [8][200/586] lr: 5.000000e-04 eta: 15:55:33 time: 0.463541 data_time: 0.025818 memory: 15239 loss_kpt: 0.000791 acc_pose: 0.647752 loss: 0.000791 2022/09/14 16:02:56 - mmengine - INFO - Epoch(train) [8][250/586] lr: 5.000000e-04 eta: 15:54:57 time: 0.473769 data_time: 0.025291 memory: 15239 loss_kpt: 0.000787 acc_pose: 0.727516 loss: 0.000787 2022/09/14 16:03:20 - mmengine - INFO - Epoch(train) [8][300/586] lr: 5.000000e-04 eta: 15:54:16 time: 0.470196 data_time: 0.026182 memory: 15239 loss_kpt: 0.000772 acc_pose: 0.751093 loss: 0.000772 2022/09/14 16:03:43 - mmengine - INFO - Epoch(train) [8][350/586] lr: 5.000000e-04 eta: 15:53:27 time: 0.463954 data_time: 0.027624 memory: 15239 loss_kpt: 0.000773 acc_pose: 0.736763 loss: 0.000773 2022/09/14 16:04:06 - mmengine - INFO - Epoch(train) [8][400/586] lr: 5.000000e-04 eta: 15:52:47 time: 0.469943 data_time: 0.032152 memory: 15239 loss_kpt: 0.000782 acc_pose: 0.811341 loss: 0.000782 2022/09/14 16:04:30 - mmengine - INFO - Epoch(train) [8][450/586] lr: 5.000000e-04 eta: 15:52:19 time: 0.479695 data_time: 0.033757 memory: 15239 loss_kpt: 0.000799 acc_pose: 0.746589 loss: 0.000799 2022/09/14 16:04:54 - mmengine - INFO - Epoch(train) [8][500/586] lr: 5.000000e-04 eta: 15:51:34 time: 0.466137 data_time: 0.029445 memory: 15239 loss_kpt: 0.000764 acc_pose: 0.777523 loss: 0.000764 2022/09/14 16:05:17 - mmengine - INFO - Epoch(train) [8][550/586] lr: 5.000000e-04 eta: 15:50:53 time: 0.468238 data_time: 0.026083 memory: 15239 loss_kpt: 0.000776 acc_pose: 0.712718 loss: 0.000776 2022/09/14 16:05:34 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 16:05:34 - mmengine - INFO - Saving checkpoint at 8 epochs 2022/09/14 16:06:05 - mmengine - INFO - Epoch(train) [9][50/586] lr: 5.000000e-04 eta: 15:42:59 time: 0.482215 data_time: 0.032740 memory: 15239 loss_kpt: 0.000759 acc_pose: 0.755006 loss: 0.000759 2022/09/14 16:06:28 - mmengine - INFO - Epoch(train) [9][100/586] lr: 5.000000e-04 eta: 15:42:21 time: 0.466697 data_time: 0.026168 memory: 15239 loss_kpt: 0.000765 acc_pose: 0.779994 loss: 0.000765 2022/09/14 16:06:52 - mmengine - INFO - Epoch(train) [9][150/586] lr: 5.000000e-04 eta: 15:41:46 time: 0.469083 data_time: 0.025873 memory: 15239 loss_kpt: 0.000770 acc_pose: 0.869616 loss: 0.000770 2022/09/14 16:07:15 - mmengine - INFO - Epoch(train) [9][200/586] lr: 5.000000e-04 eta: 15:41:06 time: 0.465055 data_time: 0.028634 memory: 15239 loss_kpt: 0.000793 acc_pose: 0.687041 loss: 0.000793 2022/09/14 16:07:40 - mmengine - INFO - Epoch(train) [9][250/586] lr: 5.000000e-04 eta: 15:40:55 time: 0.488797 data_time: 0.026333 memory: 15239 loss_kpt: 0.000763 acc_pose: 0.723875 loss: 0.000763 2022/09/14 16:08:03 - mmengine - INFO - Epoch(train) [9][300/586] lr: 5.000000e-04 eta: 15:40:22 time: 0.469929 data_time: 0.027060 memory: 15239 loss_kpt: 0.000765 acc_pose: 0.801676 loss: 0.000765 2022/09/14 16:08:09 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 16:08:26 - mmengine - INFO - Epoch(train) [9][350/586] lr: 5.000000e-04 eta: 15:39:40 time: 0.462709 data_time: 0.025309 memory: 15239 loss_kpt: 0.000760 acc_pose: 0.745287 loss: 0.000760 2022/09/14 16:08:49 - mmengine - INFO - Epoch(train) [9][400/586] lr: 5.000000e-04 eta: 15:39:04 time: 0.467108 data_time: 0.027234 memory: 15239 loss_kpt: 0.000754 acc_pose: 0.808710 loss: 0.000754 2022/09/14 16:09:13 - mmengine - INFO - Epoch(train) [9][450/586] lr: 5.000000e-04 eta: 15:38:35 time: 0.472873 data_time: 0.026562 memory: 15239 loss_kpt: 0.000741 acc_pose: 0.763507 loss: 0.000741 2022/09/14 16:09:36 - mmengine - INFO - Epoch(train) [9][500/586] lr: 5.000000e-04 eta: 15:37:54 time: 0.462733 data_time: 0.030078 memory: 15239 loss_kpt: 0.000780 acc_pose: 0.750364 loss: 0.000780 2022/09/14 16:10:00 - mmengine - INFO - Epoch(train) [9][550/586] lr: 5.000000e-04 eta: 15:37:18 time: 0.466461 data_time: 0.026001 memory: 15239 loss_kpt: 0.000753 acc_pose: 0.748158 loss: 0.000753 2022/09/14 16:10:17 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 16:10:17 - mmengine - INFO - Saving checkpoint at 9 epochs 2022/09/14 16:10:47 - mmengine - INFO - Epoch(train) [10][50/586] lr: 5.000000e-04 eta: 15:30:06 time: 0.467703 data_time: 0.033633 memory: 15239 loss_kpt: 0.000730 acc_pose: 0.798629 loss: 0.000730 2022/09/14 16:11:11 - mmengine - INFO - Epoch(train) [10][100/586] lr: 5.000000e-04 eta: 15:29:42 time: 0.473567 data_time: 0.028151 memory: 15239 loss_kpt: 0.000738 acc_pose: 0.790246 loss: 0.000738 2022/09/14 16:11:35 - mmengine - INFO - Epoch(train) [10][150/586] lr: 5.000000e-04 eta: 15:29:26 time: 0.481396 data_time: 0.025947 memory: 15239 loss_kpt: 0.000751 acc_pose: 0.769314 loss: 0.000751 2022/09/14 16:11:58 - mmengine - INFO - Epoch(train) [10][200/586] lr: 5.000000e-04 eta: 15:28:47 time: 0.459410 data_time: 0.025738 memory: 15239 loss_kpt: 0.000757 acc_pose: 0.764245 loss: 0.000757 2022/09/14 16:12:22 - mmengine - INFO - Epoch(train) [10][250/586] lr: 5.000000e-04 eta: 15:28:25 time: 0.475721 data_time: 0.028837 memory: 15239 loss_kpt: 0.000781 acc_pose: 0.790244 loss: 0.000781 2022/09/14 16:12:45 - mmengine - INFO - Epoch(train) [10][300/586] lr: 5.000000e-04 eta: 15:28:03 time: 0.475487 data_time: 0.026001 memory: 15239 loss_kpt: 0.000744 acc_pose: 0.838539 loss: 0.000744 2022/09/14 16:13:08 - mmengine - INFO - Epoch(train) [10][350/586] lr: 5.000000e-04 eta: 15:27:26 time: 0.461351 data_time: 0.025677 memory: 15239 loss_kpt: 0.000757 acc_pose: 0.757099 loss: 0.000757 2022/09/14 16:13:32 - mmengine - INFO - Epoch(train) [10][400/586] lr: 5.000000e-04 eta: 15:26:55 time: 0.466570 data_time: 0.025638 memory: 15239 loss_kpt: 0.000746 acc_pose: 0.797640 loss: 0.000746 2022/09/14 16:13:56 - mmengine - INFO - Epoch(train) [10][450/586] lr: 5.000000e-04 eta: 15:26:34 time: 0.476418 data_time: 0.027789 memory: 15239 loss_kpt: 0.000753 acc_pose: 0.751770 loss: 0.000753 2022/09/14 16:14:18 - mmengine - INFO - Epoch(train) [10][500/586] lr: 5.000000e-04 eta: 15:25:54 time: 0.457291 data_time: 0.025530 memory: 15239 loss_kpt: 0.000762 acc_pose: 0.707239 loss: 0.000762 2022/09/14 16:14:42 - mmengine - INFO - Epoch(train) [10][550/586] lr: 5.000000e-04 eta: 15:25:29 time: 0.472400 data_time: 0.030078 memory: 15239 loss_kpt: 0.000756 acc_pose: 0.782559 loss: 0.000756 2022/09/14 16:14:59 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 16:14:59 - mmengine - INFO - Saving checkpoint at 10 epochs 2022/09/14 16:15:21 - mmengine - INFO - Epoch(val) [10][50/407] eta: 0:01:30 time: 0.253773 data_time: 0.066344 memory: 15239 2022/09/14 16:15:36 - mmengine - INFO - Epoch(val) [10][100/407] eta: 0:01:27 time: 0.285046 data_time: 0.093167 memory: 2064 2022/09/14 16:15:51 - mmengine - INFO - Epoch(val) [10][150/407] eta: 0:01:16 time: 0.298625 data_time: 0.111443 memory: 2064 2022/09/14 16:16:07 - mmengine - INFO - Epoch(val) [10][200/407] eta: 0:01:08 time: 0.332344 data_time: 0.144876 memory: 2064 2022/09/14 16:16:17 - mmengine - INFO - Epoch(val) [10][250/407] eta: 0:00:30 time: 0.194082 data_time: 0.007634 memory: 2064 2022/09/14 16:16:28 - mmengine - INFO - Epoch(val) [10][300/407] eta: 0:00:24 time: 0.227927 data_time: 0.039462 memory: 2064 2022/09/14 16:16:39 - mmengine - INFO - Epoch(val) [10][350/407] eta: 0:00:12 time: 0.222476 data_time: 0.036302 memory: 2064 2022/09/14 16:16:51 - mmengine - INFO - Epoch(val) [10][400/407] eta: 0:00:01 time: 0.229763 data_time: 0.042669 memory: 2064 2022/09/14 16:17:29 - mmengine - INFO - Evaluating CocoMetric... 2022/09/14 16:17:42 - mmengine - INFO - Epoch(val) [10][407/407] coco/AP: 0.691103 coco/AP .5: 0.878836 coco/AP .75: 0.763922 coco/AP (M): 0.652058 coco/AP (L): 0.761958 coco/AR: 0.747103 coco/AR .5: 0.919710 coco/AR .75: 0.811398 coco/AR (M): 0.701721 coco/AR (L): 0.812709 2022/09/14 16:17:46 - mmengine - INFO - The best checkpoint with 0.6911 coco/AP at 10 epoch is saved to best_coco/AP_epoch_10.pth. 2022/09/14 16:18:10 - mmengine - INFO - Epoch(train) [11][50/586] lr: 5.000000e-04 eta: 15:19:03 time: 0.466940 data_time: 0.029176 memory: 15239 loss_kpt: 0.000749 acc_pose: 0.773956 loss: 0.000749 2022/09/14 16:18:34 - mmengine - INFO - Epoch(train) [11][100/586] lr: 5.000000e-04 eta: 15:18:50 time: 0.480661 data_time: 0.025768 memory: 15239 loss_kpt: 0.000738 acc_pose: 0.754187 loss: 0.000738 2022/09/14 16:18:52 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 16:18:56 - mmengine - INFO - Epoch(train) [11][150/586] lr: 5.000000e-04 eta: 15:18:13 time: 0.457889 data_time: 0.025847 memory: 15239 loss_kpt: 0.000738 acc_pose: 0.769443 loss: 0.000738 2022/09/14 16:19:20 - mmengine - INFO - Epoch(train) [11][200/586] lr: 5.000000e-04 eta: 15:17:45 time: 0.466111 data_time: 0.029017 memory: 15239 loss_kpt: 0.000745 acc_pose: 0.718434 loss: 0.000745 2022/09/14 16:19:43 - mmengine - INFO - Epoch(train) [11][250/586] lr: 5.000000e-04 eta: 15:17:12 time: 0.460376 data_time: 0.025439 memory: 15239 loss_kpt: 0.000728 acc_pose: 0.781659 loss: 0.000728 2022/09/14 16:20:06 - mmengine - INFO - Epoch(train) [11][300/586] lr: 5.000000e-04 eta: 15:16:43 time: 0.464602 data_time: 0.025721 memory: 15239 loss_kpt: 0.000740 acc_pose: 0.722109 loss: 0.000740 2022/09/14 16:20:29 - mmengine - INFO - Epoch(train) [11][350/586] lr: 5.000000e-04 eta: 15:16:15 time: 0.465796 data_time: 0.027234 memory: 15239 loss_kpt: 0.000706 acc_pose: 0.812131 loss: 0.000706 2022/09/14 16:20:53 - mmengine - INFO - Epoch(train) [11][400/586] lr: 5.000000e-04 eta: 15:15:50 time: 0.469197 data_time: 0.026103 memory: 15239 loss_kpt: 0.000752 acc_pose: 0.753009 loss: 0.000752 2022/09/14 16:21:16 - mmengine - INFO - Epoch(train) [11][450/586] lr: 5.000000e-04 eta: 15:15:22 time: 0.465116 data_time: 0.025779 memory: 15239 loss_kpt: 0.000730 acc_pose: 0.806630 loss: 0.000730 2022/09/14 16:21:39 - mmengine - INFO - Epoch(train) [11][500/586] lr: 5.000000e-04 eta: 15:14:51 time: 0.462498 data_time: 0.028762 memory: 15239 loss_kpt: 0.000747 acc_pose: 0.816761 loss: 0.000747 2022/09/14 16:22:03 - mmengine - INFO - Epoch(train) [11][550/586] lr: 5.000000e-04 eta: 15:14:33 time: 0.476212 data_time: 0.025503 memory: 15239 loss_kpt: 0.000737 acc_pose: 0.837020 loss: 0.000737 2022/09/14 16:22:19 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 16:22:19 - mmengine - INFO - Saving checkpoint at 11 epochs 2022/09/14 16:22:50 - mmengine - INFO - Epoch(train) [12][50/586] lr: 5.000000e-04 eta: 15:08:43 time: 0.464847 data_time: 0.029669 memory: 15239 loss_kpt: 0.000749 acc_pose: 0.811748 loss: 0.000749 2022/09/14 16:23:13 - mmengine - INFO - Epoch(train) [12][100/586] lr: 5.000000e-04 eta: 15:08:19 time: 0.466338 data_time: 0.025470 memory: 15239 loss_kpt: 0.000722 acc_pose: 0.774808 loss: 0.000722 2022/09/14 16:23:37 - mmengine - INFO - Epoch(train) [12][150/586] lr: 5.000000e-04 eta: 15:08:00 time: 0.472460 data_time: 0.026372 memory: 15239 loss_kpt: 0.000745 acc_pose: 0.793556 loss: 0.000745 2022/09/14 16:24:00 - mmengine - INFO - Epoch(train) [12][200/586] lr: 5.000000e-04 eta: 15:07:30 time: 0.461002 data_time: 0.027724 memory: 15239 loss_kpt: 0.000725 acc_pose: 0.806158 loss: 0.000725 2022/09/14 16:24:23 - mmengine - INFO - Epoch(train) [12][250/586] lr: 5.000000e-04 eta: 15:07:09 time: 0.470580 data_time: 0.027416 memory: 15239 loss_kpt: 0.000706 acc_pose: 0.821703 loss: 0.000706 2022/09/14 16:24:47 - mmengine - INFO - Epoch(train) [12][300/586] lr: 5.000000e-04 eta: 15:06:49 time: 0.471134 data_time: 0.027289 memory: 15239 loss_kpt: 0.000741 acc_pose: 0.792435 loss: 0.000741 2022/09/14 16:25:10 - mmengine - INFO - Epoch(train) [12][350/586] lr: 5.000000e-04 eta: 15:06:19 time: 0.460314 data_time: 0.025595 memory: 15239 loss_kpt: 0.000746 acc_pose: 0.807402 loss: 0.000746 2022/09/14 16:25:33 - mmengine - INFO - Epoch(train) [12][400/586] lr: 5.000000e-04 eta: 15:05:58 time: 0.470367 data_time: 0.027522 memory: 15239 loss_kpt: 0.000718 acc_pose: 0.806426 loss: 0.000718 2022/09/14 16:25:57 - mmengine - INFO - Epoch(train) [12][450/586] lr: 5.000000e-04 eta: 15:05:34 time: 0.467088 data_time: 0.026630 memory: 15239 loss_kpt: 0.000735 acc_pose: 0.763890 loss: 0.000735 2022/09/14 16:26:20 - mmengine - INFO - Epoch(train) [12][500/586] lr: 5.000000e-04 eta: 15:05:07 time: 0.463575 data_time: 0.025968 memory: 15239 loss_kpt: 0.000726 acc_pose: 0.847717 loss: 0.000726 2022/09/14 16:26:43 - mmengine - INFO - Epoch(train) [12][550/586] lr: 5.000000e-04 eta: 15:04:48 time: 0.473334 data_time: 0.024846 memory: 15239 loss_kpt: 0.000700 acc_pose: 0.820661 loss: 0.000700 2022/09/14 16:26:45 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 16:27:00 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 16:27:00 - mmengine - INFO - Saving checkpoint at 12 epochs 2022/09/14 16:27:30 - mmengine - INFO - Epoch(train) [13][50/586] lr: 5.000000e-04 eta: 14:59:35 time: 0.470935 data_time: 0.029790 memory: 15239 loss_kpt: 0.000742 acc_pose: 0.753903 loss: 0.000742 2022/09/14 16:27:54 - mmengine - INFO - Epoch(train) [13][100/586] lr: 5.000000e-04 eta: 14:59:14 time: 0.468536 data_time: 0.026251 memory: 15239 loss_kpt: 0.000729 acc_pose: 0.798699 loss: 0.000729 2022/09/14 16:28:17 - mmengine - INFO - Epoch(train) [13][150/586] lr: 5.000000e-04 eta: 14:58:48 time: 0.462222 data_time: 0.025651 memory: 15239 loss_kpt: 0.000740 acc_pose: 0.756391 loss: 0.000740 2022/09/14 16:28:40 - mmengine - INFO - Epoch(train) [13][200/586] lr: 5.000000e-04 eta: 14:58:22 time: 0.461574 data_time: 0.024874 memory: 15239 loss_kpt: 0.000726 acc_pose: 0.743132 loss: 0.000726 2022/09/14 16:29:03 - mmengine - INFO - Epoch(train) [13][250/586] lr: 5.000000e-04 eta: 14:58:04 time: 0.471424 data_time: 0.030652 memory: 15239 loss_kpt: 0.000730 acc_pose: 0.812192 loss: 0.000730 2022/09/14 16:29:27 - mmengine - INFO - Epoch(train) [13][300/586] lr: 5.000000e-04 eta: 14:57:38 time: 0.462338 data_time: 0.026423 memory: 15239 loss_kpt: 0.000724 acc_pose: 0.777275 loss: 0.000724 2022/09/14 16:29:50 - mmengine - INFO - Epoch(train) [13][350/586] lr: 5.000000e-04 eta: 14:57:12 time: 0.462400 data_time: 0.025879 memory: 15239 loss_kpt: 0.000704 acc_pose: 0.836014 loss: 0.000704 2022/09/14 16:30:13 - mmengine - INFO - Epoch(train) [13][400/586] lr: 5.000000e-04 eta: 14:56:52 time: 0.469392 data_time: 0.029006 memory: 15239 loss_kpt: 0.000727 acc_pose: 0.821349 loss: 0.000727 2022/09/14 16:30:36 - mmengine - INFO - Epoch(train) [13][450/586] lr: 5.000000e-04 eta: 14:56:27 time: 0.463528 data_time: 0.026622 memory: 15239 loss_kpt: 0.000738 acc_pose: 0.784219 loss: 0.000738 2022/09/14 16:31:00 - mmengine - INFO - Epoch(train) [13][500/586] lr: 5.000000e-04 eta: 14:56:03 time: 0.463971 data_time: 0.026128 memory: 15239 loss_kpt: 0.000722 acc_pose: 0.745328 loss: 0.000722 2022/09/14 16:31:23 - mmengine - INFO - Epoch(train) [13][550/586] lr: 5.000000e-04 eta: 14:55:44 time: 0.471202 data_time: 0.028820 memory: 15239 loss_kpt: 0.000734 acc_pose: 0.832324 loss: 0.000734 2022/09/14 16:31:40 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 16:31:40 - mmengine - INFO - Saving checkpoint at 13 epochs 2022/09/14 16:32:10 - mmengine - INFO - Epoch(train) [14][50/586] lr: 5.000000e-04 eta: 14:50:52 time: 0.465749 data_time: 0.033031 memory: 15239 loss_kpt: 0.000739 acc_pose: 0.773708 loss: 0.000739 2022/09/14 16:32:33 - mmengine - INFO - Epoch(train) [14][100/586] lr: 5.000000e-04 eta: 14:50:35 time: 0.471079 data_time: 0.025847 memory: 15239 loss_kpt: 0.000719 acc_pose: 0.742654 loss: 0.000719 2022/09/14 16:32:57 - mmengine - INFO - Epoch(train) [14][150/586] lr: 5.000000e-04 eta: 14:50:18 time: 0.471908 data_time: 0.026640 memory: 15239 loss_kpt: 0.000735 acc_pose: 0.796808 loss: 0.000735 2022/09/14 16:33:20 - mmengine - INFO - Epoch(train) [14][200/586] lr: 5.000000e-04 eta: 14:49:51 time: 0.457479 data_time: 0.025701 memory: 15239 loss_kpt: 0.000705 acc_pose: 0.782609 loss: 0.000705 2022/09/14 16:33:43 - mmengine - INFO - Epoch(train) [14][250/586] lr: 5.000000e-04 eta: 14:49:36 time: 0.474412 data_time: 0.026952 memory: 15239 loss_kpt: 0.000709 acc_pose: 0.791507 loss: 0.000709 2022/09/14 16:34:07 - mmengine - INFO - Epoch(train) [14][300/586] lr: 5.000000e-04 eta: 14:49:17 time: 0.468852 data_time: 0.026253 memory: 15239 loss_kpt: 0.000709 acc_pose: 0.774612 loss: 0.000709 2022/09/14 16:34:30 - mmengine - INFO - Epoch(train) [14][350/586] lr: 5.000000e-04 eta: 14:48:55 time: 0.465134 data_time: 0.026431 memory: 15239 loss_kpt: 0.000714 acc_pose: 0.733643 loss: 0.000714 2022/09/14 16:34:45 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 16:34:54 - mmengine - INFO - Epoch(train) [14][400/586] lr: 5.000000e-04 eta: 14:48:37 time: 0.471455 data_time: 0.026093 memory: 15239 loss_kpt: 0.000711 acc_pose: 0.774420 loss: 0.000711 2022/09/14 16:35:17 - mmengine - INFO - Epoch(train) [14][450/586] lr: 5.000000e-04 eta: 14:48:22 time: 0.474188 data_time: 0.024806 memory: 15239 loss_kpt: 0.000743 acc_pose: 0.751882 loss: 0.000743 2022/09/14 16:35:41 - mmengine - INFO - Epoch(train) [14][500/586] lr: 5.000000e-04 eta: 14:48:03 time: 0.469347 data_time: 0.026957 memory: 15239 loss_kpt: 0.000706 acc_pose: 0.721839 loss: 0.000706 2022/09/14 16:36:04 - mmengine - INFO - Epoch(train) [14][550/586] lr: 5.000000e-04 eta: 14:47:46 time: 0.473161 data_time: 0.025103 memory: 15239 loss_kpt: 0.000701 acc_pose: 0.822078 loss: 0.000701 2022/09/14 16:36:21 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 16:36:21 - mmengine - INFO - Saving checkpoint at 14 epochs 2022/09/14 16:36:52 - mmengine - INFO - Epoch(train) [15][50/586] lr: 5.000000e-04 eta: 14:43:17 time: 0.467223 data_time: 0.028868 memory: 15239 loss_kpt: 0.000718 acc_pose: 0.865757 loss: 0.000718 2022/09/14 16:37:16 - mmengine - INFO - Epoch(train) [15][100/586] lr: 5.000000e-04 eta: 14:42:59 time: 0.469992 data_time: 0.025696 memory: 15239 loss_kpt: 0.000721 acc_pose: 0.779204 loss: 0.000721 2022/09/14 16:37:39 - mmengine - INFO - Epoch(train) [15][150/586] lr: 5.000000e-04 eta: 14:42:40 time: 0.466337 data_time: 0.025120 memory: 15239 loss_kpt: 0.000696 acc_pose: 0.761035 loss: 0.000696 2022/09/14 16:38:02 - mmengine - INFO - Epoch(train) [15][200/586] lr: 5.000000e-04 eta: 14:42:23 time: 0.470911 data_time: 0.025474 memory: 15239 loss_kpt: 0.000701 acc_pose: 0.867402 loss: 0.000701 2022/09/14 16:38:26 - mmengine - INFO - Epoch(train) [15][250/586] lr: 5.000000e-04 eta: 14:42:02 time: 0.464803 data_time: 0.025620 memory: 15239 loss_kpt: 0.000699 acc_pose: 0.783773 loss: 0.000699 2022/09/14 16:38:49 - mmengine - INFO - Epoch(train) [15][300/586] lr: 5.000000e-04 eta: 14:41:39 time: 0.462547 data_time: 0.026568 memory: 15239 loss_kpt: 0.000705 acc_pose: 0.854330 loss: 0.000705 2022/09/14 16:39:12 - mmengine - INFO - Epoch(train) [15][350/586] lr: 5.000000e-04 eta: 14:41:20 time: 0.467594 data_time: 0.025191 memory: 15239 loss_kpt: 0.000698 acc_pose: 0.787322 loss: 0.000698 2022/09/14 16:39:36 - mmengine - INFO - Epoch(train) [15][400/586] lr: 5.000000e-04 eta: 14:41:01 time: 0.468250 data_time: 0.025621 memory: 15239 loss_kpt: 0.000707 acc_pose: 0.762184 loss: 0.000707 2022/09/14 16:39:58 - mmengine - INFO - Epoch(train) [15][450/586] lr: 5.000000e-04 eta: 14:40:35 time: 0.457459 data_time: 0.025733 memory: 15239 loss_kpt: 0.000709 acc_pose: 0.771118 loss: 0.000709 2022/09/14 16:40:22 - mmengine - INFO - Epoch(train) [15][500/586] lr: 5.000000e-04 eta: 14:40:14 time: 0.464372 data_time: 0.024928 memory: 15239 loss_kpt: 0.000703 acc_pose: 0.775318 loss: 0.000703 2022/09/14 16:40:45 - mmengine - INFO - Epoch(train) [15][550/586] lr: 5.000000e-04 eta: 14:40:00 time: 0.475648 data_time: 0.026077 memory: 15239 loss_kpt: 0.000740 acc_pose: 0.796053 loss: 0.000740 2022/09/14 16:41:02 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 16:41:02 - mmengine - INFO - Saving checkpoint at 15 epochs 2022/09/14 16:41:34 - mmengine - INFO - Epoch(train) [16][50/586] lr: 5.000000e-04 eta: 14:36:05 time: 0.493365 data_time: 0.037008 memory: 15239 loss_kpt: 0.000716 acc_pose: 0.825061 loss: 0.000716 2022/09/14 16:41:58 - mmengine - INFO - Epoch(train) [16][100/586] lr: 5.000000e-04 eta: 14:35:54 time: 0.477767 data_time: 0.030019 memory: 15239 loss_kpt: 0.000710 acc_pose: 0.793159 loss: 0.000710 2022/09/14 16:42:22 - mmengine - INFO - Epoch(train) [16][150/586] lr: 5.000000e-04 eta: 14:35:39 time: 0.474071 data_time: 0.032798 memory: 15239 loss_kpt: 0.000694 acc_pose: 0.820114 loss: 0.000694 2022/09/14 16:42:46 - mmengine - INFO - Epoch(train) [16][200/586] lr: 5.000000e-04 eta: 14:35:24 time: 0.472461 data_time: 0.033064 memory: 15239 loss_kpt: 0.000711 acc_pose: 0.786392 loss: 0.000711 2022/09/14 16:42:50 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 16:43:09 - mmengine - INFO - Epoch(train) [16][250/586] lr: 5.000000e-04 eta: 14:35:06 time: 0.468049 data_time: 0.037271 memory: 15239 loss_kpt: 0.000715 acc_pose: 0.810418 loss: 0.000715 2022/09/14 16:43:32 - mmengine - INFO - Epoch(train) [16][300/586] lr: 5.000000e-04 eta: 14:34:46 time: 0.465536 data_time: 0.032285 memory: 15239 loss_kpt: 0.000708 acc_pose: 0.860171 loss: 0.000708 2022/09/14 16:43:56 - mmengine - INFO - Epoch(train) [16][350/586] lr: 5.000000e-04 eta: 14:34:30 time: 0.471944 data_time: 0.032614 memory: 15239 loss_kpt: 0.000703 acc_pose: 0.680055 loss: 0.000703 2022/09/14 16:44:19 - mmengine - INFO - Epoch(train) [16][400/586] lr: 5.000000e-04 eta: 14:34:14 time: 0.472428 data_time: 0.032556 memory: 15239 loss_kpt: 0.000701 acc_pose: 0.814680 loss: 0.000701 2022/09/14 16:44:43 - mmengine - INFO - Epoch(train) [16][450/586] lr: 5.000000e-04 eta: 14:33:54 time: 0.464610 data_time: 0.034408 memory: 15239 loss_kpt: 0.000718 acc_pose: 0.687546 loss: 0.000718 2022/09/14 16:45:07 - mmengine - INFO - Epoch(train) [16][500/586] lr: 5.000000e-04 eta: 14:33:46 time: 0.485077 data_time: 0.039080 memory: 15239 loss_kpt: 0.000685 acc_pose: 0.771052 loss: 0.000685 2022/09/14 16:45:31 - mmengine - INFO - Epoch(train) [16][550/586] lr: 5.000000e-04 eta: 14:33:32 time: 0.475737 data_time: 0.034374 memory: 15239 loss_kpt: 0.000726 acc_pose: 0.812911 loss: 0.000726 2022/09/14 16:45:47 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 16:45:47 - mmengine - INFO - Saving checkpoint at 16 epochs 2022/09/14 16:46:18 - mmengine - INFO - Epoch(train) [17][50/586] lr: 5.000000e-04 eta: 14:29:42 time: 0.477975 data_time: 0.032645 memory: 15239 loss_kpt: 0.000702 acc_pose: 0.778539 loss: 0.000702 2022/09/14 16:46:41 - mmengine - INFO - Epoch(train) [17][100/586] lr: 5.000000e-04 eta: 14:29:25 time: 0.468789 data_time: 0.025947 memory: 15239 loss_kpt: 0.000686 acc_pose: 0.771781 loss: 0.000686 2022/09/14 16:47:05 - mmengine - INFO - Epoch(train) [17][150/586] lr: 5.000000e-04 eta: 14:29:09 time: 0.470643 data_time: 0.025199 memory: 15239 loss_kpt: 0.000706 acc_pose: 0.780040 loss: 0.000706 2022/09/14 16:47:28 - mmengine - INFO - Epoch(train) [17][200/586] lr: 5.000000e-04 eta: 14:28:50 time: 0.466456 data_time: 0.025226 memory: 15239 loss_kpt: 0.000703 acc_pose: 0.807951 loss: 0.000703 2022/09/14 16:47:52 - mmengine - INFO - Epoch(train) [17][250/586] lr: 5.000000e-04 eta: 14:28:36 time: 0.473586 data_time: 0.030778 memory: 15239 loss_kpt: 0.000692 acc_pose: 0.776335 loss: 0.000692 2022/09/14 16:48:15 - mmengine - INFO - Epoch(train) [17][300/586] lr: 5.000000e-04 eta: 14:28:19 time: 0.469540 data_time: 0.026291 memory: 15239 loss_kpt: 0.000711 acc_pose: 0.775437 loss: 0.000711 2022/09/14 16:48:38 - mmengine - INFO - Epoch(train) [17][350/586] lr: 5.000000e-04 eta: 14:27:57 time: 0.461297 data_time: 0.025928 memory: 15239 loss_kpt: 0.000684 acc_pose: 0.833370 loss: 0.000684 2022/09/14 16:49:02 - mmengine - INFO - Epoch(train) [17][400/586] lr: 5.000000e-04 eta: 14:27:43 time: 0.475635 data_time: 0.025200 memory: 15239 loss_kpt: 0.000692 acc_pose: 0.835718 loss: 0.000692 2022/09/14 16:49:25 - mmengine - INFO - Epoch(train) [17][450/586] lr: 5.000000e-04 eta: 14:27:23 time: 0.465177 data_time: 0.026646 memory: 15239 loss_kpt: 0.000707 acc_pose: 0.772275 loss: 0.000707 2022/09/14 16:49:49 - mmengine - INFO - Epoch(train) [17][500/586] lr: 5.000000e-04 eta: 14:27:03 time: 0.464938 data_time: 0.025685 memory: 15239 loss_kpt: 0.000692 acc_pose: 0.760310 loss: 0.000692 2022/09/14 16:50:13 - mmengine - INFO - Epoch(train) [17][550/586] lr: 5.000000e-04 eta: 14:26:52 time: 0.479402 data_time: 0.029153 memory: 15239 loss_kpt: 0.000710 acc_pose: 0.735373 loss: 0.000710 2022/09/14 16:50:29 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 16:50:29 - mmengine - INFO - Saving checkpoint at 17 epochs 2022/09/14 16:50:54 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 16:51:00 - mmengine - INFO - Epoch(train) [18][50/586] lr: 5.000000e-04 eta: 14:23:14 time: 0.474430 data_time: 0.030422 memory: 15239 loss_kpt: 0.000718 acc_pose: 0.791712 loss: 0.000718 2022/09/14 16:51:24 - mmengine - INFO - Epoch(train) [18][100/586] lr: 5.000000e-04 eta: 14:23:05 time: 0.483237 data_time: 0.025157 memory: 15239 loss_kpt: 0.000686 acc_pose: 0.822279 loss: 0.000686 2022/09/14 16:51:47 - mmengine - INFO - Epoch(train) [18][150/586] lr: 5.000000e-04 eta: 14:22:46 time: 0.465492 data_time: 0.024992 memory: 15239 loss_kpt: 0.000688 acc_pose: 0.802055 loss: 0.000688 2022/09/14 16:52:11 - mmengine - INFO - Epoch(train) [18][200/586] lr: 5.000000e-04 eta: 14:22:30 time: 0.471751 data_time: 0.028630 memory: 15239 loss_kpt: 0.000691 acc_pose: 0.749501 loss: 0.000691 2022/09/14 16:52:34 - mmengine - INFO - Epoch(train) [18][250/586] lr: 5.000000e-04 eta: 14:22:11 time: 0.464259 data_time: 0.025893 memory: 15239 loss_kpt: 0.000678 acc_pose: 0.714938 loss: 0.000678 2022/09/14 16:52:58 - mmengine - INFO - Epoch(train) [18][300/586] lr: 5.000000e-04 eta: 14:21:59 time: 0.478043 data_time: 0.025943 memory: 15239 loss_kpt: 0.000680 acc_pose: 0.749446 loss: 0.000680 2022/09/14 16:53:22 - mmengine - INFO - Epoch(train) [18][350/586] lr: 5.000000e-04 eta: 14:21:45 time: 0.476539 data_time: 0.025690 memory: 15239 loss_kpt: 0.000698 acc_pose: 0.818059 loss: 0.000698 2022/09/14 16:53:46 - mmengine - INFO - Epoch(train) [18][400/586] lr: 5.000000e-04 eta: 14:21:36 time: 0.482587 data_time: 0.026590 memory: 15239 loss_kpt: 0.000701 acc_pose: 0.820434 loss: 0.000701 2022/09/14 16:54:10 - mmengine - INFO - Epoch(train) [18][450/586] lr: 5.000000e-04 eta: 14:21:21 time: 0.473354 data_time: 0.026714 memory: 15239 loss_kpt: 0.000685 acc_pose: 0.766804 loss: 0.000685 2022/09/14 16:54:33 - mmengine - INFO - Epoch(train) [18][500/586] lr: 5.000000e-04 eta: 14:21:01 time: 0.464528 data_time: 0.029117 memory: 15239 loss_kpt: 0.000714 acc_pose: 0.873550 loss: 0.000714 2022/09/14 16:54:56 - mmengine - INFO - Epoch(train) [18][550/586] lr: 5.000000e-04 eta: 14:20:41 time: 0.464223 data_time: 0.025238 memory: 15239 loss_kpt: 0.000699 acc_pose: 0.801557 loss: 0.000699 2022/09/14 16:55:13 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 16:55:13 - mmengine - INFO - Saving checkpoint at 18 epochs 2022/09/14 16:55:44 - mmengine - INFO - Epoch(train) [19][50/586] lr: 5.000000e-04 eta: 14:17:13 time: 0.472653 data_time: 0.028680 memory: 15239 loss_kpt: 0.000673 acc_pose: 0.749088 loss: 0.000673 2022/09/14 16:56:07 - mmengine - INFO - Epoch(train) [19][100/586] lr: 5.000000e-04 eta: 14:16:57 time: 0.469551 data_time: 0.025733 memory: 15239 loss_kpt: 0.000675 acc_pose: 0.743472 loss: 0.000675 2022/09/14 16:56:30 - mmengine - INFO - Epoch(train) [19][150/586] lr: 5.000000e-04 eta: 14:16:35 time: 0.458884 data_time: 0.025241 memory: 15239 loss_kpt: 0.000692 acc_pose: 0.729158 loss: 0.000692 2022/09/14 16:56:54 - mmengine - INFO - Epoch(train) [19][200/586] lr: 5.000000e-04 eta: 14:16:19 time: 0.470618 data_time: 0.028455 memory: 15239 loss_kpt: 0.000669 acc_pose: 0.847806 loss: 0.000669 2022/09/14 16:57:17 - mmengine - INFO - Epoch(train) [19][250/586] lr: 5.000000e-04 eta: 14:16:04 time: 0.472193 data_time: 0.037536 memory: 15239 loss_kpt: 0.000694 acc_pose: 0.761984 loss: 0.000694 2022/09/14 16:57:41 - mmengine - INFO - Epoch(train) [19][300/586] lr: 5.000000e-04 eta: 14:15:47 time: 0.469820 data_time: 0.027396 memory: 15239 loss_kpt: 0.000692 acc_pose: 0.808986 loss: 0.000692 2022/09/14 16:58:04 - mmengine - INFO - Epoch(train) [19][350/586] lr: 5.000000e-04 eta: 14:15:27 time: 0.464085 data_time: 0.025365 memory: 15239 loss_kpt: 0.000704 acc_pose: 0.803764 loss: 0.000704 2022/09/14 16:58:27 - mmengine - INFO - Epoch(train) [19][400/586] lr: 5.000000e-04 eta: 14:15:11 time: 0.469329 data_time: 0.025906 memory: 15239 loss_kpt: 0.000687 acc_pose: 0.788297 loss: 0.000687 2022/09/14 16:58:50 - mmengine - INFO - Epoch(train) [19][450/586] lr: 5.000000e-04 eta: 14:14:50 time: 0.462266 data_time: 0.026382 memory: 15239 loss_kpt: 0.000702 acc_pose: 0.793344 loss: 0.000702 2022/09/14 16:58:51 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 16:59:14 - mmengine - INFO - Epoch(train) [19][500/586] lr: 5.000000e-04 eta: 14:14:30 time: 0.463624 data_time: 0.025801 memory: 15239 loss_kpt: 0.000686 acc_pose: 0.819961 loss: 0.000686 2022/09/14 16:59:37 - mmengine - INFO - Epoch(train) [19][550/586] lr: 5.000000e-04 eta: 14:14:15 time: 0.473712 data_time: 0.026718 memory: 15239 loss_kpt: 0.000673 acc_pose: 0.873732 loss: 0.000673 2022/09/14 16:59:54 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 16:59:54 - mmengine - INFO - Saving checkpoint at 19 epochs 2022/09/14 17:00:25 - mmengine - INFO - Epoch(train) [20][50/586] lr: 5.000000e-04 eta: 14:11:08 time: 0.491305 data_time: 0.040746 memory: 15239 loss_kpt: 0.000688 acc_pose: 0.795503 loss: 0.000688 2022/09/14 17:00:49 - mmengine - INFO - Epoch(train) [20][100/586] lr: 5.000000e-04 eta: 14:10:53 time: 0.471494 data_time: 0.025324 memory: 15239 loss_kpt: 0.000692 acc_pose: 0.819465 loss: 0.000692 2022/09/14 17:01:12 - mmengine - INFO - Epoch(train) [20][150/586] lr: 5.000000e-04 eta: 14:10:35 time: 0.467723 data_time: 0.028924 memory: 15239 loss_kpt: 0.000682 acc_pose: 0.838424 loss: 0.000682 2022/09/14 17:01:36 - mmengine - INFO - Epoch(train) [20][200/586] lr: 5.000000e-04 eta: 14:10:17 time: 0.465102 data_time: 0.026341 memory: 15239 loss_kpt: 0.000678 acc_pose: 0.865266 loss: 0.000678 2022/09/14 17:01:59 - mmengine - INFO - Epoch(train) [20][250/586] lr: 5.000000e-04 eta: 14:09:56 time: 0.460609 data_time: 0.025751 memory: 15239 loss_kpt: 0.000704 acc_pose: 0.794655 loss: 0.000704 2022/09/14 17:02:22 - mmengine - INFO - Epoch(train) [20][300/586] lr: 5.000000e-04 eta: 14:09:40 time: 0.470678 data_time: 0.030231 memory: 15239 loss_kpt: 0.000696 acc_pose: 0.736310 loss: 0.000696 2022/09/14 17:02:45 - mmengine - INFO - Epoch(train) [20][350/586] lr: 5.000000e-04 eta: 14:09:19 time: 0.461538 data_time: 0.026142 memory: 15239 loss_kpt: 0.000680 acc_pose: 0.798020 loss: 0.000680 2022/09/14 17:03:09 - mmengine - INFO - Epoch(train) [20][400/586] lr: 5.000000e-04 eta: 14:09:04 time: 0.471548 data_time: 0.027063 memory: 15239 loss_kpt: 0.000679 acc_pose: 0.773077 loss: 0.000679 2022/09/14 17:03:32 - mmengine - INFO - Epoch(train) [20][450/586] lr: 5.000000e-04 eta: 14:08:48 time: 0.470930 data_time: 0.028608 memory: 15239 loss_kpt: 0.000652 acc_pose: 0.791800 loss: 0.000652 2022/09/14 17:03:55 - mmengine - INFO - Epoch(train) [20][500/586] lr: 5.000000e-04 eta: 14:08:27 time: 0.462558 data_time: 0.026762 memory: 15239 loss_kpt: 0.000681 acc_pose: 0.766650 loss: 0.000681 2022/09/14 17:04:19 - mmengine - INFO - Epoch(train) [20][550/586] lr: 5.000000e-04 eta: 14:08:08 time: 0.464232 data_time: 0.027322 memory: 15239 loss_kpt: 0.000699 acc_pose: 0.771209 loss: 0.000699 2022/09/14 17:04:35 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 17:04:35 - mmengine - INFO - Saving checkpoint at 20 epochs 2022/09/14 17:04:53 - mmengine - INFO - Epoch(val) [20][50/407] eta: 0:01:12 time: 0.203294 data_time: 0.016427 memory: 15239 2022/09/14 17:05:03 - mmengine - INFO - Epoch(val) [20][100/407] eta: 0:01:00 time: 0.197718 data_time: 0.011462 memory: 2064 2022/09/14 17:05:13 - mmengine - INFO - Epoch(val) [20][150/407] eta: 0:00:50 time: 0.196378 data_time: 0.008664 memory: 2064 2022/09/14 17:05:23 - mmengine - INFO - Epoch(val) [20][200/407] eta: 0:00:40 time: 0.194446 data_time: 0.008820 memory: 2064 2022/09/14 17:05:32 - mmengine - INFO - Epoch(val) [20][250/407] eta: 0:00:31 time: 0.198562 data_time: 0.008153 memory: 2064 2022/09/14 17:05:42 - mmengine - INFO - Epoch(val) [20][300/407] eta: 0:00:20 time: 0.195224 data_time: 0.009464 memory: 2064 2022/09/14 17:05:52 - mmengine - INFO - Epoch(val) [20][350/407] eta: 0:00:11 time: 0.193974 data_time: 0.008356 memory: 2064 2022/09/14 17:06:02 - mmengine - INFO - Epoch(val) [20][400/407] eta: 0:00:01 time: 0.191748 data_time: 0.007596 memory: 2064 2022/09/14 17:06:39 - mmengine - INFO - Evaluating CocoMetric... 2022/09/14 17:06:53 - mmengine - INFO - Epoch(val) [20][407/407] coco/AP: 0.719466 coco/AP .5: 0.890740 coco/AP .75: 0.789114 coco/AP (M): 0.680933 coco/AP (L): 0.789574 coco/AR: 0.772072 coco/AR .5: 0.928526 coco/AR .75: 0.833911 coco/AR (M): 0.726823 coco/AR (L): 0.837087 2022/09/14 17:06:53 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220914/hrnet_w48_384/best_coco/AP_epoch_10.pth is removed 2022/09/14 17:06:57 - mmengine - INFO - The best checkpoint with 0.7195 coco/AP at 20 epoch is saved to best_coco/AP_epoch_20.pth. 2022/09/14 17:07:21 - mmengine - INFO - Epoch(train) [21][50/586] lr: 5.000000e-04 eta: 14:05:02 time: 0.476040 data_time: 0.033394 memory: 15239 loss_kpt: 0.000677 acc_pose: 0.794946 loss: 0.000677 2022/09/14 17:07:44 - mmengine - INFO - Epoch(train) [21][100/586] lr: 5.000000e-04 eta: 14:04:43 time: 0.463097 data_time: 0.024930 memory: 15239 loss_kpt: 0.000684 acc_pose: 0.833486 loss: 0.000684 2022/09/14 17:08:07 - mmengine - INFO - Epoch(train) [21][150/586] lr: 5.000000e-04 eta: 14:04:27 time: 0.469436 data_time: 0.024895 memory: 15239 loss_kpt: 0.000660 acc_pose: 0.771357 loss: 0.000660 2022/09/14 17:08:31 - mmengine - INFO - Epoch(train) [21][200/586] lr: 5.000000e-04 eta: 14:04:13 time: 0.474056 data_time: 0.026297 memory: 15239 loss_kpt: 0.000693 acc_pose: 0.674614 loss: 0.000693 2022/09/14 17:08:55 - mmengine - INFO - Epoch(train) [21][250/586] lr: 5.000000e-04 eta: 14:03:58 time: 0.473811 data_time: 0.026158 memory: 15239 loss_kpt: 0.000667 acc_pose: 0.873603 loss: 0.000667 2022/09/14 17:09:09 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 17:09:19 - mmengine - INFO - Epoch(train) [21][300/586] lr: 5.000000e-04 eta: 14:03:44 time: 0.474839 data_time: 0.026164 memory: 15239 loss_kpt: 0.000661 acc_pose: 0.738092 loss: 0.000661 2022/09/14 17:09:42 - mmengine - INFO - Epoch(train) [21][350/586] lr: 5.000000e-04 eta: 14:03:29 time: 0.471532 data_time: 0.029531 memory: 15239 loss_kpt: 0.000664 acc_pose: 0.826663 loss: 0.000664 2022/09/14 17:10:06 - mmengine - INFO - Epoch(train) [21][400/586] lr: 5.000000e-04 eta: 14:03:12 time: 0.470420 data_time: 0.026018 memory: 15239 loss_kpt: 0.000673 acc_pose: 0.782951 loss: 0.000673 2022/09/14 17:10:29 - mmengine - INFO - Epoch(train) [21][450/586] lr: 5.000000e-04 eta: 14:02:51 time: 0.460258 data_time: 0.025196 memory: 15239 loss_kpt: 0.000678 acc_pose: 0.791428 loss: 0.000678 2022/09/14 17:10:53 - mmengine - INFO - Epoch(train) [21][500/586] lr: 5.000000e-04 eta: 14:02:38 time: 0.476172 data_time: 0.029638 memory: 15239 loss_kpt: 0.000683 acc_pose: 0.786119 loss: 0.000683 2022/09/14 17:11:16 - mmengine - INFO - Epoch(train) [21][550/586] lr: 5.000000e-04 eta: 14:02:18 time: 0.462551 data_time: 0.025170 memory: 15239 loss_kpt: 0.000672 acc_pose: 0.797350 loss: 0.000672 2022/09/14 17:11:32 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 17:11:32 - mmengine - INFO - Saving checkpoint at 21 epochs 2022/09/14 17:12:04 - mmengine - INFO - Epoch(train) [22][50/586] lr: 5.000000e-04 eta: 13:59:24 time: 0.483794 data_time: 0.029041 memory: 15239 loss_kpt: 0.000688 acc_pose: 0.756153 loss: 0.000688 2022/09/14 17:12:27 - mmengine - INFO - Epoch(train) [22][100/586] lr: 5.000000e-04 eta: 13:59:07 time: 0.468536 data_time: 0.025322 memory: 15239 loss_kpt: 0.000699 acc_pose: 0.826741 loss: 0.000699 2022/09/14 17:12:50 - mmengine - INFO - Epoch(train) [22][150/586] lr: 5.000000e-04 eta: 13:58:50 time: 0.466942 data_time: 0.025500 memory: 15239 loss_kpt: 0.000670 acc_pose: 0.814895 loss: 0.000670 2022/09/14 17:13:14 - mmengine - INFO - Epoch(train) [22][200/586] lr: 5.000000e-04 eta: 13:58:35 time: 0.473091 data_time: 0.025914 memory: 15239 loss_kpt: 0.000682 acc_pose: 0.823398 loss: 0.000682 2022/09/14 17:13:38 - mmengine - INFO - Epoch(train) [22][250/586] lr: 5.000000e-04 eta: 13:58:26 time: 0.485715 data_time: 0.030819 memory: 15239 loss_kpt: 0.000678 acc_pose: 0.772838 loss: 0.000678 2022/09/14 17:14:02 - mmengine - INFO - Epoch(train) [22][300/586] lr: 5.000000e-04 eta: 13:58:08 time: 0.467377 data_time: 0.026071 memory: 15239 loss_kpt: 0.000675 acc_pose: 0.774421 loss: 0.000675 2022/09/14 17:14:25 - mmengine - INFO - Epoch(train) [22][350/586] lr: 5.000000e-04 eta: 13:57:49 time: 0.462742 data_time: 0.024767 memory: 15239 loss_kpt: 0.000677 acc_pose: 0.807733 loss: 0.000677 2022/09/14 17:14:48 - mmengine - INFO - Epoch(train) [22][400/586] lr: 5.000000e-04 eta: 13:57:31 time: 0.466478 data_time: 0.024904 memory: 15239 loss_kpt: 0.000665 acc_pose: 0.834401 loss: 0.000665 2022/09/14 17:15:12 - mmengine - INFO - Epoch(train) [22][450/586] lr: 5.000000e-04 eta: 13:57:15 time: 0.471902 data_time: 0.028377 memory: 15239 loss_kpt: 0.000673 acc_pose: 0.809844 loss: 0.000673 2022/09/14 17:15:35 - mmengine - INFO - Epoch(train) [22][500/586] lr: 5.000000e-04 eta: 13:56:57 time: 0.466481 data_time: 0.025884 memory: 15239 loss_kpt: 0.000672 acc_pose: 0.754268 loss: 0.000672 2022/09/14 17:15:59 - mmengine - INFO - Epoch(train) [22][550/586] lr: 5.000000e-04 eta: 13:56:44 time: 0.477346 data_time: 0.025468 memory: 15239 loss_kpt: 0.000672 acc_pose: 0.761048 loss: 0.000672 2022/09/14 17:16:15 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 17:16:15 - mmengine - INFO - Saving checkpoint at 22 epochs 2022/09/14 17:16:47 - mmengine - INFO - Epoch(train) [23][50/586] lr: 5.000000e-04 eta: 13:53:58 time: 0.486896 data_time: 0.036482 memory: 15239 loss_kpt: 0.000660 acc_pose: 0.846129 loss: 0.000660 2022/09/14 17:17:10 - mmengine - INFO - Epoch(train) [23][100/586] lr: 5.000000e-04 eta: 13:53:42 time: 0.469633 data_time: 0.024675 memory: 15239 loss_kpt: 0.000665 acc_pose: 0.776280 loss: 0.000665 2022/09/14 17:17:14 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 17:17:33 - mmengine - INFO - Epoch(train) [23][150/586] lr: 5.000000e-04 eta: 13:53:25 time: 0.467469 data_time: 0.025741 memory: 15239 loss_kpt: 0.000641 acc_pose: 0.851853 loss: 0.000641 2022/09/14 17:17:57 - mmengine - INFO - Epoch(train) [23][200/586] lr: 5.000000e-04 eta: 13:53:11 time: 0.474872 data_time: 0.028764 memory: 15239 loss_kpt: 0.000680 acc_pose: 0.756964 loss: 0.000680 2022/09/14 17:18:21 - mmengine - INFO - Epoch(train) [23][250/586] lr: 5.000000e-04 eta: 13:52:58 time: 0.479553 data_time: 0.025390 memory: 15239 loss_kpt: 0.000674 acc_pose: 0.843076 loss: 0.000674 2022/09/14 17:18:44 - mmengine - INFO - Epoch(train) [23][300/586] lr: 5.000000e-04 eta: 13:52:41 time: 0.466708 data_time: 0.025859 memory: 15239 loss_kpt: 0.000677 acc_pose: 0.768639 loss: 0.000677 2022/09/14 17:19:08 - mmengine - INFO - Epoch(train) [23][350/586] lr: 5.000000e-04 eta: 13:52:24 time: 0.469832 data_time: 0.028887 memory: 15239 loss_kpt: 0.000684 acc_pose: 0.814142 loss: 0.000684 2022/09/14 17:19:31 - mmengine - INFO - Epoch(train) [23][400/586] lr: 5.000000e-04 eta: 13:52:06 time: 0.466614 data_time: 0.025080 memory: 15239 loss_kpt: 0.000658 acc_pose: 0.848019 loss: 0.000658 2022/09/14 17:19:55 - mmengine - INFO - Epoch(train) [23][450/586] lr: 5.000000e-04 eta: 13:51:49 time: 0.466895 data_time: 0.024909 memory: 15239 loss_kpt: 0.000687 acc_pose: 0.822904 loss: 0.000687 2022/09/14 17:20:18 - mmengine - INFO - Epoch(train) [23][500/586] lr: 5.000000e-04 eta: 13:51:29 time: 0.463200 data_time: 0.028499 memory: 15239 loss_kpt: 0.000652 acc_pose: 0.676920 loss: 0.000652 2022/09/14 17:20:41 - mmengine - INFO - Epoch(train) [23][550/586] lr: 5.000000e-04 eta: 13:51:14 time: 0.473102 data_time: 0.025295 memory: 15239 loss_kpt: 0.000663 acc_pose: 0.837637 loss: 0.000663 2022/09/14 17:20:58 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 17:20:58 - mmengine - INFO - Saving checkpoint at 23 epochs 2022/09/14 17:21:29 - mmengine - INFO - Epoch(train) [24][50/586] lr: 5.000000e-04 eta: 13:48:33 time: 0.480898 data_time: 0.036578 memory: 15239 loss_kpt: 0.000649 acc_pose: 0.792221 loss: 0.000649 2022/09/14 17:21:52 - mmengine - INFO - Epoch(train) [24][100/586] lr: 5.000000e-04 eta: 13:48:17 time: 0.472135 data_time: 0.035096 memory: 15239 loss_kpt: 0.000668 acc_pose: 0.791936 loss: 0.000668 2022/09/14 17:22:16 - mmengine - INFO - Epoch(train) [24][150/586] lr: 5.000000e-04 eta: 13:48:02 time: 0.471553 data_time: 0.034889 memory: 15239 loss_kpt: 0.000660 acc_pose: 0.817357 loss: 0.000660 2022/09/14 17:22:40 - mmengine - INFO - Epoch(train) [24][200/586] lr: 5.000000e-04 eta: 13:47:47 time: 0.473240 data_time: 0.030011 memory: 15239 loss_kpt: 0.000659 acc_pose: 0.749952 loss: 0.000659 2022/09/14 17:23:04 - mmengine - INFO - Epoch(train) [24][250/586] lr: 5.000000e-04 eta: 13:47:34 time: 0.479372 data_time: 0.033805 memory: 15239 loss_kpt: 0.000650 acc_pose: 0.765392 loss: 0.000650 2022/09/14 17:23:27 - mmengine - INFO - Epoch(train) [24][300/586] lr: 5.000000e-04 eta: 13:47:16 time: 0.465598 data_time: 0.034242 memory: 15239 loss_kpt: 0.000656 acc_pose: 0.725648 loss: 0.000656 2022/09/14 17:23:51 - mmengine - INFO - Epoch(train) [24][350/586] lr: 5.000000e-04 eta: 13:47:04 time: 0.481412 data_time: 0.034106 memory: 15239 loss_kpt: 0.000689 acc_pose: 0.793606 loss: 0.000689 2022/09/14 17:24:15 - mmengine - INFO - Epoch(train) [24][400/586] lr: 5.000000e-04 eta: 13:46:49 time: 0.474996 data_time: 0.036591 memory: 15239 loss_kpt: 0.000664 acc_pose: 0.785952 loss: 0.000664 2022/09/14 17:24:38 - mmengine - INFO - Epoch(train) [24][450/586] lr: 5.000000e-04 eta: 13:46:33 time: 0.471271 data_time: 0.032335 memory: 15239 loss_kpt: 0.000677 acc_pose: 0.793607 loss: 0.000677 2022/09/14 17:25:02 - mmengine - INFO - Epoch(train) [24][500/586] lr: 5.000000e-04 eta: 13:46:17 time: 0.470291 data_time: 0.031981 memory: 15239 loss_kpt: 0.000689 acc_pose: 0.785584 loss: 0.000689 2022/09/14 17:25:13 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 17:25:26 - mmengine - INFO - Epoch(train) [24][550/586] lr: 5.000000e-04 eta: 13:46:03 time: 0.477315 data_time: 0.029396 memory: 15239 loss_kpt: 0.000674 acc_pose: 0.853204 loss: 0.000674 2022/09/14 17:25:43 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 17:25:43 - mmengine - INFO - Saving checkpoint at 24 epochs 2022/09/14 17:26:13 - mmengine - INFO - Epoch(train) [25][50/586] lr: 5.000000e-04 eta: 13:43:26 time: 0.478078 data_time: 0.030093 memory: 15239 loss_kpt: 0.000668 acc_pose: 0.847945 loss: 0.000668 2022/09/14 17:26:37 - mmengine - INFO - Epoch(train) [25][100/586] lr: 5.000000e-04 eta: 13:43:13 time: 0.477858 data_time: 0.028849 memory: 15239 loss_kpt: 0.000663 acc_pose: 0.815440 loss: 0.000663 2022/09/14 17:27:01 - mmengine - INFO - Epoch(train) [25][150/586] lr: 5.000000e-04 eta: 13:42:58 time: 0.472363 data_time: 0.024861 memory: 15239 loss_kpt: 0.000659 acc_pose: 0.859984 loss: 0.000659 2022/09/14 17:27:25 - mmengine - INFO - Epoch(train) [25][200/586] lr: 5.000000e-04 eta: 13:42:47 time: 0.485063 data_time: 0.028769 memory: 15239 loss_kpt: 0.000656 acc_pose: 0.796272 loss: 0.000656 2022/09/14 17:27:49 - mmengine - INFO - Epoch(train) [25][250/586] lr: 5.000000e-04 eta: 13:42:30 time: 0.469013 data_time: 0.025808 memory: 15239 loss_kpt: 0.000680 acc_pose: 0.779426 loss: 0.000680 2022/09/14 17:28:12 - mmengine - INFO - Epoch(train) [25][300/586] lr: 5.000000e-04 eta: 13:42:15 time: 0.474716 data_time: 0.026189 memory: 15239 loss_kpt: 0.000661 acc_pose: 0.811961 loss: 0.000661 2022/09/14 17:28:36 - mmengine - INFO - Epoch(train) [25][350/586] lr: 5.000000e-04 eta: 13:41:58 time: 0.468513 data_time: 0.025202 memory: 15239 loss_kpt: 0.000672 acc_pose: 0.764261 loss: 0.000672 2022/09/14 17:28:59 - mmengine - INFO - Epoch(train) [25][400/586] lr: 5.000000e-04 eta: 13:41:41 time: 0.468408 data_time: 0.024665 memory: 15239 loss_kpt: 0.000674 acc_pose: 0.850616 loss: 0.000674 2022/09/14 17:29:23 - mmengine - INFO - Epoch(train) [25][450/586] lr: 5.000000e-04 eta: 13:41:26 time: 0.475431 data_time: 0.025443 memory: 15239 loss_kpt: 0.000644 acc_pose: 0.870753 loss: 0.000644 2022/09/14 17:29:47 - mmengine - INFO - Epoch(train) [25][500/586] lr: 5.000000e-04 eta: 13:41:12 time: 0.476061 data_time: 0.025256 memory: 15239 loss_kpt: 0.000654 acc_pose: 0.742146 loss: 0.000654 2022/09/14 17:30:10 - mmengine - INFO - Epoch(train) [25][550/586] lr: 5.000000e-04 eta: 13:40:54 time: 0.467229 data_time: 0.025488 memory: 15239 loss_kpt: 0.000676 acc_pose: 0.763498 loss: 0.000676 2022/09/14 17:30:27 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 17:30:27 - mmengine - INFO - Saving checkpoint at 25 epochs 2022/09/14 17:30:58 - mmengine - INFO - Epoch(train) [26][50/586] lr: 5.000000e-04 eta: 13:38:22 time: 0.474453 data_time: 0.033645 memory: 15239 loss_kpt: 0.000671 acc_pose: 0.774747 loss: 0.000671 2022/09/14 17:31:21 - mmengine - INFO - Epoch(train) [26][100/586] lr: 5.000000e-04 eta: 13:38:02 time: 0.461917 data_time: 0.026508 memory: 15239 loss_kpt: 0.000649 acc_pose: 0.767063 loss: 0.000649 2022/09/14 17:31:44 - mmengine - INFO - Epoch(train) [26][150/586] lr: 5.000000e-04 eta: 13:37:47 time: 0.473395 data_time: 0.026004 memory: 15239 loss_kpt: 0.000663 acc_pose: 0.780939 loss: 0.000663 2022/09/14 17:32:08 - mmengine - INFO - Epoch(train) [26][200/586] lr: 5.000000e-04 eta: 13:37:29 time: 0.465246 data_time: 0.024546 memory: 15239 loss_kpt: 0.000651 acc_pose: 0.776848 loss: 0.000651 2022/09/14 17:32:31 - mmengine - INFO - Epoch(train) [26][250/586] lr: 5.000000e-04 eta: 13:37:12 time: 0.468586 data_time: 0.025115 memory: 15239 loss_kpt: 0.000657 acc_pose: 0.762930 loss: 0.000657 2022/09/14 17:32:55 - mmengine - INFO - Epoch(train) [26][300/586] lr: 5.000000e-04 eta: 13:36:56 time: 0.472054 data_time: 0.028811 memory: 15239 loss_kpt: 0.000639 acc_pose: 0.842754 loss: 0.000639 2022/09/14 17:33:18 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 17:33:18 - mmengine - INFO - Epoch(train) [26][350/586] lr: 5.000000e-04 eta: 13:36:39 time: 0.470431 data_time: 0.025120 memory: 15239 loss_kpt: 0.000643 acc_pose: 0.819755 loss: 0.000643 2022/09/14 17:33:42 - mmengine - INFO - Epoch(train) [26][400/586] lr: 5.000000e-04 eta: 13:36:21 time: 0.464866 data_time: 0.025163 memory: 15239 loss_kpt: 0.000664 acc_pose: 0.766771 loss: 0.000664 2022/09/14 17:34:05 - mmengine - INFO - Epoch(train) [26][450/586] lr: 5.000000e-04 eta: 13:36:04 time: 0.470558 data_time: 0.024711 memory: 15239 loss_kpt: 0.000670 acc_pose: 0.738743 loss: 0.000670 2022/09/14 17:34:28 - mmengine - INFO - Epoch(train) [26][500/586] lr: 5.000000e-04 eta: 13:35:46 time: 0.466118 data_time: 0.025360 memory: 15239 loss_kpt: 0.000646 acc_pose: 0.767985 loss: 0.000646 2022/09/14 17:34:52 - mmengine - INFO - Epoch(train) [26][550/586] lr: 5.000000e-04 eta: 13:35:28 time: 0.467141 data_time: 0.027268 memory: 15239 loss_kpt: 0.000656 acc_pose: 0.820191 loss: 0.000656 2022/09/14 17:35:09 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 17:35:09 - mmengine - INFO - Saving checkpoint at 26 epochs 2022/09/14 17:35:39 - mmengine - INFO - Epoch(train) [27][50/586] lr: 5.000000e-04 eta: 13:33:01 time: 0.475120 data_time: 0.038672 memory: 15239 loss_kpt: 0.000656 acc_pose: 0.817172 loss: 0.000656 2022/09/14 17:36:02 - mmengine - INFO - Epoch(train) [27][100/586] lr: 5.000000e-04 eta: 13:32:42 time: 0.462377 data_time: 0.024546 memory: 15239 loss_kpt: 0.000640 acc_pose: 0.792576 loss: 0.000640 2022/09/14 17:36:26 - mmengine - INFO - Epoch(train) [27][150/586] lr: 5.000000e-04 eta: 13:32:25 time: 0.469411 data_time: 0.025227 memory: 15239 loss_kpt: 0.000665 acc_pose: 0.843474 loss: 0.000665 2022/09/14 17:36:49 - mmengine - INFO - Epoch(train) [27][200/586] lr: 5.000000e-04 eta: 13:32:05 time: 0.460301 data_time: 0.024828 memory: 15239 loss_kpt: 0.000651 acc_pose: 0.829375 loss: 0.000651 2022/09/14 17:37:12 - mmengine - INFO - Epoch(train) [27][250/586] lr: 5.000000e-04 eta: 13:31:50 time: 0.472802 data_time: 0.024803 memory: 15239 loss_kpt: 0.000648 acc_pose: 0.790435 loss: 0.000648 2022/09/14 17:37:36 - mmengine - INFO - Epoch(train) [27][300/586] lr: 5.000000e-04 eta: 13:31:32 time: 0.466511 data_time: 0.025952 memory: 15239 loss_kpt: 0.000670 acc_pose: 0.796280 loss: 0.000670 2022/09/14 17:37:59 - mmengine - INFO - Epoch(train) [27][350/586] lr: 5.000000e-04 eta: 13:31:14 time: 0.467458 data_time: 0.025145 memory: 15239 loss_kpt: 0.000652 acc_pose: 0.837718 loss: 0.000652 2022/09/14 17:38:22 - mmengine - INFO - Epoch(train) [27][400/586] lr: 5.000000e-04 eta: 13:30:56 time: 0.465645 data_time: 0.024586 memory: 15239 loss_kpt: 0.000650 acc_pose: 0.824233 loss: 0.000650 2022/09/14 17:38:46 - mmengine - INFO - Epoch(train) [27][450/586] lr: 5.000000e-04 eta: 13:30:38 time: 0.467563 data_time: 0.024392 memory: 15239 loss_kpt: 0.000660 acc_pose: 0.869940 loss: 0.000660 2022/09/14 17:39:09 - mmengine - INFO - Epoch(train) [27][500/586] lr: 5.000000e-04 eta: 13:30:23 time: 0.473200 data_time: 0.024981 memory: 15239 loss_kpt: 0.000669 acc_pose: 0.806962 loss: 0.000669 2022/09/14 17:39:33 - mmengine - INFO - Epoch(train) [27][550/586] lr: 5.000000e-04 eta: 13:30:05 time: 0.466781 data_time: 0.025200 memory: 15239 loss_kpt: 0.000656 acc_pose: 0.836172 loss: 0.000656 2022/09/14 17:39:49 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 17:39:49 - mmengine - INFO - Saving checkpoint at 27 epochs 2022/09/14 17:40:21 - mmengine - INFO - Epoch(train) [28][50/586] lr: 5.000000e-04 eta: 13:27:46 time: 0.484740 data_time: 0.035097 memory: 15239 loss_kpt: 0.000635 acc_pose: 0.824977 loss: 0.000635 2022/09/14 17:40:44 - mmengine - INFO - Epoch(train) [28][100/586] lr: 5.000000e-04 eta: 13:27:30 time: 0.472840 data_time: 0.025002 memory: 15239 loss_kpt: 0.000624 acc_pose: 0.863250 loss: 0.000624 2022/09/14 17:41:08 - mmengine - INFO - Epoch(train) [28][150/586] lr: 5.000000e-04 eta: 13:27:11 time: 0.463024 data_time: 0.025834 memory: 15239 loss_kpt: 0.000647 acc_pose: 0.874042 loss: 0.000647 2022/09/14 17:41:21 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 17:41:31 - mmengine - INFO - Epoch(train) [28][200/586] lr: 5.000000e-04 eta: 13:26:57 time: 0.475903 data_time: 0.027769 memory: 15239 loss_kpt: 0.000650 acc_pose: 0.868332 loss: 0.000650 2022/09/14 17:41:55 - mmengine - INFO - Epoch(train) [28][250/586] lr: 5.000000e-04 eta: 13:26:40 time: 0.469686 data_time: 0.025962 memory: 15239 loss_kpt: 0.000637 acc_pose: 0.813306 loss: 0.000637 2022/09/14 17:42:18 - mmengine - INFO - Epoch(train) [28][300/586] lr: 5.000000e-04 eta: 13:26:21 time: 0.462588 data_time: 0.027865 memory: 15239 loss_kpt: 0.000680 acc_pose: 0.795748 loss: 0.000680 2022/09/14 17:42:42 - mmengine - INFO - Epoch(train) [28][350/586] lr: 5.000000e-04 eta: 13:26:05 time: 0.474744 data_time: 0.025095 memory: 15239 loss_kpt: 0.000635 acc_pose: 0.849380 loss: 0.000635 2022/09/14 17:43:05 - mmengine - INFO - Epoch(train) [28][400/586] lr: 5.000000e-04 eta: 13:25:46 time: 0.463549 data_time: 0.025200 memory: 15239 loss_kpt: 0.000675 acc_pose: 0.798847 loss: 0.000675 2022/09/14 17:43:28 - mmengine - INFO - Epoch(train) [28][450/586] lr: 5.000000e-04 eta: 13:25:28 time: 0.463988 data_time: 0.025543 memory: 15239 loss_kpt: 0.000655 acc_pose: 0.813907 loss: 0.000655 2022/09/14 17:43:52 - mmengine - INFO - Epoch(train) [28][500/586] lr: 5.000000e-04 eta: 13:25:11 time: 0.471211 data_time: 0.025088 memory: 15239 loss_kpt: 0.000646 acc_pose: 0.864362 loss: 0.000646 2022/09/14 17:44:15 - mmengine - INFO - Epoch(train) [28][550/586] lr: 5.000000e-04 eta: 13:24:51 time: 0.461477 data_time: 0.024484 memory: 15239 loss_kpt: 0.000660 acc_pose: 0.820874 loss: 0.000660 2022/09/14 17:44:31 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 17:44:31 - mmengine - INFO - Saving checkpoint at 28 epochs 2022/09/14 17:45:02 - mmengine - INFO - Epoch(train) [29][50/586] lr: 5.000000e-04 eta: 13:22:34 time: 0.474625 data_time: 0.028989 memory: 15239 loss_kpt: 0.000643 acc_pose: 0.819575 loss: 0.000643 2022/09/14 17:45:25 - mmengine - INFO - Epoch(train) [29][100/586] lr: 5.000000e-04 eta: 13:22:16 time: 0.467514 data_time: 0.025744 memory: 15239 loss_kpt: 0.000637 acc_pose: 0.828084 loss: 0.000637 2022/09/14 17:45:49 - mmengine - INFO - Epoch(train) [29][150/586] lr: 5.000000e-04 eta: 13:21:59 time: 0.469165 data_time: 0.024604 memory: 15239 loss_kpt: 0.000641 acc_pose: 0.799478 loss: 0.000641 2022/09/14 17:46:12 - mmengine - INFO - Epoch(train) [29][200/586] lr: 5.000000e-04 eta: 13:21:42 time: 0.466234 data_time: 0.025284 memory: 15239 loss_kpt: 0.000647 acc_pose: 0.777864 loss: 0.000647 2022/09/14 17:46:36 - mmengine - INFO - Epoch(train) [29][250/586] lr: 5.000000e-04 eta: 13:21:26 time: 0.474950 data_time: 0.025390 memory: 15239 loss_kpt: 0.000650 acc_pose: 0.750782 loss: 0.000650 2022/09/14 17:46:59 - mmengine - INFO - Epoch(train) [29][300/586] lr: 5.000000e-04 eta: 13:21:08 time: 0.464950 data_time: 0.024984 memory: 15239 loss_kpt: 0.000652 acc_pose: 0.778802 loss: 0.000652 2022/09/14 17:47:22 - mmengine - INFO - Epoch(train) [29][350/586] lr: 5.000000e-04 eta: 13:20:50 time: 0.465764 data_time: 0.024247 memory: 15239 loss_kpt: 0.000622 acc_pose: 0.847534 loss: 0.000622 2022/09/14 17:47:46 - mmengine - INFO - Epoch(train) [29][400/586] lr: 5.000000e-04 eta: 13:20:32 time: 0.467263 data_time: 0.024505 memory: 15239 loss_kpt: 0.000644 acc_pose: 0.829737 loss: 0.000644 2022/09/14 17:48:09 - mmengine - INFO - Epoch(train) [29][450/586] lr: 5.000000e-04 eta: 13:20:15 time: 0.469675 data_time: 0.028656 memory: 15239 loss_kpt: 0.000642 acc_pose: 0.797442 loss: 0.000642 2022/09/14 17:48:32 - mmengine - INFO - Epoch(train) [29][500/586] lr: 5.000000e-04 eta: 13:19:56 time: 0.463002 data_time: 0.025238 memory: 15239 loss_kpt: 0.000640 acc_pose: 0.822948 loss: 0.000640 2022/09/14 17:48:55 - mmengine - INFO - Epoch(train) [29][550/586] lr: 5.000000e-04 eta: 13:19:36 time: 0.463084 data_time: 0.024228 memory: 15239 loss_kpt: 0.000639 acc_pose: 0.839875 loss: 0.000639 2022/09/14 17:49:12 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 17:49:12 - mmengine - INFO - Saving checkpoint at 29 epochs 2022/09/14 17:49:23 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 17:49:43 - mmengine - INFO - Epoch(train) [30][50/586] lr: 5.000000e-04 eta: 13:17:28 time: 0.489889 data_time: 0.034227 memory: 15239 loss_kpt: 0.000644 acc_pose: 0.800666 loss: 0.000644 2022/09/14 17:50:07 - mmengine - INFO - Epoch(train) [30][100/586] lr: 5.000000e-04 eta: 13:17:12 time: 0.473077 data_time: 0.024801 memory: 15239 loss_kpt: 0.000650 acc_pose: 0.836463 loss: 0.000650 2022/09/14 17:50:30 - mmengine - INFO - Epoch(train) [30][150/586] lr: 5.000000e-04 eta: 13:16:54 time: 0.464498 data_time: 0.025197 memory: 15239 loss_kpt: 0.000646 acc_pose: 0.726713 loss: 0.000646 2022/09/14 17:50:53 - mmengine - INFO - Epoch(train) [30][200/586] lr: 5.000000e-04 eta: 13:16:34 time: 0.461865 data_time: 0.024542 memory: 15239 loss_kpt: 0.000643 acc_pose: 0.778135 loss: 0.000643 2022/09/14 17:51:17 - mmengine - INFO - Epoch(train) [30][250/586] lr: 5.000000e-04 eta: 13:16:18 time: 0.473202 data_time: 0.028644 memory: 15239 loss_kpt: 0.000648 acc_pose: 0.854529 loss: 0.000648 2022/09/14 17:51:40 - mmengine - INFO - Epoch(train) [30][300/586] lr: 5.000000e-04 eta: 13:15:59 time: 0.461902 data_time: 0.025494 memory: 15239 loss_kpt: 0.000632 acc_pose: 0.809399 loss: 0.000632 2022/09/14 17:52:03 - mmengine - INFO - Epoch(train) [30][350/586] lr: 5.000000e-04 eta: 13:15:39 time: 0.461426 data_time: 0.024720 memory: 15239 loss_kpt: 0.000638 acc_pose: 0.806550 loss: 0.000638 2022/09/14 17:52:27 - mmengine - INFO - Epoch(train) [30][400/586] lr: 5.000000e-04 eta: 13:15:24 time: 0.474130 data_time: 0.029030 memory: 15239 loss_kpt: 0.000654 acc_pose: 0.801064 loss: 0.000654 2022/09/14 17:52:50 - mmengine - INFO - Epoch(train) [30][450/586] lr: 5.000000e-04 eta: 13:15:03 time: 0.458402 data_time: 0.025419 memory: 15239 loss_kpt: 0.000650 acc_pose: 0.795583 loss: 0.000650 2022/09/14 17:53:13 - mmengine - INFO - Epoch(train) [30][500/586] lr: 5.000000e-04 eta: 13:14:44 time: 0.464028 data_time: 0.025148 memory: 15239 loss_kpt: 0.000656 acc_pose: 0.845543 loss: 0.000656 2022/09/14 17:53:37 - mmengine - INFO - Epoch(train) [30][550/586] lr: 5.000000e-04 eta: 13:14:28 time: 0.473713 data_time: 0.028007 memory: 15239 loss_kpt: 0.000655 acc_pose: 0.774140 loss: 0.000655 2022/09/14 17:53:53 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 17:53:53 - mmengine - INFO - Saving checkpoint at 30 epochs 2022/09/14 17:54:11 - mmengine - INFO - Epoch(val) [30][50/407] eta: 0:01:12 time: 0.202735 data_time: 0.013870 memory: 15239 2022/09/14 17:54:20 - mmengine - INFO - Epoch(val) [30][100/407] eta: 0:00:59 time: 0.195434 data_time: 0.008404 memory: 2064 2022/09/14 17:54:30 - mmengine - INFO - Epoch(val) [30][150/407] eta: 0:00:50 time: 0.195543 data_time: 0.008347 memory: 2064 2022/09/14 17:54:40 - mmengine - INFO - Epoch(val) [30][200/407] eta: 0:00:40 time: 0.195936 data_time: 0.008467 memory: 2064 2022/09/14 17:54:50 - mmengine - INFO - Epoch(val) [30][250/407] eta: 0:00:30 time: 0.196245 data_time: 0.008775 memory: 2064 2022/09/14 17:55:00 - mmengine - INFO - Epoch(val) [30][300/407] eta: 0:00:20 time: 0.195275 data_time: 0.008415 memory: 2064 2022/09/14 17:55:09 - mmengine - INFO - Epoch(val) [30][350/407] eta: 0:00:11 time: 0.195912 data_time: 0.008748 memory: 2064 2022/09/14 17:55:19 - mmengine - INFO - Epoch(val) [30][400/407] eta: 0:00:01 time: 0.193681 data_time: 0.008280 memory: 2064 2022/09/14 17:55:56 - mmengine - INFO - Evaluating CocoMetric... 2022/09/14 17:56:09 - mmengine - INFO - Epoch(val) [30][407/407] coco/AP: 0.728307 coco/AP .5: 0.892459 coco/AP .75: 0.792736 coco/AP (M): 0.690175 coco/AP (L): 0.797510 coco/AR: 0.781266 coco/AR .5: 0.930888 coco/AR .75: 0.839893 coco/AR (M): 0.736848 coco/AR (L): 0.844705 2022/09/14 17:56:09 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220914/hrnet_w48_384/best_coco/AP_epoch_20.pth is removed 2022/09/14 17:56:13 - mmengine - INFO - The best checkpoint with 0.7283 coco/AP at 30 epoch is saved to best_coco/AP_epoch_30.pth. 2022/09/14 17:56:37 - mmengine - INFO - Epoch(train) [31][50/586] lr: 5.000000e-04 eta: 13:12:18 time: 0.472729 data_time: 0.034906 memory: 15239 loss_kpt: 0.000652 acc_pose: 0.845058 loss: 0.000652 2022/09/14 17:57:01 - mmengine - INFO - Epoch(train) [31][100/586] lr: 5.000000e-04 eta: 13:12:03 time: 0.473364 data_time: 0.029541 memory: 15239 loss_kpt: 0.000648 acc_pose: 0.864992 loss: 0.000648 2022/09/14 17:57:24 - mmengine - INFO - Epoch(train) [31][150/586] lr: 5.000000e-04 eta: 13:11:43 time: 0.461828 data_time: 0.025903 memory: 15239 loss_kpt: 0.000657 acc_pose: 0.791218 loss: 0.000657 2022/09/14 17:57:47 - mmengine - INFO - Epoch(train) [31][200/586] lr: 5.000000e-04 eta: 13:11:24 time: 0.462857 data_time: 0.025732 memory: 15239 loss_kpt: 0.000644 acc_pose: 0.810987 loss: 0.000644 2022/09/14 17:58:10 - mmengine - INFO - Epoch(train) [31][250/586] lr: 5.000000e-04 eta: 13:11:08 time: 0.473044 data_time: 0.030644 memory: 15239 loss_kpt: 0.000661 acc_pose: 0.735100 loss: 0.000661 2022/09/14 17:58:34 - mmengine - INFO - Epoch(train) [31][300/586] lr: 5.000000e-04 eta: 13:10:50 time: 0.467299 data_time: 0.024776 memory: 15239 loss_kpt: 0.000640 acc_pose: 0.805505 loss: 0.000640 2022/09/14 17:58:58 - mmengine - INFO - Epoch(train) [31][350/586] lr: 5.000000e-04 eta: 13:10:35 time: 0.474767 data_time: 0.025004 memory: 15239 loss_kpt: 0.000638 acc_pose: 0.846933 loss: 0.000638 2022/09/14 17:59:21 - mmengine - INFO - Epoch(train) [31][400/586] lr: 5.000000e-04 eta: 13:10:17 time: 0.466737 data_time: 0.025458 memory: 15239 loss_kpt: 0.000648 acc_pose: 0.858967 loss: 0.000648 2022/09/14 17:59:30 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 17:59:44 - mmengine - INFO - Epoch(train) [31][450/586] lr: 5.000000e-04 eta: 13:09:58 time: 0.462850 data_time: 0.025094 memory: 15239 loss_kpt: 0.000638 acc_pose: 0.832605 loss: 0.000638 2022/09/14 18:00:10 - mmengine - INFO - Epoch(train) [31][500/586] lr: 5.000000e-04 eta: 13:09:56 time: 0.522467 data_time: 0.030797 memory: 15239 loss_kpt: 0.000620 acc_pose: 0.875936 loss: 0.000620 2022/09/14 18:00:34 - mmengine - INFO - Epoch(train) [31][550/586] lr: 5.000000e-04 eta: 13:09:40 time: 0.474775 data_time: 0.028579 memory: 15239 loss_kpt: 0.000674 acc_pose: 0.777188 loss: 0.000674 2022/09/14 18:00:51 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 18:00:51 - mmengine - INFO - Saving checkpoint at 31 epochs 2022/09/14 18:01:22 - mmengine - INFO - Epoch(train) [32][50/586] lr: 5.000000e-04 eta: 13:07:35 time: 0.478318 data_time: 0.039425 memory: 15239 loss_kpt: 0.000643 acc_pose: 0.679877 loss: 0.000643 2022/09/14 18:01:45 - mmengine - INFO - Epoch(train) [32][100/586] lr: 5.000000e-04 eta: 13:07:18 time: 0.468090 data_time: 0.026517 memory: 15239 loss_kpt: 0.000621 acc_pose: 0.818234 loss: 0.000621 2022/09/14 18:02:09 - mmengine - INFO - Epoch(train) [32][150/586] lr: 5.000000e-04 eta: 13:07:03 time: 0.477416 data_time: 0.025377 memory: 15239 loss_kpt: 0.000648 acc_pose: 0.812359 loss: 0.000648 2022/09/14 18:02:33 - mmengine - INFO - Epoch(train) [32][200/586] lr: 5.000000e-04 eta: 13:06:48 time: 0.477800 data_time: 0.025119 memory: 15239 loss_kpt: 0.000613 acc_pose: 0.788134 loss: 0.000613 2022/09/14 18:02:57 - mmengine - INFO - Epoch(train) [32][250/586] lr: 5.000000e-04 eta: 13:06:34 time: 0.481943 data_time: 0.025952 memory: 15239 loss_kpt: 0.000648 acc_pose: 0.800068 loss: 0.000648 2022/09/14 18:03:20 - mmengine - INFO - Epoch(train) [32][300/586] lr: 5.000000e-04 eta: 13:06:15 time: 0.464153 data_time: 0.025097 memory: 15239 loss_kpt: 0.000662 acc_pose: 0.755147 loss: 0.000662 2022/09/14 18:03:44 - mmengine - INFO - Epoch(train) [32][350/586] lr: 5.000000e-04 eta: 13:05:59 time: 0.471758 data_time: 0.025741 memory: 15239 loss_kpt: 0.000647 acc_pose: 0.796126 loss: 0.000647 2022/09/14 18:04:07 - mmengine - INFO - Epoch(train) [32][400/586] lr: 5.000000e-04 eta: 13:05:42 time: 0.473451 data_time: 0.025154 memory: 15239 loss_kpt: 0.000648 acc_pose: 0.745810 loss: 0.000648 2022/09/14 18:04:31 - mmengine - INFO - Epoch(train) [32][450/586] lr: 5.000000e-04 eta: 13:05:23 time: 0.461287 data_time: 0.025543 memory: 15239 loss_kpt: 0.000637 acc_pose: 0.848082 loss: 0.000637 2022/09/14 18:04:54 - mmengine - INFO - Epoch(train) [32][500/586] lr: 5.000000e-04 eta: 13:05:06 time: 0.471254 data_time: 0.028770 memory: 15239 loss_kpt: 0.000644 acc_pose: 0.785816 loss: 0.000644 2022/09/14 18:05:18 - mmengine - INFO - Epoch(train) [32][550/586] lr: 5.000000e-04 eta: 13:04:50 time: 0.475127 data_time: 0.025310 memory: 15239 loss_kpt: 0.000647 acc_pose: 0.849441 loss: 0.000647 2022/09/14 18:05:34 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 18:05:34 - mmengine - INFO - Saving checkpoint at 32 epochs 2022/09/14 18:06:05 - mmengine - INFO - Epoch(train) [33][50/586] lr: 5.000000e-04 eta: 13:02:50 time: 0.482957 data_time: 0.032165 memory: 15239 loss_kpt: 0.000652 acc_pose: 0.754290 loss: 0.000652 2022/09/14 18:06:29 - mmengine - INFO - Epoch(train) [33][100/586] lr: 5.000000e-04 eta: 13:02:35 time: 0.479932 data_time: 0.029270 memory: 15239 loss_kpt: 0.000630 acc_pose: 0.803225 loss: 0.000630 2022/09/14 18:06:52 - mmengine - INFO - Epoch(train) [33][150/586] lr: 5.000000e-04 eta: 13:02:15 time: 0.460067 data_time: 0.024156 memory: 15239 loss_kpt: 0.000641 acc_pose: 0.823385 loss: 0.000641 2022/09/14 18:07:16 - mmengine - INFO - Epoch(train) [33][200/586] lr: 5.000000e-04 eta: 13:01:59 time: 0.471787 data_time: 0.024407 memory: 15239 loss_kpt: 0.000658 acc_pose: 0.810168 loss: 0.000658 2022/09/14 18:07:39 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 18:07:40 - mmengine - INFO - Epoch(train) [33][250/586] lr: 5.000000e-04 eta: 13:01:43 time: 0.476450 data_time: 0.026769 memory: 15239 loss_kpt: 0.000646 acc_pose: 0.784329 loss: 0.000646 2022/09/14 18:08:03 - mmengine - INFO - Epoch(train) [33][300/586] lr: 5.000000e-04 eta: 13:01:22 time: 0.457529 data_time: 0.024923 memory: 15239 loss_kpt: 0.000636 acc_pose: 0.791203 loss: 0.000636 2022/09/14 18:08:27 - mmengine - INFO - Epoch(train) [33][350/586] lr: 5.000000e-04 eta: 13:01:10 time: 0.489531 data_time: 0.026731 memory: 15239 loss_kpt: 0.000606 acc_pose: 0.847489 loss: 0.000606 2022/09/14 18:08:51 - mmengine - INFO - Epoch(train) [33][400/586] lr: 5.000000e-04 eta: 13:00:52 time: 0.467827 data_time: 0.029761 memory: 15239 loss_kpt: 0.000643 acc_pose: 0.865416 loss: 0.000643 2022/09/14 18:09:14 - mmengine - INFO - Epoch(train) [33][450/586] lr: 5.000000e-04 eta: 13:00:33 time: 0.462102 data_time: 0.024551 memory: 15239 loss_kpt: 0.000646 acc_pose: 0.900105 loss: 0.000646 2022/09/14 18:09:37 - mmengine - INFO - Epoch(train) [33][500/586] lr: 5.000000e-04 eta: 13:00:16 time: 0.471239 data_time: 0.025547 memory: 15239 loss_kpt: 0.000649 acc_pose: 0.747352 loss: 0.000649 2022/09/14 18:10:01 - mmengine - INFO - Epoch(train) [33][550/586] lr: 5.000000e-04 eta: 12:59:58 time: 0.469538 data_time: 0.025852 memory: 15239 loss_kpt: 0.000626 acc_pose: 0.841963 loss: 0.000626 2022/09/14 18:10:17 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 18:10:17 - mmengine - INFO - Saving checkpoint at 33 epochs 2022/09/14 18:10:49 - mmengine - INFO - Epoch(train) [34][50/586] lr: 5.000000e-04 eta: 12:58:02 time: 0.487128 data_time: 0.037068 memory: 15239 loss_kpt: 0.000643 acc_pose: 0.812268 loss: 0.000643 2022/09/14 18:11:12 - mmengine - INFO - Epoch(train) [34][100/586] lr: 5.000000e-04 eta: 12:57:44 time: 0.464483 data_time: 0.026275 memory: 15239 loss_kpt: 0.000596 acc_pose: 0.852031 loss: 0.000596 2022/09/14 18:11:36 - mmengine - INFO - Epoch(train) [34][150/586] lr: 5.000000e-04 eta: 12:57:27 time: 0.471918 data_time: 0.024417 memory: 15239 loss_kpt: 0.000656 acc_pose: 0.812567 loss: 0.000656 2022/09/14 18:11:59 - mmengine - INFO - Epoch(train) [34][200/586] lr: 5.000000e-04 eta: 12:57:09 time: 0.467551 data_time: 0.024231 memory: 15239 loss_kpt: 0.000636 acc_pose: 0.766602 loss: 0.000636 2022/09/14 18:12:23 - mmengine - INFO - Epoch(train) [34][250/586] lr: 5.000000e-04 eta: 12:56:54 time: 0.481090 data_time: 0.024456 memory: 15239 loss_kpt: 0.000630 acc_pose: 0.792647 loss: 0.000630 2022/09/14 18:12:47 - mmengine - INFO - Epoch(train) [34][300/586] lr: 5.000000e-04 eta: 12:56:39 time: 0.476101 data_time: 0.026229 memory: 15239 loss_kpt: 0.000629 acc_pose: 0.818608 loss: 0.000629 2022/09/14 18:13:10 - mmengine - INFO - Epoch(train) [34][350/586] lr: 5.000000e-04 eta: 12:56:21 time: 0.467350 data_time: 0.024837 memory: 15239 loss_kpt: 0.000637 acc_pose: 0.844203 loss: 0.000637 2022/09/14 18:13:34 - mmengine - INFO - Epoch(train) [34][400/586] lr: 5.000000e-04 eta: 12:56:05 time: 0.479098 data_time: 0.025064 memory: 15239 loss_kpt: 0.000651 acc_pose: 0.813628 loss: 0.000651 2022/09/14 18:13:58 - mmengine - INFO - Epoch(train) [34][450/586] lr: 5.000000e-04 eta: 12:55:51 time: 0.482033 data_time: 0.031300 memory: 15239 loss_kpt: 0.000618 acc_pose: 0.794691 loss: 0.000618 2022/09/14 18:14:22 - mmengine - INFO - Epoch(train) [34][500/586] lr: 5.000000e-04 eta: 12:55:35 time: 0.473560 data_time: 0.025718 memory: 15239 loss_kpt: 0.000633 acc_pose: 0.825372 loss: 0.000633 2022/09/14 18:14:46 - mmengine - INFO - Epoch(train) [34][550/586] lr: 5.000000e-04 eta: 12:55:18 time: 0.474524 data_time: 0.026562 memory: 15239 loss_kpt: 0.000634 acc_pose: 0.850809 loss: 0.000634 2022/09/14 18:15:02 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 18:15:02 - mmengine - INFO - Saving checkpoint at 34 epochs 2022/09/14 18:15:33 - mmengine - INFO - Epoch(train) [35][50/586] lr: 5.000000e-04 eta: 12:53:22 time: 0.474802 data_time: 0.030481 memory: 15239 loss_kpt: 0.000642 acc_pose: 0.811596 loss: 0.000642 2022/09/14 18:15:45 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 18:15:56 - mmengine - INFO - Epoch(train) [35][100/586] lr: 5.000000e-04 eta: 12:53:03 time: 0.465229 data_time: 0.032883 memory: 15239 loss_kpt: 0.000625 acc_pose: 0.801329 loss: 0.000625 2022/09/14 18:16:21 - mmengine - INFO - Epoch(train) [35][150/586] lr: 5.000000e-04 eta: 12:52:49 time: 0.482596 data_time: 0.027918 memory: 15239 loss_kpt: 0.000640 acc_pose: 0.864514 loss: 0.000640 2022/09/14 18:16:44 - mmengine - INFO - Epoch(train) [35][200/586] lr: 5.000000e-04 eta: 12:52:30 time: 0.463433 data_time: 0.026417 memory: 15239 loss_kpt: 0.000615 acc_pose: 0.866925 loss: 0.000615 2022/09/14 18:17:07 - mmengine - INFO - Epoch(train) [35][250/586] lr: 5.000000e-04 eta: 12:52:13 time: 0.471709 data_time: 0.033224 memory: 15239 loss_kpt: 0.000634 acc_pose: 0.872915 loss: 0.000634 2022/09/14 18:17:31 - mmengine - INFO - Epoch(train) [35][300/586] lr: 5.000000e-04 eta: 12:51:56 time: 0.473245 data_time: 0.027507 memory: 15239 loss_kpt: 0.000627 acc_pose: 0.738282 loss: 0.000627 2022/09/14 18:17:54 - mmengine - INFO - Epoch(train) [35][350/586] lr: 5.000000e-04 eta: 12:51:37 time: 0.462849 data_time: 0.027667 memory: 15239 loss_kpt: 0.000627 acc_pose: 0.826337 loss: 0.000627 2022/09/14 18:18:18 - mmengine - INFO - Epoch(train) [35][400/586] lr: 5.000000e-04 eta: 12:51:20 time: 0.472630 data_time: 0.026866 memory: 15239 loss_kpt: 0.000634 acc_pose: 0.877570 loss: 0.000634 2022/09/14 18:18:41 - mmengine - INFO - Epoch(train) [35][450/586] lr: 5.000000e-04 eta: 12:51:01 time: 0.465899 data_time: 0.027304 memory: 15239 loss_kpt: 0.000639 acc_pose: 0.816701 loss: 0.000639 2022/09/14 18:19:04 - mmengine - INFO - Epoch(train) [35][500/586] lr: 5.000000e-04 eta: 12:50:41 time: 0.461996 data_time: 0.027114 memory: 15239 loss_kpt: 0.000617 acc_pose: 0.815963 loss: 0.000617 2022/09/14 18:19:28 - mmengine - INFO - Epoch(train) [35][550/586] lr: 5.000000e-04 eta: 12:50:23 time: 0.466160 data_time: 0.027498 memory: 15239 loss_kpt: 0.000637 acc_pose: 0.875675 loss: 0.000637 2022/09/14 18:19:45 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 18:19:45 - mmengine - INFO - Saving checkpoint at 35 epochs 2022/09/14 18:20:15 - mmengine - INFO - Epoch(train) [36][50/586] lr: 5.000000e-04 eta: 12:48:29 time: 0.474784 data_time: 0.032073 memory: 15239 loss_kpt: 0.000645 acc_pose: 0.800721 loss: 0.000645 2022/09/14 18:20:38 - mmengine - INFO - Epoch(train) [36][100/586] lr: 5.000000e-04 eta: 12:48:12 time: 0.471110 data_time: 0.025580 memory: 15239 loss_kpt: 0.000615 acc_pose: 0.835185 loss: 0.000615 2022/09/14 18:21:02 - mmengine - INFO - Epoch(train) [36][150/586] lr: 5.000000e-04 eta: 12:47:54 time: 0.469323 data_time: 0.027828 memory: 15239 loss_kpt: 0.000629 acc_pose: 0.809383 loss: 0.000629 2022/09/14 18:21:26 - mmengine - INFO - Epoch(train) [36][200/586] lr: 5.000000e-04 eta: 12:47:38 time: 0.474322 data_time: 0.034079 memory: 15239 loss_kpt: 0.000634 acc_pose: 0.818370 loss: 0.000634 2022/09/14 18:21:49 - mmengine - INFO - Epoch(train) [36][250/586] lr: 5.000000e-04 eta: 12:47:19 time: 0.466132 data_time: 0.027490 memory: 15239 loss_kpt: 0.000635 acc_pose: 0.849535 loss: 0.000635 2022/09/14 18:22:12 - mmengine - INFO - Epoch(train) [36][300/586] lr: 5.000000e-04 eta: 12:47:01 time: 0.466079 data_time: 0.028316 memory: 15239 loss_kpt: 0.000614 acc_pose: 0.786477 loss: 0.000614 2022/09/14 18:22:36 - mmengine - INFO - Epoch(train) [36][350/586] lr: 5.000000e-04 eta: 12:46:43 time: 0.470401 data_time: 0.025847 memory: 15239 loss_kpt: 0.000632 acc_pose: 0.793966 loss: 0.000632 2022/09/14 18:22:59 - mmengine - INFO - Epoch(train) [36][400/586] lr: 5.000000e-04 eta: 12:46:25 time: 0.468357 data_time: 0.026563 memory: 15239 loss_kpt: 0.000649 acc_pose: 0.821084 loss: 0.000649 2022/09/14 18:23:22 - mmengine - INFO - Epoch(train) [36][450/586] lr: 5.000000e-04 eta: 12:46:06 time: 0.463446 data_time: 0.027009 memory: 15239 loss_kpt: 0.000634 acc_pose: 0.830139 loss: 0.000634 2022/09/14 18:23:41 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 18:23:46 - mmengine - INFO - Epoch(train) [36][500/586] lr: 5.000000e-04 eta: 12:45:48 time: 0.467340 data_time: 0.027021 memory: 15239 loss_kpt: 0.000636 acc_pose: 0.832757 loss: 0.000636 2022/09/14 18:24:09 - mmengine - INFO - Epoch(train) [36][550/586] lr: 5.000000e-04 eta: 12:45:30 time: 0.471488 data_time: 0.026191 memory: 15239 loss_kpt: 0.000621 acc_pose: 0.880789 loss: 0.000621 2022/09/14 18:24:26 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 18:24:26 - mmengine - INFO - Saving checkpoint at 36 epochs 2022/09/14 18:24:56 - mmengine - INFO - Epoch(train) [37][50/586] lr: 5.000000e-04 eta: 12:43:40 time: 0.477577 data_time: 0.036640 memory: 15239 loss_kpt: 0.000640 acc_pose: 0.834196 loss: 0.000640 2022/09/14 18:25:20 - mmengine - INFO - Epoch(train) [37][100/586] lr: 5.000000e-04 eta: 12:43:22 time: 0.469971 data_time: 0.029379 memory: 15239 loss_kpt: 0.000615 acc_pose: 0.862715 loss: 0.000615 2022/09/14 18:25:44 - mmengine - INFO - Epoch(train) [37][150/586] lr: 5.000000e-04 eta: 12:43:05 time: 0.471900 data_time: 0.029336 memory: 15239 loss_kpt: 0.000635 acc_pose: 0.811717 loss: 0.000635 2022/09/14 18:26:07 - mmengine - INFO - Epoch(train) [37][200/586] lr: 5.000000e-04 eta: 12:42:48 time: 0.473362 data_time: 0.025809 memory: 15239 loss_kpt: 0.000638 acc_pose: 0.870714 loss: 0.000638 2022/09/14 18:26:31 - mmengine - INFO - Epoch(train) [37][250/586] lr: 5.000000e-04 eta: 12:42:31 time: 0.469091 data_time: 0.026588 memory: 15239 loss_kpt: 0.000650 acc_pose: 0.817198 loss: 0.000650 2022/09/14 18:26:54 - mmengine - INFO - Epoch(train) [37][300/586] lr: 5.000000e-04 eta: 12:42:14 time: 0.474833 data_time: 0.025900 memory: 15239 loss_kpt: 0.000634 acc_pose: 0.782792 loss: 0.000634 2022/09/14 18:27:17 - mmengine - INFO - Epoch(train) [37][350/586] lr: 5.000000e-04 eta: 12:41:54 time: 0.461068 data_time: 0.026742 memory: 15239 loss_kpt: 0.000619 acc_pose: 0.794270 loss: 0.000619 2022/09/14 18:27:41 - mmengine - INFO - Epoch(train) [37][400/586] lr: 5.000000e-04 eta: 12:41:37 time: 0.471811 data_time: 0.027365 memory: 15239 loss_kpt: 0.000629 acc_pose: 0.823675 loss: 0.000629 2022/09/14 18:28:04 - mmengine - INFO - Epoch(train) [37][450/586] lr: 5.000000e-04 eta: 12:41:18 time: 0.465298 data_time: 0.026889 memory: 15239 loss_kpt: 0.000631 acc_pose: 0.792439 loss: 0.000631 2022/09/14 18:28:28 - mmengine - INFO - Epoch(train) [37][500/586] lr: 5.000000e-04 eta: 12:40:59 time: 0.463580 data_time: 0.025222 memory: 15239 loss_kpt: 0.000637 acc_pose: 0.777438 loss: 0.000637 2022/09/14 18:28:51 - mmengine - INFO - Epoch(train) [37][550/586] lr: 5.000000e-04 eta: 12:40:40 time: 0.464807 data_time: 0.029571 memory: 15239 loss_kpt: 0.000617 acc_pose: 0.864111 loss: 0.000617 2022/09/14 18:29:07 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 18:29:07 - mmengine - INFO - Saving checkpoint at 37 epochs 2022/09/14 18:29:38 - mmengine - INFO - Epoch(train) [38][50/586] lr: 5.000000e-04 eta: 12:38:51 time: 0.474539 data_time: 0.038683 memory: 15239 loss_kpt: 0.000630 acc_pose: 0.885443 loss: 0.000630 2022/09/14 18:30:02 - mmengine - INFO - Epoch(train) [38][100/586] lr: 5.000000e-04 eta: 12:38:35 time: 0.477051 data_time: 0.032916 memory: 15239 loss_kpt: 0.000609 acc_pose: 0.864852 loss: 0.000609 2022/09/14 18:30:26 - mmengine - INFO - Epoch(train) [38][150/586] lr: 5.000000e-04 eta: 12:38:19 time: 0.477828 data_time: 0.033740 memory: 15239 loss_kpt: 0.000642 acc_pose: 0.812423 loss: 0.000642 2022/09/14 18:30:50 - mmengine - INFO - Epoch(train) [38][200/586] lr: 5.000000e-04 eta: 12:38:02 time: 0.470400 data_time: 0.035456 memory: 15239 loss_kpt: 0.000621 acc_pose: 0.778956 loss: 0.000621 2022/09/14 18:31:13 - mmengine - INFO - Epoch(train) [38][250/586] lr: 5.000000e-04 eta: 12:37:44 time: 0.472179 data_time: 0.026997 memory: 15239 loss_kpt: 0.000620 acc_pose: 0.856672 loss: 0.000620 2022/09/14 18:31:37 - mmengine - INFO - Epoch(train) [38][300/586] lr: 5.000000e-04 eta: 12:37:26 time: 0.469075 data_time: 0.031614 memory: 15239 loss_kpt: 0.000631 acc_pose: 0.777958 loss: 0.000631 2022/09/14 18:31:45 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 18:32:00 - mmengine - INFO - Epoch(train) [38][350/586] lr: 5.000000e-04 eta: 12:37:08 time: 0.465835 data_time: 0.026889 memory: 15239 loss_kpt: 0.000637 acc_pose: 0.815604 loss: 0.000637 2022/09/14 18:32:24 - mmengine - INFO - Epoch(train) [38][400/586] lr: 5.000000e-04 eta: 12:36:51 time: 0.473915 data_time: 0.027031 memory: 15239 loss_kpt: 0.000641 acc_pose: 0.871177 loss: 0.000641 2022/09/14 18:32:47 - mmengine - INFO - Epoch(train) [38][450/586] lr: 5.000000e-04 eta: 12:36:32 time: 0.466034 data_time: 0.027647 memory: 15239 loss_kpt: 0.000628 acc_pose: 0.805681 loss: 0.000628 2022/09/14 18:33:10 - mmengine - INFO - Epoch(train) [38][500/586] lr: 5.000000e-04 eta: 12:36:12 time: 0.463382 data_time: 0.027810 memory: 15239 loss_kpt: 0.000648 acc_pose: 0.784176 loss: 0.000648 2022/09/14 18:33:34 - mmengine - INFO - Epoch(train) [38][550/586] lr: 5.000000e-04 eta: 12:35:57 time: 0.479698 data_time: 0.036583 memory: 15239 loss_kpt: 0.000632 acc_pose: 0.800534 loss: 0.000632 2022/09/14 18:33:51 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 18:33:51 - mmengine - INFO - Saving checkpoint at 38 epochs 2022/09/14 18:34:21 - mmengine - INFO - Epoch(train) [39][50/586] lr: 5.000000e-04 eta: 12:34:09 time: 0.469559 data_time: 0.029331 memory: 15239 loss_kpt: 0.000623 acc_pose: 0.853744 loss: 0.000623 2022/09/14 18:34:45 - mmengine - INFO - Epoch(train) [39][100/586] lr: 5.000000e-04 eta: 12:33:52 time: 0.472454 data_time: 0.025741 memory: 15239 loss_kpt: 0.000624 acc_pose: 0.760970 loss: 0.000624 2022/09/14 18:35:08 - mmengine - INFO - Epoch(train) [39][150/586] lr: 5.000000e-04 eta: 12:33:35 time: 0.471597 data_time: 0.026765 memory: 15239 loss_kpt: 0.000630 acc_pose: 0.844486 loss: 0.000630 2022/09/14 18:35:32 - mmengine - INFO - Epoch(train) [39][200/586] lr: 5.000000e-04 eta: 12:33:16 time: 0.464282 data_time: 0.030408 memory: 15239 loss_kpt: 0.000618 acc_pose: 0.824007 loss: 0.000618 2022/09/14 18:35:56 - mmengine - INFO - Epoch(train) [39][250/586] lr: 5.000000e-04 eta: 12:33:00 time: 0.479599 data_time: 0.027205 memory: 15239 loss_kpt: 0.000621 acc_pose: 0.806290 loss: 0.000621 2022/09/14 18:36:19 - mmengine - INFO - Epoch(train) [39][300/586] lr: 5.000000e-04 eta: 12:32:42 time: 0.467980 data_time: 0.026225 memory: 15239 loss_kpt: 0.000617 acc_pose: 0.874165 loss: 0.000617 2022/09/14 18:36:43 - mmengine - INFO - Epoch(train) [39][350/586] lr: 5.000000e-04 eta: 12:32:24 time: 0.470342 data_time: 0.030181 memory: 15239 loss_kpt: 0.000636 acc_pose: 0.860676 loss: 0.000636 2022/09/14 18:37:06 - mmengine - INFO - Epoch(train) [39][400/586] lr: 5.000000e-04 eta: 12:32:06 time: 0.472370 data_time: 0.031690 memory: 15239 loss_kpt: 0.000626 acc_pose: 0.829589 loss: 0.000626 2022/09/14 18:37:29 - mmengine - INFO - Epoch(train) [39][450/586] lr: 5.000000e-04 eta: 12:31:47 time: 0.462092 data_time: 0.026223 memory: 15239 loss_kpt: 0.000622 acc_pose: 0.786772 loss: 0.000622 2022/09/14 18:37:53 - mmengine - INFO - Epoch(train) [39][500/586] lr: 5.000000e-04 eta: 12:31:30 time: 0.477536 data_time: 0.032329 memory: 15239 loss_kpt: 0.000615 acc_pose: 0.846062 loss: 0.000615 2022/09/14 18:38:17 - mmengine - INFO - Epoch(train) [39][550/586] lr: 5.000000e-04 eta: 12:31:16 time: 0.484789 data_time: 0.037354 memory: 15239 loss_kpt: 0.000605 acc_pose: 0.845642 loss: 0.000605 2022/09/14 18:38:35 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 18:38:35 - mmengine - INFO - Saving checkpoint at 39 epochs 2022/09/14 18:39:06 - mmengine - INFO - Epoch(train) [40][50/586] lr: 5.000000e-04 eta: 12:29:31 time: 0.472840 data_time: 0.037748 memory: 15239 loss_kpt: 0.000617 acc_pose: 0.807493 loss: 0.000617 2022/09/14 18:39:29 - mmengine - INFO - Epoch(train) [40][100/586] lr: 5.000000e-04 eta: 12:29:13 time: 0.466326 data_time: 0.030279 memory: 15239 loss_kpt: 0.000625 acc_pose: 0.875085 loss: 0.000625 2022/09/14 18:39:51 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 18:39:53 - mmengine - INFO - Epoch(train) [40][150/586] lr: 5.000000e-04 eta: 12:28:55 time: 0.470999 data_time: 0.029762 memory: 15239 loss_kpt: 0.000639 acc_pose: 0.774182 loss: 0.000639 2022/09/14 18:40:16 - mmengine - INFO - Epoch(train) [40][200/586] lr: 5.000000e-04 eta: 12:28:37 time: 0.469240 data_time: 0.034056 memory: 15239 loss_kpt: 0.000602 acc_pose: 0.866146 loss: 0.000602 2022/09/14 18:40:40 - mmengine - INFO - Epoch(train) [40][250/586] lr: 5.000000e-04 eta: 12:28:22 time: 0.486444 data_time: 0.030802 memory: 15239 loss_kpt: 0.000657 acc_pose: 0.782405 loss: 0.000657 2022/09/14 18:41:04 - mmengine - INFO - Epoch(train) [40][300/586] lr: 5.000000e-04 eta: 12:28:05 time: 0.470926 data_time: 0.031120 memory: 15239 loss_kpt: 0.000623 acc_pose: 0.827459 loss: 0.000623 2022/09/14 18:41:27 - mmengine - INFO - Epoch(train) [40][350/586] lr: 5.000000e-04 eta: 12:27:46 time: 0.466704 data_time: 0.033712 memory: 15239 loss_kpt: 0.000637 acc_pose: 0.837358 loss: 0.000637 2022/09/14 18:41:50 - mmengine - INFO - Epoch(train) [40][400/586] lr: 5.000000e-04 eta: 12:27:26 time: 0.463417 data_time: 0.030267 memory: 15239 loss_kpt: 0.000616 acc_pose: 0.754968 loss: 0.000616 2022/09/14 18:42:14 - mmengine - INFO - Epoch(train) [40][450/586] lr: 5.000000e-04 eta: 12:27:09 time: 0.471147 data_time: 0.027592 memory: 15239 loss_kpt: 0.000609 acc_pose: 0.820451 loss: 0.000609 2022/09/14 18:42:37 - mmengine - INFO - Epoch(train) [40][500/586] lr: 5.000000e-04 eta: 12:26:50 time: 0.468316 data_time: 0.027767 memory: 15239 loss_kpt: 0.000617 acc_pose: 0.809787 loss: 0.000617 2022/09/14 18:43:01 - mmengine - INFO - Epoch(train) [40][550/586] lr: 5.000000e-04 eta: 12:26:31 time: 0.465778 data_time: 0.027090 memory: 15239 loss_kpt: 0.000622 acc_pose: 0.790055 loss: 0.000622 2022/09/14 18:43:18 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 18:43:18 - mmengine - INFO - Saving checkpoint at 40 epochs 2022/09/14 18:43:35 - mmengine - INFO - Epoch(val) [40][50/407] eta: 0:01:11 time: 0.200021 data_time: 0.013656 memory: 15239 2022/09/14 18:43:45 - mmengine - INFO - Epoch(val) [40][100/407] eta: 0:00:59 time: 0.194878 data_time: 0.008431 memory: 2064 2022/09/14 18:43:55 - mmengine - INFO - Epoch(val) [40][150/407] eta: 0:00:51 time: 0.198699 data_time: 0.008447 memory: 2064 2022/09/14 18:44:05 - mmengine - INFO - Epoch(val) [40][200/407] eta: 0:00:40 time: 0.193771 data_time: 0.008357 memory: 2064 2022/09/14 18:44:15 - mmengine - INFO - Epoch(val) [40][250/407] eta: 0:00:30 time: 0.195183 data_time: 0.008599 memory: 2064 2022/09/14 18:44:24 - mmengine - INFO - Epoch(val) [40][300/407] eta: 0:00:20 time: 0.193958 data_time: 0.008137 memory: 2064 2022/09/14 18:44:34 - mmengine - INFO - Epoch(val) [40][350/407] eta: 0:00:11 time: 0.194435 data_time: 0.008548 memory: 2064 2022/09/14 18:44:44 - mmengine - INFO - Epoch(val) [40][400/407] eta: 0:00:01 time: 0.193596 data_time: 0.008889 memory: 2064 2022/09/14 18:45:21 - mmengine - INFO - Evaluating CocoMetric... 2022/09/14 18:45:35 - mmengine - INFO - Epoch(val) [40][407/407] coco/AP: 0.738869 coco/AP .5: 0.896574 coco/AP .75: 0.805025 coco/AP (M): 0.700146 coco/AP (L): 0.809184 coco/AR: 0.789830 coco/AR .5: 0.932777 coco/AR .75: 0.849339 coco/AR (M): 0.744715 coco/AR (L): 0.854404 2022/09/14 18:45:35 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220914/hrnet_w48_384/best_coco/AP_epoch_30.pth is removed 2022/09/14 18:45:39 - mmengine - INFO - The best checkpoint with 0.7389 coco/AP at 40 epoch is saved to best_coco/AP_epoch_40.pth. 2022/09/14 18:46:03 - mmengine - INFO - Epoch(train) [41][50/586] lr: 5.000000e-04 eta: 12:24:48 time: 0.469954 data_time: 0.031110 memory: 15239 loss_kpt: 0.000617 acc_pose: 0.847051 loss: 0.000617 2022/09/14 18:46:26 - mmengine - INFO - Epoch(train) [41][100/586] lr: 5.000000e-04 eta: 12:24:30 time: 0.470403 data_time: 0.025017 memory: 15239 loss_kpt: 0.000617 acc_pose: 0.829492 loss: 0.000617 2022/09/14 18:46:50 - mmengine - INFO - Epoch(train) [41][150/586] lr: 5.000000e-04 eta: 12:24:12 time: 0.466559 data_time: 0.029445 memory: 15239 loss_kpt: 0.000651 acc_pose: 0.750288 loss: 0.000651 2022/09/14 18:47:13 - mmengine - INFO - Epoch(train) [41][200/586] lr: 5.000000e-04 eta: 12:23:53 time: 0.466790 data_time: 0.024508 memory: 15239 loss_kpt: 0.000621 acc_pose: 0.807650 loss: 0.000621 2022/09/14 18:47:36 - mmengine - INFO - Epoch(train) [41][250/586] lr: 5.000000e-04 eta: 12:23:35 time: 0.469402 data_time: 0.024908 memory: 15239 loss_kpt: 0.000619 acc_pose: 0.840450 loss: 0.000619 2022/09/14 18:48:00 - mmengine - INFO - Epoch(train) [41][300/586] lr: 5.000000e-04 eta: 12:23:15 time: 0.462176 data_time: 0.025605 memory: 15239 loss_kpt: 0.000613 acc_pose: 0.781083 loss: 0.000613 2022/09/14 18:48:23 - mmengine - INFO - Epoch(train) [41][350/586] lr: 5.000000e-04 eta: 12:22:57 time: 0.469275 data_time: 0.026320 memory: 15239 loss_kpt: 0.000616 acc_pose: 0.761623 loss: 0.000616 2022/09/14 18:48:47 - mmengine - INFO - Epoch(train) [41][400/586] lr: 5.000000e-04 eta: 12:22:40 time: 0.472862 data_time: 0.026210 memory: 15239 loss_kpt: 0.000613 acc_pose: 0.842498 loss: 0.000613 2022/09/14 18:49:10 - mmengine - INFO - Epoch(train) [41][450/586] lr: 5.000000e-04 eta: 12:22:20 time: 0.465167 data_time: 0.029240 memory: 15239 loss_kpt: 0.000622 acc_pose: 0.837790 loss: 0.000622 2022/09/14 18:49:34 - mmengine - INFO - Epoch(train) [41][500/586] lr: 5.000000e-04 eta: 12:22:04 time: 0.476800 data_time: 0.025231 memory: 15239 loss_kpt: 0.000625 acc_pose: 0.808094 loss: 0.000625 2022/09/14 18:49:57 - mmengine - INFO - Epoch(train) [41][550/586] lr: 5.000000e-04 eta: 12:21:44 time: 0.461048 data_time: 0.025940 memory: 15239 loss_kpt: 0.000604 acc_pose: 0.806391 loss: 0.000604 2022/09/14 18:50:02 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 18:50:14 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 18:50:14 - mmengine - INFO - Saving checkpoint at 41 epochs 2022/09/14 18:50:44 - mmengine - INFO - Epoch(train) [42][50/586] lr: 5.000000e-04 eta: 12:20:05 time: 0.481297 data_time: 0.032495 memory: 15239 loss_kpt: 0.000605 acc_pose: 0.788523 loss: 0.000605 2022/09/14 18:51:08 - mmengine - INFO - Epoch(train) [42][100/586] lr: 5.000000e-04 eta: 12:19:48 time: 0.474553 data_time: 0.034263 memory: 15239 loss_kpt: 0.000617 acc_pose: 0.828696 loss: 0.000617 2022/09/14 18:51:32 - mmengine - INFO - Epoch(train) [42][150/586] lr: 5.000000e-04 eta: 12:19:30 time: 0.468003 data_time: 0.029543 memory: 15239 loss_kpt: 0.000596 acc_pose: 0.826989 loss: 0.000596 2022/09/14 18:51:55 - mmengine - INFO - Epoch(train) [42][200/586] lr: 5.000000e-04 eta: 12:19:12 time: 0.470957 data_time: 0.033709 memory: 15239 loss_kpt: 0.000617 acc_pose: 0.814127 loss: 0.000617 2022/09/14 18:52:19 - mmengine - INFO - Epoch(train) [42][250/586] lr: 5.000000e-04 eta: 12:18:54 time: 0.470880 data_time: 0.030069 memory: 15239 loss_kpt: 0.000619 acc_pose: 0.784254 loss: 0.000619 2022/09/14 18:52:42 - mmengine - INFO - Epoch(train) [42][300/586] lr: 5.000000e-04 eta: 12:18:34 time: 0.461973 data_time: 0.025682 memory: 15239 loss_kpt: 0.000630 acc_pose: 0.777923 loss: 0.000630 2022/09/14 18:53:06 - mmengine - INFO - Epoch(train) [42][350/586] lr: 5.000000e-04 eta: 12:18:16 time: 0.473238 data_time: 0.024943 memory: 15239 loss_kpt: 0.000611 acc_pose: 0.817519 loss: 0.000611 2022/09/14 18:53:29 - mmengine - INFO - Epoch(train) [42][400/586] lr: 5.000000e-04 eta: 12:17:57 time: 0.463169 data_time: 0.026111 memory: 15239 loss_kpt: 0.000625 acc_pose: 0.793511 loss: 0.000625 2022/09/14 18:53:52 - mmengine - INFO - Epoch(train) [42][450/586] lr: 5.000000e-04 eta: 12:17:39 time: 0.471761 data_time: 0.029105 memory: 15239 loss_kpt: 0.000621 acc_pose: 0.818377 loss: 0.000621 2022/09/14 18:54:16 - mmengine - INFO - Epoch(train) [42][500/586] lr: 5.000000e-04 eta: 12:17:20 time: 0.464483 data_time: 0.024969 memory: 15239 loss_kpt: 0.000612 acc_pose: 0.870785 loss: 0.000612 2022/09/14 18:54:39 - mmengine - INFO - Epoch(train) [42][550/586] lr: 5.000000e-04 eta: 12:17:00 time: 0.460700 data_time: 0.026096 memory: 15239 loss_kpt: 0.000616 acc_pose: 0.802943 loss: 0.000616 2022/09/14 18:54:56 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 18:54:56 - mmengine - INFO - Saving checkpoint at 42 epochs 2022/09/14 18:55:27 - mmengine - INFO - Epoch(train) [43][50/586] lr: 5.000000e-04 eta: 12:15:23 time: 0.479653 data_time: 0.036097 memory: 15239 loss_kpt: 0.000635 acc_pose: 0.791479 loss: 0.000635 2022/09/14 18:55:50 - mmengine - INFO - Epoch(train) [43][100/586] lr: 5.000000e-04 eta: 12:15:04 time: 0.466898 data_time: 0.033616 memory: 15239 loss_kpt: 0.000618 acc_pose: 0.805414 loss: 0.000618 2022/09/14 18:56:13 - mmengine - INFO - Epoch(train) [43][150/586] lr: 5.000000e-04 eta: 12:14:45 time: 0.467805 data_time: 0.031004 memory: 15239 loss_kpt: 0.000643 acc_pose: 0.881908 loss: 0.000643 2022/09/14 18:56:37 - mmengine - INFO - Epoch(train) [43][200/586] lr: 5.000000e-04 eta: 12:14:27 time: 0.468301 data_time: 0.030721 memory: 15239 loss_kpt: 0.000604 acc_pose: 0.797664 loss: 0.000604 2022/09/14 18:57:00 - mmengine - INFO - Epoch(train) [43][250/586] lr: 5.000000e-04 eta: 12:14:08 time: 0.466858 data_time: 0.029949 memory: 15239 loss_kpt: 0.000611 acc_pose: 0.823005 loss: 0.000611 2022/09/14 18:57:24 - mmengine - INFO - Epoch(train) [43][300/586] lr: 5.000000e-04 eta: 12:13:50 time: 0.471699 data_time: 0.031463 memory: 15239 loss_kpt: 0.000606 acc_pose: 0.824069 loss: 0.000606 2022/09/14 18:57:47 - mmengine - INFO - Epoch(train) [43][350/586] lr: 5.000000e-04 eta: 12:13:31 time: 0.465769 data_time: 0.028553 memory: 15239 loss_kpt: 0.000622 acc_pose: 0.823533 loss: 0.000622 2022/09/14 18:58:05 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 18:58:11 - mmengine - INFO - Epoch(train) [43][400/586] lr: 5.000000e-04 eta: 12:13:13 time: 0.469103 data_time: 0.024505 memory: 15239 loss_kpt: 0.000626 acc_pose: 0.678518 loss: 0.000626 2022/09/14 18:58:34 - mmengine - INFO - Epoch(train) [43][450/586] lr: 5.000000e-04 eta: 12:12:53 time: 0.465274 data_time: 0.025238 memory: 15239 loss_kpt: 0.000625 acc_pose: 0.777692 loss: 0.000625 2022/09/14 18:58:57 - mmengine - INFO - Epoch(train) [43][500/586] lr: 5.000000e-04 eta: 12:12:36 time: 0.473353 data_time: 0.024841 memory: 15239 loss_kpt: 0.000623 acc_pose: 0.846365 loss: 0.000623 2022/09/14 18:59:20 - mmengine - INFO - Epoch(train) [43][550/586] lr: 5.000000e-04 eta: 12:12:15 time: 0.459048 data_time: 0.025235 memory: 15239 loss_kpt: 0.000624 acc_pose: 0.779026 loss: 0.000624 2022/09/14 18:59:37 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 18:59:37 - mmengine - INFO - Saving checkpoint at 43 epochs 2022/09/14 19:00:08 - mmengine - INFO - Epoch(train) [44][50/586] lr: 5.000000e-04 eta: 12:10:41 time: 0.484029 data_time: 0.034237 memory: 15239 loss_kpt: 0.000626 acc_pose: 0.809641 loss: 0.000626 2022/09/14 19:00:31 - mmengine - INFO - Epoch(train) [44][100/586] lr: 5.000000e-04 eta: 12:10:22 time: 0.467789 data_time: 0.028980 memory: 15239 loss_kpt: 0.000616 acc_pose: 0.821248 loss: 0.000616 2022/09/14 19:00:55 - mmengine - INFO - Epoch(train) [44][150/586] lr: 5.000000e-04 eta: 12:10:05 time: 0.476054 data_time: 0.024975 memory: 15239 loss_kpt: 0.000632 acc_pose: 0.871521 loss: 0.000632 2022/09/14 19:01:18 - mmengine - INFO - Epoch(train) [44][200/586] lr: 5.000000e-04 eta: 12:09:45 time: 0.458094 data_time: 0.024986 memory: 15239 loss_kpt: 0.000619 acc_pose: 0.808797 loss: 0.000619 2022/09/14 19:01:42 - mmengine - INFO - Epoch(train) [44][250/586] lr: 5.000000e-04 eta: 12:09:26 time: 0.469732 data_time: 0.025293 memory: 15239 loss_kpt: 0.000602 acc_pose: 0.826488 loss: 0.000602 2022/09/14 19:02:05 - mmengine - INFO - Epoch(train) [44][300/586] lr: 5.000000e-04 eta: 12:09:07 time: 0.465081 data_time: 0.025141 memory: 15239 loss_kpt: 0.000601 acc_pose: 0.825282 loss: 0.000601 2022/09/14 19:02:28 - mmengine - INFO - Epoch(train) [44][350/586] lr: 5.000000e-04 eta: 12:08:47 time: 0.461594 data_time: 0.025281 memory: 15239 loss_kpt: 0.000593 acc_pose: 0.846383 loss: 0.000593 2022/09/14 19:02:52 - mmengine - INFO - Epoch(train) [44][400/586] lr: 5.000000e-04 eta: 12:08:30 time: 0.474883 data_time: 0.025421 memory: 15239 loss_kpt: 0.000621 acc_pose: 0.816390 loss: 0.000621 2022/09/14 19:03:15 - mmengine - INFO - Epoch(train) [44][450/586] lr: 5.000000e-04 eta: 12:08:11 time: 0.467881 data_time: 0.025190 memory: 15239 loss_kpt: 0.000612 acc_pose: 0.858553 loss: 0.000612 2022/09/14 19:03:38 - mmengine - INFO - Epoch(train) [44][500/586] lr: 5.000000e-04 eta: 12:07:51 time: 0.460861 data_time: 0.024734 memory: 15239 loss_kpt: 0.000632 acc_pose: 0.794384 loss: 0.000632 2022/09/14 19:04:02 - mmengine - INFO - Epoch(train) [44][550/586] lr: 5.000000e-04 eta: 12:07:33 time: 0.472080 data_time: 0.028602 memory: 15239 loss_kpt: 0.000624 acc_pose: 0.804295 loss: 0.000624 2022/09/14 19:04:19 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 19:04:19 - mmengine - INFO - Saving checkpoint at 44 epochs 2022/09/14 19:04:49 - mmengine - INFO - Epoch(train) [45][50/586] lr: 5.000000e-04 eta: 12:05:59 time: 0.477484 data_time: 0.030003 memory: 15239 loss_kpt: 0.000609 acc_pose: 0.770109 loss: 0.000609 2022/09/14 19:05:13 - mmengine - INFO - Epoch(train) [45][100/586] lr: 5.000000e-04 eta: 12:05:40 time: 0.467507 data_time: 0.025422 memory: 15239 loss_kpt: 0.000604 acc_pose: 0.858406 loss: 0.000604 2022/09/14 19:05:37 - mmengine - INFO - Epoch(train) [45][150/586] lr: 5.000000e-04 eta: 12:05:25 time: 0.482793 data_time: 0.025678 memory: 15239 loss_kpt: 0.000625 acc_pose: 0.817177 loss: 0.000625 2022/09/14 19:06:00 - mmengine - INFO - Epoch(train) [45][200/586] lr: 5.000000e-04 eta: 12:05:06 time: 0.466983 data_time: 0.028890 memory: 15239 loss_kpt: 0.000615 acc_pose: 0.852096 loss: 0.000615 2022/09/14 19:06:07 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 19:06:24 - mmengine - INFO - Epoch(train) [45][250/586] lr: 5.000000e-04 eta: 12:04:47 time: 0.470060 data_time: 0.024789 memory: 15239 loss_kpt: 0.000604 acc_pose: 0.849192 loss: 0.000604 2022/09/14 19:06:47 - mmengine - INFO - Epoch(train) [45][300/586] lr: 5.000000e-04 eta: 12:04:29 time: 0.467671 data_time: 0.025293 memory: 15239 loss_kpt: 0.000604 acc_pose: 0.838616 loss: 0.000604 2022/09/14 19:07:10 - mmengine - INFO - Epoch(train) [45][350/586] lr: 5.000000e-04 eta: 12:04:10 time: 0.466593 data_time: 0.025245 memory: 15239 loss_kpt: 0.000625 acc_pose: 0.844787 loss: 0.000625 2022/09/14 19:07:34 - mmengine - INFO - Epoch(train) [45][400/586] lr: 5.000000e-04 eta: 12:03:52 time: 0.473592 data_time: 0.025665 memory: 15239 loss_kpt: 0.000620 acc_pose: 0.853789 loss: 0.000620 2022/09/14 19:07:57 - mmengine - INFO - Epoch(train) [45][450/586] lr: 5.000000e-04 eta: 12:03:32 time: 0.460662 data_time: 0.026067 memory: 15239 loss_kpt: 0.000622 acc_pose: 0.850178 loss: 0.000622 2022/09/14 19:08:21 - mmengine - INFO - Epoch(train) [45][500/586] lr: 5.000000e-04 eta: 12:03:14 time: 0.472587 data_time: 0.028254 memory: 15239 loss_kpt: 0.000619 acc_pose: 0.868546 loss: 0.000619 2022/09/14 19:08:44 - mmengine - INFO - Epoch(train) [45][550/586] lr: 5.000000e-04 eta: 12:02:54 time: 0.465167 data_time: 0.025806 memory: 15239 loss_kpt: 0.000618 acc_pose: 0.870398 loss: 0.000618 2022/09/14 19:09:00 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 19:09:00 - mmengine - INFO - Saving checkpoint at 45 epochs 2022/09/14 19:09:31 - mmengine - INFO - Epoch(train) [46][50/586] lr: 5.000000e-04 eta: 12:01:22 time: 0.476519 data_time: 0.032499 memory: 15239 loss_kpt: 0.000588 acc_pose: 0.907770 loss: 0.000588 2022/09/14 19:09:55 - mmengine - INFO - Epoch(train) [46][100/586] lr: 5.000000e-04 eta: 12:01:05 time: 0.475449 data_time: 0.025199 memory: 15239 loss_kpt: 0.000609 acc_pose: 0.814747 loss: 0.000609 2022/09/14 19:10:18 - mmengine - INFO - Epoch(train) [46][150/586] lr: 5.000000e-04 eta: 12:00:45 time: 0.464274 data_time: 0.024815 memory: 15239 loss_kpt: 0.000599 acc_pose: 0.798071 loss: 0.000599 2022/09/14 19:10:42 - mmengine - INFO - Epoch(train) [46][200/586] lr: 5.000000e-04 eta: 12:00:27 time: 0.472232 data_time: 0.025560 memory: 15239 loss_kpt: 0.000618 acc_pose: 0.777051 loss: 0.000618 2022/09/14 19:11:05 - mmengine - INFO - Epoch(train) [46][250/586] lr: 5.000000e-04 eta: 12:00:08 time: 0.464078 data_time: 0.025059 memory: 15239 loss_kpt: 0.000597 acc_pose: 0.760717 loss: 0.000597 2022/09/14 19:11:28 - mmengine - INFO - Epoch(train) [46][300/586] lr: 5.000000e-04 eta: 11:59:49 time: 0.470841 data_time: 0.025055 memory: 15239 loss_kpt: 0.000590 acc_pose: 0.807218 loss: 0.000590 2022/09/14 19:11:52 - mmengine - INFO - Epoch(train) [46][350/586] lr: 5.000000e-04 eta: 11:59:31 time: 0.467775 data_time: 0.024676 memory: 15239 loss_kpt: 0.000615 acc_pose: 0.798952 loss: 0.000615 2022/09/14 19:12:16 - mmengine - INFO - Epoch(train) [46][400/586] lr: 5.000000e-04 eta: 11:59:15 time: 0.485846 data_time: 0.025333 memory: 15239 loss_kpt: 0.000605 acc_pose: 0.830787 loss: 0.000605 2022/09/14 19:12:40 - mmengine - INFO - Epoch(train) [46][450/586] lr: 5.000000e-04 eta: 11:58:57 time: 0.475417 data_time: 0.028446 memory: 15239 loss_kpt: 0.000633 acc_pose: 0.827273 loss: 0.000633 2022/09/14 19:13:03 - mmengine - INFO - Epoch(train) [46][500/586] lr: 5.000000e-04 eta: 11:58:38 time: 0.464454 data_time: 0.025623 memory: 15239 loss_kpt: 0.000615 acc_pose: 0.822197 loss: 0.000615 2022/09/14 19:13:27 - mmengine - INFO - Epoch(train) [46][550/586] lr: 5.000000e-04 eta: 11:58:20 time: 0.476194 data_time: 0.025798 memory: 15239 loss_kpt: 0.000608 acc_pose: 0.805003 loss: 0.000608 2022/09/14 19:13:43 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 19:13:43 - mmengine - INFO - Saving checkpoint at 46 epochs 2022/09/14 19:14:10 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 19:14:13 - mmengine - INFO - Epoch(train) [47][50/586] lr: 5.000000e-04 eta: 11:56:48 time: 0.466441 data_time: 0.029229 memory: 15239 loss_kpt: 0.000608 acc_pose: 0.800657 loss: 0.000608 2022/09/14 19:14:37 - mmengine - INFO - Epoch(train) [47][100/586] lr: 5.000000e-04 eta: 11:56:30 time: 0.476585 data_time: 0.029169 memory: 15239 loss_kpt: 0.000610 acc_pose: 0.841298 loss: 0.000610 2022/09/14 19:15:00 - mmengine - INFO - Epoch(train) [47][150/586] lr: 5.000000e-04 eta: 11:56:10 time: 0.457952 data_time: 0.025792 memory: 15239 loss_kpt: 0.000595 acc_pose: 0.892598 loss: 0.000595 2022/09/14 19:15:24 - mmengine - INFO - Epoch(train) [47][200/586] lr: 5.000000e-04 eta: 11:55:52 time: 0.472829 data_time: 0.025034 memory: 15239 loss_kpt: 0.000590 acc_pose: 0.848253 loss: 0.000590 2022/09/14 19:15:47 - mmengine - INFO - Epoch(train) [47][250/586] lr: 5.000000e-04 eta: 11:55:33 time: 0.468209 data_time: 0.027680 memory: 15239 loss_kpt: 0.000613 acc_pose: 0.850838 loss: 0.000613 2022/09/14 19:16:10 - mmengine - INFO - Epoch(train) [47][300/586] lr: 5.000000e-04 eta: 11:55:13 time: 0.462821 data_time: 0.025008 memory: 15239 loss_kpt: 0.000595 acc_pose: 0.827489 loss: 0.000595 2022/09/14 19:16:34 - mmengine - INFO - Epoch(train) [47][350/586] lr: 5.000000e-04 eta: 11:54:54 time: 0.466900 data_time: 0.026450 memory: 15239 loss_kpt: 0.000625 acc_pose: 0.844520 loss: 0.000625 2022/09/14 19:16:57 - mmengine - INFO - Epoch(train) [47][400/586] lr: 5.000000e-04 eta: 11:54:35 time: 0.468916 data_time: 0.028498 memory: 15239 loss_kpt: 0.000607 acc_pose: 0.794831 loss: 0.000607 2022/09/14 19:17:20 - mmengine - INFO - Epoch(train) [47][450/586] lr: 5.000000e-04 eta: 11:54:16 time: 0.466039 data_time: 0.027402 memory: 15239 loss_kpt: 0.000614 acc_pose: 0.815755 loss: 0.000614 2022/09/14 19:17:44 - mmengine - INFO - Epoch(train) [47][500/586] lr: 5.000000e-04 eta: 11:53:57 time: 0.467054 data_time: 0.025058 memory: 15239 loss_kpt: 0.000614 acc_pose: 0.863332 loss: 0.000614 2022/09/14 19:18:08 - mmengine - INFO - Epoch(train) [47][550/586] lr: 5.000000e-04 eta: 11:53:39 time: 0.475178 data_time: 0.025210 memory: 15239 loss_kpt: 0.000600 acc_pose: 0.884336 loss: 0.000600 2022/09/14 19:18:24 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 19:18:24 - mmengine - INFO - Saving checkpoint at 47 epochs 2022/09/14 19:18:55 - mmengine - INFO - Epoch(train) [48][50/586] lr: 5.000000e-04 eta: 11:52:10 time: 0.478854 data_time: 0.039701 memory: 15239 loss_kpt: 0.000594 acc_pose: 0.767058 loss: 0.000594 2022/09/14 19:19:19 - mmengine - INFO - Epoch(train) [48][100/586] lr: 5.000000e-04 eta: 11:51:53 time: 0.475973 data_time: 0.025850 memory: 15239 loss_kpt: 0.000605 acc_pose: 0.818195 loss: 0.000605 2022/09/14 19:19:42 - mmengine - INFO - Epoch(train) [48][150/586] lr: 5.000000e-04 eta: 11:51:34 time: 0.469446 data_time: 0.024254 memory: 15239 loss_kpt: 0.000631 acc_pose: 0.821536 loss: 0.000631 2022/09/14 19:20:06 - mmengine - INFO - Epoch(train) [48][200/586] lr: 5.000000e-04 eta: 11:51:17 time: 0.475563 data_time: 0.025332 memory: 15239 loss_kpt: 0.000600 acc_pose: 0.873766 loss: 0.000600 2022/09/14 19:20:29 - mmengine - INFO - Epoch(train) [48][250/586] lr: 5.000000e-04 eta: 11:50:58 time: 0.466556 data_time: 0.025492 memory: 15239 loss_kpt: 0.000626 acc_pose: 0.802204 loss: 0.000626 2022/09/14 19:20:52 - mmengine - INFO - Epoch(train) [48][300/586] lr: 5.000000e-04 eta: 11:50:37 time: 0.459370 data_time: 0.025603 memory: 15239 loss_kpt: 0.000606 acc_pose: 0.737670 loss: 0.000606 2022/09/14 19:21:16 - mmengine - INFO - Epoch(train) [48][350/586] lr: 5.000000e-04 eta: 11:50:19 time: 0.474355 data_time: 0.025396 memory: 15239 loss_kpt: 0.000624 acc_pose: 0.796527 loss: 0.000624 2022/09/14 19:21:39 - mmengine - INFO - Epoch(train) [48][400/586] lr: 5.000000e-04 eta: 11:50:01 time: 0.470547 data_time: 0.024764 memory: 15239 loss_kpt: 0.000617 acc_pose: 0.740377 loss: 0.000617 2022/09/14 19:22:03 - mmengine - INFO - Epoch(train) [48][450/586] lr: 5.000000e-04 eta: 11:49:41 time: 0.465434 data_time: 0.025786 memory: 15239 loss_kpt: 0.000598 acc_pose: 0.845838 loss: 0.000598 2022/09/14 19:22:07 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 19:22:27 - mmengine - INFO - Epoch(train) [48][500/586] lr: 5.000000e-04 eta: 11:49:24 time: 0.478051 data_time: 0.025166 memory: 15239 loss_kpt: 0.000598 acc_pose: 0.864683 loss: 0.000598 2022/09/14 19:22:50 - mmengine - INFO - Epoch(train) [48][550/586] lr: 5.000000e-04 eta: 11:49:05 time: 0.465724 data_time: 0.024984 memory: 15239 loss_kpt: 0.000589 acc_pose: 0.844010 loss: 0.000589 2022/09/14 19:23:07 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 19:23:07 - mmengine - INFO - Saving checkpoint at 48 epochs 2022/09/14 19:23:37 - mmengine - INFO - Epoch(train) [49][50/586] lr: 5.000000e-04 eta: 11:47:36 time: 0.472100 data_time: 0.029352 memory: 15239 loss_kpt: 0.000592 acc_pose: 0.900931 loss: 0.000592 2022/09/14 19:24:01 - mmengine - INFO - Epoch(train) [49][100/586] lr: 5.000000e-04 eta: 11:47:18 time: 0.472339 data_time: 0.024663 memory: 15239 loss_kpt: 0.000601 acc_pose: 0.842676 loss: 0.000601 2022/09/14 19:24:24 - mmengine - INFO - Epoch(train) [49][150/586] lr: 5.000000e-04 eta: 11:46:58 time: 0.464819 data_time: 0.025425 memory: 15239 loss_kpt: 0.000586 acc_pose: 0.855262 loss: 0.000586 2022/09/14 19:24:47 - mmengine - INFO - Epoch(train) [49][200/586] lr: 5.000000e-04 eta: 11:46:38 time: 0.461206 data_time: 0.026574 memory: 15239 loss_kpt: 0.000609 acc_pose: 0.880528 loss: 0.000609 2022/09/14 19:25:11 - mmengine - INFO - Epoch(train) [49][250/586] lr: 5.000000e-04 eta: 11:46:20 time: 0.470563 data_time: 0.024925 memory: 15239 loss_kpt: 0.000614 acc_pose: 0.796464 loss: 0.000614 2022/09/14 19:25:34 - mmengine - INFO - Epoch(train) [49][300/586] lr: 5.000000e-04 eta: 11:46:01 time: 0.468596 data_time: 0.025882 memory: 15239 loss_kpt: 0.000607 acc_pose: 0.832264 loss: 0.000607 2022/09/14 19:25:58 - mmengine - INFO - Epoch(train) [49][350/586] lr: 5.000000e-04 eta: 11:45:43 time: 0.476114 data_time: 0.025631 memory: 15239 loss_kpt: 0.000612 acc_pose: 0.887182 loss: 0.000612 2022/09/14 19:26:21 - mmengine - INFO - Epoch(train) [49][400/586] lr: 5.000000e-04 eta: 11:45:23 time: 0.463289 data_time: 0.029189 memory: 15239 loss_kpt: 0.000602 acc_pose: 0.809890 loss: 0.000602 2022/09/14 19:26:45 - mmengine - INFO - Epoch(train) [49][450/586] lr: 5.000000e-04 eta: 11:45:06 time: 0.478482 data_time: 0.025482 memory: 15239 loss_kpt: 0.000600 acc_pose: 0.818289 loss: 0.000600 2022/09/14 19:27:08 - mmengine - INFO - Epoch(train) [49][500/586] lr: 5.000000e-04 eta: 11:44:46 time: 0.465411 data_time: 0.025682 memory: 15239 loss_kpt: 0.000617 acc_pose: 0.877482 loss: 0.000617 2022/09/14 19:27:32 - mmengine - INFO - Epoch(train) [49][550/586] lr: 5.000000e-04 eta: 11:44:27 time: 0.467365 data_time: 0.024943 memory: 15239 loss_kpt: 0.000610 acc_pose: 0.858496 loss: 0.000610 2022/09/14 19:27:49 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 19:27:49 - mmengine - INFO - Saving checkpoint at 49 epochs 2022/09/14 19:28:20 - mmengine - INFO - Epoch(train) [50][50/586] lr: 5.000000e-04 eta: 11:43:01 time: 0.481269 data_time: 0.039937 memory: 15239 loss_kpt: 0.000593 acc_pose: 0.842318 loss: 0.000593 2022/09/14 19:28:44 - mmengine - INFO - Epoch(train) [50][100/586] lr: 5.000000e-04 eta: 11:42:42 time: 0.464036 data_time: 0.025054 memory: 15239 loss_kpt: 0.000595 acc_pose: 0.821291 loss: 0.000595 2022/09/14 19:29:07 - mmengine - INFO - Epoch(train) [50][150/586] lr: 5.000000e-04 eta: 11:42:22 time: 0.463592 data_time: 0.025469 memory: 15239 loss_kpt: 0.000595 acc_pose: 0.782646 loss: 0.000595 2022/09/14 19:29:30 - mmengine - INFO - Epoch(train) [50][200/586] lr: 5.000000e-04 eta: 11:42:02 time: 0.463972 data_time: 0.028098 memory: 15239 loss_kpt: 0.000609 acc_pose: 0.809259 loss: 0.000609 2022/09/14 19:29:54 - mmengine - INFO - Epoch(train) [50][250/586] lr: 5.000000e-04 eta: 11:41:45 time: 0.481240 data_time: 0.024868 memory: 15239 loss_kpt: 0.000614 acc_pose: 0.858222 loss: 0.000614 2022/09/14 19:30:11 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 19:30:17 - mmengine - INFO - Epoch(train) [50][300/586] lr: 5.000000e-04 eta: 11:41:25 time: 0.459939 data_time: 0.025226 memory: 15239 loss_kpt: 0.000615 acc_pose: 0.822792 loss: 0.000615 2022/09/14 19:30:41 - mmengine - INFO - Epoch(train) [50][350/586] lr: 5.000000e-04 eta: 11:41:08 time: 0.480433 data_time: 0.029059 memory: 15239 loss_kpt: 0.000588 acc_pose: 0.880926 loss: 0.000588 2022/09/14 19:31:04 - mmengine - INFO - Epoch(train) [50][400/586] lr: 5.000000e-04 eta: 11:40:48 time: 0.462486 data_time: 0.025263 memory: 15239 loss_kpt: 0.000615 acc_pose: 0.872510 loss: 0.000615 2022/09/14 19:31:28 - mmengine - INFO - Epoch(train) [50][450/586] lr: 5.000000e-04 eta: 11:40:29 time: 0.468829 data_time: 0.025106 memory: 15239 loss_kpt: 0.000602 acc_pose: 0.886769 loss: 0.000602 2022/09/14 19:31:51 - mmengine - INFO - Epoch(train) [50][500/586] lr: 5.000000e-04 eta: 11:40:10 time: 0.468256 data_time: 0.029889 memory: 15239 loss_kpt: 0.000617 acc_pose: 0.837817 loss: 0.000617 2022/09/14 19:32:15 - mmengine - INFO - Epoch(train) [50][550/586] lr: 5.000000e-04 eta: 11:39:52 time: 0.474575 data_time: 0.025679 memory: 15239 loss_kpt: 0.000590 acc_pose: 0.822619 loss: 0.000590 2022/09/14 19:32:32 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 19:32:32 - mmengine - INFO - Saving checkpoint at 50 epochs 2022/09/14 19:32:49 - mmengine - INFO - Epoch(val) [50][50/407] eta: 0:01:12 time: 0.203052 data_time: 0.014060 memory: 15239 2022/09/14 19:32:59 - mmengine - INFO - Epoch(val) [50][100/407] eta: 0:00:59 time: 0.195080 data_time: 0.008586 memory: 2064 2022/09/14 19:33:08 - mmengine - INFO - Epoch(val) [50][150/407] eta: 0:00:50 time: 0.196140 data_time: 0.008290 memory: 2064 2022/09/14 19:33:18 - mmengine - INFO - Epoch(val) [50][200/407] eta: 0:00:41 time: 0.198560 data_time: 0.011861 memory: 2064 2022/09/14 19:33:28 - mmengine - INFO - Epoch(val) [50][250/407] eta: 0:00:30 time: 0.195650 data_time: 0.008752 memory: 2064 2022/09/14 19:33:38 - mmengine - INFO - Epoch(val) [50][300/407] eta: 0:00:20 time: 0.194892 data_time: 0.008365 memory: 2064 2022/09/14 19:33:48 - mmengine - INFO - Epoch(val) [50][350/407] eta: 0:00:11 time: 0.194842 data_time: 0.008314 memory: 2064 2022/09/14 19:33:57 - mmengine - INFO - Epoch(val) [50][400/407] eta: 0:00:01 time: 0.193852 data_time: 0.008053 memory: 2064 2022/09/14 19:34:34 - mmengine - INFO - Evaluating CocoMetric... 2022/09/14 19:34:47 - mmengine - INFO - Epoch(val) [50][407/407] coco/AP: 0.741159 coco/AP .5: 0.898173 coco/AP .75: 0.811539 coco/AP (M): 0.703472 coco/AP (L): 0.809657 coco/AR: 0.791829 coco/AR .5: 0.935926 coco/AR .75: 0.855006 coco/AR (M): 0.748566 coco/AR (L): 0.854255 2022/09/14 19:34:47 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220914/hrnet_w48_384/best_coco/AP_epoch_40.pth is removed 2022/09/14 19:34:52 - mmengine - INFO - The best checkpoint with 0.7412 coco/AP at 50 epoch is saved to best_coco/AP_epoch_50.pth. 2022/09/14 19:35:15 - mmengine - INFO - Epoch(train) [51][50/586] lr: 5.000000e-04 eta: 11:38:26 time: 0.471870 data_time: 0.031101 memory: 15239 loss_kpt: 0.000596 acc_pose: 0.821539 loss: 0.000596 2022/09/14 19:35:39 - mmengine - INFO - Epoch(train) [51][100/586] lr: 5.000000e-04 eta: 11:38:06 time: 0.465302 data_time: 0.024326 memory: 15239 loss_kpt: 0.000600 acc_pose: 0.801411 loss: 0.000600 2022/09/14 19:36:02 - mmengine - INFO - Epoch(train) [51][150/586] lr: 5.000000e-04 eta: 11:37:49 time: 0.476895 data_time: 0.025438 memory: 15239 loss_kpt: 0.000591 acc_pose: 0.836616 loss: 0.000591 2022/09/14 19:36:26 - mmengine - INFO - Epoch(train) [51][200/586] lr: 5.000000e-04 eta: 11:37:30 time: 0.467245 data_time: 0.024989 memory: 15239 loss_kpt: 0.000583 acc_pose: 0.813876 loss: 0.000583 2022/09/14 19:36:49 - mmengine - INFO - Epoch(train) [51][250/586] lr: 5.000000e-04 eta: 11:37:11 time: 0.473363 data_time: 0.025270 memory: 15239 loss_kpt: 0.000616 acc_pose: 0.868218 loss: 0.000616 2022/09/14 19:37:13 - mmengine - INFO - Epoch(train) [51][300/586] lr: 5.000000e-04 eta: 11:36:52 time: 0.465585 data_time: 0.025108 memory: 15239 loss_kpt: 0.000590 acc_pose: 0.881113 loss: 0.000590 2022/09/14 19:37:36 - mmengine - INFO - Epoch(train) [51][350/586] lr: 5.000000e-04 eta: 11:36:32 time: 0.465162 data_time: 0.025128 memory: 15239 loss_kpt: 0.000603 acc_pose: 0.847459 loss: 0.000603 2022/09/14 19:37:59 - mmengine - INFO - Epoch(train) [51][400/586] lr: 5.000000e-04 eta: 11:36:14 time: 0.470388 data_time: 0.025395 memory: 15239 loss_kpt: 0.000592 acc_pose: 0.809403 loss: 0.000592 2022/09/14 19:38:23 - mmengine - INFO - Epoch(train) [51][450/586] lr: 5.000000e-04 eta: 11:35:54 time: 0.465061 data_time: 0.029708 memory: 15239 loss_kpt: 0.000598 acc_pose: 0.858616 loss: 0.000598 2022/09/14 19:38:46 - mmengine - INFO - Epoch(train) [51][500/586] lr: 5.000000e-04 eta: 11:35:35 time: 0.472176 data_time: 0.024811 memory: 15239 loss_kpt: 0.000618 acc_pose: 0.799860 loss: 0.000618 2022/09/14 19:39:10 - mmengine - INFO - Epoch(train) [51][550/586] lr: 5.000000e-04 eta: 11:35:16 time: 0.464107 data_time: 0.025308 memory: 15239 loss_kpt: 0.000598 acc_pose: 0.861497 loss: 0.000598 2022/09/14 19:39:26 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 19:39:26 - mmengine - INFO - Saving checkpoint at 51 epochs 2022/09/14 19:39:57 - mmengine - INFO - Epoch(train) [52][50/586] lr: 5.000000e-04 eta: 11:33:53 time: 0.485141 data_time: 0.029863 memory: 15239 loss_kpt: 0.000620 acc_pose: 0.812851 loss: 0.000620 2022/09/14 19:40:21 - mmengine - INFO - Epoch(train) [52][100/586] lr: 5.000000e-04 eta: 11:33:34 time: 0.470752 data_time: 0.024570 memory: 15239 loss_kpt: 0.000587 acc_pose: 0.837768 loss: 0.000587 2022/09/14 19:40:28 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 19:40:45 - mmengine - INFO - Epoch(train) [52][150/586] lr: 5.000000e-04 eta: 11:33:16 time: 0.473708 data_time: 0.029312 memory: 15239 loss_kpt: 0.000574 acc_pose: 0.885427 loss: 0.000574 2022/09/14 19:41:08 - mmengine - INFO - Epoch(train) [52][200/586] lr: 5.000000e-04 eta: 11:32:57 time: 0.468395 data_time: 0.025029 memory: 15239 loss_kpt: 0.000589 acc_pose: 0.813873 loss: 0.000589 2022/09/14 19:41:31 - mmengine - INFO - Epoch(train) [52][250/586] lr: 5.000000e-04 eta: 11:32:37 time: 0.463139 data_time: 0.025210 memory: 15239 loss_kpt: 0.000587 acc_pose: 0.844883 loss: 0.000587 2022/09/14 19:41:54 - mmengine - INFO - Epoch(train) [52][300/586] lr: 5.000000e-04 eta: 11:32:17 time: 0.461977 data_time: 0.024138 memory: 15239 loss_kpt: 0.000593 acc_pose: 0.829302 loss: 0.000593 2022/09/14 19:42:18 - mmengine - INFO - Epoch(train) [52][350/586] lr: 5.000000e-04 eta: 11:31:58 time: 0.472744 data_time: 0.024528 memory: 15239 loss_kpt: 0.000592 acc_pose: 0.856143 loss: 0.000592 2022/09/14 19:42:41 - mmengine - INFO - Epoch(train) [52][400/586] lr: 5.000000e-04 eta: 11:31:39 time: 0.469149 data_time: 0.025452 memory: 15239 loss_kpt: 0.000606 acc_pose: 0.891787 loss: 0.000606 2022/09/14 19:43:05 - mmengine - INFO - Epoch(train) [52][450/586] lr: 5.000000e-04 eta: 11:31:20 time: 0.468007 data_time: 0.024801 memory: 15239 loss_kpt: 0.000585 acc_pose: 0.832962 loss: 0.000585 2022/09/14 19:43:28 - mmengine - INFO - Epoch(train) [52][500/586] lr: 5.000000e-04 eta: 11:31:02 time: 0.471969 data_time: 0.024478 memory: 15239 loss_kpt: 0.000611 acc_pose: 0.845338 loss: 0.000611 2022/09/14 19:43:52 - mmengine - INFO - Epoch(train) [52][550/586] lr: 5.000000e-04 eta: 11:30:42 time: 0.464510 data_time: 0.025087 memory: 15239 loss_kpt: 0.000602 acc_pose: 0.820835 loss: 0.000602 2022/09/14 19:44:08 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 19:44:08 - mmengine - INFO - Saving checkpoint at 52 epochs 2022/09/14 19:44:39 - mmengine - INFO - Epoch(train) [53][50/586] lr: 5.000000e-04 eta: 11:29:19 time: 0.479843 data_time: 0.034220 memory: 15239 loss_kpt: 0.000619 acc_pose: 0.832758 loss: 0.000619 2022/09/14 19:45:03 - mmengine - INFO - Epoch(train) [53][100/586] lr: 5.000000e-04 eta: 11:29:00 time: 0.469292 data_time: 0.026065 memory: 15239 loss_kpt: 0.000592 acc_pose: 0.826199 loss: 0.000592 2022/09/14 19:45:26 - mmengine - INFO - Epoch(train) [53][150/586] lr: 5.000000e-04 eta: 11:28:40 time: 0.462220 data_time: 0.025236 memory: 15239 loss_kpt: 0.000607 acc_pose: 0.795934 loss: 0.000607 2022/09/14 19:45:49 - mmengine - INFO - Epoch(train) [53][200/586] lr: 5.000000e-04 eta: 11:28:21 time: 0.469110 data_time: 0.025793 memory: 15239 loss_kpt: 0.000584 acc_pose: 0.825732 loss: 0.000584 2022/09/14 19:46:12 - mmengine - INFO - Epoch(train) [53][250/586] lr: 5.000000e-04 eta: 11:28:02 time: 0.464938 data_time: 0.025093 memory: 15239 loss_kpt: 0.000597 acc_pose: 0.794428 loss: 0.000597 2022/09/14 19:46:35 - mmengine - INFO - Epoch(train) [53][300/586] lr: 5.000000e-04 eta: 11:27:42 time: 0.461562 data_time: 0.025084 memory: 15239 loss_kpt: 0.000596 acc_pose: 0.844596 loss: 0.000596 2022/09/14 19:46:59 - mmengine - INFO - Epoch(train) [53][350/586] lr: 5.000000e-04 eta: 11:27:23 time: 0.475152 data_time: 0.028612 memory: 15239 loss_kpt: 0.000623 acc_pose: 0.803646 loss: 0.000623 2022/09/14 19:47:23 - mmengine - INFO - Epoch(train) [53][400/586] lr: 5.000000e-04 eta: 11:27:04 time: 0.465938 data_time: 0.025317 memory: 15239 loss_kpt: 0.000599 acc_pose: 0.830269 loss: 0.000599 2022/09/14 19:47:46 - mmengine - INFO - Epoch(train) [53][450/586] lr: 5.000000e-04 eta: 11:26:44 time: 0.463952 data_time: 0.026024 memory: 15239 loss_kpt: 0.000567 acc_pose: 0.904858 loss: 0.000567 2022/09/14 19:48:09 - mmengine - INFO - Epoch(train) [53][500/586] lr: 5.000000e-04 eta: 11:26:24 time: 0.466309 data_time: 0.025161 memory: 15239 loss_kpt: 0.000598 acc_pose: 0.820684 loss: 0.000598 2022/09/14 19:48:22 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 19:48:32 - mmengine - INFO - Epoch(train) [53][550/586] lr: 5.000000e-04 eta: 11:26:05 time: 0.468152 data_time: 0.025191 memory: 15239 loss_kpt: 0.000598 acc_pose: 0.826122 loss: 0.000598 2022/09/14 19:48:49 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 19:48:49 - mmengine - INFO - Saving checkpoint at 53 epochs 2022/09/14 19:49:20 - mmengine - INFO - Epoch(train) [54][50/586] lr: 5.000000e-04 eta: 11:24:44 time: 0.483318 data_time: 0.029844 memory: 15239 loss_kpt: 0.000602 acc_pose: 0.788873 loss: 0.000602 2022/09/14 19:49:44 - mmengine - INFO - Epoch(train) [54][100/586] lr: 5.000000e-04 eta: 11:24:26 time: 0.475923 data_time: 0.024440 memory: 15239 loss_kpt: 0.000589 acc_pose: 0.838649 loss: 0.000589 2022/09/14 19:50:07 - mmengine - INFO - Epoch(train) [54][150/586] lr: 5.000000e-04 eta: 11:24:08 time: 0.470837 data_time: 0.024934 memory: 15239 loss_kpt: 0.000604 acc_pose: 0.853937 loss: 0.000604 2022/09/14 19:50:31 - mmengine - INFO - Epoch(train) [54][200/586] lr: 5.000000e-04 eta: 11:23:48 time: 0.468787 data_time: 0.024746 memory: 15239 loss_kpt: 0.000601 acc_pose: 0.823891 loss: 0.000601 2022/09/14 19:50:54 - mmengine - INFO - Epoch(train) [54][250/586] lr: 5.000000e-04 eta: 11:23:29 time: 0.469448 data_time: 0.024873 memory: 15239 loss_kpt: 0.000599 acc_pose: 0.774948 loss: 0.000599 2022/09/14 19:51:18 - mmengine - INFO - Epoch(train) [54][300/586] lr: 5.000000e-04 eta: 11:23:11 time: 0.472510 data_time: 0.025149 memory: 15239 loss_kpt: 0.000596 acc_pose: 0.817820 loss: 0.000596 2022/09/14 19:51:41 - mmengine - INFO - Epoch(train) [54][350/586] lr: 5.000000e-04 eta: 11:22:52 time: 0.468116 data_time: 0.025491 memory: 15239 loss_kpt: 0.000599 acc_pose: 0.867981 loss: 0.000599 2022/09/14 19:52:04 - mmengine - INFO - Epoch(train) [54][400/586] lr: 5.000000e-04 eta: 11:22:31 time: 0.460260 data_time: 0.025474 memory: 15239 loss_kpt: 0.000626 acc_pose: 0.822515 loss: 0.000626 2022/09/14 19:52:28 - mmengine - INFO - Epoch(train) [54][450/586] lr: 5.000000e-04 eta: 11:22:12 time: 0.467463 data_time: 0.029344 memory: 15239 loss_kpt: 0.000598 acc_pose: 0.821615 loss: 0.000598 2022/09/14 19:52:51 - mmengine - INFO - Epoch(train) [54][500/586] lr: 5.000000e-04 eta: 11:21:53 time: 0.469542 data_time: 0.025042 memory: 15239 loss_kpt: 0.000623 acc_pose: 0.791526 loss: 0.000623 2022/09/14 19:53:14 - mmengine - INFO - Epoch(train) [54][550/586] lr: 5.000000e-04 eta: 11:21:33 time: 0.462561 data_time: 0.025362 memory: 15239 loss_kpt: 0.000590 acc_pose: 0.919499 loss: 0.000590 2022/09/14 19:53:31 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 19:53:31 - mmengine - INFO - Saving checkpoint at 54 epochs 2022/09/14 19:54:02 - mmengine - INFO - Epoch(train) [55][50/586] lr: 5.000000e-04 eta: 11:20:12 time: 0.478306 data_time: 0.031535 memory: 15239 loss_kpt: 0.000614 acc_pose: 0.808164 loss: 0.000614 2022/09/14 19:54:26 - mmengine - INFO - Epoch(train) [55][100/586] lr: 5.000000e-04 eta: 11:19:53 time: 0.468951 data_time: 0.030421 memory: 15239 loss_kpt: 0.000599 acc_pose: 0.825684 loss: 0.000599 2022/09/14 19:54:49 - mmengine - INFO - Epoch(train) [55][150/586] lr: 5.000000e-04 eta: 11:19:33 time: 0.465435 data_time: 0.025143 memory: 15239 loss_kpt: 0.000577 acc_pose: 0.860242 loss: 0.000577 2022/09/14 19:55:13 - mmengine - INFO - Epoch(train) [55][200/586] lr: 5.000000e-04 eta: 11:19:15 time: 0.473060 data_time: 0.025655 memory: 15239 loss_kpt: 0.000595 acc_pose: 0.841446 loss: 0.000595 2022/09/14 19:55:36 - mmengine - INFO - Epoch(train) [55][250/586] lr: 5.000000e-04 eta: 11:18:55 time: 0.466669 data_time: 0.024857 memory: 15239 loss_kpt: 0.000616 acc_pose: 0.799738 loss: 0.000616 2022/09/14 19:55:59 - mmengine - INFO - Epoch(train) [55][300/586] lr: 5.000000e-04 eta: 11:18:36 time: 0.469393 data_time: 0.024875 memory: 15239 loss_kpt: 0.000609 acc_pose: 0.849970 loss: 0.000609 2022/09/14 19:56:22 - mmengine - INFO - Epoch(train) [55][350/586] lr: 5.000000e-04 eta: 11:18:16 time: 0.461108 data_time: 0.025545 memory: 15239 loss_kpt: 0.000609 acc_pose: 0.867109 loss: 0.000609 2022/09/14 19:56:25 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 19:56:46 - mmengine - INFO - Epoch(train) [55][400/586] lr: 5.000000e-04 eta: 11:17:56 time: 0.461871 data_time: 0.024923 memory: 15239 loss_kpt: 0.000602 acc_pose: 0.762561 loss: 0.000602 2022/09/14 19:57:09 - mmengine - INFO - Epoch(train) [55][450/586] lr: 5.000000e-04 eta: 11:17:36 time: 0.465556 data_time: 0.024886 memory: 15239 loss_kpt: 0.000603 acc_pose: 0.820549 loss: 0.000603 2022/09/14 19:57:33 - mmengine - INFO - Epoch(train) [55][500/586] lr: 5.000000e-04 eta: 11:17:17 time: 0.472827 data_time: 0.024873 memory: 15239 loss_kpt: 0.000592 acc_pose: 0.880762 loss: 0.000592 2022/09/14 19:57:56 - mmengine - INFO - Epoch(train) [55][550/586] lr: 5.000000e-04 eta: 11:16:58 time: 0.466598 data_time: 0.028470 memory: 15239 loss_kpt: 0.000611 acc_pose: 0.813417 loss: 0.000611 2022/09/14 19:58:13 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 19:58:13 - mmengine - INFO - Saving checkpoint at 55 epochs 2022/09/14 19:58:44 - mmengine - INFO - Epoch(train) [56][50/586] lr: 5.000000e-04 eta: 11:15:39 time: 0.483262 data_time: 0.040890 memory: 15239 loss_kpt: 0.000601 acc_pose: 0.827996 loss: 0.000601 2022/09/14 19:59:07 - mmengine - INFO - Epoch(train) [56][100/586] lr: 5.000000e-04 eta: 11:15:19 time: 0.461950 data_time: 0.025865 memory: 15239 loss_kpt: 0.000577 acc_pose: 0.774887 loss: 0.000577 2022/09/14 19:59:30 - mmengine - INFO - Epoch(train) [56][150/586] lr: 5.000000e-04 eta: 11:15:00 time: 0.468864 data_time: 0.024830 memory: 15239 loss_kpt: 0.000601 acc_pose: 0.795829 loss: 0.000601 2022/09/14 19:59:54 - mmengine - INFO - Epoch(train) [56][200/586] lr: 5.000000e-04 eta: 11:14:41 time: 0.473720 data_time: 0.024513 memory: 15239 loss_kpt: 0.000597 acc_pose: 0.838642 loss: 0.000597 2022/09/14 20:00:18 - mmengine - INFO - Epoch(train) [56][250/586] lr: 5.000000e-04 eta: 11:14:22 time: 0.472897 data_time: 0.025108 memory: 15239 loss_kpt: 0.000608 acc_pose: 0.821122 loss: 0.000608 2022/09/14 20:00:41 - mmengine - INFO - Epoch(train) [56][300/586] lr: 5.000000e-04 eta: 11:14:02 time: 0.459350 data_time: 0.024759 memory: 15239 loss_kpt: 0.000590 acc_pose: 0.841661 loss: 0.000590 2022/09/14 20:01:05 - mmengine - INFO - Epoch(train) [56][350/586] lr: 5.000000e-04 eta: 11:13:45 time: 0.485571 data_time: 0.025600 memory: 15239 loss_kpt: 0.000587 acc_pose: 0.850614 loss: 0.000587 2022/09/14 20:01:28 - mmengine - INFO - Epoch(train) [56][400/586] lr: 5.000000e-04 eta: 11:13:25 time: 0.467264 data_time: 0.025142 memory: 15239 loss_kpt: 0.000607 acc_pose: 0.852853 loss: 0.000607 2022/09/14 20:01:52 - mmengine - INFO - Epoch(train) [56][450/586] lr: 5.000000e-04 eta: 11:13:06 time: 0.466314 data_time: 0.024973 memory: 15239 loss_kpt: 0.000590 acc_pose: 0.795830 loss: 0.000590 2022/09/14 20:02:15 - mmengine - INFO - Epoch(train) [56][500/586] lr: 5.000000e-04 eta: 11:12:46 time: 0.467786 data_time: 0.024539 memory: 15239 loss_kpt: 0.000612 acc_pose: 0.839733 loss: 0.000612 2022/09/14 20:02:38 - mmengine - INFO - Epoch(train) [56][550/586] lr: 5.000000e-04 eta: 11:12:26 time: 0.464567 data_time: 0.024792 memory: 15239 loss_kpt: 0.000590 acc_pose: 0.872608 loss: 0.000590 2022/09/14 20:02:55 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 20:02:55 - mmengine - INFO - Saving checkpoint at 56 epochs 2022/09/14 20:03:26 - mmengine - INFO - Epoch(train) [57][50/586] lr: 5.000000e-04 eta: 11:11:08 time: 0.479326 data_time: 0.030160 memory: 15239 loss_kpt: 0.000587 acc_pose: 0.865573 loss: 0.000587 2022/09/14 20:03:50 - mmengine - INFO - Epoch(train) [57][100/586] lr: 5.000000e-04 eta: 11:10:50 time: 0.475437 data_time: 0.025280 memory: 15239 loss_kpt: 0.000613 acc_pose: 0.843538 loss: 0.000613 2022/09/14 20:04:13 - mmengine - INFO - Epoch(train) [57][150/586] lr: 5.000000e-04 eta: 11:10:32 time: 0.477654 data_time: 0.025255 memory: 15239 loss_kpt: 0.000604 acc_pose: 0.840376 loss: 0.000604 2022/09/14 20:04:29 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 20:04:37 - mmengine - INFO - Epoch(train) [57][200/586] lr: 5.000000e-04 eta: 11:10:12 time: 0.463948 data_time: 0.026018 memory: 15239 loss_kpt: 0.000602 acc_pose: 0.810334 loss: 0.000602 2022/09/14 20:05:00 - mmengine - INFO - Epoch(train) [57][250/586] lr: 5.000000e-04 eta: 11:09:53 time: 0.470379 data_time: 0.025853 memory: 15239 loss_kpt: 0.000592 acc_pose: 0.840132 loss: 0.000592 2022/09/14 20:05:24 - mmengine - INFO - Epoch(train) [57][300/586] lr: 5.000000e-04 eta: 11:09:34 time: 0.473591 data_time: 0.024827 memory: 15239 loss_kpt: 0.000587 acc_pose: 0.784746 loss: 0.000587 2022/09/14 20:05:47 - mmengine - INFO - Epoch(train) [57][350/586] lr: 5.000000e-04 eta: 11:09:15 time: 0.471249 data_time: 0.024640 memory: 15239 loss_kpt: 0.000582 acc_pose: 0.787378 loss: 0.000582 2022/09/14 20:06:11 - mmengine - INFO - Epoch(train) [57][400/586] lr: 5.000000e-04 eta: 11:08:55 time: 0.466539 data_time: 0.025553 memory: 15239 loss_kpt: 0.000590 acc_pose: 0.765120 loss: 0.000590 2022/09/14 20:06:35 - mmengine - INFO - Epoch(train) [57][450/586] lr: 5.000000e-04 eta: 11:08:39 time: 0.488655 data_time: 0.028586 memory: 15239 loss_kpt: 0.000611 acc_pose: 0.832959 loss: 0.000611 2022/09/14 20:06:59 - mmengine - INFO - Epoch(train) [57][500/586] lr: 5.000000e-04 eta: 11:08:19 time: 0.468303 data_time: 0.025763 memory: 15239 loss_kpt: 0.000589 acc_pose: 0.779356 loss: 0.000589 2022/09/14 20:07:22 - mmengine - INFO - Epoch(train) [57][550/586] lr: 5.000000e-04 eta: 11:08:00 time: 0.465536 data_time: 0.025077 memory: 15239 loss_kpt: 0.000620 acc_pose: 0.885940 loss: 0.000620 2022/09/14 20:07:39 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 20:07:39 - mmengine - INFO - Saving checkpoint at 57 epochs 2022/09/14 20:08:10 - mmengine - INFO - Epoch(train) [58][50/586] lr: 5.000000e-04 eta: 11:06:43 time: 0.486184 data_time: 0.036364 memory: 15239 loss_kpt: 0.000591 acc_pose: 0.819161 loss: 0.000591 2022/09/14 20:08:33 - mmengine - INFO - Epoch(train) [58][100/586] lr: 5.000000e-04 eta: 11:06:24 time: 0.471589 data_time: 0.030526 memory: 15239 loss_kpt: 0.000592 acc_pose: 0.832117 loss: 0.000592 2022/09/14 20:08:56 - mmengine - INFO - Epoch(train) [58][150/586] lr: 5.000000e-04 eta: 11:06:04 time: 0.464300 data_time: 0.030752 memory: 15239 loss_kpt: 0.000600 acc_pose: 0.835041 loss: 0.000600 2022/09/14 20:09:20 - mmengine - INFO - Epoch(train) [58][200/586] lr: 5.000000e-04 eta: 11:05:46 time: 0.478351 data_time: 0.034276 memory: 15239 loss_kpt: 0.000604 acc_pose: 0.848054 loss: 0.000604 2022/09/14 20:09:44 - mmengine - INFO - Epoch(train) [58][250/586] lr: 5.000000e-04 eta: 11:05:27 time: 0.465694 data_time: 0.026624 memory: 15239 loss_kpt: 0.000602 acc_pose: 0.858841 loss: 0.000602 2022/09/14 20:10:07 - mmengine - INFO - Epoch(train) [58][300/586] lr: 5.000000e-04 eta: 11:05:07 time: 0.466310 data_time: 0.025129 memory: 15239 loss_kpt: 0.000582 acc_pose: 0.886375 loss: 0.000582 2022/09/14 20:10:31 - mmengine - INFO - Epoch(train) [58][350/586] lr: 5.000000e-04 eta: 11:04:48 time: 0.473445 data_time: 0.025333 memory: 15239 loss_kpt: 0.000589 acc_pose: 0.863393 loss: 0.000589 2022/09/14 20:10:54 - mmengine - INFO - Epoch(train) [58][400/586] lr: 5.000000e-04 eta: 11:04:28 time: 0.464734 data_time: 0.025290 memory: 15239 loss_kpt: 0.000600 acc_pose: 0.879166 loss: 0.000600 2022/09/14 20:11:17 - mmengine - INFO - Epoch(train) [58][450/586] lr: 5.000000e-04 eta: 11:04:08 time: 0.466873 data_time: 0.028713 memory: 15239 loss_kpt: 0.000591 acc_pose: 0.837211 loss: 0.000591 2022/09/14 20:11:41 - mmengine - INFO - Epoch(train) [58][500/586] lr: 5.000000e-04 eta: 11:03:49 time: 0.470902 data_time: 0.025398 memory: 15239 loss_kpt: 0.000585 acc_pose: 0.871621 loss: 0.000585 2022/09/14 20:12:04 - mmengine - INFO - Epoch(train) [58][550/586] lr: 5.000000e-04 eta: 11:03:30 time: 0.470285 data_time: 0.025362 memory: 15239 loss_kpt: 0.000590 acc_pose: 0.855188 loss: 0.000590 2022/09/14 20:12:21 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 20:12:21 - mmengine - INFO - Saving checkpoint at 58 epochs 2022/09/14 20:12:34 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 20:12:52 - mmengine - INFO - Epoch(train) [59][50/586] lr: 5.000000e-04 eta: 11:02:13 time: 0.474889 data_time: 0.030472 memory: 15239 loss_kpt: 0.000588 acc_pose: 0.853700 loss: 0.000588 2022/09/14 20:13:15 - mmengine - INFO - Epoch(train) [59][100/586] lr: 5.000000e-04 eta: 11:01:55 time: 0.475247 data_time: 0.026367 memory: 15239 loss_kpt: 0.000576 acc_pose: 0.907261 loss: 0.000576 2022/09/14 20:13:38 - mmengine - INFO - Epoch(train) [59][150/586] lr: 5.000000e-04 eta: 11:01:35 time: 0.463063 data_time: 0.025950 memory: 15239 loss_kpt: 0.000586 acc_pose: 0.805285 loss: 0.000586 2022/09/14 20:14:02 - mmengine - INFO - Epoch(train) [59][200/586] lr: 5.000000e-04 eta: 11:01:15 time: 0.469595 data_time: 0.025503 memory: 15239 loss_kpt: 0.000575 acc_pose: 0.901585 loss: 0.000575 2022/09/14 20:14:26 - mmengine - INFO - Epoch(train) [59][250/586] lr: 5.000000e-04 eta: 11:00:56 time: 0.471756 data_time: 0.028685 memory: 15239 loss_kpt: 0.000590 acc_pose: 0.834515 loss: 0.000590 2022/09/14 20:14:49 - mmengine - INFO - Epoch(train) [59][300/586] lr: 5.000000e-04 eta: 11:00:36 time: 0.461639 data_time: 0.025480 memory: 15239 loss_kpt: 0.000604 acc_pose: 0.864853 loss: 0.000604 2022/09/14 20:15:12 - mmengine - INFO - Epoch(train) [59][350/586] lr: 5.000000e-04 eta: 11:00:17 time: 0.471369 data_time: 0.025771 memory: 15239 loss_kpt: 0.000586 acc_pose: 0.804024 loss: 0.000586 2022/09/14 20:15:36 - mmengine - INFO - Epoch(train) [59][400/586] lr: 5.000000e-04 eta: 10:59:57 time: 0.466030 data_time: 0.025708 memory: 15239 loss_kpt: 0.000590 acc_pose: 0.786824 loss: 0.000590 2022/09/14 20:15:59 - mmengine - INFO - Epoch(train) [59][450/586] lr: 5.000000e-04 eta: 10:59:37 time: 0.468942 data_time: 0.024235 memory: 15239 loss_kpt: 0.000591 acc_pose: 0.827989 loss: 0.000591 2022/09/14 20:16:23 - mmengine - INFO - Epoch(train) [59][500/586] lr: 5.000000e-04 eta: 10:59:18 time: 0.471279 data_time: 0.026884 memory: 15239 loss_kpt: 0.000583 acc_pose: 0.824648 loss: 0.000583 2022/09/14 20:16:46 - mmengine - INFO - Epoch(train) [59][550/586] lr: 5.000000e-04 eta: 10:58:59 time: 0.470033 data_time: 0.025386 memory: 15239 loss_kpt: 0.000575 acc_pose: 0.844959 loss: 0.000575 2022/09/14 20:17:03 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 20:17:03 - mmengine - INFO - Saving checkpoint at 59 epochs 2022/09/14 20:17:33 - mmengine - INFO - Epoch(train) [60][50/586] lr: 5.000000e-04 eta: 10:57:43 time: 0.474462 data_time: 0.028772 memory: 15239 loss_kpt: 0.000587 acc_pose: 0.861685 loss: 0.000587 2022/09/14 20:17:56 - mmengine - INFO - Epoch(train) [60][100/586] lr: 5.000000e-04 eta: 10:57:24 time: 0.469409 data_time: 0.024097 memory: 15239 loss_kpt: 0.000593 acc_pose: 0.788271 loss: 0.000593 2022/09/14 20:18:20 - mmengine - INFO - Epoch(train) [60][150/586] lr: 5.000000e-04 eta: 10:57:04 time: 0.466153 data_time: 0.025729 memory: 15239 loss_kpt: 0.000580 acc_pose: 0.800591 loss: 0.000580 2022/09/14 20:18:43 - mmengine - INFO - Epoch(train) [60][200/586] lr: 5.000000e-04 eta: 10:56:45 time: 0.472130 data_time: 0.029091 memory: 15239 loss_kpt: 0.000576 acc_pose: 0.877489 loss: 0.000576 2022/09/14 20:19:07 - mmengine - INFO - Epoch(train) [60][250/586] lr: 5.000000e-04 eta: 10:56:26 time: 0.470779 data_time: 0.025650 memory: 15239 loss_kpt: 0.000585 acc_pose: 0.888186 loss: 0.000585 2022/09/14 20:19:30 - mmengine - INFO - Epoch(train) [60][300/586] lr: 5.000000e-04 eta: 10:56:06 time: 0.469485 data_time: 0.025980 memory: 15239 loss_kpt: 0.000597 acc_pose: 0.799032 loss: 0.000597 2022/09/14 20:19:54 - mmengine - INFO - Epoch(train) [60][350/586] lr: 5.000000e-04 eta: 10:55:47 time: 0.474031 data_time: 0.025816 memory: 15239 loss_kpt: 0.000597 acc_pose: 0.886632 loss: 0.000597 2022/09/14 20:20:18 - mmengine - INFO - Epoch(train) [60][400/586] lr: 5.000000e-04 eta: 10:55:28 time: 0.468011 data_time: 0.025182 memory: 15239 loss_kpt: 0.000598 acc_pose: 0.828965 loss: 0.000598 2022/09/14 20:20:30 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 20:20:41 - mmengine - INFO - Epoch(train) [60][450/586] lr: 5.000000e-04 eta: 10:55:08 time: 0.467800 data_time: 0.025462 memory: 15239 loss_kpt: 0.000599 acc_pose: 0.819508 loss: 0.000599 2022/09/14 20:21:04 - mmengine - INFO - Epoch(train) [60][500/586] lr: 5.000000e-04 eta: 10:54:49 time: 0.468830 data_time: 0.027830 memory: 15239 loss_kpt: 0.000590 acc_pose: 0.811158 loss: 0.000590 2022/09/14 20:21:28 - mmengine - INFO - Epoch(train) [60][550/586] lr: 5.000000e-04 eta: 10:54:29 time: 0.465636 data_time: 0.025163 memory: 15239 loss_kpt: 0.000589 acc_pose: 0.877128 loss: 0.000589 2022/09/14 20:21:44 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 20:21:44 - mmengine - INFO - Saving checkpoint at 60 epochs 2022/09/14 20:22:02 - mmengine - INFO - Epoch(val) [60][50/407] eta: 0:01:12 time: 0.201827 data_time: 0.013775 memory: 15239 2022/09/14 20:22:12 - mmengine - INFO - Epoch(val) [60][100/407] eta: 0:01:00 time: 0.196337 data_time: 0.008385 memory: 2064 2022/09/14 20:22:21 - mmengine - INFO - Epoch(val) [60][150/407] eta: 0:00:49 time: 0.194511 data_time: 0.008257 memory: 2064 2022/09/14 20:22:31 - mmengine - INFO - Epoch(val) [60][200/407] eta: 0:00:40 time: 0.196150 data_time: 0.008935 memory: 2064 2022/09/14 20:22:41 - mmengine - INFO - Epoch(val) [60][250/407] eta: 0:00:31 time: 0.198537 data_time: 0.008920 memory: 2064 2022/09/14 20:22:51 - mmengine - INFO - Epoch(val) [60][300/407] eta: 0:00:21 time: 0.198195 data_time: 0.011617 memory: 2064 2022/09/14 20:23:01 - mmengine - INFO - Epoch(val) [60][350/407] eta: 0:00:11 time: 0.196144 data_time: 0.008605 memory: 2064 2022/09/14 20:23:10 - mmengine - INFO - Epoch(val) [60][400/407] eta: 0:00:01 time: 0.192927 data_time: 0.007948 memory: 2064 2022/09/14 20:23:47 - mmengine - INFO - Evaluating CocoMetric... 2022/09/14 20:24:00 - mmengine - INFO - Epoch(val) [60][407/407] coco/AP: 0.747278 coco/AP .5: 0.901327 coco/AP .75: 0.814604 coco/AP (M): 0.709594 coco/AP (L): 0.817238 coco/AR: 0.798725 coco/AR .5: 0.940491 coco/AR .75: 0.859257 coco/AR (M): 0.755067 coco/AR (L): 0.861353 2022/09/14 20:24:01 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220914/hrnet_w48_384/best_coco/AP_epoch_50.pth is removed 2022/09/14 20:24:04 - mmengine - INFO - The best checkpoint with 0.7473 coco/AP at 60 epoch is saved to best_coco/AP_epoch_60.pth. 2022/09/14 20:24:29 - mmengine - INFO - Epoch(train) [61][50/586] lr: 5.000000e-04 eta: 10:53:17 time: 0.500380 data_time: 0.035718 memory: 15239 loss_kpt: 0.000592 acc_pose: 0.816121 loss: 0.000592 2022/09/14 20:24:53 - mmengine - INFO - Epoch(train) [61][100/586] lr: 5.000000e-04 eta: 10:52:58 time: 0.477242 data_time: 0.028963 memory: 15239 loss_kpt: 0.000578 acc_pose: 0.833517 loss: 0.000578 2022/09/14 20:25:17 - mmengine - INFO - Epoch(train) [61][150/586] lr: 5.000000e-04 eta: 10:52:40 time: 0.474897 data_time: 0.024894 memory: 15239 loss_kpt: 0.000602 acc_pose: 0.832490 loss: 0.000602 2022/09/14 20:25:41 - mmengine - INFO - Epoch(train) [61][200/586] lr: 5.000000e-04 eta: 10:52:21 time: 0.477035 data_time: 0.026416 memory: 15239 loss_kpt: 0.000597 acc_pose: 0.833346 loss: 0.000597 2022/09/14 20:26:04 - mmengine - INFO - Epoch(train) [61][250/586] lr: 5.000000e-04 eta: 10:52:01 time: 0.466354 data_time: 0.025262 memory: 15239 loss_kpt: 0.000589 acc_pose: 0.833394 loss: 0.000589 2022/09/14 20:26:28 - mmengine - INFO - Epoch(train) [61][300/586] lr: 5.000000e-04 eta: 10:51:42 time: 0.471764 data_time: 0.025119 memory: 15239 loss_kpt: 0.000607 acc_pose: 0.765741 loss: 0.000607 2022/09/14 20:26:51 - mmengine - INFO - Epoch(train) [61][350/586] lr: 5.000000e-04 eta: 10:51:23 time: 0.471219 data_time: 0.025177 memory: 15239 loss_kpt: 0.000581 acc_pose: 0.833858 loss: 0.000581 2022/09/14 20:27:15 - mmengine - INFO - Epoch(train) [61][400/586] lr: 5.000000e-04 eta: 10:51:03 time: 0.469458 data_time: 0.026336 memory: 15239 loss_kpt: 0.000608 acc_pose: 0.898034 loss: 0.000608 2022/09/14 20:27:38 - mmengine - INFO - Epoch(train) [61][450/586] lr: 5.000000e-04 eta: 10:50:44 time: 0.471472 data_time: 0.028130 memory: 15239 loss_kpt: 0.000597 acc_pose: 0.843217 loss: 0.000597 2022/09/14 20:28:02 - mmengine - INFO - Epoch(train) [61][500/586] lr: 5.000000e-04 eta: 10:50:24 time: 0.467870 data_time: 0.024973 memory: 15239 loss_kpt: 0.000578 acc_pose: 0.851334 loss: 0.000578 2022/09/14 20:28:25 - mmengine - INFO - Epoch(train) [61][550/586] lr: 5.000000e-04 eta: 10:50:05 time: 0.466360 data_time: 0.024217 memory: 15239 loss_kpt: 0.000599 acc_pose: 0.820752 loss: 0.000599 2022/09/14 20:28:42 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 20:28:42 - mmengine - INFO - Saving checkpoint at 61 epochs 2022/09/14 20:29:13 - mmengine - INFO - Epoch(train) [62][50/586] lr: 5.000000e-04 eta: 10:48:51 time: 0.482102 data_time: 0.035231 memory: 15239 loss_kpt: 0.000562 acc_pose: 0.830946 loss: 0.000562 2022/09/14 20:29:36 - mmengine - INFO - Epoch(train) [62][100/586] lr: 5.000000e-04 eta: 10:48:31 time: 0.465173 data_time: 0.029554 memory: 15239 loss_kpt: 0.000577 acc_pose: 0.840878 loss: 0.000577 2022/09/14 20:30:00 - mmengine - INFO - Epoch(train) [62][150/586] lr: 5.000000e-04 eta: 10:48:12 time: 0.470212 data_time: 0.025615 memory: 15239 loss_kpt: 0.000582 acc_pose: 0.840122 loss: 0.000582 2022/09/14 20:30:24 - mmengine - INFO - Epoch(train) [62][200/586] lr: 5.000000e-04 eta: 10:47:55 time: 0.489577 data_time: 0.024302 memory: 15239 loss_kpt: 0.000609 acc_pose: 0.825268 loss: 0.000609 2022/09/14 20:30:48 - mmengine - INFO - Epoch(train) [62][250/586] lr: 5.000000e-04 eta: 10:47:36 time: 0.477236 data_time: 0.025513 memory: 15239 loss_kpt: 0.000598 acc_pose: 0.895531 loss: 0.000598 2022/09/14 20:30:50 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 20:31:11 - mmengine - INFO - Epoch(train) [62][300/586] lr: 5.000000e-04 eta: 10:47:17 time: 0.470806 data_time: 0.025452 memory: 15239 loss_kpt: 0.000581 acc_pose: 0.761772 loss: 0.000581 2022/09/14 20:31:35 - mmengine - INFO - Epoch(train) [62][350/586] lr: 5.000000e-04 eta: 10:46:58 time: 0.473549 data_time: 0.024963 memory: 15239 loss_kpt: 0.000606 acc_pose: 0.884514 loss: 0.000606 2022/09/14 20:31:59 - mmengine - INFO - Epoch(train) [62][400/586] lr: 5.000000e-04 eta: 10:46:38 time: 0.470429 data_time: 0.029298 memory: 15239 loss_kpt: 0.000584 acc_pose: 0.827112 loss: 0.000584 2022/09/14 20:32:22 - mmengine - INFO - Epoch(train) [62][450/586] lr: 5.000000e-04 eta: 10:46:19 time: 0.466809 data_time: 0.025086 memory: 15239 loss_kpt: 0.000592 acc_pose: 0.820695 loss: 0.000592 2022/09/14 20:32:46 - mmengine - INFO - Epoch(train) [62][500/586] lr: 5.000000e-04 eta: 10:46:00 time: 0.477598 data_time: 0.025713 memory: 15239 loss_kpt: 0.000586 acc_pose: 0.825314 loss: 0.000586 2022/09/14 20:33:09 - mmengine - INFO - Epoch(train) [62][550/586] lr: 5.000000e-04 eta: 10:45:40 time: 0.467686 data_time: 0.025259 memory: 15239 loss_kpt: 0.000598 acc_pose: 0.843770 loss: 0.000598 2022/09/14 20:33:26 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 20:33:26 - mmengine - INFO - Saving checkpoint at 62 epochs 2022/09/14 20:33:57 - mmengine - INFO - Epoch(train) [63][50/586] lr: 5.000000e-04 eta: 10:44:27 time: 0.478474 data_time: 0.033367 memory: 15239 loss_kpt: 0.000596 acc_pose: 0.802955 loss: 0.000596 2022/09/14 20:34:20 - mmengine - INFO - Epoch(train) [63][100/586] lr: 5.000000e-04 eta: 10:44:08 time: 0.472960 data_time: 0.024274 memory: 15239 loss_kpt: 0.000573 acc_pose: 0.882035 loss: 0.000573 2022/09/14 20:34:44 - mmengine - INFO - Epoch(train) [63][150/586] lr: 5.000000e-04 eta: 10:43:49 time: 0.470525 data_time: 0.025911 memory: 15239 loss_kpt: 0.000583 acc_pose: 0.909070 loss: 0.000583 2022/09/14 20:35:07 - mmengine - INFO - Epoch(train) [63][200/586] lr: 5.000000e-04 eta: 10:43:29 time: 0.466026 data_time: 0.025357 memory: 15239 loss_kpt: 0.000578 acc_pose: 0.863082 loss: 0.000578 2022/09/14 20:35:31 - mmengine - INFO - Epoch(train) [63][250/586] lr: 5.000000e-04 eta: 10:43:10 time: 0.472895 data_time: 0.024952 memory: 15239 loss_kpt: 0.000583 acc_pose: 0.765817 loss: 0.000583 2022/09/14 20:35:54 - mmengine - INFO - Epoch(train) [63][300/586] lr: 5.000000e-04 eta: 10:42:50 time: 0.469968 data_time: 0.025187 memory: 15239 loss_kpt: 0.000602 acc_pose: 0.870299 loss: 0.000602 2022/09/14 20:36:18 - mmengine - INFO - Epoch(train) [63][350/586] lr: 5.000000e-04 eta: 10:42:30 time: 0.463708 data_time: 0.025308 memory: 15239 loss_kpt: 0.000593 acc_pose: 0.788607 loss: 0.000593 2022/09/14 20:36:42 - mmengine - INFO - Epoch(train) [63][400/586] lr: 5.000000e-04 eta: 10:42:12 time: 0.485808 data_time: 0.025730 memory: 15239 loss_kpt: 0.000582 acc_pose: 0.827987 loss: 0.000582 2022/09/14 20:37:06 - mmengine - INFO - Epoch(train) [63][450/586] lr: 5.000000e-04 eta: 10:41:53 time: 0.475815 data_time: 0.024961 memory: 15239 loss_kpt: 0.000575 acc_pose: 0.835643 loss: 0.000575 2022/09/14 20:37:29 - mmengine - INFO - Epoch(train) [63][500/586] lr: 5.000000e-04 eta: 10:41:34 time: 0.467244 data_time: 0.025692 memory: 15239 loss_kpt: 0.000590 acc_pose: 0.864235 loss: 0.000590 2022/09/14 20:37:53 - mmengine - INFO - Epoch(train) [63][550/586] lr: 5.000000e-04 eta: 10:41:15 time: 0.478584 data_time: 0.025443 memory: 15239 loss_kpt: 0.000591 acc_pose: 0.870838 loss: 0.000591 2022/09/14 20:38:10 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 20:38:10 - mmengine - INFO - Saving checkpoint at 63 epochs 2022/09/14 20:38:40 - mmengine - INFO - Epoch(train) [64][50/586] lr: 5.000000e-04 eta: 10:40:02 time: 0.474364 data_time: 0.031429 memory: 15239 loss_kpt: 0.000591 acc_pose: 0.837847 loss: 0.000591 2022/09/14 20:38:55 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 20:39:04 - mmengine - INFO - Epoch(train) [64][100/586] lr: 5.000000e-04 eta: 10:39:44 time: 0.475667 data_time: 0.025355 memory: 15239 loss_kpt: 0.000587 acc_pose: 0.867530 loss: 0.000587 2022/09/14 20:39:27 - mmengine - INFO - Epoch(train) [64][150/586] lr: 5.000000e-04 eta: 10:39:23 time: 0.464671 data_time: 0.025147 memory: 15239 loss_kpt: 0.000590 acc_pose: 0.801619 loss: 0.000590 2022/09/14 20:39:50 - mmengine - INFO - Epoch(train) [64][200/586] lr: 5.000000e-04 eta: 10:39:03 time: 0.461357 data_time: 0.025223 memory: 15239 loss_kpt: 0.000590 acc_pose: 0.830503 loss: 0.000590 2022/09/14 20:40:14 - mmengine - INFO - Epoch(train) [64][250/586] lr: 5.000000e-04 eta: 10:38:44 time: 0.480425 data_time: 0.032258 memory: 15239 loss_kpt: 0.000590 acc_pose: 0.804988 loss: 0.000590 2022/09/14 20:40:37 - mmengine - INFO - Epoch(train) [64][300/586] lr: 5.000000e-04 eta: 10:38:24 time: 0.463259 data_time: 0.027781 memory: 15239 loss_kpt: 0.000580 acc_pose: 0.834845 loss: 0.000580 2022/09/14 20:41:00 - mmengine - INFO - Epoch(train) [64][350/586] lr: 5.000000e-04 eta: 10:38:04 time: 0.461829 data_time: 0.027015 memory: 15239 loss_kpt: 0.000594 acc_pose: 0.828963 loss: 0.000594 2022/09/14 20:41:24 - mmengine - INFO - Epoch(train) [64][400/586] lr: 5.000000e-04 eta: 10:37:45 time: 0.479367 data_time: 0.026366 memory: 15239 loss_kpt: 0.000598 acc_pose: 0.775706 loss: 0.000598 2022/09/14 20:41:48 - mmengine - INFO - Epoch(train) [64][450/586] lr: 5.000000e-04 eta: 10:37:25 time: 0.462593 data_time: 0.027798 memory: 15239 loss_kpt: 0.000599 acc_pose: 0.880097 loss: 0.000599 2022/09/14 20:42:11 - mmengine - INFO - Epoch(train) [64][500/586] lr: 5.000000e-04 eta: 10:37:05 time: 0.465166 data_time: 0.027364 memory: 15239 loss_kpt: 0.000600 acc_pose: 0.799229 loss: 0.000600 2022/09/14 20:42:35 - mmengine - INFO - Epoch(train) [64][550/586] lr: 5.000000e-04 eta: 10:36:45 time: 0.474954 data_time: 0.027625 memory: 15239 loss_kpt: 0.000590 acc_pose: 0.870726 loss: 0.000590 2022/09/14 20:42:51 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 20:42:51 - mmengine - INFO - Saving checkpoint at 64 epochs 2022/09/14 20:43:22 - mmengine - INFO - Epoch(train) [65][50/586] lr: 5.000000e-04 eta: 10:35:33 time: 0.472567 data_time: 0.030098 memory: 15239 loss_kpt: 0.000573 acc_pose: 0.798592 loss: 0.000573 2022/09/14 20:43:45 - mmengine - INFO - Epoch(train) [65][100/586] lr: 5.000000e-04 eta: 10:35:14 time: 0.474325 data_time: 0.027170 memory: 15239 loss_kpt: 0.000583 acc_pose: 0.894971 loss: 0.000583 2022/09/14 20:44:09 - mmengine - INFO - Epoch(train) [65][150/586] lr: 5.000000e-04 eta: 10:34:54 time: 0.467303 data_time: 0.026240 memory: 15239 loss_kpt: 0.000577 acc_pose: 0.854745 loss: 0.000577 2022/09/14 20:44:32 - mmengine - INFO - Epoch(train) [65][200/586] lr: 5.000000e-04 eta: 10:34:35 time: 0.470585 data_time: 0.025874 memory: 15239 loss_kpt: 0.000592 acc_pose: 0.806936 loss: 0.000592 2022/09/14 20:44:56 - mmengine - INFO - Epoch(train) [65][250/586] lr: 5.000000e-04 eta: 10:34:15 time: 0.466906 data_time: 0.026701 memory: 15239 loss_kpt: 0.000580 acc_pose: 0.794602 loss: 0.000580 2022/09/14 20:45:19 - mmengine - INFO - Epoch(train) [65][300/586] lr: 5.000000e-04 eta: 10:33:55 time: 0.462701 data_time: 0.027014 memory: 15239 loss_kpt: 0.000575 acc_pose: 0.887435 loss: 0.000575 2022/09/14 20:45:42 - mmengine - INFO - Epoch(train) [65][350/586] lr: 5.000000e-04 eta: 10:33:35 time: 0.469599 data_time: 0.030650 memory: 15239 loss_kpt: 0.000586 acc_pose: 0.837236 loss: 0.000586 2022/09/14 20:46:06 - mmengine - INFO - Epoch(train) [65][400/586] lr: 5.000000e-04 eta: 10:33:15 time: 0.471599 data_time: 0.026719 memory: 15239 loss_kpt: 0.000585 acc_pose: 0.807819 loss: 0.000585 2022/09/14 20:46:29 - mmengine - INFO - Epoch(train) [65][450/586] lr: 5.000000e-04 eta: 10:32:55 time: 0.460160 data_time: 0.027018 memory: 15239 loss_kpt: 0.000562 acc_pose: 0.843098 loss: 0.000562 2022/09/14 20:46:51 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 20:46:52 - mmengine - INFO - Epoch(train) [65][500/586] lr: 5.000000e-04 eta: 10:32:35 time: 0.468084 data_time: 0.026363 memory: 15239 loss_kpt: 0.000592 acc_pose: 0.779945 loss: 0.000592 2022/09/14 20:47:16 - mmengine - INFO - Epoch(train) [65][550/586] lr: 5.000000e-04 eta: 10:32:15 time: 0.468314 data_time: 0.027467 memory: 15239 loss_kpt: 0.000586 acc_pose: 0.839897 loss: 0.000586 2022/09/14 20:47:32 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 20:47:32 - mmengine - INFO - Saving checkpoint at 65 epochs 2022/09/14 20:48:03 - mmengine - INFO - Epoch(train) [66][50/586] lr: 5.000000e-04 eta: 10:31:04 time: 0.476702 data_time: 0.035689 memory: 15239 loss_kpt: 0.000564 acc_pose: 0.828096 loss: 0.000564 2022/09/14 20:48:26 - mmengine - INFO - Epoch(train) [66][100/586] lr: 5.000000e-04 eta: 10:30:44 time: 0.468546 data_time: 0.031062 memory: 15239 loss_kpt: 0.000597 acc_pose: 0.799607 loss: 0.000597 2022/09/14 20:48:50 - mmengine - INFO - Epoch(train) [66][150/586] lr: 5.000000e-04 eta: 10:30:25 time: 0.468737 data_time: 0.030302 memory: 15239 loss_kpt: 0.000581 acc_pose: 0.850569 loss: 0.000581 2022/09/14 20:49:13 - mmengine - INFO - Epoch(train) [66][200/586] lr: 5.000000e-04 eta: 10:30:05 time: 0.471834 data_time: 0.031068 memory: 15239 loss_kpt: 0.000595 acc_pose: 0.811936 loss: 0.000595 2022/09/14 20:49:37 - mmengine - INFO - Epoch(train) [66][250/586] lr: 5.000000e-04 eta: 10:29:45 time: 0.468384 data_time: 0.036140 memory: 15239 loss_kpt: 0.000577 acc_pose: 0.803927 loss: 0.000577 2022/09/14 20:50:00 - mmengine - INFO - Epoch(train) [66][300/586] lr: 5.000000e-04 eta: 10:29:25 time: 0.462512 data_time: 0.028886 memory: 15239 loss_kpt: 0.000583 acc_pose: 0.852850 loss: 0.000583 2022/09/14 20:50:23 - mmengine - INFO - Epoch(train) [66][350/586] lr: 5.000000e-04 eta: 10:29:05 time: 0.467041 data_time: 0.026797 memory: 15239 loss_kpt: 0.000580 acc_pose: 0.833217 loss: 0.000580 2022/09/14 20:50:47 - mmengine - INFO - Epoch(train) [66][400/586] lr: 5.000000e-04 eta: 10:28:45 time: 0.467626 data_time: 0.027724 memory: 15239 loss_kpt: 0.000582 acc_pose: 0.881898 loss: 0.000582 2022/09/14 20:51:10 - mmengine - INFO - Epoch(train) [66][450/586] lr: 5.000000e-04 eta: 10:28:24 time: 0.458894 data_time: 0.025743 memory: 15239 loss_kpt: 0.000584 acc_pose: 0.832052 loss: 0.000584 2022/09/14 20:51:33 - mmengine - INFO - Epoch(train) [66][500/586] lr: 5.000000e-04 eta: 10:28:05 time: 0.470905 data_time: 0.027073 memory: 15239 loss_kpt: 0.000574 acc_pose: 0.856918 loss: 0.000574 2022/09/14 20:51:56 - mmengine - INFO - Epoch(train) [66][550/586] lr: 5.000000e-04 eta: 10:27:44 time: 0.462596 data_time: 0.030449 memory: 15239 loss_kpt: 0.000561 acc_pose: 0.838880 loss: 0.000561 2022/09/14 20:52:13 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 20:52:13 - mmengine - INFO - Saving checkpoint at 66 epochs 2022/09/14 20:52:44 - mmengine - INFO - Epoch(train) [67][50/586] lr: 5.000000e-04 eta: 10:26:35 time: 0.481993 data_time: 0.030933 memory: 15239 loss_kpt: 0.000564 acc_pose: 0.851937 loss: 0.000564 2022/09/14 20:53:08 - mmengine - INFO - Epoch(train) [67][100/586] lr: 5.000000e-04 eta: 10:26:14 time: 0.465724 data_time: 0.026073 memory: 15239 loss_kpt: 0.000572 acc_pose: 0.878629 loss: 0.000572 2022/09/14 20:53:31 - mmengine - INFO - Epoch(train) [67][150/586] lr: 5.000000e-04 eta: 10:25:55 time: 0.469538 data_time: 0.027554 memory: 15239 loss_kpt: 0.000600 acc_pose: 0.848769 loss: 0.000600 2022/09/14 20:53:54 - mmengine - INFO - Epoch(train) [67][200/586] lr: 5.000000e-04 eta: 10:25:35 time: 0.465172 data_time: 0.026339 memory: 15239 loss_kpt: 0.000581 acc_pose: 0.794290 loss: 0.000581 2022/09/14 20:54:18 - mmengine - INFO - Epoch(train) [67][250/586] lr: 5.000000e-04 eta: 10:25:14 time: 0.463471 data_time: 0.026664 memory: 15239 loss_kpt: 0.000583 acc_pose: 0.897236 loss: 0.000583 2022/09/14 20:54:41 - mmengine - INFO - Epoch(train) [67][300/586] lr: 5.000000e-04 eta: 10:24:55 time: 0.471706 data_time: 0.027202 memory: 15239 loss_kpt: 0.000570 acc_pose: 0.826059 loss: 0.000570 2022/09/14 20:54:53 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 20:55:05 - mmengine - INFO - Epoch(train) [67][350/586] lr: 5.000000e-04 eta: 10:24:35 time: 0.470437 data_time: 0.026887 memory: 15239 loss_kpt: 0.000593 acc_pose: 0.808591 loss: 0.000593 2022/09/14 20:55:28 - mmengine - INFO - Epoch(train) [67][400/586] lr: 5.000000e-04 eta: 10:24:14 time: 0.457599 data_time: 0.027347 memory: 15239 loss_kpt: 0.000582 acc_pose: 0.853286 loss: 0.000582 2022/09/14 20:55:51 - mmengine - INFO - Epoch(train) [67][450/586] lr: 5.000000e-04 eta: 10:23:54 time: 0.466320 data_time: 0.027573 memory: 15239 loss_kpt: 0.000575 acc_pose: 0.821891 loss: 0.000575 2022/09/14 20:56:14 - mmengine - INFO - Epoch(train) [67][500/586] lr: 5.000000e-04 eta: 10:23:34 time: 0.469156 data_time: 0.030940 memory: 15239 loss_kpt: 0.000574 acc_pose: 0.802451 loss: 0.000574 2022/09/14 20:56:37 - mmengine - INFO - Epoch(train) [67][550/586] lr: 5.000000e-04 eta: 10:23:13 time: 0.459842 data_time: 0.027798 memory: 15239 loss_kpt: 0.000572 acc_pose: 0.817886 loss: 0.000572 2022/09/14 20:56:54 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 20:56:54 - mmengine - INFO - Saving checkpoint at 67 epochs 2022/09/14 20:57:25 - mmengine - INFO - Epoch(train) [68][50/586] lr: 5.000000e-04 eta: 10:22:04 time: 0.479713 data_time: 0.030789 memory: 15239 loss_kpt: 0.000575 acc_pose: 0.837830 loss: 0.000575 2022/09/14 20:57:48 - mmengine - INFO - Epoch(train) [68][100/586] lr: 5.000000e-04 eta: 10:21:44 time: 0.466540 data_time: 0.029645 memory: 15239 loss_kpt: 0.000578 acc_pose: 0.845205 loss: 0.000578 2022/09/14 20:58:12 - mmengine - INFO - Epoch(train) [68][150/586] lr: 5.000000e-04 eta: 10:21:25 time: 0.473717 data_time: 0.026757 memory: 15239 loss_kpt: 0.000567 acc_pose: 0.806793 loss: 0.000567 2022/09/14 20:58:35 - mmengine - INFO - Epoch(train) [68][200/586] lr: 5.000000e-04 eta: 10:21:05 time: 0.466281 data_time: 0.026807 memory: 15239 loss_kpt: 0.000591 acc_pose: 0.858926 loss: 0.000591 2022/09/14 20:58:59 - mmengine - INFO - Epoch(train) [68][250/586] lr: 5.000000e-04 eta: 10:20:45 time: 0.470565 data_time: 0.030703 memory: 15239 loss_kpt: 0.000552 acc_pose: 0.801753 loss: 0.000552 2022/09/14 20:59:22 - mmengine - INFO - Epoch(train) [68][300/586] lr: 5.000000e-04 eta: 10:20:25 time: 0.462642 data_time: 0.027079 memory: 15239 loss_kpt: 0.000578 acc_pose: 0.787040 loss: 0.000578 2022/09/14 20:59:45 - mmengine - INFO - Epoch(train) [68][350/586] lr: 5.000000e-04 eta: 10:20:05 time: 0.470023 data_time: 0.026590 memory: 15239 loss_kpt: 0.000587 acc_pose: 0.855557 loss: 0.000587 2022/09/14 21:00:09 - mmengine - INFO - Epoch(train) [68][400/586] lr: 5.000000e-04 eta: 10:19:45 time: 0.469905 data_time: 0.026874 memory: 15239 loss_kpt: 0.000590 acc_pose: 0.815512 loss: 0.000590 2022/09/14 21:00:32 - mmengine - INFO - Epoch(train) [68][450/586] lr: 5.000000e-04 eta: 10:19:25 time: 0.462968 data_time: 0.025956 memory: 15239 loss_kpt: 0.000575 acc_pose: 0.881425 loss: 0.000575 2022/09/14 21:00:55 - mmengine - INFO - Epoch(train) [68][500/586] lr: 5.000000e-04 eta: 10:19:05 time: 0.467770 data_time: 0.026140 memory: 15239 loss_kpt: 0.000589 acc_pose: 0.859098 loss: 0.000589 2022/09/14 21:01:19 - mmengine - INFO - Epoch(train) [68][550/586] lr: 5.000000e-04 eta: 10:18:44 time: 0.466630 data_time: 0.031529 memory: 15239 loss_kpt: 0.000584 acc_pose: 0.834964 loss: 0.000584 2022/09/14 21:01:35 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 21:01:35 - mmengine - INFO - Saving checkpoint at 68 epochs 2022/09/14 21:02:06 - mmengine - INFO - Epoch(train) [69][50/586] lr: 5.000000e-04 eta: 10:17:36 time: 0.478697 data_time: 0.031633 memory: 15239 loss_kpt: 0.000587 acc_pose: 0.844559 loss: 0.000587 2022/09/14 21:02:30 - mmengine - INFO - Epoch(train) [69][100/586] lr: 5.000000e-04 eta: 10:17:16 time: 0.470959 data_time: 0.026695 memory: 15239 loss_kpt: 0.000603 acc_pose: 0.785280 loss: 0.000603 2022/09/14 21:02:53 - mmengine - INFO - Epoch(train) [69][150/586] lr: 5.000000e-04 eta: 10:16:56 time: 0.467739 data_time: 0.025463 memory: 15239 loss_kpt: 0.000576 acc_pose: 0.877945 loss: 0.000576 2022/09/14 21:02:54 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 21:03:17 - mmengine - INFO - Epoch(train) [69][200/586] lr: 5.000000e-04 eta: 10:16:38 time: 0.483604 data_time: 0.031559 memory: 15239 loss_kpt: 0.000575 acc_pose: 0.934126 loss: 0.000575 2022/09/14 21:03:41 - mmengine - INFO - Epoch(train) [69][250/586] lr: 5.000000e-04 eta: 10:16:18 time: 0.468249 data_time: 0.027093 memory: 15239 loss_kpt: 0.000586 acc_pose: 0.793685 loss: 0.000586 2022/09/14 21:04:04 - mmengine - INFO - Epoch(train) [69][300/586] lr: 5.000000e-04 eta: 10:15:58 time: 0.465361 data_time: 0.026211 memory: 15239 loss_kpt: 0.000565 acc_pose: 0.805873 loss: 0.000565 2022/09/14 21:04:28 - mmengine - INFO - Epoch(train) [69][350/586] lr: 5.000000e-04 eta: 10:15:39 time: 0.477772 data_time: 0.026163 memory: 15239 loss_kpt: 0.000572 acc_pose: 0.829501 loss: 0.000572 2022/09/14 21:04:52 - mmengine - INFO - Epoch(train) [69][400/586] lr: 5.000000e-04 eta: 10:15:20 time: 0.475787 data_time: 0.026132 memory: 15239 loss_kpt: 0.000591 acc_pose: 0.835586 loss: 0.000591 2022/09/14 21:05:15 - mmengine - INFO - Epoch(train) [69][450/586] lr: 5.000000e-04 eta: 10:14:59 time: 0.460834 data_time: 0.026211 memory: 15239 loss_kpt: 0.000577 acc_pose: 0.866748 loss: 0.000577 2022/09/14 21:05:39 - mmengine - INFO - Epoch(train) [69][500/586] lr: 5.000000e-04 eta: 10:14:40 time: 0.474501 data_time: 0.031085 memory: 15239 loss_kpt: 0.000587 acc_pose: 0.837211 loss: 0.000587 2022/09/14 21:06:02 - mmengine - INFO - Epoch(train) [69][550/586] lr: 5.000000e-04 eta: 10:14:20 time: 0.477375 data_time: 0.027136 memory: 15239 loss_kpt: 0.000567 acc_pose: 0.826688 loss: 0.000567 2022/09/14 21:06:19 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 21:06:19 - mmengine - INFO - Saving checkpoint at 69 epochs 2022/09/14 21:06:50 - mmengine - INFO - Epoch(train) [70][50/586] lr: 5.000000e-04 eta: 10:13:13 time: 0.477857 data_time: 0.029993 memory: 15239 loss_kpt: 0.000574 acc_pose: 0.807541 loss: 0.000574 2022/09/14 21:07:13 - mmengine - INFO - Epoch(train) [70][100/586] lr: 5.000000e-04 eta: 10:12:53 time: 0.467349 data_time: 0.031828 memory: 15239 loss_kpt: 0.000578 acc_pose: 0.789148 loss: 0.000578 2022/09/14 21:07:36 - mmengine - INFO - Epoch(train) [70][150/586] lr: 5.000000e-04 eta: 10:12:33 time: 0.467527 data_time: 0.027064 memory: 15239 loss_kpt: 0.000575 acc_pose: 0.850288 loss: 0.000575 2022/09/14 21:08:00 - mmengine - INFO - Epoch(train) [70][200/586] lr: 5.000000e-04 eta: 10:12:13 time: 0.471183 data_time: 0.027407 memory: 15239 loss_kpt: 0.000598 acc_pose: 0.836978 loss: 0.000598 2022/09/14 21:08:23 - mmengine - INFO - Epoch(train) [70][250/586] lr: 5.000000e-04 eta: 10:11:53 time: 0.469761 data_time: 0.029079 memory: 15239 loss_kpt: 0.000566 acc_pose: 0.902787 loss: 0.000566 2022/09/14 21:08:47 - mmengine - INFO - Epoch(train) [70][300/586] lr: 5.000000e-04 eta: 10:11:34 time: 0.473959 data_time: 0.026364 memory: 15239 loss_kpt: 0.000572 acc_pose: 0.841638 loss: 0.000572 2022/09/14 21:09:10 - mmengine - INFO - Epoch(train) [70][350/586] lr: 5.000000e-04 eta: 10:11:13 time: 0.466417 data_time: 0.026783 memory: 15239 loss_kpt: 0.000568 acc_pose: 0.820710 loss: 0.000568 2022/09/14 21:09:34 - mmengine - INFO - Epoch(train) [70][400/586] lr: 5.000000e-04 eta: 10:10:53 time: 0.465746 data_time: 0.025539 memory: 15239 loss_kpt: 0.000590 acc_pose: 0.821697 loss: 0.000590 2022/09/14 21:09:58 - mmengine - INFO - Epoch(train) [70][450/586] lr: 5.000000e-04 eta: 10:10:34 time: 0.477170 data_time: 0.026819 memory: 15239 loss_kpt: 0.000564 acc_pose: 0.852244 loss: 0.000564 2022/09/14 21:10:21 - mmengine - INFO - Epoch(train) [70][500/586] lr: 5.000000e-04 eta: 10:10:13 time: 0.461502 data_time: 0.026835 memory: 15239 loss_kpt: 0.000584 acc_pose: 0.819185 loss: 0.000584 2022/09/14 21:10:44 - mmengine - INFO - Epoch(train) [70][550/586] lr: 5.000000e-04 eta: 10:09:53 time: 0.465715 data_time: 0.027061 memory: 15239 loss_kpt: 0.000557 acc_pose: 0.860884 loss: 0.000557 2022/09/14 21:10:52 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 21:11:01 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 21:11:01 - mmengine - INFO - Saving checkpoint at 70 epochs 2022/09/14 21:11:18 - mmengine - INFO - Epoch(val) [70][50/407] eta: 0:01:13 time: 0.205716 data_time: 0.014636 memory: 15239 2022/09/14 21:11:28 - mmengine - INFO - Epoch(val) [70][100/407] eta: 0:01:00 time: 0.196822 data_time: 0.010718 memory: 2064 2022/09/14 21:11:38 - mmengine - INFO - Epoch(val) [70][150/407] eta: 0:00:50 time: 0.194860 data_time: 0.008288 memory: 2064 2022/09/14 21:11:47 - mmengine - INFO - Epoch(val) [70][200/407] eta: 0:00:40 time: 0.194173 data_time: 0.008632 memory: 2064 2022/09/14 21:11:57 - mmengine - INFO - Epoch(val) [70][250/407] eta: 0:00:31 time: 0.198311 data_time: 0.011744 memory: 2064 2022/09/14 21:12:07 - mmengine - INFO - Epoch(val) [70][300/407] eta: 0:00:20 time: 0.193636 data_time: 0.008078 memory: 2064 2022/09/14 21:12:17 - mmengine - INFO - Epoch(val) [70][350/407] eta: 0:00:11 time: 0.195156 data_time: 0.008985 memory: 2064 2022/09/14 21:12:27 - mmengine - INFO - Epoch(val) [70][400/407] eta: 0:00:01 time: 0.193753 data_time: 0.008339 memory: 2064 2022/09/14 21:13:04 - mmengine - INFO - Evaluating CocoMetric... 2022/09/14 21:13:18 - mmengine - INFO - Epoch(val) [70][407/407] coco/AP: 0.745204 coco/AP .5: 0.898086 coco/AP .75: 0.811396 coco/AP (M): 0.703247 coco/AP (L): 0.817983 coco/AR: 0.796584 coco/AR .5: 0.935926 coco/AR .75: 0.855164 coco/AR (M): 0.750478 coco/AR (L): 0.862988 2022/09/14 21:13:43 - mmengine - INFO - Epoch(train) [71][50/586] lr: 5.000000e-04 eta: 10:08:47 time: 0.493129 data_time: 0.033046 memory: 15239 loss_kpt: 0.000591 acc_pose: 0.861610 loss: 0.000591 2022/09/14 21:14:06 - mmengine - INFO - Epoch(train) [71][100/586] lr: 5.000000e-04 eta: 10:08:27 time: 0.464917 data_time: 0.026484 memory: 15239 loss_kpt: 0.000580 acc_pose: 0.824762 loss: 0.000580 2022/09/14 21:14:30 - mmengine - INFO - Epoch(train) [71][150/586] lr: 5.000000e-04 eta: 10:08:07 time: 0.469321 data_time: 0.026863 memory: 15239 loss_kpt: 0.000595 acc_pose: 0.871891 loss: 0.000595 2022/09/14 21:14:53 - mmengine - INFO - Epoch(train) [71][200/586] lr: 5.000000e-04 eta: 10:07:47 time: 0.470801 data_time: 0.025639 memory: 15239 loss_kpt: 0.000594 acc_pose: 0.816894 loss: 0.000594 2022/09/14 21:15:17 - mmengine - INFO - Epoch(train) [71][250/586] lr: 5.000000e-04 eta: 10:07:28 time: 0.476708 data_time: 0.026863 memory: 15239 loss_kpt: 0.000586 acc_pose: 0.861251 loss: 0.000586 2022/09/14 21:15:40 - mmengine - INFO - Epoch(train) [71][300/586] lr: 5.000000e-04 eta: 10:07:08 time: 0.463531 data_time: 0.025719 memory: 15239 loss_kpt: 0.000573 acc_pose: 0.841887 loss: 0.000573 2022/09/14 21:16:04 - mmengine - INFO - Epoch(train) [71][350/586] lr: 5.000000e-04 eta: 10:06:48 time: 0.471017 data_time: 0.026274 memory: 15239 loss_kpt: 0.000588 acc_pose: 0.823664 loss: 0.000588 2022/09/14 21:16:27 - mmengine - INFO - Epoch(train) [71][400/586] lr: 5.000000e-04 eta: 10:06:28 time: 0.467307 data_time: 0.030863 memory: 15239 loss_kpt: 0.000573 acc_pose: 0.843342 loss: 0.000573 2022/09/14 21:16:51 - mmengine - INFO - Epoch(train) [71][450/586] lr: 5.000000e-04 eta: 10:06:07 time: 0.463859 data_time: 0.027277 memory: 15239 loss_kpt: 0.000589 acc_pose: 0.906723 loss: 0.000589 2022/09/14 21:17:16 - mmengine - INFO - Epoch(train) [71][500/586] lr: 5.000000e-04 eta: 10:05:51 time: 0.507322 data_time: 0.034018 memory: 15239 loss_kpt: 0.000582 acc_pose: 0.841169 loss: 0.000582 2022/09/14 21:17:39 - mmengine - INFO - Epoch(train) [71][550/586] lr: 5.000000e-04 eta: 10:05:31 time: 0.470471 data_time: 0.031600 memory: 15239 loss_kpt: 0.000568 acc_pose: 0.832109 loss: 0.000568 2022/09/14 21:17:56 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 21:17:56 - mmengine - INFO - Saving checkpoint at 71 epochs 2022/09/14 21:18:27 - mmengine - INFO - Epoch(train) [72][50/586] lr: 5.000000e-04 eta: 10:04:24 time: 0.472146 data_time: 0.031806 memory: 15239 loss_kpt: 0.000569 acc_pose: 0.803216 loss: 0.000569 2022/09/14 21:18:51 - mmengine - INFO - Epoch(train) [72][100/586] lr: 5.000000e-04 eta: 10:04:03 time: 0.464124 data_time: 0.027395 memory: 15239 loss_kpt: 0.000588 acc_pose: 0.853854 loss: 0.000588 2022/09/14 21:19:14 - mmengine - INFO - Epoch(train) [72][150/586] lr: 5.000000e-04 eta: 10:03:44 time: 0.471311 data_time: 0.027650 memory: 15239 loss_kpt: 0.000585 acc_pose: 0.800695 loss: 0.000585 2022/09/14 21:19:38 - mmengine - INFO - Epoch(train) [72][200/586] lr: 5.000000e-04 eta: 10:03:24 time: 0.471308 data_time: 0.031997 memory: 15239 loss_kpt: 0.000573 acc_pose: 0.866124 loss: 0.000573 2022/09/14 21:20:01 - mmengine - INFO - Epoch(train) [72][250/586] lr: 5.000000e-04 eta: 10:03:04 time: 0.472611 data_time: 0.027187 memory: 15239 loss_kpt: 0.000577 acc_pose: 0.867800 loss: 0.000577 2022/09/14 21:20:25 - mmengine - INFO - Epoch(train) [72][300/586] lr: 5.000000e-04 eta: 10:02:44 time: 0.468178 data_time: 0.025825 memory: 15239 loss_kpt: 0.000584 acc_pose: 0.870594 loss: 0.000584 2022/09/14 21:20:49 - mmengine - INFO - Epoch(train) [72][350/586] lr: 5.000000e-04 eta: 10:02:25 time: 0.475558 data_time: 0.029630 memory: 15239 loss_kpt: 0.000580 acc_pose: 0.849588 loss: 0.000580 2022/09/14 21:21:09 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 21:21:12 - mmengine - INFO - Epoch(train) [72][400/586] lr: 5.000000e-04 eta: 10:02:04 time: 0.464756 data_time: 0.026468 memory: 15239 loss_kpt: 0.000565 acc_pose: 0.783552 loss: 0.000565 2022/09/14 21:21:35 - mmengine - INFO - Epoch(train) [72][450/586] lr: 5.000000e-04 eta: 10:01:44 time: 0.461460 data_time: 0.026682 memory: 15239 loss_kpt: 0.000577 acc_pose: 0.850340 loss: 0.000577 2022/09/14 21:21:58 - mmengine - INFO - Epoch(train) [72][500/586] lr: 5.000000e-04 eta: 10:01:24 time: 0.470144 data_time: 0.026373 memory: 15239 loss_kpt: 0.000583 acc_pose: 0.804602 loss: 0.000583 2022/09/14 21:22:22 - mmengine - INFO - Epoch(train) [72][550/586] lr: 5.000000e-04 eta: 10:01:03 time: 0.466258 data_time: 0.026647 memory: 15239 loss_kpt: 0.000580 acc_pose: 0.862721 loss: 0.000580 2022/09/14 21:22:38 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 21:22:38 - mmengine - INFO - Saving checkpoint at 72 epochs 2022/09/14 21:23:09 - mmengine - INFO - Epoch(train) [73][50/586] lr: 5.000000e-04 eta: 9:59:57 time: 0.477154 data_time: 0.030720 memory: 15239 loss_kpt: 0.000596 acc_pose: 0.845759 loss: 0.000596 2022/09/14 21:23:33 - mmengine - INFO - Epoch(train) [73][100/586] lr: 5.000000e-04 eta: 9:59:38 time: 0.475868 data_time: 0.026586 memory: 15239 loss_kpt: 0.000564 acc_pose: 0.875199 loss: 0.000564 2022/09/14 21:23:56 - mmengine - INFO - Epoch(train) [73][150/586] lr: 5.000000e-04 eta: 9:59:18 time: 0.466869 data_time: 0.025738 memory: 15239 loss_kpt: 0.000566 acc_pose: 0.896449 loss: 0.000566 2022/09/14 21:24:20 - mmengine - INFO - Epoch(train) [73][200/586] lr: 5.000000e-04 eta: 9:58:58 time: 0.473976 data_time: 0.027227 memory: 15239 loss_kpt: 0.000578 acc_pose: 0.834340 loss: 0.000578 2022/09/14 21:24:44 - mmengine - INFO - Epoch(train) [73][250/586] lr: 5.000000e-04 eta: 9:58:38 time: 0.470247 data_time: 0.026323 memory: 15239 loss_kpt: 0.000561 acc_pose: 0.854072 loss: 0.000561 2022/09/14 21:25:07 - mmengine - INFO - Epoch(train) [73][300/586] lr: 5.000000e-04 eta: 9:58:17 time: 0.460476 data_time: 0.026030 memory: 15239 loss_kpt: 0.000572 acc_pose: 0.773350 loss: 0.000572 2022/09/14 21:25:30 - mmengine - INFO - Epoch(train) [73][350/586] lr: 5.000000e-04 eta: 9:57:57 time: 0.470545 data_time: 0.025682 memory: 15239 loss_kpt: 0.000572 acc_pose: 0.814808 loss: 0.000572 2022/09/14 21:25:53 - mmengine - INFO - Epoch(train) [73][400/586] lr: 5.000000e-04 eta: 9:57:37 time: 0.465217 data_time: 0.026787 memory: 15239 loss_kpt: 0.000589 acc_pose: 0.804813 loss: 0.000589 2022/09/14 21:26:17 - mmengine - INFO - Epoch(train) [73][450/586] lr: 5.000000e-04 eta: 9:57:17 time: 0.465977 data_time: 0.026962 memory: 15239 loss_kpt: 0.000563 acc_pose: 0.816414 loss: 0.000563 2022/09/14 21:26:40 - mmengine - INFO - Epoch(train) [73][500/586] lr: 5.000000e-04 eta: 9:56:56 time: 0.468016 data_time: 0.027570 memory: 15239 loss_kpt: 0.000582 acc_pose: 0.865082 loss: 0.000582 2022/09/14 21:27:03 - mmengine - INFO - Epoch(train) [73][550/586] lr: 5.000000e-04 eta: 9:56:36 time: 0.466518 data_time: 0.026495 memory: 15239 loss_kpt: 0.000588 acc_pose: 0.874783 loss: 0.000588 2022/09/14 21:27:20 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 21:27:20 - mmengine - INFO - Saving checkpoint at 73 epochs 2022/09/14 21:27:51 - mmengine - INFO - Epoch(train) [74][50/586] lr: 5.000000e-04 eta: 9:55:30 time: 0.472751 data_time: 0.031072 memory: 15239 loss_kpt: 0.000573 acc_pose: 0.778611 loss: 0.000573 2022/09/14 21:28:15 - mmengine - INFO - Epoch(train) [74][100/586] lr: 5.000000e-04 eta: 9:55:10 time: 0.469394 data_time: 0.026216 memory: 15239 loss_kpt: 0.000573 acc_pose: 0.857778 loss: 0.000573 2022/09/14 21:28:38 - mmengine - INFO - Epoch(train) [74][150/586] lr: 5.000000e-04 eta: 9:54:50 time: 0.465340 data_time: 0.029806 memory: 15239 loss_kpt: 0.000567 acc_pose: 0.905974 loss: 0.000567 2022/09/14 21:29:02 - mmengine - INFO - Epoch(train) [74][200/586] lr: 5.000000e-04 eta: 9:54:30 time: 0.473727 data_time: 0.026856 memory: 15239 loss_kpt: 0.000585 acc_pose: 0.844318 loss: 0.000585 2022/09/14 21:29:12 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 21:29:25 - mmengine - INFO - Epoch(train) [74][250/586] lr: 5.000000e-04 eta: 9:54:10 time: 0.467739 data_time: 0.026997 memory: 15239 loss_kpt: 0.000589 acc_pose: 0.852844 loss: 0.000589 2022/09/14 21:29:49 - mmengine - INFO - Epoch(train) [74][300/586] lr: 5.000000e-04 eta: 9:53:50 time: 0.468521 data_time: 0.030165 memory: 15239 loss_kpt: 0.000581 acc_pose: 0.797565 loss: 0.000581 2022/09/14 21:30:12 - mmengine - INFO - Epoch(train) [74][350/586] lr: 5.000000e-04 eta: 9:53:30 time: 0.474172 data_time: 0.027079 memory: 15239 loss_kpt: 0.000586 acc_pose: 0.818296 loss: 0.000586 2022/09/14 21:30:36 - mmengine - INFO - Epoch(train) [74][400/586] lr: 5.000000e-04 eta: 9:53:10 time: 0.462948 data_time: 0.026400 memory: 15239 loss_kpt: 0.000583 acc_pose: 0.807401 loss: 0.000583 2022/09/14 21:30:59 - mmengine - INFO - Epoch(train) [74][450/586] lr: 5.000000e-04 eta: 9:52:49 time: 0.464551 data_time: 0.027876 memory: 15239 loss_kpt: 0.000569 acc_pose: 0.818726 loss: 0.000569 2022/09/14 21:31:23 - mmengine - INFO - Epoch(train) [74][500/586] lr: 5.000000e-04 eta: 9:52:29 time: 0.475195 data_time: 0.026770 memory: 15239 loss_kpt: 0.000585 acc_pose: 0.871621 loss: 0.000585 2022/09/14 21:31:46 - mmengine - INFO - Epoch(train) [74][550/586] lr: 5.000000e-04 eta: 9:52:09 time: 0.464353 data_time: 0.027633 memory: 15239 loss_kpt: 0.000585 acc_pose: 0.888092 loss: 0.000585 2022/09/14 21:32:02 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 21:32:02 - mmengine - INFO - Saving checkpoint at 74 epochs 2022/09/14 21:32:34 - mmengine - INFO - Epoch(train) [75][50/586] lr: 5.000000e-04 eta: 9:51:05 time: 0.487137 data_time: 0.035370 memory: 15239 loss_kpt: 0.000568 acc_pose: 0.735343 loss: 0.000568 2022/09/14 21:32:57 - mmengine - INFO - Epoch(train) [75][100/586] lr: 5.000000e-04 eta: 9:50:45 time: 0.470966 data_time: 0.026601 memory: 15239 loss_kpt: 0.000563 acc_pose: 0.810523 loss: 0.000563 2022/09/14 21:33:21 - mmengine - INFO - Epoch(train) [75][150/586] lr: 5.000000e-04 eta: 9:50:25 time: 0.471582 data_time: 0.027343 memory: 15239 loss_kpt: 0.000573 acc_pose: 0.835972 loss: 0.000573 2022/09/14 21:33:44 - mmengine - INFO - Epoch(train) [75][200/586] lr: 5.000000e-04 eta: 9:50:05 time: 0.463950 data_time: 0.026953 memory: 15239 loss_kpt: 0.000583 acc_pose: 0.805462 loss: 0.000583 2022/09/14 21:34:08 - mmengine - INFO - Epoch(train) [75][250/586] lr: 5.000000e-04 eta: 9:49:45 time: 0.469286 data_time: 0.025836 memory: 15239 loss_kpt: 0.000565 acc_pose: 0.868167 loss: 0.000565 2022/09/14 21:34:31 - mmengine - INFO - Epoch(train) [75][300/586] lr: 5.000000e-04 eta: 9:49:24 time: 0.465835 data_time: 0.026465 memory: 15239 loss_kpt: 0.000575 acc_pose: 0.785552 loss: 0.000575 2022/09/14 21:34:54 - mmengine - INFO - Epoch(train) [75][350/586] lr: 5.000000e-04 eta: 9:49:04 time: 0.467649 data_time: 0.026391 memory: 15239 loss_kpt: 0.000566 acc_pose: 0.911501 loss: 0.000566 2022/09/14 21:35:18 - mmengine - INFO - Epoch(train) [75][400/586] lr: 5.000000e-04 eta: 9:48:44 time: 0.470204 data_time: 0.032266 memory: 15239 loss_kpt: 0.000587 acc_pose: 0.870025 loss: 0.000587 2022/09/14 21:35:41 - mmengine - INFO - Epoch(train) [75][450/586] lr: 5.000000e-04 eta: 9:48:23 time: 0.463407 data_time: 0.027291 memory: 15239 loss_kpt: 0.000570 acc_pose: 0.875298 loss: 0.000570 2022/09/14 21:36:05 - mmengine - INFO - Epoch(train) [75][500/586] lr: 5.000000e-04 eta: 9:48:04 time: 0.480459 data_time: 0.026628 memory: 15239 loss_kpt: 0.000596 acc_pose: 0.851474 loss: 0.000596 2022/09/14 21:36:28 - mmengine - INFO - Epoch(train) [75][550/586] lr: 5.000000e-04 eta: 9:47:43 time: 0.463761 data_time: 0.026703 memory: 15239 loss_kpt: 0.000567 acc_pose: 0.794012 loss: 0.000567 2022/09/14 21:36:45 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 21:36:45 - mmengine - INFO - Saving checkpoint at 75 epochs 2022/09/14 21:37:16 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 21:37:16 - mmengine - INFO - Epoch(train) [76][50/586] lr: 5.000000e-04 eta: 9:46:40 time: 0.481284 data_time: 0.031965 memory: 15239 loss_kpt: 0.000576 acc_pose: 0.851297 loss: 0.000576 2022/09/14 21:37:39 - mmengine - INFO - Epoch(train) [76][100/586] lr: 5.000000e-04 eta: 9:46:19 time: 0.462704 data_time: 0.027167 memory: 15239 loss_kpt: 0.000569 acc_pose: 0.888034 loss: 0.000569 2022/09/14 21:38:02 - mmengine - INFO - Epoch(train) [76][150/586] lr: 5.000000e-04 eta: 9:45:58 time: 0.465870 data_time: 0.027028 memory: 15239 loss_kpt: 0.000575 acc_pose: 0.827904 loss: 0.000575 2022/09/14 21:38:26 - mmengine - INFO - Epoch(train) [76][200/586] lr: 5.000000e-04 eta: 9:45:38 time: 0.470635 data_time: 0.030211 memory: 15239 loss_kpt: 0.000580 acc_pose: 0.834636 loss: 0.000580 2022/09/14 21:38:49 - mmengine - INFO - Epoch(train) [76][250/586] lr: 5.000000e-04 eta: 9:45:18 time: 0.466084 data_time: 0.028108 memory: 15239 loss_kpt: 0.000581 acc_pose: 0.792983 loss: 0.000581 2022/09/14 21:39:13 - mmengine - INFO - Epoch(train) [76][300/586] lr: 5.000000e-04 eta: 9:44:58 time: 0.466010 data_time: 0.027062 memory: 15239 loss_kpt: 0.000583 acc_pose: 0.802524 loss: 0.000583 2022/09/14 21:39:36 - mmengine - INFO - Epoch(train) [76][350/586] lr: 5.000000e-04 eta: 9:44:38 time: 0.471686 data_time: 0.026135 memory: 15239 loss_kpt: 0.000580 acc_pose: 0.830501 loss: 0.000580 2022/09/14 21:39:59 - mmengine - INFO - Epoch(train) [76][400/586] lr: 5.000000e-04 eta: 9:44:17 time: 0.464999 data_time: 0.026438 memory: 15239 loss_kpt: 0.000581 acc_pose: 0.837246 loss: 0.000581 2022/09/14 21:40:22 - mmengine - INFO - Epoch(train) [76][450/586] lr: 5.000000e-04 eta: 9:43:56 time: 0.457138 data_time: 0.026017 memory: 15239 loss_kpt: 0.000589 acc_pose: 0.849191 loss: 0.000589 2022/09/14 21:40:46 - mmengine - INFO - Epoch(train) [76][500/586] lr: 5.000000e-04 eta: 9:43:37 time: 0.478555 data_time: 0.031301 memory: 15239 loss_kpt: 0.000563 acc_pose: 0.811712 loss: 0.000563 2022/09/14 21:41:09 - mmengine - INFO - Epoch(train) [76][550/586] lr: 5.000000e-04 eta: 9:43:15 time: 0.458113 data_time: 0.027242 memory: 15239 loss_kpt: 0.000568 acc_pose: 0.834406 loss: 0.000568 2022/09/14 21:41:26 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 21:41:26 - mmengine - INFO - Saving checkpoint at 76 epochs 2022/09/14 21:41:57 - mmengine - INFO - Epoch(train) [77][50/586] lr: 5.000000e-04 eta: 9:42:12 time: 0.483841 data_time: 0.035349 memory: 15239 loss_kpt: 0.000581 acc_pose: 0.825130 loss: 0.000581 2022/09/14 21:42:20 - mmengine - INFO - Epoch(train) [77][100/586] lr: 5.000000e-04 eta: 9:41:52 time: 0.466810 data_time: 0.027217 memory: 15239 loss_kpt: 0.000578 acc_pose: 0.873913 loss: 0.000578 2022/09/14 21:42:44 - mmengine - INFO - Epoch(train) [77][150/586] lr: 5.000000e-04 eta: 9:41:32 time: 0.467355 data_time: 0.027384 memory: 15239 loss_kpt: 0.000571 acc_pose: 0.892095 loss: 0.000571 2022/09/14 21:43:07 - mmengine - INFO - Epoch(train) [77][200/586] lr: 5.000000e-04 eta: 9:41:12 time: 0.473015 data_time: 0.026066 memory: 15239 loss_kpt: 0.000580 acc_pose: 0.834574 loss: 0.000580 2022/09/14 21:43:30 - mmengine - INFO - Epoch(train) [77][250/586] lr: 5.000000e-04 eta: 9:40:51 time: 0.464213 data_time: 0.026900 memory: 15239 loss_kpt: 0.000569 acc_pose: 0.867194 loss: 0.000569 2022/09/14 21:43:54 - mmengine - INFO - Epoch(train) [77][300/586] lr: 5.000000e-04 eta: 9:40:31 time: 0.470132 data_time: 0.031738 memory: 15239 loss_kpt: 0.000576 acc_pose: 0.867192 loss: 0.000576 2022/09/14 21:44:18 - mmengine - INFO - Epoch(train) [77][350/586] lr: 5.000000e-04 eta: 9:40:11 time: 0.471378 data_time: 0.026868 memory: 15239 loss_kpt: 0.000567 acc_pose: 0.830259 loss: 0.000567 2022/09/14 21:44:41 - mmengine - INFO - Epoch(train) [77][400/586] lr: 5.000000e-04 eta: 9:39:51 time: 0.464906 data_time: 0.026266 memory: 15239 loss_kpt: 0.000575 acc_pose: 0.824849 loss: 0.000575 2022/09/14 21:45:04 - mmengine - INFO - Epoch(train) [77][450/586] lr: 5.000000e-04 eta: 9:39:30 time: 0.468139 data_time: 0.026217 memory: 15239 loss_kpt: 0.000578 acc_pose: 0.850722 loss: 0.000578 2022/09/14 21:45:11 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 21:45:28 - mmengine - INFO - Epoch(train) [77][500/586] lr: 5.000000e-04 eta: 9:39:10 time: 0.468762 data_time: 0.025426 memory: 15239 loss_kpt: 0.000566 acc_pose: 0.872220 loss: 0.000566 2022/09/14 21:45:51 - mmengine - INFO - Epoch(train) [77][550/586] lr: 5.000000e-04 eta: 9:38:50 time: 0.467255 data_time: 0.025593 memory: 15239 loss_kpt: 0.000581 acc_pose: 0.843594 loss: 0.000581 2022/09/14 21:46:08 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 21:46:08 - mmengine - INFO - Saving checkpoint at 77 epochs 2022/09/14 21:46:38 - mmengine - INFO - Epoch(train) [78][50/586] lr: 5.000000e-04 eta: 9:37:46 time: 0.473657 data_time: 0.030996 memory: 15239 loss_kpt: 0.000571 acc_pose: 0.846248 loss: 0.000571 2022/09/14 21:47:02 - mmengine - INFO - Epoch(train) [78][100/586] lr: 5.000000e-04 eta: 9:37:27 time: 0.482630 data_time: 0.027801 memory: 15239 loss_kpt: 0.000574 acc_pose: 0.852944 loss: 0.000574 2022/09/14 21:47:25 - mmengine - INFO - Epoch(train) [78][150/586] lr: 5.000000e-04 eta: 9:37:07 time: 0.465543 data_time: 0.025219 memory: 15239 loss_kpt: 0.000567 acc_pose: 0.853886 loss: 0.000567 2022/09/14 21:47:49 - mmengine - INFO - Epoch(train) [78][200/586] lr: 5.000000e-04 eta: 9:36:46 time: 0.463865 data_time: 0.026456 memory: 15239 loss_kpt: 0.000559 acc_pose: 0.862715 loss: 0.000559 2022/09/14 21:48:12 - mmengine - INFO - Epoch(train) [78][250/586] lr: 5.000000e-04 eta: 9:36:26 time: 0.473089 data_time: 0.026211 memory: 15239 loss_kpt: 0.000540 acc_pose: 0.860615 loss: 0.000540 2022/09/14 21:48:36 - mmengine - INFO - Epoch(train) [78][300/586] lr: 5.000000e-04 eta: 9:36:06 time: 0.473033 data_time: 0.026813 memory: 15239 loss_kpt: 0.000567 acc_pose: 0.880928 loss: 0.000567 2022/09/14 21:48:59 - mmengine - INFO - Epoch(train) [78][350/586] lr: 5.000000e-04 eta: 9:35:45 time: 0.462885 data_time: 0.025382 memory: 15239 loss_kpt: 0.000588 acc_pose: 0.875891 loss: 0.000588 2022/09/14 21:49:22 - mmengine - INFO - Epoch(train) [78][400/586] lr: 5.000000e-04 eta: 9:35:25 time: 0.467079 data_time: 0.031748 memory: 15239 loss_kpt: 0.000574 acc_pose: 0.877679 loss: 0.000574 2022/09/14 21:49:46 - mmengine - INFO - Epoch(train) [78][450/586] lr: 5.000000e-04 eta: 9:35:05 time: 0.472048 data_time: 0.026858 memory: 15239 loss_kpt: 0.000585 acc_pose: 0.808610 loss: 0.000585 2022/09/14 21:50:09 - mmengine - INFO - Epoch(train) [78][500/586] lr: 5.000000e-04 eta: 9:34:45 time: 0.467517 data_time: 0.028226 memory: 15239 loss_kpt: 0.000563 acc_pose: 0.795063 loss: 0.000563 2022/09/14 21:50:33 - mmengine - INFO - Epoch(train) [78][550/586] lr: 5.000000e-04 eta: 9:34:25 time: 0.470643 data_time: 0.026713 memory: 15239 loss_kpt: 0.000571 acc_pose: 0.869021 loss: 0.000571 2022/09/14 21:50:50 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 21:50:50 - mmengine - INFO - Saving checkpoint at 78 epochs 2022/09/14 21:51:21 - mmengine - INFO - Epoch(train) [79][50/586] lr: 5.000000e-04 eta: 9:33:23 time: 0.485461 data_time: 0.030962 memory: 15239 loss_kpt: 0.000572 acc_pose: 0.873939 loss: 0.000572 2022/09/14 21:51:44 - mmengine - INFO - Epoch(train) [79][100/586] lr: 5.000000e-04 eta: 9:33:02 time: 0.469493 data_time: 0.025788 memory: 15239 loss_kpt: 0.000562 acc_pose: 0.845496 loss: 0.000562 2022/09/14 21:52:08 - mmengine - INFO - Epoch(train) [79][150/586] lr: 5.000000e-04 eta: 9:32:42 time: 0.473730 data_time: 0.027745 memory: 15239 loss_kpt: 0.000579 acc_pose: 0.878851 loss: 0.000579 2022/09/14 21:52:31 - mmengine - INFO - Epoch(train) [79][200/586] lr: 5.000000e-04 eta: 9:32:22 time: 0.469834 data_time: 0.031093 memory: 15239 loss_kpt: 0.000576 acc_pose: 0.836518 loss: 0.000576 2022/09/14 21:52:55 - mmengine - INFO - Epoch(train) [79][250/586] lr: 5.000000e-04 eta: 9:32:02 time: 0.468278 data_time: 0.026175 memory: 15239 loss_kpt: 0.000576 acc_pose: 0.810565 loss: 0.000576 2022/09/14 21:53:14 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 21:53:18 - mmengine - INFO - Epoch(train) [79][300/586] lr: 5.000000e-04 eta: 9:31:42 time: 0.466697 data_time: 0.026093 memory: 15239 loss_kpt: 0.000569 acc_pose: 0.823452 loss: 0.000569 2022/09/14 21:53:43 - mmengine - INFO - Epoch(train) [79][350/586] lr: 5.000000e-04 eta: 9:31:23 time: 0.485946 data_time: 0.027502 memory: 15239 loss_kpt: 0.000567 acc_pose: 0.907736 loss: 0.000567 2022/09/14 21:54:06 - mmengine - INFO - Epoch(train) [79][400/586] lr: 5.000000e-04 eta: 9:31:02 time: 0.462552 data_time: 0.027259 memory: 15239 loss_kpt: 0.000576 acc_pose: 0.865285 loss: 0.000576 2022/09/14 21:54:29 - mmengine - INFO - Epoch(train) [79][450/586] lr: 5.000000e-04 eta: 9:30:41 time: 0.467920 data_time: 0.026721 memory: 15239 loss_kpt: 0.000583 acc_pose: 0.794481 loss: 0.000583 2022/09/14 21:54:53 - mmengine - INFO - Epoch(train) [79][500/586] lr: 5.000000e-04 eta: 9:30:21 time: 0.471920 data_time: 0.029017 memory: 15239 loss_kpt: 0.000558 acc_pose: 0.736885 loss: 0.000558 2022/09/14 21:55:16 - mmengine - INFO - Epoch(train) [79][550/586] lr: 5.000000e-04 eta: 9:30:01 time: 0.469870 data_time: 0.026686 memory: 15239 loss_kpt: 0.000554 acc_pose: 0.770280 loss: 0.000554 2022/09/14 21:55:33 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 21:55:33 - mmengine - INFO - Saving checkpoint at 79 epochs 2022/09/14 21:56:04 - mmengine - INFO - Epoch(train) [80][50/586] lr: 5.000000e-04 eta: 9:28:59 time: 0.481852 data_time: 0.037857 memory: 15239 loss_kpt: 0.000566 acc_pose: 0.788832 loss: 0.000566 2022/09/14 21:56:28 - mmengine - INFO - Epoch(train) [80][100/586] lr: 5.000000e-04 eta: 9:28:39 time: 0.466518 data_time: 0.027037 memory: 15239 loss_kpt: 0.000571 acc_pose: 0.807313 loss: 0.000571 2022/09/14 21:56:51 - mmengine - INFO - Epoch(train) [80][150/586] lr: 5.000000e-04 eta: 9:28:19 time: 0.473038 data_time: 0.026224 memory: 15239 loss_kpt: 0.000567 acc_pose: 0.874771 loss: 0.000567 2022/09/14 21:57:14 - mmengine - INFO - Epoch(train) [80][200/586] lr: 5.000000e-04 eta: 9:27:58 time: 0.461380 data_time: 0.027658 memory: 15239 loss_kpt: 0.000562 acc_pose: 0.887619 loss: 0.000562 2022/09/14 21:57:38 - mmengine - INFO - Epoch(train) [80][250/586] lr: 5.000000e-04 eta: 9:27:38 time: 0.474244 data_time: 0.027704 memory: 15239 loss_kpt: 0.000555 acc_pose: 0.790251 loss: 0.000555 2022/09/14 21:58:02 - mmengine - INFO - Epoch(train) [80][300/586] lr: 5.000000e-04 eta: 9:27:19 time: 0.477014 data_time: 0.026305 memory: 15239 loss_kpt: 0.000557 acc_pose: 0.812640 loss: 0.000557 2022/09/14 21:58:25 - mmengine - INFO - Epoch(train) [80][350/586] lr: 5.000000e-04 eta: 9:26:58 time: 0.470114 data_time: 0.026267 memory: 15239 loss_kpt: 0.000577 acc_pose: 0.825507 loss: 0.000577 2022/09/14 21:58:49 - mmengine - INFO - Epoch(train) [80][400/586] lr: 5.000000e-04 eta: 9:26:38 time: 0.469426 data_time: 0.025440 memory: 15239 loss_kpt: 0.000576 acc_pose: 0.771022 loss: 0.000576 2022/09/14 21:59:13 - mmengine - INFO - Epoch(train) [80][450/586] lr: 5.000000e-04 eta: 9:26:18 time: 0.475734 data_time: 0.029570 memory: 15239 loss_kpt: 0.000574 acc_pose: 0.802477 loss: 0.000574 2022/09/14 21:59:36 - mmengine - INFO - Epoch(train) [80][500/586] lr: 5.000000e-04 eta: 9:25:58 time: 0.466128 data_time: 0.025641 memory: 15239 loss_kpt: 0.000559 acc_pose: 0.787627 loss: 0.000559 2022/09/14 21:59:59 - mmengine - INFO - Epoch(train) [80][550/586] lr: 5.000000e-04 eta: 9:25:37 time: 0.464000 data_time: 0.028047 memory: 15239 loss_kpt: 0.000590 acc_pose: 0.849963 loss: 0.000590 2022/09/14 22:00:16 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 22:00:16 - mmengine - INFO - Saving checkpoint at 80 epochs 2022/09/14 22:00:33 - mmengine - INFO - Epoch(val) [80][50/407] eta: 0:01:11 time: 0.200105 data_time: 0.013397 memory: 15239 2022/09/14 22:00:43 - mmengine - INFO - Epoch(val) [80][100/407] eta: 0:00:59 time: 0.194821 data_time: 0.008415 memory: 2064 2022/09/14 22:00:53 - mmengine - INFO - Epoch(val) [80][150/407] eta: 0:00:49 time: 0.193880 data_time: 0.008433 memory: 2064 2022/09/14 22:01:02 - mmengine - INFO - Epoch(val) [80][200/407] eta: 0:00:40 time: 0.196445 data_time: 0.009561 memory: 2064 2022/09/14 22:01:12 - mmengine - INFO - Epoch(val) [80][250/407] eta: 0:00:30 time: 0.196789 data_time: 0.008216 memory: 2064 2022/09/14 22:01:22 - mmengine - INFO - Epoch(val) [80][300/407] eta: 0:00:20 time: 0.193464 data_time: 0.007953 memory: 2064 2022/09/14 22:01:32 - mmengine - INFO - Epoch(val) [80][350/407] eta: 0:00:11 time: 0.194192 data_time: 0.008494 memory: 2064 2022/09/14 22:01:41 - mmengine - INFO - Epoch(val) [80][400/407] eta: 0:00:01 time: 0.192651 data_time: 0.008209 memory: 2064 2022/09/14 22:02:19 - mmengine - INFO - Evaluating CocoMetric... 2022/09/14 22:02:34 - mmengine - INFO - Epoch(val) [80][407/407] coco/AP: 0.749342 coco/AP .5: 0.902631 coco/AP .75: 0.818850 coco/AP (M): 0.708585 coco/AP (L): 0.818349 coco/AR: 0.798457 coco/AR .5: 0.937500 coco/AR .75: 0.860359 coco/AR (M): 0.753892 coco/AR (L): 0.862282 2022/09/14 22:02:34 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220914/hrnet_w48_384/best_coco/AP_epoch_60.pth is removed 2022/09/14 22:02:38 - mmengine - INFO - The best checkpoint with 0.7493 coco/AP at 80 epoch is saved to best_coco/AP_epoch_80.pth. 2022/09/14 22:03:02 - mmengine - INFO - Epoch(train) [81][50/586] lr: 5.000000e-04 eta: 9:24:36 time: 0.485020 data_time: 0.039059 memory: 15239 loss_kpt: 0.000575 acc_pose: 0.838607 loss: 0.000575 2022/09/14 22:03:26 - mmengine - INFO - Epoch(train) [81][100/586] lr: 5.000000e-04 eta: 9:24:16 time: 0.475519 data_time: 0.033346 memory: 15239 loss_kpt: 0.000585 acc_pose: 0.848910 loss: 0.000585 2022/09/14 22:03:35 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 22:03:49 - mmengine - INFO - Epoch(train) [81][150/586] lr: 5.000000e-04 eta: 9:23:56 time: 0.472703 data_time: 0.029817 memory: 15239 loss_kpt: 0.000559 acc_pose: 0.860762 loss: 0.000559 2022/09/14 22:04:13 - mmengine - INFO - Epoch(train) [81][200/586] lr: 5.000000e-04 eta: 9:23:37 time: 0.479435 data_time: 0.030898 memory: 15239 loss_kpt: 0.000575 acc_pose: 0.854632 loss: 0.000575 2022/09/14 22:04:37 - mmengine - INFO - Epoch(train) [81][250/586] lr: 5.000000e-04 eta: 9:23:16 time: 0.466355 data_time: 0.031503 memory: 15239 loss_kpt: 0.000564 acc_pose: 0.764264 loss: 0.000564 2022/09/14 22:05:00 - mmengine - INFO - Epoch(train) [81][300/586] lr: 5.000000e-04 eta: 9:22:56 time: 0.469468 data_time: 0.029204 memory: 15239 loss_kpt: 0.000590 acc_pose: 0.867491 loss: 0.000590 2022/09/14 22:05:24 - mmengine - INFO - Epoch(train) [81][350/586] lr: 5.000000e-04 eta: 9:22:36 time: 0.478090 data_time: 0.025537 memory: 15239 loss_kpt: 0.000569 acc_pose: 0.830476 loss: 0.000569 2022/09/14 22:05:47 - mmengine - INFO - Epoch(train) [81][400/586] lr: 5.000000e-04 eta: 9:22:15 time: 0.460923 data_time: 0.025659 memory: 15239 loss_kpt: 0.000554 acc_pose: 0.872445 loss: 0.000554 2022/09/14 22:06:11 - mmengine - INFO - Epoch(train) [81][450/586] lr: 5.000000e-04 eta: 9:21:55 time: 0.472280 data_time: 0.027062 memory: 15239 loss_kpt: 0.000553 acc_pose: 0.894020 loss: 0.000553 2022/09/14 22:06:34 - mmengine - INFO - Epoch(train) [81][500/586] lr: 5.000000e-04 eta: 9:21:34 time: 0.463636 data_time: 0.027271 memory: 15239 loss_kpt: 0.000554 acc_pose: 0.866680 loss: 0.000554 2022/09/14 22:06:57 - mmengine - INFO - Epoch(train) [81][550/586] lr: 5.000000e-04 eta: 9:21:14 time: 0.466751 data_time: 0.025985 memory: 15239 loss_kpt: 0.000572 acc_pose: 0.832877 loss: 0.000572 2022/09/14 22:07:14 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 22:07:14 - mmengine - INFO - Saving checkpoint at 81 epochs 2022/09/14 22:07:46 - mmengine - INFO - Epoch(train) [82][50/586] lr: 5.000000e-04 eta: 9:20:14 time: 0.491914 data_time: 0.039085 memory: 15239 loss_kpt: 0.000561 acc_pose: 0.851458 loss: 0.000561 2022/09/14 22:08:09 - mmengine - INFO - Epoch(train) [82][100/586] lr: 5.000000e-04 eta: 9:19:54 time: 0.474414 data_time: 0.027694 memory: 15239 loss_kpt: 0.000564 acc_pose: 0.787143 loss: 0.000564 2022/09/14 22:08:33 - mmengine - INFO - Epoch(train) [82][150/586] lr: 5.000000e-04 eta: 9:19:34 time: 0.474454 data_time: 0.026366 memory: 15239 loss_kpt: 0.000568 acc_pose: 0.776175 loss: 0.000568 2022/09/14 22:08:57 - mmengine - INFO - Epoch(train) [82][200/586] lr: 5.000000e-04 eta: 9:19:15 time: 0.480932 data_time: 0.025964 memory: 15239 loss_kpt: 0.000574 acc_pose: 0.860311 loss: 0.000574 2022/09/14 22:09:21 - mmengine - INFO - Epoch(train) [82][250/586] lr: 5.000000e-04 eta: 9:18:54 time: 0.472405 data_time: 0.026250 memory: 15239 loss_kpt: 0.000568 acc_pose: 0.848670 loss: 0.000568 2022/09/14 22:09:44 - mmengine - INFO - Epoch(train) [82][300/586] lr: 5.000000e-04 eta: 9:18:34 time: 0.465443 data_time: 0.027539 memory: 15239 loss_kpt: 0.000559 acc_pose: 0.835893 loss: 0.000559 2022/09/14 22:10:07 - mmengine - INFO - Epoch(train) [82][350/586] lr: 5.000000e-04 eta: 9:18:13 time: 0.465939 data_time: 0.030043 memory: 15239 loss_kpt: 0.000579 acc_pose: 0.804740 loss: 0.000579 2022/09/14 22:10:31 - mmengine - INFO - Epoch(train) [82][400/586] lr: 5.000000e-04 eta: 9:17:53 time: 0.467102 data_time: 0.026287 memory: 15239 loss_kpt: 0.000585 acc_pose: 0.840544 loss: 0.000585 2022/09/14 22:10:54 - mmengine - INFO - Epoch(train) [82][450/586] lr: 5.000000e-04 eta: 9:17:32 time: 0.465155 data_time: 0.027524 memory: 15239 loss_kpt: 0.000570 acc_pose: 0.847967 loss: 0.000570 2022/09/14 22:11:17 - mmengine - INFO - Epoch(train) [82][500/586] lr: 5.000000e-04 eta: 9:17:12 time: 0.468495 data_time: 0.026196 memory: 15239 loss_kpt: 0.000571 acc_pose: 0.873585 loss: 0.000571 2022/09/14 22:11:33 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 22:11:41 - mmengine - INFO - Epoch(train) [82][550/586] lr: 5.000000e-04 eta: 9:16:51 time: 0.467078 data_time: 0.026778 memory: 15239 loss_kpt: 0.000550 acc_pose: 0.825335 loss: 0.000550 2022/09/14 22:11:58 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 22:11:58 - mmengine - INFO - Saving checkpoint at 82 epochs 2022/09/14 22:12:28 - mmengine - INFO - Epoch(train) [83][50/586] lr: 5.000000e-04 eta: 9:15:50 time: 0.478382 data_time: 0.032576 memory: 15239 loss_kpt: 0.000559 acc_pose: 0.854201 loss: 0.000559 2022/09/14 22:12:52 - mmengine - INFO - Epoch(train) [83][100/586] lr: 5.000000e-04 eta: 9:15:30 time: 0.466575 data_time: 0.027104 memory: 15239 loss_kpt: 0.000558 acc_pose: 0.758916 loss: 0.000558 2022/09/14 22:13:16 - mmengine - INFO - Epoch(train) [83][150/586] lr: 5.000000e-04 eta: 9:15:10 time: 0.483100 data_time: 0.026399 memory: 15239 loss_kpt: 0.000576 acc_pose: 0.859694 loss: 0.000576 2022/09/14 22:13:39 - mmengine - INFO - Epoch(train) [83][200/586] lr: 5.000000e-04 eta: 9:14:49 time: 0.461338 data_time: 0.027359 memory: 15239 loss_kpt: 0.000580 acc_pose: 0.841947 loss: 0.000580 2022/09/14 22:14:02 - mmengine - INFO - Epoch(train) [83][250/586] lr: 5.000000e-04 eta: 9:14:28 time: 0.460387 data_time: 0.027043 memory: 15239 loss_kpt: 0.000575 acc_pose: 0.823283 loss: 0.000575 2022/09/14 22:14:26 - mmengine - INFO - Epoch(train) [83][300/586] lr: 5.000000e-04 eta: 9:14:08 time: 0.472305 data_time: 0.029458 memory: 15239 loss_kpt: 0.000562 acc_pose: 0.862651 loss: 0.000562 2022/09/14 22:14:49 - mmengine - INFO - Epoch(train) [83][350/586] lr: 5.000000e-04 eta: 9:13:47 time: 0.462216 data_time: 0.027262 memory: 15239 loss_kpt: 0.000557 acc_pose: 0.818392 loss: 0.000557 2022/09/14 22:15:12 - mmengine - INFO - Epoch(train) [83][400/586] lr: 5.000000e-04 eta: 9:13:26 time: 0.460578 data_time: 0.026570 memory: 15239 loss_kpt: 0.000574 acc_pose: 0.793757 loss: 0.000574 2022/09/14 22:15:36 - mmengine - INFO - Epoch(train) [83][450/586] lr: 5.000000e-04 eta: 9:13:06 time: 0.474488 data_time: 0.026550 memory: 15239 loss_kpt: 0.000575 acc_pose: 0.816112 loss: 0.000575 2022/09/14 22:15:59 - mmengine - INFO - Epoch(train) [83][500/586] lr: 5.000000e-04 eta: 9:12:45 time: 0.464624 data_time: 0.025771 memory: 15239 loss_kpt: 0.000555 acc_pose: 0.852318 loss: 0.000555 2022/09/14 22:16:22 - mmengine - INFO - Epoch(train) [83][550/586] lr: 5.000000e-04 eta: 9:12:25 time: 0.468120 data_time: 0.026017 memory: 15239 loss_kpt: 0.000562 acc_pose: 0.862076 loss: 0.000562 2022/09/14 22:16:39 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 22:16:39 - mmengine - INFO - Saving checkpoint at 83 epochs 2022/09/14 22:17:10 - mmengine - INFO - Epoch(train) [84][50/586] lr: 5.000000e-04 eta: 9:11:25 time: 0.481580 data_time: 0.041230 memory: 15239 loss_kpt: 0.000576 acc_pose: 0.844136 loss: 0.000576 2022/09/14 22:17:34 - mmengine - INFO - Epoch(train) [84][100/586] lr: 5.000000e-04 eta: 9:11:05 time: 0.472091 data_time: 0.029095 memory: 15239 loss_kpt: 0.000576 acc_pose: 0.839155 loss: 0.000576 2022/09/14 22:17:57 - mmengine - INFO - Epoch(train) [84][150/586] lr: 5.000000e-04 eta: 9:10:45 time: 0.474943 data_time: 0.027991 memory: 15239 loss_kpt: 0.000574 acc_pose: 0.817112 loss: 0.000574 2022/09/14 22:18:21 - mmengine - INFO - Epoch(train) [84][200/586] lr: 5.000000e-04 eta: 9:10:25 time: 0.469945 data_time: 0.026359 memory: 15239 loss_kpt: 0.000564 acc_pose: 0.831085 loss: 0.000564 2022/09/14 22:18:44 - mmengine - INFO - Epoch(train) [84][250/586] lr: 5.000000e-04 eta: 9:10:04 time: 0.467488 data_time: 0.026400 memory: 15239 loss_kpt: 0.000574 acc_pose: 0.902409 loss: 0.000574 2022/09/14 22:19:07 - mmengine - INFO - Epoch(train) [84][300/586] lr: 5.000000e-04 eta: 9:09:43 time: 0.457765 data_time: 0.026997 memory: 15239 loss_kpt: 0.000572 acc_pose: 0.786400 loss: 0.000572 2022/09/14 22:19:30 - mmengine - INFO - Epoch(train) [84][350/586] lr: 5.000000e-04 eta: 9:09:22 time: 0.468618 data_time: 0.026136 memory: 15239 loss_kpt: 0.000558 acc_pose: 0.845421 loss: 0.000558 2022/09/14 22:19:36 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 22:19:54 - mmengine - INFO - Epoch(train) [84][400/586] lr: 5.000000e-04 eta: 9:09:02 time: 0.471303 data_time: 0.026840 memory: 15239 loss_kpt: 0.000567 acc_pose: 0.856639 loss: 0.000567 2022/09/14 22:20:17 - mmengine - INFO - Epoch(train) [84][450/586] lr: 5.000000e-04 eta: 9:08:41 time: 0.462322 data_time: 0.027115 memory: 15239 loss_kpt: 0.000561 acc_pose: 0.869250 loss: 0.000561 2022/09/14 22:20:41 - mmengine - INFO - Epoch(train) [84][500/586] lr: 5.000000e-04 eta: 9:08:20 time: 0.466925 data_time: 0.026559 memory: 15239 loss_kpt: 0.000562 acc_pose: 0.816036 loss: 0.000562 2022/09/14 22:21:04 - mmengine - INFO - Epoch(train) [84][550/586] lr: 5.000000e-04 eta: 9:08:00 time: 0.468909 data_time: 0.027055 memory: 15239 loss_kpt: 0.000567 acc_pose: 0.794422 loss: 0.000567 2022/09/14 22:21:20 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 22:21:20 - mmengine - INFO - Saving checkpoint at 84 epochs 2022/09/14 22:21:52 - mmengine - INFO - Epoch(train) [85][50/586] lr: 5.000000e-04 eta: 9:07:00 time: 0.481095 data_time: 0.034936 memory: 15239 loss_kpt: 0.000563 acc_pose: 0.884777 loss: 0.000563 2022/09/14 22:22:15 - mmengine - INFO - Epoch(train) [85][100/586] lr: 5.000000e-04 eta: 9:06:40 time: 0.475678 data_time: 0.026022 memory: 15239 loss_kpt: 0.000568 acc_pose: 0.921119 loss: 0.000568 2022/09/14 22:22:39 - mmengine - INFO - Epoch(train) [85][150/586] lr: 5.000000e-04 eta: 9:06:20 time: 0.474835 data_time: 0.029828 memory: 15239 loss_kpt: 0.000548 acc_pose: 0.804813 loss: 0.000548 2022/09/14 22:23:02 - mmengine - INFO - Epoch(train) [85][200/586] lr: 5.000000e-04 eta: 9:06:00 time: 0.465846 data_time: 0.025924 memory: 15239 loss_kpt: 0.000544 acc_pose: 0.876431 loss: 0.000544 2022/09/14 22:23:26 - mmengine - INFO - Epoch(train) [85][250/586] lr: 5.000000e-04 eta: 9:05:39 time: 0.463655 data_time: 0.027341 memory: 15239 loss_kpt: 0.000555 acc_pose: 0.847967 loss: 0.000555 2022/09/14 22:23:50 - mmengine - INFO - Epoch(train) [85][300/586] lr: 5.000000e-04 eta: 9:05:19 time: 0.477264 data_time: 0.027385 memory: 15239 loss_kpt: 0.000561 acc_pose: 0.843370 loss: 0.000561 2022/09/14 22:24:13 - mmengine - INFO - Epoch(train) [85][350/586] lr: 5.000000e-04 eta: 9:04:59 time: 0.467505 data_time: 0.026610 memory: 15239 loss_kpt: 0.000574 acc_pose: 0.856926 loss: 0.000574 2022/09/14 22:24:36 - mmengine - INFO - Epoch(train) [85][400/586] lr: 5.000000e-04 eta: 9:04:38 time: 0.469001 data_time: 0.027055 memory: 15239 loss_kpt: 0.000566 acc_pose: 0.837624 loss: 0.000566 2022/09/14 22:25:00 - mmengine - INFO - Epoch(train) [85][450/586] lr: 5.000000e-04 eta: 9:04:18 time: 0.470789 data_time: 0.025601 memory: 15239 loss_kpt: 0.000566 acc_pose: 0.858953 loss: 0.000566 2022/09/14 22:25:23 - mmengine - INFO - Epoch(train) [85][500/586] lr: 5.000000e-04 eta: 9:03:57 time: 0.463540 data_time: 0.027700 memory: 15239 loss_kpt: 0.000581 acc_pose: 0.928731 loss: 0.000581 2022/09/14 22:25:47 - mmengine - INFO - Epoch(train) [85][550/586] lr: 5.000000e-04 eta: 9:03:36 time: 0.469843 data_time: 0.026442 memory: 15239 loss_kpt: 0.000558 acc_pose: 0.887737 loss: 0.000558 2022/09/14 22:26:04 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 22:26:04 - mmengine - INFO - Saving checkpoint at 85 epochs 2022/09/14 22:26:35 - mmengine - INFO - Epoch(train) [86][50/586] lr: 5.000000e-04 eta: 9:02:36 time: 0.468948 data_time: 0.037549 memory: 15239 loss_kpt: 0.000543 acc_pose: 0.892990 loss: 0.000543 2022/09/14 22:26:59 - mmengine - INFO - Epoch(train) [86][100/586] lr: 5.000000e-04 eta: 9:02:17 time: 0.482460 data_time: 0.031997 memory: 15239 loss_kpt: 0.000550 acc_pose: 0.856842 loss: 0.000550 2022/09/14 22:27:22 - mmengine - INFO - Epoch(train) [86][150/586] lr: 5.000000e-04 eta: 9:01:56 time: 0.469947 data_time: 0.029727 memory: 15239 loss_kpt: 0.000547 acc_pose: 0.910170 loss: 0.000547 2022/09/14 22:27:41 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 22:27:45 - mmengine - INFO - Epoch(train) [86][200/586] lr: 5.000000e-04 eta: 9:01:36 time: 0.466087 data_time: 0.026232 memory: 15239 loss_kpt: 0.000554 acc_pose: 0.857414 loss: 0.000554 2022/09/14 22:28:09 - mmengine - INFO - Epoch(train) [86][250/586] lr: 5.000000e-04 eta: 9:01:15 time: 0.465238 data_time: 0.026178 memory: 15239 loss_kpt: 0.000558 acc_pose: 0.854880 loss: 0.000558 2022/09/14 22:28:32 - mmengine - INFO - Epoch(train) [86][300/586] lr: 5.000000e-04 eta: 9:00:55 time: 0.470522 data_time: 0.026267 memory: 15239 loss_kpt: 0.000550 acc_pose: 0.861792 loss: 0.000550 2022/09/14 22:28:56 - mmengine - INFO - Epoch(train) [86][350/586] lr: 5.000000e-04 eta: 9:00:34 time: 0.465362 data_time: 0.029921 memory: 15239 loss_kpt: 0.000571 acc_pose: 0.831694 loss: 0.000571 2022/09/14 22:29:19 - mmengine - INFO - Epoch(train) [86][400/586] lr: 5.000000e-04 eta: 9:00:13 time: 0.468806 data_time: 0.026212 memory: 15239 loss_kpt: 0.000571 acc_pose: 0.777627 loss: 0.000571 2022/09/14 22:29:42 - mmengine - INFO - Epoch(train) [86][450/586] lr: 5.000000e-04 eta: 8:59:52 time: 0.461920 data_time: 0.025886 memory: 15239 loss_kpt: 0.000556 acc_pose: 0.825522 loss: 0.000556 2022/09/14 22:30:06 - mmengine - INFO - Epoch(train) [86][500/586] lr: 5.000000e-04 eta: 8:59:32 time: 0.469154 data_time: 0.026321 memory: 15239 loss_kpt: 0.000560 acc_pose: 0.838892 loss: 0.000560 2022/09/14 22:30:29 - mmengine - INFO - Epoch(train) [86][550/586] lr: 5.000000e-04 eta: 8:59:12 time: 0.473621 data_time: 0.026442 memory: 15239 loss_kpt: 0.000571 acc_pose: 0.811382 loss: 0.000571 2022/09/14 22:30:46 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 22:30:46 - mmengine - INFO - Saving checkpoint at 86 epochs 2022/09/14 22:31:17 - mmengine - INFO - Epoch(train) [87][50/586] lr: 5.000000e-04 eta: 8:58:13 time: 0.482269 data_time: 0.039349 memory: 15239 loss_kpt: 0.000560 acc_pose: 0.876564 loss: 0.000560 2022/09/14 22:31:40 - mmengine - INFO - Epoch(train) [87][100/586] lr: 5.000000e-04 eta: 8:57:52 time: 0.467511 data_time: 0.026394 memory: 15239 loss_kpt: 0.000566 acc_pose: 0.820322 loss: 0.000566 2022/09/14 22:32:04 - mmengine - INFO - Epoch(train) [87][150/586] lr: 5.000000e-04 eta: 8:57:32 time: 0.474648 data_time: 0.026261 memory: 15239 loss_kpt: 0.000569 acc_pose: 0.831101 loss: 0.000569 2022/09/14 22:32:28 - mmengine - INFO - Epoch(train) [87][200/586] lr: 5.000000e-04 eta: 8:57:12 time: 0.474062 data_time: 0.026813 memory: 15239 loss_kpt: 0.000576 acc_pose: 0.858022 loss: 0.000576 2022/09/14 22:32:51 - mmengine - INFO - Epoch(train) [87][250/586] lr: 5.000000e-04 eta: 8:56:51 time: 0.465319 data_time: 0.025625 memory: 15239 loss_kpt: 0.000558 acc_pose: 0.880615 loss: 0.000558 2022/09/14 22:33:15 - mmengine - INFO - Epoch(train) [87][300/586] lr: 5.000000e-04 eta: 8:56:32 time: 0.477678 data_time: 0.031072 memory: 15239 loss_kpt: 0.000570 acc_pose: 0.858060 loss: 0.000570 2022/09/14 22:33:38 - mmengine - INFO - Epoch(train) [87][350/586] lr: 5.000000e-04 eta: 8:56:10 time: 0.461814 data_time: 0.027470 memory: 15239 loss_kpt: 0.000563 acc_pose: 0.837031 loss: 0.000563 2022/09/14 22:34:01 - mmengine - INFO - Epoch(train) [87][400/586] lr: 5.000000e-04 eta: 8:55:50 time: 0.463972 data_time: 0.026314 memory: 15239 loss_kpt: 0.000566 acc_pose: 0.837427 loss: 0.000566 2022/09/14 22:34:25 - mmengine - INFO - Epoch(train) [87][450/586] lr: 5.000000e-04 eta: 8:55:30 time: 0.477705 data_time: 0.027905 memory: 15239 loss_kpt: 0.000547 acc_pose: 0.884253 loss: 0.000547 2022/09/14 22:34:48 - mmengine - INFO - Epoch(train) [87][500/586] lr: 5.000000e-04 eta: 8:55:09 time: 0.463101 data_time: 0.027098 memory: 15239 loss_kpt: 0.000557 acc_pose: 0.816020 loss: 0.000557 2022/09/14 22:35:11 - mmengine - INFO - Epoch(train) [87][550/586] lr: 5.000000e-04 eta: 8:54:48 time: 0.463053 data_time: 0.026089 memory: 15239 loss_kpt: 0.000563 acc_pose: 0.751728 loss: 0.000563 2022/09/14 22:35:29 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 22:35:29 - mmengine - INFO - Saving checkpoint at 87 epochs 2022/09/14 22:35:44 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 22:35:59 - mmengine - INFO - Epoch(train) [88][50/586] lr: 5.000000e-04 eta: 8:53:49 time: 0.472027 data_time: 0.036738 memory: 15239 loss_kpt: 0.000568 acc_pose: 0.890897 loss: 0.000568 2022/09/14 22:36:23 - mmengine - INFO - Epoch(train) [88][100/586] lr: 5.000000e-04 eta: 8:53:28 time: 0.469150 data_time: 0.026691 memory: 15239 loss_kpt: 0.000539 acc_pose: 0.855085 loss: 0.000539 2022/09/14 22:36:46 - mmengine - INFO - Epoch(train) [88][150/586] lr: 5.000000e-04 eta: 8:53:08 time: 0.473097 data_time: 0.026479 memory: 15239 loss_kpt: 0.000557 acc_pose: 0.816370 loss: 0.000557 2022/09/14 22:37:10 - mmengine - INFO - Epoch(train) [88][200/586] lr: 5.000000e-04 eta: 8:52:47 time: 0.467087 data_time: 0.027126 memory: 15239 loss_kpt: 0.000550 acc_pose: 0.817260 loss: 0.000550 2022/09/14 22:37:33 - mmengine - INFO - Epoch(train) [88][250/586] lr: 5.000000e-04 eta: 8:52:26 time: 0.462062 data_time: 0.026591 memory: 15239 loss_kpt: 0.000562 acc_pose: 0.877362 loss: 0.000562 2022/09/14 22:37:57 - mmengine - INFO - Epoch(train) [88][300/586] lr: 5.000000e-04 eta: 8:52:06 time: 0.477792 data_time: 0.027543 memory: 15239 loss_kpt: 0.000548 acc_pose: 0.840003 loss: 0.000548 2022/09/14 22:38:20 - mmengine - INFO - Epoch(train) [88][350/586] lr: 5.000000e-04 eta: 8:51:46 time: 0.463875 data_time: 0.026627 memory: 15239 loss_kpt: 0.000560 acc_pose: 0.888768 loss: 0.000560 2022/09/14 22:38:43 - mmengine - INFO - Epoch(train) [88][400/586] lr: 5.000000e-04 eta: 8:51:24 time: 0.460835 data_time: 0.027577 memory: 15239 loss_kpt: 0.000541 acc_pose: 0.883031 loss: 0.000541 2022/09/14 22:39:07 - mmengine - INFO - Epoch(train) [88][450/586] lr: 5.000000e-04 eta: 8:51:04 time: 0.476140 data_time: 0.027323 memory: 15239 loss_kpt: 0.000561 acc_pose: 0.859696 loss: 0.000561 2022/09/14 22:39:30 - mmengine - INFO - Epoch(train) [88][500/586] lr: 5.000000e-04 eta: 8:50:44 time: 0.465801 data_time: 0.028140 memory: 15239 loss_kpt: 0.000553 acc_pose: 0.846272 loss: 0.000553 2022/09/14 22:39:53 - mmengine - INFO - Epoch(train) [88][550/586] lr: 5.000000e-04 eta: 8:50:23 time: 0.467375 data_time: 0.026754 memory: 15239 loss_kpt: 0.000570 acc_pose: 0.855588 loss: 0.000570 2022/09/14 22:40:10 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 22:40:10 - mmengine - INFO - Saving checkpoint at 88 epochs 2022/09/14 22:40:42 - mmengine - INFO - Epoch(train) [89][50/586] lr: 5.000000e-04 eta: 8:49:25 time: 0.486457 data_time: 0.039581 memory: 15239 loss_kpt: 0.000569 acc_pose: 0.817648 loss: 0.000569 2022/09/14 22:41:05 - mmengine - INFO - Epoch(train) [89][100/586] lr: 5.000000e-04 eta: 8:49:05 time: 0.467769 data_time: 0.033494 memory: 15239 loss_kpt: 0.000560 acc_pose: 0.863641 loss: 0.000560 2022/09/14 22:41:29 - mmengine - INFO - Epoch(train) [89][150/586] lr: 5.000000e-04 eta: 8:48:45 time: 0.474860 data_time: 0.035012 memory: 15239 loss_kpt: 0.000561 acc_pose: 0.866399 loss: 0.000561 2022/09/14 22:41:53 - mmengine - INFO - Epoch(train) [89][200/586] lr: 5.000000e-04 eta: 8:48:24 time: 0.474538 data_time: 0.033874 memory: 15239 loss_kpt: 0.000553 acc_pose: 0.882192 loss: 0.000553 2022/09/14 22:42:16 - mmengine - INFO - Epoch(train) [89][250/586] lr: 5.000000e-04 eta: 8:48:03 time: 0.464206 data_time: 0.031630 memory: 15239 loss_kpt: 0.000565 acc_pose: 0.846917 loss: 0.000565 2022/09/14 22:42:40 - mmengine - INFO - Epoch(train) [89][300/586] lr: 5.000000e-04 eta: 8:47:44 time: 0.481280 data_time: 0.035847 memory: 15239 loss_kpt: 0.000552 acc_pose: 0.847509 loss: 0.000552 2022/09/14 22:43:04 - mmengine - INFO - Epoch(train) [89][350/586] lr: 5.000000e-04 eta: 8:47:23 time: 0.471976 data_time: 0.030502 memory: 15239 loss_kpt: 0.000555 acc_pose: 0.913439 loss: 0.000555 2022/09/14 22:43:27 - mmengine - INFO - Epoch(train) [89][400/586] lr: 5.000000e-04 eta: 8:47:02 time: 0.462774 data_time: 0.033447 memory: 15239 loss_kpt: 0.000559 acc_pose: 0.816853 loss: 0.000559 2022/09/14 22:43:42 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 22:43:50 - mmengine - INFO - Epoch(train) [89][450/586] lr: 5.000000e-04 eta: 8:46:42 time: 0.469851 data_time: 0.025829 memory: 15239 loss_kpt: 0.000560 acc_pose: 0.879906 loss: 0.000560 2022/09/14 22:44:14 - mmengine - INFO - Epoch(train) [89][500/586] lr: 5.000000e-04 eta: 8:46:21 time: 0.471204 data_time: 0.026198 memory: 15239 loss_kpt: 0.000553 acc_pose: 0.834763 loss: 0.000553 2022/09/14 22:44:37 - mmengine - INFO - Epoch(train) [89][550/586] lr: 5.000000e-04 eta: 8:46:01 time: 0.467773 data_time: 0.027035 memory: 15239 loss_kpt: 0.000571 acc_pose: 0.874785 loss: 0.000571 2022/09/14 22:44:54 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 22:44:54 - mmengine - INFO - Saving checkpoint at 89 epochs 2022/09/14 22:45:25 - mmengine - INFO - Epoch(train) [90][50/586] lr: 5.000000e-04 eta: 8:45:03 time: 0.474281 data_time: 0.030109 memory: 15239 loss_kpt: 0.000557 acc_pose: 0.909283 loss: 0.000557 2022/09/14 22:45:49 - mmengine - INFO - Epoch(train) [90][100/586] lr: 5.000000e-04 eta: 8:44:42 time: 0.473117 data_time: 0.025926 memory: 15239 loss_kpt: 0.000578 acc_pose: 0.847692 loss: 0.000578 2022/09/14 22:46:13 - mmengine - INFO - Epoch(train) [90][150/586] lr: 5.000000e-04 eta: 8:44:22 time: 0.474553 data_time: 0.025669 memory: 15239 loss_kpt: 0.000561 acc_pose: 0.923240 loss: 0.000561 2022/09/14 22:46:36 - mmengine - INFO - Epoch(train) [90][200/586] lr: 5.000000e-04 eta: 8:44:02 time: 0.468055 data_time: 0.027037 memory: 15239 loss_kpt: 0.000571 acc_pose: 0.846068 loss: 0.000571 2022/09/14 22:47:00 - mmengine - INFO - Epoch(train) [90][250/586] lr: 5.000000e-04 eta: 8:43:41 time: 0.468747 data_time: 0.027725 memory: 15239 loss_kpt: 0.000552 acc_pose: 0.820268 loss: 0.000552 2022/09/14 22:47:23 - mmengine - INFO - Epoch(train) [90][300/586] lr: 5.000000e-04 eta: 8:43:20 time: 0.465826 data_time: 0.027215 memory: 15239 loss_kpt: 0.000580 acc_pose: 0.819518 loss: 0.000580 2022/09/14 22:47:46 - mmengine - INFO - Epoch(train) [90][350/586] lr: 5.000000e-04 eta: 8:43:00 time: 0.470253 data_time: 0.032943 memory: 15239 loss_kpt: 0.000569 acc_pose: 0.863754 loss: 0.000569 2022/09/14 22:48:10 - mmengine - INFO - Epoch(train) [90][400/586] lr: 5.000000e-04 eta: 8:42:39 time: 0.471003 data_time: 0.027043 memory: 15239 loss_kpt: 0.000560 acc_pose: 0.889585 loss: 0.000560 2022/09/14 22:48:33 - mmengine - INFO - Epoch(train) [90][450/586] lr: 5.000000e-04 eta: 8:42:19 time: 0.470297 data_time: 0.026358 memory: 15239 loss_kpt: 0.000564 acc_pose: 0.848459 loss: 0.000564 2022/09/14 22:48:57 - mmengine - INFO - Epoch(train) [90][500/586] lr: 5.000000e-04 eta: 8:41:58 time: 0.463610 data_time: 0.026761 memory: 15239 loss_kpt: 0.000554 acc_pose: 0.758816 loss: 0.000554 2022/09/14 22:49:20 - mmengine - INFO - Epoch(train) [90][550/586] lr: 5.000000e-04 eta: 8:41:37 time: 0.469551 data_time: 0.026055 memory: 15239 loss_kpt: 0.000564 acc_pose: 0.822408 loss: 0.000564 2022/09/14 22:49:37 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 22:49:37 - mmengine - INFO - Saving checkpoint at 90 epochs 2022/09/14 22:49:54 - mmengine - INFO - Epoch(val) [90][50/407] eta: 0:01:12 time: 0.203534 data_time: 0.016462 memory: 15239 2022/09/14 22:50:04 - mmengine - INFO - Epoch(val) [90][100/407] eta: 0:00:59 time: 0.194100 data_time: 0.008594 memory: 2064 2022/09/14 22:50:13 - mmengine - INFO - Epoch(val) [90][150/407] eta: 0:00:50 time: 0.195420 data_time: 0.009720 memory: 2064 2022/09/14 22:50:23 - mmengine - INFO - Epoch(val) [90][200/407] eta: 0:00:40 time: 0.194277 data_time: 0.008127 memory: 2064 2022/09/14 22:50:33 - mmengine - INFO - Epoch(val) [90][250/407] eta: 0:00:31 time: 0.198104 data_time: 0.011732 memory: 2064 2022/09/14 22:50:43 - mmengine - INFO - Epoch(val) [90][300/407] eta: 0:00:20 time: 0.195050 data_time: 0.009042 memory: 2064 2022/09/14 22:50:52 - mmengine - INFO - Epoch(val) [90][350/407] eta: 0:00:11 time: 0.193619 data_time: 0.008302 memory: 2064 2022/09/14 22:51:02 - mmengine - INFO - Epoch(val) [90][400/407] eta: 0:00:01 time: 0.192269 data_time: 0.007757 memory: 2064 2022/09/14 22:51:39 - mmengine - INFO - Evaluating CocoMetric... 2022/09/14 22:51:53 - mmengine - INFO - Epoch(val) [90][407/407] coco/AP: 0.752452 coco/AP .5: 0.900723 coco/AP .75: 0.820414 coco/AP (M): 0.714423 coco/AP (L): 0.821573 coco/AR: 0.802692 coco/AR .5: 0.937185 coco/AR .75: 0.861776 coco/AR (M): 0.759437 coco/AR (L): 0.865366 2022/09/14 22:51:53 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220914/hrnet_w48_384/best_coco/AP_epoch_80.pth is removed 2022/09/14 22:51:57 - mmengine - INFO - The best checkpoint with 0.7525 coco/AP at 90 epoch is saved to best_coco/AP_epoch_90.pth. 2022/09/14 22:52:21 - mmengine - INFO - Epoch(train) [91][50/586] lr: 5.000000e-04 eta: 8:40:39 time: 0.474456 data_time: 0.030762 memory: 15239 loss_kpt: 0.000548 acc_pose: 0.812758 loss: 0.000548 2022/09/14 22:52:44 - mmengine - INFO - Epoch(train) [91][100/586] lr: 5.000000e-04 eta: 8:40:19 time: 0.476030 data_time: 0.026199 memory: 15239 loss_kpt: 0.000541 acc_pose: 0.858797 loss: 0.000541 2022/09/14 22:53:08 - mmengine - INFO - Epoch(train) [91][150/586] lr: 5.000000e-04 eta: 8:39:58 time: 0.465270 data_time: 0.027948 memory: 15239 loss_kpt: 0.000569 acc_pose: 0.827240 loss: 0.000569 2022/09/14 22:53:31 - mmengine - INFO - Epoch(train) [91][200/586] lr: 5.000000e-04 eta: 8:39:38 time: 0.468494 data_time: 0.031311 memory: 15239 loss_kpt: 0.000548 acc_pose: 0.823162 loss: 0.000548 2022/09/14 22:53:54 - mmengine - INFO - Epoch(train) [91][250/586] lr: 5.000000e-04 eta: 8:39:17 time: 0.465594 data_time: 0.026443 memory: 15239 loss_kpt: 0.000547 acc_pose: 0.837063 loss: 0.000547 2022/09/14 22:53:59 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 22:54:18 - mmengine - INFO - Epoch(train) [91][300/586] lr: 5.000000e-04 eta: 8:38:56 time: 0.467858 data_time: 0.026863 memory: 15239 loss_kpt: 0.000554 acc_pose: 0.861455 loss: 0.000554 2022/09/14 22:54:41 - mmengine - INFO - Epoch(train) [91][350/586] lr: 5.000000e-04 eta: 8:38:35 time: 0.465041 data_time: 0.026974 memory: 15239 loss_kpt: 0.000560 acc_pose: 0.871836 loss: 0.000560 2022/09/14 22:55:05 - mmengine - INFO - Epoch(train) [91][400/586] lr: 5.000000e-04 eta: 8:38:15 time: 0.478176 data_time: 0.025988 memory: 15239 loss_kpt: 0.000555 acc_pose: 0.846120 loss: 0.000555 2022/09/14 22:55:29 - mmengine - INFO - Epoch(train) [91][450/586] lr: 5.000000e-04 eta: 8:37:55 time: 0.474119 data_time: 0.026197 memory: 15239 loss_kpt: 0.000556 acc_pose: 0.882283 loss: 0.000556 2022/09/14 22:55:52 - mmengine - INFO - Epoch(train) [91][500/586] lr: 5.000000e-04 eta: 8:37:34 time: 0.467418 data_time: 0.030608 memory: 15239 loss_kpt: 0.000559 acc_pose: 0.802550 loss: 0.000559 2022/09/14 22:56:16 - mmengine - INFO - Epoch(train) [91][550/586] lr: 5.000000e-04 eta: 8:37:14 time: 0.481443 data_time: 0.027520 memory: 15239 loss_kpt: 0.000566 acc_pose: 0.803445 loss: 0.000566 2022/09/14 22:56:33 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 22:56:33 - mmengine - INFO - Saving checkpoint at 91 epochs 2022/09/14 22:57:04 - mmengine - INFO - Epoch(train) [92][50/586] lr: 5.000000e-04 eta: 8:36:17 time: 0.470244 data_time: 0.030913 memory: 15239 loss_kpt: 0.000550 acc_pose: 0.870521 loss: 0.000550 2022/09/14 22:57:27 - mmengine - INFO - Epoch(train) [92][100/586] lr: 5.000000e-04 eta: 8:35:57 time: 0.473240 data_time: 0.031621 memory: 15239 loss_kpt: 0.000554 acc_pose: 0.777457 loss: 0.000554 2022/09/14 22:57:51 - mmengine - INFO - Epoch(train) [92][150/586] lr: 5.000000e-04 eta: 8:35:36 time: 0.464547 data_time: 0.026410 memory: 15239 loss_kpt: 0.000554 acc_pose: 0.833467 loss: 0.000554 2022/09/14 22:58:14 - mmengine - INFO - Epoch(train) [92][200/586] lr: 5.000000e-04 eta: 8:35:15 time: 0.469653 data_time: 0.026625 memory: 15239 loss_kpt: 0.000558 acc_pose: 0.850569 loss: 0.000558 2022/09/14 22:58:37 - mmengine - INFO - Epoch(train) [92][250/586] lr: 5.000000e-04 eta: 8:34:54 time: 0.466911 data_time: 0.029724 memory: 15239 loss_kpt: 0.000556 acc_pose: 0.853306 loss: 0.000556 2022/09/14 22:59:00 - mmengine - INFO - Epoch(train) [92][300/586] lr: 5.000000e-04 eta: 8:34:33 time: 0.460193 data_time: 0.025708 memory: 15239 loss_kpt: 0.000567 acc_pose: 0.832082 loss: 0.000567 2022/09/14 22:59:24 - mmengine - INFO - Epoch(train) [92][350/586] lr: 5.000000e-04 eta: 8:34:12 time: 0.464075 data_time: 0.026196 memory: 15239 loss_kpt: 0.000560 acc_pose: 0.873174 loss: 0.000560 2022/09/14 22:59:48 - mmengine - INFO - Epoch(train) [92][400/586] lr: 5.000000e-04 eta: 8:33:52 time: 0.478607 data_time: 0.027500 memory: 15239 loss_kpt: 0.000575 acc_pose: 0.837572 loss: 0.000575 2022/09/14 23:00:11 - mmengine - INFO - Epoch(train) [92][450/586] lr: 5.000000e-04 eta: 8:33:31 time: 0.460063 data_time: 0.026331 memory: 15239 loss_kpt: 0.000552 acc_pose: 0.839904 loss: 0.000552 2022/09/14 23:00:34 - mmengine - INFO - Epoch(train) [92][500/586] lr: 5.000000e-04 eta: 8:33:10 time: 0.464305 data_time: 0.027176 memory: 15239 loss_kpt: 0.000559 acc_pose: 0.832433 loss: 0.000559 2022/09/14 23:00:57 - mmengine - INFO - Epoch(train) [92][550/586] lr: 5.000000e-04 eta: 8:32:49 time: 0.470072 data_time: 0.027231 memory: 15239 loss_kpt: 0.000544 acc_pose: 0.892388 loss: 0.000544 2022/09/14 23:01:14 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 23:01:14 - mmengine - INFO - Saving checkpoint at 92 epochs 2022/09/14 23:01:46 - mmengine - INFO - Epoch(train) [93][50/586] lr: 5.000000e-04 eta: 8:31:54 time: 0.496511 data_time: 0.030542 memory: 15239 loss_kpt: 0.000540 acc_pose: 0.890327 loss: 0.000540 2022/09/14 23:02:04 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 23:02:10 - mmengine - INFO - Epoch(train) [93][100/586] lr: 5.000000e-04 eta: 8:31:34 time: 0.482155 data_time: 0.026163 memory: 15239 loss_kpt: 0.000547 acc_pose: 0.828274 loss: 0.000547 2022/09/14 23:02:34 - mmengine - INFO - Epoch(train) [93][150/586] lr: 5.000000e-04 eta: 8:31:14 time: 0.489166 data_time: 0.025122 memory: 15239 loss_kpt: 0.000546 acc_pose: 0.895436 loss: 0.000546 2022/09/14 23:02:58 - mmengine - INFO - Epoch(train) [93][200/586] lr: 5.000000e-04 eta: 8:30:54 time: 0.478566 data_time: 0.030382 memory: 15239 loss_kpt: 0.000563 acc_pose: 0.854162 loss: 0.000563 2022/09/14 23:03:22 - mmengine - INFO - Epoch(train) [93][250/586] lr: 5.000000e-04 eta: 8:30:34 time: 0.479977 data_time: 0.025952 memory: 15239 loss_kpt: 0.000533 acc_pose: 0.848929 loss: 0.000533 2022/09/14 23:03:46 - mmengine - INFO - Epoch(train) [93][300/586] lr: 5.000000e-04 eta: 8:30:14 time: 0.473034 data_time: 0.026564 memory: 15239 loss_kpt: 0.000546 acc_pose: 0.856131 loss: 0.000546 2022/09/14 23:04:09 - mmengine - INFO - Epoch(train) [93][350/586] lr: 5.000000e-04 eta: 8:29:53 time: 0.460653 data_time: 0.026043 memory: 15239 loss_kpt: 0.000541 acc_pose: 0.899697 loss: 0.000541 2022/09/14 23:04:32 - mmengine - INFO - Epoch(train) [93][400/586] lr: 5.000000e-04 eta: 8:29:32 time: 0.467674 data_time: 0.026800 memory: 15239 loss_kpt: 0.000549 acc_pose: 0.790370 loss: 0.000549 2022/09/14 23:04:56 - mmengine - INFO - Epoch(train) [93][450/586] lr: 5.000000e-04 eta: 8:29:11 time: 0.466797 data_time: 0.026659 memory: 15239 loss_kpt: 0.000552 acc_pose: 0.885082 loss: 0.000552 2022/09/14 23:05:19 - mmengine - INFO - Epoch(train) [93][500/586] lr: 5.000000e-04 eta: 8:28:50 time: 0.462883 data_time: 0.029535 memory: 15239 loss_kpt: 0.000544 acc_pose: 0.855357 loss: 0.000544 2022/09/14 23:05:42 - mmengine - INFO - Epoch(train) [93][550/586] lr: 5.000000e-04 eta: 8:28:29 time: 0.469885 data_time: 0.025965 memory: 15239 loss_kpt: 0.000559 acc_pose: 0.872871 loss: 0.000559 2022/09/14 23:05:59 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 23:05:59 - mmengine - INFO - Saving checkpoint at 93 epochs 2022/09/14 23:06:30 - mmengine - INFO - Epoch(train) [94][50/586] lr: 5.000000e-04 eta: 8:27:33 time: 0.472911 data_time: 0.032592 memory: 15239 loss_kpt: 0.000555 acc_pose: 0.871968 loss: 0.000555 2022/09/14 23:06:53 - mmengine - INFO - Epoch(train) [94][100/586] lr: 5.000000e-04 eta: 8:27:13 time: 0.475927 data_time: 0.030711 memory: 15239 loss_kpt: 0.000561 acc_pose: 0.834772 loss: 0.000561 2022/09/14 23:07:17 - mmengine - INFO - Epoch(train) [94][150/586] lr: 5.000000e-04 eta: 8:26:52 time: 0.477214 data_time: 0.026395 memory: 15239 loss_kpt: 0.000547 acc_pose: 0.790427 loss: 0.000547 2022/09/14 23:07:40 - mmengine - INFO - Epoch(train) [94][200/586] lr: 5.000000e-04 eta: 8:26:31 time: 0.463851 data_time: 0.025921 memory: 15239 loss_kpt: 0.000576 acc_pose: 0.800854 loss: 0.000576 2022/09/14 23:08:04 - mmengine - INFO - Epoch(train) [94][250/586] lr: 5.000000e-04 eta: 8:26:11 time: 0.466886 data_time: 0.030233 memory: 15239 loss_kpt: 0.000566 acc_pose: 0.813616 loss: 0.000566 2022/09/14 23:08:27 - mmengine - INFO - Epoch(train) [94][300/586] lr: 5.000000e-04 eta: 8:25:50 time: 0.472974 data_time: 0.026598 memory: 15239 loss_kpt: 0.000548 acc_pose: 0.870783 loss: 0.000548 2022/09/14 23:08:50 - mmengine - INFO - Epoch(train) [94][350/586] lr: 5.000000e-04 eta: 8:25:29 time: 0.458447 data_time: 0.026461 memory: 15239 loss_kpt: 0.000568 acc_pose: 0.792743 loss: 0.000568 2022/09/14 23:09:14 - mmengine - INFO - Epoch(train) [94][400/586] lr: 5.000000e-04 eta: 8:25:08 time: 0.467567 data_time: 0.026935 memory: 15239 loss_kpt: 0.000553 acc_pose: 0.843264 loss: 0.000553 2022/09/14 23:09:38 - mmengine - INFO - Epoch(train) [94][450/586] lr: 5.000000e-04 eta: 8:24:48 time: 0.475211 data_time: 0.026579 memory: 15239 loss_kpt: 0.000560 acc_pose: 0.882361 loss: 0.000560 2022/09/14 23:10:01 - mmengine - INFO - Epoch(train) [94][500/586] lr: 5.000000e-04 eta: 8:24:26 time: 0.461167 data_time: 0.027651 memory: 15239 loss_kpt: 0.000548 acc_pose: 0.903986 loss: 0.000548 2022/09/14 23:10:02 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 23:10:24 - mmengine - INFO - Epoch(train) [94][550/586] lr: 5.000000e-04 eta: 8:24:05 time: 0.464562 data_time: 0.029781 memory: 15239 loss_kpt: 0.000577 acc_pose: 0.866180 loss: 0.000577 2022/09/14 23:10:41 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 23:10:41 - mmengine - INFO - Saving checkpoint at 94 epochs 2022/09/14 23:11:13 - mmengine - INFO - Epoch(train) [95][50/586] lr: 5.000000e-04 eta: 8:23:10 time: 0.480592 data_time: 0.034557 memory: 15239 loss_kpt: 0.000549 acc_pose: 0.851084 loss: 0.000549 2022/09/14 23:11:36 - mmengine - INFO - Epoch(train) [95][100/586] lr: 5.000000e-04 eta: 8:22:49 time: 0.470622 data_time: 0.026121 memory: 15239 loss_kpt: 0.000547 acc_pose: 0.892638 loss: 0.000547 2022/09/14 23:12:00 - mmengine - INFO - Epoch(train) [95][150/586] lr: 5.000000e-04 eta: 8:22:28 time: 0.468536 data_time: 0.026347 memory: 15239 loss_kpt: 0.000555 acc_pose: 0.831278 loss: 0.000555 2022/09/14 23:12:23 - mmengine - INFO - Epoch(train) [95][200/586] lr: 5.000000e-04 eta: 8:22:08 time: 0.469955 data_time: 0.026600 memory: 15239 loss_kpt: 0.000555 acc_pose: 0.882717 loss: 0.000555 2022/09/14 23:12:47 - mmengine - INFO - Epoch(train) [95][250/586] lr: 5.000000e-04 eta: 8:21:48 time: 0.480199 data_time: 0.026483 memory: 15239 loss_kpt: 0.000547 acc_pose: 0.809413 loss: 0.000547 2022/09/14 23:13:11 - mmengine - INFO - Epoch(train) [95][300/586] lr: 5.000000e-04 eta: 8:21:27 time: 0.467188 data_time: 0.026985 memory: 15239 loss_kpt: 0.000567 acc_pose: 0.804722 loss: 0.000567 2022/09/14 23:13:34 - mmengine - INFO - Epoch(train) [95][350/586] lr: 5.000000e-04 eta: 8:21:06 time: 0.470934 data_time: 0.030428 memory: 15239 loss_kpt: 0.000550 acc_pose: 0.882932 loss: 0.000550 2022/09/14 23:13:58 - mmengine - INFO - Epoch(train) [95][400/586] lr: 5.000000e-04 eta: 8:20:46 time: 0.473317 data_time: 0.025729 memory: 15239 loss_kpt: 0.000559 acc_pose: 0.859192 loss: 0.000559 2022/09/14 23:14:21 - mmengine - INFO - Epoch(train) [95][450/586] lr: 5.000000e-04 eta: 8:20:24 time: 0.456790 data_time: 0.025906 memory: 15239 loss_kpt: 0.000547 acc_pose: 0.883977 loss: 0.000547 2022/09/14 23:14:44 - mmengine - INFO - Epoch(train) [95][500/586] lr: 5.000000e-04 eta: 8:20:03 time: 0.468933 data_time: 0.026570 memory: 15239 loss_kpt: 0.000569 acc_pose: 0.880202 loss: 0.000569 2022/09/14 23:15:08 - mmengine - INFO - Epoch(train) [95][550/586] lr: 5.000000e-04 eta: 8:19:43 time: 0.469080 data_time: 0.027391 memory: 15239 loss_kpt: 0.000575 acc_pose: 0.888047 loss: 0.000575 2022/09/14 23:15:24 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 23:15:24 - mmengine - INFO - Saving checkpoint at 95 epochs 2022/09/14 23:15:55 - mmengine - INFO - Epoch(train) [96][50/586] lr: 5.000000e-04 eta: 8:18:47 time: 0.475323 data_time: 0.031657 memory: 15239 loss_kpt: 0.000548 acc_pose: 0.892637 loss: 0.000548 2022/09/14 23:16:19 - mmengine - INFO - Epoch(train) [96][100/586] lr: 5.000000e-04 eta: 8:18:26 time: 0.472615 data_time: 0.026909 memory: 15239 loss_kpt: 0.000562 acc_pose: 0.823919 loss: 0.000562 2022/09/14 23:16:43 - mmengine - INFO - Epoch(train) [96][150/586] lr: 5.000000e-04 eta: 8:18:06 time: 0.477731 data_time: 0.028937 memory: 15239 loss_kpt: 0.000530 acc_pose: 0.910875 loss: 0.000530 2022/09/14 23:17:06 - mmengine - INFO - Epoch(train) [96][200/586] lr: 5.000000e-04 eta: 8:17:45 time: 0.469402 data_time: 0.025738 memory: 15239 loss_kpt: 0.000548 acc_pose: 0.878207 loss: 0.000548 2022/09/14 23:17:31 - mmengine - INFO - Epoch(train) [96][250/586] lr: 5.000000e-04 eta: 8:17:26 time: 0.485886 data_time: 0.026187 memory: 15239 loss_kpt: 0.000552 acc_pose: 0.834869 loss: 0.000552 2022/09/14 23:17:54 - mmengine - INFO - Epoch(train) [96][300/586] lr: 5.000000e-04 eta: 8:17:05 time: 0.474661 data_time: 0.027698 memory: 15239 loss_kpt: 0.000549 acc_pose: 0.845230 loss: 0.000549 2022/09/14 23:18:08 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 23:18:18 - mmengine - INFO - Epoch(train) [96][350/586] lr: 5.000000e-04 eta: 8:16:44 time: 0.467978 data_time: 0.027361 memory: 15239 loss_kpt: 0.000565 acc_pose: 0.830103 loss: 0.000565 2022/09/14 23:18:41 - mmengine - INFO - Epoch(train) [96][400/586] lr: 5.000000e-04 eta: 8:16:24 time: 0.468221 data_time: 0.026401 memory: 15239 loss_kpt: 0.000547 acc_pose: 0.846714 loss: 0.000547 2022/09/14 23:19:05 - mmengine - INFO - Epoch(train) [96][450/586] lr: 5.000000e-04 eta: 8:16:03 time: 0.474262 data_time: 0.025725 memory: 15239 loss_kpt: 0.000548 acc_pose: 0.864877 loss: 0.000548 2022/09/14 23:19:28 - mmengine - INFO - Epoch(train) [96][500/586] lr: 5.000000e-04 eta: 8:15:42 time: 0.471422 data_time: 0.026186 memory: 15239 loss_kpt: 0.000544 acc_pose: 0.853150 loss: 0.000544 2022/09/14 23:19:52 - mmengine - INFO - Epoch(train) [96][550/586] lr: 5.000000e-04 eta: 8:15:22 time: 0.466875 data_time: 0.027247 memory: 15239 loss_kpt: 0.000580 acc_pose: 0.877011 loss: 0.000580 2022/09/14 23:20:09 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 23:20:09 - mmengine - INFO - Saving checkpoint at 96 epochs 2022/09/14 23:20:39 - mmengine - INFO - Epoch(train) [97][50/586] lr: 5.000000e-04 eta: 8:14:26 time: 0.475618 data_time: 0.035245 memory: 15239 loss_kpt: 0.000561 acc_pose: 0.828619 loss: 0.000561 2022/09/14 23:21:03 - mmengine - INFO - Epoch(train) [97][100/586] lr: 5.000000e-04 eta: 8:14:06 time: 0.473691 data_time: 0.031753 memory: 15239 loss_kpt: 0.000576 acc_pose: 0.812397 loss: 0.000576 2022/09/14 23:21:26 - mmengine - INFO - Epoch(train) [97][150/586] lr: 5.000000e-04 eta: 8:13:45 time: 0.473802 data_time: 0.027686 memory: 15239 loss_kpt: 0.000558 acc_pose: 0.848155 loss: 0.000558 2022/09/14 23:21:50 - mmengine - INFO - Epoch(train) [97][200/586] lr: 5.000000e-04 eta: 8:13:25 time: 0.473668 data_time: 0.030811 memory: 15239 loss_kpt: 0.000565 acc_pose: 0.797718 loss: 0.000565 2022/09/14 23:22:13 - mmengine - INFO - Epoch(train) [97][250/586] lr: 5.000000e-04 eta: 8:13:04 time: 0.465808 data_time: 0.027242 memory: 15239 loss_kpt: 0.000547 acc_pose: 0.807556 loss: 0.000547 2022/09/14 23:22:37 - mmengine - INFO - Epoch(train) [97][300/586] lr: 5.000000e-04 eta: 8:12:43 time: 0.472345 data_time: 0.025669 memory: 15239 loss_kpt: 0.000537 acc_pose: 0.822786 loss: 0.000537 2022/09/14 23:23:00 - mmengine - INFO - Epoch(train) [97][350/586] lr: 5.000000e-04 eta: 8:12:22 time: 0.467265 data_time: 0.026635 memory: 15239 loss_kpt: 0.000545 acc_pose: 0.945066 loss: 0.000545 2022/09/14 23:23:24 - mmengine - INFO - Epoch(train) [97][400/586] lr: 5.000000e-04 eta: 8:12:01 time: 0.464058 data_time: 0.026460 memory: 15239 loss_kpt: 0.000549 acc_pose: 0.815908 loss: 0.000549 2022/09/14 23:23:47 - mmengine - INFO - Epoch(train) [97][450/586] lr: 5.000000e-04 eta: 8:11:40 time: 0.469329 data_time: 0.026622 memory: 15239 loss_kpt: 0.000564 acc_pose: 0.860500 loss: 0.000564 2022/09/14 23:24:10 - mmengine - INFO - Epoch(train) [97][500/586] lr: 5.000000e-04 eta: 8:11:19 time: 0.464914 data_time: 0.031975 memory: 15239 loss_kpt: 0.000553 acc_pose: 0.821601 loss: 0.000553 2022/09/14 23:24:34 - mmengine - INFO - Epoch(train) [97][550/586] lr: 5.000000e-04 eta: 8:10:58 time: 0.467453 data_time: 0.025825 memory: 15239 loss_kpt: 0.000547 acc_pose: 0.874122 loss: 0.000547 2022/09/14 23:24:51 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 23:24:51 - mmengine - INFO - Saving checkpoint at 97 epochs 2022/09/14 23:25:22 - mmengine - INFO - Epoch(train) [98][50/586] lr: 5.000000e-04 eta: 8:10:03 time: 0.475436 data_time: 0.033852 memory: 15239 loss_kpt: 0.000564 acc_pose: 0.811529 loss: 0.000564 2022/09/14 23:25:45 - mmengine - INFO - Epoch(train) [98][100/586] lr: 5.000000e-04 eta: 8:09:42 time: 0.464500 data_time: 0.026504 memory: 15239 loss_kpt: 0.000559 acc_pose: 0.853986 loss: 0.000559 2022/09/14 23:26:09 - mmengine - INFO - Epoch(train) [98][150/586] lr: 5.000000e-04 eta: 8:09:22 time: 0.475316 data_time: 0.026801 memory: 15239 loss_kpt: 0.000539 acc_pose: 0.890248 loss: 0.000539 2022/09/14 23:26:13 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 23:26:32 - mmengine - INFO - Epoch(train) [98][200/586] lr: 5.000000e-04 eta: 8:09:01 time: 0.466065 data_time: 0.026227 memory: 15239 loss_kpt: 0.000546 acc_pose: 0.873120 loss: 0.000546 2022/09/14 23:26:55 - mmengine - INFO - Epoch(train) [98][250/586] lr: 5.000000e-04 eta: 8:08:40 time: 0.463882 data_time: 0.027439 memory: 15239 loss_kpt: 0.000547 acc_pose: 0.814016 loss: 0.000547 2022/09/14 23:27:19 - mmengine - INFO - Epoch(train) [98][300/586] lr: 5.000000e-04 eta: 8:08:19 time: 0.467867 data_time: 0.026079 memory: 15239 loss_kpt: 0.000573 acc_pose: 0.857259 loss: 0.000573 2022/09/14 23:27:42 - mmengine - INFO - Epoch(train) [98][350/586] lr: 5.000000e-04 eta: 8:07:58 time: 0.464795 data_time: 0.025999 memory: 15239 loss_kpt: 0.000543 acc_pose: 0.841885 loss: 0.000543 2022/09/14 23:28:05 - mmengine - INFO - Epoch(train) [98][400/586] lr: 5.000000e-04 eta: 8:07:37 time: 0.462103 data_time: 0.026155 memory: 15239 loss_kpt: 0.000568 acc_pose: 0.841101 loss: 0.000568 2022/09/14 23:28:29 - mmengine - INFO - Epoch(train) [98][450/586] lr: 5.000000e-04 eta: 8:07:16 time: 0.465703 data_time: 0.027139 memory: 15239 loss_kpt: 0.000557 acc_pose: 0.893421 loss: 0.000557 2022/09/14 23:28:52 - mmengine - INFO - Epoch(train) [98][500/586] lr: 5.000000e-04 eta: 8:06:55 time: 0.467685 data_time: 0.031866 memory: 15239 loss_kpt: 0.000553 acc_pose: 0.917781 loss: 0.000553 2022/09/14 23:29:15 - mmengine - INFO - Epoch(train) [98][550/586] lr: 5.000000e-04 eta: 8:06:34 time: 0.466320 data_time: 0.026567 memory: 15239 loss_kpt: 0.000535 acc_pose: 0.858677 loss: 0.000535 2022/09/14 23:29:32 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 23:29:32 - mmengine - INFO - Saving checkpoint at 98 epochs 2022/09/14 23:30:03 - mmengine - INFO - Epoch(train) [99][50/586] lr: 5.000000e-04 eta: 8:05:39 time: 0.482209 data_time: 0.037430 memory: 15239 loss_kpt: 0.000564 acc_pose: 0.879002 loss: 0.000564 2022/09/14 23:30:27 - mmengine - INFO - Epoch(train) [99][100/586] lr: 5.000000e-04 eta: 8:05:19 time: 0.471278 data_time: 0.027056 memory: 15239 loss_kpt: 0.000543 acc_pose: 0.816838 loss: 0.000543 2022/09/14 23:30:50 - mmengine - INFO - Epoch(train) [99][150/586] lr: 5.000000e-04 eta: 8:04:58 time: 0.467484 data_time: 0.025378 memory: 15239 loss_kpt: 0.000543 acc_pose: 0.861555 loss: 0.000543 2022/09/14 23:31:14 - mmengine - INFO - Epoch(train) [99][200/586] lr: 5.000000e-04 eta: 8:04:37 time: 0.465500 data_time: 0.026141 memory: 15239 loss_kpt: 0.000575 acc_pose: 0.855412 loss: 0.000575 2022/09/14 23:31:37 - mmengine - INFO - Epoch(train) [99][250/586] lr: 5.000000e-04 eta: 8:04:16 time: 0.466936 data_time: 0.027008 memory: 15239 loss_kpt: 0.000547 acc_pose: 0.855019 loss: 0.000547 2022/09/14 23:32:00 - mmengine - INFO - Epoch(train) [99][300/586] lr: 5.000000e-04 eta: 8:03:55 time: 0.462648 data_time: 0.027213 memory: 15239 loss_kpt: 0.000548 acc_pose: 0.815207 loss: 0.000548 2022/09/14 23:32:24 - mmengine - INFO - Epoch(train) [99][350/586] lr: 5.000000e-04 eta: 8:03:34 time: 0.473459 data_time: 0.026333 memory: 15239 loss_kpt: 0.000558 acc_pose: 0.803761 loss: 0.000558 2022/09/14 23:32:47 - mmengine - INFO - Epoch(train) [99][400/586] lr: 5.000000e-04 eta: 8:03:13 time: 0.469281 data_time: 0.031866 memory: 15239 loss_kpt: 0.000541 acc_pose: 0.854341 loss: 0.000541 2022/09/14 23:33:11 - mmengine - INFO - Epoch(train) [99][450/586] lr: 5.000000e-04 eta: 8:02:53 time: 0.475780 data_time: 0.027874 memory: 15239 loss_kpt: 0.000540 acc_pose: 0.866695 loss: 0.000540 2022/09/14 23:33:35 - mmengine - INFO - Epoch(train) [99][500/586] lr: 5.000000e-04 eta: 8:02:32 time: 0.468765 data_time: 0.026599 memory: 15239 loss_kpt: 0.000544 acc_pose: 0.784261 loss: 0.000544 2022/09/14 23:33:58 - mmengine - INFO - Epoch(train) [99][550/586] lr: 5.000000e-04 eta: 8:02:11 time: 0.465424 data_time: 0.029413 memory: 15239 loss_kpt: 0.000579 acc_pose: 0.841097 loss: 0.000579 2022/09/14 23:34:08 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 23:34:15 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 23:34:15 - mmengine - INFO - Saving checkpoint at 99 epochs 2022/09/14 23:34:47 - mmengine - INFO - Epoch(train) [100][50/586] lr: 5.000000e-04 eta: 8:01:17 time: 0.490222 data_time: 0.038315 memory: 15239 loss_kpt: 0.000566 acc_pose: 0.800425 loss: 0.000566 2022/09/14 23:35:11 - mmengine - INFO - Epoch(train) [100][100/586] lr: 5.000000e-04 eta: 8:00:56 time: 0.466825 data_time: 0.026219 memory: 15239 loss_kpt: 0.000547 acc_pose: 0.876154 loss: 0.000547 2022/09/14 23:35:34 - mmengine - INFO - Epoch(train) [100][150/586] lr: 5.000000e-04 eta: 8:00:36 time: 0.474110 data_time: 0.027069 memory: 15239 loss_kpt: 0.000545 acc_pose: 0.853060 loss: 0.000545 2022/09/14 23:35:58 - mmengine - INFO - Epoch(train) [100][200/586] lr: 5.000000e-04 eta: 8:00:15 time: 0.466398 data_time: 0.030410 memory: 15239 loss_kpt: 0.000544 acc_pose: 0.844999 loss: 0.000544 2022/09/14 23:36:21 - mmengine - INFO - Epoch(train) [100][250/586] lr: 5.000000e-04 eta: 7:59:54 time: 0.462626 data_time: 0.026425 memory: 15239 loss_kpt: 0.000542 acc_pose: 0.893392 loss: 0.000542 2022/09/14 23:36:45 - mmengine - INFO - Epoch(train) [100][300/586] lr: 5.000000e-04 eta: 7:59:33 time: 0.473264 data_time: 0.027321 memory: 15239 loss_kpt: 0.000550 acc_pose: 0.852622 loss: 0.000550 2022/09/14 23:37:08 - mmengine - INFO - Epoch(train) [100][350/586] lr: 5.000000e-04 eta: 7:59:12 time: 0.464079 data_time: 0.030692 memory: 15239 loss_kpt: 0.000544 acc_pose: 0.884777 loss: 0.000544 2022/09/14 23:37:31 - mmengine - INFO - Epoch(train) [100][400/586] lr: 5.000000e-04 eta: 7:58:51 time: 0.462531 data_time: 0.027104 memory: 15239 loss_kpt: 0.000541 acc_pose: 0.903250 loss: 0.000541 2022/09/14 23:37:55 - mmengine - INFO - Epoch(train) [100][450/586] lr: 5.000000e-04 eta: 7:58:30 time: 0.479526 data_time: 0.029853 memory: 15239 loss_kpt: 0.000538 acc_pose: 0.777319 loss: 0.000538 2022/09/14 23:38:18 - mmengine - INFO - Epoch(train) [100][500/586] lr: 5.000000e-04 eta: 7:58:09 time: 0.465748 data_time: 0.025811 memory: 15239 loss_kpt: 0.000548 acc_pose: 0.916518 loss: 0.000548 2022/09/14 23:38:41 - mmengine - INFO - Epoch(train) [100][550/586] lr: 5.000000e-04 eta: 7:57:48 time: 0.462732 data_time: 0.027495 memory: 15239 loss_kpt: 0.000569 acc_pose: 0.867998 loss: 0.000569 2022/09/14 23:38:58 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 23:38:58 - mmengine - INFO - Saving checkpoint at 100 epochs 2022/09/14 23:39:17 - mmengine - INFO - Epoch(val) [100][50/407] eta: 0:01:13 time: 0.206895 data_time: 0.020527 memory: 15239 2022/09/14 23:39:27 - mmengine - INFO - Epoch(val) [100][100/407] eta: 0:00:59 time: 0.194214 data_time: 0.008594 memory: 2064 2022/09/14 23:39:37 - mmengine - INFO - Epoch(val) [100][150/407] eta: 0:00:49 time: 0.194138 data_time: 0.008673 memory: 2064 2022/09/14 23:39:46 - mmengine - INFO - Epoch(val) [100][200/407] eta: 0:00:40 time: 0.194805 data_time: 0.008773 memory: 2064 2022/09/14 23:39:56 - mmengine - INFO - Epoch(val) [100][250/407] eta: 0:00:31 time: 0.199842 data_time: 0.014096 memory: 2064 2022/09/14 23:40:06 - mmengine - INFO - Epoch(val) [100][300/407] eta: 0:00:20 time: 0.195088 data_time: 0.008779 memory: 2064 2022/09/14 23:40:16 - mmengine - INFO - Epoch(val) [100][350/407] eta: 0:00:11 time: 0.194101 data_time: 0.008513 memory: 2064 2022/09/14 23:40:25 - mmengine - INFO - Epoch(val) [100][400/407] eta: 0:00:01 time: 0.191831 data_time: 0.007801 memory: 2064 2022/09/14 23:41:03 - mmengine - INFO - Evaluating CocoMetric... 2022/09/14 23:41:18 - mmengine - INFO - Epoch(val) [100][407/407] coco/AP: 0.754373 coco/AP .5: 0.904323 coco/AP .75: 0.821756 coco/AP (M): 0.714105 coco/AP (L): 0.825797 coco/AR: 0.804266 coco/AR .5: 0.940806 coco/AR .75: 0.863193 coco/AR (M): 0.759164 coco/AR (L): 0.869974 2022/09/14 23:41:18 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220914/hrnet_w48_384/best_coco/AP_epoch_90.pth is removed 2022/09/14 23:41:21 - mmengine - INFO - The best checkpoint with 0.7544 coco/AP at 100 epoch is saved to best_coco/AP_epoch_100.pth. 2022/09/14 23:41:45 - mmengine - INFO - Epoch(train) [101][50/586] lr: 5.000000e-04 eta: 7:56:54 time: 0.476000 data_time: 0.032330 memory: 15239 loss_kpt: 0.000562 acc_pose: 0.787076 loss: 0.000562 2022/09/14 23:42:09 - mmengine - INFO - Epoch(train) [101][100/586] lr: 5.000000e-04 eta: 7:56:33 time: 0.473693 data_time: 0.028394 memory: 15239 loss_kpt: 0.000563 acc_pose: 0.854807 loss: 0.000563 2022/09/14 23:42:33 - mmengine - INFO - Epoch(train) [101][150/586] lr: 5.000000e-04 eta: 7:56:13 time: 0.474333 data_time: 0.028151 memory: 15239 loss_kpt: 0.000541 acc_pose: 0.877835 loss: 0.000541 2022/09/14 23:42:57 - mmengine - INFO - Epoch(train) [101][200/586] lr: 5.000000e-04 eta: 7:55:52 time: 0.477265 data_time: 0.026590 memory: 15239 loss_kpt: 0.000570 acc_pose: 0.895479 loss: 0.000570 2022/09/14 23:43:20 - mmengine - INFO - Epoch(train) [101][250/586] lr: 5.000000e-04 eta: 7:55:32 time: 0.472070 data_time: 0.024732 memory: 15239 loss_kpt: 0.000555 acc_pose: 0.865351 loss: 0.000555 2022/09/14 23:43:44 - mmengine - INFO - Epoch(train) [101][300/586] lr: 5.000000e-04 eta: 7:55:11 time: 0.470454 data_time: 0.025571 memory: 15239 loss_kpt: 0.000557 acc_pose: 0.863106 loss: 0.000557 2022/09/14 23:44:07 - mmengine - INFO - Epoch(train) [101][350/586] lr: 5.000000e-04 eta: 7:54:50 time: 0.466038 data_time: 0.025667 memory: 15239 loss_kpt: 0.000570 acc_pose: 0.837218 loss: 0.000570 2022/09/14 23:44:30 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 23:44:30 - mmengine - INFO - Epoch(train) [101][400/586] lr: 5.000000e-04 eta: 7:54:29 time: 0.468255 data_time: 0.026175 memory: 15239 loss_kpt: 0.000547 acc_pose: 0.821373 loss: 0.000547 2022/09/14 23:44:54 - mmengine - INFO - Epoch(train) [101][450/586] lr: 5.000000e-04 eta: 7:54:08 time: 0.469706 data_time: 0.025666 memory: 15239 loss_kpt: 0.000541 acc_pose: 0.875426 loss: 0.000541 2022/09/14 23:45:17 - mmengine - INFO - Epoch(train) [101][500/586] lr: 5.000000e-04 eta: 7:53:47 time: 0.463882 data_time: 0.025525 memory: 15239 loss_kpt: 0.000562 acc_pose: 0.801880 loss: 0.000562 2022/09/14 23:45:40 - mmengine - INFO - Epoch(train) [101][550/586] lr: 5.000000e-04 eta: 7:53:26 time: 0.466807 data_time: 0.025451 memory: 15239 loss_kpt: 0.000557 acc_pose: 0.860756 loss: 0.000557 2022/09/14 23:45:57 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 23:45:57 - mmengine - INFO - Saving checkpoint at 101 epochs 2022/09/14 23:46:28 - mmengine - INFO - Epoch(train) [102][50/586] lr: 5.000000e-04 eta: 7:52:32 time: 0.473940 data_time: 0.032824 memory: 15239 loss_kpt: 0.000560 acc_pose: 0.866613 loss: 0.000560 2022/09/14 23:46:52 - mmengine - INFO - Epoch(train) [102][100/586] lr: 5.000000e-04 eta: 7:52:12 time: 0.481001 data_time: 0.025622 memory: 15239 loss_kpt: 0.000541 acc_pose: 0.834411 loss: 0.000541 2022/09/14 23:47:15 - mmengine - INFO - Epoch(train) [102][150/586] lr: 5.000000e-04 eta: 7:51:51 time: 0.464653 data_time: 0.024921 memory: 15239 loss_kpt: 0.000535 acc_pose: 0.829042 loss: 0.000535 2022/09/14 23:47:39 - mmengine - INFO - Epoch(train) [102][200/586] lr: 5.000000e-04 eta: 7:51:30 time: 0.470057 data_time: 0.025256 memory: 15239 loss_kpt: 0.000554 acc_pose: 0.824892 loss: 0.000554 2022/09/14 23:48:02 - mmengine - INFO - Epoch(train) [102][250/586] lr: 5.000000e-04 eta: 7:51:09 time: 0.472603 data_time: 0.024929 memory: 15239 loss_kpt: 0.000550 acc_pose: 0.808807 loss: 0.000550 2022/09/14 23:48:26 - mmengine - INFO - Epoch(train) [102][300/586] lr: 5.000000e-04 eta: 7:50:49 time: 0.477265 data_time: 0.025696 memory: 15239 loss_kpt: 0.000547 acc_pose: 0.875589 loss: 0.000547 2022/09/14 23:48:49 - mmengine - INFO - Epoch(train) [102][350/586] lr: 5.000000e-04 eta: 7:50:28 time: 0.465323 data_time: 0.026440 memory: 15239 loss_kpt: 0.000539 acc_pose: 0.842258 loss: 0.000539 2022/09/14 23:49:13 - mmengine - INFO - Epoch(train) [102][400/586] lr: 5.000000e-04 eta: 7:50:07 time: 0.478917 data_time: 0.025364 memory: 15239 loss_kpt: 0.000547 acc_pose: 0.910568 loss: 0.000547 2022/09/14 23:49:37 - mmengine - INFO - Epoch(train) [102][450/586] lr: 5.000000e-04 eta: 7:49:46 time: 0.463490 data_time: 0.025477 memory: 15239 loss_kpt: 0.000558 acc_pose: 0.869687 loss: 0.000558 2022/09/14 23:50:00 - mmengine - INFO - Epoch(train) [102][500/586] lr: 5.000000e-04 eta: 7:49:25 time: 0.469219 data_time: 0.024954 memory: 15239 loss_kpt: 0.000553 acc_pose: 0.825591 loss: 0.000553 2022/09/14 23:50:24 - mmengine - INFO - Epoch(train) [102][550/586] lr: 5.000000e-04 eta: 7:49:05 time: 0.475865 data_time: 0.025575 memory: 15239 loss_kpt: 0.000576 acc_pose: 0.896764 loss: 0.000576 2022/09/14 23:50:41 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 23:50:41 - mmengine - INFO - Saving checkpoint at 102 epochs 2022/09/14 23:51:12 - mmengine - INFO - Epoch(train) [103][50/586] lr: 5.000000e-04 eta: 7:48:11 time: 0.480343 data_time: 0.030262 memory: 15239 loss_kpt: 0.000543 acc_pose: 0.865563 loss: 0.000543 2022/09/14 23:51:35 - mmengine - INFO - Epoch(train) [103][100/586] lr: 5.000000e-04 eta: 7:47:51 time: 0.470484 data_time: 0.025027 memory: 15239 loss_kpt: 0.000560 acc_pose: 0.825447 loss: 0.000560 2022/09/14 23:51:58 - mmengine - INFO - Epoch(train) [103][150/586] lr: 5.000000e-04 eta: 7:47:30 time: 0.468200 data_time: 0.024336 memory: 15239 loss_kpt: 0.000556 acc_pose: 0.841855 loss: 0.000556 2022/09/14 23:52:22 - mmengine - INFO - Epoch(train) [103][200/586] lr: 5.000000e-04 eta: 7:47:09 time: 0.469587 data_time: 0.029185 memory: 15239 loss_kpt: 0.000569 acc_pose: 0.836178 loss: 0.000569 2022/09/14 23:52:35 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 23:52:46 - mmengine - INFO - Epoch(train) [103][250/586] lr: 5.000000e-04 eta: 7:46:48 time: 0.472246 data_time: 0.025610 memory: 15239 loss_kpt: 0.000557 acc_pose: 0.831135 loss: 0.000557 2022/09/14 23:53:09 - mmengine - INFO - Epoch(train) [103][300/586] lr: 5.000000e-04 eta: 7:46:27 time: 0.465734 data_time: 0.025883 memory: 15239 loss_kpt: 0.000572 acc_pose: 0.763198 loss: 0.000572 2022/09/14 23:53:33 - mmengine - INFO - Epoch(train) [103][350/586] lr: 5.000000e-04 eta: 7:46:06 time: 0.473477 data_time: 0.025587 memory: 15239 loss_kpt: 0.000561 acc_pose: 0.776290 loss: 0.000561 2022/09/14 23:53:56 - mmengine - INFO - Epoch(train) [103][400/586] lr: 5.000000e-04 eta: 7:45:45 time: 0.472045 data_time: 0.025308 memory: 15239 loss_kpt: 0.000545 acc_pose: 0.793899 loss: 0.000545 2022/09/14 23:54:20 - mmengine - INFO - Epoch(train) [103][450/586] lr: 5.000000e-04 eta: 7:45:24 time: 0.467326 data_time: 0.025763 memory: 15239 loss_kpt: 0.000552 acc_pose: 0.895906 loss: 0.000552 2022/09/14 23:54:43 - mmengine - INFO - Epoch(train) [103][500/586] lr: 5.000000e-04 eta: 7:45:03 time: 0.469974 data_time: 0.025363 memory: 15239 loss_kpt: 0.000552 acc_pose: 0.825609 loss: 0.000552 2022/09/14 23:55:06 - mmengine - INFO - Epoch(train) [103][550/586] lr: 5.000000e-04 eta: 7:44:42 time: 0.466016 data_time: 0.025693 memory: 15239 loss_kpt: 0.000549 acc_pose: 0.911994 loss: 0.000549 2022/09/14 23:55:23 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/14 23:55:23 - mmengine - INFO - Saving checkpoint at 103 epochs 2022/09/14 23:55:54 - mmengine - INFO - Epoch(train) [104][50/586] lr: 5.000000e-04 eta: 7:43:49 time: 0.468532 data_time: 0.034653 memory: 15239 loss_kpt: 0.000541 acc_pose: 0.919064 loss: 0.000541 2022/09/14 23:56:17 - mmengine - INFO - Epoch(train) [104][100/586] lr: 5.000000e-04 eta: 7:43:28 time: 0.474958 data_time: 0.034511 memory: 15239 loss_kpt: 0.000551 acc_pose: 0.876916 loss: 0.000551 2022/09/14 23:56:41 - mmengine - INFO - Epoch(train) [104][150/586] lr: 5.000000e-04 eta: 7:43:08 time: 0.473642 data_time: 0.029056 memory: 15239 loss_kpt: 0.000548 acc_pose: 0.836952 loss: 0.000548 2022/09/14 23:57:05 - mmengine - INFO - Epoch(train) [104][200/586] lr: 5.000000e-04 eta: 7:42:47 time: 0.477689 data_time: 0.031763 memory: 15239 loss_kpt: 0.000566 acc_pose: 0.858172 loss: 0.000566 2022/09/14 23:57:29 - mmengine - INFO - Epoch(train) [104][250/586] lr: 5.000000e-04 eta: 7:42:26 time: 0.472936 data_time: 0.025347 memory: 15239 loss_kpt: 0.000544 acc_pose: 0.801765 loss: 0.000544 2022/09/14 23:57:52 - mmengine - INFO - Epoch(train) [104][300/586] lr: 5.000000e-04 eta: 7:42:06 time: 0.475926 data_time: 0.025620 memory: 15239 loss_kpt: 0.000548 acc_pose: 0.800784 loss: 0.000548 2022/09/14 23:58:16 - mmengine - INFO - Epoch(train) [104][350/586] lr: 5.000000e-04 eta: 7:41:45 time: 0.477577 data_time: 0.026855 memory: 15239 loss_kpt: 0.000546 acc_pose: 0.916156 loss: 0.000546 2022/09/14 23:58:39 - mmengine - INFO - Epoch(train) [104][400/586] lr: 5.000000e-04 eta: 7:41:24 time: 0.463409 data_time: 0.025414 memory: 15239 loss_kpt: 0.000564 acc_pose: 0.816130 loss: 0.000564 2022/09/14 23:59:03 - mmengine - INFO - Epoch(train) [104][450/586] lr: 5.000000e-04 eta: 7:41:03 time: 0.471522 data_time: 0.025401 memory: 15239 loss_kpt: 0.000553 acc_pose: 0.862458 loss: 0.000553 2022/09/14 23:59:26 - mmengine - INFO - Epoch(train) [104][500/586] lr: 5.000000e-04 eta: 7:40:42 time: 0.464796 data_time: 0.025817 memory: 15239 loss_kpt: 0.000516 acc_pose: 0.894496 loss: 0.000516 2022/09/14 23:59:50 - mmengine - INFO - Epoch(train) [104][550/586] lr: 5.000000e-04 eta: 7:40:21 time: 0.478791 data_time: 0.025003 memory: 15239 loss_kpt: 0.000550 acc_pose: 0.866358 loss: 0.000550 2022/09/15 00:00:09 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 00:00:09 - mmengine - INFO - Saving checkpoint at 104 epochs 2022/09/15 00:00:40 - mmengine - INFO - Epoch(train) [105][50/586] lr: 5.000000e-04 eta: 7:39:29 time: 0.474333 data_time: 0.030768 memory: 15239 loss_kpt: 0.000556 acc_pose: 0.871303 loss: 0.000556 2022/09/15 00:00:43 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 00:01:03 - mmengine - INFO - Epoch(train) [105][100/586] lr: 5.000000e-04 eta: 7:39:08 time: 0.473805 data_time: 0.025818 memory: 15239 loss_kpt: 0.000557 acc_pose: 0.857674 loss: 0.000557 2022/09/15 00:01:27 - mmengine - INFO - Epoch(train) [105][150/586] lr: 5.000000e-04 eta: 7:38:47 time: 0.474626 data_time: 0.030255 memory: 15239 loss_kpt: 0.000558 acc_pose: 0.895376 loss: 0.000558 2022/09/15 00:01:51 - mmengine - INFO - Epoch(train) [105][200/586] lr: 5.000000e-04 eta: 7:38:27 time: 0.481402 data_time: 0.025113 memory: 15239 loss_kpt: 0.000560 acc_pose: 0.777041 loss: 0.000560 2022/09/15 00:02:15 - mmengine - INFO - Epoch(train) [105][250/586] lr: 5.000000e-04 eta: 7:38:06 time: 0.472507 data_time: 0.024898 memory: 15239 loss_kpt: 0.000545 acc_pose: 0.808253 loss: 0.000545 2022/09/15 00:02:38 - mmengine - INFO - Epoch(train) [105][300/586] lr: 5.000000e-04 eta: 7:37:45 time: 0.467157 data_time: 0.025228 memory: 15239 loss_kpt: 0.000557 acc_pose: 0.766834 loss: 0.000557 2022/09/15 00:03:02 - mmengine - INFO - Epoch(train) [105][350/586] lr: 5.000000e-04 eta: 7:37:24 time: 0.467766 data_time: 0.025352 memory: 15239 loss_kpt: 0.000549 acc_pose: 0.863703 loss: 0.000549 2022/09/15 00:03:25 - mmengine - INFO - Epoch(train) [105][400/586] lr: 5.000000e-04 eta: 7:37:03 time: 0.470528 data_time: 0.025830 memory: 15239 loss_kpt: 0.000532 acc_pose: 0.802405 loss: 0.000532 2022/09/15 00:03:49 - mmengine - INFO - Epoch(train) [105][450/586] lr: 5.000000e-04 eta: 7:36:42 time: 0.471946 data_time: 0.028639 memory: 15239 loss_kpt: 0.000544 acc_pose: 0.908742 loss: 0.000544 2022/09/15 00:04:12 - mmengine - INFO - Epoch(train) [105][500/586] lr: 5.000000e-04 eta: 7:36:21 time: 0.468875 data_time: 0.024949 memory: 15239 loss_kpt: 0.000541 acc_pose: 0.877858 loss: 0.000541 2022/09/15 00:04:36 - mmengine - INFO - Epoch(train) [105][550/586] lr: 5.000000e-04 eta: 7:36:00 time: 0.472241 data_time: 0.025234 memory: 15239 loss_kpt: 0.000560 acc_pose: 0.888454 loss: 0.000560 2022/09/15 00:04:52 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 00:04:52 - mmengine - INFO - Saving checkpoint at 105 epochs 2022/09/15 00:05:23 - mmengine - INFO - Epoch(train) [106][50/586] lr: 5.000000e-04 eta: 7:35:08 time: 0.471438 data_time: 0.031080 memory: 15239 loss_kpt: 0.000550 acc_pose: 0.847670 loss: 0.000550 2022/09/15 00:05:46 - mmengine - INFO - Epoch(train) [106][100/586] lr: 5.000000e-04 eta: 7:34:47 time: 0.475011 data_time: 0.025417 memory: 15239 loss_kpt: 0.000554 acc_pose: 0.875589 loss: 0.000554 2022/09/15 00:06:10 - mmengine - INFO - Epoch(train) [106][150/586] lr: 5.000000e-04 eta: 7:34:26 time: 0.466611 data_time: 0.026634 memory: 15239 loss_kpt: 0.000561 acc_pose: 0.805909 loss: 0.000561 2022/09/15 00:06:33 - mmengine - INFO - Epoch(train) [106][200/586] lr: 5.000000e-04 eta: 7:34:05 time: 0.468341 data_time: 0.024876 memory: 15239 loss_kpt: 0.000557 acc_pose: 0.846005 loss: 0.000557 2022/09/15 00:06:57 - mmengine - INFO - Epoch(train) [106][250/586] lr: 5.000000e-04 eta: 7:33:44 time: 0.478523 data_time: 0.025080 memory: 15239 loss_kpt: 0.000535 acc_pose: 0.898910 loss: 0.000535 2022/09/15 00:07:20 - mmengine - INFO - Epoch(train) [106][300/586] lr: 5.000000e-04 eta: 7:33:23 time: 0.466852 data_time: 0.026168 memory: 15239 loss_kpt: 0.000557 acc_pose: 0.861313 loss: 0.000557 2022/09/15 00:07:44 - mmengine - INFO - Epoch(train) [106][350/586] lr: 5.000000e-04 eta: 7:33:02 time: 0.467089 data_time: 0.025118 memory: 15239 loss_kpt: 0.000552 acc_pose: 0.889086 loss: 0.000552 2022/09/15 00:08:07 - mmengine - INFO - Epoch(train) [106][400/586] lr: 5.000000e-04 eta: 7:32:41 time: 0.472083 data_time: 0.029883 memory: 15239 loss_kpt: 0.000544 acc_pose: 0.869380 loss: 0.000544 2022/09/15 00:08:31 - mmengine - INFO - Epoch(train) [106][450/586] lr: 5.000000e-04 eta: 7:32:21 time: 0.474710 data_time: 0.025790 memory: 15239 loss_kpt: 0.000548 acc_pose: 0.874128 loss: 0.000548 2022/09/15 00:08:40 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 00:08:54 - mmengine - INFO - Epoch(train) [106][500/586] lr: 5.000000e-04 eta: 7:31:59 time: 0.457405 data_time: 0.024854 memory: 15239 loss_kpt: 0.000566 acc_pose: 0.867214 loss: 0.000566 2022/09/15 00:09:18 - mmengine - INFO - Epoch(train) [106][550/586] lr: 5.000000e-04 eta: 7:31:38 time: 0.472507 data_time: 0.024585 memory: 15239 loss_kpt: 0.000544 acc_pose: 0.869605 loss: 0.000544 2022/09/15 00:09:34 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 00:09:34 - mmengine - INFO - Saving checkpoint at 106 epochs 2022/09/15 00:10:05 - mmengine - INFO - Epoch(train) [107][50/586] lr: 5.000000e-04 eta: 7:30:46 time: 0.473299 data_time: 0.030133 memory: 15239 loss_kpt: 0.000536 acc_pose: 0.872127 loss: 0.000536 2022/09/15 00:10:29 - mmengine - INFO - Epoch(train) [107][100/586] lr: 5.000000e-04 eta: 7:30:25 time: 0.481013 data_time: 0.025723 memory: 15239 loss_kpt: 0.000573 acc_pose: 0.884070 loss: 0.000573 2022/09/15 00:10:52 - mmengine - INFO - Epoch(train) [107][150/586] lr: 5.000000e-04 eta: 7:30:04 time: 0.462559 data_time: 0.024801 memory: 15239 loss_kpt: 0.000546 acc_pose: 0.856975 loss: 0.000546 2022/09/15 00:11:16 - mmengine - INFO - Epoch(train) [107][200/586] lr: 5.000000e-04 eta: 7:29:43 time: 0.478589 data_time: 0.028362 memory: 15239 loss_kpt: 0.000548 acc_pose: 0.779536 loss: 0.000548 2022/09/15 00:11:40 - mmengine - INFO - Epoch(train) [107][250/586] lr: 5.000000e-04 eta: 7:29:23 time: 0.474367 data_time: 0.025037 memory: 15239 loss_kpt: 0.000546 acc_pose: 0.865319 loss: 0.000546 2022/09/15 00:12:03 - mmengine - INFO - Epoch(train) [107][300/586] lr: 5.000000e-04 eta: 7:29:02 time: 0.467567 data_time: 0.026116 memory: 15239 loss_kpt: 0.000559 acc_pose: 0.847718 loss: 0.000559 2022/09/15 00:12:27 - mmengine - INFO - Epoch(train) [107][350/586] lr: 5.000000e-04 eta: 7:28:41 time: 0.480176 data_time: 0.025109 memory: 15239 loss_kpt: 0.000544 acc_pose: 0.826719 loss: 0.000544 2022/09/15 00:12:51 - mmengine - INFO - Epoch(train) [107][400/586] lr: 5.000000e-04 eta: 7:28:20 time: 0.476778 data_time: 0.025256 memory: 15239 loss_kpt: 0.000524 acc_pose: 0.891162 loss: 0.000524 2022/09/15 00:13:15 - mmengine - INFO - Epoch(train) [107][450/586] lr: 5.000000e-04 eta: 7:27:59 time: 0.469132 data_time: 0.026331 memory: 15239 loss_kpt: 0.000562 acc_pose: 0.849836 loss: 0.000562 2022/09/15 00:13:38 - mmengine - INFO - Epoch(train) [107][500/586] lr: 5.000000e-04 eta: 7:27:39 time: 0.473257 data_time: 0.028083 memory: 15239 loss_kpt: 0.000543 acc_pose: 0.878105 loss: 0.000543 2022/09/15 00:14:02 - mmengine - INFO - Epoch(train) [107][550/586] lr: 5.000000e-04 eta: 7:27:17 time: 0.466149 data_time: 0.025111 memory: 15239 loss_kpt: 0.000570 acc_pose: 0.908553 loss: 0.000570 2022/09/15 00:14:18 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 00:14:18 - mmengine - INFO - Saving checkpoint at 107 epochs 2022/09/15 00:14:50 - mmengine - INFO - Epoch(train) [108][50/586] lr: 5.000000e-04 eta: 7:26:26 time: 0.488752 data_time: 0.034373 memory: 15239 loss_kpt: 0.000550 acc_pose: 0.782718 loss: 0.000550 2022/09/15 00:15:13 - mmengine - INFO - Epoch(train) [108][100/586] lr: 5.000000e-04 eta: 7:26:05 time: 0.463811 data_time: 0.024422 memory: 15239 loss_kpt: 0.000551 acc_pose: 0.862916 loss: 0.000551 2022/09/15 00:15:36 - mmengine - INFO - Epoch(train) [108][150/586] lr: 5.000000e-04 eta: 7:25:44 time: 0.473303 data_time: 0.025231 memory: 15239 loss_kpt: 0.000562 acc_pose: 0.882804 loss: 0.000562 2022/09/15 00:16:00 - mmengine - INFO - Epoch(train) [108][200/586] lr: 5.000000e-04 eta: 7:25:23 time: 0.471232 data_time: 0.025303 memory: 15239 loss_kpt: 0.000534 acc_pose: 0.852468 loss: 0.000534 2022/09/15 00:16:23 - mmengine - INFO - Epoch(train) [108][250/586] lr: 5.000000e-04 eta: 7:25:02 time: 0.465325 data_time: 0.028584 memory: 15239 loss_kpt: 0.000538 acc_pose: 0.862234 loss: 0.000538 2022/09/15 00:16:46 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 00:16:46 - mmengine - INFO - Epoch(train) [108][300/586] lr: 5.000000e-04 eta: 7:24:40 time: 0.462415 data_time: 0.025036 memory: 15239 loss_kpt: 0.000552 acc_pose: 0.862846 loss: 0.000552 2022/09/15 00:17:10 - mmengine - INFO - Epoch(train) [108][350/586] lr: 5.000000e-04 eta: 7:24:19 time: 0.467097 data_time: 0.024583 memory: 15239 loss_kpt: 0.000550 acc_pose: 0.820987 loss: 0.000550 2022/09/15 00:17:33 - mmengine - INFO - Epoch(train) [108][400/586] lr: 5.000000e-04 eta: 7:23:58 time: 0.469019 data_time: 0.025268 memory: 15239 loss_kpt: 0.000537 acc_pose: 0.853360 loss: 0.000537 2022/09/15 00:17:57 - mmengine - INFO - Epoch(train) [108][450/586] lr: 5.000000e-04 eta: 7:23:37 time: 0.466695 data_time: 0.025597 memory: 15239 loss_kpt: 0.000544 acc_pose: 0.813152 loss: 0.000544 2022/09/15 00:18:20 - mmengine - INFO - Epoch(train) [108][500/586] lr: 5.000000e-04 eta: 7:23:16 time: 0.472186 data_time: 0.024729 memory: 15239 loss_kpt: 0.000546 acc_pose: 0.821719 loss: 0.000546 2022/09/15 00:18:44 - mmengine - INFO - Epoch(train) [108][550/586] lr: 5.000000e-04 eta: 7:22:55 time: 0.470013 data_time: 0.025880 memory: 15239 loss_kpt: 0.000549 acc_pose: 0.898699 loss: 0.000549 2022/09/15 00:19:00 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 00:19:00 - mmengine - INFO - Saving checkpoint at 108 epochs 2022/09/15 00:19:31 - mmengine - INFO - Epoch(train) [109][50/586] lr: 5.000000e-04 eta: 7:22:04 time: 0.482841 data_time: 0.031535 memory: 15239 loss_kpt: 0.000532 acc_pose: 0.853085 loss: 0.000532 2022/09/15 00:19:55 - mmengine - INFO - Epoch(train) [109][100/586] lr: 5.000000e-04 eta: 7:21:43 time: 0.465453 data_time: 0.026087 memory: 15239 loss_kpt: 0.000549 acc_pose: 0.844595 loss: 0.000549 2022/09/15 00:20:18 - mmengine - INFO - Epoch(train) [109][150/586] lr: 5.000000e-04 eta: 7:21:21 time: 0.468242 data_time: 0.025242 memory: 15239 loss_kpt: 0.000552 acc_pose: 0.872381 loss: 0.000552 2022/09/15 00:20:42 - mmengine - INFO - Epoch(train) [109][200/586] lr: 5.000000e-04 eta: 7:21:00 time: 0.469144 data_time: 0.024860 memory: 15239 loss_kpt: 0.000539 acc_pose: 0.894607 loss: 0.000539 2022/09/15 00:21:05 - mmengine - INFO - Epoch(train) [109][250/586] lr: 5.000000e-04 eta: 7:20:39 time: 0.471286 data_time: 0.026231 memory: 15239 loss_kpt: 0.000532 acc_pose: 0.882872 loss: 0.000532 2022/09/15 00:21:29 - mmengine - INFO - Epoch(train) [109][300/586] lr: 5.000000e-04 eta: 7:20:18 time: 0.467651 data_time: 0.026279 memory: 15239 loss_kpt: 0.000537 acc_pose: 0.848100 loss: 0.000537 2022/09/15 00:21:52 - mmengine - INFO - Epoch(train) [109][350/586] lr: 5.000000e-04 eta: 7:19:57 time: 0.469126 data_time: 0.025789 memory: 15239 loss_kpt: 0.000529 acc_pose: 0.863706 loss: 0.000529 2022/09/15 00:22:16 - mmengine - INFO - Epoch(train) [109][400/586] lr: 5.000000e-04 eta: 7:19:36 time: 0.470550 data_time: 0.024607 memory: 15239 loss_kpt: 0.000542 acc_pose: 0.879787 loss: 0.000542 2022/09/15 00:22:39 - mmengine - INFO - Epoch(train) [109][450/586] lr: 5.000000e-04 eta: 7:19:15 time: 0.470312 data_time: 0.025920 memory: 15239 loss_kpt: 0.000547 acc_pose: 0.877347 loss: 0.000547 2022/09/15 00:23:03 - mmengine - INFO - Epoch(train) [109][500/586] lr: 5.000000e-04 eta: 7:18:54 time: 0.473830 data_time: 0.025472 memory: 15239 loss_kpt: 0.000546 acc_pose: 0.810761 loss: 0.000546 2022/09/15 00:23:26 - mmengine - INFO - Epoch(train) [109][550/586] lr: 5.000000e-04 eta: 7:18:34 time: 0.471195 data_time: 0.025402 memory: 15239 loss_kpt: 0.000549 acc_pose: 0.877433 loss: 0.000549 2022/09/15 00:23:43 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 00:23:43 - mmengine - INFO - Saving checkpoint at 109 epochs 2022/09/15 00:24:14 - mmengine - INFO - Epoch(train) [110][50/586] lr: 5.000000e-04 eta: 7:17:42 time: 0.476682 data_time: 0.028424 memory: 15239 loss_kpt: 0.000554 acc_pose: 0.810980 loss: 0.000554 2022/09/15 00:24:37 - mmengine - INFO - Epoch(train) [110][100/586] lr: 5.000000e-04 eta: 7:17:21 time: 0.474734 data_time: 0.025188 memory: 15239 loss_kpt: 0.000554 acc_pose: 0.815599 loss: 0.000554 2022/09/15 00:24:49 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 00:25:01 - mmengine - INFO - Epoch(train) [110][150/586] lr: 5.000000e-04 eta: 7:17:00 time: 0.468947 data_time: 0.028438 memory: 15239 loss_kpt: 0.000562 acc_pose: 0.837214 loss: 0.000562 2022/09/15 00:25:24 - mmengine - INFO - Epoch(train) [110][200/586] lr: 5.000000e-04 eta: 7:16:39 time: 0.471861 data_time: 0.025823 memory: 15239 loss_kpt: 0.000536 acc_pose: 0.819789 loss: 0.000536 2022/09/15 00:25:48 - mmengine - INFO - Epoch(train) [110][250/586] lr: 5.000000e-04 eta: 7:16:18 time: 0.467529 data_time: 0.024141 memory: 15239 loss_kpt: 0.000536 acc_pose: 0.849266 loss: 0.000536 2022/09/15 00:26:11 - mmengine - INFO - Epoch(train) [110][300/586] lr: 5.000000e-04 eta: 7:15:57 time: 0.463752 data_time: 0.025638 memory: 15239 loss_kpt: 0.000556 acc_pose: 0.844713 loss: 0.000556 2022/09/15 00:26:34 - mmengine - INFO - Epoch(train) [110][350/586] lr: 5.000000e-04 eta: 7:15:36 time: 0.466680 data_time: 0.024571 memory: 15239 loss_kpt: 0.000546 acc_pose: 0.866049 loss: 0.000546 2022/09/15 00:26:58 - mmengine - INFO - Epoch(train) [110][400/586] lr: 5.000000e-04 eta: 7:15:15 time: 0.477144 data_time: 0.024370 memory: 15239 loss_kpt: 0.000524 acc_pose: 0.886238 loss: 0.000524 2022/09/15 00:27:21 - mmengine - INFO - Epoch(train) [110][450/586] lr: 5.000000e-04 eta: 7:14:54 time: 0.463996 data_time: 0.026078 memory: 15239 loss_kpt: 0.000561 acc_pose: 0.836299 loss: 0.000561 2022/09/15 00:27:45 - mmengine - INFO - Epoch(train) [110][500/586] lr: 5.000000e-04 eta: 7:14:33 time: 0.469196 data_time: 0.024751 memory: 15239 loss_kpt: 0.000532 acc_pose: 0.821993 loss: 0.000532 2022/09/15 00:28:09 - mmengine - INFO - Epoch(train) [110][550/586] lr: 5.000000e-04 eta: 7:14:12 time: 0.476526 data_time: 0.024662 memory: 15239 loss_kpt: 0.000563 acc_pose: 0.846723 loss: 0.000563 2022/09/15 00:28:25 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 00:28:25 - mmengine - INFO - Saving checkpoint at 110 epochs 2022/09/15 00:28:42 - mmengine - INFO - Epoch(val) [110][50/407] eta: 0:01:11 time: 0.201650 data_time: 0.014139 memory: 15239 2022/09/15 00:28:52 - mmengine - INFO - Epoch(val) [110][100/407] eta: 0:01:00 time: 0.198411 data_time: 0.009531 memory: 2064 2022/09/15 00:29:02 - mmengine - INFO - Epoch(val) [110][150/407] eta: 0:00:50 time: 0.195568 data_time: 0.008290 memory: 2064 2022/09/15 00:29:12 - mmengine - INFO - Epoch(val) [110][200/407] eta: 0:00:40 time: 0.195673 data_time: 0.008326 memory: 2064 2022/09/15 00:29:22 - mmengine - INFO - Epoch(val) [110][250/407] eta: 0:00:31 time: 0.198462 data_time: 0.011946 memory: 2064 2022/09/15 00:29:31 - mmengine - INFO - Epoch(val) [110][300/407] eta: 0:00:20 time: 0.195984 data_time: 0.008476 memory: 2064 2022/09/15 00:29:41 - mmengine - INFO - Epoch(val) [110][350/407] eta: 0:00:11 time: 0.195016 data_time: 0.008250 memory: 2064 2022/09/15 00:29:51 - mmengine - INFO - Epoch(val) [110][400/407] eta: 0:00:01 time: 0.193020 data_time: 0.007787 memory: 2064 2022/09/15 00:30:28 - mmengine - INFO - Evaluating CocoMetric... 2022/09/15 00:30:42 - mmengine - INFO - Epoch(val) [110][407/407] coco/AP: 0.759598 coco/AP .5: 0.907699 coco/AP .75: 0.826129 coco/AP (M): 0.721230 coco/AP (L): 0.828329 coco/AR: 0.808816 coco/AR .5: 0.942380 coco/AR .75: 0.869175 coco/AR (M): 0.765228 coco/AR (L): 0.872204 2022/09/15 00:30:42 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220914/hrnet_w48_384/best_coco/AP_epoch_100.pth is removed 2022/09/15 00:30:45 - mmengine - INFO - The best checkpoint with 0.7596 coco/AP at 110 epoch is saved to best_coco/AP_epoch_110.pth. 2022/09/15 00:31:09 - mmengine - INFO - Epoch(train) [111][50/586] lr: 5.000000e-04 eta: 7:13:21 time: 0.478754 data_time: 0.029451 memory: 15239 loss_kpt: 0.000564 acc_pose: 0.818164 loss: 0.000564 2022/09/15 00:31:33 - mmengine - INFO - Epoch(train) [111][100/586] lr: 5.000000e-04 eta: 7:13:00 time: 0.471583 data_time: 0.024275 memory: 15239 loss_kpt: 0.000554 acc_pose: 0.787949 loss: 0.000554 2022/09/15 00:31:57 - mmengine - INFO - Epoch(train) [111][150/586] lr: 5.000000e-04 eta: 7:12:39 time: 0.471417 data_time: 0.025256 memory: 15239 loss_kpt: 0.000553 acc_pose: 0.856133 loss: 0.000553 2022/09/15 00:32:20 - mmengine - INFO - Epoch(train) [111][200/586] lr: 5.000000e-04 eta: 7:12:17 time: 0.464130 data_time: 0.024907 memory: 15239 loss_kpt: 0.000531 acc_pose: 0.843535 loss: 0.000531 2022/09/15 00:32:44 - mmengine - INFO - Epoch(train) [111][250/586] lr: 5.000000e-04 eta: 7:11:57 time: 0.480162 data_time: 0.024038 memory: 15239 loss_kpt: 0.000543 acc_pose: 0.808833 loss: 0.000543 2022/09/15 00:33:07 - mmengine - INFO - Epoch(train) [111][300/586] lr: 5.000000e-04 eta: 7:11:35 time: 0.463060 data_time: 0.025355 memory: 15239 loss_kpt: 0.000539 acc_pose: 0.826693 loss: 0.000539 2022/09/15 00:33:31 - mmengine - INFO - Epoch(train) [111][350/586] lr: 5.000000e-04 eta: 7:11:14 time: 0.471649 data_time: 0.025116 memory: 15239 loss_kpt: 0.000557 acc_pose: 0.796978 loss: 0.000557 2022/09/15 00:33:54 - mmengine - INFO - Epoch(train) [111][400/586] lr: 5.000000e-04 eta: 7:10:54 time: 0.472958 data_time: 0.025064 memory: 15239 loss_kpt: 0.000540 acc_pose: 0.856321 loss: 0.000540 2022/09/15 00:34:17 - mmengine - INFO - Epoch(train) [111][450/586] lr: 5.000000e-04 eta: 7:10:32 time: 0.463318 data_time: 0.025541 memory: 15239 loss_kpt: 0.000534 acc_pose: 0.849060 loss: 0.000534 2022/09/15 00:34:41 - mmengine - INFO - Epoch(train) [111][500/586] lr: 5.000000e-04 eta: 7:10:11 time: 0.465705 data_time: 0.028770 memory: 15239 loss_kpt: 0.000555 acc_pose: 0.853513 loss: 0.000555 2022/09/15 00:35:00 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 00:35:04 - mmengine - INFO - Epoch(train) [111][550/586] lr: 5.000000e-04 eta: 7:09:50 time: 0.472788 data_time: 0.024713 memory: 15239 loss_kpt: 0.000537 acc_pose: 0.913225 loss: 0.000537 2022/09/15 00:35:21 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 00:35:21 - mmengine - INFO - Saving checkpoint at 111 epochs 2022/09/15 00:35:52 - mmengine - INFO - Epoch(train) [112][50/586] lr: 5.000000e-04 eta: 7:08:59 time: 0.478162 data_time: 0.035164 memory: 15239 loss_kpt: 0.000546 acc_pose: 0.859512 loss: 0.000546 2022/09/15 00:36:16 - mmengine - INFO - Epoch(train) [112][100/586] lr: 5.000000e-04 eta: 7:08:38 time: 0.480571 data_time: 0.035197 memory: 15239 loss_kpt: 0.000543 acc_pose: 0.888132 loss: 0.000543 2022/09/15 00:36:39 - mmengine - INFO - Epoch(train) [112][150/586] lr: 5.000000e-04 eta: 7:08:17 time: 0.461080 data_time: 0.031096 memory: 15239 loss_kpt: 0.000550 acc_pose: 0.879510 loss: 0.000550 2022/09/15 00:37:02 - mmengine - INFO - Epoch(train) [112][200/586] lr: 5.000000e-04 eta: 7:07:56 time: 0.470487 data_time: 0.035802 memory: 15239 loss_kpt: 0.000541 acc_pose: 0.857153 loss: 0.000541 2022/09/15 00:37:26 - mmengine - INFO - Epoch(train) [112][250/586] lr: 5.000000e-04 eta: 7:07:35 time: 0.471682 data_time: 0.030759 memory: 15239 loss_kpt: 0.000567 acc_pose: 0.855575 loss: 0.000567 2022/09/15 00:37:49 - mmengine - INFO - Epoch(train) [112][300/586] lr: 5.000000e-04 eta: 7:07:14 time: 0.467264 data_time: 0.024990 memory: 15239 loss_kpt: 0.000546 acc_pose: 0.867996 loss: 0.000546 2022/09/15 00:38:13 - mmengine - INFO - Epoch(train) [112][350/586] lr: 5.000000e-04 eta: 7:06:52 time: 0.463137 data_time: 0.025935 memory: 15239 loss_kpt: 0.000562 acc_pose: 0.906810 loss: 0.000562 2022/09/15 00:38:36 - mmengine - INFO - Epoch(train) [112][400/586] lr: 5.000000e-04 eta: 7:06:31 time: 0.469747 data_time: 0.024805 memory: 15239 loss_kpt: 0.000545 acc_pose: 0.906222 loss: 0.000545 2022/09/15 00:38:59 - mmengine - INFO - Epoch(train) [112][450/586] lr: 5.000000e-04 eta: 7:06:10 time: 0.463117 data_time: 0.025249 memory: 15239 loss_kpt: 0.000547 acc_pose: 0.842055 loss: 0.000547 2022/09/15 00:39:23 - mmengine - INFO - Epoch(train) [112][500/586] lr: 5.000000e-04 eta: 7:05:49 time: 0.473673 data_time: 0.024771 memory: 15239 loss_kpt: 0.000541 acc_pose: 0.752128 loss: 0.000541 2022/09/15 00:39:46 - mmengine - INFO - Epoch(train) [112][550/586] lr: 5.000000e-04 eta: 7:05:28 time: 0.466149 data_time: 0.025073 memory: 15239 loss_kpt: 0.000559 acc_pose: 0.827573 loss: 0.000559 2022/09/15 00:40:03 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 00:40:03 - mmengine - INFO - Saving checkpoint at 112 epochs 2022/09/15 00:40:33 - mmengine - INFO - Epoch(train) [113][50/586] lr: 5.000000e-04 eta: 7:04:37 time: 0.471752 data_time: 0.030671 memory: 15239 loss_kpt: 0.000540 acc_pose: 0.862173 loss: 0.000540 2022/09/15 00:40:57 - mmengine - INFO - Epoch(train) [113][100/586] lr: 5.000000e-04 eta: 7:04:16 time: 0.475915 data_time: 0.026405 memory: 15239 loss_kpt: 0.000530 acc_pose: 0.891101 loss: 0.000530 2022/09/15 00:41:20 - mmengine - INFO - Epoch(train) [113][150/586] lr: 5.000000e-04 eta: 7:03:55 time: 0.464078 data_time: 0.029309 memory: 15239 loss_kpt: 0.000535 acc_pose: 0.838550 loss: 0.000535 2022/09/15 00:41:44 - mmengine - INFO - Epoch(train) [113][200/586] lr: 5.000000e-04 eta: 7:03:34 time: 0.468069 data_time: 0.025376 memory: 15239 loss_kpt: 0.000555 acc_pose: 0.910679 loss: 0.000555 2022/09/15 00:42:07 - mmengine - INFO - Epoch(train) [113][250/586] lr: 5.000000e-04 eta: 7:03:12 time: 0.466597 data_time: 0.026052 memory: 15239 loss_kpt: 0.000541 acc_pose: 0.871551 loss: 0.000541 2022/09/15 00:42:30 - mmengine - INFO - Epoch(train) [113][300/586] lr: 5.000000e-04 eta: 7:02:51 time: 0.466297 data_time: 0.025442 memory: 15239 loss_kpt: 0.000550 acc_pose: 0.818671 loss: 0.000550 2022/09/15 00:42:54 - mmengine - INFO - Epoch(train) [113][350/586] lr: 5.000000e-04 eta: 7:02:30 time: 0.469591 data_time: 0.025517 memory: 15239 loss_kpt: 0.000529 acc_pose: 0.788571 loss: 0.000529 2022/09/15 00:43:02 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 00:43:17 - mmengine - INFO - Epoch(train) [113][400/586] lr: 5.000000e-04 eta: 7:02:09 time: 0.466312 data_time: 0.025397 memory: 15239 loss_kpt: 0.000546 acc_pose: 0.818276 loss: 0.000546 2022/09/15 00:43:40 - mmengine - INFO - Epoch(train) [113][450/586] lr: 5.000000e-04 eta: 7:01:47 time: 0.466541 data_time: 0.024695 memory: 15239 loss_kpt: 0.000552 acc_pose: 0.845083 loss: 0.000552 2022/09/15 00:44:04 - mmengine - INFO - Epoch(train) [113][500/586] lr: 5.000000e-04 eta: 7:01:27 time: 0.479258 data_time: 0.024509 memory: 15239 loss_kpt: 0.000547 acc_pose: 0.902206 loss: 0.000547 2022/09/15 00:44:28 - mmengine - INFO - Epoch(train) [113][550/586] lr: 5.000000e-04 eta: 7:01:06 time: 0.471654 data_time: 0.025670 memory: 15239 loss_kpt: 0.000556 acc_pose: 0.813169 loss: 0.000556 2022/09/15 00:44:45 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 00:44:45 - mmengine - INFO - Saving checkpoint at 113 epochs 2022/09/15 00:45:17 - mmengine - INFO - Epoch(train) [114][50/586] lr: 5.000000e-04 eta: 7:00:15 time: 0.476105 data_time: 0.032070 memory: 15239 loss_kpt: 0.000542 acc_pose: 0.844723 loss: 0.000542 2022/09/15 00:45:40 - mmengine - INFO - Epoch(train) [114][100/586] lr: 5.000000e-04 eta: 6:59:54 time: 0.476282 data_time: 0.028381 memory: 15239 loss_kpt: 0.000544 acc_pose: 0.880841 loss: 0.000544 2022/09/15 00:46:04 - mmengine - INFO - Epoch(train) [114][150/586] lr: 5.000000e-04 eta: 6:59:33 time: 0.463124 data_time: 0.024822 memory: 15239 loss_kpt: 0.000542 acc_pose: 0.914213 loss: 0.000542 2022/09/15 00:46:27 - mmengine - INFO - Epoch(train) [114][200/586] lr: 5.000000e-04 eta: 6:59:12 time: 0.466789 data_time: 0.024859 memory: 15239 loss_kpt: 0.000532 acc_pose: 0.811237 loss: 0.000532 2022/09/15 00:46:51 - mmengine - INFO - Epoch(train) [114][250/586] lr: 5.000000e-04 eta: 6:58:51 time: 0.477454 data_time: 0.027971 memory: 15239 loss_kpt: 0.000542 acc_pose: 0.881940 loss: 0.000542 2022/09/15 00:47:14 - mmengine - INFO - Epoch(train) [114][300/586] lr: 5.000000e-04 eta: 6:58:30 time: 0.464811 data_time: 0.024745 memory: 15239 loss_kpt: 0.000547 acc_pose: 0.816277 loss: 0.000547 2022/09/15 00:47:37 - mmengine - INFO - Epoch(train) [114][350/586] lr: 5.000000e-04 eta: 6:58:08 time: 0.460943 data_time: 0.025159 memory: 15239 loss_kpt: 0.000529 acc_pose: 0.822773 loss: 0.000529 2022/09/15 00:48:01 - mmengine - INFO - Epoch(train) [114][400/586] lr: 5.000000e-04 eta: 6:57:47 time: 0.471415 data_time: 0.024768 memory: 15239 loss_kpt: 0.000532 acc_pose: 0.817503 loss: 0.000532 2022/09/15 00:48:24 - mmengine - INFO - Epoch(train) [114][450/586] lr: 5.000000e-04 eta: 6:57:26 time: 0.467407 data_time: 0.025712 memory: 15239 loss_kpt: 0.000562 acc_pose: 0.905429 loss: 0.000562 2022/09/15 00:48:47 - mmengine - INFO - Epoch(train) [114][500/586] lr: 5.000000e-04 eta: 6:57:04 time: 0.461209 data_time: 0.025825 memory: 15239 loss_kpt: 0.000548 acc_pose: 0.845060 loss: 0.000548 2022/09/15 00:49:11 - mmengine - INFO - Epoch(train) [114][550/586] lr: 5.000000e-04 eta: 6:56:43 time: 0.471562 data_time: 0.027928 memory: 15239 loss_kpt: 0.000538 acc_pose: 0.866894 loss: 0.000538 2022/09/15 00:49:27 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 00:49:27 - mmengine - INFO - Saving checkpoint at 114 epochs 2022/09/15 00:49:59 - mmengine - INFO - Epoch(train) [115][50/586] lr: 5.000000e-04 eta: 6:55:53 time: 0.481674 data_time: 0.033751 memory: 15239 loss_kpt: 0.000558 acc_pose: 0.889420 loss: 0.000558 2022/09/15 00:50:23 - mmengine - INFO - Epoch(train) [115][100/586] lr: 5.000000e-04 eta: 6:55:32 time: 0.475591 data_time: 0.026939 memory: 15239 loss_kpt: 0.000537 acc_pose: 0.879213 loss: 0.000537 2022/09/15 00:50:46 - mmengine - INFO - Epoch(train) [115][150/586] lr: 5.000000e-04 eta: 6:55:11 time: 0.465094 data_time: 0.024539 memory: 15239 loss_kpt: 0.000536 acc_pose: 0.826736 loss: 0.000536 2022/09/15 00:51:08 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 00:51:10 - mmengine - INFO - Epoch(train) [115][200/586] lr: 5.000000e-04 eta: 6:54:50 time: 0.470902 data_time: 0.026162 memory: 15239 loss_kpt: 0.000557 acc_pose: 0.881075 loss: 0.000557 2022/09/15 00:51:33 - mmengine - INFO - Epoch(train) [115][250/586] lr: 5.000000e-04 eta: 6:54:29 time: 0.470897 data_time: 0.024963 memory: 15239 loss_kpt: 0.000543 acc_pose: 0.847970 loss: 0.000543 2022/09/15 00:51:57 - mmengine - INFO - Epoch(train) [115][300/586] lr: 5.000000e-04 eta: 6:54:08 time: 0.474326 data_time: 0.029716 memory: 15239 loss_kpt: 0.000524 acc_pose: 0.869617 loss: 0.000524 2022/09/15 00:52:20 - mmengine - INFO - Epoch(train) [115][350/586] lr: 5.000000e-04 eta: 6:53:47 time: 0.469400 data_time: 0.025637 memory: 15239 loss_kpt: 0.000531 acc_pose: 0.919507 loss: 0.000531 2022/09/15 00:52:44 - mmengine - INFO - Epoch(train) [115][400/586] lr: 5.000000e-04 eta: 6:53:26 time: 0.469719 data_time: 0.025085 memory: 15239 loss_kpt: 0.000539 acc_pose: 0.798534 loss: 0.000539 2022/09/15 00:53:07 - mmengine - INFO - Epoch(train) [115][450/586] lr: 5.000000e-04 eta: 6:53:05 time: 0.468801 data_time: 0.028648 memory: 15239 loss_kpt: 0.000534 acc_pose: 0.857119 loss: 0.000534 2022/09/15 00:53:31 - mmengine - INFO - Epoch(train) [115][500/586] lr: 5.000000e-04 eta: 6:52:43 time: 0.465773 data_time: 0.024483 memory: 15239 loss_kpt: 0.000550 acc_pose: 0.870294 loss: 0.000550 2022/09/15 00:53:54 - mmengine - INFO - Epoch(train) [115][550/586] lr: 5.000000e-04 eta: 6:52:22 time: 0.472607 data_time: 0.025291 memory: 15239 loss_kpt: 0.000543 acc_pose: 0.755453 loss: 0.000543 2022/09/15 00:54:11 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 00:54:11 - mmengine - INFO - Saving checkpoint at 115 epochs 2022/09/15 00:54:42 - mmengine - INFO - Epoch(train) [116][50/586] lr: 5.000000e-04 eta: 6:51:32 time: 0.473286 data_time: 0.030155 memory: 15239 loss_kpt: 0.000567 acc_pose: 0.908840 loss: 0.000567 2022/09/15 00:55:06 - mmengine - INFO - Epoch(train) [116][100/586] lr: 5.000000e-04 eta: 6:51:11 time: 0.477196 data_time: 0.025850 memory: 15239 loss_kpt: 0.000545 acc_pose: 0.908926 loss: 0.000545 2022/09/15 00:55:29 - mmengine - INFO - Epoch(train) [116][150/586] lr: 5.000000e-04 eta: 6:50:50 time: 0.463899 data_time: 0.025556 memory: 15239 loss_kpt: 0.000525 acc_pose: 0.847458 loss: 0.000525 2022/09/15 00:55:52 - mmengine - INFO - Epoch(train) [116][200/586] lr: 5.000000e-04 eta: 6:50:28 time: 0.463022 data_time: 0.025310 memory: 15239 loss_kpt: 0.000555 acc_pose: 0.891894 loss: 0.000555 2022/09/15 00:56:16 - mmengine - INFO - Epoch(train) [116][250/586] lr: 5.000000e-04 eta: 6:50:07 time: 0.472324 data_time: 0.029306 memory: 15239 loss_kpt: 0.000524 acc_pose: 0.798830 loss: 0.000524 2022/09/15 00:56:39 - mmengine - INFO - Epoch(train) [116][300/586] lr: 5.000000e-04 eta: 6:49:46 time: 0.467074 data_time: 0.025532 memory: 15239 loss_kpt: 0.000550 acc_pose: 0.889062 loss: 0.000550 2022/09/15 00:57:02 - mmengine - INFO - Epoch(train) [116][350/586] lr: 5.000000e-04 eta: 6:49:25 time: 0.466910 data_time: 0.025159 memory: 15239 loss_kpt: 0.000543 acc_pose: 0.797911 loss: 0.000543 2022/09/15 00:57:26 - mmengine - INFO - Epoch(train) [116][400/586] lr: 5.000000e-04 eta: 6:49:04 time: 0.470481 data_time: 0.024675 memory: 15239 loss_kpt: 0.000542 acc_pose: 0.894448 loss: 0.000542 2022/09/15 00:57:49 - mmengine - INFO - Epoch(train) [116][450/586] lr: 5.000000e-04 eta: 6:48:42 time: 0.467193 data_time: 0.025236 memory: 15239 loss_kpt: 0.000531 acc_pose: 0.866389 loss: 0.000531 2022/09/15 00:58:12 - mmengine - INFO - Epoch(train) [116][500/586] lr: 5.000000e-04 eta: 6:48:21 time: 0.458789 data_time: 0.025852 memory: 15239 loss_kpt: 0.000527 acc_pose: 0.867853 loss: 0.000527 2022/09/15 00:58:36 - mmengine - INFO - Epoch(train) [116][550/586] lr: 5.000000e-04 eta: 6:48:00 time: 0.474423 data_time: 0.025518 memory: 15239 loss_kpt: 0.000555 acc_pose: 0.818372 loss: 0.000555 2022/09/15 00:58:53 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 00:58:53 - mmengine - INFO - Saving checkpoint at 116 epochs 2022/09/15 00:59:11 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 00:59:24 - mmengine - INFO - Epoch(train) [117][50/586] lr: 5.000000e-04 eta: 6:47:10 time: 0.486357 data_time: 0.034452 memory: 15239 loss_kpt: 0.000542 acc_pose: 0.837748 loss: 0.000542 2022/09/15 00:59:48 - mmengine - INFO - Epoch(train) [117][100/586] lr: 5.000000e-04 eta: 6:46:50 time: 0.477507 data_time: 0.025468 memory: 15239 loss_kpt: 0.000539 acc_pose: 0.861103 loss: 0.000539 2022/09/15 01:00:11 - mmengine - INFO - Epoch(train) [117][150/586] lr: 5.000000e-04 eta: 6:46:28 time: 0.468825 data_time: 0.025221 memory: 15239 loss_kpt: 0.000538 acc_pose: 0.832740 loss: 0.000538 2022/09/15 01:00:35 - mmengine - INFO - Epoch(train) [117][200/586] lr: 5.000000e-04 eta: 6:46:07 time: 0.471620 data_time: 0.025866 memory: 15239 loss_kpt: 0.000544 acc_pose: 0.888420 loss: 0.000544 2022/09/15 01:00:58 - mmengine - INFO - Epoch(train) [117][250/586] lr: 5.000000e-04 eta: 6:45:46 time: 0.466409 data_time: 0.024952 memory: 15239 loss_kpt: 0.000554 acc_pose: 0.863798 loss: 0.000554 2022/09/15 01:01:21 - mmengine - INFO - Epoch(train) [117][300/586] lr: 5.000000e-04 eta: 6:45:25 time: 0.462236 data_time: 0.025268 memory: 15239 loss_kpt: 0.000529 acc_pose: 0.887574 loss: 0.000529 2022/09/15 01:01:45 - mmengine - INFO - Epoch(train) [117][350/586] lr: 5.000000e-04 eta: 6:45:03 time: 0.470880 data_time: 0.031111 memory: 15239 loss_kpt: 0.000551 acc_pose: 0.874407 loss: 0.000551 2022/09/15 01:02:08 - mmengine - INFO - Epoch(train) [117][400/586] lr: 5.000000e-04 eta: 6:44:42 time: 0.471097 data_time: 0.026064 memory: 15239 loss_kpt: 0.000559 acc_pose: 0.809687 loss: 0.000559 2022/09/15 01:02:32 - mmengine - INFO - Epoch(train) [117][450/586] lr: 5.000000e-04 eta: 6:44:21 time: 0.464024 data_time: 0.025349 memory: 15239 loss_kpt: 0.000551 acc_pose: 0.897855 loss: 0.000551 2022/09/15 01:02:55 - mmengine - INFO - Epoch(train) [117][500/586] lr: 5.000000e-04 eta: 6:44:00 time: 0.472313 data_time: 0.025316 memory: 15239 loss_kpt: 0.000523 acc_pose: 0.851895 loss: 0.000523 2022/09/15 01:03:19 - mmengine - INFO - Epoch(train) [117][550/586] lr: 5.000000e-04 eta: 6:43:39 time: 0.472968 data_time: 0.025521 memory: 15239 loss_kpt: 0.000551 acc_pose: 0.868898 loss: 0.000551 2022/09/15 01:03:35 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 01:03:35 - mmengine - INFO - Saving checkpoint at 117 epochs 2022/09/15 01:04:07 - mmengine - INFO - Epoch(train) [118][50/586] lr: 5.000000e-04 eta: 6:42:50 time: 0.492795 data_time: 0.036908 memory: 15239 loss_kpt: 0.000535 acc_pose: 0.812573 loss: 0.000535 2022/09/15 01:04:31 - mmengine - INFO - Epoch(train) [118][100/586] lr: 5.000000e-04 eta: 6:42:29 time: 0.475841 data_time: 0.033526 memory: 15239 loss_kpt: 0.000525 acc_pose: 0.824289 loss: 0.000525 2022/09/15 01:04:54 - mmengine - INFO - Epoch(train) [118][150/586] lr: 5.000000e-04 eta: 6:42:08 time: 0.468959 data_time: 0.030439 memory: 15239 loss_kpt: 0.000529 acc_pose: 0.884340 loss: 0.000529 2022/09/15 01:05:18 - mmengine - INFO - Epoch(train) [118][200/586] lr: 5.000000e-04 eta: 6:41:47 time: 0.470941 data_time: 0.031490 memory: 15239 loss_kpt: 0.000540 acc_pose: 0.826638 loss: 0.000540 2022/09/15 01:05:41 - mmengine - INFO - Epoch(train) [118][250/586] lr: 5.000000e-04 eta: 6:41:25 time: 0.470728 data_time: 0.032598 memory: 15239 loss_kpt: 0.000557 acc_pose: 0.879650 loss: 0.000557 2022/09/15 01:06:05 - mmengine - INFO - Epoch(train) [118][300/586] lr: 5.000000e-04 eta: 6:41:04 time: 0.468531 data_time: 0.025898 memory: 15239 loss_kpt: 0.000544 acc_pose: 0.857393 loss: 0.000544 2022/09/15 01:06:28 - mmengine - INFO - Epoch(train) [118][350/586] lr: 5.000000e-04 eta: 6:40:43 time: 0.466956 data_time: 0.024861 memory: 15239 loss_kpt: 0.000542 acc_pose: 0.842455 loss: 0.000542 2022/09/15 01:06:52 - mmengine - INFO - Epoch(train) [118][400/586] lr: 5.000000e-04 eta: 6:40:22 time: 0.468692 data_time: 0.028756 memory: 15239 loss_kpt: 0.000554 acc_pose: 0.857631 loss: 0.000554 2022/09/15 01:07:10 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 01:07:15 - mmengine - INFO - Epoch(train) [118][450/586] lr: 5.000000e-04 eta: 6:40:01 time: 0.472370 data_time: 0.025689 memory: 15239 loss_kpt: 0.000534 acc_pose: 0.828870 loss: 0.000534 2022/09/15 01:07:39 - mmengine - INFO - Epoch(train) [118][500/586] lr: 5.000000e-04 eta: 6:39:40 time: 0.475751 data_time: 0.025491 memory: 15239 loss_kpt: 0.000524 acc_pose: 0.891787 loss: 0.000524 2022/09/15 01:08:03 - mmengine - INFO - Epoch(train) [118][550/586] lr: 5.000000e-04 eta: 6:39:18 time: 0.470767 data_time: 0.026076 memory: 15239 loss_kpt: 0.000530 acc_pose: 0.887351 loss: 0.000530 2022/09/15 01:08:19 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 01:08:19 - mmengine - INFO - Saving checkpoint at 118 epochs 2022/09/15 01:08:50 - mmengine - INFO - Epoch(train) [119][50/586] lr: 5.000000e-04 eta: 6:38:29 time: 0.479771 data_time: 0.033466 memory: 15239 loss_kpt: 0.000534 acc_pose: 0.898016 loss: 0.000534 2022/09/15 01:09:14 - mmengine - INFO - Epoch(train) [119][100/586] lr: 5.000000e-04 eta: 6:38:08 time: 0.465962 data_time: 0.025049 memory: 15239 loss_kpt: 0.000521 acc_pose: 0.874941 loss: 0.000521 2022/09/15 01:09:37 - mmengine - INFO - Epoch(train) [119][150/586] lr: 5.000000e-04 eta: 6:37:47 time: 0.475276 data_time: 0.024506 memory: 15239 loss_kpt: 0.000519 acc_pose: 0.861074 loss: 0.000519 2022/09/15 01:10:01 - mmengine - INFO - Epoch(train) [119][200/586] lr: 5.000000e-04 eta: 6:37:26 time: 0.472025 data_time: 0.025451 memory: 15239 loss_kpt: 0.000542 acc_pose: 0.804586 loss: 0.000542 2022/09/15 01:10:25 - mmengine - INFO - Epoch(train) [119][250/586] lr: 5.000000e-04 eta: 6:37:05 time: 0.471108 data_time: 0.025244 memory: 15239 loss_kpt: 0.000545 acc_pose: 0.833901 loss: 0.000545 2022/09/15 01:10:48 - mmengine - INFO - Epoch(train) [119][300/586] lr: 5.000000e-04 eta: 6:36:43 time: 0.470943 data_time: 0.025602 memory: 15239 loss_kpt: 0.000547 acc_pose: 0.876482 loss: 0.000547 2022/09/15 01:11:12 - mmengine - INFO - Epoch(train) [119][350/586] lr: 5.000000e-04 eta: 6:36:22 time: 0.474347 data_time: 0.029566 memory: 15239 loss_kpt: 0.000538 acc_pose: 0.849627 loss: 0.000538 2022/09/15 01:11:36 - mmengine - INFO - Epoch(train) [119][400/586] lr: 5.000000e-04 eta: 6:36:02 time: 0.478843 data_time: 0.026320 memory: 15239 loss_kpt: 0.000554 acc_pose: 0.854901 loss: 0.000554 2022/09/15 01:11:59 - mmengine - INFO - Epoch(train) [119][450/586] lr: 5.000000e-04 eta: 6:35:40 time: 0.466017 data_time: 0.025632 memory: 15239 loss_kpt: 0.000542 acc_pose: 0.862901 loss: 0.000542 2022/09/15 01:12:23 - mmengine - INFO - Epoch(train) [119][500/586] lr: 5.000000e-04 eta: 6:35:19 time: 0.478908 data_time: 0.025215 memory: 15239 loss_kpt: 0.000547 acc_pose: 0.862365 loss: 0.000547 2022/09/15 01:12:46 - mmengine - INFO - Epoch(train) [119][550/586] lr: 5.000000e-04 eta: 6:34:58 time: 0.464513 data_time: 0.024921 memory: 15239 loss_kpt: 0.000550 acc_pose: 0.866868 loss: 0.000550 2022/09/15 01:13:03 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 01:13:03 - mmengine - INFO - Saving checkpoint at 119 epochs 2022/09/15 01:13:34 - mmengine - INFO - Epoch(train) [120][50/586] lr: 5.000000e-04 eta: 6:34:09 time: 0.483979 data_time: 0.039904 memory: 15239 loss_kpt: 0.000546 acc_pose: 0.854693 loss: 0.000546 2022/09/15 01:13:58 - mmengine - INFO - Epoch(train) [120][100/586] lr: 5.000000e-04 eta: 6:33:48 time: 0.472078 data_time: 0.035555 memory: 15239 loss_kpt: 0.000534 acc_pose: 0.783356 loss: 0.000534 2022/09/15 01:14:21 - mmengine - INFO - Epoch(train) [120][150/586] lr: 5.000000e-04 eta: 6:33:27 time: 0.470288 data_time: 0.032905 memory: 15239 loss_kpt: 0.000532 acc_pose: 0.874284 loss: 0.000532 2022/09/15 01:14:45 - mmengine - INFO - Epoch(train) [120][200/586] lr: 5.000000e-04 eta: 6:33:06 time: 0.472126 data_time: 0.027988 memory: 15239 loss_kpt: 0.000548 acc_pose: 0.839086 loss: 0.000548 2022/09/15 01:15:08 - mmengine - INFO - Epoch(train) [120][250/586] lr: 5.000000e-04 eta: 6:32:44 time: 0.471428 data_time: 0.029301 memory: 15239 loss_kpt: 0.000556 acc_pose: 0.875054 loss: 0.000556 2022/09/15 01:15:16 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 01:15:32 - mmengine - INFO - Epoch(train) [120][300/586] lr: 5.000000e-04 eta: 6:32:23 time: 0.467057 data_time: 0.026575 memory: 15239 loss_kpt: 0.000530 acc_pose: 0.872894 loss: 0.000530 2022/09/15 01:15:55 - mmengine - INFO - Epoch(train) [120][350/586] lr: 5.000000e-04 eta: 6:32:02 time: 0.470034 data_time: 0.024911 memory: 15239 loss_kpt: 0.000536 acc_pose: 0.901332 loss: 0.000536 2022/09/15 01:16:19 - mmengine - INFO - Epoch(train) [120][400/586] lr: 5.000000e-04 eta: 6:31:41 time: 0.469949 data_time: 0.026035 memory: 15239 loss_kpt: 0.000545 acc_pose: 0.850548 loss: 0.000545 2022/09/15 01:16:42 - mmengine - INFO - Epoch(train) [120][450/586] lr: 5.000000e-04 eta: 6:31:19 time: 0.471954 data_time: 0.026204 memory: 15239 loss_kpt: 0.000551 acc_pose: 0.831108 loss: 0.000551 2022/09/15 01:17:06 - mmengine - INFO - Epoch(train) [120][500/586] lr: 5.000000e-04 eta: 6:30:59 time: 0.477773 data_time: 0.025710 memory: 15239 loss_kpt: 0.000532 acc_pose: 0.894943 loss: 0.000532 2022/09/15 01:17:30 - mmengine - INFO - Epoch(train) [120][550/586] lr: 5.000000e-04 eta: 6:30:37 time: 0.466636 data_time: 0.029116 memory: 15239 loss_kpt: 0.000534 acc_pose: 0.831728 loss: 0.000534 2022/09/15 01:17:46 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 01:17:46 - mmengine - INFO - Saving checkpoint at 120 epochs 2022/09/15 01:18:04 - mmengine - INFO - Epoch(val) [120][50/407] eta: 0:01:13 time: 0.205749 data_time: 0.018464 memory: 15239 2022/09/15 01:18:13 - mmengine - INFO - Epoch(val) [120][100/407] eta: 0:00:59 time: 0.194695 data_time: 0.008193 memory: 2064 2022/09/15 01:18:23 - mmengine - INFO - Epoch(val) [120][150/407] eta: 0:00:50 time: 0.197083 data_time: 0.008487 memory: 2064 2022/09/15 01:18:33 - mmengine - INFO - Epoch(val) [120][200/407] eta: 0:00:40 time: 0.194770 data_time: 0.008339 memory: 2064 2022/09/15 01:18:43 - mmengine - INFO - Epoch(val) [120][250/407] eta: 0:00:30 time: 0.195038 data_time: 0.008344 memory: 2064 2022/09/15 01:18:53 - mmengine - INFO - Epoch(val) [120][300/407] eta: 0:00:21 time: 0.197253 data_time: 0.008655 memory: 2064 2022/09/15 01:19:02 - mmengine - INFO - Epoch(val) [120][350/407] eta: 0:00:11 time: 0.195139 data_time: 0.008277 memory: 2064 2022/09/15 01:19:12 - mmengine - INFO - Epoch(val) [120][400/407] eta: 0:00:01 time: 0.194388 data_time: 0.009211 memory: 2064 2022/09/15 01:19:49 - mmengine - INFO - Evaluating CocoMetric... 2022/09/15 01:20:03 - mmengine - INFO - Epoch(val) [120][407/407] coco/AP: 0.757892 coco/AP .5: 0.905384 coco/AP .75: 0.824388 coco/AP (M): 0.717651 coco/AP (L): 0.829174 coco/AR: 0.807966 coco/AR .5: 0.941751 coco/AR .75: 0.868073 coco/AR (M): 0.763453 coco/AR (L): 0.872352 2022/09/15 01:20:28 - mmengine - INFO - Epoch(train) [121][50/586] lr: 5.000000e-04 eta: 6:29:49 time: 0.497173 data_time: 0.031813 memory: 15239 loss_kpt: 0.000518 acc_pose: 0.864205 loss: 0.000518 2022/09/15 01:20:51 - mmengine - INFO - Epoch(train) [121][100/586] lr: 5.000000e-04 eta: 6:29:28 time: 0.468858 data_time: 0.025171 memory: 15239 loss_kpt: 0.000519 acc_pose: 0.860246 loss: 0.000519 2022/09/15 01:21:14 - mmengine - INFO - Epoch(train) [121][150/586] lr: 5.000000e-04 eta: 6:29:06 time: 0.467543 data_time: 0.024519 memory: 15239 loss_kpt: 0.000516 acc_pose: 0.903090 loss: 0.000516 2022/09/15 01:21:38 - mmengine - INFO - Epoch(train) [121][200/586] lr: 5.000000e-04 eta: 6:28:45 time: 0.472426 data_time: 0.024776 memory: 15239 loss_kpt: 0.000528 acc_pose: 0.872321 loss: 0.000528 2022/09/15 01:22:02 - mmengine - INFO - Epoch(train) [121][250/586] lr: 5.000000e-04 eta: 6:28:24 time: 0.474839 data_time: 0.026241 memory: 15239 loss_kpt: 0.000543 acc_pose: 0.771801 loss: 0.000543 2022/09/15 01:22:25 - mmengine - INFO - Epoch(train) [121][300/586] lr: 5.000000e-04 eta: 6:28:03 time: 0.458245 data_time: 0.024920 memory: 15239 loss_kpt: 0.000555 acc_pose: 0.801400 loss: 0.000555 2022/09/15 01:22:48 - mmengine - INFO - Epoch(train) [121][350/586] lr: 5.000000e-04 eta: 6:27:41 time: 0.470582 data_time: 0.029050 memory: 15239 loss_kpt: 0.000543 acc_pose: 0.876134 loss: 0.000543 2022/09/15 01:23:12 - mmengine - INFO - Epoch(train) [121][400/586] lr: 5.000000e-04 eta: 6:27:20 time: 0.466362 data_time: 0.024871 memory: 15239 loss_kpt: 0.000558 acc_pose: 0.829123 loss: 0.000558 2022/09/15 01:23:35 - mmengine - INFO - Epoch(train) [121][450/586] lr: 5.000000e-04 eta: 6:26:58 time: 0.462478 data_time: 0.025960 memory: 15239 loss_kpt: 0.000534 acc_pose: 0.850540 loss: 0.000534 2022/09/15 01:23:58 - mmengine - INFO - Epoch(train) [121][500/586] lr: 5.000000e-04 eta: 6:26:37 time: 0.471203 data_time: 0.027938 memory: 15239 loss_kpt: 0.000538 acc_pose: 0.860775 loss: 0.000538 2022/09/15 01:24:21 - mmengine - INFO - Epoch(train) [121][550/586] lr: 5.000000e-04 eta: 6:26:16 time: 0.461637 data_time: 0.025236 memory: 15239 loss_kpt: 0.000535 acc_pose: 0.897282 loss: 0.000535 2022/09/15 01:24:38 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 01:24:38 - mmengine - INFO - Saving checkpoint at 121 epochs 2022/09/15 01:25:09 - mmengine - INFO - Epoch(train) [122][50/586] lr: 5.000000e-04 eta: 6:25:27 time: 0.475915 data_time: 0.029608 memory: 15239 loss_kpt: 0.000538 acc_pose: 0.787017 loss: 0.000538 2022/09/15 01:25:30 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 01:25:32 - mmengine - INFO - Epoch(train) [122][100/586] lr: 5.000000e-04 eta: 6:25:06 time: 0.473492 data_time: 0.026055 memory: 15239 loss_kpt: 0.000545 acc_pose: 0.903369 loss: 0.000545 2022/09/15 01:25:56 - mmengine - INFO - Epoch(train) [122][150/586] lr: 5.000000e-04 eta: 6:24:45 time: 0.474347 data_time: 0.025192 memory: 15239 loss_kpt: 0.000542 acc_pose: 0.876180 loss: 0.000542 2022/09/15 01:26:20 - mmengine - INFO - Epoch(train) [122][200/586] lr: 5.000000e-04 eta: 6:24:24 time: 0.472424 data_time: 0.024888 memory: 15239 loss_kpt: 0.000537 acc_pose: 0.829500 loss: 0.000537 2022/09/15 01:26:43 - mmengine - INFO - Epoch(train) [122][250/586] lr: 5.000000e-04 eta: 6:24:02 time: 0.470743 data_time: 0.025888 memory: 15239 loss_kpt: 0.000543 acc_pose: 0.853910 loss: 0.000543 2022/09/15 01:27:07 - mmengine - INFO - Epoch(train) [122][300/586] lr: 5.000000e-04 eta: 6:23:41 time: 0.467601 data_time: 0.025641 memory: 15239 loss_kpt: 0.000525 acc_pose: 0.869867 loss: 0.000525 2022/09/15 01:27:30 - mmengine - INFO - Epoch(train) [122][350/586] lr: 5.000000e-04 eta: 6:23:20 time: 0.474770 data_time: 0.024933 memory: 15239 loss_kpt: 0.000529 acc_pose: 0.824176 loss: 0.000529 2022/09/15 01:27:54 - mmengine - INFO - Epoch(train) [122][400/586] lr: 5.000000e-04 eta: 6:22:59 time: 0.468117 data_time: 0.027428 memory: 15239 loss_kpt: 0.000540 acc_pose: 0.784922 loss: 0.000540 2022/09/15 01:28:17 - mmengine - INFO - Epoch(train) [122][450/586] lr: 5.000000e-04 eta: 6:22:37 time: 0.467224 data_time: 0.029483 memory: 15239 loss_kpt: 0.000540 acc_pose: 0.847593 loss: 0.000540 2022/09/15 01:28:41 - mmengine - INFO - Epoch(train) [122][500/586] lr: 5.000000e-04 eta: 6:22:16 time: 0.479167 data_time: 0.025011 memory: 15239 loss_kpt: 0.000529 acc_pose: 0.911630 loss: 0.000529 2022/09/15 01:29:05 - mmengine - INFO - Epoch(train) [122][550/586] lr: 5.000000e-04 eta: 6:21:55 time: 0.473745 data_time: 0.026477 memory: 15239 loss_kpt: 0.000537 acc_pose: 0.835382 loss: 0.000537 2022/09/15 01:29:22 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 01:29:22 - mmengine - INFO - Saving checkpoint at 122 epochs 2022/09/15 01:29:52 - mmengine - INFO - Epoch(train) [123][50/586] lr: 5.000000e-04 eta: 6:21:07 time: 0.480485 data_time: 0.032271 memory: 15239 loss_kpt: 0.000543 acc_pose: 0.803037 loss: 0.000543 2022/09/15 01:30:16 - mmengine - INFO - Epoch(train) [123][100/586] lr: 5.000000e-04 eta: 6:20:46 time: 0.468116 data_time: 0.025970 memory: 15239 loss_kpt: 0.000534 acc_pose: 0.837655 loss: 0.000534 2022/09/15 01:30:39 - mmengine - INFO - Epoch(train) [123][150/586] lr: 5.000000e-04 eta: 6:20:24 time: 0.468390 data_time: 0.024667 memory: 15239 loss_kpt: 0.000544 acc_pose: 0.874206 loss: 0.000544 2022/09/15 01:31:03 - mmengine - INFO - Epoch(train) [123][200/586] lr: 5.000000e-04 eta: 6:20:03 time: 0.473662 data_time: 0.024381 memory: 15239 loss_kpt: 0.000508 acc_pose: 0.931104 loss: 0.000508 2022/09/15 01:31:26 - mmengine - INFO - Epoch(train) [123][250/586] lr: 5.000000e-04 eta: 6:19:42 time: 0.467588 data_time: 0.028583 memory: 15239 loss_kpt: 0.000526 acc_pose: 0.852536 loss: 0.000526 2022/09/15 01:31:50 - mmengine - INFO - Epoch(train) [123][300/586] lr: 5.000000e-04 eta: 6:19:20 time: 0.462478 data_time: 0.025481 memory: 15239 loss_kpt: 0.000532 acc_pose: 0.903808 loss: 0.000532 2022/09/15 01:32:13 - mmengine - INFO - Epoch(train) [123][350/586] lr: 5.000000e-04 eta: 6:18:59 time: 0.476227 data_time: 0.025283 memory: 15239 loss_kpt: 0.000537 acc_pose: 0.924560 loss: 0.000537 2022/09/15 01:32:37 - mmengine - INFO - Epoch(train) [123][400/586] lr: 5.000000e-04 eta: 6:18:38 time: 0.469647 data_time: 0.025689 memory: 15239 loss_kpt: 0.000520 acc_pose: 0.877309 loss: 0.000520 2022/09/15 01:33:00 - mmengine - INFO - Epoch(train) [123][450/586] lr: 5.000000e-04 eta: 6:18:16 time: 0.464357 data_time: 0.025524 memory: 15239 loss_kpt: 0.000549 acc_pose: 0.922267 loss: 0.000549 2022/09/15 01:33:24 - mmengine - INFO - Epoch(train) [123][500/586] lr: 5.000000e-04 eta: 6:17:55 time: 0.474899 data_time: 0.025799 memory: 15239 loss_kpt: 0.000529 acc_pose: 0.807945 loss: 0.000529 2022/09/15 01:33:28 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 01:33:47 - mmengine - INFO - Epoch(train) [123][550/586] lr: 5.000000e-04 eta: 6:17:34 time: 0.471340 data_time: 0.025335 memory: 15239 loss_kpt: 0.000541 acc_pose: 0.885649 loss: 0.000541 2022/09/15 01:34:04 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 01:34:04 - mmengine - INFO - Saving checkpoint at 123 epochs 2022/09/15 01:34:35 - mmengine - INFO - Epoch(train) [124][50/586] lr: 5.000000e-04 eta: 6:16:46 time: 0.486580 data_time: 0.033264 memory: 15239 loss_kpt: 0.000518 acc_pose: 0.896675 loss: 0.000518 2022/09/15 01:34:59 - mmengine - INFO - Epoch(train) [124][100/586] lr: 5.000000e-04 eta: 6:16:25 time: 0.474019 data_time: 0.026544 memory: 15239 loss_kpt: 0.000520 acc_pose: 0.851072 loss: 0.000520 2022/09/15 01:35:23 - mmengine - INFO - Epoch(train) [124][150/586] lr: 5.000000e-04 eta: 6:16:04 time: 0.475638 data_time: 0.028457 memory: 15239 loss_kpt: 0.000520 acc_pose: 0.845507 loss: 0.000520 2022/09/15 01:35:46 - mmengine - INFO - Epoch(train) [124][200/586] lr: 5.000000e-04 eta: 6:15:43 time: 0.469106 data_time: 0.025357 memory: 15239 loss_kpt: 0.000536 acc_pose: 0.858117 loss: 0.000536 2022/09/15 01:36:10 - mmengine - INFO - Epoch(train) [124][250/586] lr: 5.000000e-04 eta: 6:15:21 time: 0.469939 data_time: 0.025808 memory: 15239 loss_kpt: 0.000539 acc_pose: 0.877726 loss: 0.000539 2022/09/15 01:36:34 - mmengine - INFO - Epoch(train) [124][300/586] lr: 5.000000e-04 eta: 6:15:00 time: 0.471792 data_time: 0.025224 memory: 15239 loss_kpt: 0.000537 acc_pose: 0.898059 loss: 0.000537 2022/09/15 01:36:57 - mmengine - INFO - Epoch(train) [124][350/586] lr: 5.000000e-04 eta: 6:14:39 time: 0.467970 data_time: 0.026108 memory: 15239 loss_kpt: 0.000528 acc_pose: 0.872279 loss: 0.000528 2022/09/15 01:37:20 - mmengine - INFO - Epoch(train) [124][400/586] lr: 5.000000e-04 eta: 6:14:17 time: 0.469126 data_time: 0.025783 memory: 15239 loss_kpt: 0.000543 acc_pose: 0.881232 loss: 0.000543 2022/09/15 01:37:44 - mmengine - INFO - Epoch(train) [124][450/586] lr: 5.000000e-04 eta: 6:13:56 time: 0.468975 data_time: 0.025070 memory: 15239 loss_kpt: 0.000542 acc_pose: 0.827888 loss: 0.000542 2022/09/15 01:38:07 - mmengine - INFO - Epoch(train) [124][500/586] lr: 5.000000e-04 eta: 6:13:35 time: 0.471169 data_time: 0.025678 memory: 15239 loss_kpt: 0.000527 acc_pose: 0.881153 loss: 0.000527 2022/09/15 01:38:31 - mmengine - INFO - Epoch(train) [124][550/586] lr: 5.000000e-04 eta: 6:13:13 time: 0.467497 data_time: 0.025772 memory: 15239 loss_kpt: 0.000529 acc_pose: 0.876912 loss: 0.000529 2022/09/15 01:38:48 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 01:38:48 - mmengine - INFO - Saving checkpoint at 124 epochs 2022/09/15 01:39:18 - mmengine - INFO - Epoch(train) [125][50/586] lr: 5.000000e-04 eta: 6:12:25 time: 0.473773 data_time: 0.032322 memory: 15239 loss_kpt: 0.000516 acc_pose: 0.837901 loss: 0.000516 2022/09/15 01:39:42 - mmengine - INFO - Epoch(train) [125][100/586] lr: 5.000000e-04 eta: 6:12:04 time: 0.471119 data_time: 0.028333 memory: 15239 loss_kpt: 0.000551 acc_pose: 0.878729 loss: 0.000551 2022/09/15 01:40:05 - mmengine - INFO - Epoch(train) [125][150/586] lr: 5.000000e-04 eta: 6:11:43 time: 0.475238 data_time: 0.025364 memory: 15239 loss_kpt: 0.000531 acc_pose: 0.846665 loss: 0.000531 2022/09/15 01:40:29 - mmengine - INFO - Epoch(train) [125][200/586] lr: 5.000000e-04 eta: 6:11:21 time: 0.466531 data_time: 0.025165 memory: 15239 loss_kpt: 0.000527 acc_pose: 0.869302 loss: 0.000527 2022/09/15 01:40:53 - mmengine - INFO - Epoch(train) [125][250/586] lr: 5.000000e-04 eta: 6:11:00 time: 0.478421 data_time: 0.025443 memory: 15239 loss_kpt: 0.000555 acc_pose: 0.848239 loss: 0.000555 2022/09/15 01:41:16 - mmengine - INFO - Epoch(train) [125][300/586] lr: 5.000000e-04 eta: 6:10:39 time: 0.474855 data_time: 0.025267 memory: 15239 loss_kpt: 0.000527 acc_pose: 0.768807 loss: 0.000527 2022/09/15 01:41:34 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 01:41:40 - mmengine - INFO - Epoch(train) [125][350/586] lr: 5.000000e-04 eta: 6:10:18 time: 0.471762 data_time: 0.026056 memory: 15239 loss_kpt: 0.000540 acc_pose: 0.891004 loss: 0.000540 2022/09/15 01:42:04 - mmengine - INFO - Epoch(train) [125][400/586] lr: 5.000000e-04 eta: 6:09:57 time: 0.475076 data_time: 0.027975 memory: 15239 loss_kpt: 0.000530 acc_pose: 0.794185 loss: 0.000530 2022/09/15 01:42:27 - mmengine - INFO - Epoch(train) [125][450/586] lr: 5.000000e-04 eta: 6:09:35 time: 0.463171 data_time: 0.025001 memory: 15239 loss_kpt: 0.000538 acc_pose: 0.843848 loss: 0.000538 2022/09/15 01:42:50 - mmengine - INFO - Epoch(train) [125][500/586] lr: 5.000000e-04 eta: 6:09:14 time: 0.470171 data_time: 0.025257 memory: 15239 loss_kpt: 0.000536 acc_pose: 0.837914 loss: 0.000536 2022/09/15 01:43:14 - mmengine - INFO - Epoch(train) [125][550/586] lr: 5.000000e-04 eta: 6:08:53 time: 0.473370 data_time: 0.028943 memory: 15239 loss_kpt: 0.000543 acc_pose: 0.868052 loss: 0.000543 2022/09/15 01:43:31 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 01:43:31 - mmengine - INFO - Saving checkpoint at 125 epochs 2022/09/15 01:44:02 - mmengine - INFO - Epoch(train) [126][50/586] lr: 5.000000e-04 eta: 6:08:05 time: 0.483474 data_time: 0.030396 memory: 15239 loss_kpt: 0.000532 acc_pose: 0.839293 loss: 0.000532 2022/09/15 01:44:25 - mmengine - INFO - Epoch(train) [126][100/586] lr: 5.000000e-04 eta: 6:07:44 time: 0.470917 data_time: 0.024269 memory: 15239 loss_kpt: 0.000531 acc_pose: 0.861641 loss: 0.000531 2022/09/15 01:44:49 - mmengine - INFO - Epoch(train) [126][150/586] lr: 5.000000e-04 eta: 6:07:22 time: 0.467211 data_time: 0.025022 memory: 15239 loss_kpt: 0.000535 acc_pose: 0.915866 loss: 0.000535 2022/09/15 01:45:12 - mmengine - INFO - Epoch(train) [126][200/586] lr: 5.000000e-04 eta: 6:07:01 time: 0.471274 data_time: 0.028971 memory: 15239 loss_kpt: 0.000521 acc_pose: 0.860852 loss: 0.000521 2022/09/15 01:45:36 - mmengine - INFO - Epoch(train) [126][250/586] lr: 5.000000e-04 eta: 6:06:40 time: 0.471472 data_time: 0.026035 memory: 15239 loss_kpt: 0.000510 acc_pose: 0.876207 loss: 0.000510 2022/09/15 01:45:59 - mmengine - INFO - Epoch(train) [126][300/586] lr: 5.000000e-04 eta: 6:06:18 time: 0.459689 data_time: 0.025694 memory: 15239 loss_kpt: 0.000545 acc_pose: 0.866055 loss: 0.000545 2022/09/15 01:46:23 - mmengine - INFO - Epoch(train) [126][350/586] lr: 5.000000e-04 eta: 6:05:57 time: 0.473434 data_time: 0.025472 memory: 15239 loss_kpt: 0.000543 acc_pose: 0.857842 loss: 0.000543 2022/09/15 01:46:46 - mmengine - INFO - Epoch(train) [126][400/586] lr: 5.000000e-04 eta: 6:05:36 time: 0.469208 data_time: 0.025254 memory: 15239 loss_kpt: 0.000558 acc_pose: 0.795113 loss: 0.000558 2022/09/15 01:47:09 - mmengine - INFO - Epoch(train) [126][450/586] lr: 5.000000e-04 eta: 6:05:14 time: 0.459192 data_time: 0.025118 memory: 15239 loss_kpt: 0.000518 acc_pose: 0.824517 loss: 0.000518 2022/09/15 01:47:33 - mmengine - INFO - Epoch(train) [126][500/586] lr: 5.000000e-04 eta: 6:04:53 time: 0.475622 data_time: 0.029651 memory: 15239 loss_kpt: 0.000554 acc_pose: 0.862626 loss: 0.000554 2022/09/15 01:47:56 - mmengine - INFO - Epoch(train) [126][550/586] lr: 5.000000e-04 eta: 6:04:31 time: 0.464847 data_time: 0.025450 memory: 15239 loss_kpt: 0.000525 acc_pose: 0.846420 loss: 0.000525 2022/09/15 01:48:13 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 01:48:13 - mmengine - INFO - Saving checkpoint at 126 epochs 2022/09/15 01:48:44 - mmengine - INFO - Epoch(train) [127][50/586] lr: 5.000000e-04 eta: 6:03:44 time: 0.487921 data_time: 0.032899 memory: 15239 loss_kpt: 0.000533 acc_pose: 0.910362 loss: 0.000533 2022/09/15 01:49:08 - mmengine - INFO - Epoch(train) [127][100/586] lr: 5.000000e-04 eta: 6:03:23 time: 0.482138 data_time: 0.026787 memory: 15239 loss_kpt: 0.000545 acc_pose: 0.898163 loss: 0.000545 2022/09/15 01:49:32 - mmengine - INFO - Epoch(train) [127][150/586] lr: 5.000000e-04 eta: 6:03:02 time: 0.467519 data_time: 0.026758 memory: 15239 loss_kpt: 0.000515 acc_pose: 0.884071 loss: 0.000515 2022/09/15 01:49:39 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 01:49:56 - mmengine - INFO - Epoch(train) [127][200/586] lr: 5.000000e-04 eta: 6:02:40 time: 0.474273 data_time: 0.024905 memory: 15239 loss_kpt: 0.000524 acc_pose: 0.879505 loss: 0.000524 2022/09/15 01:50:19 - mmengine - INFO - Epoch(train) [127][250/586] lr: 5.000000e-04 eta: 6:02:19 time: 0.474810 data_time: 0.029751 memory: 15239 loss_kpt: 0.000544 acc_pose: 0.849243 loss: 0.000544 2022/09/15 01:50:42 - mmengine - INFO - Epoch(train) [127][300/586] lr: 5.000000e-04 eta: 6:01:58 time: 0.463050 data_time: 0.025100 memory: 15239 loss_kpt: 0.000538 acc_pose: 0.885301 loss: 0.000538 2022/09/15 01:51:07 - mmengine - INFO - Epoch(train) [127][350/586] lr: 5.000000e-04 eta: 6:01:37 time: 0.483407 data_time: 0.025066 memory: 15239 loss_kpt: 0.000540 acc_pose: 0.885087 loss: 0.000540 2022/09/15 01:51:30 - mmengine - INFO - Epoch(train) [127][400/586] lr: 5.000000e-04 eta: 6:01:16 time: 0.470350 data_time: 0.025288 memory: 15239 loss_kpt: 0.000535 acc_pose: 0.871939 loss: 0.000535 2022/09/15 01:51:54 - mmengine - INFO - Epoch(train) [127][450/586] lr: 5.000000e-04 eta: 6:00:54 time: 0.467938 data_time: 0.024862 memory: 15239 loss_kpt: 0.000527 acc_pose: 0.886979 loss: 0.000527 2022/09/15 01:52:17 - mmengine - INFO - Epoch(train) [127][500/586] lr: 5.000000e-04 eta: 6:00:33 time: 0.475813 data_time: 0.025306 memory: 15239 loss_kpt: 0.000532 acc_pose: 0.823953 loss: 0.000532 2022/09/15 01:52:41 - mmengine - INFO - Epoch(train) [127][550/586] lr: 5.000000e-04 eta: 6:00:12 time: 0.471586 data_time: 0.027752 memory: 15239 loss_kpt: 0.000538 acc_pose: 0.858937 loss: 0.000538 2022/09/15 01:52:57 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 01:52:58 - mmengine - INFO - Saving checkpoint at 127 epochs 2022/09/15 01:53:29 - mmengine - INFO - Epoch(train) [128][50/586] lr: 5.000000e-04 eta: 5:59:24 time: 0.481812 data_time: 0.037318 memory: 15239 loss_kpt: 0.000527 acc_pose: 0.855538 loss: 0.000527 2022/09/15 01:53:52 - mmengine - INFO - Epoch(train) [128][100/586] lr: 5.000000e-04 eta: 5:59:03 time: 0.467714 data_time: 0.026497 memory: 15239 loss_kpt: 0.000546 acc_pose: 0.798318 loss: 0.000546 2022/09/15 01:54:16 - mmengine - INFO - Epoch(train) [128][150/586] lr: 5.000000e-04 eta: 5:58:42 time: 0.472488 data_time: 0.025089 memory: 15239 loss_kpt: 0.000564 acc_pose: 0.849893 loss: 0.000564 2022/09/15 01:54:39 - mmengine - INFO - Epoch(train) [128][200/586] lr: 5.000000e-04 eta: 5:58:20 time: 0.472154 data_time: 0.025107 memory: 15239 loss_kpt: 0.000532 acc_pose: 0.822289 loss: 0.000532 2022/09/15 01:55:02 - mmengine - INFO - Epoch(train) [128][250/586] lr: 5.000000e-04 eta: 5:57:59 time: 0.462534 data_time: 0.024803 memory: 15239 loss_kpt: 0.000556 acc_pose: 0.832839 loss: 0.000556 2022/09/15 01:55:26 - mmengine - INFO - Epoch(train) [128][300/586] lr: 5.000000e-04 eta: 5:57:37 time: 0.469327 data_time: 0.030564 memory: 15239 loss_kpt: 0.000536 acc_pose: 0.861964 loss: 0.000536 2022/09/15 01:55:49 - mmengine - INFO - Epoch(train) [128][350/586] lr: 5.000000e-04 eta: 5:57:16 time: 0.467895 data_time: 0.025716 memory: 15239 loss_kpt: 0.000546 acc_pose: 0.837280 loss: 0.000546 2022/09/15 01:56:13 - mmengine - INFO - Epoch(train) [128][400/586] lr: 5.000000e-04 eta: 5:56:55 time: 0.468085 data_time: 0.025676 memory: 15239 loss_kpt: 0.000527 acc_pose: 0.859353 loss: 0.000527 2022/09/15 01:56:36 - mmengine - INFO - Epoch(train) [128][450/586] lr: 5.000000e-04 eta: 5:56:33 time: 0.471627 data_time: 0.025846 memory: 15239 loss_kpt: 0.000526 acc_pose: 0.859003 loss: 0.000526 2022/09/15 01:57:00 - mmengine - INFO - Epoch(train) [128][500/586] lr: 5.000000e-04 eta: 5:56:12 time: 0.470190 data_time: 0.026438 memory: 15239 loss_kpt: 0.000539 acc_pose: 0.884603 loss: 0.000539 2022/09/15 01:57:23 - mmengine - INFO - Epoch(train) [128][550/586] lr: 5.000000e-04 eta: 5:55:50 time: 0.468278 data_time: 0.026065 memory: 15239 loss_kpt: 0.000545 acc_pose: 0.852878 loss: 0.000545 2022/09/15 01:57:37 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 01:57:40 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 01:57:40 - mmengine - INFO - Saving checkpoint at 128 epochs 2022/09/15 01:58:11 - mmengine - INFO - Epoch(train) [129][50/586] lr: 5.000000e-04 eta: 5:55:03 time: 0.481285 data_time: 0.037097 memory: 15239 loss_kpt: 0.000522 acc_pose: 0.824178 loss: 0.000522 2022/09/15 01:58:35 - mmengine - INFO - Epoch(train) [129][100/586] lr: 5.000000e-04 eta: 5:54:42 time: 0.477000 data_time: 0.030181 memory: 15239 loss_kpt: 0.000521 acc_pose: 0.864354 loss: 0.000521 2022/09/15 01:58:58 - mmengine - INFO - Epoch(train) [129][150/586] lr: 5.000000e-04 eta: 5:54:21 time: 0.469921 data_time: 0.025555 memory: 15239 loss_kpt: 0.000538 acc_pose: 0.849664 loss: 0.000538 2022/09/15 01:59:22 - mmengine - INFO - Epoch(train) [129][200/586] lr: 5.000000e-04 eta: 5:53:59 time: 0.469293 data_time: 0.026045 memory: 15239 loss_kpt: 0.000548 acc_pose: 0.902096 loss: 0.000548 2022/09/15 01:59:45 - mmengine - INFO - Epoch(train) [129][250/586] lr: 5.000000e-04 eta: 5:53:38 time: 0.470343 data_time: 0.024808 memory: 15239 loss_kpt: 0.000543 acc_pose: 0.841243 loss: 0.000543 2022/09/15 02:00:10 - mmengine - INFO - Epoch(train) [129][300/586] lr: 5.000000e-04 eta: 5:53:17 time: 0.496757 data_time: 0.026635 memory: 15239 loss_kpt: 0.000526 acc_pose: 0.849179 loss: 0.000526 2022/09/15 02:00:34 - mmengine - INFO - Epoch(train) [129][350/586] lr: 5.000000e-04 eta: 5:52:56 time: 0.479567 data_time: 0.025833 memory: 15239 loss_kpt: 0.000538 acc_pose: 0.810179 loss: 0.000538 2022/09/15 02:00:58 - mmengine - INFO - Epoch(train) [129][400/586] lr: 5.000000e-04 eta: 5:52:35 time: 0.469392 data_time: 0.029363 memory: 15239 loss_kpt: 0.000545 acc_pose: 0.801043 loss: 0.000545 2022/09/15 02:01:21 - mmengine - INFO - Epoch(train) [129][450/586] lr: 5.000000e-04 eta: 5:52:14 time: 0.467129 data_time: 0.024752 memory: 15239 loss_kpt: 0.000536 acc_pose: 0.880887 loss: 0.000536 2022/09/15 02:01:45 - mmengine - INFO - Epoch(train) [129][500/586] lr: 5.000000e-04 eta: 5:51:52 time: 0.471261 data_time: 0.025238 memory: 15239 loss_kpt: 0.000536 acc_pose: 0.837772 loss: 0.000536 2022/09/15 02:02:08 - mmengine - INFO - Epoch(train) [129][550/586] lr: 5.000000e-04 eta: 5:51:31 time: 0.465293 data_time: 0.029068 memory: 15239 loss_kpt: 0.000540 acc_pose: 0.876214 loss: 0.000540 2022/09/15 02:02:25 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 02:02:25 - mmengine - INFO - Saving checkpoint at 129 epochs 2022/09/15 02:02:56 - mmengine - INFO - Epoch(train) [130][50/586] lr: 5.000000e-04 eta: 5:50:44 time: 0.483567 data_time: 0.034154 memory: 15239 loss_kpt: 0.000531 acc_pose: 0.878760 loss: 0.000531 2022/09/15 02:03:19 - mmengine - INFO - Epoch(train) [130][100/586] lr: 5.000000e-04 eta: 5:50:22 time: 0.465647 data_time: 0.024890 memory: 15239 loss_kpt: 0.000523 acc_pose: 0.822354 loss: 0.000523 2022/09/15 02:03:43 - mmengine - INFO - Epoch(train) [130][150/586] lr: 5.000000e-04 eta: 5:50:01 time: 0.473181 data_time: 0.025149 memory: 15239 loss_kpt: 0.000536 acc_pose: 0.823403 loss: 0.000536 2022/09/15 02:04:07 - mmengine - INFO - Epoch(train) [130][200/586] lr: 5.000000e-04 eta: 5:49:40 time: 0.475513 data_time: 0.025538 memory: 15239 loss_kpt: 0.000516 acc_pose: 0.873387 loss: 0.000516 2022/09/15 02:04:30 - mmengine - INFO - Epoch(train) [130][250/586] lr: 5.000000e-04 eta: 5:49:18 time: 0.465101 data_time: 0.024981 memory: 15239 loss_kpt: 0.000526 acc_pose: 0.842352 loss: 0.000526 2022/09/15 02:04:54 - mmengine - INFO - Epoch(train) [130][300/586] lr: 5.000000e-04 eta: 5:48:57 time: 0.471958 data_time: 0.029933 memory: 15239 loss_kpt: 0.000533 acc_pose: 0.925951 loss: 0.000533 2022/09/15 02:05:17 - mmengine - INFO - Epoch(train) [130][350/586] lr: 5.000000e-04 eta: 5:48:35 time: 0.466992 data_time: 0.025847 memory: 15239 loss_kpt: 0.000526 acc_pose: 0.815658 loss: 0.000526 2022/09/15 02:05:40 - mmengine - INFO - Epoch(train) [130][400/586] lr: 5.000000e-04 eta: 5:48:14 time: 0.468091 data_time: 0.026479 memory: 15239 loss_kpt: 0.000551 acc_pose: 0.915479 loss: 0.000551 2022/09/15 02:05:43 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 02:06:04 - mmengine - INFO - Epoch(train) [130][450/586] lr: 5.000000e-04 eta: 5:47:53 time: 0.473182 data_time: 0.025123 memory: 15239 loss_kpt: 0.000524 acc_pose: 0.824152 loss: 0.000524 2022/09/15 02:06:28 - mmengine - INFO - Epoch(train) [130][500/586] lr: 5.000000e-04 eta: 5:47:31 time: 0.471023 data_time: 0.025350 memory: 15239 loss_kpt: 0.000523 acc_pose: 0.886499 loss: 0.000523 2022/09/15 02:06:51 - mmengine - INFO - Epoch(train) [130][550/586] lr: 5.000000e-04 eta: 5:47:10 time: 0.460958 data_time: 0.025251 memory: 15239 loss_kpt: 0.000528 acc_pose: 0.835359 loss: 0.000528 2022/09/15 02:07:08 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 02:07:08 - mmengine - INFO - Saving checkpoint at 130 epochs 2022/09/15 02:07:25 - mmengine - INFO - Epoch(val) [130][50/407] eta: 0:01:11 time: 0.201416 data_time: 0.013395 memory: 15239 2022/09/15 02:07:35 - mmengine - INFO - Epoch(val) [130][100/407] eta: 0:01:00 time: 0.195463 data_time: 0.008390 memory: 2064 2022/09/15 02:07:45 - mmengine - INFO - Epoch(val) [130][150/407] eta: 0:00:50 time: 0.197542 data_time: 0.008636 memory: 2064 2022/09/15 02:07:55 - mmengine - INFO - Epoch(val) [130][200/407] eta: 0:00:41 time: 0.201091 data_time: 0.012290 memory: 2064 2022/09/15 02:08:05 - mmengine - INFO - Epoch(val) [130][250/407] eta: 0:00:30 time: 0.196535 data_time: 0.008716 memory: 2064 2022/09/15 02:08:15 - mmengine - INFO - Epoch(val) [130][300/407] eta: 0:00:20 time: 0.196079 data_time: 0.008622 memory: 2064 2022/09/15 02:08:24 - mmengine - INFO - Epoch(val) [130][350/407] eta: 0:00:11 time: 0.197008 data_time: 0.008443 memory: 2064 2022/09/15 02:08:34 - mmengine - INFO - Epoch(val) [130][400/407] eta: 0:00:01 time: 0.192707 data_time: 0.007680 memory: 2064 2022/09/15 02:09:11 - mmengine - INFO - Evaluating CocoMetric... 2022/09/15 02:09:24 - mmengine - INFO - Epoch(val) [130][407/407] coco/AP: 0.757398 coco/AP .5: 0.905527 coco/AP .75: 0.822127 coco/AP (M): 0.717271 coco/AP (L): 0.830745 coco/AR: 0.808045 coco/AR .5: 0.942538 coco/AR .75: 0.864767 coco/AR (M): 0.762360 coco/AR (L): 0.874322 2022/09/15 02:09:49 - mmengine - INFO - Epoch(train) [131][50/586] lr: 5.000000e-04 eta: 5:46:23 time: 0.489993 data_time: 0.039324 memory: 15239 loss_kpt: 0.000518 acc_pose: 0.891970 loss: 0.000518 2022/09/15 02:10:12 - mmengine - INFO - Epoch(train) [131][100/586] lr: 5.000000e-04 eta: 5:46:02 time: 0.466158 data_time: 0.028016 memory: 15239 loss_kpt: 0.000521 acc_pose: 0.864030 loss: 0.000521 2022/09/15 02:10:35 - mmengine - INFO - Epoch(train) [131][150/586] lr: 5.000000e-04 eta: 5:45:40 time: 0.465058 data_time: 0.028486 memory: 15239 loss_kpt: 0.000514 acc_pose: 0.796165 loss: 0.000514 2022/09/15 02:10:59 - mmengine - INFO - Epoch(train) [131][200/586] lr: 5.000000e-04 eta: 5:45:19 time: 0.474410 data_time: 0.033102 memory: 15239 loss_kpt: 0.000514 acc_pose: 0.904529 loss: 0.000514 2022/09/15 02:11:23 - mmengine - INFO - Epoch(train) [131][250/586] lr: 5.000000e-04 eta: 5:44:57 time: 0.471337 data_time: 0.025401 memory: 15239 loss_kpt: 0.000546 acc_pose: 0.837632 loss: 0.000546 2022/09/15 02:11:46 - mmengine - INFO - Epoch(train) [131][300/586] lr: 5.000000e-04 eta: 5:44:36 time: 0.470215 data_time: 0.025684 memory: 15239 loss_kpt: 0.000529 acc_pose: 0.862068 loss: 0.000529 2022/09/15 02:12:10 - mmengine - INFO - Epoch(train) [131][350/586] lr: 5.000000e-04 eta: 5:44:15 time: 0.474115 data_time: 0.024958 memory: 15239 loss_kpt: 0.000538 acc_pose: 0.867655 loss: 0.000538 2022/09/15 02:12:33 - mmengine - INFO - Epoch(train) [131][400/586] lr: 5.000000e-04 eta: 5:43:53 time: 0.465967 data_time: 0.025136 memory: 15239 loss_kpt: 0.000515 acc_pose: 0.843466 loss: 0.000515 2022/09/15 02:12:56 - mmengine - INFO - Epoch(train) [131][450/586] lr: 5.000000e-04 eta: 5:43:32 time: 0.464609 data_time: 0.026070 memory: 15239 loss_kpt: 0.000534 acc_pose: 0.862597 loss: 0.000534 2022/09/15 02:13:20 - mmengine - INFO - Epoch(train) [131][500/586] lr: 5.000000e-04 eta: 5:43:10 time: 0.476406 data_time: 0.024949 memory: 15239 loss_kpt: 0.000536 acc_pose: 0.848691 loss: 0.000536 2022/09/15 02:13:44 - mmengine - INFO - Epoch(train) [131][550/586] lr: 5.000000e-04 eta: 5:42:49 time: 0.465806 data_time: 0.024999 memory: 15239 loss_kpt: 0.000527 acc_pose: 0.882722 loss: 0.000527 2022/09/15 02:14:00 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 02:14:00 - mmengine - INFO - Saving checkpoint at 131 epochs 2022/09/15 02:14:31 - mmengine - INFO - Epoch(train) [132][50/586] lr: 5.000000e-04 eta: 5:42:02 time: 0.483616 data_time: 0.029518 memory: 15239 loss_kpt: 0.000516 acc_pose: 0.813831 loss: 0.000516 2022/09/15 02:14:55 - mmengine - INFO - Epoch(train) [132][100/586] lr: 5.000000e-04 eta: 5:41:41 time: 0.477208 data_time: 0.025584 memory: 15239 loss_kpt: 0.000529 acc_pose: 0.832816 loss: 0.000529 2022/09/15 02:15:19 - mmengine - INFO - Epoch(train) [132][150/586] lr: 5.000000e-04 eta: 5:41:20 time: 0.471800 data_time: 0.024587 memory: 15239 loss_kpt: 0.000531 acc_pose: 0.885085 loss: 0.000531 2022/09/15 02:15:42 - mmengine - INFO - Epoch(train) [132][200/586] lr: 5.000000e-04 eta: 5:40:58 time: 0.464487 data_time: 0.024909 memory: 15239 loss_kpt: 0.000536 acc_pose: 0.860746 loss: 0.000536 2022/09/15 02:15:58 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 02:16:05 - mmengine - INFO - Epoch(train) [132][250/586] lr: 5.000000e-04 eta: 5:40:37 time: 0.466348 data_time: 0.025319 memory: 15239 loss_kpt: 0.000520 acc_pose: 0.921532 loss: 0.000520 2022/09/15 02:16:29 - mmengine - INFO - Epoch(train) [132][300/586] lr: 5.000000e-04 eta: 5:40:15 time: 0.471638 data_time: 0.025960 memory: 15239 loss_kpt: 0.000531 acc_pose: 0.821800 loss: 0.000531 2022/09/15 02:16:52 - mmengine - INFO - Epoch(train) [132][350/586] lr: 5.000000e-04 eta: 5:39:54 time: 0.465759 data_time: 0.024954 memory: 15239 loss_kpt: 0.000543 acc_pose: 0.845360 loss: 0.000543 2022/09/15 02:17:16 - mmengine - INFO - Epoch(train) [132][400/586] lr: 5.000000e-04 eta: 5:39:32 time: 0.469300 data_time: 0.025393 memory: 15239 loss_kpt: 0.000541 acc_pose: 0.871680 loss: 0.000541 2022/09/15 02:17:39 - mmengine - INFO - Epoch(train) [132][450/586] lr: 5.000000e-04 eta: 5:39:11 time: 0.461157 data_time: 0.025041 memory: 15239 loss_kpt: 0.000523 acc_pose: 0.853250 loss: 0.000523 2022/09/15 02:18:03 - mmengine - INFO - Epoch(train) [132][500/586] lr: 5.000000e-04 eta: 5:38:49 time: 0.473433 data_time: 0.028873 memory: 15239 loss_kpt: 0.000529 acc_pose: 0.802532 loss: 0.000529 2022/09/15 02:18:26 - mmengine - INFO - Epoch(train) [132][550/586] lr: 5.000000e-04 eta: 5:38:28 time: 0.471276 data_time: 0.025118 memory: 15239 loss_kpt: 0.000512 acc_pose: 0.888590 loss: 0.000512 2022/09/15 02:18:43 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 02:18:43 - mmengine - INFO - Saving checkpoint at 132 epochs 2022/09/15 02:19:14 - mmengine - INFO - Epoch(train) [133][50/586] lr: 5.000000e-04 eta: 5:37:41 time: 0.485508 data_time: 0.032492 memory: 15239 loss_kpt: 0.000518 acc_pose: 0.855759 loss: 0.000518 2022/09/15 02:19:38 - mmengine - INFO - Epoch(train) [133][100/586] lr: 5.000000e-04 eta: 5:37:20 time: 0.480696 data_time: 0.030353 memory: 15239 loss_kpt: 0.000530 acc_pose: 0.852380 loss: 0.000530 2022/09/15 02:20:01 - mmengine - INFO - Epoch(train) [133][150/586] lr: 5.000000e-04 eta: 5:36:59 time: 0.470491 data_time: 0.029470 memory: 15239 loss_kpt: 0.000516 acc_pose: 0.807178 loss: 0.000516 2022/09/15 02:20:25 - mmengine - INFO - Epoch(train) [133][200/586] lr: 5.000000e-04 eta: 5:36:38 time: 0.470312 data_time: 0.033579 memory: 15239 loss_kpt: 0.000533 acc_pose: 0.887275 loss: 0.000533 2022/09/15 02:20:48 - mmengine - INFO - Epoch(train) [133][250/586] lr: 5.000000e-04 eta: 5:36:16 time: 0.471481 data_time: 0.031881 memory: 15239 loss_kpt: 0.000521 acc_pose: 0.878988 loss: 0.000521 2022/09/15 02:21:12 - mmengine - INFO - Epoch(train) [133][300/586] lr: 5.000000e-04 eta: 5:35:55 time: 0.476760 data_time: 0.034410 memory: 15239 loss_kpt: 0.000529 acc_pose: 0.806519 loss: 0.000529 2022/09/15 02:21:36 - mmengine - INFO - Epoch(train) [133][350/586] lr: 5.000000e-04 eta: 5:35:33 time: 0.466151 data_time: 0.030851 memory: 15239 loss_kpt: 0.000535 acc_pose: 0.824419 loss: 0.000535 2022/09/15 02:21:59 - mmengine - INFO - Epoch(train) [133][400/586] lr: 5.000000e-04 eta: 5:35:12 time: 0.476068 data_time: 0.035390 memory: 15239 loss_kpt: 0.000543 acc_pose: 0.891792 loss: 0.000543 2022/09/15 02:22:23 - mmengine - INFO - Epoch(train) [133][450/586] lr: 5.000000e-04 eta: 5:34:51 time: 0.471861 data_time: 0.032407 memory: 15239 loss_kpt: 0.000537 acc_pose: 0.854046 loss: 0.000537 2022/09/15 02:22:47 - mmengine - INFO - Epoch(train) [133][500/586] lr: 5.000000e-04 eta: 5:34:29 time: 0.470690 data_time: 0.032104 memory: 15239 loss_kpt: 0.000526 acc_pose: 0.906048 loss: 0.000526 2022/09/15 02:23:10 - mmengine - INFO - Epoch(train) [133][550/586] lr: 5.000000e-04 eta: 5:34:08 time: 0.470198 data_time: 0.031545 memory: 15239 loss_kpt: 0.000542 acc_pose: 0.858074 loss: 0.000542 2022/09/15 02:23:27 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 02:23:27 - mmengine - INFO - Saving checkpoint at 133 epochs 2022/09/15 02:23:57 - mmengine - INFO - Epoch(train) [134][50/586] lr: 5.000000e-04 eta: 5:33:21 time: 0.472882 data_time: 0.034429 memory: 15239 loss_kpt: 0.000532 acc_pose: 0.851503 loss: 0.000532 2022/09/15 02:24:03 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 02:24:21 - mmengine - INFO - Epoch(train) [134][100/586] lr: 5.000000e-04 eta: 5:33:00 time: 0.467499 data_time: 0.024912 memory: 15239 loss_kpt: 0.000536 acc_pose: 0.883530 loss: 0.000536 2022/09/15 02:24:44 - mmengine - INFO - Epoch(train) [134][150/586] lr: 5.000000e-04 eta: 5:32:38 time: 0.469279 data_time: 0.025306 memory: 15239 loss_kpt: 0.000529 acc_pose: 0.883176 loss: 0.000529 2022/09/15 02:25:08 - mmengine - INFO - Epoch(train) [134][200/586] lr: 5.000000e-04 eta: 5:32:17 time: 0.466667 data_time: 0.025310 memory: 15239 loss_kpt: 0.000525 acc_pose: 0.837517 loss: 0.000525 2022/09/15 02:25:31 - mmengine - INFO - Epoch(train) [134][250/586] lr: 5.000000e-04 eta: 5:31:55 time: 0.471502 data_time: 0.024570 memory: 15239 loss_kpt: 0.000536 acc_pose: 0.840073 loss: 0.000536 2022/09/15 02:25:55 - mmengine - INFO - Epoch(train) [134][300/586] lr: 5.000000e-04 eta: 5:31:34 time: 0.468839 data_time: 0.026089 memory: 15239 loss_kpt: 0.000543 acc_pose: 0.876189 loss: 0.000543 2022/09/15 02:26:18 - mmengine - INFO - Epoch(train) [134][350/586] lr: 5.000000e-04 eta: 5:31:13 time: 0.470326 data_time: 0.025039 memory: 15239 loss_kpt: 0.000526 acc_pose: 0.893288 loss: 0.000526 2022/09/15 02:26:41 - mmengine - INFO - Epoch(train) [134][400/586] lr: 5.000000e-04 eta: 5:30:51 time: 0.465090 data_time: 0.025625 memory: 15239 loss_kpt: 0.000543 acc_pose: 0.914693 loss: 0.000543 2022/09/15 02:27:05 - mmengine - INFO - Epoch(train) [134][450/586] lr: 5.000000e-04 eta: 5:30:29 time: 0.466940 data_time: 0.025942 memory: 15239 loss_kpt: 0.000525 acc_pose: 0.835328 loss: 0.000525 2022/09/15 02:27:28 - mmengine - INFO - Epoch(train) [134][500/586] lr: 5.000000e-04 eta: 5:30:08 time: 0.471484 data_time: 0.025561 memory: 15239 loss_kpt: 0.000524 acc_pose: 0.874504 loss: 0.000524 2022/09/15 02:27:52 - mmengine - INFO - Epoch(train) [134][550/586] lr: 5.000000e-04 eta: 5:29:47 time: 0.471044 data_time: 0.025287 memory: 15239 loss_kpt: 0.000526 acc_pose: 0.901908 loss: 0.000526 2022/09/15 02:28:09 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 02:28:09 - mmengine - INFO - Saving checkpoint at 134 epochs 2022/09/15 02:28:39 - mmengine - INFO - Epoch(train) [135][50/586] lr: 5.000000e-04 eta: 5:29:00 time: 0.473247 data_time: 0.034833 memory: 15239 loss_kpt: 0.000529 acc_pose: 0.867849 loss: 0.000529 2022/09/15 02:29:03 - mmengine - INFO - Epoch(train) [135][100/586] lr: 5.000000e-04 eta: 5:28:39 time: 0.470571 data_time: 0.024683 memory: 15239 loss_kpt: 0.000523 acc_pose: 0.820806 loss: 0.000523 2022/09/15 02:29:26 - mmengine - INFO - Epoch(train) [135][150/586] lr: 5.000000e-04 eta: 5:28:17 time: 0.470819 data_time: 0.025339 memory: 15239 loss_kpt: 0.000524 acc_pose: 0.880753 loss: 0.000524 2022/09/15 02:29:50 - mmengine - INFO - Epoch(train) [135][200/586] lr: 5.000000e-04 eta: 5:27:56 time: 0.468932 data_time: 0.025123 memory: 15239 loss_kpt: 0.000526 acc_pose: 0.864620 loss: 0.000526 2022/09/15 02:30:13 - mmengine - INFO - Epoch(train) [135][250/586] lr: 5.000000e-04 eta: 5:27:35 time: 0.474527 data_time: 0.026885 memory: 15239 loss_kpt: 0.000520 acc_pose: 0.873145 loss: 0.000520 2022/09/15 02:30:37 - mmengine - INFO - Epoch(train) [135][300/586] lr: 5.000000e-04 eta: 5:27:13 time: 0.463572 data_time: 0.025568 memory: 15239 loss_kpt: 0.000535 acc_pose: 0.863095 loss: 0.000535 2022/09/15 02:31:00 - mmengine - INFO - Epoch(train) [135][350/586] lr: 5.000000e-04 eta: 5:26:51 time: 0.468547 data_time: 0.028866 memory: 15239 loss_kpt: 0.000522 acc_pose: 0.833900 loss: 0.000522 2022/09/15 02:31:24 - mmengine - INFO - Epoch(train) [135][400/586] lr: 5.000000e-04 eta: 5:26:30 time: 0.470115 data_time: 0.025671 memory: 15239 loss_kpt: 0.000533 acc_pose: 0.843521 loss: 0.000533 2022/09/15 02:31:47 - mmengine - INFO - Epoch(train) [135][450/586] lr: 5.000000e-04 eta: 5:26:08 time: 0.462207 data_time: 0.025811 memory: 15239 loss_kpt: 0.000548 acc_pose: 0.840524 loss: 0.000548 2022/09/15 02:31:59 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 02:32:10 - mmengine - INFO - Epoch(train) [135][500/586] lr: 5.000000e-04 eta: 5:25:47 time: 0.464381 data_time: 0.024319 memory: 15239 loss_kpt: 0.000537 acc_pose: 0.782916 loss: 0.000537 2022/09/15 02:32:34 - mmengine - INFO - Epoch(train) [135][550/586] lr: 5.000000e-04 eta: 5:25:25 time: 0.471246 data_time: 0.024743 memory: 15239 loss_kpt: 0.000525 acc_pose: 0.895894 loss: 0.000525 2022/09/15 02:32:50 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 02:32:50 - mmengine - INFO - Saving checkpoint at 135 epochs 2022/09/15 02:33:21 - mmengine - INFO - Epoch(train) [136][50/586] lr: 5.000000e-04 eta: 5:24:39 time: 0.470060 data_time: 0.030890 memory: 15239 loss_kpt: 0.000538 acc_pose: 0.834063 loss: 0.000538 2022/09/15 02:33:45 - mmengine - INFO - Epoch(train) [136][100/586] lr: 5.000000e-04 eta: 5:24:18 time: 0.478392 data_time: 0.024765 memory: 15239 loss_kpt: 0.000539 acc_pose: 0.872576 loss: 0.000539 2022/09/15 02:34:08 - mmengine - INFO - Epoch(train) [136][150/586] lr: 5.000000e-04 eta: 5:23:56 time: 0.470171 data_time: 0.024802 memory: 15239 loss_kpt: 0.000536 acc_pose: 0.827928 loss: 0.000536 2022/09/15 02:34:32 - mmengine - INFO - Epoch(train) [136][200/586] lr: 5.000000e-04 eta: 5:23:35 time: 0.476870 data_time: 0.024874 memory: 15239 loss_kpt: 0.000528 acc_pose: 0.852482 loss: 0.000528 2022/09/15 02:34:56 - mmengine - INFO - Epoch(train) [136][250/586] lr: 5.000000e-04 eta: 5:23:14 time: 0.473727 data_time: 0.024957 memory: 15239 loss_kpt: 0.000536 acc_pose: 0.887436 loss: 0.000536 2022/09/15 02:35:19 - mmengine - INFO - Epoch(train) [136][300/586] lr: 5.000000e-04 eta: 5:22:52 time: 0.472869 data_time: 0.028518 memory: 15239 loss_kpt: 0.000534 acc_pose: 0.797894 loss: 0.000534 2022/09/15 02:35:43 - mmengine - INFO - Epoch(train) [136][350/586] lr: 5.000000e-04 eta: 5:22:31 time: 0.472923 data_time: 0.026219 memory: 15239 loss_kpt: 0.000540 acc_pose: 0.881150 loss: 0.000540 2022/09/15 02:36:06 - mmengine - INFO - Epoch(train) [136][400/586] lr: 5.000000e-04 eta: 5:22:09 time: 0.466754 data_time: 0.025405 memory: 15239 loss_kpt: 0.000537 acc_pose: 0.838026 loss: 0.000537 2022/09/15 02:36:30 - mmengine - INFO - Epoch(train) [136][450/586] lr: 5.000000e-04 eta: 5:21:48 time: 0.480333 data_time: 0.025520 memory: 15239 loss_kpt: 0.000503 acc_pose: 0.897297 loss: 0.000503 2022/09/15 02:36:54 - mmengine - INFO - Epoch(train) [136][500/586] lr: 5.000000e-04 eta: 5:21:26 time: 0.467129 data_time: 0.024794 memory: 15239 loss_kpt: 0.000543 acc_pose: 0.844179 loss: 0.000543 2022/09/15 02:37:17 - mmengine - INFO - Epoch(train) [136][550/586] lr: 5.000000e-04 eta: 5:21:05 time: 0.468286 data_time: 0.025500 memory: 15239 loss_kpt: 0.000520 acc_pose: 0.873289 loss: 0.000520 2022/09/15 02:37:34 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 02:37:34 - mmengine - INFO - Saving checkpoint at 136 epochs 2022/09/15 02:38:05 - mmengine - INFO - Epoch(train) [137][50/586] lr: 5.000000e-04 eta: 5:20:19 time: 0.488258 data_time: 0.036839 memory: 15239 loss_kpt: 0.000517 acc_pose: 0.901570 loss: 0.000517 2022/09/15 02:38:29 - mmengine - INFO - Epoch(train) [137][100/586] lr: 5.000000e-04 eta: 5:19:58 time: 0.477995 data_time: 0.034515 memory: 15239 loss_kpt: 0.000523 acc_pose: 0.868875 loss: 0.000523 2022/09/15 02:38:53 - mmengine - INFO - Epoch(train) [137][150/586] lr: 5.000000e-04 eta: 5:19:37 time: 0.479748 data_time: 0.029930 memory: 15239 loss_kpt: 0.000521 acc_pose: 0.837406 loss: 0.000521 2022/09/15 02:39:17 - mmengine - INFO - Epoch(train) [137][200/586] lr: 5.000000e-04 eta: 5:19:15 time: 0.475413 data_time: 0.029925 memory: 15239 loss_kpt: 0.000528 acc_pose: 0.862570 loss: 0.000528 2022/09/15 02:39:41 - mmengine - INFO - Epoch(train) [137][250/586] lr: 5.000000e-04 eta: 5:18:54 time: 0.480628 data_time: 0.033864 memory: 15239 loss_kpt: 0.000520 acc_pose: 0.845437 loss: 0.000520 2022/09/15 02:40:05 - mmengine - INFO - Epoch(train) [137][300/586] lr: 5.000000e-04 eta: 5:18:33 time: 0.472337 data_time: 0.033708 memory: 15239 loss_kpt: 0.000512 acc_pose: 0.890554 loss: 0.000512 2022/09/15 02:40:07 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 02:40:28 - mmengine - INFO - Epoch(train) [137][350/586] lr: 5.000000e-04 eta: 5:18:11 time: 0.473620 data_time: 0.025882 memory: 15239 loss_kpt: 0.000543 acc_pose: 0.869045 loss: 0.000543 2022/09/15 02:40:52 - mmengine - INFO - Epoch(train) [137][400/586] lr: 5.000000e-04 eta: 5:17:50 time: 0.465277 data_time: 0.025257 memory: 15239 loss_kpt: 0.000537 acc_pose: 0.859836 loss: 0.000537 2022/09/15 02:41:15 - mmengine - INFO - Epoch(train) [137][450/586] lr: 5.000000e-04 eta: 5:17:28 time: 0.470306 data_time: 0.024774 memory: 15239 loss_kpt: 0.000522 acc_pose: 0.864553 loss: 0.000522 2022/09/15 02:41:39 - mmengine - INFO - Epoch(train) [137][500/586] lr: 5.000000e-04 eta: 5:17:07 time: 0.474496 data_time: 0.025206 memory: 15239 loss_kpt: 0.000528 acc_pose: 0.791247 loss: 0.000528 2022/09/15 02:42:02 - mmengine - INFO - Epoch(train) [137][550/586] lr: 5.000000e-04 eta: 5:16:45 time: 0.466602 data_time: 0.025407 memory: 15239 loss_kpt: 0.000531 acc_pose: 0.872145 loss: 0.000531 2022/09/15 02:42:19 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 02:42:19 - mmengine - INFO - Saving checkpoint at 137 epochs 2022/09/15 02:42:50 - mmengine - INFO - Epoch(train) [138][50/586] lr: 5.000000e-04 eta: 5:16:00 time: 0.481779 data_time: 0.028713 memory: 15239 loss_kpt: 0.000523 acc_pose: 0.854474 loss: 0.000523 2022/09/15 02:43:14 - mmengine - INFO - Epoch(train) [138][100/586] lr: 5.000000e-04 eta: 5:15:38 time: 0.476435 data_time: 0.027935 memory: 15239 loss_kpt: 0.000519 acc_pose: 0.919394 loss: 0.000519 2022/09/15 02:43:37 - mmengine - INFO - Epoch(train) [138][150/586] lr: 5.000000e-04 eta: 5:15:17 time: 0.470770 data_time: 0.024216 memory: 15239 loss_kpt: 0.000505 acc_pose: 0.841831 loss: 0.000505 2022/09/15 02:44:01 - mmengine - INFO - Epoch(train) [138][200/586] lr: 5.000000e-04 eta: 5:14:56 time: 0.476969 data_time: 0.024582 memory: 15239 loss_kpt: 0.000538 acc_pose: 0.881770 loss: 0.000538 2022/09/15 02:44:25 - mmengine - INFO - Epoch(train) [138][250/586] lr: 5.000000e-04 eta: 5:14:34 time: 0.476502 data_time: 0.028891 memory: 15239 loss_kpt: 0.000513 acc_pose: 0.881922 loss: 0.000513 2022/09/15 02:44:49 - mmengine - INFO - Epoch(train) [138][300/586] lr: 5.000000e-04 eta: 5:14:13 time: 0.472437 data_time: 0.024848 memory: 15239 loss_kpt: 0.000538 acc_pose: 0.866591 loss: 0.000538 2022/09/15 02:45:12 - mmengine - INFO - Epoch(train) [138][350/586] lr: 5.000000e-04 eta: 5:13:51 time: 0.474756 data_time: 0.024735 memory: 15239 loss_kpt: 0.000526 acc_pose: 0.869436 loss: 0.000526 2022/09/15 02:45:36 - mmengine - INFO - Epoch(train) [138][400/586] lr: 5.000000e-04 eta: 5:13:30 time: 0.474432 data_time: 0.028669 memory: 15239 loss_kpt: 0.000531 acc_pose: 0.851532 loss: 0.000531 2022/09/15 02:46:00 - mmengine - INFO - Epoch(train) [138][450/586] lr: 5.000000e-04 eta: 5:13:09 time: 0.478376 data_time: 0.025636 memory: 15239 loss_kpt: 0.000543 acc_pose: 0.827708 loss: 0.000543 2022/09/15 02:46:24 - mmengine - INFO - Epoch(train) [138][500/586] lr: 5.000000e-04 eta: 5:12:47 time: 0.468442 data_time: 0.024478 memory: 15239 loss_kpt: 0.000527 acc_pose: 0.843663 loss: 0.000527 2022/09/15 02:46:47 - mmengine - INFO - Epoch(train) [138][550/586] lr: 5.000000e-04 eta: 5:12:26 time: 0.474500 data_time: 0.025036 memory: 15239 loss_kpt: 0.000525 acc_pose: 0.868829 loss: 0.000525 2022/09/15 02:47:04 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 02:47:04 - mmengine - INFO - Saving checkpoint at 138 epochs 2022/09/15 02:47:35 - mmengine - INFO - Epoch(train) [139][50/586] lr: 5.000000e-04 eta: 5:11:40 time: 0.476452 data_time: 0.029365 memory: 15239 loss_kpt: 0.000523 acc_pose: 0.872818 loss: 0.000523 2022/09/15 02:47:58 - mmengine - INFO - Epoch(train) [139][100/586] lr: 5.000000e-04 eta: 5:11:19 time: 0.464793 data_time: 0.025480 memory: 15239 loss_kpt: 0.000520 acc_pose: 0.896081 loss: 0.000520 2022/09/15 02:48:13 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 02:48:22 - mmengine - INFO - Epoch(train) [139][150/586] lr: 5.000000e-04 eta: 5:10:57 time: 0.471133 data_time: 0.025214 memory: 15239 loss_kpt: 0.000524 acc_pose: 0.856911 loss: 0.000524 2022/09/15 02:48:45 - mmengine - INFO - Epoch(train) [139][200/586] lr: 5.000000e-04 eta: 5:10:36 time: 0.477129 data_time: 0.029597 memory: 15239 loss_kpt: 0.000516 acc_pose: 0.858083 loss: 0.000516 2022/09/15 02:49:09 - mmengine - INFO - Epoch(train) [139][250/586] lr: 5.000000e-04 eta: 5:10:14 time: 0.466248 data_time: 0.024845 memory: 15239 loss_kpt: 0.000523 acc_pose: 0.853069 loss: 0.000523 2022/09/15 02:49:32 - mmengine - INFO - Epoch(train) [139][300/586] lr: 5.000000e-04 eta: 5:09:53 time: 0.474543 data_time: 0.025295 memory: 15239 loss_kpt: 0.000515 acc_pose: 0.885642 loss: 0.000515 2022/09/15 02:49:56 - mmengine - INFO - Epoch(train) [139][350/586] lr: 5.000000e-04 eta: 5:09:31 time: 0.475771 data_time: 0.024315 memory: 15239 loss_kpt: 0.000532 acc_pose: 0.826359 loss: 0.000532 2022/09/15 02:50:20 - mmengine - INFO - Epoch(train) [139][400/586] lr: 5.000000e-04 eta: 5:09:10 time: 0.473758 data_time: 0.024642 memory: 15239 loss_kpt: 0.000498 acc_pose: 0.853372 loss: 0.000498 2022/09/15 02:50:44 - mmengine - INFO - Epoch(train) [139][450/586] lr: 5.000000e-04 eta: 5:08:49 time: 0.474573 data_time: 0.024377 memory: 15239 loss_kpt: 0.000525 acc_pose: 0.884333 loss: 0.000525 2022/09/15 02:51:07 - mmengine - INFO - Epoch(train) [139][500/586] lr: 5.000000e-04 eta: 5:08:27 time: 0.475228 data_time: 0.028462 memory: 15239 loss_kpt: 0.000511 acc_pose: 0.821793 loss: 0.000511 2022/09/15 02:51:31 - mmengine - INFO - Epoch(train) [139][550/586] lr: 5.000000e-04 eta: 5:08:06 time: 0.473152 data_time: 0.024921 memory: 15239 loss_kpt: 0.000507 acc_pose: 0.908302 loss: 0.000507 2022/09/15 02:51:48 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 02:51:48 - mmengine - INFO - Saving checkpoint at 139 epochs 2022/09/15 02:52:19 - mmengine - INFO - Epoch(train) [140][50/586] lr: 5.000000e-04 eta: 5:07:20 time: 0.473188 data_time: 0.029254 memory: 15239 loss_kpt: 0.000510 acc_pose: 0.865859 loss: 0.000510 2022/09/15 02:52:43 - mmengine - INFO - Epoch(train) [140][100/586] lr: 5.000000e-04 eta: 5:06:59 time: 0.478590 data_time: 0.024614 memory: 15239 loss_kpt: 0.000524 acc_pose: 0.879438 loss: 0.000524 2022/09/15 02:53:06 - mmengine - INFO - Epoch(train) [140][150/586] lr: 5.000000e-04 eta: 5:06:37 time: 0.470367 data_time: 0.025021 memory: 15239 loss_kpt: 0.000530 acc_pose: 0.849446 loss: 0.000530 2022/09/15 02:53:30 - mmengine - INFO - Epoch(train) [140][200/586] lr: 5.000000e-04 eta: 5:06:16 time: 0.470852 data_time: 0.024809 memory: 15239 loss_kpt: 0.000529 acc_pose: 0.834477 loss: 0.000529 2022/09/15 02:53:54 - mmengine - INFO - Epoch(train) [140][250/586] lr: 5.000000e-04 eta: 5:05:54 time: 0.476944 data_time: 0.025117 memory: 15239 loss_kpt: 0.000520 acc_pose: 0.822599 loss: 0.000520 2022/09/15 02:54:17 - mmengine - INFO - Epoch(train) [140][300/586] lr: 5.000000e-04 eta: 5:05:33 time: 0.468541 data_time: 0.025200 memory: 15239 loss_kpt: 0.000526 acc_pose: 0.815694 loss: 0.000526 2022/09/15 02:54:41 - mmengine - INFO - Epoch(train) [140][350/586] lr: 5.000000e-04 eta: 5:05:11 time: 0.470526 data_time: 0.025008 memory: 15239 loss_kpt: 0.000512 acc_pose: 0.868813 loss: 0.000512 2022/09/15 02:55:04 - mmengine - INFO - Epoch(train) [140][400/586] lr: 5.000000e-04 eta: 5:04:50 time: 0.471505 data_time: 0.029212 memory: 15239 loss_kpt: 0.000531 acc_pose: 0.901700 loss: 0.000531 2022/09/15 02:55:27 - mmengine - INFO - Epoch(train) [140][450/586] lr: 5.000000e-04 eta: 5:04:28 time: 0.467377 data_time: 0.024751 memory: 15239 loss_kpt: 0.000536 acc_pose: 0.908306 loss: 0.000536 2022/09/15 02:55:51 - mmengine - INFO - Epoch(train) [140][500/586] lr: 5.000000e-04 eta: 5:04:07 time: 0.467692 data_time: 0.025142 memory: 15239 loss_kpt: 0.000530 acc_pose: 0.862286 loss: 0.000530 2022/09/15 02:56:13 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 02:56:14 - mmengine - INFO - Epoch(train) [140][550/586] lr: 5.000000e-04 eta: 5:03:45 time: 0.471669 data_time: 0.024588 memory: 15239 loss_kpt: 0.000516 acc_pose: 0.852476 loss: 0.000516 2022/09/15 02:56:31 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 02:56:31 - mmengine - INFO - Saving checkpoint at 140 epochs 2022/09/15 02:56:49 - mmengine - INFO - Epoch(val) [140][50/407] eta: 0:01:14 time: 0.208121 data_time: 0.019003 memory: 15239 2022/09/15 02:56:59 - mmengine - INFO - Epoch(val) [140][100/407] eta: 0:01:00 time: 0.197078 data_time: 0.009082 memory: 2064 2022/09/15 02:57:08 - mmengine - INFO - Epoch(val) [140][150/407] eta: 0:00:50 time: 0.195080 data_time: 0.008508 memory: 2064 2022/09/15 02:57:18 - mmengine - INFO - Epoch(val) [140][200/407] eta: 0:00:40 time: 0.195405 data_time: 0.008453 memory: 2064 2022/09/15 02:57:28 - mmengine - INFO - Epoch(val) [140][250/407] eta: 0:00:30 time: 0.195815 data_time: 0.008508 memory: 2064 2022/09/15 02:57:38 - mmengine - INFO - Epoch(val) [140][300/407] eta: 0:00:20 time: 0.195246 data_time: 0.008184 memory: 2064 2022/09/15 02:57:48 - mmengine - INFO - Epoch(val) [140][350/407] eta: 0:00:11 time: 0.194908 data_time: 0.008174 memory: 2064 2022/09/15 02:57:57 - mmengine - INFO - Epoch(val) [140][400/407] eta: 0:00:01 time: 0.192802 data_time: 0.007740 memory: 2064 2022/09/15 02:58:34 - mmengine - INFO - Evaluating CocoMetric... 2022/09/15 02:58:48 - mmengine - INFO - Epoch(val) [140][407/407] coco/AP: 0.758034 coco/AP .5: 0.908026 coco/AP .75: 0.824318 coco/AP (M): 0.718559 coco/AP (L): 0.829549 coco/AR: 0.807525 coco/AR .5: 0.941908 coco/AR .75: 0.867443 coco/AR (M): 0.762196 coco/AR (L): 0.872761 2022/09/15 02:59:13 - mmengine - INFO - Epoch(train) [141][50/586] lr: 5.000000e-04 eta: 5:03:00 time: 0.498928 data_time: 0.034375 memory: 15239 loss_kpt: 0.000530 acc_pose: 0.859381 loss: 0.000530 2022/09/15 02:59:36 - mmengine - INFO - Epoch(train) [141][100/586] lr: 5.000000e-04 eta: 5:02:39 time: 0.473377 data_time: 0.028210 memory: 15239 loss_kpt: 0.000533 acc_pose: 0.891320 loss: 0.000533 2022/09/15 03:00:01 - mmengine - INFO - Epoch(train) [141][150/586] lr: 5.000000e-04 eta: 5:02:18 time: 0.484002 data_time: 0.024864 memory: 15239 loss_kpt: 0.000521 acc_pose: 0.839463 loss: 0.000521 2022/09/15 03:00:24 - mmengine - INFO - Epoch(train) [141][200/586] lr: 5.000000e-04 eta: 5:01:56 time: 0.464615 data_time: 0.025033 memory: 15239 loss_kpt: 0.000526 acc_pose: 0.885526 loss: 0.000526 2022/09/15 03:00:48 - mmengine - INFO - Epoch(train) [141][250/586] lr: 5.000000e-04 eta: 5:01:35 time: 0.482116 data_time: 0.028859 memory: 15239 loss_kpt: 0.000523 acc_pose: 0.922115 loss: 0.000523 2022/09/15 03:01:12 - mmengine - INFO - Epoch(train) [141][300/586] lr: 5.000000e-04 eta: 5:01:13 time: 0.473960 data_time: 0.025698 memory: 15239 loss_kpt: 0.000543 acc_pose: 0.888416 loss: 0.000543 2022/09/15 03:01:36 - mmengine - INFO - Epoch(train) [141][350/586] lr: 5.000000e-04 eta: 5:00:52 time: 0.474586 data_time: 0.025260 memory: 15239 loss_kpt: 0.000534 acc_pose: 0.873170 loss: 0.000534 2022/09/15 03:01:59 - mmengine - INFO - Epoch(train) [141][400/586] lr: 5.000000e-04 eta: 5:00:30 time: 0.471175 data_time: 0.028847 memory: 15239 loss_kpt: 0.000516 acc_pose: 0.880326 loss: 0.000516 2022/09/15 03:02:22 - mmengine - INFO - Epoch(train) [141][450/586] lr: 5.000000e-04 eta: 5:00:09 time: 0.466899 data_time: 0.024958 memory: 15239 loss_kpt: 0.000512 acc_pose: 0.917186 loss: 0.000512 2022/09/15 03:02:46 - mmengine - INFO - Epoch(train) [141][500/586] lr: 5.000000e-04 eta: 4:59:47 time: 0.468859 data_time: 0.025025 memory: 15239 loss_kpt: 0.000524 acc_pose: 0.864380 loss: 0.000524 2022/09/15 03:03:09 - mmengine - INFO - Epoch(train) [141][550/586] lr: 5.000000e-04 eta: 4:59:26 time: 0.470849 data_time: 0.028955 memory: 15239 loss_kpt: 0.000533 acc_pose: 0.864455 loss: 0.000533 2022/09/15 03:03:27 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 03:03:27 - mmengine - INFO - Saving checkpoint at 141 epochs 2022/09/15 03:03:57 - mmengine - INFO - Epoch(train) [142][50/586] lr: 5.000000e-04 eta: 4:58:41 time: 0.480827 data_time: 0.038087 memory: 15239 loss_kpt: 0.000508 acc_pose: 0.797648 loss: 0.000508 2022/09/15 03:04:21 - mmengine - INFO - Epoch(train) [142][100/586] lr: 5.000000e-04 eta: 4:58:19 time: 0.465349 data_time: 0.028713 memory: 15239 loss_kpt: 0.000509 acc_pose: 0.887761 loss: 0.000509 2022/09/15 03:04:44 - mmengine - INFO - Epoch(train) [142][150/586] lr: 5.000000e-04 eta: 4:57:57 time: 0.474690 data_time: 0.031446 memory: 15239 loss_kpt: 0.000535 acc_pose: 0.835752 loss: 0.000535 2022/09/15 03:05:08 - mmengine - INFO - Epoch(train) [142][200/586] lr: 5.000000e-04 eta: 4:57:36 time: 0.473708 data_time: 0.028297 memory: 15239 loss_kpt: 0.000534 acc_pose: 0.889921 loss: 0.000534 2022/09/15 03:05:32 - mmengine - INFO - Epoch(train) [142][250/586] lr: 5.000000e-04 eta: 4:57:15 time: 0.479492 data_time: 0.026222 memory: 15239 loss_kpt: 0.000523 acc_pose: 0.850411 loss: 0.000523 2022/09/15 03:05:56 - mmengine - INFO - Epoch(train) [142][300/586] lr: 5.000000e-04 eta: 4:56:53 time: 0.469701 data_time: 0.024639 memory: 15239 loss_kpt: 0.000518 acc_pose: 0.893815 loss: 0.000518 2022/09/15 03:06:19 - mmengine - INFO - Epoch(train) [142][350/586] lr: 5.000000e-04 eta: 4:56:32 time: 0.468871 data_time: 0.025342 memory: 15239 loss_kpt: 0.000545 acc_pose: 0.858890 loss: 0.000545 2022/09/15 03:06:30 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 03:06:43 - mmengine - INFO - Epoch(train) [142][400/586] lr: 5.000000e-04 eta: 4:56:10 time: 0.468381 data_time: 0.028815 memory: 15239 loss_kpt: 0.000534 acc_pose: 0.859866 loss: 0.000534 2022/09/15 03:07:06 - mmengine - INFO - Epoch(train) [142][450/586] lr: 5.000000e-04 eta: 4:55:48 time: 0.474455 data_time: 0.025180 memory: 15239 loss_kpt: 0.000528 acc_pose: 0.911011 loss: 0.000528 2022/09/15 03:07:30 - mmengine - INFO - Epoch(train) [142][500/586] lr: 5.000000e-04 eta: 4:55:27 time: 0.470357 data_time: 0.025348 memory: 15239 loss_kpt: 0.000504 acc_pose: 0.887831 loss: 0.000504 2022/09/15 03:07:54 - mmengine - INFO - Epoch(train) [142][550/586] lr: 5.000000e-04 eta: 4:55:05 time: 0.474208 data_time: 0.024845 memory: 15239 loss_kpt: 0.000530 acc_pose: 0.878208 loss: 0.000530 2022/09/15 03:08:11 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 03:08:11 - mmengine - INFO - Saving checkpoint at 142 epochs 2022/09/15 03:08:41 - mmengine - INFO - Epoch(train) [143][50/586] lr: 5.000000e-04 eta: 4:54:21 time: 0.481838 data_time: 0.030253 memory: 15239 loss_kpt: 0.000526 acc_pose: 0.809207 loss: 0.000526 2022/09/15 03:09:05 - mmengine - INFO - Epoch(train) [143][100/586] lr: 5.000000e-04 eta: 4:53:59 time: 0.466894 data_time: 0.025462 memory: 15239 loss_kpt: 0.000526 acc_pose: 0.853851 loss: 0.000526 2022/09/15 03:09:29 - mmengine - INFO - Epoch(train) [143][150/586] lr: 5.000000e-04 eta: 4:53:38 time: 0.477439 data_time: 0.024171 memory: 15239 loss_kpt: 0.000525 acc_pose: 0.907368 loss: 0.000525 2022/09/15 03:09:52 - mmengine - INFO - Epoch(train) [143][200/586] lr: 5.000000e-04 eta: 4:53:16 time: 0.470516 data_time: 0.027464 memory: 15239 loss_kpt: 0.000526 acc_pose: 0.871387 loss: 0.000526 2022/09/15 03:10:16 - mmengine - INFO - Epoch(train) [143][250/586] lr: 5.000000e-04 eta: 4:52:54 time: 0.474347 data_time: 0.024409 memory: 15239 loss_kpt: 0.000514 acc_pose: 0.857504 loss: 0.000514 2022/09/15 03:10:40 - mmengine - INFO - Epoch(train) [143][300/586] lr: 5.000000e-04 eta: 4:52:33 time: 0.476380 data_time: 0.023890 memory: 15239 loss_kpt: 0.000522 acc_pose: 0.880391 loss: 0.000522 2022/09/15 03:11:04 - mmengine - INFO - Epoch(train) [143][350/586] lr: 5.000000e-04 eta: 4:52:12 time: 0.478154 data_time: 0.025339 memory: 15239 loss_kpt: 0.000521 acc_pose: 0.852901 loss: 0.000521 2022/09/15 03:11:28 - mmengine - INFO - Epoch(train) [143][400/586] lr: 5.000000e-04 eta: 4:51:50 time: 0.478348 data_time: 0.024369 memory: 15239 loss_kpt: 0.000510 acc_pose: 0.876639 loss: 0.000510 2022/09/15 03:11:51 - mmengine - INFO - Epoch(train) [143][450/586] lr: 5.000000e-04 eta: 4:51:29 time: 0.470381 data_time: 0.024993 memory: 15239 loss_kpt: 0.000516 acc_pose: 0.789426 loss: 0.000516 2022/09/15 03:12:15 - mmengine - INFO - Epoch(train) [143][500/586] lr: 5.000000e-04 eta: 4:51:07 time: 0.477144 data_time: 0.024987 memory: 15239 loss_kpt: 0.000543 acc_pose: 0.881836 loss: 0.000543 2022/09/15 03:12:38 - mmengine - INFO - Epoch(train) [143][550/586] lr: 5.000000e-04 eta: 4:50:46 time: 0.463900 data_time: 0.024409 memory: 15239 loss_kpt: 0.000525 acc_pose: 0.873488 loss: 0.000525 2022/09/15 03:12:55 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 03:12:55 - mmengine - INFO - Saving checkpoint at 143 epochs 2022/09/15 03:13:26 - mmengine - INFO - Epoch(train) [144][50/586] lr: 5.000000e-04 eta: 4:50:01 time: 0.477153 data_time: 0.033572 memory: 15239 loss_kpt: 0.000522 acc_pose: 0.904717 loss: 0.000522 2022/09/15 03:13:50 - mmengine - INFO - Epoch(train) [144][100/586] lr: 5.000000e-04 eta: 4:49:39 time: 0.481401 data_time: 0.029221 memory: 15239 loss_kpt: 0.000516 acc_pose: 0.850819 loss: 0.000516 2022/09/15 03:14:14 - mmengine - INFO - Epoch(train) [144][150/586] lr: 5.000000e-04 eta: 4:49:18 time: 0.477769 data_time: 0.025236 memory: 15239 loss_kpt: 0.000514 acc_pose: 0.946102 loss: 0.000514 2022/09/15 03:14:37 - mmengine - INFO - Epoch(train) [144][200/586] lr: 5.000000e-04 eta: 4:48:56 time: 0.469235 data_time: 0.024630 memory: 15239 loss_kpt: 0.000538 acc_pose: 0.751298 loss: 0.000538 2022/09/15 03:14:38 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 03:15:01 - mmengine - INFO - Epoch(train) [144][250/586] lr: 5.000000e-04 eta: 4:48:35 time: 0.477987 data_time: 0.028281 memory: 15239 loss_kpt: 0.000526 acc_pose: 0.879522 loss: 0.000526 2022/09/15 03:15:25 - mmengine - INFO - Epoch(train) [144][300/586] lr: 5.000000e-04 eta: 4:48:13 time: 0.471121 data_time: 0.024340 memory: 15239 loss_kpt: 0.000522 acc_pose: 0.838388 loss: 0.000522 2022/09/15 03:15:48 - mmengine - INFO - Epoch(train) [144][350/586] lr: 5.000000e-04 eta: 4:47:52 time: 0.472862 data_time: 0.025998 memory: 15239 loss_kpt: 0.000513 acc_pose: 0.912385 loss: 0.000513 2022/09/15 03:16:12 - mmengine - INFO - Epoch(train) [144][400/586] lr: 5.000000e-04 eta: 4:47:30 time: 0.472918 data_time: 0.025209 memory: 15239 loss_kpt: 0.000521 acc_pose: 0.904042 loss: 0.000521 2022/09/15 03:16:36 - mmengine - INFO - Epoch(train) [144][450/586] lr: 5.000000e-04 eta: 4:47:09 time: 0.484526 data_time: 0.024640 memory: 15239 loss_kpt: 0.000534 acc_pose: 0.877488 loss: 0.000534 2022/09/15 03:17:00 - mmengine - INFO - Epoch(train) [144][500/586] lr: 5.000000e-04 eta: 4:46:48 time: 0.474871 data_time: 0.025547 memory: 15239 loss_kpt: 0.000509 acc_pose: 0.860732 loss: 0.000509 2022/09/15 03:17:24 - mmengine - INFO - Epoch(train) [144][550/586] lr: 5.000000e-04 eta: 4:46:26 time: 0.473157 data_time: 0.024865 memory: 15239 loss_kpt: 0.000511 acc_pose: 0.830489 loss: 0.000511 2022/09/15 03:17:41 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 03:17:41 - mmengine - INFO - Saving checkpoint at 144 epochs 2022/09/15 03:18:12 - mmengine - INFO - Epoch(train) [145][50/586] lr: 5.000000e-04 eta: 4:45:42 time: 0.485420 data_time: 0.028263 memory: 15239 loss_kpt: 0.000509 acc_pose: 0.857275 loss: 0.000509 2022/09/15 03:18:36 - mmengine - INFO - Epoch(train) [145][100/586] lr: 5.000000e-04 eta: 4:45:20 time: 0.476422 data_time: 0.025129 memory: 15239 loss_kpt: 0.000521 acc_pose: 0.809834 loss: 0.000521 2022/09/15 03:19:00 - mmengine - INFO - Epoch(train) [145][150/586] lr: 5.000000e-04 eta: 4:44:59 time: 0.477129 data_time: 0.025010 memory: 15239 loss_kpt: 0.000523 acc_pose: 0.835661 loss: 0.000523 2022/09/15 03:19:23 - mmengine - INFO - Epoch(train) [145][200/586] lr: 5.000000e-04 eta: 4:44:37 time: 0.475538 data_time: 0.024855 memory: 15239 loss_kpt: 0.000523 acc_pose: 0.855822 loss: 0.000523 2022/09/15 03:19:47 - mmengine - INFO - Epoch(train) [145][250/586] lr: 5.000000e-04 eta: 4:44:16 time: 0.477365 data_time: 0.025363 memory: 15239 loss_kpt: 0.000534 acc_pose: 0.805750 loss: 0.000534 2022/09/15 03:20:11 - mmengine - INFO - Epoch(train) [145][300/586] lr: 5.000000e-04 eta: 4:43:54 time: 0.474409 data_time: 0.024668 memory: 15239 loss_kpt: 0.000526 acc_pose: 0.859096 loss: 0.000526 2022/09/15 03:20:35 - mmengine - INFO - Epoch(train) [145][350/586] lr: 5.000000e-04 eta: 4:43:33 time: 0.475640 data_time: 0.024363 memory: 15239 loss_kpt: 0.000521 acc_pose: 0.826501 loss: 0.000521 2022/09/15 03:20:58 - mmengine - INFO - Epoch(train) [145][400/586] lr: 5.000000e-04 eta: 4:43:11 time: 0.466325 data_time: 0.024490 memory: 15239 loss_kpt: 0.000528 acc_pose: 0.879328 loss: 0.000528 2022/09/15 03:21:22 - mmengine - INFO - Epoch(train) [145][450/586] lr: 5.000000e-04 eta: 4:42:50 time: 0.472313 data_time: 0.025115 memory: 15239 loss_kpt: 0.000527 acc_pose: 0.898693 loss: 0.000527 2022/09/15 03:21:45 - mmengine - INFO - Epoch(train) [145][500/586] lr: 5.000000e-04 eta: 4:42:28 time: 0.468769 data_time: 0.024310 memory: 15239 loss_kpt: 0.000529 acc_pose: 0.887160 loss: 0.000529 2022/09/15 03:22:09 - mmengine - INFO - Epoch(train) [145][550/586] lr: 5.000000e-04 eta: 4:42:06 time: 0.473091 data_time: 0.024956 memory: 15239 loss_kpt: 0.000531 acc_pose: 0.822400 loss: 0.000531 2022/09/15 03:22:26 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 03:22:26 - mmengine - INFO - Saving checkpoint at 145 epochs 2022/09/15 03:22:47 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 03:22:57 - mmengine - INFO - Epoch(train) [146][50/586] lr: 5.000000e-04 eta: 4:41:22 time: 0.490699 data_time: 0.036400 memory: 15239 loss_kpt: 0.000535 acc_pose: 0.886173 loss: 0.000535 2022/09/15 03:23:21 - mmengine - INFO - Epoch(train) [146][100/586] lr: 5.000000e-04 eta: 4:41:01 time: 0.480909 data_time: 0.031578 memory: 15239 loss_kpt: 0.000527 acc_pose: 0.855671 loss: 0.000527 2022/09/15 03:23:45 - mmengine - INFO - Epoch(train) [146][150/586] lr: 5.000000e-04 eta: 4:40:39 time: 0.474246 data_time: 0.025002 memory: 15239 loss_kpt: 0.000518 acc_pose: 0.893008 loss: 0.000518 2022/09/15 03:24:09 - mmengine - INFO - Epoch(train) [146][200/586] lr: 5.000000e-04 eta: 4:40:18 time: 0.477358 data_time: 0.024959 memory: 15239 loss_kpt: 0.000517 acc_pose: 0.838527 loss: 0.000517 2022/09/15 03:24:32 - mmengine - INFO - Epoch(train) [146][250/586] lr: 5.000000e-04 eta: 4:39:56 time: 0.472793 data_time: 0.025086 memory: 15239 loss_kpt: 0.000508 acc_pose: 0.778685 loss: 0.000508 2022/09/15 03:24:56 - mmengine - INFO - Epoch(train) [146][300/586] lr: 5.000000e-04 eta: 4:39:35 time: 0.479216 data_time: 0.024519 memory: 15239 loss_kpt: 0.000518 acc_pose: 0.828684 loss: 0.000518 2022/09/15 03:25:20 - mmengine - INFO - Epoch(train) [146][350/586] lr: 5.000000e-04 eta: 4:39:13 time: 0.468595 data_time: 0.024297 memory: 15239 loss_kpt: 0.000521 acc_pose: 0.881692 loss: 0.000521 2022/09/15 03:25:43 - mmengine - INFO - Epoch(train) [146][400/586] lr: 5.000000e-04 eta: 4:38:52 time: 0.467500 data_time: 0.027830 memory: 15239 loss_kpt: 0.000523 acc_pose: 0.833042 loss: 0.000523 2022/09/15 03:26:07 - mmengine - INFO - Epoch(train) [146][450/586] lr: 5.000000e-04 eta: 4:38:30 time: 0.478011 data_time: 0.025537 memory: 15239 loss_kpt: 0.000534 acc_pose: 0.812105 loss: 0.000534 2022/09/15 03:26:31 - mmengine - INFO - Epoch(train) [146][500/586] lr: 5.000000e-04 eta: 4:38:08 time: 0.470996 data_time: 0.024420 memory: 15239 loss_kpt: 0.000518 acc_pose: 0.870306 loss: 0.000518 2022/09/15 03:26:54 - mmengine - INFO - Epoch(train) [146][550/586] lr: 5.000000e-04 eta: 4:37:47 time: 0.473154 data_time: 0.025362 memory: 15239 loss_kpt: 0.000521 acc_pose: 0.820708 loss: 0.000521 2022/09/15 03:27:11 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 03:27:11 - mmengine - INFO - Saving checkpoint at 146 epochs 2022/09/15 03:27:42 - mmengine - INFO - Epoch(train) [147][50/586] lr: 5.000000e-04 eta: 4:37:03 time: 0.481889 data_time: 0.029498 memory: 15239 loss_kpt: 0.000511 acc_pose: 0.851322 loss: 0.000511 2022/09/15 03:28:06 - mmengine - INFO - Epoch(train) [147][100/586] lr: 5.000000e-04 eta: 4:36:41 time: 0.478599 data_time: 0.024400 memory: 15239 loss_kpt: 0.000508 acc_pose: 0.887576 loss: 0.000508 2022/09/15 03:28:30 - mmengine - INFO - Epoch(train) [147][150/586] lr: 5.000000e-04 eta: 4:36:20 time: 0.476669 data_time: 0.025073 memory: 15239 loss_kpt: 0.000536 acc_pose: 0.860539 loss: 0.000536 2022/09/15 03:28:53 - mmengine - INFO - Epoch(train) [147][200/586] lr: 5.000000e-04 eta: 4:35:58 time: 0.471248 data_time: 0.028430 memory: 15239 loss_kpt: 0.000531 acc_pose: 0.822699 loss: 0.000531 2022/09/15 03:29:17 - mmengine - INFO - Epoch(train) [147][250/586] lr: 5.000000e-04 eta: 4:35:36 time: 0.473997 data_time: 0.024741 memory: 15239 loss_kpt: 0.000516 acc_pose: 0.861252 loss: 0.000516 2022/09/15 03:29:41 - mmengine - INFO - Epoch(train) [147][300/586] lr: 5.000000e-04 eta: 4:35:15 time: 0.472568 data_time: 0.024975 memory: 15239 loss_kpt: 0.000532 acc_pose: 0.867358 loss: 0.000532 2022/09/15 03:30:04 - mmengine - INFO - Epoch(train) [147][350/586] lr: 5.000000e-04 eta: 4:34:53 time: 0.468744 data_time: 0.024622 memory: 15239 loss_kpt: 0.000531 acc_pose: 0.901700 loss: 0.000531 2022/09/15 03:30:28 - mmengine - INFO - Epoch(train) [147][400/586] lr: 5.000000e-04 eta: 4:34:32 time: 0.483657 data_time: 0.025235 memory: 15239 loss_kpt: 0.000521 acc_pose: 0.893556 loss: 0.000521 2022/09/15 03:30:49 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 03:30:52 - mmengine - INFO - Epoch(train) [147][450/586] lr: 5.000000e-04 eta: 4:34:10 time: 0.467189 data_time: 0.025527 memory: 15239 loss_kpt: 0.000534 acc_pose: 0.899024 loss: 0.000534 2022/09/15 03:31:16 - mmengine - INFO - Epoch(train) [147][500/586] lr: 5.000000e-04 eta: 4:33:49 time: 0.483099 data_time: 0.029165 memory: 15239 loss_kpt: 0.000535 acc_pose: 0.815628 loss: 0.000535 2022/09/15 03:31:39 - mmengine - INFO - Epoch(train) [147][550/586] lr: 5.000000e-04 eta: 4:33:27 time: 0.470249 data_time: 0.024809 memory: 15239 loss_kpt: 0.000525 acc_pose: 0.897613 loss: 0.000525 2022/09/15 03:31:56 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 03:31:56 - mmengine - INFO - Saving checkpoint at 147 epochs 2022/09/15 03:32:27 - mmengine - INFO - Epoch(train) [148][50/586] lr: 5.000000e-04 eta: 4:32:43 time: 0.493334 data_time: 0.033643 memory: 15239 loss_kpt: 0.000504 acc_pose: 0.899584 loss: 0.000504 2022/09/15 03:32:51 - mmengine - INFO - Epoch(train) [148][100/586] lr: 5.000000e-04 eta: 4:32:22 time: 0.476537 data_time: 0.031816 memory: 15239 loss_kpt: 0.000529 acc_pose: 0.892254 loss: 0.000529 2022/09/15 03:33:15 - mmengine - INFO - Epoch(train) [148][150/586] lr: 5.000000e-04 eta: 4:32:00 time: 0.469686 data_time: 0.028946 memory: 15239 loss_kpt: 0.000511 acc_pose: 0.862853 loss: 0.000511 2022/09/15 03:33:38 - mmengine - INFO - Epoch(train) [148][200/586] lr: 5.000000e-04 eta: 4:31:39 time: 0.471264 data_time: 0.029827 memory: 15239 loss_kpt: 0.000508 acc_pose: 0.880047 loss: 0.000508 2022/09/15 03:34:01 - mmengine - INFO - Epoch(train) [148][250/586] lr: 5.000000e-04 eta: 4:31:17 time: 0.466947 data_time: 0.028259 memory: 15239 loss_kpt: 0.000511 acc_pose: 0.807625 loss: 0.000511 2022/09/15 03:34:25 - mmengine - INFO - Epoch(train) [148][300/586] lr: 5.000000e-04 eta: 4:30:55 time: 0.470967 data_time: 0.031914 memory: 15239 loss_kpt: 0.000532 acc_pose: 0.871125 loss: 0.000532 2022/09/15 03:34:49 - mmengine - INFO - Epoch(train) [148][350/586] lr: 5.000000e-04 eta: 4:30:34 time: 0.469330 data_time: 0.025774 memory: 15239 loss_kpt: 0.000519 acc_pose: 0.848640 loss: 0.000519 2022/09/15 03:35:12 - mmengine - INFO - Epoch(train) [148][400/586] lr: 5.000000e-04 eta: 4:30:12 time: 0.468681 data_time: 0.024496 memory: 15239 loss_kpt: 0.000520 acc_pose: 0.777421 loss: 0.000520 2022/09/15 03:35:35 - mmengine - INFO - Epoch(train) [148][450/586] lr: 5.000000e-04 eta: 4:29:50 time: 0.469809 data_time: 0.025179 memory: 15239 loss_kpt: 0.000519 acc_pose: 0.744380 loss: 0.000519 2022/09/15 03:35:59 - mmengine - INFO - Epoch(train) [148][500/586] lr: 5.000000e-04 eta: 4:29:29 time: 0.470752 data_time: 0.028427 memory: 15239 loss_kpt: 0.000527 acc_pose: 0.891455 loss: 0.000527 2022/09/15 03:36:23 - mmengine - INFO - Epoch(train) [148][550/586] lr: 5.000000e-04 eta: 4:29:07 time: 0.471696 data_time: 0.025140 memory: 15239 loss_kpt: 0.000533 acc_pose: 0.839641 loss: 0.000533 2022/09/15 03:36:39 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 03:36:39 - mmengine - INFO - Saving checkpoint at 148 epochs 2022/09/15 03:37:10 - mmengine - INFO - Epoch(train) [149][50/586] lr: 5.000000e-04 eta: 4:28:23 time: 0.483393 data_time: 0.033157 memory: 15239 loss_kpt: 0.000534 acc_pose: 0.803378 loss: 0.000534 2022/09/15 03:37:34 - mmengine - INFO - Epoch(train) [149][100/586] lr: 5.000000e-04 eta: 4:28:01 time: 0.474370 data_time: 0.032243 memory: 15239 loss_kpt: 0.000518 acc_pose: 0.848784 loss: 0.000518 2022/09/15 03:37:57 - mmengine - INFO - Epoch(train) [149][150/586] lr: 5.000000e-04 eta: 4:27:40 time: 0.471562 data_time: 0.029258 memory: 15239 loss_kpt: 0.000521 acc_pose: 0.835672 loss: 0.000521 2022/09/15 03:38:22 - mmengine - INFO - Epoch(train) [149][200/586] lr: 5.000000e-04 eta: 4:27:18 time: 0.484800 data_time: 0.033597 memory: 15239 loss_kpt: 0.000521 acc_pose: 0.867978 loss: 0.000521 2022/09/15 03:38:45 - mmengine - INFO - Epoch(train) [149][250/586] lr: 5.000000e-04 eta: 4:26:57 time: 0.470014 data_time: 0.028632 memory: 15239 loss_kpt: 0.000536 acc_pose: 0.893503 loss: 0.000536 2022/09/15 03:38:56 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 03:39:09 - mmengine - INFO - Epoch(train) [149][300/586] lr: 5.000000e-04 eta: 4:26:35 time: 0.476332 data_time: 0.026903 memory: 15239 loss_kpt: 0.000508 acc_pose: 0.891532 loss: 0.000508 2022/09/15 03:39:33 - mmengine - INFO - Epoch(train) [149][350/586] lr: 5.000000e-04 eta: 4:26:14 time: 0.483160 data_time: 0.025748 memory: 15239 loss_kpt: 0.000534 acc_pose: 0.901569 loss: 0.000534 2022/09/15 03:39:57 - mmengine - INFO - Epoch(train) [149][400/586] lr: 5.000000e-04 eta: 4:25:52 time: 0.481170 data_time: 0.024790 memory: 15239 loss_kpt: 0.000519 acc_pose: 0.824320 loss: 0.000519 2022/09/15 03:40:21 - mmengine - INFO - Epoch(train) [149][450/586] lr: 5.000000e-04 eta: 4:25:31 time: 0.468527 data_time: 0.024772 memory: 15239 loss_kpt: 0.000519 acc_pose: 0.816495 loss: 0.000519 2022/09/15 03:40:45 - mmengine - INFO - Epoch(train) [149][500/586] lr: 5.000000e-04 eta: 4:25:09 time: 0.488070 data_time: 0.025539 memory: 15239 loss_kpt: 0.000509 acc_pose: 0.837052 loss: 0.000509 2022/09/15 03:41:09 - mmengine - INFO - Epoch(train) [149][550/586] lr: 5.000000e-04 eta: 4:24:48 time: 0.471655 data_time: 0.024892 memory: 15239 loss_kpt: 0.000511 acc_pose: 0.872755 loss: 0.000511 2022/09/15 03:41:26 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 03:41:26 - mmengine - INFO - Saving checkpoint at 149 epochs 2022/09/15 03:41:56 - mmengine - INFO - Epoch(train) [150][50/586] lr: 5.000000e-04 eta: 4:24:04 time: 0.480392 data_time: 0.034104 memory: 15239 loss_kpt: 0.000518 acc_pose: 0.908441 loss: 0.000518 2022/09/15 03:42:20 - mmengine - INFO - Epoch(train) [150][100/586] lr: 5.000000e-04 eta: 4:23:42 time: 0.475887 data_time: 0.025415 memory: 15239 loss_kpt: 0.000508 acc_pose: 0.825113 loss: 0.000508 2022/09/15 03:42:44 - mmengine - INFO - Epoch(train) [150][150/586] lr: 5.000000e-04 eta: 4:23:21 time: 0.471878 data_time: 0.024309 memory: 15239 loss_kpt: 0.000528 acc_pose: 0.893518 loss: 0.000528 2022/09/15 03:43:07 - mmengine - INFO - Epoch(train) [150][200/586] lr: 5.000000e-04 eta: 4:22:59 time: 0.468739 data_time: 0.024416 memory: 15239 loss_kpt: 0.000524 acc_pose: 0.917718 loss: 0.000524 2022/09/15 03:43:31 - mmengine - INFO - Epoch(train) [150][250/586] lr: 5.000000e-04 eta: 4:22:37 time: 0.478854 data_time: 0.024525 memory: 15239 loss_kpt: 0.000507 acc_pose: 0.899255 loss: 0.000507 2022/09/15 03:43:55 - mmengine - INFO - Epoch(train) [150][300/586] lr: 5.000000e-04 eta: 4:22:16 time: 0.470887 data_time: 0.024170 memory: 15239 loss_kpt: 0.000522 acc_pose: 0.899010 loss: 0.000522 2022/09/15 03:44:19 - mmengine - INFO - Epoch(train) [150][350/586] lr: 5.000000e-04 eta: 4:21:54 time: 0.474738 data_time: 0.025345 memory: 15239 loss_kpt: 0.000541 acc_pose: 0.839222 loss: 0.000541 2022/09/15 03:44:42 - mmengine - INFO - Epoch(train) [150][400/586] lr: 5.000000e-04 eta: 4:21:33 time: 0.472815 data_time: 0.025098 memory: 15239 loss_kpt: 0.000535 acc_pose: 0.848408 loss: 0.000535 2022/09/15 03:45:06 - mmengine - INFO - Epoch(train) [150][450/586] lr: 5.000000e-04 eta: 4:21:11 time: 0.483097 data_time: 0.024329 memory: 15239 loss_kpt: 0.000513 acc_pose: 0.761440 loss: 0.000513 2022/09/15 03:45:30 - mmengine - INFO - Epoch(train) [150][500/586] lr: 5.000000e-04 eta: 4:20:50 time: 0.472287 data_time: 0.024472 memory: 15239 loss_kpt: 0.000543 acc_pose: 0.853630 loss: 0.000543 2022/09/15 03:45:54 - mmengine - INFO - Epoch(train) [150][550/586] lr: 5.000000e-04 eta: 4:20:28 time: 0.478887 data_time: 0.027597 memory: 15239 loss_kpt: 0.000513 acc_pose: 0.804547 loss: 0.000513 2022/09/15 03:46:11 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 03:46:11 - mmengine - INFO - Saving checkpoint at 150 epochs 2022/09/15 03:46:29 - mmengine - INFO - Epoch(val) [150][50/407] eta: 0:01:12 time: 0.202296 data_time: 0.013700 memory: 15239 2022/09/15 03:46:38 - mmengine - INFO - Epoch(val) [150][100/407] eta: 0:00:59 time: 0.195008 data_time: 0.008408 memory: 2064 2022/09/15 03:46:48 - mmengine - INFO - Epoch(val) [150][150/407] eta: 0:00:50 time: 0.197307 data_time: 0.009310 memory: 2064 2022/09/15 03:46:58 - mmengine - INFO - Epoch(val) [150][200/407] eta: 0:00:40 time: 0.196808 data_time: 0.008606 memory: 2064 2022/09/15 03:47:08 - mmengine - INFO - Epoch(val) [150][250/407] eta: 0:00:31 time: 0.198267 data_time: 0.008743 memory: 2064 2022/09/15 03:47:18 - mmengine - INFO - Epoch(val) [150][300/407] eta: 0:00:20 time: 0.194449 data_time: 0.008412 memory: 2064 2022/09/15 03:47:28 - mmengine - INFO - Epoch(val) [150][350/407] eta: 0:00:11 time: 0.199564 data_time: 0.008487 memory: 2064 2022/09/15 03:47:37 - mmengine - INFO - Epoch(val) [150][400/407] eta: 0:00:01 time: 0.192925 data_time: 0.007660 memory: 2064 2022/09/15 03:48:14 - mmengine - INFO - Evaluating CocoMetric... 2022/09/15 03:48:28 - mmengine - INFO - Epoch(val) [150][407/407] coco/AP: 0.758960 coco/AP .5: 0.907770 coco/AP .75: 0.824184 coco/AP (M): 0.719465 coco/AP (L): 0.830030 coco/AR: 0.809351 coco/AR .5: 0.943797 coco/AR .75: 0.866656 coco/AR (M): 0.764545 coco/AR (L): 0.873987 2022/09/15 03:48:52 - mmengine - INFO - Epoch(train) [151][50/586] lr: 5.000000e-04 eta: 4:19:44 time: 0.489209 data_time: 0.030582 memory: 15239 loss_kpt: 0.000544 acc_pose: 0.858718 loss: 0.000544 2022/09/15 03:49:16 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 03:49:16 - mmengine - INFO - Epoch(train) [151][100/586] lr: 5.000000e-04 eta: 4:19:23 time: 0.477438 data_time: 0.029254 memory: 15239 loss_kpt: 0.000518 acc_pose: 0.899329 loss: 0.000518 2022/09/15 03:49:40 - mmengine - INFO - Epoch(train) [151][150/586] lr: 5.000000e-04 eta: 4:19:01 time: 0.471145 data_time: 0.024675 memory: 15239 loss_kpt: 0.000514 acc_pose: 0.918090 loss: 0.000514 2022/09/15 03:50:04 - mmengine - INFO - Epoch(train) [151][200/586] lr: 5.000000e-04 eta: 4:18:40 time: 0.476039 data_time: 0.024056 memory: 15239 loss_kpt: 0.000524 acc_pose: 0.870393 loss: 0.000524 2022/09/15 03:50:28 - mmengine - INFO - Epoch(train) [151][250/586] lr: 5.000000e-04 eta: 4:18:18 time: 0.477431 data_time: 0.024664 memory: 15239 loss_kpt: 0.000515 acc_pose: 0.867173 loss: 0.000515 2022/09/15 03:50:51 - mmengine - INFO - Epoch(train) [151][300/586] lr: 5.000000e-04 eta: 4:17:56 time: 0.472003 data_time: 0.025254 memory: 15239 loss_kpt: 0.000529 acc_pose: 0.847527 loss: 0.000529 2022/09/15 03:51:15 - mmengine - INFO - Epoch(train) [151][350/586] lr: 5.000000e-04 eta: 4:17:35 time: 0.471237 data_time: 0.024811 memory: 15239 loss_kpt: 0.000526 acc_pose: 0.800145 loss: 0.000526 2022/09/15 03:51:39 - mmengine - INFO - Epoch(train) [151][400/586] lr: 5.000000e-04 eta: 4:17:13 time: 0.474988 data_time: 0.024463 memory: 15239 loss_kpt: 0.000537 acc_pose: 0.826067 loss: 0.000537 2022/09/15 03:52:02 - mmengine - INFO - Epoch(train) [151][450/586] lr: 5.000000e-04 eta: 4:16:52 time: 0.468124 data_time: 0.024992 memory: 15239 loss_kpt: 0.000518 acc_pose: 0.886636 loss: 0.000518 2022/09/15 03:52:26 - mmengine - INFO - Epoch(train) [151][500/586] lr: 5.000000e-04 eta: 4:16:30 time: 0.475626 data_time: 0.024447 memory: 15239 loss_kpt: 0.000514 acc_pose: 0.854334 loss: 0.000514 2022/09/15 03:52:50 - mmengine - INFO - Epoch(train) [151][550/586] lr: 5.000000e-04 eta: 4:16:08 time: 0.478896 data_time: 0.024672 memory: 15239 loss_kpt: 0.000528 acc_pose: 0.833898 loss: 0.000528 2022/09/15 03:53:06 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 03:53:06 - mmengine - INFO - Saving checkpoint at 151 epochs 2022/09/15 03:53:37 - mmengine - INFO - Epoch(train) [152][50/586] lr: 5.000000e-04 eta: 4:15:25 time: 0.482925 data_time: 0.034000 memory: 15239 loss_kpt: 0.000529 acc_pose: 0.869364 loss: 0.000529 2022/09/15 03:54:01 - mmengine - INFO - Epoch(train) [152][100/586] lr: 5.000000e-04 eta: 4:15:03 time: 0.472629 data_time: 0.024236 memory: 15239 loss_kpt: 0.000501 acc_pose: 0.895843 loss: 0.000501 2022/09/15 03:54:25 - mmengine - INFO - Epoch(train) [152][150/586] lr: 5.000000e-04 eta: 4:14:41 time: 0.472368 data_time: 0.024627 memory: 15239 loss_kpt: 0.000529 acc_pose: 0.864921 loss: 0.000529 2022/09/15 03:54:48 - mmengine - INFO - Epoch(train) [152][200/586] lr: 5.000000e-04 eta: 4:14:20 time: 0.475204 data_time: 0.029826 memory: 15239 loss_kpt: 0.000530 acc_pose: 0.871275 loss: 0.000530 2022/09/15 03:55:12 - mmengine - INFO - Epoch(train) [152][250/586] lr: 5.000000e-04 eta: 4:13:58 time: 0.472463 data_time: 0.024616 memory: 15239 loss_kpt: 0.000491 acc_pose: 0.896210 loss: 0.000491 2022/09/15 03:55:35 - mmengine - INFO - Epoch(train) [152][300/586] lr: 5.000000e-04 eta: 4:13:36 time: 0.462983 data_time: 0.025357 memory: 15239 loss_kpt: 0.000522 acc_pose: 0.870335 loss: 0.000522 2022/09/15 03:55:59 - mmengine - INFO - Epoch(train) [152][350/586] lr: 5.000000e-04 eta: 4:13:15 time: 0.474187 data_time: 0.029165 memory: 15239 loss_kpt: 0.000506 acc_pose: 0.819358 loss: 0.000506 2022/09/15 03:56:23 - mmengine - INFO - Epoch(train) [152][400/586] lr: 5.000000e-04 eta: 4:12:53 time: 0.475715 data_time: 0.025294 memory: 15239 loss_kpt: 0.000514 acc_pose: 0.891424 loss: 0.000514 2022/09/15 03:56:46 - mmengine - INFO - Epoch(train) [152][450/586] lr: 5.000000e-04 eta: 4:12:31 time: 0.468651 data_time: 0.025079 memory: 15239 loss_kpt: 0.000529 acc_pose: 0.901816 loss: 0.000529 2022/09/15 03:57:10 - mmengine - INFO - Epoch(train) [152][500/586] lr: 5.000000e-04 eta: 4:12:10 time: 0.477888 data_time: 0.028599 memory: 15239 loss_kpt: 0.000514 acc_pose: 0.859634 loss: 0.000514 2022/09/15 03:57:17 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 03:57:34 - mmengine - INFO - Epoch(train) [152][550/586] lr: 5.000000e-04 eta: 4:11:48 time: 0.470967 data_time: 0.025159 memory: 15239 loss_kpt: 0.000532 acc_pose: 0.857931 loss: 0.000532 2022/09/15 03:57:50 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 03:57:50 - mmengine - INFO - Saving checkpoint at 152 epochs 2022/09/15 03:58:21 - mmengine - INFO - Epoch(train) [153][50/586] lr: 5.000000e-04 eta: 4:11:05 time: 0.475049 data_time: 0.034274 memory: 15239 loss_kpt: 0.000517 acc_pose: 0.860927 loss: 0.000517 2022/09/15 03:58:45 - mmengine - INFO - Epoch(train) [153][100/586] lr: 5.000000e-04 eta: 4:10:43 time: 0.483138 data_time: 0.027790 memory: 15239 loss_kpt: 0.000522 acc_pose: 0.868776 loss: 0.000522 2022/09/15 03:59:08 - mmengine - INFO - Epoch(train) [153][150/586] lr: 5.000000e-04 eta: 4:10:21 time: 0.464811 data_time: 0.027379 memory: 15239 loss_kpt: 0.000535 acc_pose: 0.872629 loss: 0.000535 2022/09/15 03:59:33 - mmengine - INFO - Epoch(train) [153][200/586] lr: 5.000000e-04 eta: 4:10:00 time: 0.487225 data_time: 0.028519 memory: 15239 loss_kpt: 0.000507 acc_pose: 0.905389 loss: 0.000507 2022/09/15 03:59:56 - mmengine - INFO - Epoch(train) [153][250/586] lr: 5.000000e-04 eta: 4:09:38 time: 0.473153 data_time: 0.027920 memory: 15239 loss_kpt: 0.000511 acc_pose: 0.931518 loss: 0.000511 2022/09/15 04:00:20 - mmengine - INFO - Epoch(train) [153][300/586] lr: 5.000000e-04 eta: 4:09:16 time: 0.464563 data_time: 0.024498 memory: 15239 loss_kpt: 0.000504 acc_pose: 0.848222 loss: 0.000504 2022/09/15 04:00:44 - mmengine - INFO - Epoch(train) [153][350/586] lr: 5.000000e-04 eta: 4:08:55 time: 0.481040 data_time: 0.028525 memory: 15239 loss_kpt: 0.000511 acc_pose: 0.881603 loss: 0.000511 2022/09/15 04:01:07 - mmengine - INFO - Epoch(train) [153][400/586] lr: 5.000000e-04 eta: 4:08:33 time: 0.465168 data_time: 0.025140 memory: 15239 loss_kpt: 0.000528 acc_pose: 0.836349 loss: 0.000528 2022/09/15 04:01:31 - mmengine - INFO - Epoch(train) [153][450/586] lr: 5.000000e-04 eta: 4:08:11 time: 0.469774 data_time: 0.025788 memory: 15239 loss_kpt: 0.000522 acc_pose: 0.801284 loss: 0.000522 2022/09/15 04:01:54 - mmengine - INFO - Epoch(train) [153][500/586] lr: 5.000000e-04 eta: 4:07:50 time: 0.478282 data_time: 0.027726 memory: 15239 loss_kpt: 0.000509 acc_pose: 0.845211 loss: 0.000509 2022/09/15 04:02:18 - mmengine - INFO - Epoch(train) [153][550/586] lr: 5.000000e-04 eta: 4:07:28 time: 0.472873 data_time: 0.025595 memory: 15239 loss_kpt: 0.000531 acc_pose: 0.820118 loss: 0.000531 2022/09/15 04:02:35 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 04:02:35 - mmengine - INFO - Saving checkpoint at 153 epochs 2022/09/15 04:03:05 - mmengine - INFO - Epoch(train) [154][50/586] lr: 5.000000e-04 eta: 4:06:45 time: 0.480677 data_time: 0.028807 memory: 15239 loss_kpt: 0.000536 acc_pose: 0.911741 loss: 0.000536 2022/09/15 04:03:29 - mmengine - INFO - Epoch(train) [154][100/586] lr: 5.000000e-04 eta: 4:06:23 time: 0.468991 data_time: 0.024830 memory: 15239 loss_kpt: 0.000520 acc_pose: 0.864624 loss: 0.000520 2022/09/15 04:03:52 - mmengine - INFO - Epoch(train) [154][150/586] lr: 5.000000e-04 eta: 4:06:01 time: 0.469982 data_time: 0.024008 memory: 15239 loss_kpt: 0.000535 acc_pose: 0.857618 loss: 0.000535 2022/09/15 04:04:16 - mmengine - INFO - Epoch(train) [154][200/586] lr: 5.000000e-04 eta: 4:05:40 time: 0.478046 data_time: 0.024679 memory: 15239 loss_kpt: 0.000529 acc_pose: 0.832284 loss: 0.000529 2022/09/15 04:04:40 - mmengine - INFO - Epoch(train) [154][250/586] lr: 5.000000e-04 eta: 4:05:18 time: 0.474307 data_time: 0.024853 memory: 15239 loss_kpt: 0.000514 acc_pose: 0.856326 loss: 0.000514 2022/09/15 04:05:04 - mmengine - INFO - Epoch(train) [154][300/586] lr: 5.000000e-04 eta: 4:04:56 time: 0.470218 data_time: 0.024649 memory: 15239 loss_kpt: 0.000519 acc_pose: 0.846016 loss: 0.000519 2022/09/15 04:05:24 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 04:05:27 - mmengine - INFO - Epoch(train) [154][350/586] lr: 5.000000e-04 eta: 4:04:35 time: 0.475762 data_time: 0.025582 memory: 15239 loss_kpt: 0.000516 acc_pose: 0.836316 loss: 0.000516 2022/09/15 04:05:51 - mmengine - INFO - Epoch(train) [154][400/586] lr: 5.000000e-04 eta: 4:04:13 time: 0.466269 data_time: 0.024703 memory: 15239 loss_kpt: 0.000539 acc_pose: 0.888061 loss: 0.000539 2022/09/15 04:06:14 - mmengine - INFO - Epoch(train) [154][450/586] lr: 5.000000e-04 eta: 4:03:51 time: 0.472770 data_time: 0.029749 memory: 15239 loss_kpt: 0.000523 acc_pose: 0.898271 loss: 0.000523 2022/09/15 04:06:38 - mmengine - INFO - Epoch(train) [154][500/586] lr: 5.000000e-04 eta: 4:03:30 time: 0.473233 data_time: 0.024609 memory: 15239 loss_kpt: 0.000528 acc_pose: 0.915764 loss: 0.000528 2022/09/15 04:07:01 - mmengine - INFO - Epoch(train) [154][550/586] lr: 5.000000e-04 eta: 4:03:08 time: 0.467291 data_time: 0.025319 memory: 15239 loss_kpt: 0.000518 acc_pose: 0.873830 loss: 0.000518 2022/09/15 04:07:18 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 04:07:18 - mmengine - INFO - Saving checkpoint at 154 epochs 2022/09/15 04:07:50 - mmengine - INFO - Epoch(train) [155][50/586] lr: 5.000000e-04 eta: 4:02:25 time: 0.492078 data_time: 0.029194 memory: 15239 loss_kpt: 0.000520 acc_pose: 0.869383 loss: 0.000520 2022/09/15 04:08:13 - mmengine - INFO - Epoch(train) [155][100/586] lr: 5.000000e-04 eta: 4:02:03 time: 0.467884 data_time: 0.026848 memory: 15239 loss_kpt: 0.000523 acc_pose: 0.873531 loss: 0.000523 2022/09/15 04:08:37 - mmengine - INFO - Epoch(train) [155][150/586] lr: 5.000000e-04 eta: 4:01:41 time: 0.474722 data_time: 0.024919 memory: 15239 loss_kpt: 0.000514 acc_pose: 0.920515 loss: 0.000514 2022/09/15 04:09:01 - mmengine - INFO - Epoch(train) [155][200/586] lr: 5.000000e-04 eta: 4:01:20 time: 0.469754 data_time: 0.023930 memory: 15239 loss_kpt: 0.000530 acc_pose: 0.855717 loss: 0.000530 2022/09/15 04:09:24 - mmengine - INFO - Epoch(train) [155][250/586] lr: 5.000000e-04 eta: 4:00:58 time: 0.471999 data_time: 0.025463 memory: 15239 loss_kpt: 0.000496 acc_pose: 0.832456 loss: 0.000496 2022/09/15 04:09:48 - mmengine - INFO - Epoch(train) [155][300/586] lr: 5.000000e-04 eta: 4:00:36 time: 0.472114 data_time: 0.026219 memory: 15239 loss_kpt: 0.000515 acc_pose: 0.924752 loss: 0.000515 2022/09/15 04:10:12 - mmengine - INFO - Epoch(train) [155][350/586] lr: 5.000000e-04 eta: 4:00:15 time: 0.471675 data_time: 0.025241 memory: 15239 loss_kpt: 0.000522 acc_pose: 0.861759 loss: 0.000522 2022/09/15 04:10:35 - mmengine - INFO - Epoch(train) [155][400/586] lr: 5.000000e-04 eta: 3:59:53 time: 0.477758 data_time: 0.024641 memory: 15239 loss_kpt: 0.000518 acc_pose: 0.881928 loss: 0.000518 2022/09/15 04:10:59 - mmengine - INFO - Epoch(train) [155][450/586] lr: 5.000000e-04 eta: 3:59:31 time: 0.469661 data_time: 0.029494 memory: 15239 loss_kpt: 0.000521 acc_pose: 0.851133 loss: 0.000521 2022/09/15 04:11:23 - mmengine - INFO - Epoch(train) [155][500/586] lr: 5.000000e-04 eta: 3:59:09 time: 0.472243 data_time: 0.024376 memory: 15239 loss_kpt: 0.000513 acc_pose: 0.849036 loss: 0.000513 2022/09/15 04:11:47 - mmengine - INFO - Epoch(train) [155][550/586] lr: 5.000000e-04 eta: 3:58:48 time: 0.478893 data_time: 0.025885 memory: 15239 loss_kpt: 0.000534 acc_pose: 0.842141 loss: 0.000534 2022/09/15 04:12:03 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 04:12:03 - mmengine - INFO - Saving checkpoint at 155 epochs 2022/09/15 04:12:34 - mmengine - INFO - Epoch(train) [156][50/586] lr: 5.000000e-04 eta: 3:58:05 time: 0.479576 data_time: 0.035810 memory: 15239 loss_kpt: 0.000521 acc_pose: 0.814264 loss: 0.000521 2022/09/15 04:12:58 - mmengine - INFO - Epoch(train) [156][100/586] lr: 5.000000e-04 eta: 3:57:43 time: 0.488962 data_time: 0.025561 memory: 15239 loss_kpt: 0.000518 acc_pose: 0.899817 loss: 0.000518 2022/09/15 04:13:22 - mmengine - INFO - Epoch(train) [156][150/586] lr: 5.000000e-04 eta: 3:57:21 time: 0.467768 data_time: 0.024821 memory: 15239 loss_kpt: 0.000533 acc_pose: 0.878719 loss: 0.000533 2022/09/15 04:13:31 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 04:13:45 - mmengine - INFO - Epoch(train) [156][200/586] lr: 5.000000e-04 eta: 3:57:00 time: 0.472629 data_time: 0.025621 memory: 15239 loss_kpt: 0.000519 acc_pose: 0.834288 loss: 0.000519 2022/09/15 04:14:09 - mmengine - INFO - Epoch(train) [156][250/586] lr: 5.000000e-04 eta: 3:56:38 time: 0.474254 data_time: 0.029504 memory: 15239 loss_kpt: 0.000509 acc_pose: 0.824297 loss: 0.000509 2022/09/15 04:14:33 - mmengine - INFO - Epoch(train) [156][300/586] lr: 5.000000e-04 eta: 3:56:16 time: 0.470200 data_time: 0.024513 memory: 15239 loss_kpt: 0.000513 acc_pose: 0.894863 loss: 0.000513 2022/09/15 04:14:56 - mmengine - INFO - Epoch(train) [156][350/586] lr: 5.000000e-04 eta: 3:55:55 time: 0.471707 data_time: 0.024204 memory: 15239 loss_kpt: 0.000494 acc_pose: 0.916598 loss: 0.000494 2022/09/15 04:15:20 - mmengine - INFO - Epoch(train) [156][400/586] lr: 5.000000e-04 eta: 3:55:33 time: 0.472987 data_time: 0.027863 memory: 15239 loss_kpt: 0.000512 acc_pose: 0.908026 loss: 0.000512 2022/09/15 04:15:44 - mmengine - INFO - Epoch(train) [156][450/586] lr: 5.000000e-04 eta: 3:55:11 time: 0.471081 data_time: 0.025388 memory: 15239 loss_kpt: 0.000513 acc_pose: 0.868851 loss: 0.000513 2022/09/15 04:16:07 - mmengine - INFO - Epoch(train) [156][500/586] lr: 5.000000e-04 eta: 3:54:49 time: 0.462005 data_time: 0.024534 memory: 15239 loss_kpt: 0.000509 acc_pose: 0.847553 loss: 0.000509 2022/09/15 04:16:31 - mmengine - INFO - Epoch(train) [156][550/586] lr: 5.000000e-04 eta: 3:54:28 time: 0.479182 data_time: 0.027836 memory: 15239 loss_kpt: 0.000531 acc_pose: 0.812512 loss: 0.000531 2022/09/15 04:16:47 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 04:16:47 - mmengine - INFO - Saving checkpoint at 156 epochs 2022/09/15 04:17:18 - mmengine - INFO - Epoch(train) [157][50/586] lr: 5.000000e-04 eta: 3:53:45 time: 0.473989 data_time: 0.033892 memory: 15239 loss_kpt: 0.000503 acc_pose: 0.899642 loss: 0.000503 2022/09/15 04:17:42 - mmengine - INFO - Epoch(train) [157][100/586] lr: 5.000000e-04 eta: 3:53:23 time: 0.471301 data_time: 0.029909 memory: 15239 loss_kpt: 0.000523 acc_pose: 0.839328 loss: 0.000523 2022/09/15 04:18:06 - mmengine - INFO - Epoch(train) [157][150/586] lr: 5.000000e-04 eta: 3:53:01 time: 0.477857 data_time: 0.036704 memory: 15239 loss_kpt: 0.000508 acc_pose: 0.914055 loss: 0.000508 2022/09/15 04:18:30 - mmengine - INFO - Epoch(train) [157][200/586] lr: 5.000000e-04 eta: 3:52:40 time: 0.472111 data_time: 0.029744 memory: 15239 loss_kpt: 0.000528 acc_pose: 0.864189 loss: 0.000528 2022/09/15 04:18:53 - mmengine - INFO - Epoch(train) [157][250/586] lr: 5.000000e-04 eta: 3:52:18 time: 0.470441 data_time: 0.029878 memory: 15239 loss_kpt: 0.000513 acc_pose: 0.900518 loss: 0.000513 2022/09/15 04:19:17 - mmengine - INFO - Epoch(train) [157][300/586] lr: 5.000000e-04 eta: 3:51:56 time: 0.475529 data_time: 0.029493 memory: 15239 loss_kpt: 0.000515 acc_pose: 0.939678 loss: 0.000515 2022/09/15 04:19:41 - mmengine - INFO - Epoch(train) [157][350/586] lr: 5.000000e-04 eta: 3:51:34 time: 0.474383 data_time: 0.027705 memory: 15239 loss_kpt: 0.000498 acc_pose: 0.882577 loss: 0.000498 2022/09/15 04:20:04 - mmengine - INFO - Epoch(train) [157][400/586] lr: 5.000000e-04 eta: 3:51:13 time: 0.465979 data_time: 0.024653 memory: 15239 loss_kpt: 0.000509 acc_pose: 0.887756 loss: 0.000509 2022/09/15 04:20:28 - mmengine - INFO - Epoch(train) [157][450/586] lr: 5.000000e-04 eta: 3:50:51 time: 0.474785 data_time: 0.024693 memory: 15239 loss_kpt: 0.000515 acc_pose: 0.854058 loss: 0.000515 2022/09/15 04:20:51 - mmengine - INFO - Epoch(train) [157][500/586] lr: 5.000000e-04 eta: 3:50:29 time: 0.472298 data_time: 0.026124 memory: 15239 loss_kpt: 0.000527 acc_pose: 0.852436 loss: 0.000527 2022/09/15 04:21:15 - mmengine - INFO - Epoch(train) [157][550/586] lr: 5.000000e-04 eta: 3:50:07 time: 0.472172 data_time: 0.025115 memory: 15239 loss_kpt: 0.000522 acc_pose: 0.891382 loss: 0.000522 2022/09/15 04:21:31 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 04:21:32 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 04:21:32 - mmengine - INFO - Saving checkpoint at 157 epochs 2022/09/15 04:22:04 - mmengine - INFO - Epoch(train) [158][50/586] lr: 5.000000e-04 eta: 3:49:25 time: 0.486899 data_time: 0.036240 memory: 15239 loss_kpt: 0.000518 acc_pose: 0.858454 loss: 0.000518 2022/09/15 04:22:28 - mmengine - INFO - Epoch(train) [158][100/586] lr: 5.000000e-04 eta: 3:49:03 time: 0.479122 data_time: 0.025382 memory: 15239 loss_kpt: 0.000511 acc_pose: 0.851241 loss: 0.000511 2022/09/15 04:22:51 - mmengine - INFO - Epoch(train) [158][150/586] lr: 5.000000e-04 eta: 3:48:41 time: 0.469297 data_time: 0.028288 memory: 15239 loss_kpt: 0.000505 acc_pose: 0.925907 loss: 0.000505 2022/09/15 04:23:15 - mmengine - INFO - Epoch(train) [158][200/586] lr: 5.000000e-04 eta: 3:48:20 time: 0.474327 data_time: 0.024630 memory: 15239 loss_kpt: 0.000518 acc_pose: 0.860300 loss: 0.000518 2022/09/15 04:23:39 - mmengine - INFO - Epoch(train) [158][250/586] lr: 5.000000e-04 eta: 3:47:58 time: 0.473210 data_time: 0.025162 memory: 15239 loss_kpt: 0.000516 acc_pose: 0.832432 loss: 0.000516 2022/09/15 04:24:02 - mmengine - INFO - Epoch(train) [158][300/586] lr: 5.000000e-04 eta: 3:47:36 time: 0.474266 data_time: 0.025176 memory: 15239 loss_kpt: 0.000504 acc_pose: 0.880760 loss: 0.000504 2022/09/15 04:24:26 - mmengine - INFO - Epoch(train) [158][350/586] lr: 5.000000e-04 eta: 3:47:14 time: 0.473520 data_time: 0.024756 memory: 15239 loss_kpt: 0.000508 acc_pose: 0.846857 loss: 0.000508 2022/09/15 04:24:50 - mmengine - INFO - Epoch(train) [158][400/586] lr: 5.000000e-04 eta: 3:46:53 time: 0.469511 data_time: 0.024142 memory: 15239 loss_kpt: 0.000533 acc_pose: 0.882633 loss: 0.000533 2022/09/15 04:25:13 - mmengine - INFO - Epoch(train) [158][450/586] lr: 5.000000e-04 eta: 3:46:31 time: 0.475583 data_time: 0.024097 memory: 15239 loss_kpt: 0.000518 acc_pose: 0.882582 loss: 0.000518 2022/09/15 04:25:37 - mmengine - INFO - Epoch(train) [158][500/586] lr: 5.000000e-04 eta: 3:46:09 time: 0.464819 data_time: 0.024370 memory: 15239 loss_kpt: 0.000504 acc_pose: 0.859732 loss: 0.000504 2022/09/15 04:26:00 - mmengine - INFO - Epoch(train) [158][550/586] lr: 5.000000e-04 eta: 3:45:47 time: 0.473544 data_time: 0.024828 memory: 15239 loss_kpt: 0.000508 acc_pose: 0.813708 loss: 0.000508 2022/09/15 04:26:17 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 04:26:17 - mmengine - INFO - Saving checkpoint at 158 epochs 2022/09/15 04:26:48 - mmengine - INFO - Epoch(train) [159][50/586] lr: 5.000000e-04 eta: 3:45:04 time: 0.474016 data_time: 0.030292 memory: 15239 loss_kpt: 0.000512 acc_pose: 0.908036 loss: 0.000512 2022/09/15 04:27:11 - mmengine - INFO - Epoch(train) [159][100/586] lr: 5.000000e-04 eta: 3:44:43 time: 0.475805 data_time: 0.027917 memory: 15239 loss_kpt: 0.000519 acc_pose: 0.909123 loss: 0.000519 2022/09/15 04:27:35 - mmengine - INFO - Epoch(train) [159][150/586] lr: 5.000000e-04 eta: 3:44:21 time: 0.470271 data_time: 0.025016 memory: 15239 loss_kpt: 0.000534 acc_pose: 0.850606 loss: 0.000534 2022/09/15 04:27:58 - mmengine - INFO - Epoch(train) [159][200/586] lr: 5.000000e-04 eta: 3:43:59 time: 0.470662 data_time: 0.024278 memory: 15239 loss_kpt: 0.000506 acc_pose: 0.850997 loss: 0.000506 2022/09/15 04:28:23 - mmengine - INFO - Epoch(train) [159][250/586] lr: 5.000000e-04 eta: 3:43:38 time: 0.481721 data_time: 0.025631 memory: 15239 loss_kpt: 0.000519 acc_pose: 0.865162 loss: 0.000519 2022/09/15 04:28:46 - mmengine - INFO - Epoch(train) [159][300/586] lr: 5.000000e-04 eta: 3:43:16 time: 0.475362 data_time: 0.024890 memory: 15239 loss_kpt: 0.000515 acc_pose: 0.870548 loss: 0.000515 2022/09/15 04:29:10 - mmengine - INFO - Epoch(train) [159][350/586] lr: 5.000000e-04 eta: 3:42:54 time: 0.469261 data_time: 0.024981 memory: 15239 loss_kpt: 0.000531 acc_pose: 0.915325 loss: 0.000531 2022/09/15 04:29:34 - mmengine - INFO - Epoch(train) [159][400/586] lr: 5.000000e-04 eta: 3:42:32 time: 0.474546 data_time: 0.029193 memory: 15239 loss_kpt: 0.000509 acc_pose: 0.917002 loss: 0.000509 2022/09/15 04:29:39 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 04:29:57 - mmengine - INFO - Epoch(train) [159][450/586] lr: 5.000000e-04 eta: 3:42:11 time: 0.470561 data_time: 0.025342 memory: 15239 loss_kpt: 0.000502 acc_pose: 0.912101 loss: 0.000502 2022/09/15 04:30:20 - mmengine - INFO - Epoch(train) [159][500/586] lr: 5.000000e-04 eta: 3:41:49 time: 0.467845 data_time: 0.024440 memory: 15239 loss_kpt: 0.000502 acc_pose: 0.883460 loss: 0.000502 2022/09/15 04:30:44 - mmengine - INFO - Epoch(train) [159][550/586] lr: 5.000000e-04 eta: 3:41:27 time: 0.472069 data_time: 0.028551 memory: 15239 loss_kpt: 0.000532 acc_pose: 0.835329 loss: 0.000532 2022/09/15 04:31:01 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 04:31:01 - mmengine - INFO - Saving checkpoint at 159 epochs 2022/09/15 04:31:32 - mmengine - INFO - Epoch(train) [160][50/586] lr: 5.000000e-04 eta: 3:40:44 time: 0.485216 data_time: 0.033818 memory: 15239 loss_kpt: 0.000494 acc_pose: 0.838396 loss: 0.000494 2022/09/15 04:31:56 - mmengine - INFO - Epoch(train) [160][100/586] lr: 5.000000e-04 eta: 3:40:23 time: 0.479472 data_time: 0.024902 memory: 15239 loss_kpt: 0.000503 acc_pose: 0.877153 loss: 0.000503 2022/09/15 04:32:20 - mmengine - INFO - Epoch(train) [160][150/586] lr: 5.000000e-04 eta: 3:40:01 time: 0.468422 data_time: 0.024980 memory: 15239 loss_kpt: 0.000500 acc_pose: 0.914878 loss: 0.000500 2022/09/15 04:32:44 - mmengine - INFO - Epoch(train) [160][200/586] lr: 5.000000e-04 eta: 3:39:39 time: 0.478275 data_time: 0.027466 memory: 15239 loss_kpt: 0.000482 acc_pose: 0.868153 loss: 0.000482 2022/09/15 04:33:07 - mmengine - INFO - Epoch(train) [160][250/586] lr: 5.000000e-04 eta: 3:39:18 time: 0.469843 data_time: 0.024680 memory: 15239 loss_kpt: 0.000511 acc_pose: 0.875006 loss: 0.000511 2022/09/15 04:33:31 - mmengine - INFO - Epoch(train) [160][300/586] lr: 5.000000e-04 eta: 3:38:56 time: 0.468802 data_time: 0.025253 memory: 15239 loss_kpt: 0.000516 acc_pose: 0.898248 loss: 0.000516 2022/09/15 04:33:55 - mmengine - INFO - Epoch(train) [160][350/586] lr: 5.000000e-04 eta: 3:38:34 time: 0.480163 data_time: 0.024221 memory: 15239 loss_kpt: 0.000518 acc_pose: 0.809704 loss: 0.000518 2022/09/15 04:34:18 - mmengine - INFO - Epoch(train) [160][400/586] lr: 5.000000e-04 eta: 3:38:12 time: 0.466459 data_time: 0.025178 memory: 15239 loss_kpt: 0.000521 acc_pose: 0.832529 loss: 0.000521 2022/09/15 04:34:41 - mmengine - INFO - Epoch(train) [160][450/586] lr: 5.000000e-04 eta: 3:37:51 time: 0.471260 data_time: 0.024919 memory: 15239 loss_kpt: 0.000522 acc_pose: 0.880390 loss: 0.000522 2022/09/15 04:35:05 - mmengine - INFO - Epoch(train) [160][500/586] lr: 5.000000e-04 eta: 3:37:29 time: 0.480199 data_time: 0.028739 memory: 15239 loss_kpt: 0.000522 acc_pose: 0.860602 loss: 0.000522 2022/09/15 04:35:29 - mmengine - INFO - Epoch(train) [160][550/586] lr: 5.000000e-04 eta: 3:37:07 time: 0.473900 data_time: 0.025211 memory: 15239 loss_kpt: 0.000505 acc_pose: 0.875674 loss: 0.000505 2022/09/15 04:35:46 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 04:35:46 - mmengine - INFO - Saving checkpoint at 160 epochs 2022/09/15 04:36:03 - mmengine - INFO - Epoch(val) [160][50/407] eta: 0:01:12 time: 0.204280 data_time: 0.014352 memory: 15239 2022/09/15 04:36:13 - mmengine - INFO - Epoch(val) [160][100/407] eta: 0:01:00 time: 0.195654 data_time: 0.008657 memory: 2064 2022/09/15 04:36:23 - mmengine - INFO - Epoch(val) [160][150/407] eta: 0:00:50 time: 0.195970 data_time: 0.008500 memory: 2064 2022/09/15 04:36:33 - mmengine - INFO - Epoch(val) [160][200/407] eta: 0:00:40 time: 0.195358 data_time: 0.008350 memory: 2064 2022/09/15 04:36:42 - mmengine - INFO - Epoch(val) [160][250/407] eta: 0:00:30 time: 0.195043 data_time: 0.008605 memory: 2064 2022/09/15 04:36:52 - mmengine - INFO - Epoch(val) [160][300/407] eta: 0:00:21 time: 0.199929 data_time: 0.008622 memory: 2064 2022/09/15 04:37:02 - mmengine - INFO - Epoch(val) [160][350/407] eta: 0:00:11 time: 0.196628 data_time: 0.008566 memory: 2064 2022/09/15 04:37:12 - mmengine - INFO - Epoch(val) [160][400/407] eta: 0:00:01 time: 0.192997 data_time: 0.007839 memory: 2064 2022/09/15 04:37:49 - mmengine - INFO - Evaluating CocoMetric... 2022/09/15 04:38:03 - mmengine - INFO - Epoch(val) [160][407/407] coco/AP: 0.760205 coco/AP .5: 0.907609 coco/AP .75: 0.827030 coco/AP (M): 0.721752 coco/AP (L): 0.829651 coco/AR: 0.810202 coco/AR .5: 0.942853 coco/AR .75: 0.869805 coco/AR (M): 0.766840 coco/AR (L): 0.873021 2022/09/15 04:38:03 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220914/hrnet_w48_384/best_coco/AP_epoch_110.pth is removed 2022/09/15 04:38:06 - mmengine - INFO - The best checkpoint with 0.7602 coco/AP at 160 epoch is saved to best_coco/AP_epoch_160.pth. 2022/09/15 04:38:31 - mmengine - INFO - Epoch(train) [161][50/586] lr: 5.000000e-04 eta: 3:36:25 time: 0.485588 data_time: 0.036322 memory: 15239 loss_kpt: 0.000499 acc_pose: 0.854077 loss: 0.000499 2022/09/15 04:38:54 - mmengine - INFO - Epoch(train) [161][100/586] lr: 5.000000e-04 eta: 3:36:03 time: 0.468348 data_time: 0.027770 memory: 15239 loss_kpt: 0.000522 acc_pose: 0.875347 loss: 0.000522 2022/09/15 04:39:18 - mmengine - INFO - Epoch(train) [161][150/586] lr: 5.000000e-04 eta: 3:35:41 time: 0.471596 data_time: 0.026278 memory: 15239 loss_kpt: 0.000517 acc_pose: 0.900169 loss: 0.000517 2022/09/15 04:39:42 - mmengine - INFO - Epoch(train) [161][200/586] lr: 5.000000e-04 eta: 3:35:19 time: 0.477082 data_time: 0.025003 memory: 15239 loss_kpt: 0.000510 acc_pose: 0.931417 loss: 0.000510 2022/09/15 04:40:00 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 04:40:05 - mmengine - INFO - Epoch(train) [161][250/586] lr: 5.000000e-04 eta: 3:34:58 time: 0.467443 data_time: 0.024930 memory: 15239 loss_kpt: 0.000499 acc_pose: 0.841887 loss: 0.000499 2022/09/15 04:40:29 - mmengine - INFO - Epoch(train) [161][300/586] lr: 5.000000e-04 eta: 3:34:36 time: 0.482901 data_time: 0.024542 memory: 15239 loss_kpt: 0.000514 acc_pose: 0.893919 loss: 0.000514 2022/09/15 04:40:53 - mmengine - INFO - Epoch(train) [161][350/586] lr: 5.000000e-04 eta: 3:34:14 time: 0.475452 data_time: 0.027713 memory: 15239 loss_kpt: 0.000522 acc_pose: 0.864476 loss: 0.000522 2022/09/15 04:41:17 - mmengine - INFO - Epoch(train) [161][400/586] lr: 5.000000e-04 eta: 3:33:52 time: 0.473314 data_time: 0.025077 memory: 15239 loss_kpt: 0.000516 acc_pose: 0.879611 loss: 0.000516 2022/09/15 04:41:40 - mmengine - INFO - Epoch(train) [161][450/586] lr: 5.000000e-04 eta: 3:33:31 time: 0.472589 data_time: 0.024506 memory: 15239 loss_kpt: 0.000497 acc_pose: 0.851127 loss: 0.000497 2022/09/15 04:42:04 - mmengine - INFO - Epoch(train) [161][500/586] lr: 5.000000e-04 eta: 3:33:09 time: 0.472951 data_time: 0.025302 memory: 15239 loss_kpt: 0.000512 acc_pose: 0.862072 loss: 0.000512 2022/09/15 04:42:28 - mmengine - INFO - Epoch(train) [161][550/586] lr: 5.000000e-04 eta: 3:32:47 time: 0.484676 data_time: 0.025681 memory: 15239 loss_kpt: 0.000505 acc_pose: 0.879071 loss: 0.000505 2022/09/15 04:42:45 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 04:42:45 - mmengine - INFO - Saving checkpoint at 161 epochs 2022/09/15 04:43:15 - mmengine - INFO - Epoch(train) [162][50/586] lr: 5.000000e-04 eta: 3:32:05 time: 0.479590 data_time: 0.031058 memory: 15239 loss_kpt: 0.000507 acc_pose: 0.914983 loss: 0.000507 2022/09/15 04:43:40 - mmengine - INFO - Epoch(train) [162][100/586] lr: 5.000000e-04 eta: 3:31:43 time: 0.481494 data_time: 0.029472 memory: 15239 loss_kpt: 0.000521 acc_pose: 0.878157 loss: 0.000521 2022/09/15 04:44:03 - mmengine - INFO - Epoch(train) [162][150/586] lr: 5.000000e-04 eta: 3:31:21 time: 0.475293 data_time: 0.024418 memory: 15239 loss_kpt: 0.000516 acc_pose: 0.864761 loss: 0.000516 2022/09/15 04:44:27 - mmengine - INFO - Epoch(train) [162][200/586] lr: 5.000000e-04 eta: 3:31:00 time: 0.473685 data_time: 0.024896 memory: 15239 loss_kpt: 0.000515 acc_pose: 0.789226 loss: 0.000515 2022/09/15 04:44:51 - mmengine - INFO - Epoch(train) [162][250/586] lr: 5.000000e-04 eta: 3:30:38 time: 0.479639 data_time: 0.028316 memory: 15239 loss_kpt: 0.000493 acc_pose: 0.901041 loss: 0.000493 2022/09/15 04:45:15 - mmengine - INFO - Epoch(train) [162][300/586] lr: 5.000000e-04 eta: 3:30:16 time: 0.474692 data_time: 0.025484 memory: 15239 loss_kpt: 0.000512 acc_pose: 0.890763 loss: 0.000512 2022/09/15 04:45:38 - mmengine - INFO - Epoch(train) [162][350/586] lr: 5.000000e-04 eta: 3:29:54 time: 0.466734 data_time: 0.025560 memory: 15239 loss_kpt: 0.000521 acc_pose: 0.883858 loss: 0.000521 2022/09/15 04:46:02 - mmengine - INFO - Epoch(train) [162][400/586] lr: 5.000000e-04 eta: 3:29:33 time: 0.478487 data_time: 0.024399 memory: 15239 loss_kpt: 0.000508 acc_pose: 0.829080 loss: 0.000508 2022/09/15 04:46:25 - mmengine - INFO - Epoch(train) [162][450/586] lr: 5.000000e-04 eta: 3:29:11 time: 0.466295 data_time: 0.024427 memory: 15239 loss_kpt: 0.000521 acc_pose: 0.868049 loss: 0.000521 2022/09/15 04:46:49 - mmengine - INFO - Epoch(train) [162][500/586] lr: 5.000000e-04 eta: 3:28:49 time: 0.467650 data_time: 0.025081 memory: 15239 loss_kpt: 0.000520 acc_pose: 0.854711 loss: 0.000520 2022/09/15 04:47:13 - mmengine - INFO - Epoch(train) [162][550/586] lr: 5.000000e-04 eta: 3:28:27 time: 0.478174 data_time: 0.025021 memory: 15239 loss_kpt: 0.000523 acc_pose: 0.864728 loss: 0.000523 2022/09/15 04:47:30 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 04:47:30 - mmengine - INFO - Saving checkpoint at 162 epochs 2022/09/15 04:48:01 - mmengine - INFO - Epoch(train) [163][50/586] lr: 5.000000e-04 eta: 3:27:45 time: 0.480027 data_time: 0.034101 memory: 15239 loss_kpt: 0.000517 acc_pose: 0.848150 loss: 0.000517 2022/09/15 04:48:10 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 04:48:25 - mmengine - INFO - Epoch(train) [163][100/586] lr: 5.000000e-04 eta: 3:27:23 time: 0.475346 data_time: 0.028477 memory: 15239 loss_kpt: 0.000516 acc_pose: 0.838963 loss: 0.000516 2022/09/15 04:48:48 - mmengine - INFO - Epoch(train) [163][150/586] lr: 5.000000e-04 eta: 3:27:01 time: 0.471169 data_time: 0.033132 memory: 15239 loss_kpt: 0.000523 acc_pose: 0.896867 loss: 0.000523 2022/09/15 04:49:12 - mmengine - INFO - Epoch(train) [163][200/586] lr: 5.000000e-04 eta: 3:26:40 time: 0.467398 data_time: 0.027844 memory: 15239 loss_kpt: 0.000506 acc_pose: 0.862504 loss: 0.000506 2022/09/15 04:49:35 - mmengine - INFO - Epoch(train) [163][250/586] lr: 5.000000e-04 eta: 3:26:18 time: 0.474930 data_time: 0.025943 memory: 15239 loss_kpt: 0.000525 acc_pose: 0.908158 loss: 0.000525 2022/09/15 04:49:59 - mmengine - INFO - Epoch(train) [163][300/586] lr: 5.000000e-04 eta: 3:25:56 time: 0.468280 data_time: 0.027865 memory: 15239 loss_kpt: 0.000488 acc_pose: 0.900670 loss: 0.000488 2022/09/15 04:50:23 - mmengine - INFO - Epoch(train) [163][350/586] lr: 5.000000e-04 eta: 3:25:34 time: 0.473617 data_time: 0.024827 memory: 15239 loss_kpt: 0.000504 acc_pose: 0.895143 loss: 0.000504 2022/09/15 04:50:46 - mmengine - INFO - Epoch(train) [163][400/586] lr: 5.000000e-04 eta: 3:25:12 time: 0.470579 data_time: 0.024684 memory: 15239 loss_kpt: 0.000513 acc_pose: 0.866561 loss: 0.000513 2022/09/15 04:51:10 - mmengine - INFO - Epoch(train) [163][450/586] lr: 5.000000e-04 eta: 3:24:51 time: 0.475211 data_time: 0.024880 memory: 15239 loss_kpt: 0.000502 acc_pose: 0.862617 loss: 0.000502 2022/09/15 04:51:33 - mmengine - INFO - Epoch(train) [163][500/586] lr: 5.000000e-04 eta: 3:24:29 time: 0.468085 data_time: 0.025286 memory: 15239 loss_kpt: 0.000515 acc_pose: 0.871209 loss: 0.000515 2022/09/15 04:51:57 - mmengine - INFO - Epoch(train) [163][550/586] lr: 5.000000e-04 eta: 3:24:07 time: 0.468576 data_time: 0.024853 memory: 15239 loss_kpt: 0.000508 acc_pose: 0.896694 loss: 0.000508 2022/09/15 04:52:14 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 04:52:14 - mmengine - INFO - Saving checkpoint at 163 epochs 2022/09/15 04:52:45 - mmengine - INFO - Epoch(train) [164][50/586] lr: 5.000000e-04 eta: 3:23:25 time: 0.486353 data_time: 0.035382 memory: 15239 loss_kpt: 0.000512 acc_pose: 0.916631 loss: 0.000512 2022/09/15 04:53:09 - mmengine - INFO - Epoch(train) [164][100/586] lr: 5.000000e-04 eta: 3:23:03 time: 0.475109 data_time: 0.026255 memory: 15239 loss_kpt: 0.000521 acc_pose: 0.888162 loss: 0.000521 2022/09/15 04:53:32 - mmengine - INFO - Epoch(train) [164][150/586] lr: 5.000000e-04 eta: 3:22:41 time: 0.470019 data_time: 0.024729 memory: 15239 loss_kpt: 0.000513 acc_pose: 0.903742 loss: 0.000513 2022/09/15 04:53:56 - mmengine - INFO - Epoch(train) [164][200/586] lr: 5.000000e-04 eta: 3:22:19 time: 0.469031 data_time: 0.024574 memory: 15239 loss_kpt: 0.000540 acc_pose: 0.924496 loss: 0.000540 2022/09/15 04:54:20 - mmengine - INFO - Epoch(train) [164][250/586] lr: 5.000000e-04 eta: 3:21:58 time: 0.480114 data_time: 0.024704 memory: 15239 loss_kpt: 0.000508 acc_pose: 0.879796 loss: 0.000508 2022/09/15 04:54:43 - mmengine - INFO - Epoch(train) [164][300/586] lr: 5.000000e-04 eta: 3:21:36 time: 0.469943 data_time: 0.024973 memory: 15239 loss_kpt: 0.000532 acc_pose: 0.883336 loss: 0.000532 2022/09/15 04:55:07 - mmengine - INFO - Epoch(train) [164][350/586] lr: 5.000000e-04 eta: 3:21:14 time: 0.470146 data_time: 0.025171 memory: 15239 loss_kpt: 0.000517 acc_pose: 0.888832 loss: 0.000517 2022/09/15 04:55:30 - mmengine - INFO - Epoch(train) [164][400/586] lr: 5.000000e-04 eta: 3:20:52 time: 0.468924 data_time: 0.024721 memory: 15239 loss_kpt: 0.000515 acc_pose: 0.877925 loss: 0.000515 2022/09/15 04:55:54 - mmengine - INFO - Epoch(train) [164][450/586] lr: 5.000000e-04 eta: 3:20:30 time: 0.466105 data_time: 0.024990 memory: 15239 loss_kpt: 0.000510 acc_pose: 0.849415 loss: 0.000510 2022/09/15 04:56:09 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 04:56:17 - mmengine - INFO - Epoch(train) [164][500/586] lr: 5.000000e-04 eta: 3:20:08 time: 0.473189 data_time: 0.028658 memory: 15239 loss_kpt: 0.000511 acc_pose: 0.924223 loss: 0.000511 2022/09/15 04:56:41 - mmengine - INFO - Epoch(train) [164][550/586] lr: 5.000000e-04 eta: 3:19:47 time: 0.471547 data_time: 0.024646 memory: 15239 loss_kpt: 0.000514 acc_pose: 0.860751 loss: 0.000514 2022/09/15 04:56:58 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 04:56:58 - mmengine - INFO - Saving checkpoint at 164 epochs 2022/09/15 04:57:29 - mmengine - INFO - Epoch(train) [165][50/586] lr: 5.000000e-04 eta: 3:19:05 time: 0.485267 data_time: 0.035139 memory: 15239 loss_kpt: 0.000529 acc_pose: 0.877623 loss: 0.000529 2022/09/15 04:57:52 - mmengine - INFO - Epoch(train) [165][100/586] lr: 5.000000e-04 eta: 3:18:43 time: 0.468159 data_time: 0.024955 memory: 15239 loss_kpt: 0.000511 acc_pose: 0.822270 loss: 0.000511 2022/09/15 04:58:16 - mmengine - INFO - Epoch(train) [165][150/586] lr: 5.000000e-04 eta: 3:18:21 time: 0.478796 data_time: 0.029333 memory: 15239 loss_kpt: 0.000519 acc_pose: 0.884593 loss: 0.000519 2022/09/15 04:58:39 - mmengine - INFO - Epoch(train) [165][200/586] lr: 5.000000e-04 eta: 3:17:59 time: 0.464482 data_time: 0.024325 memory: 15239 loss_kpt: 0.000511 acc_pose: 0.876267 loss: 0.000511 2022/09/15 04:59:03 - mmengine - INFO - Epoch(train) [165][250/586] lr: 5.000000e-04 eta: 3:17:37 time: 0.472275 data_time: 0.024928 memory: 15239 loss_kpt: 0.000513 acc_pose: 0.881195 loss: 0.000513 2022/09/15 04:59:27 - mmengine - INFO - Epoch(train) [165][300/586] lr: 5.000000e-04 eta: 3:17:15 time: 0.472806 data_time: 0.028330 memory: 15239 loss_kpt: 0.000519 acc_pose: 0.856742 loss: 0.000519 2022/09/15 04:59:50 - mmengine - INFO - Epoch(train) [165][350/586] lr: 5.000000e-04 eta: 3:16:54 time: 0.469350 data_time: 0.024464 memory: 15239 loss_kpt: 0.000502 acc_pose: 0.921749 loss: 0.000502 2022/09/15 05:00:14 - mmengine - INFO - Epoch(train) [165][400/586] lr: 5.000000e-04 eta: 3:16:32 time: 0.484856 data_time: 0.027204 memory: 15239 loss_kpt: 0.000510 acc_pose: 0.833658 loss: 0.000510 2022/09/15 05:00:38 - mmengine - INFO - Epoch(train) [165][450/586] lr: 5.000000e-04 eta: 3:16:10 time: 0.477736 data_time: 0.029368 memory: 15239 loss_kpt: 0.000516 acc_pose: 0.894055 loss: 0.000516 2022/09/15 05:01:02 - mmengine - INFO - Epoch(train) [165][500/586] lr: 5.000000e-04 eta: 3:15:48 time: 0.465119 data_time: 0.024927 memory: 15239 loss_kpt: 0.000520 acc_pose: 0.891924 loss: 0.000520 2022/09/15 05:01:26 - mmengine - INFO - Epoch(train) [165][550/586] lr: 5.000000e-04 eta: 3:15:27 time: 0.484031 data_time: 0.027112 memory: 15239 loss_kpt: 0.000509 acc_pose: 0.890123 loss: 0.000509 2022/09/15 05:01:43 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 05:01:43 - mmengine - INFO - Saving checkpoint at 165 epochs 2022/09/15 05:02:15 - mmengine - INFO - Epoch(train) [166][50/586] lr: 5.000000e-04 eta: 3:14:45 time: 0.484133 data_time: 0.036358 memory: 15239 loss_kpt: 0.000487 acc_pose: 0.881966 loss: 0.000487 2022/09/15 05:02:38 - mmengine - INFO - Epoch(train) [166][100/586] lr: 5.000000e-04 eta: 3:14:23 time: 0.470016 data_time: 0.025267 memory: 15239 loss_kpt: 0.000509 acc_pose: 0.898388 loss: 0.000509 2022/09/15 05:03:02 - mmengine - INFO - Epoch(train) [166][150/586] lr: 5.000000e-04 eta: 3:14:01 time: 0.469511 data_time: 0.024440 memory: 15239 loss_kpt: 0.000506 acc_pose: 0.904765 loss: 0.000506 2022/09/15 05:03:25 - mmengine - INFO - Epoch(train) [166][200/586] lr: 5.000000e-04 eta: 3:13:39 time: 0.473658 data_time: 0.024494 memory: 15239 loss_kpt: 0.000502 acc_pose: 0.919407 loss: 0.000502 2022/09/15 05:03:49 - mmengine - INFO - Epoch(train) [166][250/586] lr: 5.000000e-04 eta: 3:13:17 time: 0.476266 data_time: 0.024567 memory: 15239 loss_kpt: 0.000508 acc_pose: 0.902217 loss: 0.000508 2022/09/15 05:04:13 - mmengine - INFO - Epoch(train) [166][300/586] lr: 5.000000e-04 eta: 3:12:56 time: 0.470589 data_time: 0.024507 memory: 15239 loss_kpt: 0.000524 acc_pose: 0.880710 loss: 0.000524 2022/09/15 05:04:18 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 05:04:37 - mmengine - INFO - Epoch(train) [166][350/586] lr: 5.000000e-04 eta: 3:12:34 time: 0.474386 data_time: 0.024183 memory: 15239 loss_kpt: 0.000514 acc_pose: 0.897462 loss: 0.000514 2022/09/15 05:05:00 - mmengine - INFO - Epoch(train) [166][400/586] lr: 5.000000e-04 eta: 3:12:12 time: 0.474500 data_time: 0.024741 memory: 15239 loss_kpt: 0.000529 acc_pose: 0.875206 loss: 0.000529 2022/09/15 05:05:24 - mmengine - INFO - Epoch(train) [166][450/586] lr: 5.000000e-04 eta: 3:11:50 time: 0.472596 data_time: 0.024647 memory: 15239 loss_kpt: 0.000505 acc_pose: 0.839061 loss: 0.000505 2022/09/15 05:05:48 - mmengine - INFO - Epoch(train) [166][500/586] lr: 5.000000e-04 eta: 3:11:28 time: 0.472488 data_time: 0.024284 memory: 15239 loss_kpt: 0.000508 acc_pose: 0.854664 loss: 0.000508 2022/09/15 05:06:11 - mmengine - INFO - Epoch(train) [166][550/586] lr: 5.000000e-04 eta: 3:11:07 time: 0.477665 data_time: 0.025048 memory: 15239 loss_kpt: 0.000517 acc_pose: 0.871311 loss: 0.000517 2022/09/15 05:06:28 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 05:06:28 - mmengine - INFO - Saving checkpoint at 166 epochs 2022/09/15 05:07:00 - mmengine - INFO - Epoch(train) [167][50/586] lr: 5.000000e-04 eta: 3:10:25 time: 0.486972 data_time: 0.034542 memory: 15239 loss_kpt: 0.000525 acc_pose: 0.826242 loss: 0.000525 2022/09/15 05:07:23 - mmengine - INFO - Epoch(train) [167][100/586] lr: 5.000000e-04 eta: 3:10:03 time: 0.475223 data_time: 0.027210 memory: 15239 loss_kpt: 0.000520 acc_pose: 0.862359 loss: 0.000520 2022/09/15 05:07:47 - mmengine - INFO - Epoch(train) [167][150/586] lr: 5.000000e-04 eta: 3:09:41 time: 0.480772 data_time: 0.032130 memory: 15239 loss_kpt: 0.000517 acc_pose: 0.839638 loss: 0.000517 2022/09/15 05:08:11 - mmengine - INFO - Epoch(train) [167][200/586] lr: 5.000000e-04 eta: 3:09:19 time: 0.479446 data_time: 0.027689 memory: 15239 loss_kpt: 0.000523 acc_pose: 0.859171 loss: 0.000523 2022/09/15 05:08:35 - mmengine - INFO - Epoch(train) [167][250/586] lr: 5.000000e-04 eta: 3:08:58 time: 0.475512 data_time: 0.027957 memory: 15239 loss_kpt: 0.000492 acc_pose: 0.863375 loss: 0.000492 2022/09/15 05:08:59 - mmengine - INFO - Epoch(train) [167][300/586] lr: 5.000000e-04 eta: 3:08:36 time: 0.475976 data_time: 0.026973 memory: 15239 loss_kpt: 0.000497 acc_pose: 0.874788 loss: 0.000497 2022/09/15 05:09:23 - mmengine - INFO - Epoch(train) [167][350/586] lr: 5.000000e-04 eta: 3:08:14 time: 0.472570 data_time: 0.027822 memory: 15239 loss_kpt: 0.000511 acc_pose: 0.814513 loss: 0.000511 2022/09/15 05:09:46 - mmengine - INFO - Epoch(train) [167][400/586] lr: 5.000000e-04 eta: 3:07:52 time: 0.472057 data_time: 0.024701 memory: 15239 loss_kpt: 0.000509 acc_pose: 0.898108 loss: 0.000509 2022/09/15 05:10:10 - mmengine - INFO - Epoch(train) [167][450/586] lr: 5.000000e-04 eta: 3:07:30 time: 0.480485 data_time: 0.024495 memory: 15239 loss_kpt: 0.000495 acc_pose: 0.893388 loss: 0.000495 2022/09/15 05:10:34 - mmengine - INFO - Epoch(train) [167][500/586] lr: 5.000000e-04 eta: 3:07:09 time: 0.469772 data_time: 0.024763 memory: 15239 loss_kpt: 0.000506 acc_pose: 0.907898 loss: 0.000506 2022/09/15 05:10:58 - mmengine - INFO - Epoch(train) [167][550/586] lr: 5.000000e-04 eta: 3:06:47 time: 0.478594 data_time: 0.024500 memory: 15239 loss_kpt: 0.000530 acc_pose: 0.740663 loss: 0.000530 2022/09/15 05:11:15 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 05:11:15 - mmengine - INFO - Saving checkpoint at 167 epochs 2022/09/15 05:11:46 - mmengine - INFO - Epoch(train) [168][50/586] lr: 5.000000e-04 eta: 3:06:05 time: 0.481507 data_time: 0.041585 memory: 15239 loss_kpt: 0.000530 acc_pose: 0.910516 loss: 0.000530 2022/09/15 05:12:10 - mmengine - INFO - Epoch(train) [168][100/586] lr: 5.000000e-04 eta: 3:05:43 time: 0.476995 data_time: 0.028094 memory: 15239 loss_kpt: 0.000522 acc_pose: 0.895638 loss: 0.000522 2022/09/15 05:12:28 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 05:12:34 - mmengine - INFO - Epoch(train) [168][150/586] lr: 5.000000e-04 eta: 3:05:21 time: 0.471282 data_time: 0.028084 memory: 15239 loss_kpt: 0.000510 acc_pose: 0.904634 loss: 0.000510 2022/09/15 05:12:57 - mmengine - INFO - Epoch(train) [168][200/586] lr: 5.000000e-04 eta: 3:05:00 time: 0.468757 data_time: 0.028309 memory: 15239 loss_kpt: 0.000501 acc_pose: 0.907517 loss: 0.000501 2022/09/15 05:13:21 - mmengine - INFO - Epoch(train) [168][250/586] lr: 5.000000e-04 eta: 3:04:38 time: 0.471056 data_time: 0.032844 memory: 15239 loss_kpt: 0.000493 acc_pose: 0.916414 loss: 0.000493 2022/09/15 05:13:44 - mmengine - INFO - Epoch(train) [168][300/586] lr: 5.000000e-04 eta: 3:04:16 time: 0.472583 data_time: 0.029373 memory: 15239 loss_kpt: 0.000506 acc_pose: 0.866765 loss: 0.000506 2022/09/15 05:14:08 - mmengine - INFO - Epoch(train) [168][350/586] lr: 5.000000e-04 eta: 3:03:54 time: 0.476375 data_time: 0.024483 memory: 15239 loss_kpt: 0.000522 acc_pose: 0.908812 loss: 0.000522 2022/09/15 05:14:32 - mmengine - INFO - Epoch(train) [168][400/586] lr: 5.000000e-04 eta: 3:03:32 time: 0.468526 data_time: 0.024519 memory: 15239 loss_kpt: 0.000496 acc_pose: 0.898839 loss: 0.000496 2022/09/15 05:14:55 - mmengine - INFO - Epoch(train) [168][450/586] lr: 5.000000e-04 eta: 3:03:10 time: 0.468637 data_time: 0.025145 memory: 15239 loss_kpt: 0.000522 acc_pose: 0.851553 loss: 0.000522 2022/09/15 05:15:19 - mmengine - INFO - Epoch(train) [168][500/586] lr: 5.000000e-04 eta: 3:02:48 time: 0.468591 data_time: 0.026200 memory: 15239 loss_kpt: 0.000521 acc_pose: 0.859214 loss: 0.000521 2022/09/15 05:15:42 - mmengine - INFO - Epoch(train) [168][550/586] lr: 5.000000e-04 eta: 3:02:27 time: 0.478418 data_time: 0.025702 memory: 15239 loss_kpt: 0.000522 acc_pose: 0.862193 loss: 0.000522 2022/09/15 05:15:59 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 05:15:59 - mmengine - INFO - Saving checkpoint at 168 epochs 2022/09/15 05:16:30 - mmengine - INFO - Epoch(train) [169][50/586] lr: 5.000000e-04 eta: 3:01:45 time: 0.481096 data_time: 0.038869 memory: 15239 loss_kpt: 0.000504 acc_pose: 0.899132 loss: 0.000504 2022/09/15 05:16:54 - mmengine - INFO - Epoch(train) [169][100/586] lr: 5.000000e-04 eta: 3:01:23 time: 0.473685 data_time: 0.030899 memory: 15239 loss_kpt: 0.000506 acc_pose: 0.853679 loss: 0.000506 2022/09/15 05:17:18 - mmengine - INFO - Epoch(train) [169][150/586] lr: 5.000000e-04 eta: 3:01:01 time: 0.475885 data_time: 0.036382 memory: 15239 loss_kpt: 0.000495 acc_pose: 0.849794 loss: 0.000495 2022/09/15 05:17:41 - mmengine - INFO - Epoch(train) [169][200/586] lr: 5.000000e-04 eta: 3:00:39 time: 0.474694 data_time: 0.031216 memory: 15239 loss_kpt: 0.000498 acc_pose: 0.878812 loss: 0.000498 2022/09/15 05:18:05 - mmengine - INFO - Epoch(train) [169][250/586] lr: 5.000000e-04 eta: 3:00:17 time: 0.470469 data_time: 0.031974 memory: 15239 loss_kpt: 0.000514 acc_pose: 0.838455 loss: 0.000514 2022/09/15 05:18:28 - mmengine - INFO - Epoch(train) [169][300/586] lr: 5.000000e-04 eta: 2:59:56 time: 0.471251 data_time: 0.030295 memory: 15239 loss_kpt: 0.000511 acc_pose: 0.756851 loss: 0.000511 2022/09/15 05:18:52 - mmengine - INFO - Epoch(train) [169][350/586] lr: 5.000000e-04 eta: 2:59:34 time: 0.474568 data_time: 0.029320 memory: 15239 loss_kpt: 0.000508 acc_pose: 0.890032 loss: 0.000508 2022/09/15 05:19:16 - mmengine - INFO - Epoch(train) [169][400/586] lr: 5.000000e-04 eta: 2:59:12 time: 0.468889 data_time: 0.025472 memory: 15239 loss_kpt: 0.000530 acc_pose: 0.835296 loss: 0.000530 2022/09/15 05:19:39 - mmengine - INFO - Epoch(train) [169][450/586] lr: 5.000000e-04 eta: 2:58:50 time: 0.470537 data_time: 0.025230 memory: 15239 loss_kpt: 0.000506 acc_pose: 0.879388 loss: 0.000506 2022/09/15 05:20:03 - mmengine - INFO - Epoch(train) [169][500/586] lr: 5.000000e-04 eta: 2:58:28 time: 0.473957 data_time: 0.025648 memory: 15239 loss_kpt: 0.000512 acc_pose: 0.814064 loss: 0.000512 2022/09/15 05:20:26 - mmengine - INFO - Epoch(train) [169][550/586] lr: 5.000000e-04 eta: 2:58:06 time: 0.472459 data_time: 0.024537 memory: 15239 loss_kpt: 0.000505 acc_pose: 0.889888 loss: 0.000505 2022/09/15 05:20:27 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 05:20:43 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 05:20:43 - mmengine - INFO - Saving checkpoint at 169 epochs 2022/09/15 05:21:14 - mmengine - INFO - Epoch(train) [170][50/586] lr: 5.000000e-04 eta: 2:57:25 time: 0.478868 data_time: 0.031448 memory: 15239 loss_kpt: 0.000503 acc_pose: 0.834026 loss: 0.000503 2022/09/15 05:21:38 - mmengine - INFO - Epoch(train) [170][100/586] lr: 5.000000e-04 eta: 2:57:03 time: 0.477067 data_time: 0.028773 memory: 15239 loss_kpt: 0.000527 acc_pose: 0.860086 loss: 0.000527 2022/09/15 05:22:02 - mmengine - INFO - Epoch(train) [170][150/586] lr: 5.000000e-04 eta: 2:56:41 time: 0.474834 data_time: 0.026668 memory: 15239 loss_kpt: 0.000497 acc_pose: 0.896550 loss: 0.000497 2022/09/15 05:22:25 - mmengine - INFO - Epoch(train) [170][200/586] lr: 5.000000e-04 eta: 2:56:19 time: 0.472604 data_time: 0.025635 memory: 15239 loss_kpt: 0.000500 acc_pose: 0.913397 loss: 0.000500 2022/09/15 05:22:49 - mmengine - INFO - Epoch(train) [170][250/586] lr: 5.000000e-04 eta: 2:55:57 time: 0.482799 data_time: 0.025017 memory: 15239 loss_kpt: 0.000502 acc_pose: 0.911817 loss: 0.000502 2022/09/15 05:23:13 - mmengine - INFO - Epoch(train) [170][300/586] lr: 5.000000e-04 eta: 2:55:36 time: 0.475706 data_time: 0.025195 memory: 15239 loss_kpt: 0.000510 acc_pose: 0.908155 loss: 0.000510 2022/09/15 05:23:37 - mmengine - INFO - Epoch(train) [170][350/586] lr: 5.000000e-04 eta: 2:55:14 time: 0.469624 data_time: 0.025050 memory: 15239 loss_kpt: 0.000513 acc_pose: 0.866983 loss: 0.000513 2022/09/15 05:24:00 - mmengine - INFO - Epoch(train) [170][400/586] lr: 5.000000e-04 eta: 2:54:52 time: 0.468938 data_time: 0.029090 memory: 15239 loss_kpt: 0.000497 acc_pose: 0.872856 loss: 0.000497 2022/09/15 05:24:24 - mmengine - INFO - Epoch(train) [170][450/586] lr: 5.000000e-04 eta: 2:54:30 time: 0.470547 data_time: 0.024937 memory: 15239 loss_kpt: 0.000497 acc_pose: 0.903932 loss: 0.000497 2022/09/15 05:24:47 - mmengine - INFO - Epoch(train) [170][500/586] lr: 5.000000e-04 eta: 2:54:08 time: 0.469785 data_time: 0.024978 memory: 15239 loss_kpt: 0.000502 acc_pose: 0.809243 loss: 0.000502 2022/09/15 05:25:11 - mmengine - INFO - Epoch(train) [170][550/586] lr: 5.000000e-04 eta: 2:53:46 time: 0.473377 data_time: 0.025029 memory: 15239 loss_kpt: 0.000496 acc_pose: 0.924784 loss: 0.000496 2022/09/15 05:25:28 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 05:25:28 - mmengine - INFO - Saving checkpoint at 170 epochs 2022/09/15 05:25:45 - mmengine - INFO - Epoch(val) [170][50/407] eta: 0:01:12 time: 0.203859 data_time: 0.015169 memory: 15239 2022/09/15 05:25:55 - mmengine - INFO - Epoch(val) [170][100/407] eta: 0:01:01 time: 0.198984 data_time: 0.012036 memory: 2064 2022/09/15 05:26:05 - mmengine - INFO - Epoch(val) [170][150/407] eta: 0:00:50 time: 0.195961 data_time: 0.008429 memory: 2064 2022/09/15 05:26:15 - mmengine - INFO - Epoch(val) [170][200/407] eta: 0:00:40 time: 0.196362 data_time: 0.008484 memory: 2064 2022/09/15 05:26:25 - mmengine - INFO - Epoch(val) [170][250/407] eta: 0:00:30 time: 0.196718 data_time: 0.008745 memory: 2064 2022/09/15 05:26:35 - mmengine - INFO - Epoch(val) [170][300/407] eta: 0:00:20 time: 0.196246 data_time: 0.008521 memory: 2064 2022/09/15 05:26:44 - mmengine - INFO - Epoch(val) [170][350/407] eta: 0:00:11 time: 0.195515 data_time: 0.008580 memory: 2064 2022/09/15 05:26:54 - mmengine - INFO - Epoch(val) [170][400/407] eta: 0:00:01 time: 0.193186 data_time: 0.007868 memory: 2064 2022/09/15 05:27:31 - mmengine - INFO - Evaluating CocoMetric... 2022/09/15 05:27:45 - mmengine - INFO - Epoch(val) [170][407/407] coco/AP: 0.756349 coco/AP .5: 0.906754 coco/AP .75: 0.821768 coco/AP (M): 0.715476 coco/AP (L): 0.826816 coco/AR: 0.805919 coco/AR .5: 0.941121 coco/AR .75: 0.864610 coco/AR (M): 0.761786 coco/AR (L): 0.869900 2022/09/15 05:28:09 - mmengine - INFO - Epoch(train) [171][50/586] lr: 5.000000e-05 eta: 2:53:05 time: 0.486163 data_time: 0.030622 memory: 15239 loss_kpt: 0.000513 acc_pose: 0.924347 loss: 0.000513 2022/09/15 05:28:33 - mmengine - INFO - Epoch(train) [171][100/586] lr: 5.000000e-05 eta: 2:52:43 time: 0.477864 data_time: 0.024508 memory: 15239 loss_kpt: 0.000501 acc_pose: 0.882255 loss: 0.000501 2022/09/15 05:28:57 - mmengine - INFO - Epoch(train) [171][150/586] lr: 5.000000e-05 eta: 2:52:21 time: 0.475601 data_time: 0.025215 memory: 15239 loss_kpt: 0.000522 acc_pose: 0.891995 loss: 0.000522 2022/09/15 05:29:21 - mmengine - INFO - Epoch(train) [171][200/586] lr: 5.000000e-05 eta: 2:51:59 time: 0.471945 data_time: 0.025055 memory: 15239 loss_kpt: 0.000504 acc_pose: 0.901063 loss: 0.000504 2022/09/15 05:29:45 - mmengine - INFO - Epoch(train) [171][250/586] lr: 5.000000e-05 eta: 2:51:38 time: 0.490195 data_time: 0.025896 memory: 15239 loss_kpt: 0.000497 acc_pose: 0.873589 loss: 0.000497 2022/09/15 05:30:09 - mmengine - INFO - Epoch(train) [171][300/586] lr: 5.000000e-05 eta: 2:51:16 time: 0.470213 data_time: 0.024701 memory: 15239 loss_kpt: 0.000500 acc_pose: 0.915274 loss: 0.000500 2022/09/15 05:30:32 - mmengine - INFO - Epoch(train) [171][350/586] lr: 5.000000e-05 eta: 2:50:54 time: 0.467446 data_time: 0.024800 memory: 15239 loss_kpt: 0.000503 acc_pose: 0.881606 loss: 0.000503 2022/09/15 05:30:46 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 05:30:56 - mmengine - INFO - Epoch(train) [171][400/586] lr: 5.000000e-05 eta: 2:50:32 time: 0.474730 data_time: 0.025174 memory: 15239 loss_kpt: 0.000490 acc_pose: 0.907998 loss: 0.000490 2022/09/15 05:31:19 - mmengine - INFO - Epoch(train) [171][450/586] lr: 5.000000e-05 eta: 2:50:10 time: 0.466928 data_time: 0.023824 memory: 15239 loss_kpt: 0.000483 acc_pose: 0.894867 loss: 0.000483 2022/09/15 05:31:43 - mmengine - INFO - Epoch(train) [171][500/586] lr: 5.000000e-05 eta: 2:49:48 time: 0.476405 data_time: 0.024977 memory: 15239 loss_kpt: 0.000495 acc_pose: 0.848101 loss: 0.000495 2022/09/15 05:32:07 - mmengine - INFO - Epoch(train) [171][550/586] lr: 5.000000e-05 eta: 2:49:26 time: 0.478080 data_time: 0.029649 memory: 15239 loss_kpt: 0.000498 acc_pose: 0.856353 loss: 0.000498 2022/09/15 05:32:24 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 05:32:24 - mmengine - INFO - Saving checkpoint at 171 epochs 2022/09/15 05:32:55 - mmengine - INFO - Epoch(train) [172][50/586] lr: 5.000000e-05 eta: 2:48:45 time: 0.482564 data_time: 0.034704 memory: 15239 loss_kpt: 0.000491 acc_pose: 0.911388 loss: 0.000491 2022/09/15 05:33:18 - mmengine - INFO - Epoch(train) [172][100/586] lr: 5.000000e-05 eta: 2:48:23 time: 0.470242 data_time: 0.029243 memory: 15239 loss_kpt: 0.000492 acc_pose: 0.849504 loss: 0.000492 2022/09/15 05:33:42 - mmengine - INFO - Epoch(train) [172][150/586] lr: 5.000000e-05 eta: 2:48:01 time: 0.474495 data_time: 0.030519 memory: 15239 loss_kpt: 0.000492 acc_pose: 0.881956 loss: 0.000492 2022/09/15 05:34:05 - mmengine - INFO - Epoch(train) [172][200/586] lr: 5.000000e-05 eta: 2:47:39 time: 0.464279 data_time: 0.027219 memory: 15239 loss_kpt: 0.000505 acc_pose: 0.865796 loss: 0.000505 2022/09/15 05:34:29 - mmengine - INFO - Epoch(train) [172][250/586] lr: 5.000000e-05 eta: 2:47:17 time: 0.475541 data_time: 0.025044 memory: 15239 loss_kpt: 0.000491 acc_pose: 0.910730 loss: 0.000491 2022/09/15 05:34:53 - mmengine - INFO - Epoch(train) [172][300/586] lr: 5.000000e-05 eta: 2:46:55 time: 0.469815 data_time: 0.028508 memory: 15239 loss_kpt: 0.000510 acc_pose: 0.920449 loss: 0.000510 2022/09/15 05:35:16 - mmengine - INFO - Epoch(train) [172][350/586] lr: 5.000000e-05 eta: 2:46:33 time: 0.467875 data_time: 0.025055 memory: 15239 loss_kpt: 0.000487 acc_pose: 0.918919 loss: 0.000487 2022/09/15 05:35:40 - mmengine - INFO - Epoch(train) [172][400/586] lr: 5.000000e-05 eta: 2:46:12 time: 0.484440 data_time: 0.024888 memory: 15239 loss_kpt: 0.000488 acc_pose: 0.908967 loss: 0.000488 2022/09/15 05:36:04 - mmengine - INFO - Epoch(train) [172][450/586] lr: 5.000000e-05 eta: 2:45:50 time: 0.475514 data_time: 0.025258 memory: 15239 loss_kpt: 0.000490 acc_pose: 0.858280 loss: 0.000490 2022/09/15 05:36:27 - mmengine - INFO - Epoch(train) [172][500/586] lr: 5.000000e-05 eta: 2:45:28 time: 0.465613 data_time: 0.024858 memory: 15239 loss_kpt: 0.000490 acc_pose: 0.933042 loss: 0.000490 2022/09/15 05:36:51 - mmengine - INFO - Epoch(train) [172][550/586] lr: 5.000000e-05 eta: 2:45:06 time: 0.470834 data_time: 0.024236 memory: 15239 loss_kpt: 0.000481 acc_pose: 0.914655 loss: 0.000481 2022/09/15 05:37:08 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 05:37:08 - mmengine - INFO - Saving checkpoint at 172 epochs 2022/09/15 05:37:39 - mmengine - INFO - Epoch(train) [173][50/586] lr: 5.000000e-05 eta: 2:44:25 time: 0.478883 data_time: 0.032676 memory: 15239 loss_kpt: 0.000501 acc_pose: 0.829083 loss: 0.000501 2022/09/15 05:38:02 - mmengine - INFO - Epoch(train) [173][100/586] lr: 5.000000e-05 eta: 2:44:03 time: 0.472822 data_time: 0.027909 memory: 15239 loss_kpt: 0.000497 acc_pose: 0.913999 loss: 0.000497 2022/09/15 05:38:26 - mmengine - INFO - Epoch(train) [173][150/586] lr: 5.000000e-05 eta: 2:43:41 time: 0.471839 data_time: 0.027563 memory: 15239 loss_kpt: 0.000485 acc_pose: 0.910254 loss: 0.000485 2022/09/15 05:38:50 - mmengine - INFO - Epoch(train) [173][200/586] lr: 5.000000e-05 eta: 2:43:19 time: 0.480198 data_time: 0.027857 memory: 15239 loss_kpt: 0.000487 acc_pose: 0.905478 loss: 0.000487 2022/09/15 05:38:54 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 05:39:13 - mmengine - INFO - Epoch(train) [173][250/586] lr: 5.000000e-05 eta: 2:42:57 time: 0.468038 data_time: 0.027631 memory: 15239 loss_kpt: 0.000485 acc_pose: 0.814727 loss: 0.000485 2022/09/15 05:39:37 - mmengine - INFO - Epoch(train) [173][300/586] lr: 5.000000e-05 eta: 2:42:35 time: 0.479406 data_time: 0.031877 memory: 15239 loss_kpt: 0.000499 acc_pose: 0.886353 loss: 0.000499 2022/09/15 05:40:01 - mmengine - INFO - Epoch(train) [173][350/586] lr: 5.000000e-05 eta: 2:42:13 time: 0.464924 data_time: 0.027892 memory: 15239 loss_kpt: 0.000489 acc_pose: 0.882041 loss: 0.000489 2022/09/15 05:40:24 - mmengine - INFO - Epoch(train) [173][400/586] lr: 5.000000e-05 eta: 2:41:51 time: 0.477052 data_time: 0.030450 memory: 15239 loss_kpt: 0.000497 acc_pose: 0.872612 loss: 0.000497 2022/09/15 05:40:49 - mmengine - INFO - Epoch(train) [173][450/586] lr: 5.000000e-05 eta: 2:41:30 time: 0.486368 data_time: 0.028790 memory: 15239 loss_kpt: 0.000488 acc_pose: 0.849373 loss: 0.000488 2022/09/15 05:41:12 - mmengine - INFO - Epoch(train) [173][500/586] lr: 5.000000e-05 eta: 2:41:08 time: 0.472394 data_time: 0.031875 memory: 15239 loss_kpt: 0.000484 acc_pose: 0.911021 loss: 0.000484 2022/09/15 05:41:36 - mmengine - INFO - Epoch(train) [173][550/586] lr: 5.000000e-05 eta: 2:40:46 time: 0.472655 data_time: 0.033139 memory: 15239 loss_kpt: 0.000488 acc_pose: 0.887316 loss: 0.000488 2022/09/15 05:41:53 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 05:41:53 - mmengine - INFO - Saving checkpoint at 173 epochs 2022/09/15 05:42:24 - mmengine - INFO - Epoch(train) [174][50/586] lr: 5.000000e-05 eta: 2:40:05 time: 0.480666 data_time: 0.034421 memory: 15239 loss_kpt: 0.000479 acc_pose: 0.889064 loss: 0.000479 2022/09/15 05:42:48 - mmengine - INFO - Epoch(train) [174][100/586] lr: 5.000000e-05 eta: 2:39:43 time: 0.470431 data_time: 0.024872 memory: 15239 loss_kpt: 0.000474 acc_pose: 0.879772 loss: 0.000474 2022/09/15 05:43:12 - mmengine - INFO - Epoch(train) [174][150/586] lr: 5.000000e-05 eta: 2:39:21 time: 0.480434 data_time: 0.024470 memory: 15239 loss_kpt: 0.000503 acc_pose: 0.826152 loss: 0.000503 2022/09/15 05:43:35 - mmengine - INFO - Epoch(train) [174][200/586] lr: 5.000000e-05 eta: 2:38:59 time: 0.470895 data_time: 0.025217 memory: 15239 loss_kpt: 0.000479 acc_pose: 0.919107 loss: 0.000479 2022/09/15 05:43:59 - mmengine - INFO - Epoch(train) [174][250/586] lr: 5.000000e-05 eta: 2:38:37 time: 0.469783 data_time: 0.025435 memory: 15239 loss_kpt: 0.000496 acc_pose: 0.857203 loss: 0.000496 2022/09/15 05:44:23 - mmengine - INFO - Epoch(train) [174][300/586] lr: 5.000000e-05 eta: 2:38:15 time: 0.477150 data_time: 0.024349 memory: 15239 loss_kpt: 0.000479 acc_pose: 0.893074 loss: 0.000479 2022/09/15 05:44:46 - mmengine - INFO - Epoch(train) [174][350/586] lr: 5.000000e-05 eta: 2:37:53 time: 0.465797 data_time: 0.024531 memory: 15239 loss_kpt: 0.000486 acc_pose: 0.940352 loss: 0.000486 2022/09/15 05:45:10 - mmengine - INFO - Epoch(train) [174][400/586] lr: 5.000000e-05 eta: 2:37:31 time: 0.477243 data_time: 0.024650 memory: 15239 loss_kpt: 0.000489 acc_pose: 0.922369 loss: 0.000489 2022/09/15 05:45:33 - mmengine - INFO - Epoch(train) [174][450/586] lr: 5.000000e-05 eta: 2:37:09 time: 0.473105 data_time: 0.029428 memory: 15239 loss_kpt: 0.000500 acc_pose: 0.895461 loss: 0.000500 2022/09/15 05:45:57 - mmengine - INFO - Epoch(train) [174][500/586] lr: 5.000000e-05 eta: 2:36:47 time: 0.470089 data_time: 0.024841 memory: 15239 loss_kpt: 0.000488 acc_pose: 0.903840 loss: 0.000488 2022/09/15 05:46:21 - mmengine - INFO - Epoch(train) [174][550/586] lr: 5.000000e-05 eta: 2:36:26 time: 0.476305 data_time: 0.024506 memory: 15239 loss_kpt: 0.000486 acc_pose: 0.898748 loss: 0.000486 2022/09/15 05:46:37 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 05:46:38 - mmengine - INFO - Saving checkpoint at 174 epochs 2022/09/15 05:47:02 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 05:47:08 - mmengine - INFO - Epoch(train) [175][50/586] lr: 5.000000e-05 eta: 2:35:44 time: 0.479236 data_time: 0.033622 memory: 15239 loss_kpt: 0.000472 acc_pose: 0.850242 loss: 0.000472 2022/09/15 05:47:32 - mmengine - INFO - Epoch(train) [175][100/586] lr: 5.000000e-05 eta: 2:35:23 time: 0.476944 data_time: 0.027703 memory: 15239 loss_kpt: 0.000477 acc_pose: 0.923152 loss: 0.000477 2022/09/15 05:47:56 - mmengine - INFO - Epoch(train) [175][150/586] lr: 5.000000e-05 eta: 2:35:01 time: 0.468796 data_time: 0.029531 memory: 15239 loss_kpt: 0.000485 acc_pose: 0.842605 loss: 0.000485 2022/09/15 05:48:19 - mmengine - INFO - Epoch(train) [175][200/586] lr: 5.000000e-05 eta: 2:34:39 time: 0.472284 data_time: 0.028522 memory: 15239 loss_kpt: 0.000468 acc_pose: 0.915884 loss: 0.000468 2022/09/15 05:48:43 - mmengine - INFO - Epoch(train) [175][250/586] lr: 5.000000e-05 eta: 2:34:17 time: 0.470019 data_time: 0.027568 memory: 15239 loss_kpt: 0.000486 acc_pose: 0.872909 loss: 0.000486 2022/09/15 05:49:06 - mmengine - INFO - Epoch(train) [175][300/586] lr: 5.000000e-05 eta: 2:33:55 time: 0.474093 data_time: 0.028884 memory: 15239 loss_kpt: 0.000470 acc_pose: 0.873553 loss: 0.000470 2022/09/15 05:49:30 - mmengine - INFO - Epoch(train) [175][350/586] lr: 5.000000e-05 eta: 2:33:33 time: 0.467903 data_time: 0.024650 memory: 15239 loss_kpt: 0.000485 acc_pose: 0.866167 loss: 0.000485 2022/09/15 05:49:54 - mmengine - INFO - Epoch(train) [175][400/586] lr: 5.000000e-05 eta: 2:33:11 time: 0.473464 data_time: 0.024109 memory: 15239 loss_kpt: 0.000474 acc_pose: 0.909515 loss: 0.000474 2022/09/15 05:50:17 - mmengine - INFO - Epoch(train) [175][450/586] lr: 5.000000e-05 eta: 2:32:49 time: 0.470102 data_time: 0.028807 memory: 15239 loss_kpt: 0.000483 acc_pose: 0.836549 loss: 0.000483 2022/09/15 05:50:41 - mmengine - INFO - Epoch(train) [175][500/586] lr: 5.000000e-05 eta: 2:32:27 time: 0.477815 data_time: 0.024612 memory: 15239 loss_kpt: 0.000478 acc_pose: 0.855482 loss: 0.000478 2022/09/15 05:51:05 - mmengine - INFO - Epoch(train) [175][550/586] lr: 5.000000e-05 eta: 2:32:05 time: 0.473147 data_time: 0.025267 memory: 15239 loss_kpt: 0.000482 acc_pose: 0.880102 loss: 0.000482 2022/09/15 05:51:21 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 05:51:21 - mmengine - INFO - Saving checkpoint at 175 epochs 2022/09/15 05:51:52 - mmengine - INFO - Epoch(train) [176][50/586] lr: 5.000000e-05 eta: 2:31:24 time: 0.472311 data_time: 0.028559 memory: 15239 loss_kpt: 0.000467 acc_pose: 0.896221 loss: 0.000467 2022/09/15 05:52:16 - mmengine - INFO - Epoch(train) [176][100/586] lr: 5.000000e-05 eta: 2:31:02 time: 0.474906 data_time: 0.029140 memory: 15239 loss_kpt: 0.000475 acc_pose: 0.858891 loss: 0.000475 2022/09/15 05:52:40 - mmengine - INFO - Epoch(train) [176][150/586] lr: 5.000000e-05 eta: 2:30:40 time: 0.469679 data_time: 0.025298 memory: 15239 loss_kpt: 0.000468 acc_pose: 0.856500 loss: 0.000468 2022/09/15 05:53:03 - mmengine - INFO - Epoch(train) [176][200/586] lr: 5.000000e-05 eta: 2:30:18 time: 0.476871 data_time: 0.024660 memory: 15239 loss_kpt: 0.000495 acc_pose: 0.874319 loss: 0.000495 2022/09/15 05:53:27 - mmengine - INFO - Epoch(train) [176][250/586] lr: 5.000000e-05 eta: 2:29:57 time: 0.479241 data_time: 0.025126 memory: 15239 loss_kpt: 0.000478 acc_pose: 0.914350 loss: 0.000478 2022/09/15 05:53:51 - mmengine - INFO - Epoch(train) [176][300/586] lr: 5.000000e-05 eta: 2:29:35 time: 0.468394 data_time: 0.024839 memory: 15239 loss_kpt: 0.000482 acc_pose: 0.869829 loss: 0.000482 2022/09/15 05:54:14 - mmengine - INFO - Epoch(train) [176][350/586] lr: 5.000000e-05 eta: 2:29:13 time: 0.469109 data_time: 0.024355 memory: 15239 loss_kpt: 0.000477 acc_pose: 0.920129 loss: 0.000477 2022/09/15 05:54:38 - mmengine - INFO - Epoch(train) [176][400/586] lr: 5.000000e-05 eta: 2:28:51 time: 0.472593 data_time: 0.029302 memory: 15239 loss_kpt: 0.000477 acc_pose: 0.935413 loss: 0.000477 2022/09/15 05:55:01 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 05:55:01 - mmengine - INFO - Epoch(train) [176][450/586] lr: 5.000000e-05 eta: 2:28:29 time: 0.467166 data_time: 0.025227 memory: 15239 loss_kpt: 0.000459 acc_pose: 0.854303 loss: 0.000459 2022/09/15 05:55:25 - mmengine - INFO - Epoch(train) [176][500/586] lr: 5.000000e-05 eta: 2:28:07 time: 0.466314 data_time: 0.026114 memory: 15239 loss_kpt: 0.000483 acc_pose: 0.889641 loss: 0.000483 2022/09/15 05:55:48 - mmengine - INFO - Epoch(train) [176][550/586] lr: 5.000000e-05 eta: 2:27:45 time: 0.477529 data_time: 0.024753 memory: 15239 loss_kpt: 0.000472 acc_pose: 0.862166 loss: 0.000472 2022/09/15 05:56:05 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 05:56:05 - mmengine - INFO - Saving checkpoint at 176 epochs 2022/09/15 05:56:37 - mmengine - INFO - Epoch(train) [177][50/586] lr: 5.000000e-05 eta: 2:27:04 time: 0.486902 data_time: 0.028657 memory: 15239 loss_kpt: 0.000486 acc_pose: 0.840713 loss: 0.000486 2022/09/15 05:57:00 - mmengine - INFO - Epoch(train) [177][100/586] lr: 5.000000e-05 eta: 2:26:42 time: 0.472830 data_time: 0.024059 memory: 15239 loss_kpt: 0.000471 acc_pose: 0.887371 loss: 0.000471 2022/09/15 05:57:24 - mmengine - INFO - Epoch(train) [177][150/586] lr: 5.000000e-05 eta: 2:26:20 time: 0.473154 data_time: 0.024957 memory: 15239 loss_kpt: 0.000475 acc_pose: 0.905101 loss: 0.000475 2022/09/15 05:57:48 - mmengine - INFO - Epoch(train) [177][200/586] lr: 5.000000e-05 eta: 2:25:58 time: 0.474417 data_time: 0.028579 memory: 15239 loss_kpt: 0.000477 acc_pose: 0.888462 loss: 0.000477 2022/09/15 05:58:11 - mmengine - INFO - Epoch(train) [177][250/586] lr: 5.000000e-05 eta: 2:25:36 time: 0.476290 data_time: 0.025702 memory: 15239 loss_kpt: 0.000478 acc_pose: 0.899461 loss: 0.000478 2022/09/15 05:58:35 - mmengine - INFO - Epoch(train) [177][300/586] lr: 5.000000e-05 eta: 2:25:14 time: 0.462859 data_time: 0.024650 memory: 15239 loss_kpt: 0.000473 acc_pose: 0.875066 loss: 0.000473 2022/09/15 05:58:58 - mmengine - INFO - Epoch(train) [177][350/586] lr: 5.000000e-05 eta: 2:24:52 time: 0.474600 data_time: 0.024215 memory: 15239 loss_kpt: 0.000486 acc_pose: 0.858218 loss: 0.000486 2022/09/15 05:59:22 - mmengine - INFO - Epoch(train) [177][400/586] lr: 5.000000e-05 eta: 2:24:31 time: 0.478874 data_time: 0.024998 memory: 15239 loss_kpt: 0.000479 acc_pose: 0.904288 loss: 0.000479 2022/09/15 05:59:46 - mmengine - INFO - Epoch(train) [177][450/586] lr: 5.000000e-05 eta: 2:24:09 time: 0.463346 data_time: 0.024836 memory: 15239 loss_kpt: 0.000483 acc_pose: 0.870726 loss: 0.000483 2022/09/15 06:00:11 - mmengine - INFO - Epoch(train) [177][500/586] lr: 5.000000e-05 eta: 2:23:47 time: 0.506375 data_time: 0.033003 memory: 15239 loss_kpt: 0.000482 acc_pose: 0.801814 loss: 0.000482 2022/09/15 06:00:35 - mmengine - INFO - Epoch(train) [177][550/586] lr: 5.000000e-05 eta: 2:23:25 time: 0.474086 data_time: 0.025150 memory: 15239 loss_kpt: 0.000464 acc_pose: 0.892533 loss: 0.000464 2022/09/15 06:00:51 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 06:00:51 - mmengine - INFO - Saving checkpoint at 177 epochs 2022/09/15 06:01:23 - mmengine - INFO - Epoch(train) [178][50/586] lr: 5.000000e-05 eta: 2:22:44 time: 0.494220 data_time: 0.044359 memory: 15239 loss_kpt: 0.000473 acc_pose: 0.900553 loss: 0.000473 2022/09/15 06:01:47 - mmengine - INFO - Epoch(train) [178][100/586] lr: 5.000000e-05 eta: 2:22:22 time: 0.471860 data_time: 0.024799 memory: 15239 loss_kpt: 0.000470 acc_pose: 0.831304 loss: 0.000470 2022/09/15 06:02:10 - mmengine - INFO - Epoch(train) [178][150/586] lr: 5.000000e-05 eta: 2:22:00 time: 0.470935 data_time: 0.028332 memory: 15239 loss_kpt: 0.000500 acc_pose: 0.843101 loss: 0.000500 2022/09/15 06:02:34 - mmengine - INFO - Epoch(train) [178][200/586] lr: 5.000000e-05 eta: 2:21:38 time: 0.472237 data_time: 0.025014 memory: 15239 loss_kpt: 0.000486 acc_pose: 0.840060 loss: 0.000486 2022/09/15 06:02:58 - mmengine - INFO - Epoch(train) [178][250/586] lr: 5.000000e-05 eta: 2:21:17 time: 0.480713 data_time: 0.024969 memory: 15239 loss_kpt: 0.000484 acc_pose: 0.867637 loss: 0.000484 2022/09/15 06:03:11 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 06:03:22 - mmengine - INFO - Epoch(train) [178][300/586] lr: 5.000000e-05 eta: 2:20:55 time: 0.473634 data_time: 0.028819 memory: 15239 loss_kpt: 0.000475 acc_pose: 0.865120 loss: 0.000475 2022/09/15 06:03:45 - mmengine - INFO - Epoch(train) [178][350/586] lr: 5.000000e-05 eta: 2:20:33 time: 0.467883 data_time: 0.025339 memory: 15239 loss_kpt: 0.000477 acc_pose: 0.862863 loss: 0.000477 2022/09/15 06:04:08 - mmengine - INFO - Epoch(train) [178][400/586] lr: 5.000000e-05 eta: 2:20:11 time: 0.469700 data_time: 0.024476 memory: 15239 loss_kpt: 0.000484 acc_pose: 0.843368 loss: 0.000484 2022/09/15 06:04:32 - mmengine - INFO - Epoch(train) [178][450/586] lr: 5.000000e-05 eta: 2:19:49 time: 0.469512 data_time: 0.024813 memory: 15239 loss_kpt: 0.000488 acc_pose: 0.888303 loss: 0.000488 2022/09/15 06:04:56 - mmengine - INFO - Epoch(train) [178][500/586] lr: 5.000000e-05 eta: 2:19:27 time: 0.475005 data_time: 0.026187 memory: 15239 loss_kpt: 0.000485 acc_pose: 0.886482 loss: 0.000485 2022/09/15 06:05:20 - mmengine - INFO - Epoch(train) [178][550/586] lr: 5.000000e-05 eta: 2:19:05 time: 0.477858 data_time: 0.024980 memory: 15239 loss_kpt: 0.000482 acc_pose: 0.916492 loss: 0.000482 2022/09/15 06:05:37 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 06:05:37 - mmengine - INFO - Saving checkpoint at 178 epochs 2022/09/15 06:06:07 - mmengine - INFO - Epoch(train) [179][50/586] lr: 5.000000e-05 eta: 2:18:24 time: 0.482744 data_time: 0.029479 memory: 15239 loss_kpt: 0.000485 acc_pose: 0.895742 loss: 0.000485 2022/09/15 06:06:31 - mmengine - INFO - Epoch(train) [179][100/586] lr: 5.000000e-05 eta: 2:18:02 time: 0.474937 data_time: 0.027786 memory: 15239 loss_kpt: 0.000479 acc_pose: 0.905213 loss: 0.000479 2022/09/15 06:06:55 - mmengine - INFO - Epoch(train) [179][150/586] lr: 5.000000e-05 eta: 2:17:40 time: 0.476989 data_time: 0.024991 memory: 15239 loss_kpt: 0.000463 acc_pose: 0.925428 loss: 0.000463 2022/09/15 06:07:18 - mmengine - INFO - Epoch(train) [179][200/586] lr: 5.000000e-05 eta: 2:17:18 time: 0.467707 data_time: 0.024516 memory: 15239 loss_kpt: 0.000473 acc_pose: 0.895406 loss: 0.000473 2022/09/15 06:07:42 - mmengine - INFO - Epoch(train) [179][250/586] lr: 5.000000e-05 eta: 2:16:56 time: 0.479305 data_time: 0.027567 memory: 15239 loss_kpt: 0.000468 acc_pose: 0.934201 loss: 0.000468 2022/09/15 06:08:06 - mmengine - INFO - Epoch(train) [179][300/586] lr: 5.000000e-05 eta: 2:16:34 time: 0.467980 data_time: 0.025127 memory: 15239 loss_kpt: 0.000471 acc_pose: 0.861382 loss: 0.000471 2022/09/15 06:08:30 - mmengine - INFO - Epoch(train) [179][350/586] lr: 5.000000e-05 eta: 2:16:13 time: 0.476630 data_time: 0.024720 memory: 15239 loss_kpt: 0.000480 acc_pose: 0.914983 loss: 0.000480 2022/09/15 06:08:54 - mmengine - INFO - Epoch(train) [179][400/586] lr: 5.000000e-05 eta: 2:15:51 time: 0.483194 data_time: 0.024296 memory: 15239 loss_kpt: 0.000492 acc_pose: 0.870085 loss: 0.000492 2022/09/15 06:09:17 - mmengine - INFO - Epoch(train) [179][450/586] lr: 5.000000e-05 eta: 2:15:29 time: 0.465346 data_time: 0.025058 memory: 15239 loss_kpt: 0.000486 acc_pose: 0.914780 loss: 0.000486 2022/09/15 06:09:41 - mmengine - INFO - Epoch(train) [179][500/586] lr: 5.000000e-05 eta: 2:15:07 time: 0.477980 data_time: 0.025273 memory: 15239 loss_kpt: 0.000466 acc_pose: 0.868284 loss: 0.000466 2022/09/15 06:10:05 - mmengine - INFO - Epoch(train) [179][550/586] lr: 5.000000e-05 eta: 2:14:45 time: 0.476962 data_time: 0.028493 memory: 15239 loss_kpt: 0.000483 acc_pose: 0.881206 loss: 0.000483 2022/09/15 06:10:22 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 06:10:22 - mmengine - INFO - Saving checkpoint at 179 epochs 2022/09/15 06:10:53 - mmengine - INFO - Epoch(train) [180][50/586] lr: 5.000000e-05 eta: 2:14:04 time: 0.481154 data_time: 0.033269 memory: 15239 loss_kpt: 0.000477 acc_pose: 0.882737 loss: 0.000477 2022/09/15 06:11:16 - mmengine - INFO - Epoch(train) [180][100/586] lr: 5.000000e-05 eta: 2:13:42 time: 0.465349 data_time: 0.028183 memory: 15239 loss_kpt: 0.000491 acc_pose: 0.820388 loss: 0.000491 2022/09/15 06:11:19 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 06:11:40 - mmengine - INFO - Epoch(train) [180][150/586] lr: 5.000000e-05 eta: 2:13:20 time: 0.472874 data_time: 0.034050 memory: 15239 loss_kpt: 0.000489 acc_pose: 0.855045 loss: 0.000489 2022/09/15 06:12:03 - mmengine - INFO - Epoch(train) [180][200/586] lr: 5.000000e-05 eta: 2:12:58 time: 0.478512 data_time: 0.030285 memory: 15239 loss_kpt: 0.000477 acc_pose: 0.880914 loss: 0.000477 2022/09/15 06:12:27 - mmengine - INFO - Epoch(train) [180][250/586] lr: 5.000000e-05 eta: 2:12:36 time: 0.474141 data_time: 0.024984 memory: 15239 loss_kpt: 0.000474 acc_pose: 0.899889 loss: 0.000474 2022/09/15 06:12:51 - mmengine - INFO - Epoch(train) [180][300/586] lr: 5.000000e-05 eta: 2:12:14 time: 0.469748 data_time: 0.030429 memory: 15239 loss_kpt: 0.000457 acc_pose: 0.857811 loss: 0.000457 2022/09/15 06:13:14 - mmengine - INFO - Epoch(train) [180][350/586] lr: 5.000000e-05 eta: 2:11:52 time: 0.473087 data_time: 0.024373 memory: 15239 loss_kpt: 0.000477 acc_pose: 0.867299 loss: 0.000477 2022/09/15 06:13:38 - mmengine - INFO - Epoch(train) [180][400/586] lr: 5.000000e-05 eta: 2:11:30 time: 0.473400 data_time: 0.025156 memory: 15239 loss_kpt: 0.000482 acc_pose: 0.897466 loss: 0.000482 2022/09/15 06:14:02 - mmengine - INFO - Epoch(train) [180][450/586] lr: 5.000000e-05 eta: 2:11:08 time: 0.468894 data_time: 0.025168 memory: 15239 loss_kpt: 0.000498 acc_pose: 0.869059 loss: 0.000498 2022/09/15 06:14:25 - mmengine - INFO - Epoch(train) [180][500/586] lr: 5.000000e-05 eta: 2:10:46 time: 0.477033 data_time: 0.024565 memory: 15239 loss_kpt: 0.000473 acc_pose: 0.909409 loss: 0.000473 2022/09/15 06:14:49 - mmengine - INFO - Epoch(train) [180][550/586] lr: 5.000000e-05 eta: 2:10:24 time: 0.470216 data_time: 0.025386 memory: 15239 loss_kpt: 0.000471 acc_pose: 0.862680 loss: 0.000471 2022/09/15 06:15:06 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 06:15:06 - mmengine - INFO - Saving checkpoint at 180 epochs 2022/09/15 06:15:23 - mmengine - INFO - Epoch(val) [180][50/407] eta: 0:01:11 time: 0.201379 data_time: 0.013476 memory: 15239 2022/09/15 06:15:33 - mmengine - INFO - Epoch(val) [180][100/407] eta: 0:01:00 time: 0.197080 data_time: 0.008960 memory: 2064 2022/09/15 06:15:42 - mmengine - INFO - Epoch(val) [180][150/407] eta: 0:00:50 time: 0.196343 data_time: 0.009583 memory: 2064 2022/09/15 06:15:52 - mmengine - INFO - Epoch(val) [180][200/407] eta: 0:00:41 time: 0.199921 data_time: 0.011998 memory: 2064 2022/09/15 06:16:02 - mmengine - INFO - Epoch(val) [180][250/407] eta: 0:00:30 time: 0.195841 data_time: 0.008686 memory: 2064 2022/09/15 06:16:12 - mmengine - INFO - Epoch(val) [180][300/407] eta: 0:00:21 time: 0.196454 data_time: 0.008413 memory: 2064 2022/09/15 06:16:22 - mmengine - INFO - Epoch(val) [180][350/407] eta: 0:00:11 time: 0.196350 data_time: 0.009004 memory: 2064 2022/09/15 06:16:32 - mmengine - INFO - Epoch(val) [180][400/407] eta: 0:00:01 time: 0.194426 data_time: 0.008510 memory: 2064 2022/09/15 06:17:08 - mmengine - INFO - Evaluating CocoMetric... 2022/09/15 06:17:22 - mmengine - INFO - Epoch(val) [180][407/407] coco/AP: 0.765590 coco/AP .5: 0.909220 coco/AP .75: 0.829831 coco/AP (M): 0.727013 coco/AP (L): 0.835079 coco/AR: 0.815365 coco/AR .5: 0.944899 coco/AR .75: 0.871851 coco/AR (M): 0.771838 coco/AR (L): 0.877852 2022/09/15 06:17:22 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220914/hrnet_w48_384/best_coco/AP_epoch_160.pth is removed 2022/09/15 06:17:26 - mmengine - INFO - The best checkpoint with 0.7656 coco/AP at 180 epoch is saved to best_coco/AP_epoch_180.pth. 2022/09/15 06:17:50 - mmengine - INFO - Epoch(train) [181][50/586] lr: 5.000000e-05 eta: 2:09:44 time: 0.483908 data_time: 0.028558 memory: 15239 loss_kpt: 0.000461 acc_pose: 0.914881 loss: 0.000461 2022/09/15 06:18:14 - mmengine - INFO - Epoch(train) [181][100/586] lr: 5.000000e-05 eta: 2:09:22 time: 0.469406 data_time: 0.024704 memory: 15239 loss_kpt: 0.000486 acc_pose: 0.808208 loss: 0.000486 2022/09/15 06:18:38 - mmengine - INFO - Epoch(train) [181][150/586] lr: 5.000000e-05 eta: 2:09:00 time: 0.474709 data_time: 0.028710 memory: 15239 loss_kpt: 0.000483 acc_pose: 0.919922 loss: 0.000483 2022/09/15 06:19:02 - mmengine - INFO - Epoch(train) [181][200/586] lr: 5.000000e-05 eta: 2:08:38 time: 0.481265 data_time: 0.024436 memory: 15239 loss_kpt: 0.000468 acc_pose: 0.816404 loss: 0.000468 2022/09/15 06:19:25 - mmengine - INFO - Epoch(train) [181][250/586] lr: 5.000000e-05 eta: 2:08:16 time: 0.473326 data_time: 0.024558 memory: 15239 loss_kpt: 0.000480 acc_pose: 0.871543 loss: 0.000480 2022/09/15 06:19:49 - mmengine - INFO - Epoch(train) [181][300/586] lr: 5.000000e-05 eta: 2:07:54 time: 0.470742 data_time: 0.025456 memory: 15239 loss_kpt: 0.000481 acc_pose: 0.878032 loss: 0.000481 2022/09/15 06:20:13 - mmengine - INFO - Epoch(train) [181][350/586] lr: 5.000000e-05 eta: 2:07:32 time: 0.480320 data_time: 0.024715 memory: 15239 loss_kpt: 0.000478 acc_pose: 0.895346 loss: 0.000478 2022/09/15 06:20:37 - mmengine - INFO - Epoch(train) [181][400/586] lr: 5.000000e-05 eta: 2:07:10 time: 0.473728 data_time: 0.025142 memory: 15239 loss_kpt: 0.000467 acc_pose: 0.902605 loss: 0.000467 2022/09/15 06:21:00 - mmengine - INFO - Epoch(train) [181][450/586] lr: 5.000000e-05 eta: 2:06:48 time: 0.475137 data_time: 0.024696 memory: 15239 loss_kpt: 0.000460 acc_pose: 0.885854 loss: 0.000460 2022/09/15 06:21:25 - mmengine - INFO - Epoch(train) [181][500/586] lr: 5.000000e-05 eta: 2:06:26 time: 0.484103 data_time: 0.025264 memory: 15239 loss_kpt: 0.000477 acc_pose: 0.895329 loss: 0.000477 2022/09/15 06:21:34 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 06:21:48 - mmengine - INFO - Epoch(train) [181][550/586] lr: 5.000000e-05 eta: 2:06:04 time: 0.472176 data_time: 0.024989 memory: 15239 loss_kpt: 0.000480 acc_pose: 0.886152 loss: 0.000480 2022/09/15 06:22:05 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 06:22:05 - mmengine - INFO - Saving checkpoint at 181 epochs 2022/09/15 06:22:37 - mmengine - INFO - Epoch(train) [182][50/586] lr: 5.000000e-05 eta: 2:05:24 time: 0.490294 data_time: 0.033024 memory: 15239 loss_kpt: 0.000469 acc_pose: 0.892558 loss: 0.000469 2022/09/15 06:23:00 - mmengine - INFO - Epoch(train) [182][100/586] lr: 5.000000e-05 eta: 2:05:02 time: 0.472476 data_time: 0.031301 memory: 15239 loss_kpt: 0.000489 acc_pose: 0.915160 loss: 0.000489 2022/09/15 06:23:24 - mmengine - INFO - Epoch(train) [182][150/586] lr: 5.000000e-05 eta: 2:04:40 time: 0.477798 data_time: 0.027751 memory: 15239 loss_kpt: 0.000485 acc_pose: 0.890867 loss: 0.000485 2022/09/15 06:23:48 - mmengine - INFO - Epoch(train) [182][200/586] lr: 5.000000e-05 eta: 2:04:18 time: 0.473562 data_time: 0.028486 memory: 15239 loss_kpt: 0.000481 acc_pose: 0.876588 loss: 0.000481 2022/09/15 06:24:12 - mmengine - INFO - Epoch(train) [182][250/586] lr: 5.000000e-05 eta: 2:03:56 time: 0.486282 data_time: 0.029024 memory: 15239 loss_kpt: 0.000468 acc_pose: 0.865471 loss: 0.000468 2022/09/15 06:24:36 - mmengine - INFO - Epoch(train) [182][300/586] lr: 5.000000e-05 eta: 2:03:34 time: 0.479789 data_time: 0.032090 memory: 15239 loss_kpt: 0.000485 acc_pose: 0.883401 loss: 0.000485 2022/09/15 06:25:00 - mmengine - INFO - Epoch(train) [182][350/586] lr: 5.000000e-05 eta: 2:03:12 time: 0.476967 data_time: 0.028509 memory: 15239 loss_kpt: 0.000495 acc_pose: 0.904335 loss: 0.000495 2022/09/15 06:25:24 - mmengine - INFO - Epoch(train) [182][400/586] lr: 5.000000e-05 eta: 2:02:50 time: 0.471165 data_time: 0.027918 memory: 15239 loss_kpt: 0.000486 acc_pose: 0.838659 loss: 0.000486 2022/09/15 06:25:48 - mmengine - INFO - Epoch(train) [182][450/586] lr: 5.000000e-05 eta: 2:02:28 time: 0.476771 data_time: 0.030658 memory: 15239 loss_kpt: 0.000485 acc_pose: 0.910779 loss: 0.000485 2022/09/15 06:26:12 - mmengine - INFO - Epoch(train) [182][500/586] lr: 5.000000e-05 eta: 2:02:06 time: 0.476046 data_time: 0.024907 memory: 15239 loss_kpt: 0.000466 acc_pose: 0.809357 loss: 0.000466 2022/09/15 06:26:35 - mmengine - INFO - Epoch(train) [182][550/586] lr: 5.000000e-05 eta: 2:01:44 time: 0.471487 data_time: 0.025072 memory: 15239 loss_kpt: 0.000483 acc_pose: 0.858624 loss: 0.000483 2022/09/15 06:26:52 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 06:26:52 - mmengine - INFO - Saving checkpoint at 182 epochs 2022/09/15 06:27:23 - mmengine - INFO - Epoch(train) [183][50/586] lr: 5.000000e-05 eta: 2:01:04 time: 0.478356 data_time: 0.036690 memory: 15239 loss_kpt: 0.000469 acc_pose: 0.900761 loss: 0.000469 2022/09/15 06:27:47 - mmengine - INFO - Epoch(train) [183][100/586] lr: 5.000000e-05 eta: 2:00:42 time: 0.475334 data_time: 0.024614 memory: 15239 loss_kpt: 0.000458 acc_pose: 0.860035 loss: 0.000458 2022/09/15 06:28:10 - mmengine - INFO - Epoch(train) [183][150/586] lr: 5.000000e-05 eta: 2:00:20 time: 0.471027 data_time: 0.024894 memory: 15239 loss_kpt: 0.000475 acc_pose: 0.902247 loss: 0.000475 2022/09/15 06:28:34 - mmengine - INFO - Epoch(train) [183][200/586] lr: 5.000000e-05 eta: 1:59:58 time: 0.474541 data_time: 0.024600 memory: 15239 loss_kpt: 0.000476 acc_pose: 0.905421 loss: 0.000476 2022/09/15 06:28:58 - mmengine - INFO - Epoch(train) [183][250/586] lr: 5.000000e-05 eta: 1:59:36 time: 0.474088 data_time: 0.024187 memory: 15239 loss_kpt: 0.000482 acc_pose: 0.864644 loss: 0.000482 2022/09/15 06:29:21 - mmengine - INFO - Epoch(train) [183][300/586] lr: 5.000000e-05 eta: 1:59:14 time: 0.467310 data_time: 0.025732 memory: 15239 loss_kpt: 0.000475 acc_pose: 0.862094 loss: 0.000475 2022/09/15 06:29:44 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 06:29:45 - mmengine - INFO - Epoch(train) [183][350/586] lr: 5.000000e-05 eta: 1:58:52 time: 0.477783 data_time: 0.028207 memory: 15239 loss_kpt: 0.000470 acc_pose: 0.902198 loss: 0.000470 2022/09/15 06:30:09 - mmengine - INFO - Epoch(train) [183][400/586] lr: 5.000000e-05 eta: 1:58:30 time: 0.469931 data_time: 0.024271 memory: 15239 loss_kpt: 0.000472 acc_pose: 0.850039 loss: 0.000472 2022/09/15 06:30:32 - mmengine - INFO - Epoch(train) [183][450/586] lr: 5.000000e-05 eta: 1:58:08 time: 0.469070 data_time: 0.025201 memory: 15239 loss_kpt: 0.000479 acc_pose: 0.861656 loss: 0.000479 2022/09/15 06:30:56 - mmengine - INFO - Epoch(train) [183][500/586] lr: 5.000000e-05 eta: 1:57:46 time: 0.471352 data_time: 0.024330 memory: 15239 loss_kpt: 0.000465 acc_pose: 0.875172 loss: 0.000465 2022/09/15 06:31:20 - mmengine - INFO - Epoch(train) [183][550/586] lr: 5.000000e-05 eta: 1:57:24 time: 0.477064 data_time: 0.025144 memory: 15239 loss_kpt: 0.000466 acc_pose: 0.856761 loss: 0.000466 2022/09/15 06:31:36 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 06:31:36 - mmengine - INFO - Saving checkpoint at 183 epochs 2022/09/15 06:32:08 - mmengine - INFO - Epoch(train) [184][50/586] lr: 5.000000e-05 eta: 1:56:44 time: 0.488809 data_time: 0.032577 memory: 15239 loss_kpt: 0.000464 acc_pose: 0.866176 loss: 0.000464 2022/09/15 06:32:32 - mmengine - INFO - Epoch(train) [184][100/586] lr: 5.000000e-05 eta: 1:56:22 time: 0.480704 data_time: 0.025949 memory: 15239 loss_kpt: 0.000484 acc_pose: 0.888279 loss: 0.000484 2022/09/15 06:32:56 - mmengine - INFO - Epoch(train) [184][150/586] lr: 5.000000e-05 eta: 1:56:00 time: 0.486844 data_time: 0.024219 memory: 15239 loss_kpt: 0.000465 acc_pose: 0.856650 loss: 0.000465 2022/09/15 06:33:20 - mmengine - INFO - Epoch(train) [184][200/586] lr: 5.000000e-05 eta: 1:55:38 time: 0.482853 data_time: 0.024756 memory: 15239 loss_kpt: 0.000483 acc_pose: 0.900305 loss: 0.000483 2022/09/15 06:33:44 - mmengine - INFO - Epoch(train) [184][250/586] lr: 5.000000e-05 eta: 1:55:16 time: 0.478156 data_time: 0.024726 memory: 15239 loss_kpt: 0.000475 acc_pose: 0.840077 loss: 0.000475 2022/09/15 06:34:08 - mmengine - INFO - Epoch(train) [184][300/586] lr: 5.000000e-05 eta: 1:54:54 time: 0.479993 data_time: 0.027743 memory: 15239 loss_kpt: 0.000478 acc_pose: 0.892836 loss: 0.000478 2022/09/15 06:34:32 - mmengine - INFO - Epoch(train) [184][350/586] lr: 5.000000e-05 eta: 1:54:32 time: 0.477777 data_time: 0.024669 memory: 15239 loss_kpt: 0.000482 acc_pose: 0.877110 loss: 0.000482 2022/09/15 06:34:56 - mmengine - INFO - Epoch(train) [184][400/586] lr: 5.000000e-05 eta: 1:54:10 time: 0.474608 data_time: 0.025416 memory: 15239 loss_kpt: 0.000479 acc_pose: 0.853139 loss: 0.000479 2022/09/15 06:35:20 - mmengine - INFO - Epoch(train) [184][450/586] lr: 5.000000e-05 eta: 1:53:48 time: 0.483754 data_time: 0.024996 memory: 15239 loss_kpt: 0.000468 acc_pose: 0.887607 loss: 0.000468 2022/09/15 06:35:44 - mmengine - INFO - Epoch(train) [184][500/586] lr: 5.000000e-05 eta: 1:53:26 time: 0.472803 data_time: 0.024994 memory: 15239 loss_kpt: 0.000459 acc_pose: 0.882448 loss: 0.000459 2022/09/15 06:36:07 - mmengine - INFO - Epoch(train) [184][550/586] lr: 5.000000e-05 eta: 1:53:04 time: 0.471333 data_time: 0.024834 memory: 15239 loss_kpt: 0.000464 acc_pose: 0.894393 loss: 0.000464 2022/09/15 06:36:24 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 06:36:24 - mmengine - INFO - Saving checkpoint at 184 epochs 2022/09/15 06:36:55 - mmengine - INFO - Epoch(train) [185][50/586] lr: 5.000000e-05 eta: 1:52:24 time: 0.478257 data_time: 0.031623 memory: 15239 loss_kpt: 0.000488 acc_pose: 0.883214 loss: 0.000488 2022/09/15 06:37:19 - mmengine - INFO - Epoch(train) [185][100/586] lr: 5.000000e-05 eta: 1:52:02 time: 0.481295 data_time: 0.032924 memory: 15239 loss_kpt: 0.000472 acc_pose: 0.888495 loss: 0.000472 2022/09/15 06:37:43 - mmengine - INFO - Epoch(train) [185][150/586] lr: 5.000000e-05 eta: 1:51:40 time: 0.472721 data_time: 0.028813 memory: 15239 loss_kpt: 0.000474 acc_pose: 0.881715 loss: 0.000474 2022/09/15 06:37:55 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 06:38:07 - mmengine - INFO - Epoch(train) [185][200/586] lr: 5.000000e-05 eta: 1:51:18 time: 0.475395 data_time: 0.027151 memory: 15239 loss_kpt: 0.000474 acc_pose: 0.768253 loss: 0.000474 2022/09/15 06:38:30 - mmengine - INFO - Epoch(train) [185][250/586] lr: 5.000000e-05 eta: 1:50:56 time: 0.470218 data_time: 0.027914 memory: 15239 loss_kpt: 0.000464 acc_pose: 0.826920 loss: 0.000464 2022/09/15 06:38:54 - mmengine - INFO - Epoch(train) [185][300/586] lr: 5.000000e-05 eta: 1:50:34 time: 0.475905 data_time: 0.032464 memory: 15239 loss_kpt: 0.000462 acc_pose: 0.898088 loss: 0.000462 2022/09/15 06:39:18 - mmengine - INFO - Epoch(train) [185][350/586] lr: 5.000000e-05 eta: 1:50:12 time: 0.472074 data_time: 0.027785 memory: 15239 loss_kpt: 0.000469 acc_pose: 0.835751 loss: 0.000469 2022/09/15 06:39:41 - mmengine - INFO - Epoch(train) [185][400/586] lr: 5.000000e-05 eta: 1:49:50 time: 0.474601 data_time: 0.029188 memory: 15239 loss_kpt: 0.000476 acc_pose: 0.861870 loss: 0.000476 2022/09/15 06:40:05 - mmengine - INFO - Epoch(train) [185][450/586] lr: 5.000000e-05 eta: 1:49:28 time: 0.478179 data_time: 0.028952 memory: 15239 loss_kpt: 0.000467 acc_pose: 0.919012 loss: 0.000467 2022/09/15 06:40:29 - mmengine - INFO - Epoch(train) [185][500/586] lr: 5.000000e-05 eta: 1:49:06 time: 0.468504 data_time: 0.028186 memory: 15239 loss_kpt: 0.000474 acc_pose: 0.875501 loss: 0.000474 2022/09/15 06:40:53 - mmengine - INFO - Epoch(train) [185][550/586] lr: 5.000000e-05 eta: 1:48:44 time: 0.479708 data_time: 0.028404 memory: 15239 loss_kpt: 0.000468 acc_pose: 0.872475 loss: 0.000468 2022/09/15 06:41:10 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 06:41:10 - mmengine - INFO - Saving checkpoint at 185 epochs 2022/09/15 06:41:41 - mmengine - INFO - Epoch(train) [186][50/586] lr: 5.000000e-05 eta: 1:48:04 time: 0.475784 data_time: 0.033182 memory: 15239 loss_kpt: 0.000480 acc_pose: 0.850937 loss: 0.000480 2022/09/15 06:42:04 - mmengine - INFO - Epoch(train) [186][100/586] lr: 5.000000e-05 eta: 1:47:42 time: 0.475457 data_time: 0.029996 memory: 15239 loss_kpt: 0.000466 acc_pose: 0.888563 loss: 0.000466 2022/09/15 06:42:28 - mmengine - INFO - Epoch(train) [186][150/586] lr: 5.000000e-05 eta: 1:47:20 time: 0.472883 data_time: 0.025373 memory: 15239 loss_kpt: 0.000463 acc_pose: 0.872059 loss: 0.000463 2022/09/15 06:42:52 - mmengine - INFO - Epoch(train) [186][200/586] lr: 5.000000e-05 eta: 1:46:58 time: 0.473605 data_time: 0.025143 memory: 15239 loss_kpt: 0.000459 acc_pose: 0.849219 loss: 0.000459 2022/09/15 06:43:15 - mmengine - INFO - Epoch(train) [186][250/586] lr: 5.000000e-05 eta: 1:46:36 time: 0.470753 data_time: 0.024650 memory: 15239 loss_kpt: 0.000476 acc_pose: 0.898789 loss: 0.000476 2022/09/15 06:43:39 - mmengine - INFO - Epoch(train) [186][300/586] lr: 5.000000e-05 eta: 1:46:14 time: 0.475074 data_time: 0.028285 memory: 15239 loss_kpt: 0.000479 acc_pose: 0.889209 loss: 0.000479 2022/09/15 06:44:02 - mmengine - INFO - Epoch(train) [186][350/586] lr: 5.000000e-05 eta: 1:45:52 time: 0.469861 data_time: 0.024742 memory: 15239 loss_kpt: 0.000473 acc_pose: 0.855405 loss: 0.000473 2022/09/15 06:44:26 - mmengine - INFO - Epoch(train) [186][400/586] lr: 5.000000e-05 eta: 1:45:30 time: 0.474893 data_time: 0.024513 memory: 15239 loss_kpt: 0.000474 acc_pose: 0.864400 loss: 0.000474 2022/09/15 06:44:50 - mmengine - INFO - Epoch(train) [186][450/586] lr: 5.000000e-05 eta: 1:45:08 time: 0.472597 data_time: 0.024664 memory: 15239 loss_kpt: 0.000485 acc_pose: 0.892648 loss: 0.000485 2022/09/15 06:45:13 - mmengine - INFO - Epoch(train) [186][500/586] lr: 5.000000e-05 eta: 1:44:46 time: 0.468954 data_time: 0.024702 memory: 15239 loss_kpt: 0.000476 acc_pose: 0.928341 loss: 0.000476 2022/09/15 06:45:37 - mmengine - INFO - Epoch(train) [186][550/586] lr: 5.000000e-05 eta: 1:44:24 time: 0.476667 data_time: 0.025457 memory: 15239 loss_kpt: 0.000472 acc_pose: 0.871018 loss: 0.000472 2022/09/15 06:45:54 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 06:45:54 - mmengine - INFO - Saving checkpoint at 186 epochs 2022/09/15 06:46:04 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 06:46:25 - mmengine - INFO - Epoch(train) [187][50/586] lr: 5.000000e-05 eta: 1:43:44 time: 0.479880 data_time: 0.030615 memory: 15239 loss_kpt: 0.000458 acc_pose: 0.901350 loss: 0.000458 2022/09/15 06:46:49 - mmengine - INFO - Epoch(train) [187][100/586] lr: 5.000000e-05 eta: 1:43:22 time: 0.474423 data_time: 0.024672 memory: 15239 loss_kpt: 0.000479 acc_pose: 0.909271 loss: 0.000479 2022/09/15 06:47:13 - mmengine - INFO - Epoch(train) [187][150/586] lr: 5.000000e-05 eta: 1:43:00 time: 0.476196 data_time: 0.024173 memory: 15239 loss_kpt: 0.000467 acc_pose: 0.908205 loss: 0.000467 2022/09/15 06:47:37 - mmengine - INFO - Epoch(train) [187][200/586] lr: 5.000000e-05 eta: 1:42:38 time: 0.478244 data_time: 0.024345 memory: 15239 loss_kpt: 0.000469 acc_pose: 0.832725 loss: 0.000469 2022/09/15 06:48:01 - mmengine - INFO - Epoch(train) [187][250/586] lr: 5.000000e-05 eta: 1:42:16 time: 0.480519 data_time: 0.025600 memory: 15239 loss_kpt: 0.000473 acc_pose: 0.868600 loss: 0.000473 2022/09/15 06:48:25 - mmengine - INFO - Epoch(train) [187][300/586] lr: 5.000000e-05 eta: 1:41:54 time: 0.474513 data_time: 0.025266 memory: 15239 loss_kpt: 0.000465 acc_pose: 0.886717 loss: 0.000465 2022/09/15 06:48:48 - mmengine - INFO - Epoch(train) [187][350/586] lr: 5.000000e-05 eta: 1:41:32 time: 0.476754 data_time: 0.024944 memory: 15239 loss_kpt: 0.000467 acc_pose: 0.898267 loss: 0.000467 2022/09/15 06:49:13 - mmengine - INFO - Epoch(train) [187][400/586] lr: 5.000000e-05 eta: 1:41:10 time: 0.482170 data_time: 0.030151 memory: 15239 loss_kpt: 0.000469 acc_pose: 0.869270 loss: 0.000469 2022/09/15 06:49:36 - mmengine - INFO - Epoch(train) [187][450/586] lr: 5.000000e-05 eta: 1:40:48 time: 0.473683 data_time: 0.025308 memory: 15239 loss_kpt: 0.000449 acc_pose: 0.888098 loss: 0.000449 2022/09/15 06:50:00 - mmengine - INFO - Epoch(train) [187][500/586] lr: 5.000000e-05 eta: 1:40:26 time: 0.471411 data_time: 0.025087 memory: 15239 loss_kpt: 0.000471 acc_pose: 0.870589 loss: 0.000471 2022/09/15 06:50:23 - mmengine - INFO - Epoch(train) [187][550/586] lr: 5.000000e-05 eta: 1:40:04 time: 0.471804 data_time: 0.025076 memory: 15239 loss_kpt: 0.000494 acc_pose: 0.839346 loss: 0.000494 2022/09/15 06:50:41 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 06:50:41 - mmengine - INFO - Saving checkpoint at 187 epochs 2022/09/15 06:51:12 - mmengine - INFO - Epoch(train) [188][50/586] lr: 5.000000e-05 eta: 1:39:24 time: 0.488061 data_time: 0.032685 memory: 15239 loss_kpt: 0.000459 acc_pose: 0.883752 loss: 0.000459 2022/09/15 06:51:36 - mmengine - INFO - Epoch(train) [188][100/586] lr: 5.000000e-05 eta: 1:39:02 time: 0.475595 data_time: 0.027707 memory: 15239 loss_kpt: 0.000470 acc_pose: 0.901397 loss: 0.000470 2022/09/15 06:51:59 - mmengine - INFO - Epoch(train) [188][150/586] lr: 5.000000e-05 eta: 1:38:40 time: 0.466640 data_time: 0.025246 memory: 15239 loss_kpt: 0.000479 acc_pose: 0.884645 loss: 0.000479 2022/09/15 06:52:23 - mmengine - INFO - Epoch(train) [188][200/586] lr: 5.000000e-05 eta: 1:38:18 time: 0.481868 data_time: 0.025279 memory: 15239 loss_kpt: 0.000468 acc_pose: 0.903188 loss: 0.000468 2022/09/15 06:52:47 - mmengine - INFO - Epoch(train) [188][250/586] lr: 5.000000e-05 eta: 1:37:56 time: 0.468385 data_time: 0.025814 memory: 15239 loss_kpt: 0.000462 acc_pose: 0.906584 loss: 0.000462 2022/09/15 06:53:10 - mmengine - INFO - Epoch(train) [188][300/586] lr: 5.000000e-05 eta: 1:37:34 time: 0.473178 data_time: 0.024716 memory: 15239 loss_kpt: 0.000472 acc_pose: 0.853177 loss: 0.000472 2022/09/15 06:53:34 - mmengine - INFO - Epoch(train) [188][350/586] lr: 5.000000e-05 eta: 1:37:12 time: 0.480332 data_time: 0.024353 memory: 15239 loss_kpt: 0.000461 acc_pose: 0.901181 loss: 0.000461 2022/09/15 06:53:58 - mmengine - INFO - Epoch(train) [188][400/586] lr: 5.000000e-05 eta: 1:36:50 time: 0.479208 data_time: 0.026203 memory: 15239 loss_kpt: 0.000475 acc_pose: 0.860008 loss: 0.000475 2022/09/15 06:54:07 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 06:54:22 - mmengine - INFO - Epoch(train) [188][450/586] lr: 5.000000e-05 eta: 1:36:27 time: 0.465935 data_time: 0.024693 memory: 15239 loss_kpt: 0.000469 acc_pose: 0.927968 loss: 0.000469 2022/09/15 06:54:45 - mmengine - INFO - Epoch(train) [188][500/586] lr: 5.000000e-05 eta: 1:36:05 time: 0.470804 data_time: 0.027672 memory: 15239 loss_kpt: 0.000470 acc_pose: 0.875315 loss: 0.000470 2022/09/15 06:55:09 - mmengine - INFO - Epoch(train) [188][550/586] lr: 5.000000e-05 eta: 1:35:43 time: 0.476126 data_time: 0.024548 memory: 15239 loss_kpt: 0.000466 acc_pose: 0.887129 loss: 0.000466 2022/09/15 06:55:26 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 06:55:26 - mmengine - INFO - Saving checkpoint at 188 epochs 2022/09/15 06:55:57 - mmengine - INFO - Epoch(train) [189][50/586] lr: 5.000000e-05 eta: 1:35:04 time: 0.483281 data_time: 0.036868 memory: 15239 loss_kpt: 0.000455 acc_pose: 0.922034 loss: 0.000455 2022/09/15 06:56:21 - mmengine - INFO - Epoch(train) [189][100/586] lr: 5.000000e-05 eta: 1:34:42 time: 0.477472 data_time: 0.033944 memory: 15239 loss_kpt: 0.000468 acc_pose: 0.938447 loss: 0.000468 2022/09/15 06:56:45 - mmengine - INFO - Epoch(train) [189][150/586] lr: 5.000000e-05 eta: 1:34:20 time: 0.473717 data_time: 0.028431 memory: 15239 loss_kpt: 0.000479 acc_pose: 0.862609 loss: 0.000479 2022/09/15 06:57:08 - mmengine - INFO - Epoch(train) [189][200/586] lr: 5.000000e-05 eta: 1:33:57 time: 0.472686 data_time: 0.024624 memory: 15239 loss_kpt: 0.000468 acc_pose: 0.849487 loss: 0.000468 2022/09/15 06:57:32 - mmengine - INFO - Epoch(train) [189][250/586] lr: 5.000000e-05 eta: 1:33:35 time: 0.478623 data_time: 0.027953 memory: 15239 loss_kpt: 0.000486 acc_pose: 0.933620 loss: 0.000486 2022/09/15 06:57:56 - mmengine - INFO - Epoch(train) [189][300/586] lr: 5.000000e-05 eta: 1:33:13 time: 0.474446 data_time: 0.023851 memory: 15239 loss_kpt: 0.000464 acc_pose: 0.865912 loss: 0.000464 2022/09/15 06:58:20 - mmengine - INFO - Epoch(train) [189][350/586] lr: 5.000000e-05 eta: 1:32:51 time: 0.485108 data_time: 0.025299 memory: 15239 loss_kpt: 0.000471 acc_pose: 0.921401 loss: 0.000471 2022/09/15 06:58:44 - mmengine - INFO - Epoch(train) [189][400/586] lr: 5.000000e-05 eta: 1:32:29 time: 0.477139 data_time: 0.024939 memory: 15239 loss_kpt: 0.000467 acc_pose: 0.802028 loss: 0.000467 2022/09/15 06:59:08 - mmengine - INFO - Epoch(train) [189][450/586] lr: 5.000000e-05 eta: 1:32:07 time: 0.472534 data_time: 0.025224 memory: 15239 loss_kpt: 0.000479 acc_pose: 0.880788 loss: 0.000479 2022/09/15 06:59:32 - mmengine - INFO - Epoch(train) [189][500/586] lr: 5.000000e-05 eta: 1:31:45 time: 0.471710 data_time: 0.024934 memory: 15239 loss_kpt: 0.000452 acc_pose: 0.895027 loss: 0.000452 2022/09/15 06:59:55 - mmengine - INFO - Epoch(train) [189][550/586] lr: 5.000000e-05 eta: 1:31:23 time: 0.474197 data_time: 0.028282 memory: 15239 loss_kpt: 0.000469 acc_pose: 0.877149 loss: 0.000469 2022/09/15 07:00:12 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 07:00:12 - mmengine - INFO - Saving checkpoint at 189 epochs 2022/09/15 07:00:43 - mmengine - INFO - Epoch(train) [190][50/586] lr: 5.000000e-05 eta: 1:30:43 time: 0.476630 data_time: 0.034956 memory: 15239 loss_kpt: 0.000467 acc_pose: 0.902718 loss: 0.000467 2022/09/15 07:01:07 - mmengine - INFO - Epoch(train) [190][100/586] lr: 5.000000e-05 eta: 1:30:21 time: 0.473213 data_time: 0.024626 memory: 15239 loss_kpt: 0.000479 acc_pose: 0.869498 loss: 0.000479 2022/09/15 07:01:31 - mmengine - INFO - Epoch(train) [190][150/586] lr: 5.000000e-05 eta: 1:29:59 time: 0.476679 data_time: 0.024573 memory: 15239 loss_kpt: 0.000466 acc_pose: 0.920542 loss: 0.000466 2022/09/15 07:01:54 - mmengine - INFO - Epoch(train) [190][200/586] lr: 5.000000e-05 eta: 1:29:37 time: 0.474187 data_time: 0.024554 memory: 15239 loss_kpt: 0.000476 acc_pose: 0.858878 loss: 0.000476 2022/09/15 07:02:16 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 07:02:18 - mmengine - INFO - Epoch(train) [190][250/586] lr: 5.000000e-05 eta: 1:29:15 time: 0.476808 data_time: 0.024785 memory: 15239 loss_kpt: 0.000474 acc_pose: 0.871755 loss: 0.000474 2022/09/15 07:02:42 - mmengine - INFO - Epoch(train) [190][300/586] lr: 5.000000e-05 eta: 1:28:53 time: 0.473331 data_time: 0.024304 memory: 15239 loss_kpt: 0.000478 acc_pose: 0.846414 loss: 0.000478 2022/09/15 07:03:05 - mmengine - INFO - Epoch(train) [190][350/586] lr: 5.000000e-05 eta: 1:28:31 time: 0.469747 data_time: 0.029174 memory: 15239 loss_kpt: 0.000469 acc_pose: 0.908648 loss: 0.000469 2022/09/15 07:03:29 - mmengine - INFO - Epoch(train) [190][400/586] lr: 5.000000e-05 eta: 1:28:09 time: 0.476293 data_time: 0.024308 memory: 15239 loss_kpt: 0.000461 acc_pose: 0.916418 loss: 0.000461 2022/09/15 07:03:53 - mmengine - INFO - Epoch(train) [190][450/586] lr: 5.000000e-05 eta: 1:27:47 time: 0.475250 data_time: 0.025034 memory: 15239 loss_kpt: 0.000487 acc_pose: 0.873468 loss: 0.000487 2022/09/15 07:04:16 - mmengine - INFO - Epoch(train) [190][500/586] lr: 5.000000e-05 eta: 1:27:25 time: 0.471012 data_time: 0.024469 memory: 15239 loss_kpt: 0.000471 acc_pose: 0.890428 loss: 0.000471 2022/09/15 07:04:40 - mmengine - INFO - Epoch(train) [190][550/586] lr: 5.000000e-05 eta: 1:27:03 time: 0.469772 data_time: 0.024327 memory: 15239 loss_kpt: 0.000463 acc_pose: 0.899916 loss: 0.000463 2022/09/15 07:04:57 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 07:04:57 - mmengine - INFO - Saving checkpoint at 190 epochs 2022/09/15 07:05:14 - mmengine - INFO - Epoch(val) [190][50/407] eta: 0:01:12 time: 0.201920 data_time: 0.013893 memory: 15239 2022/09/15 07:05:24 - mmengine - INFO - Epoch(val) [190][100/407] eta: 0:01:00 time: 0.195518 data_time: 0.008269 memory: 2064 2022/09/15 07:05:34 - mmengine - INFO - Epoch(val) [190][150/407] eta: 0:00:50 time: 0.195951 data_time: 0.008495 memory: 2064 2022/09/15 07:05:44 - mmengine - INFO - Epoch(val) [190][200/407] eta: 0:00:40 time: 0.194909 data_time: 0.008372 memory: 2064 2022/09/15 07:05:54 - mmengine - INFO - Epoch(val) [190][250/407] eta: 0:00:30 time: 0.196790 data_time: 0.008821 memory: 2064 2022/09/15 07:06:03 - mmengine - INFO - Epoch(val) [190][300/407] eta: 0:00:20 time: 0.195421 data_time: 0.008487 memory: 2064 2022/09/15 07:06:13 - mmengine - INFO - Epoch(val) [190][350/407] eta: 0:00:11 time: 0.200044 data_time: 0.011765 memory: 2064 2022/09/15 07:06:23 - mmengine - INFO - Epoch(val) [190][400/407] eta: 0:00:01 time: 0.192714 data_time: 0.007806 memory: 2064 2022/09/15 07:07:00 - mmengine - INFO - Evaluating CocoMetric... 2022/09/15 07:07:14 - mmengine - INFO - Epoch(val) [190][407/407] coco/AP: 0.767326 coco/AP .5: 0.910916 coco/AP .75: 0.832367 coco/AP (M): 0.727675 coco/AP (L): 0.837540 coco/AR: 0.816735 coco/AR .5: 0.946631 coco/AR .75: 0.874370 coco/AR (M): 0.772548 coco/AR (L): 0.880416 2022/09/15 07:07:14 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220914/hrnet_w48_384/best_coco/AP_epoch_180.pth is removed 2022/09/15 07:07:18 - mmengine - INFO - The best checkpoint with 0.7673 coco/AP at 190 epoch is saved to best_coco/AP_epoch_190.pth. 2022/09/15 07:07:41 - mmengine - INFO - Epoch(train) [191][50/586] lr: 5.000000e-05 eta: 1:26:23 time: 0.472444 data_time: 0.029091 memory: 15239 loss_kpt: 0.000462 acc_pose: 0.880770 loss: 0.000462 2022/09/15 07:08:05 - mmengine - INFO - Epoch(train) [191][100/586] lr: 5.000000e-05 eta: 1:26:01 time: 0.475271 data_time: 0.024745 memory: 15239 loss_kpt: 0.000483 acc_pose: 0.838538 loss: 0.000483 2022/09/15 07:08:29 - mmengine - INFO - Epoch(train) [191][150/586] lr: 5.000000e-05 eta: 1:25:39 time: 0.473592 data_time: 0.024549 memory: 15239 loss_kpt: 0.000467 acc_pose: 0.886646 loss: 0.000467 2022/09/15 07:08:52 - mmengine - INFO - Epoch(train) [191][200/586] lr: 5.000000e-05 eta: 1:25:17 time: 0.473440 data_time: 0.024480 memory: 15239 loss_kpt: 0.000464 acc_pose: 0.843955 loss: 0.000464 2022/09/15 07:09:16 - mmengine - INFO - Epoch(train) [191][250/586] lr: 5.000000e-05 eta: 1:24:55 time: 0.472940 data_time: 0.024754 memory: 15239 loss_kpt: 0.000467 acc_pose: 0.873766 loss: 0.000467 2022/09/15 07:09:40 - mmengine - INFO - Epoch(train) [191][300/586] lr: 5.000000e-05 eta: 1:24:33 time: 0.471718 data_time: 0.025077 memory: 15239 loss_kpt: 0.000463 acc_pose: 0.943126 loss: 0.000463 2022/09/15 07:10:03 - mmengine - INFO - Epoch(train) [191][350/586] lr: 5.000000e-05 eta: 1:24:11 time: 0.474291 data_time: 0.024436 memory: 15239 loss_kpt: 0.000483 acc_pose: 0.820862 loss: 0.000483 2022/09/15 07:10:27 - mmengine - INFO - Epoch(train) [191][400/586] lr: 5.000000e-05 eta: 1:23:49 time: 0.474725 data_time: 0.024947 memory: 15239 loss_kpt: 0.000462 acc_pose: 0.904036 loss: 0.000462 2022/09/15 07:10:51 - mmengine - INFO - Epoch(train) [191][450/586] lr: 5.000000e-05 eta: 1:23:27 time: 0.477260 data_time: 0.027972 memory: 15239 loss_kpt: 0.000481 acc_pose: 0.861028 loss: 0.000481 2022/09/15 07:11:15 - mmengine - INFO - Epoch(train) [191][500/586] lr: 5.000000e-05 eta: 1:23:05 time: 0.469632 data_time: 0.024447 memory: 15239 loss_kpt: 0.000465 acc_pose: 0.774815 loss: 0.000465 2022/09/15 07:11:38 - mmengine - INFO - Epoch(train) [191][550/586] lr: 5.000000e-05 eta: 1:22:43 time: 0.474043 data_time: 0.024647 memory: 15239 loss_kpt: 0.000464 acc_pose: 0.851659 loss: 0.000464 2022/09/15 07:11:55 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 07:11:55 - mmengine - INFO - Saving checkpoint at 191 epochs 2022/09/15 07:12:26 - mmengine - INFO - Epoch(train) [192][50/586] lr: 5.000000e-05 eta: 1:22:03 time: 0.477819 data_time: 0.033333 memory: 15239 loss_kpt: 0.000449 acc_pose: 0.893880 loss: 0.000449 2022/09/15 07:12:38 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 07:12:50 - mmengine - INFO - Epoch(train) [192][100/586] lr: 5.000000e-05 eta: 1:21:41 time: 0.485351 data_time: 0.032099 memory: 15239 loss_kpt: 0.000465 acc_pose: 0.868343 loss: 0.000465 2022/09/15 07:13:14 - mmengine - INFO - Epoch(train) [192][150/586] lr: 5.000000e-05 eta: 1:21:19 time: 0.479094 data_time: 0.027966 memory: 15239 loss_kpt: 0.000481 acc_pose: 0.859639 loss: 0.000481 2022/09/15 07:13:38 - mmengine - INFO - Epoch(train) [192][200/586] lr: 5.000000e-05 eta: 1:20:57 time: 0.471589 data_time: 0.028148 memory: 15239 loss_kpt: 0.000461 acc_pose: 0.900398 loss: 0.000461 2022/09/15 07:14:02 - mmengine - INFO - Epoch(train) [192][250/586] lr: 5.000000e-05 eta: 1:20:35 time: 0.480230 data_time: 0.032540 memory: 15239 loss_kpt: 0.000479 acc_pose: 0.884897 loss: 0.000479 2022/09/15 07:14:26 - mmengine - INFO - Epoch(train) [192][300/586] lr: 5.000000e-05 eta: 1:20:13 time: 0.471657 data_time: 0.028389 memory: 15239 loss_kpt: 0.000471 acc_pose: 0.896128 loss: 0.000471 2022/09/15 07:14:49 - mmengine - INFO - Epoch(train) [192][350/586] lr: 5.000000e-05 eta: 1:19:51 time: 0.470867 data_time: 0.025783 memory: 15239 loss_kpt: 0.000460 acc_pose: 0.866464 loss: 0.000460 2022/09/15 07:15:13 - mmengine - INFO - Epoch(train) [192][400/586] lr: 5.000000e-05 eta: 1:19:29 time: 0.478238 data_time: 0.025313 memory: 15239 loss_kpt: 0.000462 acc_pose: 0.922839 loss: 0.000462 2022/09/15 07:15:37 - mmengine - INFO - Epoch(train) [192][450/586] lr: 5.000000e-05 eta: 1:19:06 time: 0.470518 data_time: 0.028699 memory: 15239 loss_kpt: 0.000472 acc_pose: 0.881564 loss: 0.000472 2022/09/15 07:16:00 - mmengine - INFO - Epoch(train) [192][500/586] lr: 5.000000e-05 eta: 1:18:44 time: 0.471497 data_time: 0.024854 memory: 15239 loss_kpt: 0.000456 acc_pose: 0.878214 loss: 0.000456 2022/09/15 07:16:24 - mmengine - INFO - Epoch(train) [192][550/586] lr: 5.000000e-05 eta: 1:18:22 time: 0.475686 data_time: 0.025220 memory: 15239 loss_kpt: 0.000477 acc_pose: 0.931204 loss: 0.000477 2022/09/15 07:16:41 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 07:16:41 - mmengine - INFO - Saving checkpoint at 192 epochs 2022/09/15 07:17:12 - mmengine - INFO - Epoch(train) [193][50/586] lr: 5.000000e-05 eta: 1:17:43 time: 0.485006 data_time: 0.039625 memory: 15239 loss_kpt: 0.000459 acc_pose: 0.867718 loss: 0.000459 2022/09/15 07:17:36 - mmengine - INFO - Epoch(train) [193][100/586] lr: 5.000000e-05 eta: 1:17:21 time: 0.481289 data_time: 0.028083 memory: 15239 loss_kpt: 0.000459 acc_pose: 0.892046 loss: 0.000459 2022/09/15 07:17:59 - mmengine - INFO - Epoch(train) [193][150/586] lr: 5.000000e-05 eta: 1:16:59 time: 0.470935 data_time: 0.027648 memory: 15239 loss_kpt: 0.000475 acc_pose: 0.899797 loss: 0.000475 2022/09/15 07:18:23 - mmengine - INFO - Epoch(train) [193][200/586] lr: 5.000000e-05 eta: 1:16:37 time: 0.479567 data_time: 0.031551 memory: 15239 loss_kpt: 0.000465 acc_pose: 0.942279 loss: 0.000465 2022/09/15 07:18:47 - mmengine - INFO - Epoch(train) [193][250/586] lr: 5.000000e-05 eta: 1:16:15 time: 0.470066 data_time: 0.028292 memory: 15239 loss_kpt: 0.000476 acc_pose: 0.910183 loss: 0.000476 2022/09/15 07:19:10 - mmengine - INFO - Epoch(train) [193][300/586] lr: 5.000000e-05 eta: 1:15:52 time: 0.470777 data_time: 0.025036 memory: 15239 loss_kpt: 0.000485 acc_pose: 0.864429 loss: 0.000485 2022/09/15 07:19:34 - mmengine - INFO - Epoch(train) [193][350/586] lr: 5.000000e-05 eta: 1:15:30 time: 0.473909 data_time: 0.024426 memory: 15239 loss_kpt: 0.000471 acc_pose: 0.899320 loss: 0.000471 2022/09/15 07:19:58 - mmengine - INFO - Epoch(train) [193][400/586] lr: 5.000000e-05 eta: 1:15:08 time: 0.472414 data_time: 0.024824 memory: 15239 loss_kpt: 0.000463 acc_pose: 0.859231 loss: 0.000463 2022/09/15 07:20:21 - mmengine - INFO - Epoch(train) [193][450/586] lr: 5.000000e-05 eta: 1:14:46 time: 0.473669 data_time: 0.028275 memory: 15239 loss_kpt: 0.000472 acc_pose: 0.888026 loss: 0.000472 2022/09/15 07:20:39 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 07:20:45 - mmengine - INFO - Epoch(train) [193][500/586] lr: 5.000000e-05 eta: 1:14:24 time: 0.471094 data_time: 0.024412 memory: 15239 loss_kpt: 0.000464 acc_pose: 0.898508 loss: 0.000464 2022/09/15 07:21:09 - mmengine - INFO - Epoch(train) [193][550/586] lr: 5.000000e-05 eta: 1:14:02 time: 0.478375 data_time: 0.024646 memory: 15239 loss_kpt: 0.000466 acc_pose: 0.893782 loss: 0.000466 2022/09/15 07:21:26 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 07:21:26 - mmengine - INFO - Saving checkpoint at 193 epochs 2022/09/15 07:21:57 - mmengine - INFO - Epoch(train) [194][50/586] lr: 5.000000e-05 eta: 1:13:23 time: 0.476112 data_time: 0.031412 memory: 15239 loss_kpt: 0.000464 acc_pose: 0.850597 loss: 0.000464 2022/09/15 07:22:21 - mmengine - INFO - Epoch(train) [194][100/586] lr: 5.000000e-05 eta: 1:13:00 time: 0.478570 data_time: 0.028099 memory: 15239 loss_kpt: 0.000471 acc_pose: 0.912644 loss: 0.000471 2022/09/15 07:22:44 - mmengine - INFO - Epoch(train) [194][150/586] lr: 5.000000e-05 eta: 1:12:38 time: 0.472208 data_time: 0.024480 memory: 15239 loss_kpt: 0.000473 acc_pose: 0.854064 loss: 0.000473 2022/09/15 07:23:08 - mmengine - INFO - Epoch(train) [194][200/586] lr: 5.000000e-05 eta: 1:12:16 time: 0.479335 data_time: 0.025179 memory: 15239 loss_kpt: 0.000479 acc_pose: 0.914087 loss: 0.000479 2022/09/15 07:23:32 - mmengine - INFO - Epoch(train) [194][250/586] lr: 5.000000e-05 eta: 1:11:54 time: 0.475644 data_time: 0.025538 memory: 15239 loss_kpt: 0.000477 acc_pose: 0.966452 loss: 0.000477 2022/09/15 07:23:55 - mmengine - INFO - Epoch(train) [194][300/586] lr: 5.000000e-05 eta: 1:11:32 time: 0.470062 data_time: 0.025725 memory: 15239 loss_kpt: 0.000476 acc_pose: 0.825169 loss: 0.000476 2022/09/15 07:24:19 - mmengine - INFO - Epoch(train) [194][350/586] lr: 5.000000e-05 eta: 1:11:10 time: 0.466053 data_time: 0.024685 memory: 15239 loss_kpt: 0.000453 acc_pose: 0.845378 loss: 0.000453 2022/09/15 07:24:43 - mmengine - INFO - Epoch(train) [194][400/586] lr: 5.000000e-05 eta: 1:10:48 time: 0.474146 data_time: 0.028669 memory: 15239 loss_kpt: 0.000461 acc_pose: 0.895920 loss: 0.000461 2022/09/15 07:25:06 - mmengine - INFO - Epoch(train) [194][450/586] lr: 5.000000e-05 eta: 1:10:26 time: 0.468319 data_time: 0.024435 memory: 15239 loss_kpt: 0.000464 acc_pose: 0.916119 loss: 0.000464 2022/09/15 07:25:29 - mmengine - INFO - Epoch(train) [194][500/586] lr: 5.000000e-05 eta: 1:10:04 time: 0.468168 data_time: 0.024664 memory: 15239 loss_kpt: 0.000468 acc_pose: 0.916331 loss: 0.000468 2022/09/15 07:25:53 - mmengine - INFO - Epoch(train) [194][550/586] lr: 5.000000e-05 eta: 1:09:42 time: 0.476754 data_time: 0.028236 memory: 15239 loss_kpt: 0.000469 acc_pose: 0.866772 loss: 0.000469 2022/09/15 07:26:10 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 07:26:10 - mmengine - INFO - Saving checkpoint at 194 epochs 2022/09/15 07:26:41 - mmengine - INFO - Epoch(train) [195][50/586] lr: 5.000000e-05 eta: 1:09:02 time: 0.479805 data_time: 0.031539 memory: 15239 loss_kpt: 0.000466 acc_pose: 0.865123 loss: 0.000466 2022/09/15 07:27:05 - mmengine - INFO - Epoch(train) [195][100/586] lr: 5.000000e-05 eta: 1:08:40 time: 0.482351 data_time: 0.025068 memory: 15239 loss_kpt: 0.000485 acc_pose: 0.846612 loss: 0.000485 2022/09/15 07:27:29 - mmengine - INFO - Epoch(train) [195][150/586] lr: 5.000000e-05 eta: 1:08:18 time: 0.471521 data_time: 0.023893 memory: 15239 loss_kpt: 0.000462 acc_pose: 0.859181 loss: 0.000462 2022/09/15 07:27:52 - mmengine - INFO - Epoch(train) [195][200/586] lr: 5.000000e-05 eta: 1:07:56 time: 0.472188 data_time: 0.028566 memory: 15239 loss_kpt: 0.000491 acc_pose: 0.899322 loss: 0.000491 2022/09/15 07:28:17 - mmengine - INFO - Epoch(train) [195][250/586] lr: 5.000000e-05 eta: 1:07:34 time: 0.483523 data_time: 0.025850 memory: 15239 loss_kpt: 0.000462 acc_pose: 0.906944 loss: 0.000462 2022/09/15 07:28:40 - mmengine - INFO - Epoch(train) [195][300/586] lr: 5.000000e-05 eta: 1:07:12 time: 0.476461 data_time: 0.024141 memory: 15239 loss_kpt: 0.000475 acc_pose: 0.809907 loss: 0.000475 2022/09/15 07:28:48 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 07:29:04 - mmengine - INFO - Epoch(train) [195][350/586] lr: 5.000000e-05 eta: 1:06:50 time: 0.468370 data_time: 0.024984 memory: 15239 loss_kpt: 0.000475 acc_pose: 0.873597 loss: 0.000475 2022/09/15 07:29:28 - mmengine - INFO - Epoch(train) [195][400/586] lr: 5.000000e-05 eta: 1:06:28 time: 0.472481 data_time: 0.024713 memory: 15239 loss_kpt: 0.000485 acc_pose: 0.772967 loss: 0.000485 2022/09/15 07:29:51 - mmengine - INFO - Epoch(train) [195][450/586] lr: 5.000000e-05 eta: 1:06:05 time: 0.469656 data_time: 0.025059 memory: 15239 loss_kpt: 0.000465 acc_pose: 0.919881 loss: 0.000465 2022/09/15 07:30:15 - mmengine - INFO - Epoch(train) [195][500/586] lr: 5.000000e-05 eta: 1:05:43 time: 0.472613 data_time: 0.028101 memory: 15239 loss_kpt: 0.000483 acc_pose: 0.884483 loss: 0.000483 2022/09/15 07:30:39 - mmengine - INFO - Epoch(train) [195][550/586] lr: 5.000000e-05 eta: 1:05:21 time: 0.479304 data_time: 0.025667 memory: 15239 loss_kpt: 0.000484 acc_pose: 0.911762 loss: 0.000484 2022/09/15 07:30:56 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 07:30:56 - mmengine - INFO - Saving checkpoint at 195 epochs 2022/09/15 07:31:27 - mmengine - INFO - Epoch(train) [196][50/586] lr: 5.000000e-05 eta: 1:04:42 time: 0.474787 data_time: 0.028369 memory: 15239 loss_kpt: 0.000456 acc_pose: 0.931589 loss: 0.000456 2022/09/15 07:31:50 - mmengine - INFO - Epoch(train) [196][100/586] lr: 5.000000e-05 eta: 1:04:20 time: 0.474607 data_time: 0.025003 memory: 15239 loss_kpt: 0.000478 acc_pose: 0.897639 loss: 0.000478 2022/09/15 07:32:14 - mmengine - INFO - Epoch(train) [196][150/586] lr: 5.000000e-05 eta: 1:03:58 time: 0.474056 data_time: 0.024990 memory: 15239 loss_kpt: 0.000473 acc_pose: 0.865765 loss: 0.000473 2022/09/15 07:32:37 - mmengine - INFO - Epoch(train) [196][200/586] lr: 5.000000e-05 eta: 1:03:36 time: 0.462285 data_time: 0.024558 memory: 15239 loss_kpt: 0.000471 acc_pose: 0.809428 loss: 0.000471 2022/09/15 07:33:01 - mmengine - INFO - Epoch(train) [196][250/586] lr: 5.000000e-05 eta: 1:03:14 time: 0.479032 data_time: 0.025162 memory: 15239 loss_kpt: 0.000468 acc_pose: 0.886559 loss: 0.000468 2022/09/15 07:33:25 - mmengine - INFO - Epoch(train) [196][300/586] lr: 5.000000e-05 eta: 1:02:51 time: 0.470283 data_time: 0.024271 memory: 15239 loss_kpt: 0.000455 acc_pose: 0.813891 loss: 0.000455 2022/09/15 07:33:48 - mmengine - INFO - Epoch(train) [196][350/586] lr: 5.000000e-05 eta: 1:02:29 time: 0.469888 data_time: 0.024493 memory: 15239 loss_kpt: 0.000473 acc_pose: 0.877056 loss: 0.000473 2022/09/15 07:34:12 - mmengine - INFO - Epoch(train) [196][400/586] lr: 5.000000e-05 eta: 1:02:07 time: 0.477335 data_time: 0.025162 memory: 15239 loss_kpt: 0.000482 acc_pose: 0.864754 loss: 0.000482 2022/09/15 07:34:36 - mmengine - INFO - Epoch(train) [196][450/586] lr: 5.000000e-05 eta: 1:01:45 time: 0.477575 data_time: 0.029558 memory: 15239 loss_kpt: 0.000472 acc_pose: 0.883604 loss: 0.000472 2022/09/15 07:35:00 - mmengine - INFO - Epoch(train) [196][500/586] lr: 5.000000e-05 eta: 1:01:23 time: 0.479134 data_time: 0.024629 memory: 15239 loss_kpt: 0.000470 acc_pose: 0.879795 loss: 0.000470 2022/09/15 07:35:24 - mmengine - INFO - Epoch(train) [196][550/586] lr: 5.000000e-05 eta: 1:01:01 time: 0.475667 data_time: 0.025134 memory: 15239 loss_kpt: 0.000472 acc_pose: 0.869012 loss: 0.000472 2022/09/15 07:35:41 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 07:35:41 - mmengine - INFO - Saving checkpoint at 196 epochs 2022/09/15 07:36:12 - mmengine - INFO - Epoch(train) [197][50/586] lr: 5.000000e-05 eta: 1:00:22 time: 0.476066 data_time: 0.028243 memory: 15239 loss_kpt: 0.000459 acc_pose: 0.889873 loss: 0.000459 2022/09/15 07:36:35 - mmengine - INFO - Epoch(train) [197][100/586] lr: 5.000000e-05 eta: 1:00:00 time: 0.474261 data_time: 0.024366 memory: 15239 loss_kpt: 0.000472 acc_pose: 0.850698 loss: 0.000472 2022/09/15 07:36:56 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 07:36:59 - mmengine - INFO - Epoch(train) [197][150/586] lr: 5.000000e-05 eta: 0:59:37 time: 0.466325 data_time: 0.024928 memory: 15239 loss_kpt: 0.000464 acc_pose: 0.911206 loss: 0.000464 2022/09/15 07:37:22 - mmengine - INFO - Epoch(train) [197][200/586] lr: 5.000000e-05 eta: 0:59:15 time: 0.474906 data_time: 0.024369 memory: 15239 loss_kpt: 0.000478 acc_pose: 0.899743 loss: 0.000478 2022/09/15 07:37:46 - mmengine - INFO - Epoch(train) [197][250/586] lr: 5.000000e-05 eta: 0:58:53 time: 0.474699 data_time: 0.027560 memory: 15239 loss_kpt: 0.000480 acc_pose: 0.833061 loss: 0.000480 2022/09/15 07:38:10 - mmengine - INFO - Epoch(train) [197][300/586] lr: 5.000000e-05 eta: 0:58:31 time: 0.473319 data_time: 0.024264 memory: 15239 loss_kpt: 0.000483 acc_pose: 0.855420 loss: 0.000483 2022/09/15 07:38:33 - mmengine - INFO - Epoch(train) [197][350/586] lr: 5.000000e-05 eta: 0:58:09 time: 0.469683 data_time: 0.024860 memory: 15239 loss_kpt: 0.000473 acc_pose: 0.884035 loss: 0.000473 2022/09/15 07:38:57 - mmengine - INFO - Epoch(train) [197][400/586] lr: 5.000000e-05 eta: 0:57:47 time: 0.472040 data_time: 0.024267 memory: 15239 loss_kpt: 0.000469 acc_pose: 0.896622 loss: 0.000469 2022/09/15 07:39:21 - mmengine - INFO - Epoch(train) [197][450/586] lr: 5.000000e-05 eta: 0:57:25 time: 0.473689 data_time: 0.024610 memory: 15239 loss_kpt: 0.000459 acc_pose: 0.845889 loss: 0.000459 2022/09/15 07:39:44 - mmengine - INFO - Epoch(train) [197][500/586] lr: 5.000000e-05 eta: 0:57:03 time: 0.468027 data_time: 0.024873 memory: 15239 loss_kpt: 0.000455 acc_pose: 0.918817 loss: 0.000455 2022/09/15 07:40:08 - mmengine - INFO - Epoch(train) [197][550/586] lr: 5.000000e-05 eta: 0:56:41 time: 0.478025 data_time: 0.028355 memory: 15239 loss_kpt: 0.000469 acc_pose: 0.903134 loss: 0.000469 2022/09/15 07:40:25 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 07:40:25 - mmengine - INFO - Saving checkpoint at 197 epochs 2022/09/15 07:40:56 - mmengine - INFO - Epoch(train) [198][50/586] lr: 5.000000e-05 eta: 0:56:01 time: 0.479467 data_time: 0.033423 memory: 15239 loss_kpt: 0.000443 acc_pose: 0.903105 loss: 0.000443 2022/09/15 07:41:20 - mmengine - INFO - Epoch(train) [198][100/586] lr: 5.000000e-05 eta: 0:55:39 time: 0.475882 data_time: 0.032679 memory: 15239 loss_kpt: 0.000465 acc_pose: 0.911283 loss: 0.000465 2022/09/15 07:41:44 - mmengine - INFO - Epoch(train) [198][150/586] lr: 5.000000e-05 eta: 0:55:17 time: 0.483988 data_time: 0.029939 memory: 15239 loss_kpt: 0.000472 acc_pose: 0.843418 loss: 0.000472 2022/09/15 07:42:07 - mmengine - INFO - Epoch(train) [198][200/586] lr: 5.000000e-05 eta: 0:54:55 time: 0.470874 data_time: 0.024981 memory: 15239 loss_kpt: 0.000464 acc_pose: 0.842742 loss: 0.000464 2022/09/15 07:42:31 - mmengine - INFO - Epoch(train) [198][250/586] lr: 5.000000e-05 eta: 0:54:33 time: 0.470153 data_time: 0.025275 memory: 15239 loss_kpt: 0.000462 acc_pose: 0.915407 loss: 0.000462 2022/09/15 07:42:55 - mmengine - INFO - Epoch(train) [198][300/586] lr: 5.000000e-05 eta: 0:54:11 time: 0.479054 data_time: 0.025165 memory: 15239 loss_kpt: 0.000466 acc_pose: 0.908832 loss: 0.000466 2022/09/15 07:43:19 - mmengine - INFO - Epoch(train) [198][350/586] lr: 5.000000e-05 eta: 0:53:49 time: 0.474221 data_time: 0.025536 memory: 15239 loss_kpt: 0.000467 acc_pose: 0.887001 loss: 0.000467 2022/09/15 07:43:42 - mmengine - INFO - Epoch(train) [198][400/586] lr: 5.000000e-05 eta: 0:53:27 time: 0.475566 data_time: 0.027401 memory: 15239 loss_kpt: 0.000471 acc_pose: 0.892550 loss: 0.000471 2022/09/15 07:44:06 - mmengine - INFO - Epoch(train) [198][450/586] lr: 5.000000e-05 eta: 0:53:04 time: 0.474954 data_time: 0.029565 memory: 15239 loss_kpt: 0.000493 acc_pose: 0.899167 loss: 0.000493 2022/09/15 07:44:29 - mmengine - INFO - Epoch(train) [198][500/586] lr: 5.000000e-05 eta: 0:52:42 time: 0.465107 data_time: 0.025534 memory: 15239 loss_kpt: 0.000468 acc_pose: 0.874412 loss: 0.000468 2022/09/15 07:44:53 - mmengine - INFO - Epoch(train) [198][550/586] lr: 5.000000e-05 eta: 0:52:20 time: 0.465744 data_time: 0.024727 memory: 15239 loss_kpt: 0.000466 acc_pose: 0.898342 loss: 0.000466 2022/09/15 07:44:57 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 07:45:10 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 07:45:10 - mmengine - INFO - Saving checkpoint at 198 epochs 2022/09/15 07:45:41 - mmengine - INFO - Epoch(train) [199][50/586] lr: 5.000000e-05 eta: 0:51:41 time: 0.484490 data_time: 0.036290 memory: 15239 loss_kpt: 0.000472 acc_pose: 0.902623 loss: 0.000472 2022/09/15 07:46:05 - mmengine - INFO - Epoch(train) [199][100/586] lr: 5.000000e-05 eta: 0:51:19 time: 0.480823 data_time: 0.031073 memory: 15239 loss_kpt: 0.000467 acc_pose: 0.873108 loss: 0.000467 2022/09/15 07:46:29 - mmengine - INFO - Epoch(train) [199][150/586] lr: 5.000000e-05 eta: 0:50:57 time: 0.473407 data_time: 0.029223 memory: 15239 loss_kpt: 0.000476 acc_pose: 0.882722 loss: 0.000476 2022/09/15 07:46:53 - mmengine - INFO - Epoch(train) [199][200/586] lr: 5.000000e-05 eta: 0:50:35 time: 0.478383 data_time: 0.031868 memory: 15239 loss_kpt: 0.000467 acc_pose: 0.950844 loss: 0.000467 2022/09/15 07:47:17 - mmengine - INFO - Epoch(train) [199][250/586] lr: 5.000000e-05 eta: 0:50:13 time: 0.476142 data_time: 0.025267 memory: 15239 loss_kpt: 0.000460 acc_pose: 0.897407 loss: 0.000460 2022/09/15 07:47:40 - mmengine - INFO - Epoch(train) [199][300/586] lr: 5.000000e-05 eta: 0:49:51 time: 0.470493 data_time: 0.024908 memory: 15239 loss_kpt: 0.000472 acc_pose: 0.873307 loss: 0.000472 2022/09/15 07:48:04 - mmengine - INFO - Epoch(train) [199][350/586] lr: 5.000000e-05 eta: 0:49:28 time: 0.471092 data_time: 0.024491 memory: 15239 loss_kpt: 0.000459 acc_pose: 0.851133 loss: 0.000459 2022/09/15 07:48:28 - mmengine - INFO - Epoch(train) [199][400/586] lr: 5.000000e-05 eta: 0:49:06 time: 0.474948 data_time: 0.024280 memory: 15239 loss_kpt: 0.000464 acc_pose: 0.853485 loss: 0.000464 2022/09/15 07:48:51 - mmengine - INFO - Epoch(train) [199][450/586] lr: 5.000000e-05 eta: 0:48:44 time: 0.473304 data_time: 0.025165 memory: 15239 loss_kpt: 0.000457 acc_pose: 0.901369 loss: 0.000457 2022/09/15 07:49:15 - mmengine - INFO - Epoch(train) [199][500/586] lr: 5.000000e-05 eta: 0:48:22 time: 0.470069 data_time: 0.025232 memory: 15239 loss_kpt: 0.000473 acc_pose: 0.849657 loss: 0.000473 2022/09/15 07:49:39 - mmengine - INFO - Epoch(train) [199][550/586] lr: 5.000000e-05 eta: 0:48:00 time: 0.479617 data_time: 0.024294 memory: 15239 loss_kpt: 0.000476 acc_pose: 0.868294 loss: 0.000476 2022/09/15 07:49:56 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 07:49:56 - mmengine - INFO - Saving checkpoint at 199 epochs 2022/09/15 07:50:27 - mmengine - INFO - Epoch(train) [200][50/586] lr: 5.000000e-05 eta: 0:47:21 time: 0.475366 data_time: 0.029345 memory: 15239 loss_kpt: 0.000478 acc_pose: 0.902211 loss: 0.000478 2022/09/15 07:50:51 - mmengine - INFO - Epoch(train) [200][100/586] lr: 5.000000e-05 eta: 0:46:59 time: 0.478920 data_time: 0.025055 memory: 15239 loss_kpt: 0.000466 acc_pose: 0.798055 loss: 0.000466 2022/09/15 07:51:14 - mmengine - INFO - Epoch(train) [200][150/586] lr: 5.000000e-05 eta: 0:46:37 time: 0.471780 data_time: 0.025237 memory: 15239 loss_kpt: 0.000461 acc_pose: 0.877107 loss: 0.000461 2022/09/15 07:51:38 - mmengine - INFO - Epoch(train) [200][200/586] lr: 5.000000e-05 eta: 0:46:14 time: 0.472407 data_time: 0.024811 memory: 15239 loss_kpt: 0.000449 acc_pose: 0.874594 loss: 0.000449 2022/09/15 07:52:02 - mmengine - INFO - Epoch(train) [200][250/586] lr: 5.000000e-05 eta: 0:45:52 time: 0.481633 data_time: 0.025598 memory: 15239 loss_kpt: 0.000463 acc_pose: 0.904874 loss: 0.000463 2022/09/15 07:52:26 - mmengine - INFO - Epoch(train) [200][300/586] lr: 5.000000e-05 eta: 0:45:30 time: 0.476692 data_time: 0.025659 memory: 15239 loss_kpt: 0.000457 acc_pose: 0.880738 loss: 0.000457 2022/09/15 07:52:49 - mmengine - INFO - Epoch(train) [200][350/586] lr: 5.000000e-05 eta: 0:45:08 time: 0.470145 data_time: 0.025338 memory: 15239 loss_kpt: 0.000466 acc_pose: 0.884635 loss: 0.000466 2022/09/15 07:53:07 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 07:53:13 - mmengine - INFO - Epoch(train) [200][400/586] lr: 5.000000e-05 eta: 0:44:46 time: 0.474786 data_time: 0.025007 memory: 15239 loss_kpt: 0.000465 acc_pose: 0.882848 loss: 0.000465 2022/09/15 07:53:37 - mmengine - INFO - Epoch(train) [200][450/586] lr: 5.000000e-05 eta: 0:44:24 time: 0.475745 data_time: 0.024117 memory: 15239 loss_kpt: 0.000474 acc_pose: 0.921234 loss: 0.000474 2022/09/15 07:54:01 - mmengine - INFO - Epoch(train) [200][500/586] lr: 5.000000e-05 eta: 0:44:02 time: 0.480694 data_time: 0.025946 memory: 15239 loss_kpt: 0.000470 acc_pose: 0.906994 loss: 0.000470 2022/09/15 07:54:25 - mmengine - INFO - Epoch(train) [200][550/586] lr: 5.000000e-05 eta: 0:43:40 time: 0.480439 data_time: 0.028277 memory: 15239 loss_kpt: 0.000469 acc_pose: 0.901097 loss: 0.000469 2022/09/15 07:54:42 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 07:54:42 - mmengine - INFO - Saving checkpoint at 200 epochs 2022/09/15 07:55:00 - mmengine - INFO - Epoch(val) [200][50/407] eta: 0:01:13 time: 0.207253 data_time: 0.014036 memory: 15239 2022/09/15 07:55:10 - mmengine - INFO - Epoch(val) [200][100/407] eta: 0:01:00 time: 0.196004 data_time: 0.008510 memory: 2064 2022/09/15 07:55:19 - mmengine - INFO - Epoch(val) [200][150/407] eta: 0:00:50 time: 0.196154 data_time: 0.008535 memory: 2064 2022/09/15 07:55:29 - mmengine - INFO - Epoch(val) [200][200/407] eta: 0:00:40 time: 0.194641 data_time: 0.008142 memory: 2064 2022/09/15 07:55:39 - mmengine - INFO - Epoch(val) [200][250/407] eta: 0:00:30 time: 0.196231 data_time: 0.008901 memory: 2064 2022/09/15 07:55:49 - mmengine - INFO - Epoch(val) [200][300/407] eta: 0:00:21 time: 0.196608 data_time: 0.008679 memory: 2064 2022/09/15 07:55:59 - mmengine - INFO - Epoch(val) [200][350/407] eta: 0:00:11 time: 0.195780 data_time: 0.008543 memory: 2064 2022/09/15 07:56:08 - mmengine - INFO - Epoch(val) [200][400/407] eta: 0:00:01 time: 0.193104 data_time: 0.007983 memory: 2064 2022/09/15 07:56:46 - mmengine - INFO - Evaluating CocoMetric... 2022/09/15 07:56:59 - mmengine - INFO - Epoch(val) [200][407/407] coco/AP: 0.766461 coco/AP .5: 0.909616 coco/AP .75: 0.832045 coco/AP (M): 0.726807 coco/AP (L): 0.837102 coco/AR: 0.815932 coco/AR .5: 0.945372 coco/AR .75: 0.874685 coco/AR (M): 0.771811 coco/AR (L): 0.879710 2022/09/15 07:57:24 - mmengine - INFO - Epoch(train) [201][50/586] lr: 5.000000e-06 eta: 0:43:01 time: 0.491003 data_time: 0.032810 memory: 15239 loss_kpt: 0.000449 acc_pose: 0.898562 loss: 0.000449 2022/09/15 07:57:48 - mmengine - INFO - Epoch(train) [201][100/586] lr: 5.000000e-06 eta: 0:42:39 time: 0.481648 data_time: 0.025158 memory: 15239 loss_kpt: 0.000457 acc_pose: 0.866932 loss: 0.000457 2022/09/15 07:58:11 - mmengine - INFO - Epoch(train) [201][150/586] lr: 5.000000e-06 eta: 0:42:16 time: 0.467892 data_time: 0.024420 memory: 15239 loss_kpt: 0.000474 acc_pose: 0.844370 loss: 0.000474 2022/09/15 07:58:35 - mmengine - INFO - Epoch(train) [201][200/586] lr: 5.000000e-06 eta: 0:41:54 time: 0.473683 data_time: 0.030456 memory: 15239 loss_kpt: 0.000454 acc_pose: 0.931187 loss: 0.000454 2022/09/15 07:58:59 - mmengine - INFO - Epoch(train) [201][250/586] lr: 5.000000e-06 eta: 0:41:32 time: 0.479483 data_time: 0.026111 memory: 15239 loss_kpt: 0.000471 acc_pose: 0.883243 loss: 0.000471 2022/09/15 07:59:23 - mmengine - INFO - Epoch(train) [201][300/586] lr: 5.000000e-06 eta: 0:41:10 time: 0.471929 data_time: 0.027930 memory: 15239 loss_kpt: 0.000488 acc_pose: 0.891608 loss: 0.000488 2022/09/15 07:59:46 - mmengine - INFO - Epoch(train) [201][350/586] lr: 5.000000e-06 eta: 0:40:48 time: 0.473375 data_time: 0.026072 memory: 15239 loss_kpt: 0.000469 acc_pose: 0.854899 loss: 0.000469 2022/09/15 08:00:10 - mmengine - INFO - Epoch(train) [201][400/586] lr: 5.000000e-06 eta: 0:40:26 time: 0.480124 data_time: 0.025667 memory: 15239 loss_kpt: 0.000459 acc_pose: 0.885166 loss: 0.000459 2022/09/15 08:00:34 - mmengine - INFO - Epoch(train) [201][450/586] lr: 5.000000e-06 eta: 0:40:04 time: 0.479524 data_time: 0.025024 memory: 15239 loss_kpt: 0.000476 acc_pose: 0.936249 loss: 0.000476 2022/09/15 08:00:58 - mmengine - INFO - Epoch(train) [201][500/586] lr: 5.000000e-06 eta: 0:39:41 time: 0.471107 data_time: 0.029411 memory: 15239 loss_kpt: 0.000455 acc_pose: 0.900750 loss: 0.000455 2022/09/15 08:01:22 - mmengine - INFO - Epoch(train) [201][550/586] lr: 5.000000e-06 eta: 0:39:19 time: 0.477919 data_time: 0.025065 memory: 15239 loss_kpt: 0.000476 acc_pose: 0.915487 loss: 0.000476 2022/09/15 08:01:39 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 08:01:39 - mmengine - INFO - Saving checkpoint at 201 epochs 2022/09/15 08:02:10 - mmengine - INFO - Epoch(train) [202][50/586] lr: 5.000000e-06 eta: 0:38:40 time: 0.479679 data_time: 0.032862 memory: 15239 loss_kpt: 0.000467 acc_pose: 0.829818 loss: 0.000467 2022/09/15 08:02:34 - mmengine - INFO - Epoch(train) [202][100/586] lr: 5.000000e-06 eta: 0:38:18 time: 0.480480 data_time: 0.027953 memory: 15239 loss_kpt: 0.000470 acc_pose: 0.922755 loss: 0.000470 2022/09/15 08:02:57 - mmengine - INFO - Epoch(train) [202][150/586] lr: 5.000000e-06 eta: 0:37:56 time: 0.471096 data_time: 0.032403 memory: 15239 loss_kpt: 0.000479 acc_pose: 0.846907 loss: 0.000479 2022/09/15 08:03:21 - mmengine - INFO - Epoch(train) [202][200/586] lr: 5.000000e-06 eta: 0:37:34 time: 0.478801 data_time: 0.032054 memory: 15239 loss_kpt: 0.000470 acc_pose: 0.895070 loss: 0.000470 2022/09/15 08:03:28 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 08:03:45 - mmengine - INFO - Epoch(train) [202][250/586] lr: 5.000000e-06 eta: 0:37:12 time: 0.480416 data_time: 0.032125 memory: 15239 loss_kpt: 0.000457 acc_pose: 0.923568 loss: 0.000457 2022/09/15 08:04:09 - mmengine - INFO - Epoch(train) [202][300/586] lr: 5.000000e-06 eta: 0:36:50 time: 0.471584 data_time: 0.027589 memory: 15239 loss_kpt: 0.000469 acc_pose: 0.946705 loss: 0.000469 2022/09/15 08:04:33 - mmengine - INFO - Epoch(train) [202][350/586] lr: 5.000000e-06 eta: 0:36:27 time: 0.473918 data_time: 0.032363 memory: 15239 loss_kpt: 0.000476 acc_pose: 0.874398 loss: 0.000476 2022/09/15 08:04:56 - mmengine - INFO - Epoch(train) [202][400/586] lr: 5.000000e-06 eta: 0:36:05 time: 0.475261 data_time: 0.029881 memory: 15239 loss_kpt: 0.000448 acc_pose: 0.905387 loss: 0.000448 2022/09/15 08:05:20 - mmengine - INFO - Epoch(train) [202][450/586] lr: 5.000000e-06 eta: 0:35:43 time: 0.477590 data_time: 0.032924 memory: 15239 loss_kpt: 0.000447 acc_pose: 0.848563 loss: 0.000447 2022/09/15 08:05:44 - mmengine - INFO - Epoch(train) [202][500/586] lr: 5.000000e-06 eta: 0:35:21 time: 0.469607 data_time: 0.029097 memory: 15239 loss_kpt: 0.000458 acc_pose: 0.921504 loss: 0.000458 2022/09/15 08:06:08 - mmengine - INFO - Epoch(train) [202][550/586] lr: 5.000000e-06 eta: 0:34:59 time: 0.478006 data_time: 0.029675 memory: 15239 loss_kpt: 0.000460 acc_pose: 0.914242 loss: 0.000460 2022/09/15 08:06:25 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 08:06:25 - mmengine - INFO - Saving checkpoint at 202 epochs 2022/09/15 08:06:56 - mmengine - INFO - Epoch(train) [203][50/586] lr: 5.000000e-06 eta: 0:34:20 time: 0.484538 data_time: 0.037849 memory: 15239 loss_kpt: 0.000450 acc_pose: 0.913625 loss: 0.000450 2022/09/15 08:07:19 - mmengine - INFO - Epoch(train) [203][100/586] lr: 5.000000e-06 eta: 0:33:58 time: 0.469437 data_time: 0.027677 memory: 15239 loss_kpt: 0.000453 acc_pose: 0.880461 loss: 0.000453 2022/09/15 08:07:43 - mmengine - INFO - Epoch(train) [203][150/586] lr: 5.000000e-06 eta: 0:33:36 time: 0.486548 data_time: 0.027980 memory: 15239 loss_kpt: 0.000462 acc_pose: 0.858644 loss: 0.000462 2022/09/15 08:08:07 - mmengine - INFO - Epoch(train) [203][200/586] lr: 5.000000e-06 eta: 0:33:14 time: 0.472015 data_time: 0.032033 memory: 15239 loss_kpt: 0.000476 acc_pose: 0.854067 loss: 0.000476 2022/09/15 08:08:31 - mmengine - INFO - Epoch(train) [203][250/586] lr: 5.000000e-06 eta: 0:32:51 time: 0.482151 data_time: 0.028774 memory: 15239 loss_kpt: 0.000464 acc_pose: 0.863108 loss: 0.000464 2022/09/15 08:08:55 - mmengine - INFO - Epoch(train) [203][300/586] lr: 5.000000e-06 eta: 0:32:29 time: 0.469559 data_time: 0.031869 memory: 15239 loss_kpt: 0.000468 acc_pose: 0.857549 loss: 0.000468 2022/09/15 08:09:18 - mmengine - INFO - Epoch(train) [203][350/586] lr: 5.000000e-06 eta: 0:32:07 time: 0.471258 data_time: 0.028592 memory: 15239 loss_kpt: 0.000464 acc_pose: 0.875696 loss: 0.000464 2022/09/15 08:09:42 - mmengine - INFO - Epoch(train) [203][400/586] lr: 5.000000e-06 eta: 0:31:45 time: 0.479067 data_time: 0.028755 memory: 15239 loss_kpt: 0.000454 acc_pose: 0.926800 loss: 0.000454 2022/09/15 08:10:05 - mmengine - INFO - Epoch(train) [203][450/586] lr: 5.000000e-06 eta: 0:31:23 time: 0.463558 data_time: 0.029920 memory: 15239 loss_kpt: 0.000467 acc_pose: 0.901587 loss: 0.000467 2022/09/15 08:10:29 - mmengine - INFO - Epoch(train) [203][500/586] lr: 5.000000e-06 eta: 0:31:01 time: 0.475622 data_time: 0.034005 memory: 15239 loss_kpt: 0.000474 acc_pose: 0.907496 loss: 0.000474 2022/09/15 08:10:53 - mmengine - INFO - Epoch(train) [203][550/586] lr: 5.000000e-06 eta: 0:30:38 time: 0.483187 data_time: 0.031632 memory: 15239 loss_kpt: 0.000472 acc_pose: 0.909813 loss: 0.000472 2022/09/15 08:11:10 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 08:11:10 - mmengine - INFO - Saving checkpoint at 203 epochs 2022/09/15 08:11:37 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 08:11:41 - mmengine - INFO - Epoch(train) [204][50/586] lr: 5.000000e-06 eta: 0:30:00 time: 0.472408 data_time: 0.034222 memory: 15239 loss_kpt: 0.000472 acc_pose: 0.870014 loss: 0.000472 2022/09/15 08:12:05 - mmengine - INFO - Epoch(train) [204][100/586] lr: 5.000000e-06 eta: 0:29:38 time: 0.477874 data_time: 0.028022 memory: 15239 loss_kpt: 0.000467 acc_pose: 0.869697 loss: 0.000467 2022/09/15 08:12:28 - mmengine - INFO - Epoch(train) [204][150/586] lr: 5.000000e-06 eta: 0:29:15 time: 0.466776 data_time: 0.028958 memory: 15239 loss_kpt: 0.000460 acc_pose: 0.876394 loss: 0.000460 2022/09/15 08:12:52 - mmengine - INFO - Epoch(train) [204][200/586] lr: 5.000000e-06 eta: 0:28:53 time: 0.479859 data_time: 0.032884 memory: 15239 loss_kpt: 0.000470 acc_pose: 0.874239 loss: 0.000470 2022/09/15 08:13:15 - mmengine - INFO - Epoch(train) [204][250/586] lr: 5.000000e-06 eta: 0:28:31 time: 0.469186 data_time: 0.028748 memory: 15239 loss_kpt: 0.000459 acc_pose: 0.875569 loss: 0.000459 2022/09/15 08:13:39 - mmengine - INFO - Epoch(train) [204][300/586] lr: 5.000000e-06 eta: 0:28:09 time: 0.479165 data_time: 0.025202 memory: 15239 loss_kpt: 0.000443 acc_pose: 0.881803 loss: 0.000443 2022/09/15 08:14:03 - mmengine - INFO - Epoch(train) [204][350/586] lr: 5.000000e-06 eta: 0:27:47 time: 0.471125 data_time: 0.028425 memory: 15239 loss_kpt: 0.000461 acc_pose: 0.908232 loss: 0.000461 2022/09/15 08:14:27 - mmengine - INFO - Epoch(train) [204][400/586] lr: 5.000000e-06 eta: 0:27:25 time: 0.479728 data_time: 0.024728 memory: 15239 loss_kpt: 0.000446 acc_pose: 0.907152 loss: 0.000446 2022/09/15 08:14:51 - mmengine - INFO - Epoch(train) [204][450/586] lr: 5.000000e-06 eta: 0:27:02 time: 0.472666 data_time: 0.025620 memory: 15239 loss_kpt: 0.000466 acc_pose: 0.897696 loss: 0.000466 2022/09/15 08:15:14 - mmengine - INFO - Epoch(train) [204][500/586] lr: 5.000000e-06 eta: 0:26:40 time: 0.470905 data_time: 0.025702 memory: 15239 loss_kpt: 0.000471 acc_pose: 0.867989 loss: 0.000471 2022/09/15 08:15:38 - mmengine - INFO - Epoch(train) [204][550/586] lr: 5.000000e-06 eta: 0:26:18 time: 0.473894 data_time: 0.024610 memory: 15239 loss_kpt: 0.000461 acc_pose: 0.888601 loss: 0.000461 2022/09/15 08:15:55 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 08:15:55 - mmengine - INFO - Saving checkpoint at 204 epochs 2022/09/15 08:16:26 - mmengine - INFO - Epoch(train) [205][50/586] lr: 5.000000e-06 eta: 0:25:39 time: 0.479483 data_time: 0.034502 memory: 15239 loss_kpt: 0.000460 acc_pose: 0.843527 loss: 0.000460 2022/09/15 08:16:50 - mmengine - INFO - Epoch(train) [205][100/586] lr: 5.000000e-06 eta: 0:25:17 time: 0.483088 data_time: 0.028527 memory: 15239 loss_kpt: 0.000453 acc_pose: 0.880033 loss: 0.000453 2022/09/15 08:17:14 - mmengine - INFO - Epoch(train) [205][150/586] lr: 5.000000e-06 eta: 0:24:55 time: 0.476555 data_time: 0.032940 memory: 15239 loss_kpt: 0.000459 acc_pose: 0.876337 loss: 0.000459 2022/09/15 08:17:37 - mmengine - INFO - Epoch(train) [205][200/586] lr: 5.000000e-06 eta: 0:24:33 time: 0.475207 data_time: 0.033351 memory: 15239 loss_kpt: 0.000464 acc_pose: 0.860988 loss: 0.000464 2022/09/15 08:18:01 - mmengine - INFO - Epoch(train) [205][250/586] lr: 5.000000e-06 eta: 0:24:11 time: 0.477152 data_time: 0.025507 memory: 15239 loss_kpt: 0.000466 acc_pose: 0.900664 loss: 0.000466 2022/09/15 08:18:25 - mmengine - INFO - Epoch(train) [205][300/586] lr: 5.000000e-06 eta: 0:23:49 time: 0.472667 data_time: 0.024975 memory: 15239 loss_kpt: 0.000466 acc_pose: 0.861912 loss: 0.000466 2022/09/15 08:18:48 - mmengine - INFO - Epoch(train) [205][350/586] lr: 5.000000e-06 eta: 0:23:26 time: 0.468901 data_time: 0.025181 memory: 15239 loss_kpt: 0.000456 acc_pose: 0.864772 loss: 0.000456 2022/09/15 08:19:12 - mmengine - INFO - Epoch(train) [205][400/586] lr: 5.000000e-06 eta: 0:23:04 time: 0.475809 data_time: 0.028279 memory: 15239 loss_kpt: 0.000465 acc_pose: 0.787489 loss: 0.000465 2022/09/15 08:19:36 - mmengine - INFO - Epoch(train) [205][450/586] lr: 5.000000e-06 eta: 0:22:42 time: 0.471897 data_time: 0.024467 memory: 15239 loss_kpt: 0.000458 acc_pose: 0.821003 loss: 0.000458 2022/09/15 08:19:39 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 08:20:00 - mmengine - INFO - Epoch(train) [205][500/586] lr: 5.000000e-06 eta: 0:22:20 time: 0.471431 data_time: 0.025009 memory: 15239 loss_kpt: 0.000459 acc_pose: 0.836908 loss: 0.000459 2022/09/15 08:20:23 - mmengine - INFO - Epoch(train) [205][550/586] lr: 5.000000e-06 eta: 0:21:58 time: 0.477466 data_time: 0.025554 memory: 15239 loss_kpt: 0.000456 acc_pose: 0.899625 loss: 0.000456 2022/09/15 08:20:40 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 08:20:40 - mmengine - INFO - Saving checkpoint at 205 epochs 2022/09/15 08:21:11 - mmengine - INFO - Epoch(train) [206][50/586] lr: 5.000000e-06 eta: 0:21:19 time: 0.476960 data_time: 0.032063 memory: 15239 loss_kpt: 0.000465 acc_pose: 0.845800 loss: 0.000465 2022/09/15 08:21:35 - mmengine - INFO - Epoch(train) [206][100/586] lr: 5.000000e-06 eta: 0:20:57 time: 0.475864 data_time: 0.028245 memory: 15239 loss_kpt: 0.000469 acc_pose: 0.902235 loss: 0.000469 2022/09/15 08:21:59 - mmengine - INFO - Epoch(train) [206][150/586] lr: 5.000000e-06 eta: 0:20:35 time: 0.475796 data_time: 0.031345 memory: 15239 loss_kpt: 0.000462 acc_pose: 0.822289 loss: 0.000462 2022/09/15 08:22:23 - mmengine - INFO - Epoch(train) [206][200/586] lr: 5.000000e-06 eta: 0:20:13 time: 0.473199 data_time: 0.028789 memory: 15239 loss_kpt: 0.000476 acc_pose: 0.901553 loss: 0.000476 2022/09/15 08:22:46 - mmengine - INFO - Epoch(train) [206][250/586] lr: 5.000000e-06 eta: 0:19:50 time: 0.476356 data_time: 0.032855 memory: 15239 loss_kpt: 0.000465 acc_pose: 0.901363 loss: 0.000465 2022/09/15 08:23:10 - mmengine - INFO - Epoch(train) [206][300/586] lr: 5.000000e-06 eta: 0:19:28 time: 0.468524 data_time: 0.028797 memory: 15239 loss_kpt: 0.000481 acc_pose: 0.884151 loss: 0.000481 2022/09/15 08:23:33 - mmengine - INFO - Epoch(train) [206][350/586] lr: 5.000000e-06 eta: 0:19:06 time: 0.470717 data_time: 0.028096 memory: 15239 loss_kpt: 0.000457 acc_pose: 0.919326 loss: 0.000457 2022/09/15 08:23:57 - mmengine - INFO - Epoch(train) [206][400/586] lr: 5.000000e-06 eta: 0:18:44 time: 0.472790 data_time: 0.031781 memory: 15239 loss_kpt: 0.000456 acc_pose: 0.918450 loss: 0.000456 2022/09/15 08:24:21 - mmengine - INFO - Epoch(train) [206][450/586] lr: 5.000000e-06 eta: 0:18:22 time: 0.475480 data_time: 0.028599 memory: 15239 loss_kpt: 0.000472 acc_pose: 0.892374 loss: 0.000472 2022/09/15 08:24:44 - mmengine - INFO - Epoch(train) [206][500/586] lr: 5.000000e-06 eta: 0:17:59 time: 0.473467 data_time: 0.033243 memory: 15239 loss_kpt: 0.000453 acc_pose: 0.932692 loss: 0.000453 2022/09/15 08:25:08 - mmengine - INFO - Epoch(train) [206][550/586] lr: 5.000000e-06 eta: 0:17:37 time: 0.472521 data_time: 0.026221 memory: 15239 loss_kpt: 0.000458 acc_pose: 0.849154 loss: 0.000458 2022/09/15 08:25:25 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 08:25:25 - mmengine - INFO - Saving checkpoint at 206 epochs 2022/09/15 08:25:56 - mmengine - INFO - Epoch(train) [207][50/586] lr: 5.000000e-06 eta: 0:16:59 time: 0.488724 data_time: 0.033459 memory: 15239 loss_kpt: 0.000467 acc_pose: 0.893869 loss: 0.000467 2022/09/15 08:26:20 - mmengine - INFO - Epoch(train) [207][100/586] lr: 5.000000e-06 eta: 0:16:37 time: 0.479641 data_time: 0.030207 memory: 15239 loss_kpt: 0.000463 acc_pose: 0.884855 loss: 0.000463 2022/09/15 08:26:44 - mmengine - INFO - Epoch(train) [207][150/586] lr: 5.000000e-06 eta: 0:16:14 time: 0.469869 data_time: 0.028038 memory: 15239 loss_kpt: 0.000478 acc_pose: 0.917564 loss: 0.000478 2022/09/15 08:27:08 - mmengine - INFO - Epoch(train) [207][200/586] lr: 5.000000e-06 eta: 0:15:52 time: 0.478855 data_time: 0.027576 memory: 15239 loss_kpt: 0.000456 acc_pose: 0.872320 loss: 0.000456 2022/09/15 08:27:32 - mmengine - INFO - Epoch(train) [207][250/586] lr: 5.000000e-06 eta: 0:15:30 time: 0.479359 data_time: 0.027601 memory: 15239 loss_kpt: 0.000474 acc_pose: 0.891911 loss: 0.000474 2022/09/15 08:27:48 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 08:27:55 - mmengine - INFO - Epoch(train) [207][300/586] lr: 5.000000e-06 eta: 0:15:08 time: 0.468861 data_time: 0.032146 memory: 15239 loss_kpt: 0.000483 acc_pose: 0.851276 loss: 0.000483 2022/09/15 08:28:19 - mmengine - INFO - Epoch(train) [207][350/586] lr: 5.000000e-06 eta: 0:14:46 time: 0.474257 data_time: 0.028363 memory: 15239 loss_kpt: 0.000463 acc_pose: 0.871390 loss: 0.000463 2022/09/15 08:28:43 - mmengine - INFO - Epoch(train) [207][400/586] lr: 5.000000e-06 eta: 0:14:23 time: 0.472896 data_time: 0.029499 memory: 15239 loss_kpt: 0.000467 acc_pose: 0.897506 loss: 0.000467 2022/09/15 08:29:06 - mmengine - INFO - Epoch(train) [207][450/586] lr: 5.000000e-06 eta: 0:14:01 time: 0.475723 data_time: 0.030557 memory: 15239 loss_kpt: 0.000474 acc_pose: 0.897715 loss: 0.000474 2022/09/15 08:29:30 - mmengine - INFO - Epoch(train) [207][500/586] lr: 5.000000e-06 eta: 0:13:39 time: 0.467986 data_time: 0.027491 memory: 15239 loss_kpt: 0.000466 acc_pose: 0.831865 loss: 0.000466 2022/09/15 08:29:54 - mmengine - INFO - Epoch(train) [207][550/586] lr: 5.000000e-06 eta: 0:13:17 time: 0.491596 data_time: 0.024533 memory: 15239 loss_kpt: 0.000478 acc_pose: 0.928084 loss: 0.000478 2022/09/15 08:30:11 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 08:30:11 - mmengine - INFO - Saving checkpoint at 207 epochs 2022/09/15 08:30:43 - mmengine - INFO - Epoch(train) [208][50/586] lr: 5.000000e-06 eta: 0:12:38 time: 0.477305 data_time: 0.029183 memory: 15239 loss_kpt: 0.000473 acc_pose: 0.878535 loss: 0.000473 2022/09/15 08:31:06 - mmengine - INFO - Epoch(train) [208][100/586] lr: 5.000000e-06 eta: 0:12:16 time: 0.473362 data_time: 0.025031 memory: 15239 loss_kpt: 0.000447 acc_pose: 0.823496 loss: 0.000447 2022/09/15 08:31:30 - mmengine - INFO - Epoch(train) [208][150/586] lr: 5.000000e-06 eta: 0:11:54 time: 0.471775 data_time: 0.024427 memory: 15239 loss_kpt: 0.000470 acc_pose: 0.933068 loss: 0.000470 2022/09/15 08:31:54 - mmengine - INFO - Epoch(train) [208][200/586] lr: 5.000000e-06 eta: 0:11:32 time: 0.475725 data_time: 0.024553 memory: 15239 loss_kpt: 0.000457 acc_pose: 0.858887 loss: 0.000457 2022/09/15 08:32:17 - mmengine - INFO - Epoch(train) [208][250/586] lr: 5.000000e-06 eta: 0:11:10 time: 0.474712 data_time: 0.024948 memory: 15239 loss_kpt: 0.000451 acc_pose: 0.905065 loss: 0.000451 2022/09/15 08:32:41 - mmengine - INFO - Epoch(train) [208][300/586] lr: 5.000000e-06 eta: 0:10:47 time: 0.471785 data_time: 0.026406 memory: 15239 loss_kpt: 0.000471 acc_pose: 0.930271 loss: 0.000471 2022/09/15 08:33:05 - mmengine - INFO - Epoch(train) [208][350/586] lr: 5.000000e-06 eta: 0:10:25 time: 0.476868 data_time: 0.024738 memory: 15239 loss_kpt: 0.000460 acc_pose: 0.923628 loss: 0.000460 2022/09/15 08:33:29 - mmengine - INFO - Epoch(train) [208][400/586] lr: 5.000000e-06 eta: 0:10:03 time: 0.482787 data_time: 0.025155 memory: 15239 loss_kpt: 0.000457 acc_pose: 0.888859 loss: 0.000457 2022/09/15 08:33:53 - mmengine - INFO - Epoch(train) [208][450/586] lr: 5.000000e-06 eta: 0:09:41 time: 0.477184 data_time: 0.025498 memory: 15239 loss_kpt: 0.000463 acc_pose: 0.934054 loss: 0.000463 2022/09/15 08:34:17 - mmengine - INFO - Epoch(train) [208][500/586] lr: 5.000000e-06 eta: 0:09:19 time: 0.481448 data_time: 0.028396 memory: 15239 loss_kpt: 0.000477 acc_pose: 0.868991 loss: 0.000477 2022/09/15 08:34:41 - mmengine - INFO - Epoch(train) [208][550/586] lr: 5.000000e-06 eta: 0:08:56 time: 0.477402 data_time: 0.024619 memory: 15239 loss_kpt: 0.000484 acc_pose: 0.841510 loss: 0.000484 2022/09/15 08:34:58 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 08:34:58 - mmengine - INFO - Saving checkpoint at 208 epochs 2022/09/15 08:35:29 - mmengine - INFO - Epoch(train) [209][50/586] lr: 5.000000e-06 eta: 0:08:18 time: 0.480181 data_time: 0.029009 memory: 15239 loss_kpt: 0.000455 acc_pose: 0.811782 loss: 0.000455 2022/09/15 08:35:53 - mmengine - INFO - Epoch(train) [209][100/586] lr: 5.000000e-06 eta: 0:07:56 time: 0.484144 data_time: 0.026009 memory: 15239 loss_kpt: 0.000467 acc_pose: 0.879998 loss: 0.000467 2022/09/15 08:35:59 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 08:36:17 - mmengine - INFO - Epoch(train) [209][150/586] lr: 5.000000e-06 eta: 0:07:34 time: 0.468226 data_time: 0.023825 memory: 15239 loss_kpt: 0.000468 acc_pose: 0.856205 loss: 0.000468 2022/09/15 08:36:40 - mmengine - INFO - Epoch(train) [209][200/586] lr: 5.000000e-06 eta: 0:07:11 time: 0.467622 data_time: 0.024803 memory: 15239 loss_kpt: 0.000491 acc_pose: 0.853907 loss: 0.000491 2022/09/15 08:37:04 - mmengine - INFO - Epoch(train) [209][250/586] lr: 5.000000e-06 eta: 0:06:49 time: 0.476782 data_time: 0.024550 memory: 15239 loss_kpt: 0.000473 acc_pose: 0.830699 loss: 0.000473 2022/09/15 08:37:27 - mmengine - INFO - Epoch(train) [209][300/586] lr: 5.000000e-06 eta: 0:06:27 time: 0.467022 data_time: 0.024998 memory: 15239 loss_kpt: 0.000457 acc_pose: 0.902760 loss: 0.000457 2022/09/15 08:37:52 - mmengine - INFO - Epoch(train) [209][350/586] lr: 5.000000e-06 eta: 0:06:05 time: 0.483338 data_time: 0.025351 memory: 15239 loss_kpt: 0.000465 acc_pose: 0.914082 loss: 0.000465 2022/09/15 08:38:16 - mmengine - INFO - Epoch(train) [209][400/586] lr: 5.000000e-06 eta: 0:05:43 time: 0.479559 data_time: 0.028358 memory: 15239 loss_kpt: 0.000454 acc_pose: 0.889579 loss: 0.000454 2022/09/15 08:38:40 - mmengine - INFO - Epoch(train) [209][450/586] lr: 5.000000e-06 eta: 0:05:20 time: 0.488148 data_time: 0.024583 memory: 15239 loss_kpt: 0.000443 acc_pose: 0.886244 loss: 0.000443 2022/09/15 08:39:03 - mmengine - INFO - Epoch(train) [209][500/586] lr: 5.000000e-06 eta: 0:04:58 time: 0.466588 data_time: 0.024674 memory: 15239 loss_kpt: 0.000476 acc_pose: 0.865748 loss: 0.000476 2022/09/15 08:39:27 - mmengine - INFO - Epoch(train) [209][550/586] lr: 5.000000e-06 eta: 0:04:36 time: 0.471604 data_time: 0.030243 memory: 15239 loss_kpt: 0.000469 acc_pose: 0.853630 loss: 0.000469 2022/09/15 08:39:44 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 08:39:44 - mmengine - INFO - Saving checkpoint at 209 epochs 2022/09/15 08:40:15 - mmengine - INFO - Epoch(train) [210][50/586] lr: 5.000000e-06 eta: 0:03:58 time: 0.477076 data_time: 0.031904 memory: 15239 loss_kpt: 0.000461 acc_pose: 0.885925 loss: 0.000461 2022/09/15 08:40:38 - mmengine - INFO - Epoch(train) [210][100/586] lr: 5.000000e-06 eta: 0:03:35 time: 0.465104 data_time: 0.028328 memory: 15239 loss_kpt: 0.000449 acc_pose: 0.854518 loss: 0.000449 2022/09/15 08:41:02 - mmengine - INFO - Epoch(train) [210][150/586] lr: 5.000000e-06 eta: 0:03:13 time: 0.479627 data_time: 0.027895 memory: 15239 loss_kpt: 0.000453 acc_pose: 0.876536 loss: 0.000453 2022/09/15 08:41:26 - mmengine - INFO - Epoch(train) [210][200/586] lr: 5.000000e-06 eta: 0:02:51 time: 0.469367 data_time: 0.028978 memory: 15239 loss_kpt: 0.000464 acc_pose: 0.933344 loss: 0.000464 2022/09/15 08:41:49 - mmengine - INFO - Epoch(train) [210][250/586] lr: 5.000000e-06 eta: 0:02:29 time: 0.476600 data_time: 0.029296 memory: 15239 loss_kpt: 0.000473 acc_pose: 0.951297 loss: 0.000473 2022/09/15 08:42:13 - mmengine - INFO - Epoch(train) [210][300/586] lr: 5.000000e-06 eta: 0:02:07 time: 0.475011 data_time: 0.024915 memory: 15239 loss_kpt: 0.000452 acc_pose: 0.904408 loss: 0.000452 2022/09/15 08:42:37 - mmengine - INFO - Epoch(train) [210][350/586] lr: 5.000000e-06 eta: 0:01:44 time: 0.471301 data_time: 0.026020 memory: 15239 loss_kpt: 0.000461 acc_pose: 0.908417 loss: 0.000461 2022/09/15 08:43:01 - mmengine - INFO - Epoch(train) [210][400/586] lr: 5.000000e-06 eta: 0:01:22 time: 0.476882 data_time: 0.025102 memory: 15239 loss_kpt: 0.000476 acc_pose: 0.859266 loss: 0.000476 2022/09/15 08:43:24 - mmengine - INFO - Epoch(train) [210][450/586] lr: 5.000000e-06 eta: 0:01:00 time: 0.473268 data_time: 0.026059 memory: 15239 loss_kpt: 0.000454 acc_pose: 0.930910 loss: 0.000454 2022/09/15 08:43:48 - mmengine - INFO - Epoch(train) [210][500/586] lr: 5.000000e-06 eta: 0:00:38 time: 0.469206 data_time: 0.025990 memory: 15239 loss_kpt: 0.000459 acc_pose: 0.869650 loss: 0.000459 2022/09/15 08:44:00 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 08:44:11 - mmengine - INFO - Epoch(train) [210][550/586] lr: 5.000000e-06 eta: 0:00:16 time: 0.471266 data_time: 0.025929 memory: 15239 loss_kpt: 0.000473 acc_pose: 0.880453 loss: 0.000473 2022/09/15 08:44:28 - mmengine - INFO - Exp name: td-hm_hrnet-w48_8xb32-210e_coco-384x288_20220914_152358 2022/09/15 08:44:28 - mmengine - INFO - Saving checkpoint at 210 epochs 2022/09/15 08:44:46 - mmengine - INFO - Epoch(val) [210][50/407] eta: 0:01:12 time: 0.203277 data_time: 0.014428 memory: 15239 2022/09/15 08:44:56 - mmengine - INFO - Epoch(val) [210][100/407] eta: 0:01:01 time: 0.200821 data_time: 0.011438 memory: 2064 2022/09/15 08:45:06 - mmengine - INFO - Epoch(val) [210][150/407] eta: 0:00:50 time: 0.197344 data_time: 0.009202 memory: 2064 2022/09/15 08:45:15 - mmengine - INFO - Epoch(val) [210][200/407] eta: 0:00:40 time: 0.195310 data_time: 0.008464 memory: 2064 2022/09/15 08:45:25 - mmengine - INFO - Epoch(val) [210][250/407] eta: 0:00:30 time: 0.195568 data_time: 0.008567 memory: 2064 2022/09/15 08:45:35 - mmengine - INFO - Epoch(val) [210][300/407] eta: 0:00:20 time: 0.196136 data_time: 0.008419 memory: 2064 2022/09/15 08:45:45 - mmengine - INFO - Epoch(val) [210][350/407] eta: 0:00:11 time: 0.195545 data_time: 0.008530 memory: 2064 2022/09/15 08:45:55 - mmengine - INFO - Epoch(val) [210][400/407] eta: 0:00:01 time: 0.193725 data_time: 0.007950 memory: 2064 2022/09/15 08:46:32 - mmengine - INFO - Evaluating CocoMetric... 2022/09/15 08:46:45 - mmengine - INFO - Epoch(val) [210][407/407] coco/AP: 0.767045 coco/AP .5: 0.910233 coco/AP .75: 0.831886 coco/AP (M): 0.727640 coco/AP (L): 0.837145 coco/AR: 0.816184 coco/AR .5: 0.945372 coco/AR .75: 0.875630 coco/AR (M): 0.772794 coco/AR (L): 0.879227