2022/09/22 23:28:01 - mmengine - INFO - ------------------------------------------------------------ System environment: sys.platform: linux Python: 3.8.13 (default, Mar 28 2022, 11:38:47) [GCC 7.5.0] CUDA available: True numpy_random_seed: 1324479199 GPU 0,1,2,3,4,5,6,7: NVIDIA A100-SXM4-80GB CUDA_HOME: /mnt/lustre/share/cuda-11.3 NVCC: Cuda compilation tools, release 11.3, V11.3.109 GCC: gcc (GCC) 5.4.0 PyTorch: 1.12.1 PyTorch compiling details: PyTorch built with: - GCC 9.3 - C++ Version: 201402 - Intel(R) oneAPI Math Kernel Library Version 2021.4-Product Build 20210904 for Intel(R) 64 architecture applications - Intel(R) MKL-DNN v2.6.0 (Git Hash 52b5f107dd9cf10910aaa19cb47f3abf9b349815) - OpenMP 201511 (a.k.a. OpenMP 4.5) - LAPACK is enabled (usually provided by MKL) - NNPACK is enabled - CPU capability usage: AVX2 - CUDA Runtime 11.3 - 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_61,code=sm_61;-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;-gencode;arch=compute_37,code=compute_37 - CuDNN 8.3.2 (built against CUDA 11.5) - Magma 2.5.2 - Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.3, CUDNN_VERSION=8.3.2, CXX_COMPILER=/opt/rh/devtoolset-9/root/usr/bin/c++, CXX_FLAGS= -fabi-version=11 -Wno-deprecated -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -fopenmp -DNDEBUG -DUSE_KINETO -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DSYMBOLICATE_MOBILE_DEBUG_HANDLE -DEDGE_PROFILER_USE_KINETO -O2 -fPIC -Wno-narrowing -Wall -Wextra -Werror=return-type -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wno-unused-parameter -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 -Werror=cast-function-type -Wno-stringop-overflow, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, TORCH_VERSION=1.12.1, USE_CUDA=ON, USE_CUDNN=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=OFF, USE_MPI=OFF, USE_NCCL=ON, USE_NNPACK=ON, USE_OPENMP=ON, USE_ROCM=OFF, TorchVision: 0.13.1 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 ------------------------------------------------------------ 2022/09/22 23:28:03 - 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=10, max_keep_ckpts=1, save_best='coco/AP', rule='greater'), 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='ResNet', depth=50, init_cfg=dict(type='Pretrained', checkpoint='torchvision://resnet50')), head=dict( type='HeatmapHead', in_channels=2048, out_channels=17, 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') ] val_pipeline = [ dict( type='LoadImage', file_client_args=dict( backend='petrel', path_mapping=dict({ './data/': 's3://openmmlab/datasets/detection/', 'data/': 's3://openmmlab/datasets/detection/' }))), dict(type='GetBBoxCenterScale'), dict(type='TopdownAffine', input_size=(288, 384)), dict(type='PackPoseInputs') ] train_dataloader = dict( batch_size=64, num_workers=2, persistent_workers=True, sampler=dict(type='DefaultSampler', shuffle=True), dataset=dict( type='CocoDataset', data_root='data/coco/', data_mode='topdown', ann_file='annotations/person_keypoints_train2017.json', data_prefix=dict(img='train2017/'), pipeline=[ dict( type='LoadImage', file_client_args=dict( backend='petrel', path_mapping=dict({ './data/': 's3://openmmlab/datasets/detection/', 'data/': 's3://openmmlab/datasets/detection/' }))), dict(type='GetBBoxCenterScale'), dict(type='RandomFlip', direction='horizontal'), dict(type='RandomHalfBody'), dict(type='RandomBBoxTransform'), dict(type='TopdownAffine', input_size=(288, 384)), dict( type='GenerateTarget', target_type='heatmap', encoder=dict( type='MSRAHeatmap', input_size=(288, 384), heatmap_size=(72, 96), sigma=3)), 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/20220922/res50_384_2/' 2022/09/22 23:28:43 - 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. 2022/09/22 23:28:43 - 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. 2022/09/22 23:28:43 - 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. 2022/09/22 23:28:43 - 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. 2022/09/22 23:28:43 - 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. 2022/09/22 23:28:43 - 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. 2022/09/22 23:28:43 - 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. 2022/09/22 23:28:43 - 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. 2022/09/22 23:28:47 - mmengine - WARNING - Failed to search registry with scope "mmpose" in the "data sampler" registry tree. As a workaround, the current "data sampler" registry in "mmengine" is used to build instance. This may cause unexpected failure when running the built modules. Please check whether "mmpose" is a correct scope, or whether the registry is initialized. 2022/09/22 23:28:49 - 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. 2022/09/22 23:28:52 - 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. 2022/09/22 23:28:52 - 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. Name of parameter - Initialization information backbone.conv1.weight - torch.Size([64, 3, 7, 7]): PretrainedInit: load from torchvision://resnet50 backbone.bn1.weight - torch.Size([64]): PretrainedInit: load from torchvision://resnet50 backbone.bn1.bias - torch.Size([64]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.0.conv1.weight - torch.Size([64, 64, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.0.bn1.weight - torch.Size([64]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.0.bn1.bias - torch.Size([64]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.0.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.0.bn2.weight - torch.Size([64]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.0.bn2.bias - torch.Size([64]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.0.conv3.weight - torch.Size([256, 64, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.0.bn3.weight - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.0.bn3.bias - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.0.downsample.0.weight - torch.Size([256, 64, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.0.downsample.1.weight - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.0.downsample.1.bias - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.1.conv1.weight - torch.Size([64, 256, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.1.bn1.weight - torch.Size([64]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.1.bn1.bias - torch.Size([64]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.1.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.1.bn2.weight - torch.Size([64]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.1.bn2.bias - torch.Size([64]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.1.conv3.weight - torch.Size([256, 64, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.1.bn3.weight - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.1.bn3.bias - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.2.conv1.weight - torch.Size([64, 256, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.2.bn1.weight - torch.Size([64]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.2.bn1.bias - torch.Size([64]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.2.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.2.bn2.weight - torch.Size([64]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.2.bn2.bias - torch.Size([64]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.2.conv3.weight - torch.Size([256, 64, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.2.bn3.weight - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer1.2.bn3.bias - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.0.conv1.weight - torch.Size([128, 256, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.0.bn1.weight - torch.Size([128]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.0.bn1.bias - torch.Size([128]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.0.conv2.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.0.bn2.weight - torch.Size([128]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.0.bn2.bias - torch.Size([128]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.0.conv3.weight - torch.Size([512, 128, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.0.bn3.weight - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.0.bn3.bias - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.0.downsample.0.weight - torch.Size([512, 256, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.0.downsample.1.weight - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.0.downsample.1.bias - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.1.conv1.weight - torch.Size([128, 512, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.1.bn1.weight - torch.Size([128]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.1.bn1.bias - torch.Size([128]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.1.conv2.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.1.bn2.weight - torch.Size([128]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.1.bn2.bias - torch.Size([128]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.1.conv3.weight - torch.Size([512, 128, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.1.bn3.weight - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.1.bn3.bias - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.2.conv1.weight - torch.Size([128, 512, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.2.bn1.weight - torch.Size([128]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.2.bn1.bias - torch.Size([128]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.2.conv2.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.2.bn2.weight - torch.Size([128]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.2.bn2.bias - torch.Size([128]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.2.conv3.weight - torch.Size([512, 128, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.2.bn3.weight - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.2.bn3.bias - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.3.conv1.weight - torch.Size([128, 512, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.3.bn1.weight - torch.Size([128]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.3.bn1.bias - torch.Size([128]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.3.conv2.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.3.bn2.weight - torch.Size([128]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.3.bn2.bias - torch.Size([128]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.3.conv3.weight - torch.Size([512, 128, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.3.bn3.weight - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer2.3.bn3.bias - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.0.conv1.weight - torch.Size([256, 512, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.0.bn1.weight - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.0.bn1.bias - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.0.conv2.weight - torch.Size([256, 256, 3, 3]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.0.bn2.weight - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.0.bn2.bias - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.0.conv3.weight - torch.Size([1024, 256, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.0.bn3.weight - torch.Size([1024]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.0.bn3.bias - torch.Size([1024]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.0.downsample.0.weight - torch.Size([1024, 512, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.0.downsample.1.weight - torch.Size([1024]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.0.downsample.1.bias - torch.Size([1024]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.1.conv1.weight - torch.Size([256, 1024, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.1.bn1.weight - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.1.bn1.bias - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.1.conv2.weight - torch.Size([256, 256, 3, 3]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.1.bn2.weight - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.1.bn2.bias - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.1.conv3.weight - torch.Size([1024, 256, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.1.bn3.weight - torch.Size([1024]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.1.bn3.bias - torch.Size([1024]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.2.conv1.weight - torch.Size([256, 1024, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.2.bn1.weight - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.2.bn1.bias - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.2.conv2.weight - torch.Size([256, 256, 3, 3]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.2.bn2.weight - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.2.bn2.bias - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.2.conv3.weight - torch.Size([1024, 256, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.2.bn3.weight - torch.Size([1024]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.2.bn3.bias - torch.Size([1024]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.3.conv1.weight - torch.Size([256, 1024, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.3.bn1.weight - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.3.bn1.bias - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.3.conv2.weight - torch.Size([256, 256, 3, 3]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.3.bn2.weight - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.3.bn2.bias - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.3.conv3.weight - torch.Size([1024, 256, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.3.bn3.weight - torch.Size([1024]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.3.bn3.bias - torch.Size([1024]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.4.conv1.weight - torch.Size([256, 1024, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.4.bn1.weight - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.4.bn1.bias - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.4.conv2.weight - torch.Size([256, 256, 3, 3]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.4.bn2.weight - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.4.bn2.bias - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.4.conv3.weight - torch.Size([1024, 256, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.4.bn3.weight - torch.Size([1024]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.4.bn3.bias - torch.Size([1024]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.5.conv1.weight - torch.Size([256, 1024, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.5.bn1.weight - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.5.bn1.bias - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.5.conv2.weight - torch.Size([256, 256, 3, 3]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.5.bn2.weight - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.5.bn2.bias - torch.Size([256]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.5.conv3.weight - torch.Size([1024, 256, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.5.bn3.weight - torch.Size([1024]): PretrainedInit: load from torchvision://resnet50 backbone.layer3.5.bn3.bias - torch.Size([1024]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.0.conv1.weight - torch.Size([512, 1024, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.0.bn1.weight - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.0.bn1.bias - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.0.conv2.weight - torch.Size([512, 512, 3, 3]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.0.bn2.weight - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.0.bn2.bias - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.0.conv3.weight - torch.Size([2048, 512, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.0.bn3.weight - torch.Size([2048]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.0.bn3.bias - torch.Size([2048]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.0.downsample.0.weight - torch.Size([2048, 1024, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.0.downsample.1.weight - torch.Size([2048]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.0.downsample.1.bias - torch.Size([2048]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.1.conv1.weight - torch.Size([512, 2048, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.1.bn1.weight - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.1.bn1.bias - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.1.conv2.weight - torch.Size([512, 512, 3, 3]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.1.bn2.weight - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.1.bn2.bias - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.1.conv3.weight - torch.Size([2048, 512, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.1.bn3.weight - torch.Size([2048]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.1.bn3.bias - torch.Size([2048]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.2.conv1.weight - torch.Size([512, 2048, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.2.bn1.weight - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.2.bn1.bias - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.2.conv2.weight - torch.Size([512, 512, 3, 3]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.2.bn2.weight - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.2.bn2.bias - torch.Size([512]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.2.conv3.weight - torch.Size([2048, 512, 1, 1]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.2.bn3.weight - torch.Size([2048]): PretrainedInit: load from torchvision://resnet50 backbone.layer4.2.bn3.bias - torch.Size([2048]): PretrainedInit: load from torchvision://resnet50 head.deconv_layers.0.weight - torch.Size([2048, 256, 4, 4]): NormalInit: mean=0, std=0.001, bias=0 head.deconv_layers.1.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator head.deconv_layers.1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator head.deconv_layers.3.weight - torch.Size([256, 256, 4, 4]): NormalInit: mean=0, std=0.001, bias=0 head.deconv_layers.4.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator head.deconv_layers.4.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator head.deconv_layers.6.weight - torch.Size([256, 256, 4, 4]): NormalInit: mean=0, std=0.001, bias=0 head.deconv_layers.7.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator head.deconv_layers.7.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator head.final_layer.weight - torch.Size([17, 256, 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 2022/09/22 23:28:52 - mmengine - INFO - Checkpoints will be saved to /mnt/lustre/liqikai/work_dirs/20220922/res50_384_2 by HardDiskBackend. 2022/09/22 23:30:07 - mmengine - INFO - Epoch(train) [1][50/293] lr: 4.954910e-05 eta: 1 day, 1:32:01 time: 1.495140 data_time: 0.389908 memory: 14267 loss_kpt: 0.002147 acc_pose: 0.152940 loss: 0.002147 2022/09/22 23:31:03 - mmengine - INFO - Epoch(train) [1][100/293] lr: 9.959920e-05 eta: 22:20:49 time: 1.124083 data_time: 0.134706 memory: 14267 loss_kpt: 0.001757 acc_pose: 0.419903 loss: 0.001757 2022/09/22 23:32:00 - mmengine - INFO - Epoch(train) [1][150/293] lr: 1.496493e-04 eta: 21:17:32 time: 1.127232 data_time: 0.142458 memory: 14267 loss_kpt: 0.001503 acc_pose: 0.514396 loss: 0.001503 2022/09/22 23:32:55 - mmengine - INFO - Epoch(train) [1][200/293] lr: 1.996994e-04 eta: 20:43:06 time: 1.118145 data_time: 0.125364 memory: 14267 loss_kpt: 0.001369 acc_pose: 0.596492 loss: 0.001369 2022/09/22 23:33:49 - mmengine - INFO - Epoch(train) [1][250/293] lr: 2.497495e-04 eta: 20:12:53 time: 1.073199 data_time: 0.133828 memory: 14267 loss_kpt: 0.001311 acc_pose: 0.579020 loss: 0.001311 2022/09/22 23:34:36 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/22 23:35:34 - mmengine - INFO - Epoch(train) [2][50/293] lr: 3.428427e-04 eta: 17:35:23 time: 1.161683 data_time: 0.156278 memory: 14267 loss_kpt: 0.001210 acc_pose: 0.561737 loss: 0.001210 2022/09/22 23:36:30 - mmengine - INFO - Epoch(train) [2][100/293] lr: 3.928928e-04 eta: 17:46:09 time: 1.124670 data_time: 0.142458 memory: 14267 loss_kpt: 0.001178 acc_pose: 0.616344 loss: 0.001178 2022/09/22 23:37:25 - mmengine - INFO - Epoch(train) [2][150/293] lr: 4.429429e-04 eta: 17:50:00 time: 1.087378 data_time: 0.142231 memory: 14267 loss_kpt: 0.001175 acc_pose: 0.601866 loss: 0.001175 2022/09/22 23:38:21 - mmengine - INFO - Epoch(train) [2][200/293] lr: 4.929930e-04 eta: 17:57:00 time: 1.127372 data_time: 0.126970 memory: 14267 loss_kpt: 0.001152 acc_pose: 0.624519 loss: 0.001152 2022/09/22 23:39:16 - mmengine - INFO - Epoch(train) [2][250/293] lr: 5.000000e-04 eta: 17:59:50 time: 1.098314 data_time: 0.134841 memory: 14267 loss_kpt: 0.001147 acc_pose: 0.583308 loss: 0.001147 2022/09/22 23:40:03 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/22 23:41:00 - mmengine - INFO - Epoch(train) [3][50/293] lr: 5.000000e-04 eta: 16:51:13 time: 1.136695 data_time: 0.180487 memory: 14267 loss_kpt: 0.001099 acc_pose: 0.656698 loss: 0.001099 2022/09/22 23:41:55 - mmengine - INFO - Epoch(train) [3][100/293] lr: 5.000000e-04 eta: 16:57:15 time: 1.089272 data_time: 0.134191 memory: 14267 loss_kpt: 0.001086 acc_pose: 0.601543 loss: 0.001086 2022/09/22 23:42:50 - mmengine - INFO - Epoch(train) [3][150/293] lr: 5.000000e-04 eta: 17:03:14 time: 1.102184 data_time: 0.148745 memory: 14267 loss_kpt: 0.001063 acc_pose: 0.649700 loss: 0.001063 2022/09/22 23:43:45 - mmengine - INFO - Epoch(train) [3][200/293] lr: 5.000000e-04 eta: 17:08:44 time: 1.108428 data_time: 0.129619 memory: 14267 loss_kpt: 0.001060 acc_pose: 0.645431 loss: 0.001060 2022/09/22 23:44:42 - mmengine - INFO - Epoch(train) [3][250/293] lr: 5.000000e-04 eta: 17:15:42 time: 1.145158 data_time: 0.134417 memory: 14267 loss_kpt: 0.001053 acc_pose: 0.681348 loss: 0.001053 2022/09/22 23:45:30 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/22 23:46:27 - mmengine - INFO - Epoch(train) [4][50/293] lr: 5.000000e-04 eta: 16:32:49 time: 1.144884 data_time: 0.167854 memory: 14267 loss_kpt: 0.001034 acc_pose: 0.634968 loss: 0.001034 2022/09/22 23:47:23 - mmengine - INFO - Epoch(train) [4][100/293] lr: 5.000000e-04 eta: 16:39:00 time: 1.118805 data_time: 0.145305 memory: 14267 loss_kpt: 0.001014 acc_pose: 0.716818 loss: 0.001014 2022/09/22 23:47:46 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/22 23:48:20 - mmengine - INFO - Epoch(train) [4][150/293] lr: 5.000000e-04 eta: 16:45:32 time: 1.140096 data_time: 0.136916 memory: 14267 loss_kpt: 0.001016 acc_pose: 0.718350 loss: 0.001016 2022/09/22 23:49:17 - mmengine - INFO - Epoch(train) [4][200/293] lr: 5.000000e-04 eta: 16:51:18 time: 1.138564 data_time: 0.156686 memory: 14267 loss_kpt: 0.000984 acc_pose: 0.720498 loss: 0.000984 2022/09/22 23:50:13 - mmengine - INFO - Epoch(train) [4][250/293] lr: 5.000000e-04 eta: 16:55:15 time: 1.111134 data_time: 0.133233 memory: 14267 loss_kpt: 0.000990 acc_pose: 0.610439 loss: 0.000990 2022/09/22 23:51:00 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/22 23:51:56 - mmengine - INFO - Epoch(train) [5][50/293] lr: 5.000000e-04 eta: 16:22:07 time: 1.108291 data_time: 0.143528 memory: 14267 loss_kpt: 0.000978 acc_pose: 0.660361 loss: 0.000978 2022/09/22 23:52:51 - mmengine - INFO - Epoch(train) [5][100/293] lr: 5.000000e-04 eta: 16:26:19 time: 1.103868 data_time: 0.135715 memory: 14267 loss_kpt: 0.000956 acc_pose: 0.614145 loss: 0.000956 2022/09/22 23:53:46 - mmengine - INFO - Epoch(train) [5][150/293] lr: 5.000000e-04 eta: 16:30:04 time: 1.102349 data_time: 0.126810 memory: 14267 loss_kpt: 0.000970 acc_pose: 0.693558 loss: 0.000970 2022/09/22 23:54:43 - mmengine - INFO - Epoch(train) [5][200/293] lr: 5.000000e-04 eta: 16:34:44 time: 1.137020 data_time: 0.141454 memory: 14267 loss_kpt: 0.000959 acc_pose: 0.641955 loss: 0.000959 2022/09/22 23:55:39 - mmengine - INFO - Epoch(train) [5][250/293] lr: 5.000000e-04 eta: 16:38:12 time: 1.114206 data_time: 0.136416 memory: 14267 loss_kpt: 0.000945 acc_pose: 0.735843 loss: 0.000945 2022/09/22 23:56:26 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/22 23:57:24 - mmengine - INFO - Epoch(train) [6][50/293] lr: 5.000000e-04 eta: 16:13:32 time: 1.152747 data_time: 0.160015 memory: 14267 loss_kpt: 0.000940 acc_pose: 0.700485 loss: 0.000940 2022/09/22 23:58:21 - mmengine - INFO - Epoch(train) [6][100/293] lr: 5.000000e-04 eta: 16:18:22 time: 1.150310 data_time: 0.154359 memory: 14267 loss_kpt: 0.000939 acc_pose: 0.753175 loss: 0.000939 2022/09/22 23:59:16 - mmengine - INFO - Epoch(train) [6][150/293] lr: 5.000000e-04 eta: 16:21:32 time: 1.107631 data_time: 0.141973 memory: 14267 loss_kpt: 0.000934 acc_pose: 0.722967 loss: 0.000934 2022/09/23 00:00:15 - mmengine - INFO - Epoch(train) [6][200/293] lr: 5.000000e-04 eta: 16:26:08 time: 1.163677 data_time: 0.143865 memory: 14267 loss_kpt: 0.000923 acc_pose: 0.725463 loss: 0.000923 2022/09/23 00:01:12 - mmengine - INFO - Epoch(train) [6][250/293] lr: 5.000000e-04 eta: 16:29:49 time: 1.143517 data_time: 0.132439 memory: 14267 loss_kpt: 0.000925 acc_pose: 0.664149 loss: 0.000925 2022/09/23 00:01:58 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 00:02:55 - mmengine - INFO - Epoch(train) [7][50/293] lr: 5.000000e-04 eta: 16:08:51 time: 1.140902 data_time: 0.145590 memory: 14267 loss_kpt: 0.000937 acc_pose: 0.692612 loss: 0.000937 2022/09/23 00:03:51 - mmengine - INFO - Epoch(train) [7][100/293] lr: 5.000000e-04 eta: 16:12:13 time: 1.129787 data_time: 0.151807 memory: 14267 loss_kpt: 0.000922 acc_pose: 0.689479 loss: 0.000922 2022/09/23 00:04:47 - mmengine - INFO - Epoch(train) [7][150/293] lr: 5.000000e-04 eta: 16:14:46 time: 1.106449 data_time: 0.135649 memory: 14267 loss_kpt: 0.000902 acc_pose: 0.711458 loss: 0.000902 2022/09/23 00:05:44 - mmengine - INFO - Epoch(train) [7][200/293] lr: 5.000000e-04 eta: 16:17:59 time: 1.140420 data_time: 0.131374 memory: 14267 loss_kpt: 0.000904 acc_pose: 0.722110 loss: 0.000904 2022/09/23 00:06:30 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 00:06:39 - mmengine - INFO - Epoch(train) [7][250/293] lr: 5.000000e-04 eta: 16:20:13 time: 1.108551 data_time: 0.133332 memory: 14267 loss_kpt: 0.000921 acc_pose: 0.669632 loss: 0.000921 2022/09/23 00:07:28 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 00:08:26 - mmengine - INFO - Epoch(train) [8][50/293] lr: 5.000000e-04 eta: 16:03:08 time: 1.177711 data_time: 0.172680 memory: 14267 loss_kpt: 0.000900 acc_pose: 0.750895 loss: 0.000900 2022/09/23 00:09:21 - mmengine - INFO - Epoch(train) [8][100/293] lr: 5.000000e-04 eta: 16:05:11 time: 1.096952 data_time: 0.130496 memory: 14267 loss_kpt: 0.000922 acc_pose: 0.689583 loss: 0.000922 2022/09/23 00:10:17 - mmengine - INFO - Epoch(train) [8][150/293] lr: 5.000000e-04 eta: 16:07:22 time: 1.108278 data_time: 0.133125 memory: 14267 loss_kpt: 0.000886 acc_pose: 0.759448 loss: 0.000886 2022/09/23 00:11:12 - mmengine - INFO - Epoch(train) [8][200/293] lr: 5.000000e-04 eta: 16:09:22 time: 1.107226 data_time: 0.133502 memory: 14267 loss_kpt: 0.000899 acc_pose: 0.684045 loss: 0.000899 2022/09/23 00:12:08 - mmengine - INFO - Epoch(train) [8][250/293] lr: 5.000000e-04 eta: 16:11:36 time: 1.123465 data_time: 0.140934 memory: 14267 loss_kpt: 0.000905 acc_pose: 0.715887 loss: 0.000905 2022/09/23 00:12:56 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 00:13:54 - mmengine - INFO - Epoch(train) [9][50/293] lr: 5.000000e-04 eta: 15:56:18 time: 1.161350 data_time: 0.162129 memory: 14267 loss_kpt: 0.000875 acc_pose: 0.675276 loss: 0.000875 2022/09/23 00:14:49 - mmengine - INFO - Epoch(train) [9][100/293] lr: 5.000000e-04 eta: 15:58:25 time: 1.115684 data_time: 0.142178 memory: 14267 loss_kpt: 0.000898 acc_pose: 0.720467 loss: 0.000898 2022/09/23 00:15:45 - mmengine - INFO - Epoch(train) [9][150/293] lr: 5.000000e-04 eta: 16:00:21 time: 1.111900 data_time: 0.133348 memory: 14267 loss_kpt: 0.000893 acc_pose: 0.752265 loss: 0.000893 2022/09/23 00:16:41 - mmengine - INFO - Epoch(train) [9][200/293] lr: 5.000000e-04 eta: 16:02:10 time: 1.112334 data_time: 0.147145 memory: 14267 loss_kpt: 0.000893 acc_pose: 0.756554 loss: 0.000893 2022/09/23 00:17:39 - mmengine - INFO - Epoch(train) [9][250/293] lr: 5.000000e-04 eta: 16:04:46 time: 1.159312 data_time: 0.136709 memory: 14267 loss_kpt: 0.000875 acc_pose: 0.785477 loss: 0.000875 2022/09/23 00:18:26 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 00:19:23 - mmengine - INFO - Epoch(train) [10][50/293] lr: 5.000000e-04 eta: 15:50:36 time: 1.133546 data_time: 0.156603 memory: 14267 loss_kpt: 0.000864 acc_pose: 0.709622 loss: 0.000864 2022/09/23 00:20:17 - mmengine - INFO - Epoch(train) [10][100/293] lr: 5.000000e-04 eta: 15:51:59 time: 1.091858 data_time: 0.162606 memory: 14267 loss_kpt: 0.000850 acc_pose: 0.676786 loss: 0.000850 2022/09/23 00:21:12 - mmengine - INFO - Epoch(train) [10][150/293] lr: 5.000000e-04 eta: 15:53:26 time: 1.100020 data_time: 0.128809 memory: 14267 loss_kpt: 0.000874 acc_pose: 0.695493 loss: 0.000874 2022/09/23 00:22:08 - mmengine - INFO - Epoch(train) [10][200/293] lr: 5.000000e-04 eta: 15:55:07 time: 1.118423 data_time: 0.130814 memory: 14267 loss_kpt: 0.000863 acc_pose: 0.677104 loss: 0.000863 2022/09/23 00:23:02 - mmengine - INFO - Epoch(train) [10][250/293] lr: 5.000000e-04 eta: 15:56:08 time: 1.085353 data_time: 0.135027 memory: 14267 loss_kpt: 0.000875 acc_pose: 0.716466 loss: 0.000875 2022/09/23 00:23:51 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 00:23:51 - mmengine - INFO - Saving checkpoint at 10 epochs 2022/09/23 00:24:28 - mmengine - INFO - Epoch(val) [10][50/407] eta: 0:04:04 time: 0.686195 data_time: 0.323399 memory: 14267 2022/09/23 00:24:49 - mmengine - INFO - Epoch(val) [10][100/407] eta: 0:02:09 time: 0.423137 data_time: 0.062302 memory: 1464 2022/09/23 00:25:11 - mmengine - INFO - Epoch(val) [10][150/407] eta: 0:01:53 time: 0.440793 data_time: 0.111796 memory: 1464 2022/09/23 00:25:33 - mmengine - INFO - Epoch(val) [10][200/407] eta: 0:01:28 time: 0.428629 data_time: 0.083470 memory: 1464 2022/09/23 00:25:55 - mmengine - INFO - Epoch(val) [10][250/407] eta: 0:01:09 time: 0.441297 data_time: 0.066184 memory: 1464 2022/09/23 00:26:16 - mmengine - INFO - Epoch(val) [10][300/407] eta: 0:00:45 time: 0.422784 data_time: 0.064496 memory: 1464 2022/09/23 00:26:38 - mmengine - INFO - Epoch(val) [10][350/407] eta: 0:00:25 time: 0.444637 data_time: 0.091204 memory: 1464 2022/09/23 00:26:59 - mmengine - INFO - Epoch(val) [10][400/407] eta: 0:00:02 time: 0.426225 data_time: 0.108724 memory: 1464 2022/09/23 00:27:39 - mmengine - INFO - Evaluating CocoMetric... 2022/09/23 00:27:53 - mmengine - INFO - Epoch(val) [10][407/407] coco/AP: 0.619057 coco/AP .5: 0.854240 coco/AP .75: 0.682170 coco/AP (M): 0.574814 coco/AP (L): 0.693235 coco/AR: 0.680400 coco/AR .5: 0.898142 coco/AR .75: 0.741971 coco/AR (M): 0.629582 coco/AR (L): 0.751951 2022/09/23 00:27:56 - mmengine - INFO - The best checkpoint with 0.6191 coco/AP at 10 epoch is saved to best_coco/AP_epoch_10.pth. 2022/09/23 00:28:53 - mmengine - INFO - Epoch(train) [11][50/293] lr: 5.000000e-04 eta: 15:43:29 time: 1.139052 data_time: 0.144091 memory: 14267 loss_kpt: 0.000862 acc_pose: 0.797893 loss: 0.000862 2022/09/23 00:29:16 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 00:29:48 - mmengine - INFO - Epoch(train) [11][100/293] lr: 5.000000e-04 eta: 15:44:37 time: 1.087188 data_time: 0.136217 memory: 14267 loss_kpt: 0.000868 acc_pose: 0.716241 loss: 0.000868 2022/09/23 00:30:43 - mmengine - INFO - Epoch(train) [11][150/293] lr: 5.000000e-04 eta: 15:46:03 time: 1.110558 data_time: 0.133136 memory: 14267 loss_kpt: 0.000848 acc_pose: 0.763615 loss: 0.000848 2022/09/23 00:31:39 - mmengine - INFO - Epoch(train) [11][200/293] lr: 5.000000e-04 eta: 15:47:26 time: 1.112530 data_time: 0.151500 memory: 14267 loss_kpt: 0.000875 acc_pose: 0.734603 loss: 0.000875 2022/09/23 00:32:34 - mmengine - INFO - Epoch(train) [11][250/293] lr: 5.000000e-04 eta: 15:48:41 time: 1.108284 data_time: 0.139563 memory: 14267 loss_kpt: 0.000864 acc_pose: 0.715888 loss: 0.000864 2022/09/23 00:33:22 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 00:34:19 - mmengine - INFO - Epoch(train) [12][50/293] lr: 5.000000e-04 eta: 15:37:02 time: 1.130890 data_time: 0.151089 memory: 14267 loss_kpt: 0.000843 acc_pose: 0.770784 loss: 0.000843 2022/09/23 00:35:14 - mmengine - INFO - Epoch(train) [12][100/293] lr: 5.000000e-04 eta: 15:38:27 time: 1.117113 data_time: 0.132152 memory: 14267 loss_kpt: 0.000830 acc_pose: 0.723649 loss: 0.000830 2022/09/23 00:36:10 - mmengine - INFO - Epoch(train) [12][150/293] lr: 5.000000e-04 eta: 15:39:43 time: 1.111323 data_time: 0.131393 memory: 14267 loss_kpt: 0.000842 acc_pose: 0.745776 loss: 0.000842 2022/09/23 00:37:06 - mmengine - INFO - Epoch(train) [12][200/293] lr: 5.000000e-04 eta: 15:40:55 time: 1.111308 data_time: 0.146041 memory: 14267 loss_kpt: 0.000846 acc_pose: 0.722619 loss: 0.000846 2022/09/23 00:38:01 - mmengine - INFO - Epoch(train) [12][250/293] lr: 5.000000e-04 eta: 15:42:05 time: 1.114413 data_time: 0.147031 memory: 14267 loss_kpt: 0.000861 acc_pose: 0.755553 loss: 0.000861 2022/09/23 00:38:49 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 00:39:45 - mmengine - INFO - Epoch(train) [13][50/293] lr: 5.000000e-04 eta: 15:31:10 time: 1.116109 data_time: 0.142411 memory: 14267 loss_kpt: 0.000832 acc_pose: 0.738917 loss: 0.000832 2022/09/23 00:40:38 - mmengine - INFO - Epoch(train) [13][100/293] lr: 5.000000e-04 eta: 15:31:35 time: 1.055610 data_time: 0.128431 memory: 14267 loss_kpt: 0.000844 acc_pose: 0.747483 loss: 0.000844 2022/09/23 00:41:32 - mmengine - INFO - Epoch(train) [13][150/293] lr: 5.000000e-04 eta: 15:32:29 time: 1.094198 data_time: 0.138013 memory: 14267 loss_kpt: 0.000832 acc_pose: 0.741322 loss: 0.000832 2022/09/23 00:42:29 - mmengine - INFO - Epoch(train) [13][200/293] lr: 5.000000e-04 eta: 15:33:41 time: 1.121922 data_time: 0.135733 memory: 14267 loss_kpt: 0.000838 acc_pose: 0.744985 loss: 0.000838 2022/09/23 00:43:26 - mmengine - INFO - Epoch(train) [13][250/293] lr: 5.000000e-04 eta: 15:35:17 time: 1.157608 data_time: 0.154953 memory: 14267 loss_kpt: 0.000832 acc_pose: 0.749162 loss: 0.000832 2022/09/23 00:44:14 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 00:45:11 - mmengine - INFO - Epoch(train) [14][50/293] lr: 5.000000e-04 eta: 15:25:22 time: 1.131089 data_time: 0.161805 memory: 14267 loss_kpt: 0.000823 acc_pose: 0.738270 loss: 0.000823 2022/09/23 00:46:06 - mmengine - INFO - Epoch(train) [14][100/293] lr: 5.000000e-04 eta: 15:26:21 time: 1.107540 data_time: 0.140297 memory: 14267 loss_kpt: 0.000822 acc_pose: 0.729730 loss: 0.000822 2022/09/23 00:47:01 - mmengine - INFO - Epoch(train) [14][150/293] lr: 5.000000e-04 eta: 15:27:00 time: 1.084846 data_time: 0.131898 memory: 14267 loss_kpt: 0.000831 acc_pose: 0.726824 loss: 0.000831 2022/09/23 00:47:46 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 00:47:56 - mmengine - INFO - Epoch(train) [14][200/293] lr: 5.000000e-04 eta: 15:27:52 time: 1.106232 data_time: 0.135521 memory: 14267 loss_kpt: 0.000839 acc_pose: 0.752606 loss: 0.000839 2022/09/23 00:48:52 - mmengine - INFO - Epoch(train) [14][250/293] lr: 5.000000e-04 eta: 15:28:54 time: 1.123074 data_time: 0.139260 memory: 14267 loss_kpt: 0.000829 acc_pose: 0.734413 loss: 0.000829 2022/09/23 00:49:38 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 00:50:34 - mmengine - INFO - Epoch(train) [15][50/293] lr: 5.000000e-04 eta: 15:19:26 time: 1.112580 data_time: 0.152693 memory: 14267 loss_kpt: 0.000811 acc_pose: 0.790942 loss: 0.000811 2022/09/23 00:51:29 - mmengine - INFO - Epoch(train) [15][100/293] lr: 5.000000e-04 eta: 15:20:12 time: 1.100325 data_time: 0.126446 memory: 14267 loss_kpt: 0.000829 acc_pose: 0.740658 loss: 0.000829 2022/09/23 00:52:25 - mmengine - INFO - Epoch(train) [15][150/293] lr: 5.000000e-04 eta: 15:21:09 time: 1.118916 data_time: 0.151128 memory: 14267 loss_kpt: 0.000821 acc_pose: 0.727366 loss: 0.000821 2022/09/23 00:53:22 - mmengine - INFO - Epoch(train) [15][200/293] lr: 5.000000e-04 eta: 15:22:22 time: 1.147019 data_time: 0.134624 memory: 14267 loss_kpt: 0.000827 acc_pose: 0.750361 loss: 0.000827 2022/09/23 00:54:19 - mmengine - INFO - Epoch(train) [15][250/293] lr: 5.000000e-04 eta: 15:23:19 time: 1.127966 data_time: 0.153649 memory: 14267 loss_kpt: 0.000813 acc_pose: 0.776322 loss: 0.000813 2022/09/23 00:55:06 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 00:56:02 - mmengine - INFO - Epoch(train) [16][50/293] lr: 5.000000e-04 eta: 15:14:28 time: 1.115255 data_time: 0.152282 memory: 14267 loss_kpt: 0.000823 acc_pose: 0.807662 loss: 0.000823 2022/09/23 00:56:57 - mmengine - INFO - Epoch(train) [16][100/293] lr: 5.000000e-04 eta: 15:15:14 time: 1.109356 data_time: 0.131874 memory: 14267 loss_kpt: 0.000799 acc_pose: 0.806951 loss: 0.000799 2022/09/23 00:57:54 - mmengine - INFO - Epoch(train) [16][150/293] lr: 5.000000e-04 eta: 15:16:10 time: 1.129165 data_time: 0.140158 memory: 14267 loss_kpt: 0.000824 acc_pose: 0.753797 loss: 0.000824 2022/09/23 00:58:50 - mmengine - INFO - Epoch(train) [16][200/293] lr: 5.000000e-04 eta: 15:17:04 time: 1.129585 data_time: 0.137752 memory: 14267 loss_kpt: 0.000830 acc_pose: 0.765666 loss: 0.000830 2022/09/23 00:59:44 - mmengine - INFO - Epoch(train) [16][250/293] lr: 5.000000e-04 eta: 15:17:26 time: 1.080118 data_time: 0.143030 memory: 14267 loss_kpt: 0.000809 acc_pose: 0.795043 loss: 0.000809 2022/09/23 01:00:30 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 01:01:26 - mmengine - INFO - Epoch(train) [17][50/293] lr: 5.000000e-04 eta: 15:09:14 time: 1.130211 data_time: 0.159659 memory: 14267 loss_kpt: 0.000797 acc_pose: 0.799880 loss: 0.000797 2022/09/23 01:02:22 - mmengine - INFO - Epoch(train) [17][100/293] lr: 5.000000e-04 eta: 15:10:01 time: 1.121382 data_time: 0.126055 memory: 14267 loss_kpt: 0.000825 acc_pose: 0.703366 loss: 0.000825 2022/09/23 01:03:18 - mmengine - INFO - Epoch(train) [17][150/293] lr: 5.000000e-04 eta: 15:10:41 time: 1.111465 data_time: 0.132411 memory: 14267 loss_kpt: 0.000803 acc_pose: 0.745555 loss: 0.000803 2022/09/23 01:04:15 - mmengine - INFO - Epoch(train) [17][200/293] lr: 5.000000e-04 eta: 15:11:37 time: 1.144243 data_time: 0.143410 memory: 14267 loss_kpt: 0.000803 acc_pose: 0.779547 loss: 0.000803 2022/09/23 01:05:12 - mmengine - INFO - Epoch(train) [17][250/293] lr: 5.000000e-04 eta: 15:12:22 time: 1.127588 data_time: 0.133048 memory: 14267 loss_kpt: 0.000809 acc_pose: 0.735621 loss: 0.000809 2022/09/23 01:06:00 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 01:06:23 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 01:06:57 - mmengine - INFO - Epoch(train) [18][50/293] lr: 5.000000e-04 eta: 15:04:49 time: 1.152875 data_time: 0.172740 memory: 14267 loss_kpt: 0.000808 acc_pose: 0.765726 loss: 0.000808 2022/09/23 01:07:54 - mmengine - INFO - Epoch(train) [18][100/293] lr: 5.000000e-04 eta: 15:05:33 time: 1.126807 data_time: 0.127035 memory: 14267 loss_kpt: 0.000802 acc_pose: 0.716708 loss: 0.000802 2022/09/23 01:08:50 - mmengine - INFO - Epoch(train) [18][150/293] lr: 5.000000e-04 eta: 15:06:16 time: 1.127935 data_time: 0.139923 memory: 14267 loss_kpt: 0.000795 acc_pose: 0.771615 loss: 0.000795 2022/09/23 01:09:44 - mmengine - INFO - Epoch(train) [18][200/293] lr: 5.000000e-04 eta: 15:06:29 time: 1.077747 data_time: 0.136666 memory: 14267 loss_kpt: 0.000798 acc_pose: 0.756309 loss: 0.000798 2022/09/23 01:10:39 - mmengine - INFO - Epoch(train) [18][250/293] lr: 5.000000e-04 eta: 15:06:56 time: 1.104533 data_time: 0.128585 memory: 14267 loss_kpt: 0.000817 acc_pose: 0.753235 loss: 0.000817 2022/09/23 01:11:28 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 01:12:24 - mmengine - INFO - Epoch(train) [19][50/293] lr: 5.000000e-04 eta: 14:59:24 time: 1.111968 data_time: 0.149098 memory: 14267 loss_kpt: 0.000812 acc_pose: 0.778786 loss: 0.000812 2022/09/23 01:13:19 - mmengine - INFO - Epoch(train) [19][100/293] lr: 5.000000e-04 eta: 14:59:55 time: 1.112320 data_time: 0.136574 memory: 14267 loss_kpt: 0.000797 acc_pose: 0.775159 loss: 0.000797 2022/09/23 01:14:15 - mmengine - INFO - Epoch(train) [19][150/293] lr: 5.000000e-04 eta: 15:00:29 time: 1.119531 data_time: 0.138170 memory: 14267 loss_kpt: 0.000794 acc_pose: 0.779775 loss: 0.000794 2022/09/23 01:15:12 - mmengine - INFO - Epoch(train) [19][200/293] lr: 5.000000e-04 eta: 15:01:07 time: 1.131902 data_time: 0.138605 memory: 14267 loss_kpt: 0.000791 acc_pose: 0.730185 loss: 0.000791 2022/09/23 01:16:08 - mmengine - INFO - Epoch(train) [19][250/293] lr: 5.000000e-04 eta: 15:01:41 time: 1.126611 data_time: 0.129393 memory: 14267 loss_kpt: 0.000790 acc_pose: 0.756852 loss: 0.000790 2022/09/23 01:16:57 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 01:17:53 - mmengine - INFO - Epoch(train) [20][50/293] lr: 5.000000e-04 eta: 14:54:42 time: 1.133925 data_time: 0.162429 memory: 14267 loss_kpt: 0.000788 acc_pose: 0.794750 loss: 0.000788 2022/09/23 01:18:50 - mmengine - INFO - Epoch(train) [20][100/293] lr: 5.000000e-04 eta: 14:55:17 time: 1.130100 data_time: 0.129515 memory: 14267 loss_kpt: 0.000795 acc_pose: 0.734612 loss: 0.000795 2022/09/23 01:19:46 - mmengine - INFO - Epoch(train) [20][150/293] lr: 5.000000e-04 eta: 14:55:44 time: 1.114191 data_time: 0.125598 memory: 14267 loss_kpt: 0.000794 acc_pose: 0.719859 loss: 0.000794 2022/09/23 01:20:41 - mmengine - INFO - Epoch(train) [20][200/293] lr: 5.000000e-04 eta: 14:56:06 time: 1.108504 data_time: 0.138382 memory: 14267 loss_kpt: 0.000794 acc_pose: 0.797468 loss: 0.000794 2022/09/23 01:21:38 - mmengine - INFO - Epoch(train) [20][250/293] lr: 5.000000e-04 eta: 14:56:39 time: 1.132841 data_time: 0.149386 memory: 14267 loss_kpt: 0.000799 acc_pose: 0.756867 loss: 0.000799 2022/09/23 01:22:25 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 01:22:25 - mmengine - INFO - Saving checkpoint at 20 epochs 2022/09/23 01:22:56 - mmengine - INFO - Epoch(val) [20][50/407] eta: 0:02:46 time: 0.467331 data_time: 0.116965 memory: 14267 2022/09/23 01:23:19 - mmengine - INFO - Epoch(val) [20][100/407] eta: 0:02:22 time: 0.463947 data_time: 0.079960 memory: 1464 2022/09/23 01:23:39 - mmengine - INFO - Epoch(val) [20][150/407] eta: 0:01:44 time: 0.405083 data_time: 0.063005 memory: 1464 2022/09/23 01:24:00 - mmengine - INFO - Epoch(val) [20][200/407] eta: 0:01:28 time: 0.428542 data_time: 0.063035 memory: 1464 2022/09/23 01:24:23 - mmengine - INFO - Epoch(val) [20][250/407] eta: 0:01:09 time: 0.441029 data_time: 0.092771 memory: 1464 2022/09/23 01:24:44 - mmengine - INFO - Epoch(val) [20][300/407] eta: 0:00:45 time: 0.427959 data_time: 0.088702 memory: 1464 2022/09/23 01:25:06 - mmengine - INFO - Epoch(val) [20][350/407] eta: 0:00:25 time: 0.445096 data_time: 0.113392 memory: 1464 2022/09/23 01:25:25 - mmengine - INFO - Epoch(val) [20][400/407] eta: 0:00:02 time: 0.377492 data_time: 0.046425 memory: 1464 2022/09/23 01:26:02 - mmengine - INFO - Evaluating CocoMetric... 2022/09/23 01:26:17 - mmengine - INFO - Epoch(val) [20][407/407] coco/AP: 0.658313 coco/AP .5: 0.871313 coco/AP .75: 0.722463 coco/AP (M): 0.612787 coco/AP (L): 0.733267 coco/AR: 0.717081 coco/AR .5: 0.911366 coco/AR .75: 0.779597 coco/AR (M): 0.666730 coco/AR (L): 0.788369 2022/09/23 01:26:17 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220922/res50_384_2/best_coco/AP_epoch_10.pth is removed 2022/09/23 01:26:20 - mmengine - INFO - The best checkpoint with 0.6583 coco/AP at 20 epoch is saved to best_coco/AP_epoch_20.pth. 2022/09/23 01:27:18 - mmengine - INFO - Epoch(train) [21][50/293] lr: 5.000000e-04 eta: 14:50:07 time: 1.154316 data_time: 0.152337 memory: 14267 loss_kpt: 0.000810 acc_pose: 0.797621 loss: 0.000810 2022/09/23 01:28:14 - mmengine - INFO - Epoch(train) [21][100/293] lr: 5.000000e-04 eta: 14:50:36 time: 1.126720 data_time: 0.128172 memory: 14267 loss_kpt: 0.000793 acc_pose: 0.710150 loss: 0.000793 2022/09/23 01:28:57 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 01:29:08 - mmengine - INFO - Epoch(train) [21][150/293] lr: 5.000000e-04 eta: 14:50:39 time: 1.071623 data_time: 0.138444 memory: 14267 loss_kpt: 0.000785 acc_pose: 0.790737 loss: 0.000785 2022/09/23 01:30:02 - mmengine - INFO - Epoch(train) [21][200/293] lr: 5.000000e-04 eta: 14:50:49 time: 1.088839 data_time: 0.130916 memory: 14267 loss_kpt: 0.000793 acc_pose: 0.778342 loss: 0.000793 2022/09/23 01:30:57 - mmengine - INFO - Epoch(train) [21][250/293] lr: 5.000000e-04 eta: 14:51:06 time: 1.107128 data_time: 0.132472 memory: 14267 loss_kpt: 0.000791 acc_pose: 0.738708 loss: 0.000791 2022/09/23 01:31:45 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 01:32:42 - mmengine - INFO - Epoch(train) [22][50/293] lr: 5.000000e-04 eta: 14:44:43 time: 1.138421 data_time: 0.158361 memory: 14267 loss_kpt: 0.000794 acc_pose: 0.723326 loss: 0.000794 2022/09/23 01:33:38 - mmengine - INFO - Epoch(train) [22][100/293] lr: 5.000000e-04 eta: 14:45:01 time: 1.107562 data_time: 0.139338 memory: 14267 loss_kpt: 0.000776 acc_pose: 0.784979 loss: 0.000776 2022/09/23 01:34:33 - mmengine - INFO - Epoch(train) [22][150/293] lr: 5.000000e-04 eta: 14:45:22 time: 1.118088 data_time: 0.128385 memory: 14267 loss_kpt: 0.000791 acc_pose: 0.773221 loss: 0.000791 2022/09/23 01:35:29 - mmengine - INFO - Epoch(train) [22][200/293] lr: 5.000000e-04 eta: 14:45:41 time: 1.115911 data_time: 0.140200 memory: 14267 loss_kpt: 0.000794 acc_pose: 0.752010 loss: 0.000794 2022/09/23 01:36:25 - mmengine - INFO - Epoch(train) [22][250/293] lr: 5.000000e-04 eta: 14:45:56 time: 1.110644 data_time: 0.141164 memory: 14267 loss_kpt: 0.000782 acc_pose: 0.727671 loss: 0.000782 2022/09/23 01:37:13 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 01:38:11 - mmengine - INFO - Epoch(train) [23][50/293] lr: 5.000000e-04 eta: 14:39:52 time: 1.144630 data_time: 0.147125 memory: 14267 loss_kpt: 0.000775 acc_pose: 0.799179 loss: 0.000775 2022/09/23 01:39:05 - mmengine - INFO - Epoch(train) [23][100/293] lr: 5.000000e-04 eta: 14:39:55 time: 1.081668 data_time: 0.135691 memory: 14267 loss_kpt: 0.000779 acc_pose: 0.755368 loss: 0.000779 2022/09/23 01:40:02 - mmengine - INFO - Epoch(train) [23][150/293] lr: 5.000000e-04 eta: 14:40:22 time: 1.140444 data_time: 0.150951 memory: 14267 loss_kpt: 0.000776 acc_pose: 0.763122 loss: 0.000776 2022/09/23 01:40:58 - mmengine - INFO - Epoch(train) [23][200/293] lr: 5.000000e-04 eta: 14:40:36 time: 1.112623 data_time: 0.136884 memory: 14267 loss_kpt: 0.000782 acc_pose: 0.765565 loss: 0.000782 2022/09/23 01:41:51 - mmengine - INFO - Epoch(train) [23][250/293] lr: 5.000000e-04 eta: 14:40:36 time: 1.079376 data_time: 0.132859 memory: 14267 loss_kpt: 0.000773 acc_pose: 0.713209 loss: 0.000773 2022/09/23 01:42:41 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 01:43:37 - mmengine - INFO - Epoch(train) [24][50/293] lr: 5.000000e-04 eta: 14:34:40 time: 1.131342 data_time: 0.147300 memory: 14267 loss_kpt: 0.000778 acc_pose: 0.721503 loss: 0.000778 2022/09/23 01:44:35 - mmengine - INFO - Epoch(train) [24][100/293] lr: 5.000000e-04 eta: 14:35:07 time: 1.146460 data_time: 0.148065 memory: 14267 loss_kpt: 0.000778 acc_pose: 0.771109 loss: 0.000778 2022/09/23 01:45:31 - mmengine - INFO - Epoch(train) [24][150/293] lr: 5.000000e-04 eta: 14:35:29 time: 1.135454 data_time: 0.138990 memory: 14267 loss_kpt: 0.000782 acc_pose: 0.716466 loss: 0.000782 2022/09/23 01:46:26 - mmengine - INFO - Epoch(train) [24][200/293] lr: 5.000000e-04 eta: 14:35:36 time: 1.101545 data_time: 0.138415 memory: 14267 loss_kpt: 0.000783 acc_pose: 0.830479 loss: 0.000783 2022/09/23 01:47:23 - mmengine - INFO - Epoch(train) [24][250/293] lr: 5.000000e-04 eta: 14:35:51 time: 1.125716 data_time: 0.136346 memory: 14267 loss_kpt: 0.000775 acc_pose: 0.759114 loss: 0.000775 2022/09/23 01:47:35 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 01:48:09 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 01:49:06 - mmengine - INFO - Epoch(train) [25][50/293] lr: 5.000000e-04 eta: 14:30:08 time: 1.132107 data_time: 0.164004 memory: 14267 loss_kpt: 0.000781 acc_pose: 0.759921 loss: 0.000781 2022/09/23 01:50:02 - mmengine - INFO - Epoch(train) [25][100/293] lr: 5.000000e-04 eta: 14:30:22 time: 1.121826 data_time: 0.134190 memory: 14267 loss_kpt: 0.000756 acc_pose: 0.821920 loss: 0.000756 2022/09/23 01:50:58 - mmengine - INFO - Epoch(train) [25][150/293] lr: 5.000000e-04 eta: 14:30:31 time: 1.111502 data_time: 0.139262 memory: 14267 loss_kpt: 0.000783 acc_pose: 0.712028 loss: 0.000783 2022/09/23 01:51:55 - mmengine - INFO - Epoch(train) [25][200/293] lr: 5.000000e-04 eta: 14:30:52 time: 1.144998 data_time: 0.152156 memory: 14267 loss_kpt: 0.000768 acc_pose: 0.796565 loss: 0.000768 2022/09/23 01:52:53 - mmengine - INFO - Epoch(train) [25][250/293] lr: 5.000000e-04 eta: 14:31:17 time: 1.158289 data_time: 0.140758 memory: 14267 loss_kpt: 0.000775 acc_pose: 0.780881 loss: 0.000775 2022/09/23 01:53:40 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 01:54:37 - mmengine - INFO - Epoch(train) [26][50/293] lr: 5.000000e-04 eta: 14:25:49 time: 1.140988 data_time: 0.168637 memory: 14267 loss_kpt: 0.000775 acc_pose: 0.805710 loss: 0.000775 2022/09/23 01:55:31 - mmengine - INFO - Epoch(train) [26][100/293] lr: 5.000000e-04 eta: 14:25:47 time: 1.087288 data_time: 0.130192 memory: 14267 loss_kpt: 0.000771 acc_pose: 0.831009 loss: 0.000771 2022/09/23 01:56:27 - mmengine - INFO - Epoch(train) [26][150/293] lr: 5.000000e-04 eta: 14:25:55 time: 1.115603 data_time: 0.143837 memory: 14267 loss_kpt: 0.000763 acc_pose: 0.727967 loss: 0.000763 2022/09/23 01:57:23 - mmengine - INFO - Epoch(train) [26][200/293] lr: 5.000000e-04 eta: 14:26:05 time: 1.122525 data_time: 0.144582 memory: 14267 loss_kpt: 0.000764 acc_pose: 0.755911 loss: 0.000764 2022/09/23 01:58:19 - mmengine - INFO - Epoch(train) [26][250/293] lr: 5.000000e-04 eta: 14:26:11 time: 1.114074 data_time: 0.147045 memory: 14267 loss_kpt: 0.000764 acc_pose: 0.768174 loss: 0.000764 2022/09/23 01:59:05 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 02:00:01 - mmengine - INFO - Epoch(train) [27][50/293] lr: 5.000000e-04 eta: 14:20:47 time: 1.122894 data_time: 0.178150 memory: 14267 loss_kpt: 0.000771 acc_pose: 0.794266 loss: 0.000771 2022/09/23 02:01:00 - mmengine - INFO - Epoch(train) [27][100/293] lr: 5.000000e-04 eta: 14:21:12 time: 1.167973 data_time: 0.130561 memory: 14267 loss_kpt: 0.000767 acc_pose: 0.747750 loss: 0.000767 2022/09/23 02:01:58 - mmengine - INFO - Epoch(train) [27][150/293] lr: 5.000000e-04 eta: 14:21:31 time: 1.153909 data_time: 0.153095 memory: 14267 loss_kpt: 0.000767 acc_pose: 0.769726 loss: 0.000767 2022/09/23 02:02:54 - mmengine - INFO - Epoch(train) [27][200/293] lr: 5.000000e-04 eta: 14:21:38 time: 1.123377 data_time: 0.138869 memory: 14267 loss_kpt: 0.000778 acc_pose: 0.717669 loss: 0.000778 2022/09/23 02:03:49 - mmengine - INFO - Epoch(train) [27][250/293] lr: 5.000000e-04 eta: 14:21:41 time: 1.112364 data_time: 0.150258 memory: 14267 loss_kpt: 0.000781 acc_pose: 0.778990 loss: 0.000781 2022/09/23 02:04:38 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 02:05:35 - mmengine - INFO - Epoch(train) [28][50/293] lr: 5.000000e-04 eta: 14:16:32 time: 1.138094 data_time: 0.154712 memory: 14267 loss_kpt: 0.000733 acc_pose: 0.797615 loss: 0.000733 2022/09/23 02:06:18 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 02:06:30 - mmengine - INFO - Epoch(train) [28][100/293] lr: 5.000000e-04 eta: 14:16:34 time: 1.110124 data_time: 0.132779 memory: 14267 loss_kpt: 0.000780 acc_pose: 0.766055 loss: 0.000780 2022/09/23 02:07:25 - mmengine - INFO - Epoch(train) [28][150/293] lr: 5.000000e-04 eta: 14:16:31 time: 1.096140 data_time: 0.130911 memory: 14267 loss_kpt: 0.000765 acc_pose: 0.714693 loss: 0.000765 2022/09/23 02:08:19 - mmengine - INFO - Epoch(train) [28][200/293] lr: 5.000000e-04 eta: 14:16:24 time: 1.086094 data_time: 0.144929 memory: 14267 loss_kpt: 0.000759 acc_pose: 0.735308 loss: 0.000759 2022/09/23 02:09:15 - mmengine - INFO - Epoch(train) [28][250/293] lr: 5.000000e-04 eta: 14:16:23 time: 1.106044 data_time: 0.137693 memory: 14267 loss_kpt: 0.000747 acc_pose: 0.828818 loss: 0.000747 2022/09/23 02:10:02 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 02:11:00 - mmengine - INFO - Epoch(train) [29][50/293] lr: 5.000000e-04 eta: 14:11:31 time: 1.161758 data_time: 0.154772 memory: 14267 loss_kpt: 0.000751 acc_pose: 0.775742 loss: 0.000751 2022/09/23 02:11:59 - mmengine - INFO - Epoch(train) [29][100/293] lr: 5.000000e-04 eta: 14:11:50 time: 1.168374 data_time: 0.133393 memory: 14267 loss_kpt: 0.000753 acc_pose: 0.764174 loss: 0.000753 2022/09/23 02:12:55 - mmengine - INFO - Epoch(train) [29][150/293] lr: 5.000000e-04 eta: 14:11:54 time: 1.124255 data_time: 0.143505 memory: 14267 loss_kpt: 0.000759 acc_pose: 0.760606 loss: 0.000759 2022/09/23 02:13:50 - mmengine - INFO - Epoch(train) [29][200/293] lr: 5.000000e-04 eta: 14:11:52 time: 1.106529 data_time: 0.137132 memory: 14267 loss_kpt: 0.000762 acc_pose: 0.715145 loss: 0.000762 2022/09/23 02:14:46 - mmengine - INFO - Epoch(train) [29][250/293] lr: 5.000000e-04 eta: 14:11:50 time: 1.110984 data_time: 0.126878 memory: 14267 loss_kpt: 0.000757 acc_pose: 0.817606 loss: 0.000757 2022/09/23 02:15:34 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 02:16:33 - mmengine - INFO - Epoch(train) [30][50/293] lr: 5.000000e-04 eta: 14:07:12 time: 1.182419 data_time: 0.163634 memory: 14267 loss_kpt: 0.000744 acc_pose: 0.839375 loss: 0.000744 2022/09/23 02:17:28 - mmengine - INFO - Epoch(train) [30][100/293] lr: 5.000000e-04 eta: 14:07:07 time: 1.096797 data_time: 0.137611 memory: 14267 loss_kpt: 0.000748 acc_pose: 0.774902 loss: 0.000748 2022/09/23 02:18:24 - mmengine - INFO - Epoch(train) [30][150/293] lr: 5.000000e-04 eta: 14:07:09 time: 1.124996 data_time: 0.132882 memory: 14267 loss_kpt: 0.000764 acc_pose: 0.784581 loss: 0.000764 2022/09/23 02:19:21 - mmengine - INFO - Epoch(train) [30][200/293] lr: 5.000000e-04 eta: 14:07:11 time: 1.126704 data_time: 0.128495 memory: 14267 loss_kpt: 0.000755 acc_pose: 0.772029 loss: 0.000755 2022/09/23 02:20:18 - mmengine - INFO - Epoch(train) [30][250/293] lr: 5.000000e-04 eta: 14:07:20 time: 1.150681 data_time: 0.131771 memory: 14267 loss_kpt: 0.000747 acc_pose: 0.748549 loss: 0.000747 2022/09/23 02:21:07 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 02:21:07 - mmengine - INFO - Saving checkpoint at 30 epochs 2022/09/23 02:21:38 - mmengine - INFO - Epoch(val) [30][50/407] eta: 0:02:42 time: 0.455324 data_time: 0.107340 memory: 14267 2022/09/23 02:22:01 - mmengine - INFO - Epoch(val) [30][100/407] eta: 0:02:19 time: 0.455350 data_time: 0.098096 memory: 1464 2022/09/23 02:22:23 - mmengine - INFO - Epoch(val) [30][150/407] eta: 0:01:56 time: 0.452580 data_time: 0.092615 memory: 1464 2022/09/23 02:22:44 - mmengine - INFO - Epoch(val) [30][200/407] eta: 0:01:26 time: 0.419074 data_time: 0.061183 memory: 1464 2022/09/23 02:23:06 - mmengine - INFO - Epoch(val) [30][250/407] eta: 0:01:09 time: 0.440225 data_time: 0.054382 memory: 1464 2022/09/23 02:23:28 - mmengine - INFO - Epoch(val) [30][300/407] eta: 0:00:46 time: 0.435124 data_time: 0.068446 memory: 1464 2022/09/23 02:23:51 - mmengine - INFO - Epoch(val) [30][350/407] eta: 0:00:25 time: 0.450195 data_time: 0.092642 memory: 1464 2022/09/23 02:24:10 - mmengine - INFO - Epoch(val) [30][400/407] eta: 0:00:02 time: 0.387088 data_time: 0.082343 memory: 1464 2022/09/23 02:24:48 - mmengine - INFO - Evaluating CocoMetric... 2022/09/23 02:25:02 - mmengine - INFO - Epoch(val) [30][407/407] coco/AP: 0.675098 coco/AP .5: 0.874713 coco/AP .75: 0.742151 coco/AP (M): 0.629727 coco/AP (L): 0.749126 coco/AR: 0.731518 coco/AR .5: 0.914987 coco/AR .75: 0.794868 coco/AR (M): 0.680852 coco/AR (L): 0.803159 2022/09/23 02:25:02 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220922/res50_384_2/best_coco/AP_epoch_20.pth is removed 2022/09/23 02:25:05 - mmengine - INFO - The best checkpoint with 0.6751 coco/AP at 30 epoch is saved to best_coco/AP_epoch_30.pth. 2022/09/23 02:26:02 - mmengine - INFO - Epoch(train) [31][50/293] lr: 5.000000e-04 eta: 14:02:34 time: 1.132377 data_time: 0.154487 memory: 14267 loss_kpt: 0.000743 acc_pose: 0.757264 loss: 0.000743 2022/09/23 02:26:56 - mmengine - INFO - Epoch(train) [31][100/293] lr: 5.000000e-04 eta: 14:02:24 time: 1.089714 data_time: 0.152271 memory: 14267 loss_kpt: 0.000742 acc_pose: 0.775714 loss: 0.000742 2022/09/23 02:27:53 - mmengine - INFO - Epoch(train) [31][150/293] lr: 5.000000e-04 eta: 14:02:28 time: 1.133903 data_time: 0.143641 memory: 14267 loss_kpt: 0.000730 acc_pose: 0.801862 loss: 0.000730 2022/09/23 02:28:49 - mmengine - INFO - Epoch(train) [31][200/293] lr: 5.000000e-04 eta: 14:02:26 time: 1.118946 data_time: 0.137965 memory: 14267 loss_kpt: 0.000748 acc_pose: 0.801419 loss: 0.000748 2022/09/23 02:28:59 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 02:29:46 - mmengine - INFO - Epoch(train) [31][250/293] lr: 5.000000e-04 eta: 14:02:30 time: 1.143006 data_time: 0.143865 memory: 14267 loss_kpt: 0.000751 acc_pose: 0.793125 loss: 0.000751 2022/09/23 02:30:34 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 02:31:31 - mmengine - INFO - Epoch(train) [32][50/293] lr: 5.000000e-04 eta: 13:57:54 time: 1.142578 data_time: 0.165671 memory: 14267 loss_kpt: 0.000743 acc_pose: 0.817394 loss: 0.000743 2022/09/23 02:32:27 - mmengine - INFO - Epoch(train) [32][100/293] lr: 5.000000e-04 eta: 13:57:56 time: 1.131935 data_time: 0.133334 memory: 14267 loss_kpt: 0.000748 acc_pose: 0.789816 loss: 0.000748 2022/09/23 02:33:23 - mmengine - INFO - Epoch(train) [32][150/293] lr: 5.000000e-04 eta: 13:57:51 time: 1.114536 data_time: 0.135330 memory: 14267 loss_kpt: 0.000735 acc_pose: 0.774008 loss: 0.000735 2022/09/23 02:34:19 - mmengine - INFO - Epoch(train) [32][200/293] lr: 5.000000e-04 eta: 13:57:49 time: 1.125241 data_time: 0.138584 memory: 14267 loss_kpt: 0.000755 acc_pose: 0.813471 loss: 0.000755 2022/09/23 02:35:15 - mmengine - INFO - Epoch(train) [32][250/293] lr: 5.000000e-04 eta: 13:57:45 time: 1.117434 data_time: 0.130981 memory: 14267 loss_kpt: 0.000738 acc_pose: 0.763081 loss: 0.000738 2022/09/23 02:36:02 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 02:36:57 - mmengine - INFO - Epoch(train) [33][50/293] lr: 5.000000e-04 eta: 13:53:05 time: 1.103238 data_time: 0.151351 memory: 14267 loss_kpt: 0.000739 acc_pose: 0.692523 loss: 0.000739 2022/09/23 02:37:53 - mmengine - INFO - Epoch(train) [33][100/293] lr: 5.000000e-04 eta: 13:52:58 time: 1.108300 data_time: 0.134140 memory: 14267 loss_kpt: 0.000747 acc_pose: 0.780834 loss: 0.000747 2022/09/23 02:38:49 - mmengine - INFO - Epoch(train) [33][150/293] lr: 5.000000e-04 eta: 13:52:56 time: 1.130125 data_time: 0.126676 memory: 14267 loss_kpt: 0.000761 acc_pose: 0.752761 loss: 0.000761 2022/09/23 02:39:45 - mmengine - INFO - Epoch(train) [33][200/293] lr: 5.000000e-04 eta: 13:52:49 time: 1.109864 data_time: 0.154054 memory: 14267 loss_kpt: 0.000727 acc_pose: 0.777404 loss: 0.000727 2022/09/23 02:40:40 - mmengine - INFO - Epoch(train) [33][250/293] lr: 5.000000e-04 eta: 13:52:40 time: 1.108583 data_time: 0.131043 memory: 14267 loss_kpt: 0.000730 acc_pose: 0.794055 loss: 0.000730 2022/09/23 02:41:27 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 02:42:24 - mmengine - INFO - Epoch(train) [34][50/293] lr: 5.000000e-04 eta: 13:48:16 time: 1.136493 data_time: 0.155805 memory: 14267 loss_kpt: 0.000749 acc_pose: 0.788041 loss: 0.000749 2022/09/23 02:43:21 - mmengine - INFO - Epoch(train) [34][100/293] lr: 5.000000e-04 eta: 13:48:15 time: 1.134194 data_time: 0.129832 memory: 14267 loss_kpt: 0.000725 acc_pose: 0.750041 loss: 0.000725 2022/09/23 02:44:16 - mmengine - INFO - Epoch(train) [34][150/293] lr: 5.000000e-04 eta: 13:48:08 time: 1.116441 data_time: 0.144437 memory: 14267 loss_kpt: 0.000746 acc_pose: 0.783268 loss: 0.000746 2022/09/23 02:45:11 - mmengine - INFO - Epoch(train) [34][200/293] lr: 5.000000e-04 eta: 13:47:54 time: 1.091467 data_time: 0.136780 memory: 14267 loss_kpt: 0.000736 acc_pose: 0.753556 loss: 0.000736 2022/09/23 02:46:06 - mmengine - INFO - Epoch(train) [34][250/293] lr: 5.000000e-04 eta: 13:47:43 time: 1.102612 data_time: 0.125707 memory: 14267 loss_kpt: 0.000749 acc_pose: 0.796452 loss: 0.000749 2022/09/23 02:46:51 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 02:47:35 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 02:47:48 - mmengine - INFO - Epoch(train) [35][50/293] lr: 5.000000e-04 eta: 13:43:30 time: 1.156533 data_time: 0.153613 memory: 14267 loss_kpt: 0.000728 acc_pose: 0.782455 loss: 0.000728 2022/09/23 02:48:45 - mmengine - INFO - Epoch(train) [35][100/293] lr: 5.000000e-04 eta: 13:43:24 time: 1.124179 data_time: 0.152126 memory: 14267 loss_kpt: 0.000736 acc_pose: 0.768832 loss: 0.000736 2022/09/23 02:49:41 - mmengine - INFO - Epoch(train) [35][150/293] lr: 5.000000e-04 eta: 13:43:20 time: 1.132924 data_time: 0.132345 memory: 14267 loss_kpt: 0.000751 acc_pose: 0.770135 loss: 0.000751 2022/09/23 02:50:38 - mmengine - INFO - Epoch(train) [35][200/293] lr: 5.000000e-04 eta: 13:43:16 time: 1.132238 data_time: 0.136684 memory: 14267 loss_kpt: 0.000747 acc_pose: 0.762874 loss: 0.000747 2022/09/23 02:51:32 - mmengine - INFO - Epoch(train) [35][250/293] lr: 5.000000e-04 eta: 13:43:00 time: 1.089468 data_time: 0.125604 memory: 14267 loss_kpt: 0.000744 acc_pose: 0.777968 loss: 0.000744 2022/09/23 02:52:21 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 02:53:18 - mmengine - INFO - Epoch(train) [36][50/293] lr: 5.000000e-04 eta: 13:38:50 time: 1.143091 data_time: 0.146837 memory: 14267 loss_kpt: 0.000731 acc_pose: 0.801812 loss: 0.000731 2022/09/23 02:54:14 - mmengine - INFO - Epoch(train) [36][100/293] lr: 5.000000e-04 eta: 13:38:39 time: 1.112191 data_time: 0.137771 memory: 14267 loss_kpt: 0.000745 acc_pose: 0.771476 loss: 0.000745 2022/09/23 02:55:10 - mmengine - INFO - Epoch(train) [36][150/293] lr: 5.000000e-04 eta: 13:38:34 time: 1.132355 data_time: 0.145499 memory: 14267 loss_kpt: 0.000728 acc_pose: 0.769133 loss: 0.000728 2022/09/23 02:56:05 - mmengine - INFO - Epoch(train) [36][200/293] lr: 5.000000e-04 eta: 13:38:17 time: 1.090464 data_time: 0.132788 memory: 14267 loss_kpt: 0.000730 acc_pose: 0.773415 loss: 0.000730 2022/09/23 02:57:02 - mmengine - INFO - Epoch(train) [36][250/293] lr: 5.000000e-04 eta: 13:38:11 time: 1.133066 data_time: 0.156354 memory: 14267 loss_kpt: 0.000730 acc_pose: 0.774944 loss: 0.000730 2022/09/23 02:57:49 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 02:58:46 - mmengine - INFO - Epoch(train) [37][50/293] lr: 5.000000e-04 eta: 13:34:06 time: 1.142566 data_time: 0.175151 memory: 14267 loss_kpt: 0.000730 acc_pose: 0.772768 loss: 0.000730 2022/09/23 02:59:43 - mmengine - INFO - Epoch(train) [37][100/293] lr: 5.000000e-04 eta: 13:34:00 time: 1.134780 data_time: 0.135061 memory: 14267 loss_kpt: 0.000733 acc_pose: 0.740268 loss: 0.000733 2022/09/23 03:00:39 - mmengine - INFO - Epoch(train) [37][150/293] lr: 5.000000e-04 eta: 13:33:51 time: 1.123867 data_time: 0.133906 memory: 14267 loss_kpt: 0.000722 acc_pose: 0.790328 loss: 0.000722 2022/09/23 03:01:36 - mmengine - INFO - Epoch(train) [37][200/293] lr: 5.000000e-04 eta: 13:33:48 time: 1.149790 data_time: 0.130499 memory: 14267 loss_kpt: 0.000738 acc_pose: 0.748215 loss: 0.000738 2022/09/23 03:02:33 - mmengine - INFO - Epoch(train) [37][250/293] lr: 5.000000e-04 eta: 13:33:41 time: 1.137612 data_time: 0.152165 memory: 14267 loss_kpt: 0.000744 acc_pose: 0.778085 loss: 0.000744 2022/09/23 03:03:22 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 03:04:20 - mmengine - INFO - Epoch(train) [38][50/293] lr: 5.000000e-04 eta: 13:29:48 time: 1.170295 data_time: 0.154153 memory: 14267 loss_kpt: 0.000725 acc_pose: 0.747262 loss: 0.000725 2022/09/23 03:05:16 - mmengine - INFO - Epoch(train) [38][100/293] lr: 5.000000e-04 eta: 13:29:35 time: 1.111627 data_time: 0.127572 memory: 14267 loss_kpt: 0.000724 acc_pose: 0.812163 loss: 0.000724 2022/09/23 03:06:11 - mmengine - INFO - Epoch(train) [38][150/293] lr: 5.000000e-04 eta: 13:29:18 time: 1.096289 data_time: 0.149602 memory: 14267 loss_kpt: 0.000738 acc_pose: 0.780805 loss: 0.000738 2022/09/23 03:06:21 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 03:07:07 - mmengine - INFO - Epoch(train) [38][200/293] lr: 5.000000e-04 eta: 13:29:08 time: 1.129029 data_time: 0.142499 memory: 14267 loss_kpt: 0.000722 acc_pose: 0.804788 loss: 0.000722 2022/09/23 03:08:04 - mmengine - INFO - Epoch(train) [38][250/293] lr: 5.000000e-04 eta: 13:28:59 time: 1.129825 data_time: 0.141047 memory: 14267 loss_kpt: 0.000736 acc_pose: 0.785097 loss: 0.000736 2022/09/23 03:08:53 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 03:09:51 - mmengine - INFO - Epoch(train) [39][50/293] lr: 5.000000e-04 eta: 13:25:07 time: 1.159151 data_time: 0.169542 memory: 14267 loss_kpt: 0.000705 acc_pose: 0.759435 loss: 0.000705 2022/09/23 03:10:47 - mmengine - INFO - Epoch(train) [39][100/293] lr: 5.000000e-04 eta: 13:24:57 time: 1.128322 data_time: 0.127740 memory: 14267 loss_kpt: 0.000715 acc_pose: 0.763680 loss: 0.000715 2022/09/23 03:11:44 - mmengine - INFO - Epoch(train) [39][150/293] lr: 5.000000e-04 eta: 13:24:49 time: 1.140904 data_time: 0.139374 memory: 14267 loss_kpt: 0.000734 acc_pose: 0.800037 loss: 0.000734 2022/09/23 03:12:40 - mmengine - INFO - Epoch(train) [39][200/293] lr: 5.000000e-04 eta: 13:24:38 time: 1.126873 data_time: 0.151831 memory: 14267 loss_kpt: 0.000721 acc_pose: 0.747638 loss: 0.000721 2022/09/23 03:13:36 - mmengine - INFO - Epoch(train) [39][250/293] lr: 5.000000e-04 eta: 13:24:24 time: 1.118630 data_time: 0.128842 memory: 14267 loss_kpt: 0.000738 acc_pose: 0.787150 loss: 0.000738 2022/09/23 03:14:25 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 03:15:21 - mmengine - INFO - Epoch(train) [40][50/293] lr: 5.000000e-04 eta: 13:20:28 time: 1.116642 data_time: 0.158246 memory: 14267 loss_kpt: 0.000728 acc_pose: 0.795836 loss: 0.000728 2022/09/23 03:16:16 - mmengine - INFO - Epoch(train) [40][100/293] lr: 5.000000e-04 eta: 13:20:13 time: 1.113215 data_time: 0.142560 memory: 14267 loss_kpt: 0.000740 acc_pose: 0.807859 loss: 0.000740 2022/09/23 03:17:13 - mmengine - INFO - Epoch(train) [40][150/293] lr: 5.000000e-04 eta: 13:20:02 time: 1.128819 data_time: 0.140009 memory: 14267 loss_kpt: 0.000731 acc_pose: 0.755555 loss: 0.000731 2022/09/23 03:18:08 - mmengine - INFO - Epoch(train) [40][200/293] lr: 5.000000e-04 eta: 13:19:44 time: 1.102982 data_time: 0.141873 memory: 14267 loss_kpt: 0.000716 acc_pose: 0.788780 loss: 0.000716 2022/09/23 03:19:05 - mmengine - INFO - Epoch(train) [40][250/293] lr: 5.000000e-04 eta: 13:19:33 time: 1.136867 data_time: 0.156566 memory: 14267 loss_kpt: 0.000720 acc_pose: 0.819253 loss: 0.000720 2022/09/23 03:19:52 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 03:19:52 - mmengine - INFO - Saving checkpoint at 40 epochs 2022/09/23 03:20:23 - mmengine - INFO - Epoch(val) [40][50/407] eta: 0:02:43 time: 0.458966 data_time: 0.109664 memory: 14267 2022/09/23 03:20:45 - mmengine - INFO - Epoch(val) [40][100/407] eta: 0:02:14 time: 0.437154 data_time: 0.089361 memory: 1464 2022/09/23 03:21:07 - mmengine - INFO - Epoch(val) [40][150/407] eta: 0:01:51 time: 0.433673 data_time: 0.099639 memory: 1464 2022/09/23 03:21:28 - mmengine - INFO - Epoch(val) [40][200/407] eta: 0:01:28 time: 0.427648 data_time: 0.066911 memory: 1464 2022/09/23 03:21:50 - mmengine - INFO - Epoch(val) [40][250/407] eta: 0:01:07 time: 0.432900 data_time: 0.069540 memory: 1464 2022/09/23 03:22:12 - mmengine - INFO - Epoch(val) [40][300/407] eta: 0:00:45 time: 0.429758 data_time: 0.059102 memory: 1464 2022/09/23 03:22:34 - mmengine - INFO - Epoch(val) [40][350/407] eta: 0:00:25 time: 0.447314 data_time: 0.119929 memory: 1464 2022/09/23 03:22:53 - mmengine - INFO - Epoch(val) [40][400/407] eta: 0:00:02 time: 0.377323 data_time: 0.066587 memory: 1464 2022/09/23 03:23:31 - mmengine - INFO - Evaluating CocoMetric... 2022/09/23 03:23:45 - mmengine - INFO - Epoch(val) [40][407/407] coco/AP: 0.683838 coco/AP .5: 0.880968 coco/AP .75: 0.752925 coco/AP (M): 0.638031 coco/AP (L): 0.759516 coco/AR: 0.738933 coco/AR .5: 0.919238 coco/AR .75: 0.802739 coco/AR (M): 0.687135 coco/AR (L): 0.812449 2022/09/23 03:23:45 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220922/res50_384_2/best_coco/AP_epoch_30.pth is removed 2022/09/23 03:23:48 - mmengine - INFO - The best checkpoint with 0.6838 coco/AP at 40 epoch is saved to best_coco/AP_epoch_40.pth. 2022/09/23 03:24:45 - mmengine - INFO - Epoch(train) [41][50/293] lr: 5.000000e-04 eta: 13:15:43 time: 1.121453 data_time: 0.141910 memory: 14267 loss_kpt: 0.000722 acc_pose: 0.760040 loss: 0.000722 2022/09/23 03:25:40 - mmengine - INFO - Epoch(train) [41][100/293] lr: 5.000000e-04 eta: 13:15:26 time: 1.110237 data_time: 0.151033 memory: 14267 loss_kpt: 0.000725 acc_pose: 0.728568 loss: 0.000725 2022/09/23 03:26:38 - mmengine - INFO - Epoch(train) [41][150/293] lr: 5.000000e-04 eta: 13:15:19 time: 1.154893 data_time: 0.137171 memory: 14267 loss_kpt: 0.000727 acc_pose: 0.820601 loss: 0.000727 2022/09/23 03:27:33 - mmengine - INFO - Epoch(train) [41][200/293] lr: 5.000000e-04 eta: 13:15:02 time: 1.111794 data_time: 0.149029 memory: 14267 loss_kpt: 0.000708 acc_pose: 0.756076 loss: 0.000708 2022/09/23 03:28:30 - mmengine - INFO - Epoch(train) [41][250/293] lr: 5.000000e-04 eta: 13:14:52 time: 1.141427 data_time: 0.144422 memory: 14267 loss_kpt: 0.000719 acc_pose: 0.733187 loss: 0.000719 2022/09/23 03:29:04 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 03:29:18 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 03:30:16 - mmengine - INFO - Epoch(train) [42][50/293] lr: 5.000000e-04 eta: 13:11:11 time: 1.148926 data_time: 0.183097 memory: 14267 loss_kpt: 0.000726 acc_pose: 0.742199 loss: 0.000726 2022/09/23 03:31:12 - mmengine - INFO - Epoch(train) [42][100/293] lr: 5.000000e-04 eta: 13:10:58 time: 1.134260 data_time: 0.136349 memory: 14267 loss_kpt: 0.000708 acc_pose: 0.780561 loss: 0.000708 2022/09/23 03:32:08 - mmengine - INFO - Epoch(train) [42][150/293] lr: 5.000000e-04 eta: 13:10:40 time: 1.107996 data_time: 0.123825 memory: 14267 loss_kpt: 0.000707 acc_pose: 0.729462 loss: 0.000707 2022/09/23 03:33:04 - mmengine - INFO - Epoch(train) [42][200/293] lr: 5.000000e-04 eta: 13:10:23 time: 1.114352 data_time: 0.144124 memory: 14267 loss_kpt: 0.000713 acc_pose: 0.795867 loss: 0.000713 2022/09/23 03:33:59 - mmengine - INFO - Epoch(train) [42][250/293] lr: 5.000000e-04 eta: 13:10:05 time: 1.112006 data_time: 0.147894 memory: 14267 loss_kpt: 0.000725 acc_pose: 0.784316 loss: 0.000725 2022/09/23 03:34:45 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 03:35:42 - mmengine - INFO - Epoch(train) [43][50/293] lr: 5.000000e-04 eta: 13:06:26 time: 1.139287 data_time: 0.156845 memory: 14267 loss_kpt: 0.000715 acc_pose: 0.786332 loss: 0.000715 2022/09/23 03:36:38 - mmengine - INFO - Epoch(train) [43][100/293] lr: 5.000000e-04 eta: 13:06:09 time: 1.113195 data_time: 0.147144 memory: 14267 loss_kpt: 0.000718 acc_pose: 0.782440 loss: 0.000718 2022/09/23 03:37:33 - mmengine - INFO - Epoch(train) [43][150/293] lr: 5.000000e-04 eta: 13:05:51 time: 1.111547 data_time: 0.135992 memory: 14267 loss_kpt: 0.000716 acc_pose: 0.776268 loss: 0.000716 2022/09/23 03:38:29 - mmengine - INFO - Epoch(train) [43][200/293] lr: 5.000000e-04 eta: 13:05:35 time: 1.124308 data_time: 0.152610 memory: 14267 loss_kpt: 0.000721 acc_pose: 0.777944 loss: 0.000721 2022/09/23 03:39:26 - mmengine - INFO - Epoch(train) [43][250/293] lr: 5.000000e-04 eta: 13:05:20 time: 1.132829 data_time: 0.129140 memory: 14267 loss_kpt: 0.000705 acc_pose: 0.777148 loss: 0.000705 2022/09/23 03:40:14 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 03:41:12 - mmengine - INFO - Epoch(train) [44][50/293] lr: 5.000000e-04 eta: 13:01:46 time: 1.142920 data_time: 0.170315 memory: 14267 loss_kpt: 0.000713 acc_pose: 0.832815 loss: 0.000713 2022/09/23 03:42:07 - mmengine - INFO - Epoch(train) [44][100/293] lr: 5.000000e-04 eta: 13:01:26 time: 1.106923 data_time: 0.135191 memory: 14267 loss_kpt: 0.000718 acc_pose: 0.826597 loss: 0.000718 2022/09/23 03:43:03 - mmengine - INFO - Epoch(train) [44][150/293] lr: 5.000000e-04 eta: 13:01:08 time: 1.116981 data_time: 0.124931 memory: 14267 loss_kpt: 0.000699 acc_pose: 0.807869 loss: 0.000699 2022/09/23 03:43:56 - mmengine - INFO - Epoch(train) [44][200/293] lr: 5.000000e-04 eta: 13:00:41 time: 1.070829 data_time: 0.131136 memory: 14267 loss_kpt: 0.000727 acc_pose: 0.827408 loss: 0.000727 2022/09/23 03:44:52 - mmengine - INFO - Epoch(train) [44][250/293] lr: 5.000000e-04 eta: 13:00:20 time: 1.105382 data_time: 0.130195 memory: 14267 loss_kpt: 0.000728 acc_pose: 0.833542 loss: 0.000728 2022/09/23 03:45:38 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 03:46:35 - mmengine - INFO - Epoch(train) [45][50/293] lr: 5.000000e-04 eta: 12:56:49 time: 1.139527 data_time: 0.151792 memory: 14267 loss_kpt: 0.000715 acc_pose: 0.788980 loss: 0.000715 2022/09/23 03:47:32 - mmengine - INFO - Epoch(train) [45][100/293] lr: 5.000000e-04 eta: 12:56:35 time: 1.142663 data_time: 0.139835 memory: 14267 loss_kpt: 0.000713 acc_pose: 0.778683 loss: 0.000713 2022/09/23 03:47:41 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 03:48:28 - mmengine - INFO - Epoch(train) [45][150/293] lr: 5.000000e-04 eta: 12:56:17 time: 1.123431 data_time: 0.145286 memory: 14267 loss_kpt: 0.000714 acc_pose: 0.796052 loss: 0.000714 2022/09/23 03:49:26 - mmengine - INFO - Epoch(train) [45][200/293] lr: 5.000000e-04 eta: 12:56:03 time: 1.144838 data_time: 0.127989 memory: 14267 loss_kpt: 0.000722 acc_pose: 0.819122 loss: 0.000722 2022/09/23 03:50:21 - mmengine - INFO - Epoch(train) [45][250/293] lr: 5.000000e-04 eta: 12:55:43 time: 1.114204 data_time: 0.142027 memory: 14267 loss_kpt: 0.000703 acc_pose: 0.840579 loss: 0.000703 2022/09/23 03:51:10 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 03:52:07 - mmengine - INFO - Epoch(train) [46][50/293] lr: 5.000000e-04 eta: 12:52:17 time: 1.148769 data_time: 0.146106 memory: 14267 loss_kpt: 0.000705 acc_pose: 0.748449 loss: 0.000705 2022/09/23 03:53:03 - mmengine - INFO - Epoch(train) [46][100/293] lr: 5.000000e-04 eta: 12:51:59 time: 1.122957 data_time: 0.132731 memory: 14267 loss_kpt: 0.000706 acc_pose: 0.800751 loss: 0.000706 2022/09/23 03:53:57 - mmengine - INFO - Epoch(train) [46][150/293] lr: 5.000000e-04 eta: 12:51:30 time: 1.063816 data_time: 0.126753 memory: 14267 loss_kpt: 0.000707 acc_pose: 0.790650 loss: 0.000707 2022/09/23 03:54:51 - mmengine - INFO - Epoch(train) [46][200/293] lr: 5.000000e-04 eta: 12:51:06 time: 1.095789 data_time: 0.138908 memory: 14267 loss_kpt: 0.000715 acc_pose: 0.739942 loss: 0.000715 2022/09/23 03:55:47 - mmengine - INFO - Epoch(train) [46][250/293] lr: 5.000000e-04 eta: 12:50:44 time: 1.106158 data_time: 0.123591 memory: 14267 loss_kpt: 0.000701 acc_pose: 0.833606 loss: 0.000701 2022/09/23 03:56:36 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 03:57:34 - mmengine - INFO - Epoch(train) [47][50/293] lr: 5.000000e-04 eta: 12:47:23 time: 1.161080 data_time: 0.155407 memory: 14267 loss_kpt: 0.000702 acc_pose: 0.794547 loss: 0.000702 2022/09/23 03:58:31 - mmengine - INFO - Epoch(train) [47][100/293] lr: 5.000000e-04 eta: 12:47:07 time: 1.141381 data_time: 0.128712 memory: 14267 loss_kpt: 0.000724 acc_pose: 0.775800 loss: 0.000724 2022/09/23 03:59:26 - mmengine - INFO - Epoch(train) [47][150/293] lr: 5.000000e-04 eta: 12:46:44 time: 1.098366 data_time: 0.128033 memory: 14267 loss_kpt: 0.000707 acc_pose: 0.850961 loss: 0.000707 2022/09/23 04:00:23 - mmengine - INFO - Epoch(train) [47][200/293] lr: 5.000000e-04 eta: 12:46:28 time: 1.146798 data_time: 0.126503 memory: 14267 loss_kpt: 0.000704 acc_pose: 0.849952 loss: 0.000704 2022/09/23 04:01:19 - mmengine - INFO - Epoch(train) [47][250/293] lr: 5.000000e-04 eta: 12:46:06 time: 1.111100 data_time: 0.132969 memory: 14267 loss_kpt: 0.000729 acc_pose: 0.772813 loss: 0.000729 2022/09/23 04:02:08 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 04:03:02 - mmengine - INFO - Epoch(train) [48][50/293] lr: 5.000000e-04 eta: 12:42:34 time: 1.078631 data_time: 0.147367 memory: 14267 loss_kpt: 0.000708 acc_pose: 0.801607 loss: 0.000708 2022/09/23 04:03:58 - mmengine - INFO - Epoch(train) [48][100/293] lr: 5.000000e-04 eta: 12:42:14 time: 1.116880 data_time: 0.126912 memory: 14267 loss_kpt: 0.000702 acc_pose: 0.793337 loss: 0.000702 2022/09/23 04:04:56 - mmengine - INFO - Epoch(train) [48][150/293] lr: 5.000000e-04 eta: 12:41:59 time: 1.156691 data_time: 0.141921 memory: 14267 loss_kpt: 0.000716 acc_pose: 0.747051 loss: 0.000716 2022/09/23 04:05:54 - mmengine - INFO - Epoch(train) [48][200/293] lr: 5.000000e-04 eta: 12:41:45 time: 1.157047 data_time: 0.123799 memory: 14267 loss_kpt: 0.000704 acc_pose: 0.752049 loss: 0.000704 2022/09/23 04:06:28 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 04:06:51 - mmengine - INFO - Epoch(train) [48][250/293] lr: 5.000000e-04 eta: 12:41:28 time: 1.147599 data_time: 0.122768 memory: 14267 loss_kpt: 0.000700 acc_pose: 0.791789 loss: 0.000700 2022/09/23 04:07:38 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 04:08:34 - mmengine - INFO - Epoch(train) [49][50/293] lr: 5.000000e-04 eta: 12:38:09 time: 1.132733 data_time: 0.154373 memory: 14267 loss_kpt: 0.000693 acc_pose: 0.828158 loss: 0.000693 2022/09/23 04:09:32 - mmengine - INFO - Epoch(train) [49][100/293] lr: 5.000000e-04 eta: 12:37:52 time: 1.144611 data_time: 0.130262 memory: 14267 loss_kpt: 0.000699 acc_pose: 0.767707 loss: 0.000699 2022/09/23 04:10:30 - mmengine - INFO - Epoch(train) [49][150/293] lr: 5.000000e-04 eta: 12:37:38 time: 1.167838 data_time: 0.130750 memory: 14267 loss_kpt: 0.000691 acc_pose: 0.813075 loss: 0.000691 2022/09/23 04:11:27 - mmengine - INFO - Epoch(train) [49][200/293] lr: 5.000000e-04 eta: 12:37:18 time: 1.127824 data_time: 0.126408 memory: 14267 loss_kpt: 0.000713 acc_pose: 0.800979 loss: 0.000713 2022/09/23 04:12:21 - mmengine - INFO - Epoch(train) [49][250/293] lr: 5.000000e-04 eta: 12:36:52 time: 1.096403 data_time: 0.119800 memory: 14267 loss_kpt: 0.000699 acc_pose: 0.794155 loss: 0.000699 2022/09/23 04:13:08 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 04:14:06 - mmengine - INFO - Epoch(train) [50][50/293] lr: 5.000000e-04 eta: 12:33:39 time: 1.153341 data_time: 0.152849 memory: 14267 loss_kpt: 0.000698 acc_pose: 0.795868 loss: 0.000698 2022/09/23 04:15:02 - mmengine - INFO - Epoch(train) [50][100/293] lr: 5.000000e-04 eta: 12:33:18 time: 1.127333 data_time: 0.143315 memory: 14267 loss_kpt: 0.000716 acc_pose: 0.786324 loss: 0.000716 2022/09/23 04:15:59 - mmengine - INFO - Epoch(train) [50][150/293] lr: 5.000000e-04 eta: 12:32:59 time: 1.141068 data_time: 0.127237 memory: 14267 loss_kpt: 0.000701 acc_pose: 0.789912 loss: 0.000701 2022/09/23 04:16:56 - mmengine - INFO - Epoch(train) [50][200/293] lr: 5.000000e-04 eta: 12:32:40 time: 1.135967 data_time: 0.143943 memory: 14267 loss_kpt: 0.000709 acc_pose: 0.766407 loss: 0.000709 2022/09/23 04:17:53 - mmengine - INFO - Epoch(train) [50][250/293] lr: 5.000000e-04 eta: 12:32:19 time: 1.134563 data_time: 0.119416 memory: 14267 loss_kpt: 0.000689 acc_pose: 0.812397 loss: 0.000689 2022/09/23 04:18:40 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 04:18:40 - mmengine - INFO - Saving checkpoint at 50 epochs 2022/09/23 04:19:11 - mmengine - INFO - Epoch(val) [50][50/407] eta: 0:02:49 time: 0.473804 data_time: 0.095732 memory: 14267 2022/09/23 04:19:32 - mmengine - INFO - Epoch(val) [50][100/407] eta: 0:02:10 time: 0.423730 data_time: 0.046787 memory: 1464 2022/09/23 04:19:54 - mmengine - INFO - Epoch(val) [50][150/407] eta: 0:01:50 time: 0.429563 data_time: 0.051164 memory: 1464 2022/09/23 04:20:16 - mmengine - INFO - Epoch(val) [50][200/407] eta: 0:01:30 time: 0.437214 data_time: 0.043742 memory: 1464 2022/09/23 04:20:36 - mmengine - INFO - Epoch(val) [50][250/407] eta: 0:01:04 time: 0.412559 data_time: 0.078673 memory: 1464 2022/09/23 04:20:57 - mmengine - INFO - Epoch(val) [50][300/407] eta: 0:00:44 time: 0.418917 data_time: 0.080590 memory: 1464 2022/09/23 04:21:19 - mmengine - INFO - Epoch(val) [50][350/407] eta: 0:00:24 time: 0.435336 data_time: 0.125639 memory: 1464 2022/09/23 04:21:38 - mmengine - INFO - Epoch(val) [50][400/407] eta: 0:00:02 time: 0.370498 data_time: 0.072007 memory: 1464 2022/09/23 04:22:14 - mmengine - INFO - Evaluating CocoMetric... 2022/09/23 04:22:27 - mmengine - INFO - Epoch(val) [50][407/407] coco/AP: 0.683574 coco/AP .5: 0.875945 coco/AP .75: 0.751206 coco/AP (M): 0.637160 coco/AP (L): 0.761956 coco/AR: 0.740302 coco/AR .5: 0.915932 coco/AR .75: 0.803526 coco/AR (M): 0.687572 coco/AR (L): 0.814790 2022/09/23 04:23:26 - mmengine - INFO - Epoch(train) [51][50/293] lr: 5.000000e-04 eta: 12:29:12 time: 1.173155 data_time: 0.145262 memory: 14267 loss_kpt: 0.000689 acc_pose: 0.835124 loss: 0.000689 2022/09/23 04:24:22 - mmengine - INFO - Epoch(train) [51][100/293] lr: 5.000000e-04 eta: 12:28:50 time: 1.125465 data_time: 0.134240 memory: 14267 loss_kpt: 0.000710 acc_pose: 0.789803 loss: 0.000710 2022/09/23 04:25:19 - mmengine - INFO - Epoch(train) [51][150/293] lr: 5.000000e-04 eta: 12:28:31 time: 1.143726 data_time: 0.134961 memory: 14267 loss_kpt: 0.000699 acc_pose: 0.804140 loss: 0.000699 2022/09/23 04:26:16 - mmengine - INFO - Epoch(train) [51][200/293] lr: 5.000000e-04 eta: 12:28:11 time: 1.139697 data_time: 0.135370 memory: 14267 loss_kpt: 0.000704 acc_pose: 0.823227 loss: 0.000704 2022/09/23 04:27:15 - mmengine - INFO - Epoch(train) [51][250/293] lr: 5.000000e-04 eta: 12:27:56 time: 1.173898 data_time: 0.155023 memory: 14267 loss_kpt: 0.000695 acc_pose: 0.778487 loss: 0.000695 2022/09/23 04:28:03 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 04:29:02 - mmengine - INFO - Epoch(train) [52][50/293] lr: 5.000000e-04 eta: 12:24:52 time: 1.183157 data_time: 0.156533 memory: 14267 loss_kpt: 0.000701 acc_pose: 0.810882 loss: 0.000701 2022/09/23 04:29:09 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 04:29:56 - mmengine - INFO - Epoch(train) [52][100/293] lr: 5.000000e-04 eta: 12:24:23 time: 1.083077 data_time: 0.127623 memory: 14267 loss_kpt: 0.000686 acc_pose: 0.794626 loss: 0.000686 2022/09/23 04:30:50 - mmengine - INFO - Epoch(train) [52][150/293] lr: 5.000000e-04 eta: 12:23:55 time: 1.089615 data_time: 0.134223 memory: 14267 loss_kpt: 0.000706 acc_pose: 0.810908 loss: 0.000706 2022/09/23 04:31:44 - mmengine - INFO - Epoch(train) [52][200/293] lr: 5.000000e-04 eta: 12:23:25 time: 1.081447 data_time: 0.128383 memory: 14267 loss_kpt: 0.000695 acc_pose: 0.798915 loss: 0.000695 2022/09/23 04:32:41 - mmengine - INFO - Epoch(train) [52][250/293] lr: 5.000000e-04 eta: 12:23:03 time: 1.127922 data_time: 0.128778 memory: 14267 loss_kpt: 0.000701 acc_pose: 0.805278 loss: 0.000701 2022/09/23 04:33:29 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 04:34:27 - mmengine - INFO - Epoch(train) [53][50/293] lr: 5.000000e-04 eta: 12:19:57 time: 1.150269 data_time: 0.142897 memory: 14267 loss_kpt: 0.000692 acc_pose: 0.812176 loss: 0.000692 2022/09/23 04:35:22 - mmengine - INFO - Epoch(train) [53][100/293] lr: 5.000000e-04 eta: 12:19:29 time: 1.096130 data_time: 0.133906 memory: 14267 loss_kpt: 0.000717 acc_pose: 0.800145 loss: 0.000717 2022/09/23 04:36:19 - mmengine - INFO - Epoch(train) [53][150/293] lr: 5.000000e-04 eta: 12:19:08 time: 1.140752 data_time: 0.160555 memory: 14267 loss_kpt: 0.000688 acc_pose: 0.824267 loss: 0.000688 2022/09/23 04:37:14 - mmengine - INFO - Epoch(train) [53][200/293] lr: 5.000000e-04 eta: 12:18:42 time: 1.108960 data_time: 0.123035 memory: 14267 loss_kpt: 0.000710 acc_pose: 0.793486 loss: 0.000710 2022/09/23 04:38:11 - mmengine - INFO - Epoch(train) [53][250/293] lr: 5.000000e-04 eta: 12:18:18 time: 1.124668 data_time: 0.124348 memory: 14267 loss_kpt: 0.000683 acc_pose: 0.822282 loss: 0.000683 2022/09/23 04:38:59 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 04:39:55 - mmengine - INFO - Epoch(train) [54][50/293] lr: 5.000000e-04 eta: 12:15:09 time: 1.115752 data_time: 0.169547 memory: 14267 loss_kpt: 0.000691 acc_pose: 0.823891 loss: 0.000691 2022/09/23 04:40:50 - mmengine - INFO - Epoch(train) [54][100/293] lr: 5.000000e-04 eta: 12:14:42 time: 1.098557 data_time: 0.122146 memory: 14267 loss_kpt: 0.000694 acc_pose: 0.820727 loss: 0.000694 2022/09/23 04:41:45 - mmengine - INFO - Epoch(train) [54][150/293] lr: 5.000000e-04 eta: 12:14:15 time: 1.105551 data_time: 0.128002 memory: 14267 loss_kpt: 0.000692 acc_pose: 0.803134 loss: 0.000692 2022/09/23 04:42:43 - mmengine - INFO - Epoch(train) [54][200/293] lr: 5.000000e-04 eta: 12:13:56 time: 1.162754 data_time: 0.134146 memory: 14267 loss_kpt: 0.000700 acc_pose: 0.767882 loss: 0.000700 2022/09/23 04:43:39 - mmengine - INFO - Epoch(train) [54][250/293] lr: 5.000000e-04 eta: 12:13:31 time: 1.121653 data_time: 0.142626 memory: 14267 loss_kpt: 0.000694 acc_pose: 0.800239 loss: 0.000694 2022/09/23 04:44:27 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 04:45:25 - mmengine - INFO - Epoch(train) [55][50/293] lr: 5.000000e-04 eta: 12:10:31 time: 1.154240 data_time: 0.153243 memory: 14267 loss_kpt: 0.000682 acc_pose: 0.814589 loss: 0.000682 2022/09/23 04:46:20 - mmengine - INFO - Epoch(train) [55][100/293] lr: 5.000000e-04 eta: 12:10:02 time: 1.096035 data_time: 0.130477 memory: 14267 loss_kpt: 0.000684 acc_pose: 0.827156 loss: 0.000684 2022/09/23 04:47:16 - mmengine - INFO - Epoch(train) [55][150/293] lr: 5.000000e-04 eta: 12:09:37 time: 1.119448 data_time: 0.134529 memory: 14267 loss_kpt: 0.000698 acc_pose: 0.794854 loss: 0.000698 2022/09/23 04:47:49 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 04:48:12 - mmengine - INFO - Epoch(train) [55][200/293] lr: 5.000000e-04 eta: 12:09:12 time: 1.122590 data_time: 0.131879 memory: 14267 loss_kpt: 0.000691 acc_pose: 0.785446 loss: 0.000691 2022/09/23 04:49:05 - mmengine - INFO - Epoch(train) [55][250/293] lr: 5.000000e-04 eta: 12:08:38 time: 1.060682 data_time: 0.128340 memory: 14267 loss_kpt: 0.000699 acc_pose: 0.778795 loss: 0.000699 2022/09/23 04:49:53 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 04:50:50 - mmengine - INFO - Epoch(train) [56][50/293] lr: 5.000000e-04 eta: 12:05:38 time: 1.146901 data_time: 0.168399 memory: 14267 loss_kpt: 0.000697 acc_pose: 0.799567 loss: 0.000697 2022/09/23 04:51:47 - mmengine - INFO - Epoch(train) [56][100/293] lr: 5.000000e-04 eta: 12:05:15 time: 1.134851 data_time: 0.138328 memory: 14267 loss_kpt: 0.000710 acc_pose: 0.794876 loss: 0.000710 2022/09/23 04:52:45 - mmengine - INFO - Epoch(train) [56][150/293] lr: 5.000000e-04 eta: 12:04:56 time: 1.170849 data_time: 0.126459 memory: 14267 loss_kpt: 0.000700 acc_pose: 0.749367 loss: 0.000700 2022/09/23 04:53:41 - mmengine - INFO - Epoch(train) [56][200/293] lr: 5.000000e-04 eta: 12:04:30 time: 1.119367 data_time: 0.130636 memory: 14267 loss_kpt: 0.000687 acc_pose: 0.802813 loss: 0.000687 2022/09/23 04:54:38 - mmengine - INFO - Epoch(train) [56][250/293] lr: 5.000000e-04 eta: 12:04:07 time: 1.143000 data_time: 0.135524 memory: 14267 loss_kpt: 0.000690 acc_pose: 0.759492 loss: 0.000690 2022/09/23 04:55:28 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 04:56:26 - mmengine - INFO - Epoch(train) [57][50/293] lr: 5.000000e-04 eta: 12:01:12 time: 1.167143 data_time: 0.167361 memory: 14267 loss_kpt: 0.000702 acc_pose: 0.806529 loss: 0.000702 2022/09/23 04:57:23 - mmengine - INFO - Epoch(train) [57][100/293] lr: 5.000000e-04 eta: 12:00:49 time: 1.139982 data_time: 0.139942 memory: 14267 loss_kpt: 0.000687 acc_pose: 0.766520 loss: 0.000687 2022/09/23 04:58:18 - mmengine - INFO - Epoch(train) [57][150/293] lr: 5.000000e-04 eta: 12:00:18 time: 1.087986 data_time: 0.126202 memory: 14267 loss_kpt: 0.000701 acc_pose: 0.819815 loss: 0.000701 2022/09/23 04:59:14 - mmengine - INFO - Epoch(train) [57][200/293] lr: 5.000000e-04 eta: 11:59:52 time: 1.122606 data_time: 0.140166 memory: 14267 loss_kpt: 0.000699 acc_pose: 0.799923 loss: 0.000699 2022/09/23 05:00:11 - mmengine - INFO - Epoch(train) [57][250/293] lr: 5.000000e-04 eta: 11:59:29 time: 1.146252 data_time: 0.152645 memory: 14267 loss_kpt: 0.000695 acc_pose: 0.776301 loss: 0.000695 2022/09/23 05:00:59 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 05:01:57 - mmengine - INFO - Epoch(train) [58][50/293] lr: 5.000000e-04 eta: 11:56:35 time: 1.163649 data_time: 0.150254 memory: 14267 loss_kpt: 0.000695 acc_pose: 0.751313 loss: 0.000695 2022/09/23 05:02:54 - mmengine - INFO - Epoch(train) [58][100/293] lr: 5.000000e-04 eta: 11:56:11 time: 1.135825 data_time: 0.137239 memory: 14267 loss_kpt: 0.000698 acc_pose: 0.805178 loss: 0.000698 2022/09/23 05:03:51 - mmengine - INFO - Epoch(train) [58][150/293] lr: 5.000000e-04 eta: 11:55:46 time: 1.138020 data_time: 0.141315 memory: 14267 loss_kpt: 0.000688 acc_pose: 0.768940 loss: 0.000688 2022/09/23 05:04:48 - mmengine - INFO - Epoch(train) [58][200/293] lr: 5.000000e-04 eta: 11:55:23 time: 1.148177 data_time: 0.139598 memory: 14267 loss_kpt: 0.000696 acc_pose: 0.810309 loss: 0.000696 2022/09/23 05:05:44 - mmengine - INFO - Epoch(train) [58][250/293] lr: 5.000000e-04 eta: 11:54:56 time: 1.120205 data_time: 0.135455 memory: 14267 loss_kpt: 0.000685 acc_pose: 0.837119 loss: 0.000685 2022/09/23 05:06:31 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 05:06:39 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 05:07:27 - mmengine - INFO - Epoch(train) [59][50/293] lr: 5.000000e-04 eta: 11:51:58 time: 1.115583 data_time: 0.166232 memory: 14267 loss_kpt: 0.000679 acc_pose: 0.808705 loss: 0.000679 2022/09/23 05:08:21 - mmengine - INFO - Epoch(train) [59][100/293] lr: 5.000000e-04 eta: 11:51:28 time: 1.094238 data_time: 0.131085 memory: 14267 loss_kpt: 0.000691 acc_pose: 0.799729 loss: 0.000691 2022/09/23 05:09:18 - mmengine - INFO - Epoch(train) [59][150/293] lr: 5.000000e-04 eta: 11:51:02 time: 1.131939 data_time: 0.134303 memory: 14267 loss_kpt: 0.000684 acc_pose: 0.794210 loss: 0.000684 2022/09/23 05:10:15 - mmengine - INFO - Epoch(train) [59][200/293] lr: 5.000000e-04 eta: 11:50:37 time: 1.139648 data_time: 0.137043 memory: 14267 loss_kpt: 0.000688 acc_pose: 0.822789 loss: 0.000688 2022/09/23 05:11:11 - mmengine - INFO - Epoch(train) [59][250/293] lr: 5.000000e-04 eta: 11:50:10 time: 1.125541 data_time: 0.127212 memory: 14267 loss_kpt: 0.000699 acc_pose: 0.798298 loss: 0.000699 2022/09/23 05:12:01 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 05:12:57 - mmengine - INFO - Epoch(train) [60][50/293] lr: 5.000000e-04 eta: 11:47:15 time: 1.122745 data_time: 0.150908 memory: 14267 loss_kpt: 0.000701 acc_pose: 0.869484 loss: 0.000701 2022/09/23 05:13:51 - mmengine - INFO - Epoch(train) [60][100/293] lr: 5.000000e-04 eta: 11:46:44 time: 1.092648 data_time: 0.130626 memory: 14267 loss_kpt: 0.000693 acc_pose: 0.833990 loss: 0.000693 2022/09/23 05:14:49 - mmengine - INFO - Epoch(train) [60][150/293] lr: 5.000000e-04 eta: 11:46:19 time: 1.143001 data_time: 0.120329 memory: 14267 loss_kpt: 0.000679 acc_pose: 0.826020 loss: 0.000679 2022/09/23 05:15:43 - mmengine - INFO - Epoch(train) [60][200/293] lr: 5.000000e-04 eta: 11:45:48 time: 1.092918 data_time: 0.136257 memory: 14267 loss_kpt: 0.000704 acc_pose: 0.814084 loss: 0.000704 2022/09/23 05:16:38 - mmengine - INFO - Epoch(train) [60][250/293] lr: 5.000000e-04 eta: 11:45:16 time: 1.096279 data_time: 0.135820 memory: 14267 loss_kpt: 0.000697 acc_pose: 0.780877 loss: 0.000697 2022/09/23 05:17:24 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 05:17:25 - mmengine - INFO - Saving checkpoint at 60 epochs 2022/09/23 05:17:56 - mmengine - INFO - Epoch(val) [60][50/407] eta: 0:02:45 time: 0.462906 data_time: 0.078383 memory: 14267 2022/09/23 05:18:17 - mmengine - INFO - Epoch(val) [60][100/407] eta: 0:02:08 time: 0.418010 data_time: 0.065400 memory: 1464 2022/09/23 05:18:40 - mmengine - INFO - Epoch(val) [60][150/407] eta: 0:01:54 time: 0.444233 data_time: 0.072561 memory: 1464 2022/09/23 05:19:01 - mmengine - INFO - Epoch(val) [60][200/407] eta: 0:01:28 time: 0.427144 data_time: 0.062852 memory: 1464 2022/09/23 05:19:23 - mmengine - INFO - Epoch(val) [60][250/407] eta: 0:01:08 time: 0.436882 data_time: 0.073422 memory: 1464 2022/09/23 05:19:45 - mmengine - INFO - Epoch(val) [60][300/407] eta: 0:00:46 time: 0.434710 data_time: 0.045358 memory: 1464 2022/09/23 05:20:06 - mmengine - INFO - Epoch(val) [60][350/407] eta: 0:00:24 time: 0.433033 data_time: 0.071054 memory: 1464 2022/09/23 05:20:22 - mmengine - INFO - Epoch(val) [60][400/407] eta: 0:00:02 time: 0.323887 data_time: 0.038473 memory: 1464 2022/09/23 05:20:59 - mmengine - INFO - Evaluating CocoMetric... 2022/09/23 05:21:13 - mmengine - INFO - Epoch(val) [60][407/407] coco/AP: 0.683537 coco/AP .5: 0.876200 coco/AP .75: 0.749067 coco/AP (M): 0.636271 coco/AP (L): 0.761926 coco/AR: 0.739059 coco/AR .5: 0.914358 coco/AR .75: 0.801008 coco/AR (M): 0.685687 coco/AR (L): 0.814530 2022/09/23 05:22:12 - mmengine - INFO - Epoch(train) [61][50/293] lr: 5.000000e-04 eta: 11:42:31 time: 1.181449 data_time: 0.140028 memory: 14267 loss_kpt: 0.000687 acc_pose: 0.804486 loss: 0.000687 2022/09/23 05:23:08 - mmengine - INFO - Epoch(train) [61][100/293] lr: 5.000000e-04 eta: 11:42:04 time: 1.123727 data_time: 0.132073 memory: 14267 loss_kpt: 0.000706 acc_pose: 0.819821 loss: 0.000706 2022/09/23 05:24:05 - mmengine - INFO - Epoch(train) [61][150/293] lr: 5.000000e-04 eta: 11:41:38 time: 1.139590 data_time: 0.129284 memory: 14267 loss_kpt: 0.000676 acc_pose: 0.860029 loss: 0.000676 2022/09/23 05:25:01 - mmengine - INFO - Epoch(train) [61][200/293] lr: 5.000000e-04 eta: 11:41:08 time: 1.107303 data_time: 0.124248 memory: 14267 loss_kpt: 0.000693 acc_pose: 0.779937 loss: 0.000693 2022/09/23 05:25:53 - mmengine - INFO - Epoch(train) [61][250/293] lr: 5.000000e-04 eta: 11:40:30 time: 1.051601 data_time: 0.127492 memory: 14267 loss_kpt: 0.000682 acc_pose: 0.805779 loss: 0.000682 2022/09/23 05:26:41 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 05:27:38 - mmengine - INFO - Epoch(train) [62][50/293] lr: 5.000000e-04 eta: 11:37:43 time: 1.148385 data_time: 0.158839 memory: 14267 loss_kpt: 0.000673 acc_pose: 0.773412 loss: 0.000673 2022/09/23 05:28:37 - mmengine - INFO - Epoch(train) [62][100/293] lr: 5.000000e-04 eta: 11:37:21 time: 1.174670 data_time: 0.144522 memory: 14267 loss_kpt: 0.000676 acc_pose: 0.759641 loss: 0.000676 2022/09/23 05:29:08 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 05:29:35 - mmengine - INFO - Epoch(train) [62][150/293] lr: 5.000000e-04 eta: 11:36:58 time: 1.163344 data_time: 0.132814 memory: 14267 loss_kpt: 0.000677 acc_pose: 0.849015 loss: 0.000677 2022/09/23 05:30:33 - mmengine - INFO - Epoch(train) [62][200/293] lr: 5.000000e-04 eta: 11:36:33 time: 1.153433 data_time: 0.127591 memory: 14267 loss_kpt: 0.000687 acc_pose: 0.822869 loss: 0.000687 2022/09/23 05:31:32 - mmengine - INFO - Epoch(train) [62][250/293] lr: 5.000000e-04 eta: 11:36:11 time: 1.183364 data_time: 0.136404 memory: 14267 loss_kpt: 0.000692 acc_pose: 0.809196 loss: 0.000692 2022/09/23 05:32:19 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 05:33:17 - mmengine - INFO - Epoch(train) [63][50/293] lr: 5.000000e-04 eta: 11:33:28 time: 1.167210 data_time: 0.155440 memory: 14267 loss_kpt: 0.000676 acc_pose: 0.828384 loss: 0.000676 2022/09/23 05:34:13 - mmengine - INFO - Epoch(train) [63][100/293] lr: 5.000000e-04 eta: 11:32:58 time: 1.114960 data_time: 0.120125 memory: 14267 loss_kpt: 0.000685 acc_pose: 0.808172 loss: 0.000685 2022/09/23 05:35:06 - mmengine - INFO - Epoch(train) [63][150/293] lr: 5.000000e-04 eta: 11:32:22 time: 1.066330 data_time: 0.120237 memory: 14267 loss_kpt: 0.000685 acc_pose: 0.785980 loss: 0.000685 2022/09/23 05:36:06 - mmengine - INFO - Epoch(train) [63][200/293] lr: 5.000000e-04 eta: 11:32:01 time: 1.186224 data_time: 0.135499 memory: 14267 loss_kpt: 0.000683 acc_pose: 0.797790 loss: 0.000683 2022/09/23 05:37:02 - mmengine - INFO - Epoch(train) [63][250/293] lr: 5.000000e-04 eta: 11:31:31 time: 1.119194 data_time: 0.124966 memory: 14267 loss_kpt: 0.000688 acc_pose: 0.790213 loss: 0.000688 2022/09/23 05:37:50 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 05:38:50 - mmengine - INFO - Epoch(train) [64][50/293] lr: 5.000000e-04 eta: 11:28:51 time: 1.187286 data_time: 0.158323 memory: 14267 loss_kpt: 0.000674 acc_pose: 0.806548 loss: 0.000674 2022/09/23 05:39:45 - mmengine - INFO - Epoch(train) [64][100/293] lr: 5.000000e-04 eta: 11:28:20 time: 1.109473 data_time: 0.120635 memory: 14267 loss_kpt: 0.000692 acc_pose: 0.812256 loss: 0.000692 2022/09/23 05:40:43 - mmengine - INFO - Epoch(train) [64][150/293] lr: 5.000000e-04 eta: 11:27:54 time: 1.149437 data_time: 0.128608 memory: 14267 loss_kpt: 0.000686 acc_pose: 0.799787 loss: 0.000686 2022/09/23 05:41:42 - mmengine - INFO - Epoch(train) [64][200/293] lr: 5.000000e-04 eta: 11:27:31 time: 1.177695 data_time: 0.134359 memory: 14267 loss_kpt: 0.000678 acc_pose: 0.813920 loss: 0.000678 2022/09/23 05:42:37 - mmengine - INFO - Epoch(train) [64][250/293] lr: 5.000000e-04 eta: 11:27:00 time: 1.111971 data_time: 0.128263 memory: 14267 loss_kpt: 0.000675 acc_pose: 0.802948 loss: 0.000675 2022/09/23 05:43:25 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 05:44:21 - mmengine - INFO - Epoch(train) [65][50/293] lr: 5.000000e-04 eta: 11:24:15 time: 1.127358 data_time: 0.152406 memory: 14267 loss_kpt: 0.000674 acc_pose: 0.840916 loss: 0.000674 2022/09/23 05:45:19 - mmengine - INFO - Epoch(train) [65][100/293] lr: 5.000000e-04 eta: 11:23:49 time: 1.151490 data_time: 0.136116 memory: 14267 loss_kpt: 0.000693 acc_pose: 0.806309 loss: 0.000693 2022/09/23 05:46:17 - mmengine - INFO - Epoch(train) [65][150/293] lr: 5.000000e-04 eta: 11:23:24 time: 1.165833 data_time: 0.126248 memory: 14267 loss_kpt: 0.000696 acc_pose: 0.769117 loss: 0.000696 2022/09/23 05:47:16 - mmengine - INFO - Epoch(train) [65][200/293] lr: 5.000000e-04 eta: 11:23:01 time: 1.186437 data_time: 0.126987 memory: 14267 loss_kpt: 0.000671 acc_pose: 0.809658 loss: 0.000671 2022/09/23 05:48:13 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 05:48:15 - mmengine - INFO - Epoch(train) [65][250/293] lr: 5.000000e-04 eta: 11:22:36 time: 1.175286 data_time: 0.137257 memory: 14267 loss_kpt: 0.000679 acc_pose: 0.808356 loss: 0.000679 2022/09/23 05:49:04 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 05:50:04 - mmengine - INFO - Epoch(train) [66][50/293] lr: 5.000000e-04 eta: 11:20:00 time: 1.192059 data_time: 0.158482 memory: 14267 loss_kpt: 0.000682 acc_pose: 0.777805 loss: 0.000682 2022/09/23 05:51:02 - mmengine - INFO - Epoch(train) [66][100/293] lr: 5.000000e-04 eta: 11:19:33 time: 1.153858 data_time: 0.142783 memory: 14267 loss_kpt: 0.000676 acc_pose: 0.841107 loss: 0.000676 2022/09/23 05:51:55 - mmengine - INFO - Epoch(train) [66][150/293] lr: 5.000000e-04 eta: 11:18:56 time: 1.059465 data_time: 0.128560 memory: 14267 loss_kpt: 0.000679 acc_pose: 0.824149 loss: 0.000679 2022/09/23 05:52:52 - mmengine - INFO - Epoch(train) [66][200/293] lr: 5.000000e-04 eta: 11:18:29 time: 1.151996 data_time: 0.127850 memory: 14267 loss_kpt: 0.000673 acc_pose: 0.738621 loss: 0.000673 2022/09/23 05:53:50 - mmengine - INFO - Epoch(train) [66][250/293] lr: 5.000000e-04 eta: 11:18:01 time: 1.147529 data_time: 0.139300 memory: 14267 loss_kpt: 0.000677 acc_pose: 0.798488 loss: 0.000677 2022/09/23 05:54:39 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 05:55:37 - mmengine - INFO - Epoch(train) [67][50/293] lr: 5.000000e-04 eta: 11:15:22 time: 1.151980 data_time: 0.139087 memory: 14267 loss_kpt: 0.000663 acc_pose: 0.782479 loss: 0.000663 2022/09/23 05:56:35 - mmengine - INFO - Epoch(train) [67][100/293] lr: 5.000000e-04 eta: 11:14:56 time: 1.163948 data_time: 0.138319 memory: 14267 loss_kpt: 0.000680 acc_pose: 0.807355 loss: 0.000680 2022/09/23 05:57:32 - mmengine - INFO - Epoch(train) [67][150/293] lr: 5.000000e-04 eta: 11:14:27 time: 1.139489 data_time: 0.128057 memory: 14267 loss_kpt: 0.000669 acc_pose: 0.777960 loss: 0.000669 2022/09/23 05:58:28 - mmengine - INFO - Epoch(train) [67][200/293] lr: 5.000000e-04 eta: 11:13:55 time: 1.117975 data_time: 0.129574 memory: 14267 loss_kpt: 0.000686 acc_pose: 0.753988 loss: 0.000686 2022/09/23 05:59:26 - mmengine - INFO - Epoch(train) [67][250/293] lr: 5.000000e-04 eta: 11:13:29 time: 1.164849 data_time: 0.128705 memory: 14267 loss_kpt: 0.000683 acc_pose: 0.799927 loss: 0.000683 2022/09/23 06:00:12 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 06:01:08 - mmengine - INFO - Epoch(train) [68][50/293] lr: 5.000000e-04 eta: 11:10:48 time: 1.118887 data_time: 0.150936 memory: 14267 loss_kpt: 0.000684 acc_pose: 0.767479 loss: 0.000684 2022/09/23 06:02:04 - mmengine - INFO - Epoch(train) [68][100/293] lr: 5.000000e-04 eta: 11:10:17 time: 1.131184 data_time: 0.123068 memory: 14267 loss_kpt: 0.000687 acc_pose: 0.795424 loss: 0.000687 2022/09/23 06:03:00 - mmengine - INFO - Epoch(train) [68][150/293] lr: 5.000000e-04 eta: 11:09:46 time: 1.120132 data_time: 0.131543 memory: 14267 loss_kpt: 0.000692 acc_pose: 0.713233 loss: 0.000692 2022/09/23 06:03:58 - mmengine - INFO - Epoch(train) [68][200/293] lr: 5.000000e-04 eta: 11:09:19 time: 1.162104 data_time: 0.123631 memory: 14267 loss_kpt: 0.000680 acc_pose: 0.814529 loss: 0.000680 2022/09/23 06:04:52 - mmengine - INFO - Epoch(train) [68][250/293] lr: 5.000000e-04 eta: 11:08:42 time: 1.071606 data_time: 0.124596 memory: 14267 loss_kpt: 0.000676 acc_pose: 0.814780 loss: 0.000676 2022/09/23 06:05:43 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 06:06:40 - mmengine - INFO - Epoch(train) [69][50/293] lr: 5.000000e-04 eta: 11:06:04 time: 1.138369 data_time: 0.149978 memory: 14267 loss_kpt: 0.000677 acc_pose: 0.791055 loss: 0.000677 2022/09/23 06:07:09 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 06:07:37 - mmengine - INFO - Epoch(train) [69][100/293] lr: 5.000000e-04 eta: 11:05:34 time: 1.130315 data_time: 0.120288 memory: 14267 loss_kpt: 0.000683 acc_pose: 0.807182 loss: 0.000683 2022/09/23 06:08:31 - mmengine - INFO - Epoch(train) [69][150/293] lr: 5.000000e-04 eta: 11:04:59 time: 1.090914 data_time: 0.134732 memory: 14267 loss_kpt: 0.000670 acc_pose: 0.789897 loss: 0.000670 2022/09/23 06:09:24 - mmengine - INFO - Epoch(train) [69][200/293] lr: 5.000000e-04 eta: 11:04:21 time: 1.061389 data_time: 0.128755 memory: 14267 loss_kpt: 0.000681 acc_pose: 0.773643 loss: 0.000681 2022/09/23 06:10:24 - mmengine - INFO - Epoch(train) [69][250/293] lr: 5.000000e-04 eta: 11:03:57 time: 1.193461 data_time: 0.117003 memory: 14267 loss_kpt: 0.000673 acc_pose: 0.840525 loss: 0.000673 2022/09/23 06:11:11 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 06:12:11 - mmengine - INFO - Epoch(train) [70][50/293] lr: 5.000000e-04 eta: 11:01:27 time: 1.206869 data_time: 0.173958 memory: 14267 loss_kpt: 0.000684 acc_pose: 0.758601 loss: 0.000684 2022/09/23 06:13:05 - mmengine - INFO - Epoch(train) [70][100/293] lr: 5.000000e-04 eta: 11:00:51 time: 1.076998 data_time: 0.126477 memory: 14267 loss_kpt: 0.000652 acc_pose: 0.812609 loss: 0.000652 2022/09/23 06:14:01 - mmengine - INFO - Epoch(train) [70][150/293] lr: 5.000000e-04 eta: 11:00:19 time: 1.118483 data_time: 0.126145 memory: 14267 loss_kpt: 0.000672 acc_pose: 0.777236 loss: 0.000672 2022/09/23 06:14:59 - mmengine - INFO - Epoch(train) [70][200/293] lr: 5.000000e-04 eta: 10:59:52 time: 1.171010 data_time: 0.137700 memory: 14267 loss_kpt: 0.000679 acc_pose: 0.801368 loss: 0.000679 2022/09/23 06:15:56 - mmengine - INFO - Epoch(train) [70][250/293] lr: 5.000000e-04 eta: 10:59:20 time: 1.125506 data_time: 0.127333 memory: 14267 loss_kpt: 0.000683 acc_pose: 0.802330 loss: 0.000683 2022/09/23 06:16:45 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 06:16:45 - mmengine - INFO - Saving checkpoint at 70 epochs 2022/09/23 06:17:13 - mmengine - INFO - Epoch(val) [70][50/407] eta: 0:02:33 time: 0.430806 data_time: 0.060962 memory: 14267 2022/09/23 06:17:33 - mmengine - INFO - Epoch(val) [70][100/407] eta: 0:02:01 time: 0.394387 data_time: 0.057218 memory: 1464 2022/09/23 06:17:52 - mmengine - INFO - Epoch(val) [70][150/407] eta: 0:01:37 time: 0.379134 data_time: 0.084795 memory: 1464 2022/09/23 06:18:12 - mmengine - INFO - Epoch(val) [70][200/407] eta: 0:01:23 time: 0.403939 data_time: 0.075833 memory: 1464 2022/09/23 06:18:35 - mmengine - INFO - Epoch(val) [70][250/407] eta: 0:01:10 time: 0.449909 data_time: 0.049876 memory: 1464 2022/09/23 06:18:56 - mmengine - INFO - Epoch(val) [70][300/407] eta: 0:00:46 time: 0.430424 data_time: 0.032994 memory: 1464 2022/09/23 06:19:17 - mmengine - INFO - Epoch(val) [70][350/407] eta: 0:00:23 time: 0.410334 data_time: 0.035411 memory: 1464 2022/09/23 06:19:33 - mmengine - INFO - Epoch(val) [70][400/407] eta: 0:00:02 time: 0.327617 data_time: 0.029830 memory: 1464 2022/09/23 06:20:10 - mmengine - INFO - Evaluating CocoMetric... 2022/09/23 06:20:23 - mmengine - INFO - Epoch(val) [70][407/407] coco/AP: 0.701573 coco/AP .5: 0.888815 coco/AP .75: 0.769815 coco/AP (M): 0.656871 coco/AP (L): 0.776946 coco/AR: 0.755321 coco/AR .5: 0.927582 coco/AR .75: 0.817380 coco/AR (M): 0.705572 coco/AR (L): 0.826273 2022/09/23 06:20:23 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220922/res50_384_2/best_coco/AP_epoch_40.pth is removed 2022/09/23 06:20:26 - mmengine - INFO - The best checkpoint with 0.7016 coco/AP at 70 epoch is saved to best_coco/AP_epoch_70.pth. 2022/09/23 06:21:26 - mmengine - INFO - Epoch(train) [71][50/293] lr: 5.000000e-04 eta: 10:56:50 time: 1.187062 data_time: 0.141381 memory: 14267 loss_kpt: 0.000679 acc_pose: 0.836390 loss: 0.000679 2022/09/23 06:22:18 - mmengine - INFO - Epoch(train) [71][100/293] lr: 5.000000e-04 eta: 10:56:10 time: 1.046499 data_time: 0.126368 memory: 14267 loss_kpt: 0.000679 acc_pose: 0.777980 loss: 0.000679 2022/09/23 06:23:15 - mmengine - INFO - Epoch(train) [71][150/293] lr: 5.000000e-04 eta: 10:55:40 time: 1.143644 data_time: 0.115321 memory: 14267 loss_kpt: 0.000678 acc_pose: 0.807060 loss: 0.000678 2022/09/23 06:24:11 - mmengine - INFO - Epoch(train) [71][200/293] lr: 5.000000e-04 eta: 10:55:08 time: 1.126879 data_time: 0.127049 memory: 14267 loss_kpt: 0.000678 acc_pose: 0.815854 loss: 0.000678 2022/09/23 06:25:10 - mmengine - INFO - Epoch(train) [71][250/293] lr: 5.000000e-04 eta: 10:54:40 time: 1.162164 data_time: 0.125521 memory: 14267 loss_kpt: 0.000667 acc_pose: 0.833218 loss: 0.000667 2022/09/23 06:25:58 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 06:26:52 - mmengine - INFO - Epoch(train) [72][50/293] lr: 5.000000e-04 eta: 10:52:00 time: 1.070810 data_time: 0.144189 memory: 14267 loss_kpt: 0.000668 acc_pose: 0.807893 loss: 0.000668 2022/09/23 06:27:49 - mmengine - INFO - Epoch(train) [72][100/293] lr: 5.000000e-04 eta: 10:51:28 time: 1.133933 data_time: 0.116050 memory: 14267 loss_kpt: 0.000672 acc_pose: 0.776192 loss: 0.000672 2022/09/23 06:28:46 - mmengine - INFO - Epoch(train) [72][150/293] lr: 5.000000e-04 eta: 10:50:58 time: 1.147594 data_time: 0.133933 memory: 14267 loss_kpt: 0.000660 acc_pose: 0.807635 loss: 0.000660 2022/09/23 06:29:40 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 06:29:44 - mmengine - INFO - Epoch(train) [72][200/293] lr: 5.000000e-04 eta: 10:50:28 time: 1.153590 data_time: 0.118317 memory: 14267 loss_kpt: 0.000681 acc_pose: 0.807035 loss: 0.000681 2022/09/23 06:30:43 - mmengine - INFO - Epoch(train) [72][250/293] lr: 5.000000e-04 eta: 10:50:01 time: 1.181564 data_time: 0.132488 memory: 14267 loss_kpt: 0.000691 acc_pose: 0.792971 loss: 0.000691 2022/09/23 06:31:28 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 06:32:28 - mmengine - INFO - Epoch(train) [73][50/293] lr: 5.000000e-04 eta: 10:47:34 time: 1.193281 data_time: 0.174316 memory: 14267 loss_kpt: 0.000658 acc_pose: 0.786406 loss: 0.000658 2022/09/23 06:33:27 - mmengine - INFO - Epoch(train) [73][100/293] lr: 5.000000e-04 eta: 10:47:06 time: 1.173235 data_time: 0.143474 memory: 14267 loss_kpt: 0.000668 acc_pose: 0.810491 loss: 0.000668 2022/09/23 06:34:24 - mmengine - INFO - Epoch(train) [73][150/293] lr: 5.000000e-04 eta: 10:46:35 time: 1.143405 data_time: 0.128200 memory: 14267 loss_kpt: 0.000670 acc_pose: 0.793564 loss: 0.000670 2022/09/23 06:35:20 - mmengine - INFO - Epoch(train) [73][200/293] lr: 5.000000e-04 eta: 10:46:02 time: 1.116519 data_time: 0.119723 memory: 14267 loss_kpt: 0.000670 acc_pose: 0.835434 loss: 0.000670 2022/09/23 06:36:16 - mmengine - INFO - Epoch(train) [73][250/293] lr: 5.000000e-04 eta: 10:45:29 time: 1.131559 data_time: 0.130532 memory: 14267 loss_kpt: 0.000676 acc_pose: 0.803106 loss: 0.000676 2022/09/23 06:37:09 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 06:38:09 - mmengine - INFO - Epoch(train) [74][50/293] lr: 5.000000e-04 eta: 10:43:04 time: 1.191187 data_time: 0.144019 memory: 14267 loss_kpt: 0.000673 acc_pose: 0.768400 loss: 0.000673 2022/09/23 06:39:07 - mmengine - INFO - Epoch(train) [74][100/293] lr: 5.000000e-04 eta: 10:42:35 time: 1.167640 data_time: 0.124053 memory: 14267 loss_kpt: 0.000677 acc_pose: 0.813937 loss: 0.000677 2022/09/23 06:40:04 - mmengine - INFO - Epoch(train) [74][150/293] lr: 5.000000e-04 eta: 10:42:03 time: 1.137709 data_time: 0.127728 memory: 14267 loss_kpt: 0.000667 acc_pose: 0.774063 loss: 0.000667 2022/09/23 06:40:58 - mmengine - INFO - Epoch(train) [74][200/293] lr: 5.000000e-04 eta: 10:41:25 time: 1.081805 data_time: 0.132695 memory: 14267 loss_kpt: 0.000674 acc_pose: 0.806716 loss: 0.000674 2022/09/23 06:41:58 - mmengine - INFO - Epoch(train) [74][250/293] lr: 5.000000e-04 eta: 10:40:59 time: 1.202315 data_time: 0.124926 memory: 14267 loss_kpt: 0.000689 acc_pose: 0.769396 loss: 0.000689 2022/09/23 06:42:46 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 06:43:43 - mmengine - INFO - Epoch(train) [75][50/293] lr: 5.000000e-04 eta: 10:38:29 time: 1.129395 data_time: 0.149082 memory: 14267 loss_kpt: 0.000661 acc_pose: 0.777689 loss: 0.000661 2022/09/23 06:44:40 - mmengine - INFO - Epoch(train) [75][100/293] lr: 5.000000e-04 eta: 10:37:58 time: 1.149000 data_time: 0.118448 memory: 14267 loss_kpt: 0.000665 acc_pose: 0.839453 loss: 0.000665 2022/09/23 06:45:36 - mmengine - INFO - Epoch(train) [75][150/293] lr: 5.000000e-04 eta: 10:37:24 time: 1.124729 data_time: 0.128951 memory: 14267 loss_kpt: 0.000660 acc_pose: 0.820621 loss: 0.000660 2022/09/23 06:46:34 - mmengine - INFO - Epoch(train) [75][200/293] lr: 5.000000e-04 eta: 10:36:54 time: 1.160034 data_time: 0.121419 memory: 14267 loss_kpt: 0.000681 acc_pose: 0.819731 loss: 0.000681 2022/09/23 06:47:31 - mmengine - INFO - Epoch(train) [75][250/293] lr: 5.000000e-04 eta: 10:36:20 time: 1.123463 data_time: 0.127865 memory: 14267 loss_kpt: 0.000659 acc_pose: 0.803779 loss: 0.000659 2022/09/23 06:48:21 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 06:48:52 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 06:49:20 - mmengine - INFO - Epoch(train) [76][50/293] lr: 5.000000e-04 eta: 10:33:54 time: 1.166260 data_time: 0.157521 memory: 14267 loss_kpt: 0.000676 acc_pose: 0.825573 loss: 0.000676 2022/09/23 06:50:16 - mmengine - INFO - Epoch(train) [76][100/293] lr: 5.000000e-04 eta: 10:33:22 time: 1.136315 data_time: 0.124906 memory: 14267 loss_kpt: 0.000665 acc_pose: 0.793709 loss: 0.000665 2022/09/23 06:51:14 - mmengine - INFO - Epoch(train) [76][150/293] lr: 5.000000e-04 eta: 10:32:50 time: 1.152485 data_time: 0.136409 memory: 14267 loss_kpt: 0.000666 acc_pose: 0.774729 loss: 0.000666 2022/09/23 06:52:09 - mmengine - INFO - Epoch(train) [76][200/293] lr: 5.000000e-04 eta: 10:32:14 time: 1.098474 data_time: 0.132206 memory: 14267 loss_kpt: 0.000679 acc_pose: 0.808540 loss: 0.000679 2022/09/23 06:53:06 - mmengine - INFO - Epoch(train) [76][250/293] lr: 5.000000e-04 eta: 10:31:42 time: 1.150766 data_time: 0.124075 memory: 14267 loss_kpt: 0.000674 acc_pose: 0.823523 loss: 0.000674 2022/09/23 06:53:57 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 06:54:54 - mmengine - INFO - Epoch(train) [77][50/293] lr: 5.000000e-04 eta: 10:29:16 time: 1.148730 data_time: 0.141125 memory: 14267 loss_kpt: 0.000677 acc_pose: 0.802735 loss: 0.000677 2022/09/23 06:55:51 - mmengine - INFO - Epoch(train) [77][100/293] lr: 5.000000e-04 eta: 10:28:44 time: 1.143997 data_time: 0.129195 memory: 14267 loss_kpt: 0.000661 acc_pose: 0.827010 loss: 0.000661 2022/09/23 06:56:51 - mmengine - INFO - Epoch(train) [77][150/293] lr: 5.000000e-04 eta: 10:28:15 time: 1.186511 data_time: 0.135454 memory: 14267 loss_kpt: 0.000656 acc_pose: 0.819821 loss: 0.000656 2022/09/23 06:57:49 - mmengine - INFO - Epoch(train) [77][200/293] lr: 5.000000e-04 eta: 10:27:44 time: 1.159976 data_time: 0.126415 memory: 14267 loss_kpt: 0.000668 acc_pose: 0.868898 loss: 0.000668 2022/09/23 06:58:46 - mmengine - INFO - Epoch(train) [77][250/293] lr: 5.000000e-04 eta: 10:27:12 time: 1.153333 data_time: 0.127619 memory: 14267 loss_kpt: 0.000670 acc_pose: 0.781728 loss: 0.000670 2022/09/23 06:59:35 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 07:00:32 - mmengine - INFO - Epoch(train) [78][50/293] lr: 5.000000e-04 eta: 10:24:46 time: 1.138541 data_time: 0.179205 memory: 14267 loss_kpt: 0.000654 acc_pose: 0.781897 loss: 0.000654 2022/09/23 07:01:30 - mmengine - INFO - Epoch(train) [78][100/293] lr: 5.000000e-04 eta: 10:24:15 time: 1.161613 data_time: 0.115158 memory: 14267 loss_kpt: 0.000686 acc_pose: 0.841004 loss: 0.000686 2022/09/23 07:02:30 - mmengine - INFO - Epoch(train) [78][150/293] lr: 5.000000e-04 eta: 10:23:47 time: 1.198838 data_time: 0.127683 memory: 14267 loss_kpt: 0.000676 acc_pose: 0.789920 loss: 0.000676 2022/09/23 07:03:26 - mmengine - INFO - Epoch(train) [78][200/293] lr: 5.000000e-04 eta: 10:23:11 time: 1.112546 data_time: 0.137144 memory: 14267 loss_kpt: 0.000652 acc_pose: 0.809002 loss: 0.000652 2022/09/23 07:04:23 - mmengine - INFO - Epoch(train) [78][250/293] lr: 5.000000e-04 eta: 10:22:38 time: 1.137740 data_time: 0.123008 memory: 14267 loss_kpt: 0.000643 acc_pose: 0.747468 loss: 0.000643 2022/09/23 07:05:13 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 07:06:12 - mmengine - INFO - Epoch(train) [79][50/293] lr: 5.000000e-04 eta: 10:20:16 time: 1.176452 data_time: 0.134736 memory: 14267 loss_kpt: 0.000662 acc_pose: 0.793619 loss: 0.000662 2022/09/23 07:07:12 - mmengine - INFO - Epoch(train) [79][100/293] lr: 5.000000e-04 eta: 10:19:47 time: 1.198646 data_time: 0.114427 memory: 14267 loss_kpt: 0.000674 acc_pose: 0.806512 loss: 0.000674 2022/09/23 07:08:04 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 07:08:08 - mmengine - INFO - Epoch(train) [79][150/293] lr: 5.000000e-04 eta: 10:19:11 time: 1.109744 data_time: 0.124634 memory: 14267 loss_kpt: 0.000675 acc_pose: 0.820527 loss: 0.000675 2022/09/23 07:09:02 - mmengine - INFO - Epoch(train) [79][200/293] lr: 5.000000e-04 eta: 10:18:34 time: 1.095102 data_time: 0.121202 memory: 14267 loss_kpt: 0.000657 acc_pose: 0.813955 loss: 0.000657 2022/09/23 07:10:01 - mmengine - INFO - Epoch(train) [79][250/293] lr: 5.000000e-04 eta: 10:18:04 time: 1.179626 data_time: 0.137558 memory: 14267 loss_kpt: 0.000661 acc_pose: 0.778329 loss: 0.000661 2022/09/23 07:10:50 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 07:11:52 - mmengine - INFO - Epoch(train) [80][50/293] lr: 5.000000e-04 eta: 10:15:48 time: 1.233243 data_time: 0.143765 memory: 14267 loss_kpt: 0.000689 acc_pose: 0.732733 loss: 0.000689 2022/09/23 07:12:48 - mmengine - INFO - Epoch(train) [80][100/293] lr: 5.000000e-04 eta: 10:15:13 time: 1.134728 data_time: 0.127832 memory: 14267 loss_kpt: 0.000653 acc_pose: 0.811442 loss: 0.000653 2022/09/23 07:13:49 - mmengine - INFO - Epoch(train) [80][150/293] lr: 5.000000e-04 eta: 10:14:45 time: 1.209323 data_time: 0.132120 memory: 14267 loss_kpt: 0.000660 acc_pose: 0.834387 loss: 0.000660 2022/09/23 07:14:48 - mmengine - INFO - Epoch(train) [80][200/293] lr: 5.000000e-04 eta: 10:14:14 time: 1.177316 data_time: 0.127613 memory: 14267 loss_kpt: 0.000656 acc_pose: 0.792652 loss: 0.000656 2022/09/23 07:15:49 - mmengine - INFO - Epoch(train) [80][250/293] lr: 5.000000e-04 eta: 10:13:48 time: 1.233452 data_time: 0.136641 memory: 14267 loss_kpt: 0.000660 acc_pose: 0.825165 loss: 0.000660 2022/09/23 07:16:40 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 07:16:40 - mmengine - INFO - Saving checkpoint at 80 epochs 2022/09/23 07:17:09 - mmengine - INFO - Epoch(val) [80][50/407] eta: 0:02:32 time: 0.425946 data_time: 0.096532 memory: 14267 2022/09/23 07:17:30 - mmengine - INFO - Epoch(val) [80][100/407] eta: 0:02:06 time: 0.411708 data_time: 0.069062 memory: 1464 2022/09/23 07:17:53 - mmengine - INFO - Epoch(val) [80][150/407] eta: 0:02:01 time: 0.473159 data_time: 0.031410 memory: 1464 2022/09/23 07:18:15 - mmengine - INFO - Epoch(val) [80][200/407] eta: 0:01:30 time: 0.435252 data_time: 0.036295 memory: 1464 2022/09/23 07:18:37 - mmengine - INFO - Epoch(val) [80][250/407] eta: 0:01:08 time: 0.439127 data_time: 0.035194 memory: 1464 2022/09/23 07:18:58 - mmengine - INFO - Epoch(val) [80][300/407] eta: 0:00:43 time: 0.411206 data_time: 0.029552 memory: 1464 2022/09/23 07:19:19 - mmengine - INFO - Epoch(val) [80][350/407] eta: 0:00:24 time: 0.429316 data_time: 0.048111 memory: 1464 2022/09/23 07:19:34 - mmengine - INFO - Epoch(val) [80][400/407] eta: 0:00:02 time: 0.302060 data_time: 0.015805 memory: 1464 2022/09/23 07:20:10 - mmengine - INFO - Evaluating CocoMetric... 2022/09/23 07:20:23 - mmengine - INFO - Epoch(val) [80][407/407] coco/AP: 0.703312 coco/AP .5: 0.887903 coco/AP .75: 0.773494 coco/AP (M): 0.661935 coco/AP (L): 0.776314 coco/AR: 0.757714 coco/AR .5: 0.928054 coco/AR .75: 0.821474 coco/AR (M): 0.709478 coco/AR (L): 0.826496 2022/09/23 07:20:23 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220922/res50_384_2/best_coco/AP_epoch_70.pth is removed 2022/09/23 07:20:26 - mmengine - INFO - The best checkpoint with 0.7033 coco/AP at 80 epoch is saved to best_coco/AP_epoch_80.pth. 2022/09/23 07:21:25 - mmengine - INFO - Epoch(train) [81][50/293] lr: 5.000000e-04 eta: 10:11:29 time: 1.184153 data_time: 0.124392 memory: 14267 loss_kpt: 0.000650 acc_pose: 0.864915 loss: 0.000650 2022/09/23 07:22:31 - mmengine - INFO - Epoch(train) [81][100/293] lr: 5.000000e-04 eta: 10:11:09 time: 1.315750 data_time: 0.117601 memory: 14267 loss_kpt: 0.000654 acc_pose: 0.857648 loss: 0.000654 2022/09/23 07:23:35 - mmengine - INFO - Epoch(train) [81][150/293] lr: 5.000000e-04 eta: 10:10:45 time: 1.269005 data_time: 0.125796 memory: 14267 loss_kpt: 0.000670 acc_pose: 0.784330 loss: 0.000670 2022/09/23 07:24:39 - mmengine - INFO - Epoch(train) [81][200/293] lr: 5.000000e-04 eta: 10:10:22 time: 1.283855 data_time: 0.118643 memory: 14267 loss_kpt: 0.000676 acc_pose: 0.764921 loss: 0.000676 2022/09/23 07:25:34 - mmengine - INFO - Epoch(train) [81][250/293] lr: 5.000000e-04 eta: 10:09:45 time: 1.101596 data_time: 0.112270 memory: 14267 loss_kpt: 0.000659 acc_pose: 0.805532 loss: 0.000659 2022/09/23 07:26:24 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 07:27:27 - mmengine - INFO - Epoch(train) [82][50/293] lr: 5.000000e-04 eta: 10:07:31 time: 1.253356 data_time: 0.143316 memory: 14267 loss_kpt: 0.000659 acc_pose: 0.847507 loss: 0.000659 2022/09/23 07:28:30 - mmengine - INFO - Epoch(train) [82][100/293] lr: 5.000000e-04 eta: 10:07:07 time: 1.263960 data_time: 0.110700 memory: 14267 loss_kpt: 0.000648 acc_pose: 0.824144 loss: 0.000648 2022/09/23 07:29:33 - mmengine - INFO - Epoch(train) [82][150/293] lr: 5.000000e-04 eta: 10:06:41 time: 1.257374 data_time: 0.113338 memory: 14267 loss_kpt: 0.000653 acc_pose: 0.808408 loss: 0.000653 2022/09/23 07:30:33 - mmengine - INFO - Epoch(train) [82][200/293] lr: 5.000000e-04 eta: 10:06:12 time: 1.203373 data_time: 0.132797 memory: 14267 loss_kpt: 0.000671 acc_pose: 0.809405 loss: 0.000671 2022/09/23 07:31:34 - mmengine - INFO - Epoch(train) [82][250/293] lr: 5.000000e-04 eta: 10:05:43 time: 1.217791 data_time: 0.115469 memory: 14267 loss_kpt: 0.000653 acc_pose: 0.782556 loss: 0.000653 2022/09/23 07:31:55 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 07:32:28 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 07:33:25 - mmengine - INFO - Epoch(train) [83][50/293] lr: 5.000000e-04 eta: 10:03:22 time: 1.148907 data_time: 0.149455 memory: 14267 loss_kpt: 0.000658 acc_pose: 0.849901 loss: 0.000658 2022/09/23 07:34:25 - mmengine - INFO - Epoch(train) [83][100/293] lr: 5.000000e-04 eta: 10:02:51 time: 1.187555 data_time: 0.113979 memory: 14267 loss_kpt: 0.000677 acc_pose: 0.795736 loss: 0.000677 2022/09/23 07:35:25 - mmengine - INFO - Epoch(train) [83][150/293] lr: 5.000000e-04 eta: 10:02:21 time: 1.207310 data_time: 0.118991 memory: 14267 loss_kpt: 0.000666 acc_pose: 0.795686 loss: 0.000666 2022/09/23 07:36:29 - mmengine - INFO - Epoch(train) [83][200/293] lr: 5.000000e-04 eta: 10:01:57 time: 1.283833 data_time: 0.109821 memory: 14267 loss_kpt: 0.000657 acc_pose: 0.792524 loss: 0.000657 2022/09/23 07:37:31 - mmengine - INFO - Epoch(train) [83][250/293] lr: 5.000000e-04 eta: 10:01:29 time: 1.230660 data_time: 0.114377 memory: 14267 loss_kpt: 0.000657 acc_pose: 0.811997 loss: 0.000657 2022/09/23 07:38:25 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 07:39:24 - mmengine - INFO - Epoch(train) [84][50/293] lr: 5.000000e-04 eta: 9:59:11 time: 1.181087 data_time: 0.138637 memory: 14267 loss_kpt: 0.000645 acc_pose: 0.821601 loss: 0.000645 2022/09/23 07:40:27 - mmengine - INFO - Epoch(train) [84][100/293] lr: 5.000000e-04 eta: 9:58:45 time: 1.261541 data_time: 0.117065 memory: 14267 loss_kpt: 0.000652 acc_pose: 0.813141 loss: 0.000652 2022/09/23 07:41:26 - mmengine - INFO - Epoch(train) [84][150/293] lr: 5.000000e-04 eta: 9:58:12 time: 1.167289 data_time: 0.112747 memory: 14267 loss_kpt: 0.000648 acc_pose: 0.840786 loss: 0.000648 2022/09/23 07:42:30 - mmengine - INFO - Epoch(train) [84][200/293] lr: 5.000000e-04 eta: 9:57:47 time: 1.278906 data_time: 0.120438 memory: 14267 loss_kpt: 0.000639 acc_pose: 0.807880 loss: 0.000639 2022/09/23 07:43:28 - mmengine - INFO - Epoch(train) [84][250/293] lr: 5.000000e-04 eta: 9:57:13 time: 1.163856 data_time: 0.118593 memory: 14267 loss_kpt: 0.000658 acc_pose: 0.778941 loss: 0.000658 2022/09/23 07:44:23 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 07:45:25 - mmengine - INFO - Epoch(train) [85][50/293] lr: 5.000000e-04 eta: 9:55:01 time: 1.239954 data_time: 0.174598 memory: 14267 loss_kpt: 0.000654 acc_pose: 0.825929 loss: 0.000654 2022/09/23 07:46:29 - mmengine - INFO - Epoch(train) [85][100/293] lr: 5.000000e-04 eta: 9:54:36 time: 1.277553 data_time: 0.126848 memory: 14267 loss_kpt: 0.000656 acc_pose: 0.767395 loss: 0.000656 2022/09/23 07:47:29 - mmengine - INFO - Epoch(train) [85][150/293] lr: 5.000000e-04 eta: 9:54:04 time: 1.193793 data_time: 0.122799 memory: 14267 loss_kpt: 0.000669 acc_pose: 0.809184 loss: 0.000669 2022/09/23 07:48:32 - mmengine - INFO - Epoch(train) [85][200/293] lr: 5.000000e-04 eta: 9:53:37 time: 1.260858 data_time: 0.121463 memory: 14267 loss_kpt: 0.000657 acc_pose: 0.795888 loss: 0.000657 2022/09/23 07:49:30 - mmengine - INFO - Epoch(train) [85][250/293] lr: 5.000000e-04 eta: 9:53:03 time: 1.172317 data_time: 0.125436 memory: 14267 loss_kpt: 0.000664 acc_pose: 0.753564 loss: 0.000664 2022/09/23 07:50:27 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 07:51:31 - mmengine - INFO - Epoch(train) [86][50/293] lr: 5.000000e-04 eta: 9:50:55 time: 1.288516 data_time: 0.183969 memory: 14267 loss_kpt: 0.000655 acc_pose: 0.750190 loss: 0.000655 2022/09/23 07:52:25 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 07:52:31 - mmengine - INFO - Epoch(train) [86][100/293] lr: 5.000000e-04 eta: 9:50:24 time: 1.199775 data_time: 0.112990 memory: 14267 loss_kpt: 0.000654 acc_pose: 0.796931 loss: 0.000654 2022/09/23 07:53:33 - mmengine - INFO - Epoch(train) [86][150/293] lr: 5.000000e-04 eta: 9:49:54 time: 1.228719 data_time: 0.123690 memory: 14267 loss_kpt: 0.000661 acc_pose: 0.844710 loss: 0.000661 2022/09/23 07:54:33 - mmengine - INFO - Epoch(train) [86][200/293] lr: 5.000000e-04 eta: 9:49:22 time: 1.200210 data_time: 0.126836 memory: 14267 loss_kpt: 0.000662 acc_pose: 0.838228 loss: 0.000662 2022/09/23 07:55:34 - mmengine - INFO - Epoch(train) [86][250/293] lr: 5.000000e-04 eta: 9:48:52 time: 1.225878 data_time: 0.117426 memory: 14267 loss_kpt: 0.000658 acc_pose: 0.782850 loss: 0.000658 2022/09/23 07:56:22 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 07:57:24 - mmengine - INFO - Epoch(train) [87][50/293] lr: 5.000000e-04 eta: 9:46:41 time: 1.243644 data_time: 0.147519 memory: 14267 loss_kpt: 0.000652 acc_pose: 0.836552 loss: 0.000652 2022/09/23 07:58:22 - mmengine - INFO - Epoch(train) [87][100/293] lr: 5.000000e-04 eta: 9:46:05 time: 1.146526 data_time: 0.112597 memory: 14267 loss_kpt: 0.000659 acc_pose: 0.815015 loss: 0.000659 2022/09/23 07:59:24 - mmengine - INFO - Epoch(train) [87][150/293] lr: 5.000000e-04 eta: 9:45:36 time: 1.245996 data_time: 0.121571 memory: 14267 loss_kpt: 0.000657 acc_pose: 0.816579 loss: 0.000657 2022/09/23 08:00:25 - mmengine - INFO - Epoch(train) [87][200/293] lr: 5.000000e-04 eta: 9:45:06 time: 1.219285 data_time: 0.132023 memory: 14267 loss_kpt: 0.000644 acc_pose: 0.857410 loss: 0.000644 2022/09/23 08:01:26 - mmengine - INFO - Epoch(train) [87][250/293] lr: 5.000000e-04 eta: 9:44:35 time: 1.218783 data_time: 0.112346 memory: 14267 loss_kpt: 0.000667 acc_pose: 0.793734 loss: 0.000667 2022/09/23 08:02:19 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 08:03:22 - mmengine - INFO - Epoch(train) [88][50/293] lr: 5.000000e-04 eta: 9:42:25 time: 1.250836 data_time: 0.133798 memory: 14267 loss_kpt: 0.000648 acc_pose: 0.814498 loss: 0.000648 2022/09/23 08:04:27 - mmengine - INFO - Epoch(train) [88][100/293] lr: 5.000000e-04 eta: 9:42:00 time: 1.303451 data_time: 0.105341 memory: 14267 loss_kpt: 0.000657 acc_pose: 0.812276 loss: 0.000657 2022/09/23 08:05:32 - mmengine - INFO - Epoch(train) [88][150/293] lr: 5.000000e-04 eta: 9:41:33 time: 1.291194 data_time: 0.105405 memory: 14267 loss_kpt: 0.000665 acc_pose: 0.822343 loss: 0.000665 2022/09/23 08:06:35 - mmengine - INFO - Epoch(train) [88][200/293] lr: 5.000000e-04 eta: 9:41:06 time: 1.269878 data_time: 0.119265 memory: 14267 loss_kpt: 0.000662 acc_pose: 0.828848 loss: 0.000662 2022/09/23 08:07:39 - mmengine - INFO - Epoch(train) [88][250/293] lr: 5.000000e-04 eta: 9:40:39 time: 1.285880 data_time: 0.112006 memory: 14267 loss_kpt: 0.000647 acc_pose: 0.827912 loss: 0.000647 2022/09/23 08:08:35 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 08:09:39 - mmengine - INFO - Epoch(train) [89][50/293] lr: 5.000000e-04 eta: 9:38:31 time: 1.267238 data_time: 0.126155 memory: 14267 loss_kpt: 0.000656 acc_pose: 0.780653 loss: 0.000656 2022/09/23 08:10:42 - mmengine - INFO - Epoch(train) [89][100/293] lr: 5.000000e-04 eta: 9:38:03 time: 1.275782 data_time: 0.122880 memory: 14267 loss_kpt: 0.000650 acc_pose: 0.780437 loss: 0.000650 2022/09/23 08:11:46 - mmengine - INFO - Epoch(train) [89][150/293] lr: 5.000000e-04 eta: 9:37:35 time: 1.269592 data_time: 0.118588 memory: 14267 loss_kpt: 0.000646 acc_pose: 0.811313 loss: 0.000646 2022/09/23 08:12:49 - mmengine - INFO - Epoch(train) [89][200/293] lr: 5.000000e-04 eta: 9:37:05 time: 1.259341 data_time: 0.106095 memory: 14267 loss_kpt: 0.000648 acc_pose: 0.765866 loss: 0.000648 2022/09/23 08:13:07 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 08:13:53 - mmengine - INFO - Epoch(train) [89][250/293] lr: 5.000000e-04 eta: 9:36:38 time: 1.282760 data_time: 0.113192 memory: 14267 loss_kpt: 0.000647 acc_pose: 0.791958 loss: 0.000647 2022/09/23 08:14:47 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 08:15:48 - mmengine - INFO - Epoch(train) [90][50/293] lr: 5.000000e-04 eta: 9:34:27 time: 1.226015 data_time: 0.130946 memory: 14267 loss_kpt: 0.000652 acc_pose: 0.850670 loss: 0.000652 2022/09/23 08:16:53 - mmengine - INFO - Epoch(train) [90][100/293] lr: 5.000000e-04 eta: 9:34:00 time: 1.285735 data_time: 0.113591 memory: 14267 loss_kpt: 0.000653 acc_pose: 0.811218 loss: 0.000653 2022/09/23 08:17:52 - mmengine - INFO - Epoch(train) [90][150/293] lr: 5.000000e-04 eta: 9:33:25 time: 1.183446 data_time: 0.114784 memory: 14267 loss_kpt: 0.000657 acc_pose: 0.792241 loss: 0.000657 2022/09/23 08:18:54 - mmengine - INFO - Epoch(train) [90][200/293] lr: 5.000000e-04 eta: 9:32:54 time: 1.236278 data_time: 0.125151 memory: 14267 loss_kpt: 0.000652 acc_pose: 0.786978 loss: 0.000652 2022/09/23 08:19:56 - mmengine - INFO - Epoch(train) [90][250/293] lr: 5.000000e-04 eta: 9:32:24 time: 1.248689 data_time: 0.119290 memory: 14267 loss_kpt: 0.000661 acc_pose: 0.739303 loss: 0.000661 2022/09/23 08:20:53 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 08:20:53 - mmengine - INFO - Saving checkpoint at 90 epochs 2022/09/23 08:21:23 - mmengine - INFO - Epoch(val) [90][50/407] eta: 0:02:38 time: 0.444738 data_time: 0.047010 memory: 14267 2022/09/23 08:21:46 - mmengine - INFO - Epoch(val) [90][100/407] eta: 0:02:21 time: 0.459725 data_time: 0.036852 memory: 1464 2022/09/23 08:22:09 - mmengine - INFO - Epoch(val) [90][150/407] eta: 0:01:59 time: 0.465200 data_time: 0.033593 memory: 1464 2022/09/23 08:22:33 - mmengine - INFO - Epoch(val) [90][200/407] eta: 0:01:39 time: 0.481375 data_time: 0.033604 memory: 1464 2022/09/23 08:22:55 - mmengine - INFO - Epoch(val) [90][250/407] eta: 0:01:09 time: 0.441531 data_time: 0.036065 memory: 1464 2022/09/23 08:23:16 - mmengine - INFO - Epoch(val) [90][300/407] eta: 0:00:45 time: 0.423283 data_time: 0.036117 memory: 1464 2022/09/23 08:23:34 - mmengine - INFO - Epoch(val) [90][350/407] eta: 0:00:19 time: 0.348272 data_time: 0.023806 memory: 1464 2022/09/23 08:23:48 - mmengine - INFO - Epoch(val) [90][400/407] eta: 0:00:01 time: 0.282881 data_time: 0.012390 memory: 1464 2022/09/23 08:24:23 - mmengine - INFO - Evaluating CocoMetric... 2022/09/23 08:24:36 - mmengine - INFO - Epoch(val) [90][407/407] coco/AP: 0.709523 coco/AP .5: 0.890967 coco/AP .75: 0.776378 coco/AP (M): 0.665967 coco/AP (L): 0.783162 coco/AR: 0.762421 coco/AR .5: 0.929786 coco/AR .75: 0.823048 coco/AR (M): 0.713985 coco/AR (L): 0.831810 2022/09/23 08:24:36 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220922/res50_384_2/best_coco/AP_epoch_80.pth is removed 2022/09/23 08:24:39 - mmengine - INFO - The best checkpoint with 0.7095 coco/AP at 90 epoch is saved to best_coco/AP_epoch_90.pth. 2022/09/23 08:25:40 - mmengine - INFO - Epoch(train) [91][50/293] lr: 5.000000e-04 eta: 9:30:13 time: 1.212105 data_time: 0.121054 memory: 14267 loss_kpt: 0.000661 acc_pose: 0.815435 loss: 0.000661 2022/09/23 08:26:47 - mmengine - INFO - Epoch(train) [91][100/293] lr: 5.000000e-04 eta: 9:29:48 time: 1.337985 data_time: 0.112200 memory: 14267 loss_kpt: 0.000658 acc_pose: 0.823899 loss: 0.000658 2022/09/23 08:27:47 - mmengine - INFO - Epoch(train) [91][150/293] lr: 5.000000e-04 eta: 9:29:14 time: 1.199858 data_time: 0.112215 memory: 14267 loss_kpt: 0.000647 acc_pose: 0.843834 loss: 0.000647 2022/09/23 08:28:54 - mmengine - INFO - Epoch(train) [91][200/293] lr: 5.000000e-04 eta: 9:28:50 time: 1.345533 data_time: 0.108450 memory: 14267 loss_kpt: 0.000646 acc_pose: 0.832562 loss: 0.000646 2022/09/23 08:29:54 - mmengine - INFO - Epoch(train) [91][250/293] lr: 5.000000e-04 eta: 9:28:16 time: 1.199437 data_time: 0.120340 memory: 14267 loss_kpt: 0.000644 acc_pose: 0.804660 loss: 0.000644 2022/09/23 08:30:52 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 08:31:53 - mmengine - INFO - Epoch(train) [92][50/293] lr: 5.000000e-04 eta: 9:26:05 time: 1.209211 data_time: 0.138177 memory: 14267 loss_kpt: 0.000657 acc_pose: 0.823045 loss: 0.000657 2022/09/23 08:33:01 - mmengine - INFO - Epoch(train) [92][100/293] lr: 5.000000e-04 eta: 9:25:41 time: 1.361925 data_time: 0.112875 memory: 14267 loss_kpt: 0.000652 acc_pose: 0.837269 loss: 0.000652 2022/09/23 08:34:03 - mmengine - INFO - Epoch(train) [92][150/293] lr: 5.000000e-04 eta: 9:25:10 time: 1.242893 data_time: 0.122503 memory: 14267 loss_kpt: 0.000644 acc_pose: 0.868140 loss: 0.000644 2022/09/23 08:35:10 - mmengine - INFO - Epoch(train) [92][200/293] lr: 5.000000e-04 eta: 9:24:44 time: 1.333315 data_time: 0.125136 memory: 14267 loss_kpt: 0.000663 acc_pose: 0.798512 loss: 0.000663 2022/09/23 08:36:13 - mmengine - INFO - Epoch(train) [92][250/293] lr: 5.000000e-04 eta: 9:24:13 time: 1.259020 data_time: 0.103018 memory: 14267 loss_kpt: 0.000662 acc_pose: 0.773238 loss: 0.000662 2022/09/23 08:37:12 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 08:38:07 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 08:38:15 - mmengine - INFO - Epoch(train) [93][50/293] lr: 5.000000e-04 eta: 9:22:07 time: 1.259024 data_time: 0.145502 memory: 14267 loss_kpt: 0.000647 acc_pose: 0.815666 loss: 0.000647 2022/09/23 08:39:21 - mmengine - INFO - Epoch(train) [93][100/293] lr: 5.000000e-04 eta: 9:21:40 time: 1.324800 data_time: 0.123675 memory: 14267 loss_kpt: 0.000657 acc_pose: 0.829487 loss: 0.000657 2022/09/23 08:40:22 - mmengine - INFO - Epoch(train) [93][150/293] lr: 5.000000e-04 eta: 9:21:06 time: 1.217864 data_time: 0.107849 memory: 14267 loss_kpt: 0.000649 acc_pose: 0.744535 loss: 0.000649 2022/09/23 08:41:28 - mmengine - INFO - Epoch(train) [93][200/293] lr: 5.000000e-04 eta: 9:20:39 time: 1.323809 data_time: 0.112572 memory: 14267 loss_kpt: 0.000651 acc_pose: 0.826906 loss: 0.000651 2022/09/23 08:42:29 - mmengine - INFO - Epoch(train) [93][250/293] lr: 5.000000e-04 eta: 9:20:06 time: 1.232044 data_time: 0.103524 memory: 14267 loss_kpt: 0.000647 acc_pose: 0.800272 loss: 0.000647 2022/09/23 08:43:26 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 08:44:28 - mmengine - INFO - Epoch(train) [94][50/293] lr: 5.000000e-04 eta: 9:17:58 time: 1.226118 data_time: 0.124660 memory: 14267 loss_kpt: 0.000647 acc_pose: 0.835844 loss: 0.000647 2022/09/23 08:45:33 - mmengine - INFO - Epoch(train) [94][100/293] lr: 5.000000e-04 eta: 9:17:30 time: 1.314139 data_time: 0.113136 memory: 14267 loss_kpt: 0.000651 acc_pose: 0.801676 loss: 0.000651 2022/09/23 08:46:36 - mmengine - INFO - Epoch(train) [94][150/293] lr: 5.000000e-04 eta: 9:16:58 time: 1.254881 data_time: 0.115934 memory: 14267 loss_kpt: 0.000641 acc_pose: 0.822743 loss: 0.000641 2022/09/23 08:47:42 - mmengine - INFO - Epoch(train) [94][200/293] lr: 5.000000e-04 eta: 9:16:30 time: 1.316946 data_time: 0.122808 memory: 14267 loss_kpt: 0.000650 acc_pose: 0.761638 loss: 0.000650 2022/09/23 08:48:44 - mmengine - INFO - Epoch(train) [94][250/293] lr: 5.000000e-04 eta: 9:15:58 time: 1.248770 data_time: 0.119338 memory: 14267 loss_kpt: 0.000656 acc_pose: 0.853132 loss: 0.000656 2022/09/23 08:49:41 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 08:50:45 - mmengine - INFO - Epoch(train) [95][50/293] lr: 5.000000e-04 eta: 9:13:53 time: 1.279044 data_time: 0.129235 memory: 14267 loss_kpt: 0.000646 acc_pose: 0.838124 loss: 0.000646 2022/09/23 08:51:50 - mmengine - INFO - Epoch(train) [95][100/293] lr: 5.000000e-04 eta: 9:13:25 time: 1.307857 data_time: 0.122538 memory: 14267 loss_kpt: 0.000653 acc_pose: 0.772092 loss: 0.000653 2022/09/23 08:52:55 - mmengine - INFO - Epoch(train) [95][150/293] lr: 5.000000e-04 eta: 9:12:54 time: 1.282137 data_time: 0.111106 memory: 14267 loss_kpt: 0.000637 acc_pose: 0.854726 loss: 0.000637 2022/09/23 08:54:00 - mmengine - INFO - Epoch(train) [95][200/293] lr: 5.000000e-04 eta: 9:12:25 time: 1.303189 data_time: 0.124331 memory: 14267 loss_kpt: 0.000653 acc_pose: 0.836882 loss: 0.000653 2022/09/23 08:55:03 - mmengine - INFO - Epoch(train) [95][250/293] lr: 5.000000e-04 eta: 9:11:53 time: 1.275125 data_time: 0.107223 memory: 14267 loss_kpt: 0.000639 acc_pose: 0.782171 loss: 0.000639 2022/09/23 08:55:57 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 08:57:03 - mmengine - INFO - Epoch(train) [96][50/293] lr: 5.000000e-04 eta: 9:09:51 time: 1.310061 data_time: 0.148502 memory: 14267 loss_kpt: 0.000656 acc_pose: 0.824608 loss: 0.000656 2022/09/23 08:58:08 - mmengine - INFO - Epoch(train) [96][100/293] lr: 5.000000e-04 eta: 9:09:21 time: 1.300232 data_time: 0.121393 memory: 14267 loss_kpt: 0.000637 acc_pose: 0.768840 loss: 0.000637 2022/09/23 08:59:10 - mmengine - INFO - Epoch(train) [96][150/293] lr: 5.000000e-04 eta: 9:08:49 time: 1.254503 data_time: 0.107458 memory: 14267 loss_kpt: 0.000642 acc_pose: 0.775085 loss: 0.000642 2022/09/23 08:59:31 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 09:00:15 - mmengine - INFO - Epoch(train) [96][200/293] lr: 5.000000e-04 eta: 9:08:18 time: 1.288592 data_time: 0.115962 memory: 14267 loss_kpt: 0.000655 acc_pose: 0.862150 loss: 0.000655 2022/09/23 09:01:19 - mmengine - INFO - Epoch(train) [96][250/293] lr: 5.000000e-04 eta: 9:07:47 time: 1.284227 data_time: 0.116421 memory: 14267 loss_kpt: 0.000640 acc_pose: 0.815529 loss: 0.000640 2022/09/23 09:02:14 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 09:03:19 - mmengine - INFO - Epoch(train) [97][50/293] lr: 5.000000e-04 eta: 9:05:43 time: 1.289460 data_time: 0.129500 memory: 14267 loss_kpt: 0.000652 acc_pose: 0.772526 loss: 0.000652 2022/09/23 09:04:21 - mmengine - INFO - Epoch(train) [97][100/293] lr: 5.000000e-04 eta: 9:05:10 time: 1.243234 data_time: 0.113064 memory: 14267 loss_kpt: 0.000644 acc_pose: 0.841095 loss: 0.000644 2022/09/23 09:05:26 - mmengine - INFO - Epoch(train) [97][150/293] lr: 5.000000e-04 eta: 9:04:39 time: 1.292489 data_time: 0.108634 memory: 14267 loss_kpt: 0.000633 acc_pose: 0.839589 loss: 0.000633 2022/09/23 09:06:32 - mmengine - INFO - Epoch(train) [97][200/293] lr: 5.000000e-04 eta: 9:04:09 time: 1.318571 data_time: 0.119689 memory: 14267 loss_kpt: 0.000649 acc_pose: 0.834712 loss: 0.000649 2022/09/23 09:07:36 - mmengine - INFO - Epoch(train) [97][250/293] lr: 5.000000e-04 eta: 9:03:38 time: 1.283339 data_time: 0.114661 memory: 14267 loss_kpt: 0.000640 acc_pose: 0.837459 loss: 0.000640 2022/09/23 09:08:29 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 09:09:34 - mmengine - INFO - Epoch(train) [98][50/293] lr: 5.000000e-04 eta: 9:01:36 time: 1.299129 data_time: 0.127880 memory: 14267 loss_kpt: 0.000657 acc_pose: 0.807771 loss: 0.000657 2022/09/23 09:10:41 - mmengine - INFO - Epoch(train) [98][100/293] lr: 5.000000e-04 eta: 9:01:06 time: 1.327399 data_time: 0.121193 memory: 14267 loss_kpt: 0.000641 acc_pose: 0.855466 loss: 0.000641 2022/09/23 09:11:45 - mmengine - INFO - Epoch(train) [98][150/293] lr: 5.000000e-04 eta: 9:00:35 time: 1.289190 data_time: 0.120806 memory: 14267 loss_kpt: 0.000643 acc_pose: 0.850599 loss: 0.000643 2022/09/23 09:12:46 - mmengine - INFO - Epoch(train) [98][200/293] lr: 5.000000e-04 eta: 8:59:59 time: 1.210545 data_time: 0.111905 memory: 14267 loss_kpt: 0.000645 acc_pose: 0.784096 loss: 0.000645 2022/09/23 09:13:53 - mmengine - INFO - Epoch(train) [98][250/293] lr: 5.000000e-04 eta: 8:59:30 time: 1.339227 data_time: 0.114740 memory: 14267 loss_kpt: 0.000655 acc_pose: 0.878928 loss: 0.000655 2022/09/23 09:14:48 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 09:15:54 - mmengine - INFO - Epoch(train) [99][50/293] lr: 5.000000e-04 eta: 8:57:28 time: 1.312547 data_time: 0.137754 memory: 14267 loss_kpt: 0.000642 acc_pose: 0.810561 loss: 0.000642 2022/09/23 09:16:56 - mmengine - INFO - Epoch(train) [99][100/293] lr: 5.000000e-04 eta: 8:56:53 time: 1.233112 data_time: 0.137301 memory: 14267 loss_kpt: 0.000634 acc_pose: 0.821792 loss: 0.000634 2022/09/23 09:18:04 - mmengine - INFO - Epoch(train) [99][150/293] lr: 5.000000e-04 eta: 8:56:26 time: 1.363483 data_time: 0.103810 memory: 14267 loss_kpt: 0.000653 acc_pose: 0.825297 loss: 0.000653 2022/09/23 09:19:08 - mmengine - INFO - Epoch(train) [99][200/293] lr: 5.000000e-04 eta: 8:55:53 time: 1.280047 data_time: 0.112907 memory: 14267 loss_kpt: 0.000649 acc_pose: 0.806939 loss: 0.000649 2022/09/23 09:20:14 - mmengine - INFO - Epoch(train) [99][250/293] lr: 5.000000e-04 eta: 8:55:23 time: 1.323117 data_time: 0.104629 memory: 14267 loss_kpt: 0.000655 acc_pose: 0.832486 loss: 0.000655 2022/09/23 09:20:58 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 09:21:04 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 09:22:14 - mmengine - INFO - Epoch(train) [100][50/293] lr: 5.000000e-04 eta: 8:53:27 time: 1.409697 data_time: 0.182412 memory: 14267 loss_kpt: 0.000647 acc_pose: 0.853025 loss: 0.000647 2022/09/23 09:23:17 - mmengine - INFO - Epoch(train) [100][100/293] lr: 5.000000e-04 eta: 8:52:53 time: 1.254701 data_time: 0.131856 memory: 14267 loss_kpt: 0.000646 acc_pose: 0.819692 loss: 0.000646 2022/09/23 09:24:23 - mmengine - INFO - Epoch(train) [100][150/293] lr: 5.000000e-04 eta: 8:52:22 time: 1.327485 data_time: 0.121469 memory: 14267 loss_kpt: 0.000653 acc_pose: 0.785792 loss: 0.000653 2022/09/23 09:25:23 - mmengine - INFO - Epoch(train) [100][200/293] lr: 5.000000e-04 eta: 8:51:45 time: 1.200564 data_time: 0.115942 memory: 14267 loss_kpt: 0.000627 acc_pose: 0.826340 loss: 0.000627 2022/09/23 09:26:31 - mmengine - INFO - Epoch(train) [100][250/293] lr: 5.000000e-04 eta: 8:51:16 time: 1.361071 data_time: 0.119025 memory: 14267 loss_kpt: 0.000634 acc_pose: 0.847481 loss: 0.000634 2022/09/23 09:27:23 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 09:27:23 - mmengine - INFO - Saving checkpoint at 100 epochs 2022/09/23 09:27:54 - mmengine - INFO - Epoch(val) [100][50/407] eta: 0:02:53 time: 0.485758 data_time: 0.058154 memory: 14267 2022/09/23 09:28:17 - mmengine - INFO - Epoch(val) [100][100/407] eta: 0:02:22 time: 0.462752 data_time: 0.026473 memory: 1464 2022/09/23 09:28:41 - mmengine - INFO - Epoch(val) [100][150/407] eta: 0:02:03 time: 0.478663 data_time: 0.038466 memory: 1464 2022/09/23 09:29:02 - mmengine - INFO - Epoch(val) [100][200/407] eta: 0:01:26 time: 0.416967 data_time: 0.033367 memory: 1464 2022/09/23 09:29:22 - mmengine - INFO - Epoch(val) [100][250/407] eta: 0:01:00 time: 0.387323 data_time: 0.048595 memory: 1464 2022/09/23 09:29:45 - mmengine - INFO - Epoch(val) [100][300/407] eta: 0:00:50 time: 0.470756 data_time: 0.037199 memory: 1464 2022/09/23 09:30:04 - mmengine - INFO - Epoch(val) [100][350/407] eta: 0:00:21 time: 0.377647 data_time: 0.028369 memory: 1464 2022/09/23 09:30:18 - mmengine - INFO - Epoch(val) [100][400/407] eta: 0:00:01 time: 0.277200 data_time: 0.011935 memory: 1464 2022/09/23 09:30:56 - mmengine - INFO - Evaluating CocoMetric... 2022/09/23 09:31:10 - mmengine - INFO - Epoch(val) [100][407/407] coco/AP: 0.709303 coco/AP .5: 0.891830 coco/AP .75: 0.777580 coco/AP (M): 0.664228 coco/AP (L): 0.784620 coco/AR: 0.762941 coco/AR .5: 0.930101 coco/AR .75: 0.825882 coco/AR (M): 0.713384 coco/AR (L): 0.833259 2022/09/23 09:32:16 - mmengine - INFO - Epoch(train) [101][50/293] lr: 5.000000e-04 eta: 8:49:16 time: 1.316208 data_time: 0.125748 memory: 14267 loss_kpt: 0.000654 acc_pose: 0.811560 loss: 0.000654 2022/09/23 09:33:16 - mmengine - INFO - Epoch(train) [101][100/293] lr: 5.000000e-04 eta: 8:48:38 time: 1.200059 data_time: 0.118272 memory: 14267 loss_kpt: 0.000636 acc_pose: 0.862304 loss: 0.000636 2022/09/23 09:34:21 - mmengine - INFO - Epoch(train) [101][150/293] lr: 5.000000e-04 eta: 8:48:07 time: 1.313361 data_time: 0.114329 memory: 14267 loss_kpt: 0.000639 acc_pose: 0.824805 loss: 0.000639 2022/09/23 09:35:25 - mmengine - INFO - Epoch(train) [101][200/293] lr: 5.000000e-04 eta: 8:47:32 time: 1.266313 data_time: 0.113357 memory: 14267 loss_kpt: 0.000640 acc_pose: 0.856719 loss: 0.000640 2022/09/23 09:36:30 - mmengine - INFO - Epoch(train) [101][250/293] lr: 5.000000e-04 eta: 8:47:01 time: 1.315885 data_time: 0.114829 memory: 14267 loss_kpt: 0.000632 acc_pose: 0.858690 loss: 0.000632 2022/09/23 09:37:22 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 09:38:30 - mmengine - INFO - Epoch(train) [102][50/293] lr: 5.000000e-04 eta: 8:45:03 time: 1.355165 data_time: 0.169996 memory: 14267 loss_kpt: 0.000634 acc_pose: 0.823915 loss: 0.000634 2022/09/23 09:39:33 - mmengine - INFO - Epoch(train) [102][100/293] lr: 5.000000e-04 eta: 8:44:28 time: 1.263907 data_time: 0.138390 memory: 14267 loss_kpt: 0.000642 acc_pose: 0.815009 loss: 0.000642 2022/09/23 09:40:39 - mmengine - INFO - Epoch(train) [102][150/293] lr: 5.000000e-04 eta: 8:43:56 time: 1.312515 data_time: 0.125793 memory: 14267 loss_kpt: 0.000645 acc_pose: 0.848309 loss: 0.000645 2022/09/23 09:41:40 - mmengine - INFO - Epoch(train) [102][200/293] lr: 5.000000e-04 eta: 8:43:18 time: 1.214942 data_time: 0.110020 memory: 14267 loss_kpt: 0.000639 acc_pose: 0.794912 loss: 0.000639 2022/09/23 09:42:47 - mmengine - INFO - Epoch(train) [102][250/293] lr: 5.000000e-04 eta: 8:42:48 time: 1.340099 data_time: 0.116092 memory: 14267 loss_kpt: 0.000624 acc_pose: 0.810384 loss: 0.000624 2022/09/23 09:43:40 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 09:44:45 - mmengine - INFO - Epoch(train) [103][50/293] lr: 5.000000e-04 eta: 8:40:47 time: 1.300225 data_time: 0.116978 memory: 14267 loss_kpt: 0.000640 acc_pose: 0.814362 loss: 0.000640 2022/09/23 09:45:45 - mmengine - INFO - Epoch(train) [103][100/293] lr: 5.000000e-04 eta: 8:40:08 time: 1.184328 data_time: 0.123746 memory: 14267 loss_kpt: 0.000648 acc_pose: 0.776486 loss: 0.000648 2022/09/23 09:46:03 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 09:46:52 - mmengine - INFO - Epoch(train) [103][150/293] lr: 5.000000e-04 eta: 8:39:37 time: 1.337808 data_time: 0.110278 memory: 14267 loss_kpt: 0.000647 acc_pose: 0.816507 loss: 0.000647 2022/09/23 09:47:55 - mmengine - INFO - Epoch(train) [103][200/293] lr: 5.000000e-04 eta: 8:39:01 time: 1.264956 data_time: 0.104483 memory: 14267 loss_kpt: 0.000639 acc_pose: 0.817187 loss: 0.000639 2022/09/23 09:48:59 - mmengine - INFO - Epoch(train) [103][250/293] lr: 5.000000e-04 eta: 8:38:27 time: 1.276028 data_time: 0.105005 memory: 14267 loss_kpt: 0.000633 acc_pose: 0.823576 loss: 0.000633 2022/09/23 09:49:51 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 09:50:52 - mmengine - INFO - Epoch(train) [104][50/293] lr: 5.000000e-04 eta: 8:36:23 time: 1.235213 data_time: 0.144883 memory: 14267 loss_kpt: 0.000639 acc_pose: 0.790645 loss: 0.000639 2022/09/23 09:51:59 - mmengine - INFO - Epoch(train) [104][100/293] lr: 5.000000e-04 eta: 8:35:52 time: 1.338428 data_time: 0.107876 memory: 14267 loss_kpt: 0.000650 acc_pose: 0.781800 loss: 0.000650 2022/09/23 09:52:59 - mmengine - INFO - Epoch(train) [104][150/293] lr: 5.000000e-04 eta: 8:35:13 time: 1.198651 data_time: 0.104258 memory: 14267 loss_kpt: 0.000644 acc_pose: 0.804371 loss: 0.000644 2022/09/23 09:53:58 - mmengine - INFO - Epoch(train) [104][200/293] lr: 5.000000e-04 eta: 8:34:32 time: 1.168607 data_time: 0.123508 memory: 14267 loss_kpt: 0.000654 acc_pose: 0.810618 loss: 0.000654 2022/09/23 09:55:03 - mmengine - INFO - Epoch(train) [104][250/293] lr: 5.000000e-04 eta: 8:33:59 time: 1.302265 data_time: 0.103523 memory: 14267 loss_kpt: 0.000635 acc_pose: 0.807864 loss: 0.000635 2022/09/23 09:55:56 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 09:57:05 - mmengine - INFO - Epoch(train) [105][50/293] lr: 5.000000e-04 eta: 8:32:03 time: 1.382033 data_time: 0.128347 memory: 14267 loss_kpt: 0.000636 acc_pose: 0.796753 loss: 0.000636 2022/09/23 09:58:01 - mmengine - INFO - Epoch(train) [105][100/293] lr: 5.000000e-04 eta: 8:31:20 time: 1.117613 data_time: 0.112033 memory: 14267 loss_kpt: 0.000641 acc_pose: 0.825073 loss: 0.000641 2022/09/23 09:59:08 - mmengine - INFO - Epoch(train) [105][150/293] lr: 5.000000e-04 eta: 8:30:48 time: 1.339012 data_time: 0.128162 memory: 14267 loss_kpt: 0.000637 acc_pose: 0.796518 loss: 0.000637 2022/09/23 10:00:09 - mmengine - INFO - Epoch(train) [105][200/293] lr: 5.000000e-04 eta: 8:30:09 time: 1.208456 data_time: 0.108220 memory: 14267 loss_kpt: 0.000646 acc_pose: 0.824593 loss: 0.000646 2022/09/23 10:01:17 - mmengine - INFO - Epoch(train) [105][250/293] lr: 5.000000e-04 eta: 8:29:39 time: 1.375638 data_time: 0.113358 memory: 14267 loss_kpt: 0.000650 acc_pose: 0.796104 loss: 0.000650 2022/09/23 10:02:06 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 10:03:12 - mmengine - INFO - Epoch(train) [106][50/293] lr: 5.000000e-04 eta: 8:27:40 time: 1.314370 data_time: 0.132812 memory: 14267 loss_kpt: 0.000637 acc_pose: 0.786055 loss: 0.000637 2022/09/23 10:04:19 - mmengine - INFO - Epoch(train) [106][100/293] lr: 5.000000e-04 eta: 8:27:08 time: 1.336411 data_time: 0.111393 memory: 14267 loss_kpt: 0.000635 acc_pose: 0.821698 loss: 0.000635 2022/09/23 10:05:23 - mmengine - INFO - Epoch(train) [106][150/293] lr: 5.000000e-04 eta: 8:26:32 time: 1.276696 data_time: 0.113535 memory: 14267 loss_kpt: 0.000628 acc_pose: 0.871996 loss: 0.000628 2022/09/23 10:06:24 - mmengine - INFO - Epoch(train) [106][200/293] lr: 5.000000e-04 eta: 8:25:54 time: 1.234303 data_time: 0.119045 memory: 14267 loss_kpt: 0.000635 acc_pose: 0.793708 loss: 0.000635 2022/09/23 10:07:05 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 10:07:26 - mmengine - INFO - Epoch(train) [106][250/293] lr: 5.000000e-04 eta: 8:25:16 time: 1.227470 data_time: 0.107941 memory: 14267 loss_kpt: 0.000640 acc_pose: 0.806985 loss: 0.000640 2022/09/23 10:08:22 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 10:09:28 - mmengine - INFO - Epoch(train) [107][50/293] lr: 5.000000e-04 eta: 8:23:17 time: 1.304209 data_time: 0.144439 memory: 14267 loss_kpt: 0.000643 acc_pose: 0.809166 loss: 0.000643 2022/09/23 10:10:27 - mmengine - INFO - Epoch(train) [107][100/293] lr: 5.000000e-04 eta: 8:22:37 time: 1.191729 data_time: 0.117014 memory: 14267 loss_kpt: 0.000645 acc_pose: 0.834317 loss: 0.000645 2022/09/23 10:11:32 - mmengine - INFO - Epoch(train) [107][150/293] lr: 5.000000e-04 eta: 8:22:02 time: 1.291045 data_time: 0.103103 memory: 14267 loss_kpt: 0.000650 acc_pose: 0.808835 loss: 0.000650 2022/09/23 10:12:34 - mmengine - INFO - Epoch(train) [107][200/293] lr: 5.000000e-04 eta: 8:21:25 time: 1.243379 data_time: 0.105378 memory: 14267 loss_kpt: 0.000649 acc_pose: 0.815671 loss: 0.000649 2022/09/23 10:13:41 - mmengine - INFO - Epoch(train) [107][250/293] lr: 5.000000e-04 eta: 8:20:51 time: 1.333634 data_time: 0.105829 memory: 14267 loss_kpt: 0.000636 acc_pose: 0.842971 loss: 0.000636 2022/09/23 10:14:28 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 10:15:37 - mmengine - INFO - Epoch(train) [108][50/293] lr: 5.000000e-04 eta: 8:18:56 time: 1.376579 data_time: 0.135266 memory: 14267 loss_kpt: 0.000634 acc_pose: 0.771837 loss: 0.000634 2022/09/23 10:16:40 - mmengine - INFO - Epoch(train) [108][100/293] lr: 5.000000e-04 eta: 8:18:19 time: 1.245415 data_time: 0.107315 memory: 14267 loss_kpt: 0.000627 acc_pose: 0.821309 loss: 0.000627 2022/09/23 10:17:54 - mmengine - INFO - Epoch(train) [108][150/293] lr: 5.000000e-04 eta: 8:17:52 time: 1.488513 data_time: 0.114756 memory: 14267 loss_kpt: 0.000652 acc_pose: 0.774781 loss: 0.000652 2022/09/23 10:19:07 - mmengine - INFO - Epoch(train) [108][200/293] lr: 5.000000e-04 eta: 8:17:25 time: 1.457652 data_time: 0.113765 memory: 14267 loss_kpt: 0.000625 acc_pose: 0.855613 loss: 0.000625 2022/09/23 10:20:26 - mmengine - INFO - Epoch(train) [108][250/293] lr: 5.000000e-04 eta: 8:17:03 time: 1.581236 data_time: 0.103715 memory: 14267 loss_kpt: 0.000649 acc_pose: 0.825402 loss: 0.000649 2022/09/23 10:21:32 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 10:22:49 - mmengine - INFO - Epoch(train) [109][50/293] lr: 5.000000e-04 eta: 8:15:15 time: 1.538441 data_time: 0.207122 memory: 14267 loss_kpt: 0.000619 acc_pose: 0.766548 loss: 0.000619 2022/09/23 10:24:03 - mmengine - INFO - Epoch(train) [109][100/293] lr: 5.000000e-04 eta: 8:14:48 time: 1.488272 data_time: 0.148222 memory: 14267 loss_kpt: 0.000638 acc_pose: 0.824016 loss: 0.000638 2022/09/23 10:25:04 - mmengine - INFO - Epoch(train) [109][150/293] lr: 5.000000e-04 eta: 8:14:09 time: 1.221034 data_time: 0.117031 memory: 14267 loss_kpt: 0.000649 acc_pose: 0.762598 loss: 0.000649 2022/09/23 10:26:10 - mmengine - INFO - Epoch(train) [109][200/293] lr: 5.000000e-04 eta: 8:13:34 time: 1.322233 data_time: 0.112678 memory: 14267 loss_kpt: 0.000652 acc_pose: 0.833602 loss: 0.000652 2022/09/23 10:27:11 - mmengine - INFO - Epoch(train) [109][250/293] lr: 5.000000e-04 eta: 8:12:54 time: 1.208755 data_time: 0.104527 memory: 14267 loss_kpt: 0.000636 acc_pose: 0.858126 loss: 0.000636 2022/09/23 10:28:08 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 10:29:25 - mmengine - INFO - Epoch(train) [110][50/293] lr: 5.000000e-04 eta: 8:11:07 time: 1.532749 data_time: 0.138316 memory: 14267 loss_kpt: 0.000641 acc_pose: 0.824754 loss: 0.000641 2022/09/23 10:29:43 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 10:30:42 - mmengine - INFO - Epoch(train) [110][100/293] lr: 5.000000e-04 eta: 8:10:42 time: 1.550252 data_time: 0.104886 memory: 14267 loss_kpt: 0.000626 acc_pose: 0.823417 loss: 0.000626 2022/09/23 10:31:58 - mmengine - INFO - Epoch(train) [110][150/293] lr: 5.000000e-04 eta: 8:10:16 time: 1.513553 data_time: 0.115263 memory: 14267 loss_kpt: 0.000630 acc_pose: 0.835316 loss: 0.000630 2022/09/23 10:33:08 - mmengine - INFO - Epoch(train) [110][200/293] lr: 5.000000e-04 eta: 8:09:44 time: 1.403966 data_time: 0.108747 memory: 14267 loss_kpt: 0.000636 acc_pose: 0.856217 loss: 0.000636 2022/09/23 10:34:21 - mmengine - INFO - Epoch(train) [110][250/293] lr: 5.000000e-04 eta: 8:09:15 time: 1.459090 data_time: 0.125616 memory: 14267 loss_kpt: 0.000636 acc_pose: 0.856241 loss: 0.000636 2022/09/23 10:35:17 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 10:35:17 - mmengine - INFO - Saving checkpoint at 110 epochs 2022/09/23 10:35:52 - mmengine - INFO - Epoch(val) [110][50/407] eta: 0:03:13 time: 0.543069 data_time: 0.048262 memory: 14267 2022/09/23 10:36:19 - mmengine - INFO - Epoch(val) [110][100/407] eta: 0:02:42 time: 0.528965 data_time: 0.036616 memory: 1464 2022/09/23 10:36:42 - mmengine - INFO - Epoch(val) [110][150/407] eta: 0:01:59 time: 0.466849 data_time: 0.025182 memory: 1464 2022/09/23 10:37:05 - mmengine - INFO - Epoch(val) [110][200/407] eta: 0:01:33 time: 0.452973 data_time: 0.028821 memory: 1464 2022/09/23 10:37:29 - mmengine - INFO - Epoch(val) [110][250/407] eta: 0:01:17 time: 0.494230 data_time: 0.029057 memory: 1464 2022/09/23 10:37:53 - mmengine - INFO - Epoch(val) [110][300/407] eta: 0:00:49 time: 0.462595 data_time: 0.027421 memory: 1464 2022/09/23 10:38:09 - mmengine - INFO - Epoch(val) [110][350/407] eta: 0:00:19 time: 0.336089 data_time: 0.012749 memory: 1464 2022/09/23 10:38:25 - mmengine - INFO - Epoch(val) [110][400/407] eta: 0:00:02 time: 0.318893 data_time: 0.012316 memory: 1464 2022/09/23 10:39:01 - mmengine - INFO - Evaluating CocoMetric... 2022/09/23 10:39:14 - mmengine - INFO - Epoch(val) [110][407/407] coco/AP: 0.708343 coco/AP .5: 0.892584 coco/AP .75: 0.779484 coco/AP (M): 0.662501 coco/AP (L): 0.785303 coco/AR: 0.763791 coco/AR .5: 0.930888 coco/AR .75: 0.827771 coco/AR (M): 0.712101 coco/AR (L): 0.836789 2022/09/23 10:40:40 - mmengine - INFO - Epoch(train) [111][50/293] lr: 5.000000e-04 eta: 8:07:36 time: 1.720884 data_time: 0.155978 memory: 14267 loss_kpt: 0.000628 acc_pose: 0.863836 loss: 0.000628 2022/09/23 10:42:08 - mmengine - INFO - Epoch(train) [111][100/293] lr: 5.000000e-04 eta: 8:07:20 time: 1.744423 data_time: 0.143571 memory: 14267 loss_kpt: 0.000630 acc_pose: 0.834339 loss: 0.000630 2022/09/23 10:43:24 - mmengine - INFO - Epoch(train) [111][150/293] lr: 5.000000e-04 eta: 8:06:53 time: 1.531875 data_time: 0.137512 memory: 14267 loss_kpt: 0.000633 acc_pose: 0.856317 loss: 0.000633 2022/09/23 10:44:39 - mmengine - INFO - Epoch(train) [111][200/293] lr: 5.000000e-04 eta: 8:06:26 time: 1.504263 data_time: 0.128046 memory: 14267 loss_kpt: 0.000631 acc_pose: 0.822856 loss: 0.000631 2022/09/23 10:45:56 - mmengine - INFO - Epoch(train) [111][250/293] lr: 5.000000e-04 eta: 8:06:00 time: 1.537484 data_time: 0.135336 memory: 14267 loss_kpt: 0.000648 acc_pose: 0.830603 loss: 0.000648 2022/09/23 10:46:49 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 10:47:58 - mmengine - INFO - Epoch(train) [112][50/293] lr: 5.000000e-04 eta: 8:04:05 time: 1.393742 data_time: 0.157299 memory: 14267 loss_kpt: 0.000646 acc_pose: 0.845558 loss: 0.000646 2022/09/23 10:48:58 - mmengine - INFO - Epoch(train) [112][100/293] lr: 5.000000e-04 eta: 8:03:23 time: 1.189935 data_time: 0.107183 memory: 14267 loss_kpt: 0.000632 acc_pose: 0.765437 loss: 0.000632 2022/09/23 10:50:05 - mmengine - INFO - Epoch(train) [112][150/293] lr: 5.000000e-04 eta: 8:02:48 time: 1.342758 data_time: 0.111814 memory: 14267 loss_kpt: 0.000637 acc_pose: 0.791114 loss: 0.000637 2022/09/23 10:51:00 - mmengine - INFO - Epoch(train) [112][200/293] lr: 5.000000e-04 eta: 8:02:02 time: 1.098504 data_time: 0.105421 memory: 14267 loss_kpt: 0.000637 acc_pose: 0.820672 loss: 0.000637 2022/09/23 10:52:09 - mmengine - INFO - Epoch(train) [112][250/293] lr: 5.000000e-04 eta: 8:01:28 time: 1.375158 data_time: 0.132482 memory: 14267 loss_kpt: 0.000635 acc_pose: 0.810608 loss: 0.000635 2022/09/23 10:53:03 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 10:54:08 - mmengine - INFO - Epoch(train) [113][50/293] lr: 5.000000e-04 eta: 7:59:30 time: 1.296598 data_time: 0.125312 memory: 14267 loss_kpt: 0.000640 acc_pose: 0.784935 loss: 0.000640 2022/09/23 10:55:17 - mmengine - INFO - Epoch(train) [113][100/293] lr: 5.000000e-04 eta: 7:58:55 time: 1.367414 data_time: 0.116327 memory: 14267 loss_kpt: 0.000635 acc_pose: 0.835056 loss: 0.000635 2022/09/23 10:56:30 - mmengine - INFO - Epoch(train) [113][150/293] lr: 5.000000e-04 eta: 7:58:25 time: 1.467023 data_time: 0.114630 memory: 14267 loss_kpt: 0.000626 acc_pose: 0.762578 loss: 0.000626 2022/09/23 10:57:24 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 10:57:50 - mmengine - INFO - Epoch(train) [113][200/293] lr: 5.000000e-04 eta: 7:58:01 time: 1.600450 data_time: 0.123118 memory: 14267 loss_kpt: 0.000634 acc_pose: 0.802459 loss: 0.000634 2022/09/23 10:59:02 - mmengine - INFO - Epoch(train) [113][250/293] lr: 5.000000e-04 eta: 7:57:30 time: 1.449533 data_time: 0.106837 memory: 14267 loss_kpt: 0.000637 acc_pose: 0.842259 loss: 0.000637 2022/09/23 11:00:02 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 11:01:21 - mmengine - INFO - Epoch(train) [114][50/293] lr: 5.000000e-04 eta: 7:55:43 time: 1.568693 data_time: 0.177920 memory: 14267 loss_kpt: 0.000633 acc_pose: 0.816689 loss: 0.000633 2022/09/23 11:02:25 - mmengine - INFO - Epoch(train) [114][100/293] lr: 5.000000e-04 eta: 7:55:05 time: 1.291772 data_time: 0.124905 memory: 14267 loss_kpt: 0.000627 acc_pose: 0.786489 loss: 0.000627 2022/09/23 11:03:30 - mmengine - INFO - Epoch(train) [114][150/293] lr: 5.000000e-04 eta: 7:54:27 time: 1.305322 data_time: 0.114549 memory: 14267 loss_kpt: 0.000626 acc_pose: 0.824787 loss: 0.000626 2022/09/23 11:04:29 - mmengine - INFO - Epoch(train) [114][200/293] lr: 5.000000e-04 eta: 7:53:44 time: 1.166082 data_time: 0.110381 memory: 14267 loss_kpt: 0.000627 acc_pose: 0.871984 loss: 0.000627 2022/09/23 11:05:38 - mmengine - INFO - Epoch(train) [114][250/293] lr: 5.000000e-04 eta: 7:53:09 time: 1.377244 data_time: 0.114618 memory: 14267 loss_kpt: 0.000633 acc_pose: 0.814188 loss: 0.000633 2022/09/23 11:06:29 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 11:07:39 - mmengine - INFO - Epoch(train) [115][50/293] lr: 5.000000e-04 eta: 7:51:15 time: 1.386374 data_time: 0.127758 memory: 14267 loss_kpt: 0.000624 acc_pose: 0.819458 loss: 0.000624 2022/09/23 11:08:35 - mmengine - INFO - Epoch(train) [115][100/293] lr: 5.000000e-04 eta: 7:50:29 time: 1.127650 data_time: 0.105186 memory: 14267 loss_kpt: 0.000637 acc_pose: 0.839632 loss: 0.000637 2022/09/23 11:09:38 - mmengine - INFO - Epoch(train) [115][150/293] lr: 5.000000e-04 eta: 7:49:50 time: 1.264653 data_time: 0.116897 memory: 14267 loss_kpt: 0.000634 acc_pose: 0.835984 loss: 0.000634 2022/09/23 11:10:40 - mmengine - INFO - Epoch(train) [115][200/293] lr: 5.000000e-04 eta: 7:49:08 time: 1.226090 data_time: 0.130072 memory: 14267 loss_kpt: 0.000625 acc_pose: 0.854873 loss: 0.000625 2022/09/23 11:11:41 - mmengine - INFO - Epoch(train) [115][250/293] lr: 5.000000e-04 eta: 7:48:27 time: 1.221013 data_time: 0.107118 memory: 14267 loss_kpt: 0.000642 acc_pose: 0.863000 loss: 0.000642 2022/09/23 11:12:31 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 11:13:34 - mmengine - INFO - Epoch(train) [116][50/293] lr: 5.000000e-04 eta: 7:46:28 time: 1.254712 data_time: 0.147932 memory: 14267 loss_kpt: 0.000636 acc_pose: 0.766668 loss: 0.000636 2022/09/23 11:14:37 - mmengine - INFO - Epoch(train) [116][100/293] lr: 5.000000e-04 eta: 7:45:47 time: 1.253323 data_time: 0.107451 memory: 14267 loss_kpt: 0.000630 acc_pose: 0.809540 loss: 0.000630 2022/09/23 11:15:39 - mmengine - INFO - Epoch(train) [116][150/293] lr: 5.000000e-04 eta: 7:45:06 time: 1.236281 data_time: 0.105971 memory: 14267 loss_kpt: 0.000627 acc_pose: 0.773574 loss: 0.000627 2022/09/23 11:16:38 - mmengine - INFO - Epoch(train) [116][200/293] lr: 5.000000e-04 eta: 7:44:23 time: 1.179829 data_time: 0.124311 memory: 14267 loss_kpt: 0.000640 acc_pose: 0.776017 loss: 0.000640 2022/09/23 11:17:40 - mmengine - INFO - Epoch(train) [116][250/293] lr: 5.000000e-04 eta: 7:43:42 time: 1.241540 data_time: 0.121372 memory: 14267 loss_kpt: 0.000638 acc_pose: 0.828750 loss: 0.000638 2022/09/23 11:18:29 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 11:18:46 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 11:19:36 - mmengine - INFO - Epoch(train) [117][50/293] lr: 5.000000e-04 eta: 7:41:46 time: 1.336847 data_time: 0.199680 memory: 14267 loss_kpt: 0.000623 acc_pose: 0.848376 loss: 0.000623 2022/09/23 11:20:38 - mmengine - INFO - Epoch(train) [117][100/293] lr: 5.000000e-04 eta: 7:41:05 time: 1.227672 data_time: 0.142286 memory: 14267 loss_kpt: 0.000631 acc_pose: 0.837181 loss: 0.000631 2022/09/23 11:21:37 - mmengine - INFO - Epoch(train) [117][150/293] lr: 5.000000e-04 eta: 7:40:22 time: 1.189669 data_time: 0.108292 memory: 14267 loss_kpt: 0.000630 acc_pose: 0.804637 loss: 0.000630 2022/09/23 11:22:17 - mmengine - INFO - Epoch(train) [117][200/293] lr: 5.000000e-04 eta: 7:39:23 time: 0.797203 data_time: 0.113830 memory: 14267 loss_kpt: 0.000616 acc_pose: 0.839770 loss: 0.000616 2022/09/23 11:22:47 - mmengine - INFO - Epoch(train) [117][250/293] lr: 5.000000e-04 eta: 7:38:16 time: 0.590664 data_time: 0.092573 memory: 14267 loss_kpt: 0.000623 acc_pose: 0.831309 loss: 0.000623 2022/09/23 11:23:11 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 11:23:42 - mmengine - INFO - Epoch(train) [118][50/293] lr: 5.000000e-04 eta: 7:35:53 time: 0.621897 data_time: 0.117943 memory: 14267 loss_kpt: 0.000623 acc_pose: 0.794253 loss: 0.000623 2022/09/23 11:24:12 - mmengine - INFO - Epoch(train) [118][100/293] lr: 5.000000e-04 eta: 7:34:46 time: 0.596568 data_time: 0.095896 memory: 14267 loss_kpt: 0.000633 acc_pose: 0.835861 loss: 0.000633 2022/09/23 11:24:41 - mmengine - INFO - Epoch(train) [118][150/293] lr: 5.000000e-04 eta: 7:33:39 time: 0.573569 data_time: 0.078181 memory: 14267 loss_kpt: 0.000640 acc_pose: 0.832353 loss: 0.000640 2022/09/23 11:25:11 - mmengine - INFO - Epoch(train) [118][200/293] lr: 5.000000e-04 eta: 7:32:33 time: 0.605248 data_time: 0.104703 memory: 14267 loss_kpt: 0.000630 acc_pose: 0.808958 loss: 0.000630 2022/09/23 11:25:42 - mmengine - INFO - Epoch(train) [118][250/293] lr: 5.000000e-04 eta: 7:31:27 time: 0.605549 data_time: 0.085627 memory: 14267 loss_kpt: 0.000613 acc_pose: 0.839602 loss: 0.000613 2022/09/23 11:26:08 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 11:26:38 - mmengine - INFO - Epoch(train) [119][50/293] lr: 5.000000e-04 eta: 7:29:05 time: 0.606200 data_time: 0.116066 memory: 14267 loss_kpt: 0.000635 acc_pose: 0.829318 loss: 0.000635 2022/09/23 11:27:08 - mmengine - INFO - Epoch(train) [119][100/293] lr: 5.000000e-04 eta: 7:27:59 time: 0.586516 data_time: 0.093782 memory: 14267 loss_kpt: 0.000610 acc_pose: 0.832888 loss: 0.000610 2022/09/23 11:27:37 - mmengine - INFO - Epoch(train) [119][150/293] lr: 5.000000e-04 eta: 7:26:53 time: 0.586606 data_time: 0.089106 memory: 14267 loss_kpt: 0.000630 acc_pose: 0.805678 loss: 0.000630 2022/09/23 11:28:08 - mmengine - INFO - Epoch(train) [119][200/293] lr: 5.000000e-04 eta: 7:25:48 time: 0.614265 data_time: 0.089026 memory: 14267 loss_kpt: 0.000629 acc_pose: 0.819465 loss: 0.000629 2022/09/23 11:28:36 - mmengine - INFO - Epoch(train) [119][250/293] lr: 5.000000e-04 eta: 7:24:41 time: 0.566922 data_time: 0.089583 memory: 14267 loss_kpt: 0.000635 acc_pose: 0.833686 loss: 0.000635 2022/09/23 11:29:01 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 11:29:32 - mmengine - INFO - Epoch(train) [120][50/293] lr: 5.000000e-04 eta: 7:22:21 time: 0.618472 data_time: 0.095422 memory: 14267 loss_kpt: 0.000626 acc_pose: 0.767881 loss: 0.000626 2022/09/23 11:30:02 - mmengine - INFO - Epoch(train) [120][100/293] lr: 5.000000e-04 eta: 7:21:16 time: 0.583878 data_time: 0.089382 memory: 14267 loss_kpt: 0.000641 acc_pose: 0.849193 loss: 0.000641 2022/09/23 11:30:21 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 11:30:31 - mmengine - INFO - Epoch(train) [120][150/293] lr: 5.000000e-04 eta: 7:20:10 time: 0.583602 data_time: 0.094336 memory: 14267 loss_kpt: 0.000647 acc_pose: 0.852109 loss: 0.000647 2022/09/23 11:31:00 - mmengine - INFO - Epoch(train) [120][200/293] lr: 5.000000e-04 eta: 7:19:05 time: 0.584817 data_time: 0.105194 memory: 14267 loss_kpt: 0.000641 acc_pose: 0.855752 loss: 0.000641 2022/09/23 11:31:30 - mmengine - INFO - Epoch(train) [120][250/293] lr: 5.000000e-04 eta: 7:18:00 time: 0.603079 data_time: 0.111236 memory: 14267 loss_kpt: 0.000620 acc_pose: 0.867924 loss: 0.000620 2022/09/23 11:31:54 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 11:31:54 - mmengine - INFO - Saving checkpoint at 120 epochs 2022/09/23 11:32:16 - mmengine - INFO - Epoch(val) [120][50/407] eta: 0:02:02 time: 0.343943 data_time: 0.170664 memory: 14267 2022/09/23 11:32:32 - mmengine - INFO - Epoch(val) [120][100/407] eta: 0:01:36 time: 0.314809 data_time: 0.151643 memory: 1464 2022/09/23 11:32:48 - mmengine - INFO - Epoch(val) [120][150/407] eta: 0:01:23 time: 0.323728 data_time: 0.151747 memory: 1464 2022/09/23 11:33:04 - mmengine - INFO - Epoch(val) [120][200/407] eta: 0:01:03 time: 0.307659 data_time: 0.155281 memory: 1464 2022/09/23 11:33:20 - mmengine - INFO - Epoch(val) [120][250/407] eta: 0:00:50 time: 0.320364 data_time: 0.148874 memory: 1464 2022/09/23 11:33:35 - mmengine - INFO - Epoch(val) [120][300/407] eta: 0:00:33 time: 0.309935 data_time: 0.148072 memory: 1464 2022/09/23 11:33:51 - mmengine - INFO - Epoch(val) [120][350/407] eta: 0:00:18 time: 0.323021 data_time: 0.167110 memory: 1464 2022/09/23 11:34:04 - mmengine - INFO - Epoch(val) [120][400/407] eta: 0:00:01 time: 0.252903 data_time: 0.122941 memory: 1464 2022/09/23 11:34:38 - mmengine - INFO - Evaluating CocoMetric... 2022/09/23 11:34:51 - mmengine - INFO - Epoch(val) [120][407/407] coco/AP: 0.714877 coco/AP .5: 0.892785 coco/AP .75: 0.788164 coco/AP (M): 0.670434 coco/AP (L): 0.789145 coco/AR: 0.767616 coco/AR .5: 0.929943 coco/AR .75: 0.832021 coco/AR (M): 0.717864 coco/AR (L): 0.838424 2022/09/23 11:34:51 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220922/res50_384_2/best_coco/AP_epoch_90.pth is removed 2022/09/23 11:34:53 - mmengine - INFO - The best checkpoint with 0.7149 coco/AP at 120 epoch is saved to best_coco/AP_epoch_120.pth. 2022/09/23 11:35:23 - mmengine - INFO - Epoch(train) [121][50/293] lr: 5.000000e-04 eta: 7:15:40 time: 0.587042 data_time: 0.106717 memory: 14267 loss_kpt: 0.000632 acc_pose: 0.739717 loss: 0.000632 2022/09/23 11:35:52 - mmengine - INFO - Epoch(train) [121][100/293] lr: 5.000000e-04 eta: 7:14:36 time: 0.587893 data_time: 0.085603 memory: 14267 loss_kpt: 0.000631 acc_pose: 0.836636 loss: 0.000631 2022/09/23 11:36:21 - mmengine - INFO - Epoch(train) [121][150/293] lr: 5.000000e-04 eta: 7:13:31 time: 0.582798 data_time: 0.077830 memory: 14267 loss_kpt: 0.000617 acc_pose: 0.796848 loss: 0.000617 2022/09/23 11:36:51 - mmengine - INFO - Epoch(train) [121][200/293] lr: 5.000000e-04 eta: 7:12:27 time: 0.604100 data_time: 0.105019 memory: 14267 loss_kpt: 0.000641 acc_pose: 0.856031 loss: 0.000641 2022/09/23 11:37:21 - mmengine - INFO - Epoch(train) [121][250/293] lr: 5.000000e-04 eta: 7:11:22 time: 0.588046 data_time: 0.101602 memory: 14267 loss_kpt: 0.000629 acc_pose: 0.777704 loss: 0.000629 2022/09/23 11:37:46 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 11:38:17 - mmengine - INFO - Epoch(train) [122][50/293] lr: 5.000000e-04 eta: 7:09:06 time: 0.623042 data_time: 0.122845 memory: 14267 loss_kpt: 0.000635 acc_pose: 0.837612 loss: 0.000635 2022/09/23 11:38:46 - mmengine - INFO - Epoch(train) [122][100/293] lr: 5.000000e-04 eta: 7:08:01 time: 0.583846 data_time: 0.097903 memory: 14267 loss_kpt: 0.000643 acc_pose: 0.815348 loss: 0.000643 2022/09/23 11:39:16 - mmengine - INFO - Epoch(train) [122][150/293] lr: 5.000000e-04 eta: 7:06:57 time: 0.591344 data_time: 0.087273 memory: 14267 loss_kpt: 0.000649 acc_pose: 0.836675 loss: 0.000649 2022/09/23 11:39:46 - mmengine - INFO - Epoch(train) [122][200/293] lr: 5.000000e-04 eta: 7:05:54 time: 0.599172 data_time: 0.092758 memory: 14267 loss_kpt: 0.000614 acc_pose: 0.806609 loss: 0.000614 2022/09/23 11:40:15 - mmengine - INFO - Epoch(train) [122][250/293] lr: 5.000000e-04 eta: 7:04:50 time: 0.584347 data_time: 0.089943 memory: 14267 loss_kpt: 0.000621 acc_pose: 0.868394 loss: 0.000621 2022/09/23 11:40:40 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 11:41:11 - mmengine - INFO - Epoch(train) [123][50/293] lr: 5.000000e-04 eta: 7:02:34 time: 0.612052 data_time: 0.114387 memory: 14267 loss_kpt: 0.000628 acc_pose: 0.801349 loss: 0.000628 2022/09/23 11:41:41 - mmengine - INFO - Epoch(train) [123][100/293] lr: 5.000000e-04 eta: 7:01:31 time: 0.596771 data_time: 0.114468 memory: 14267 loss_kpt: 0.000627 acc_pose: 0.820088 loss: 0.000627 2022/09/23 11:42:10 - mmengine - INFO - Epoch(train) [123][150/293] lr: 5.000000e-04 eta: 7:00:28 time: 0.587375 data_time: 0.092985 memory: 14267 loss_kpt: 0.000619 acc_pose: 0.846904 loss: 0.000619 2022/09/23 11:42:40 - mmengine - INFO - Epoch(train) [123][200/293] lr: 5.000000e-04 eta: 6:59:24 time: 0.593317 data_time: 0.105390 memory: 14267 loss_kpt: 0.000645 acc_pose: 0.842931 loss: 0.000645 2022/09/23 11:43:09 - mmengine - INFO - Epoch(train) [123][250/293] lr: 5.000000e-04 eta: 6:58:21 time: 0.578670 data_time: 0.095631 memory: 14267 loss_kpt: 0.000623 acc_pose: 0.822943 loss: 0.000623 2022/09/23 11:43:11 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 11:43:32 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 11:44:03 - mmengine - INFO - Epoch(train) [124][50/293] lr: 5.000000e-04 eta: 6:56:06 time: 0.606611 data_time: 0.103167 memory: 14267 loss_kpt: 0.000623 acc_pose: 0.870300 loss: 0.000623 2022/09/23 11:44:33 - mmengine - INFO - Epoch(train) [124][100/293] lr: 5.000000e-04 eta: 6:55:04 time: 0.602353 data_time: 0.095735 memory: 14267 loss_kpt: 0.000622 acc_pose: 0.839826 loss: 0.000622 2022/09/23 11:45:02 - mmengine - INFO - Epoch(train) [124][150/293] lr: 5.000000e-04 eta: 6:54:01 time: 0.585817 data_time: 0.106778 memory: 14267 loss_kpt: 0.000617 acc_pose: 0.836053 loss: 0.000617 2022/09/23 11:45:31 - mmengine - INFO - Epoch(train) [124][200/293] lr: 5.000000e-04 eta: 6:52:58 time: 0.575577 data_time: 0.110067 memory: 14267 loss_kpt: 0.000642 acc_pose: 0.786535 loss: 0.000642 2022/09/23 11:46:00 - mmengine - INFO - Epoch(train) [124][250/293] lr: 5.000000e-04 eta: 6:51:55 time: 0.586934 data_time: 0.100201 memory: 14267 loss_kpt: 0.000631 acc_pose: 0.823540 loss: 0.000631 2022/09/23 11:46:25 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 11:46:56 - mmengine - INFO - Epoch(train) [125][50/293] lr: 5.000000e-04 eta: 6:49:43 time: 0.632468 data_time: 0.109971 memory: 14267 loss_kpt: 0.000626 acc_pose: 0.800389 loss: 0.000626 2022/09/23 11:47:27 - mmengine - INFO - Epoch(train) [125][100/293] lr: 5.000000e-04 eta: 6:48:42 time: 0.610276 data_time: 0.101086 memory: 14267 loss_kpt: 0.000610 acc_pose: 0.859110 loss: 0.000610 2022/09/23 11:47:55 - mmengine - INFO - Epoch(train) [125][150/293] lr: 5.000000e-04 eta: 6:47:39 time: 0.570197 data_time: 0.091945 memory: 14267 loss_kpt: 0.000615 acc_pose: 0.804623 loss: 0.000615 2022/09/23 11:48:25 - mmengine - INFO - Epoch(train) [125][200/293] lr: 5.000000e-04 eta: 6:46:37 time: 0.599506 data_time: 0.100678 memory: 14267 loss_kpt: 0.000631 acc_pose: 0.765024 loss: 0.000631 2022/09/23 11:48:54 - mmengine - INFO - Epoch(train) [125][250/293] lr: 5.000000e-04 eta: 6:45:35 time: 0.573791 data_time: 0.088949 memory: 14267 loss_kpt: 0.000630 acc_pose: 0.797646 loss: 0.000630 2022/09/23 11:49:20 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 11:49:52 - mmengine - INFO - Epoch(train) [126][50/293] lr: 5.000000e-04 eta: 6:43:24 time: 0.645975 data_time: 0.122971 memory: 14267 loss_kpt: 0.000633 acc_pose: 0.803907 loss: 0.000633 2022/09/23 11:50:21 - mmengine - INFO - Epoch(train) [126][100/293] lr: 5.000000e-04 eta: 6:42:22 time: 0.578466 data_time: 0.093073 memory: 14267 loss_kpt: 0.000634 acc_pose: 0.819481 loss: 0.000634 2022/09/23 11:50:50 - mmengine - INFO - Epoch(train) [126][150/293] lr: 5.000000e-04 eta: 6:41:20 time: 0.570080 data_time: 0.096542 memory: 14267 loss_kpt: 0.000616 acc_pose: 0.796849 loss: 0.000616 2022/09/23 11:51:19 - mmengine - INFO - Epoch(train) [126][200/293] lr: 5.000000e-04 eta: 6:40:19 time: 0.590385 data_time: 0.094034 memory: 14267 loss_kpt: 0.000629 acc_pose: 0.835740 loss: 0.000629 2022/09/23 11:51:48 - mmengine - INFO - Epoch(train) [126][250/293] lr: 5.000000e-04 eta: 6:39:17 time: 0.585320 data_time: 0.086858 memory: 14267 loss_kpt: 0.000615 acc_pose: 0.856030 loss: 0.000615 2022/09/23 11:52:13 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 11:52:45 - mmengine - INFO - Epoch(train) [127][50/293] lr: 5.000000e-04 eta: 6:37:08 time: 0.644823 data_time: 0.139303 memory: 14267 loss_kpt: 0.000618 acc_pose: 0.794910 loss: 0.000618 2022/09/23 11:53:04 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 11:53:14 - mmengine - INFO - Epoch(train) [127][100/293] lr: 5.000000e-04 eta: 6:36:06 time: 0.573862 data_time: 0.092257 memory: 14267 loss_kpt: 0.000625 acc_pose: 0.793715 loss: 0.000625 2022/09/23 11:53:45 - mmengine - INFO - Epoch(train) [127][150/293] lr: 5.000000e-04 eta: 6:35:06 time: 0.620824 data_time: 0.097575 memory: 14267 loss_kpt: 0.000636 acc_pose: 0.824976 loss: 0.000636 2022/09/23 11:54:15 - mmengine - INFO - Epoch(train) [127][200/293] lr: 5.000000e-04 eta: 6:34:05 time: 0.589452 data_time: 0.106095 memory: 14267 loss_kpt: 0.000628 acc_pose: 0.832284 loss: 0.000628 2022/09/23 11:54:44 - mmengine - INFO - Epoch(train) [127][250/293] lr: 5.000000e-04 eta: 6:33:05 time: 0.591647 data_time: 0.092824 memory: 14267 loss_kpt: 0.000618 acc_pose: 0.824917 loss: 0.000618 2022/09/23 11:55:09 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 11:55:39 - mmengine - INFO - Epoch(train) [128][50/293] lr: 5.000000e-04 eta: 6:30:56 time: 0.603948 data_time: 0.110491 memory: 14267 loss_kpt: 0.000637 acc_pose: 0.853448 loss: 0.000637 2022/09/23 11:56:09 - mmengine - INFO - Epoch(train) [128][100/293] lr: 5.000000e-04 eta: 6:29:55 time: 0.595693 data_time: 0.100997 memory: 14267 loss_kpt: 0.000632 acc_pose: 0.845905 loss: 0.000632 2022/09/23 11:56:37 - mmengine - INFO - Epoch(train) [128][150/293] lr: 5.000000e-04 eta: 6:28:54 time: 0.562886 data_time: 0.078102 memory: 14267 loss_kpt: 0.000618 acc_pose: 0.838451 loss: 0.000618 2022/09/23 11:57:07 - mmengine - INFO - Epoch(train) [128][200/293] lr: 5.000000e-04 eta: 6:27:54 time: 0.606397 data_time: 0.093549 memory: 14267 loss_kpt: 0.000620 acc_pose: 0.809933 loss: 0.000620 2022/09/23 11:57:37 - mmengine - INFO - Epoch(train) [128][250/293] lr: 5.000000e-04 eta: 6:26:54 time: 0.589454 data_time: 0.081241 memory: 14267 loss_kpt: 0.000610 acc_pose: 0.850254 loss: 0.000610 2022/09/23 11:58:03 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 11:58:35 - mmengine - INFO - Epoch(train) [129][50/293] lr: 5.000000e-04 eta: 6:24:47 time: 0.632067 data_time: 0.116032 memory: 14267 loss_kpt: 0.000622 acc_pose: 0.827807 loss: 0.000622 2022/09/23 11:59:05 - mmengine - INFO - Epoch(train) [129][100/293] lr: 5.000000e-04 eta: 6:23:47 time: 0.602697 data_time: 0.097048 memory: 14267 loss_kpt: 0.000625 acc_pose: 0.825155 loss: 0.000625 2022/09/23 11:59:33 - mmengine - INFO - Epoch(train) [129][150/293] lr: 5.000000e-04 eta: 6:22:47 time: 0.567697 data_time: 0.085949 memory: 14267 loss_kpt: 0.000629 acc_pose: 0.804505 loss: 0.000629 2022/09/23 12:00:06 - mmengine - INFO - Epoch(train) [129][200/293] lr: 5.000000e-04 eta: 6:21:49 time: 0.645079 data_time: 0.103619 memory: 14267 loss_kpt: 0.000623 acc_pose: 0.802459 loss: 0.000623 2022/09/23 12:00:35 - mmengine - INFO - Epoch(train) [129][250/293] lr: 5.000000e-04 eta: 6:20:49 time: 0.587055 data_time: 0.092352 memory: 14267 loss_kpt: 0.000620 acc_pose: 0.807187 loss: 0.000620 2022/09/23 12:01:01 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 12:01:33 - mmengine - INFO - Epoch(train) [130][50/293] lr: 5.000000e-04 eta: 6:18:43 time: 0.619789 data_time: 0.107918 memory: 14267 loss_kpt: 0.000622 acc_pose: 0.816765 loss: 0.000622 2022/09/23 12:02:02 - mmengine - INFO - Epoch(train) [130][100/293] lr: 5.000000e-04 eta: 6:17:44 time: 0.596137 data_time: 0.099478 memory: 14267 loss_kpt: 0.000617 acc_pose: 0.805426 loss: 0.000617 2022/09/23 12:02:31 - mmengine - INFO - Epoch(train) [130][150/293] lr: 5.000000e-04 eta: 6:16:44 time: 0.576521 data_time: 0.104651 memory: 14267 loss_kpt: 0.000621 acc_pose: 0.880896 loss: 0.000621 2022/09/23 12:03:01 - mmengine - INFO - Epoch(train) [130][200/293] lr: 5.000000e-04 eta: 6:15:45 time: 0.595150 data_time: 0.112645 memory: 14267 loss_kpt: 0.000618 acc_pose: 0.765433 loss: 0.000618 2022/09/23 12:03:03 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 12:03:30 - mmengine - INFO - Epoch(train) [130][250/293] lr: 5.000000e-04 eta: 6:14:45 time: 0.571694 data_time: 0.090368 memory: 14267 loss_kpt: 0.000637 acc_pose: 0.812254 loss: 0.000637 2022/09/23 12:03:55 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 12:03:55 - mmengine - INFO - Saving checkpoint at 130 epochs 2022/09/23 12:04:16 - mmengine - INFO - Epoch(val) [130][50/407] eta: 0:01:51 time: 0.312978 data_time: 0.156341 memory: 14267 2022/09/23 12:04:31 - mmengine - INFO - Epoch(val) [130][100/407] eta: 0:01:33 time: 0.303491 data_time: 0.153231 memory: 1464 2022/09/23 12:04:47 - mmengine - INFO - Epoch(val) [130][150/407] eta: 0:01:21 time: 0.318172 data_time: 0.166224 memory: 1464 2022/09/23 12:05:04 - mmengine - INFO - Epoch(val) [130][200/407] eta: 0:01:08 time: 0.333310 data_time: 0.171917 memory: 1464 2022/09/23 12:05:20 - mmengine - INFO - Epoch(val) [130][250/407] eta: 0:00:50 time: 0.322484 data_time: 0.169639 memory: 1464 2022/09/23 12:05:36 - mmengine - INFO - Epoch(val) [130][300/407] eta: 0:00:34 time: 0.323035 data_time: 0.152315 memory: 1464 2022/09/23 12:05:51 - mmengine - INFO - Epoch(val) [130][350/407] eta: 0:00:17 time: 0.302529 data_time: 0.134716 memory: 1464 2022/09/23 12:06:05 - mmengine - INFO - Epoch(val) [130][400/407] eta: 0:00:01 time: 0.285360 data_time: 0.146458 memory: 1464 2022/09/23 12:06:38 - mmengine - INFO - Evaluating CocoMetric... 2022/09/23 12:06:52 - mmengine - INFO - Epoch(val) [130][407/407] coco/AP: 0.714122 coco/AP .5: 0.891629 coco/AP .75: 0.780886 coco/AP (M): 0.668954 coco/AP (L): 0.789287 coco/AR: 0.767144 coco/AR .5: 0.929943 coco/AR .75: 0.828558 coco/AR (M): 0.717126 coco/AR (L): 0.838276 2022/09/23 12:07:23 - mmengine - INFO - Epoch(train) [131][50/293] lr: 5.000000e-04 eta: 6:12:40 time: 0.624415 data_time: 0.105719 memory: 14267 loss_kpt: 0.000626 acc_pose: 0.819451 loss: 0.000626 2022/09/23 12:07:52 - mmengine - INFO - Epoch(train) [131][100/293] lr: 5.000000e-04 eta: 6:11:41 time: 0.586787 data_time: 0.088257 memory: 14267 loss_kpt: 0.000627 acc_pose: 0.828612 loss: 0.000627 2022/09/23 12:08:23 - mmengine - INFO - Epoch(train) [131][150/293] lr: 5.000000e-04 eta: 6:10:43 time: 0.618687 data_time: 0.105511 memory: 14267 loss_kpt: 0.000633 acc_pose: 0.810723 loss: 0.000633 2022/09/23 12:08:54 - mmengine - INFO - Epoch(train) [131][200/293] lr: 5.000000e-04 eta: 6:09:45 time: 0.622750 data_time: 0.104475 memory: 14267 loss_kpt: 0.000631 acc_pose: 0.804876 loss: 0.000631 2022/09/23 12:09:24 - mmengine - INFO - Epoch(train) [131][250/293] lr: 5.000000e-04 eta: 6:08:47 time: 0.602715 data_time: 0.099645 memory: 14267 loss_kpt: 0.000631 acc_pose: 0.873058 loss: 0.000631 2022/09/23 12:09:49 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 12:10:20 - mmengine - INFO - Epoch(train) [132][50/293] lr: 5.000000e-04 eta: 6:06:43 time: 0.611754 data_time: 0.109270 memory: 14267 loss_kpt: 0.000626 acc_pose: 0.831642 loss: 0.000626 2022/09/23 12:10:50 - mmengine - INFO - Epoch(train) [132][100/293] lr: 5.000000e-04 eta: 6:05:45 time: 0.599282 data_time: 0.082642 memory: 14267 loss_kpt: 0.000605 acc_pose: 0.855254 loss: 0.000605 2022/09/23 12:11:20 - mmengine - INFO - Epoch(train) [132][150/293] lr: 5.000000e-04 eta: 6:04:47 time: 0.596658 data_time: 0.095576 memory: 14267 loss_kpt: 0.000627 acc_pose: 0.822795 loss: 0.000627 2022/09/23 12:11:50 - mmengine - INFO - Epoch(train) [132][200/293] lr: 5.000000e-04 eta: 6:03:49 time: 0.596156 data_time: 0.095217 memory: 14267 loss_kpt: 0.000615 acc_pose: 0.848203 loss: 0.000615 2022/09/23 12:12:20 - mmengine - INFO - Epoch(train) [132][250/293] lr: 5.000000e-04 eta: 6:02:51 time: 0.616003 data_time: 0.092994 memory: 14267 loss_kpt: 0.000615 acc_pose: 0.873395 loss: 0.000615 2022/09/23 12:12:45 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 12:13:17 - mmengine - INFO - Epoch(train) [133][50/293] lr: 5.000000e-04 eta: 6:00:49 time: 0.634796 data_time: 0.117318 memory: 14267 loss_kpt: 0.000603 acc_pose: 0.863693 loss: 0.000603 2022/09/23 12:13:47 - mmengine - INFO - Epoch(train) [133][100/293] lr: 5.000000e-04 eta: 5:59:52 time: 0.608997 data_time: 0.105696 memory: 14267 loss_kpt: 0.000619 acc_pose: 0.836804 loss: 0.000619 2022/09/23 12:14:17 - mmengine - INFO - Epoch(train) [133][150/293] lr: 5.000000e-04 eta: 5:58:54 time: 0.599581 data_time: 0.096394 memory: 14267 loss_kpt: 0.000616 acc_pose: 0.801226 loss: 0.000616 2022/09/23 12:14:46 - mmengine - INFO - Epoch(train) [133][200/293] lr: 5.000000e-04 eta: 5:57:56 time: 0.574359 data_time: 0.088086 memory: 14267 loss_kpt: 0.000628 acc_pose: 0.838107 loss: 0.000628 2022/09/23 12:15:15 - mmengine - INFO - Epoch(train) [133][250/293] lr: 5.000000e-04 eta: 5:56:58 time: 0.581728 data_time: 0.097329 memory: 14267 loss_kpt: 0.000623 acc_pose: 0.835587 loss: 0.000623 2022/09/23 12:15:41 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 12:16:01 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 12:16:12 - mmengine - INFO - Epoch(train) [134][50/293] lr: 5.000000e-04 eta: 5:54:57 time: 0.619932 data_time: 0.117427 memory: 14267 loss_kpt: 0.000605 acc_pose: 0.804439 loss: 0.000605 2022/09/23 12:16:42 - mmengine - INFO - Epoch(train) [134][100/293] lr: 5.000000e-04 eta: 5:53:59 time: 0.594243 data_time: 0.104381 memory: 14267 loss_kpt: 0.000617 acc_pose: 0.848270 loss: 0.000617 2022/09/23 12:17:11 - mmengine - INFO - Epoch(train) [134][150/293] lr: 5.000000e-04 eta: 5:53:02 time: 0.584482 data_time: 0.080082 memory: 14267 loss_kpt: 0.000619 acc_pose: 0.811399 loss: 0.000619 2022/09/23 12:17:42 - mmengine - INFO - Epoch(train) [134][200/293] lr: 5.000000e-04 eta: 5:52:05 time: 0.607160 data_time: 0.095527 memory: 14267 loss_kpt: 0.000622 acc_pose: 0.790403 loss: 0.000622 2022/09/23 12:18:11 - mmengine - INFO - Epoch(train) [134][250/293] lr: 5.000000e-04 eta: 5:51:08 time: 0.595055 data_time: 0.088453 memory: 14267 loss_kpt: 0.000610 acc_pose: 0.815092 loss: 0.000610 2022/09/23 12:18:37 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 12:19:08 - mmengine - INFO - Epoch(train) [135][50/293] lr: 5.000000e-04 eta: 5:49:07 time: 0.607947 data_time: 0.116312 memory: 14267 loss_kpt: 0.000629 acc_pose: 0.830905 loss: 0.000629 2022/09/23 12:19:38 - mmengine - INFO - Epoch(train) [135][100/293] lr: 5.000000e-04 eta: 5:48:11 time: 0.605339 data_time: 0.103099 memory: 14267 loss_kpt: 0.000613 acc_pose: 0.758338 loss: 0.000613 2022/09/23 12:20:07 - mmengine - INFO - Epoch(train) [135][150/293] lr: 5.000000e-04 eta: 5:47:14 time: 0.593057 data_time: 0.093997 memory: 14267 loss_kpt: 0.000611 acc_pose: 0.819904 loss: 0.000611 2022/09/23 12:20:36 - mmengine - INFO - Epoch(train) [135][200/293] lr: 5.000000e-04 eta: 5:46:17 time: 0.578726 data_time: 0.102350 memory: 14267 loss_kpt: 0.000626 acc_pose: 0.849991 loss: 0.000626 2022/09/23 12:21:05 - mmengine - INFO - Epoch(train) [135][250/293] lr: 5.000000e-04 eta: 5:45:19 time: 0.566948 data_time: 0.081850 memory: 14267 loss_kpt: 0.000626 acc_pose: 0.797684 loss: 0.000626 2022/09/23 12:21:30 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 12:22:00 - mmengine - INFO - Epoch(train) [136][50/293] lr: 5.000000e-04 eta: 5:43:19 time: 0.587291 data_time: 0.098411 memory: 14267 loss_kpt: 0.000624 acc_pose: 0.858836 loss: 0.000624 2022/09/23 12:22:29 - mmengine - INFO - Epoch(train) [136][100/293] lr: 5.000000e-04 eta: 5:42:23 time: 0.591874 data_time: 0.092020 memory: 14267 loss_kpt: 0.000619 acc_pose: 0.832878 loss: 0.000619 2022/09/23 12:22:59 - mmengine - INFO - Epoch(train) [136][150/293] lr: 5.000000e-04 eta: 5:41:26 time: 0.594706 data_time: 0.100257 memory: 14267 loss_kpt: 0.000624 acc_pose: 0.824802 loss: 0.000624 2022/09/23 12:23:29 - mmengine - INFO - Epoch(train) [136][200/293] lr: 5.000000e-04 eta: 5:40:30 time: 0.592475 data_time: 0.095658 memory: 14267 loss_kpt: 0.000617 acc_pose: 0.811677 loss: 0.000617 2022/09/23 12:23:59 - mmengine - INFO - Epoch(train) [136][250/293] lr: 5.000000e-04 eta: 5:39:34 time: 0.608686 data_time: 0.098973 memory: 14267 loss_kpt: 0.000624 acc_pose: 0.819196 loss: 0.000624 2022/09/23 12:24:23 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 12:24:54 - mmengine - INFO - Epoch(train) [137][50/293] lr: 5.000000e-04 eta: 5:37:36 time: 0.604643 data_time: 0.094115 memory: 14267 loss_kpt: 0.000613 acc_pose: 0.801280 loss: 0.000613 2022/09/23 12:25:23 - mmengine - INFO - Epoch(train) [137][100/293] lr: 5.000000e-04 eta: 5:36:40 time: 0.585351 data_time: 0.105726 memory: 14267 loss_kpt: 0.000613 acc_pose: 0.858166 loss: 0.000613 2022/09/23 12:25:52 - mmengine - INFO - Epoch(train) [137][150/293] lr: 5.000000e-04 eta: 5:35:43 time: 0.577212 data_time: 0.086939 memory: 14267 loss_kpt: 0.000624 acc_pose: 0.853735 loss: 0.000624 2022/09/23 12:25:53 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 12:26:21 - mmengine - INFO - Epoch(train) [137][200/293] lr: 5.000000e-04 eta: 5:34:47 time: 0.581757 data_time: 0.088109 memory: 14267 loss_kpt: 0.000621 acc_pose: 0.826097 loss: 0.000621 2022/09/23 12:26:51 - mmengine - INFO - Epoch(train) [137][250/293] lr: 5.000000e-04 eta: 5:33:51 time: 0.596926 data_time: 0.085277 memory: 14267 loss_kpt: 0.000604 acc_pose: 0.832080 loss: 0.000604 2022/09/23 12:27:16 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 12:27:47 - mmengine - INFO - Epoch(train) [138][50/293] lr: 5.000000e-04 eta: 5:31:54 time: 0.617820 data_time: 0.106193 memory: 14267 loss_kpt: 0.000619 acc_pose: 0.810102 loss: 0.000619 2022/09/23 12:28:19 - mmengine - INFO - Epoch(train) [138][100/293] lr: 5.000000e-04 eta: 5:31:00 time: 0.633960 data_time: 0.106916 memory: 14267 loss_kpt: 0.000618 acc_pose: 0.865545 loss: 0.000618 2022/09/23 12:28:49 - mmengine - INFO - Epoch(train) [138][150/293] lr: 5.000000e-04 eta: 5:30:04 time: 0.596065 data_time: 0.099678 memory: 14267 loss_kpt: 0.000626 acc_pose: 0.867402 loss: 0.000626 2022/09/23 12:29:18 - mmengine - INFO - Epoch(train) [138][200/293] lr: 5.000000e-04 eta: 5:29:09 time: 0.591234 data_time: 0.105406 memory: 14267 loss_kpt: 0.000612 acc_pose: 0.892000 loss: 0.000612 2022/09/23 12:29:48 - mmengine - INFO - Epoch(train) [138][250/293] lr: 5.000000e-04 eta: 5:28:13 time: 0.592727 data_time: 0.095845 memory: 14267 loss_kpt: 0.000625 acc_pose: 0.852964 loss: 0.000625 2022/09/23 12:30:13 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 12:30:44 - mmengine - INFO - Epoch(train) [139][50/293] lr: 5.000000e-04 eta: 5:26:18 time: 0.617387 data_time: 0.109723 memory: 14267 loss_kpt: 0.000618 acc_pose: 0.870880 loss: 0.000618 2022/09/23 12:31:14 - mmengine - INFO - Epoch(train) [139][100/293] lr: 5.000000e-04 eta: 5:25:23 time: 0.603508 data_time: 0.095411 memory: 14267 loss_kpt: 0.000614 acc_pose: 0.780223 loss: 0.000614 2022/09/23 12:31:45 - mmengine - INFO - Epoch(train) [139][150/293] lr: 5.000000e-04 eta: 5:24:28 time: 0.604508 data_time: 0.104443 memory: 14267 loss_kpt: 0.000612 acc_pose: 0.871672 loss: 0.000612 2022/09/23 12:32:15 - mmengine - INFO - Epoch(train) [139][200/293] lr: 5.000000e-04 eta: 5:23:33 time: 0.603978 data_time: 0.081665 memory: 14267 loss_kpt: 0.000596 acc_pose: 0.842624 loss: 0.000596 2022/09/23 12:32:44 - mmengine - INFO - Epoch(train) [139][250/293] lr: 5.000000e-04 eta: 5:22:38 time: 0.583358 data_time: 0.101972 memory: 14267 loss_kpt: 0.000599 acc_pose: 0.880550 loss: 0.000599 2022/09/23 12:33:08 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 12:33:39 - mmengine - INFO - Epoch(train) [140][50/293] lr: 5.000000e-04 eta: 5:20:43 time: 0.614081 data_time: 0.110948 memory: 14267 loss_kpt: 0.000604 acc_pose: 0.801582 loss: 0.000604 2022/09/23 12:34:08 - mmengine - INFO - Epoch(train) [140][100/293] lr: 5.000000e-04 eta: 5:19:48 time: 0.596656 data_time: 0.095613 memory: 14267 loss_kpt: 0.000638 acc_pose: 0.823967 loss: 0.000638 2022/09/23 12:34:39 - mmengine - INFO - Epoch(train) [140][150/293] lr: 5.000000e-04 eta: 5:18:54 time: 0.605818 data_time: 0.098458 memory: 14267 loss_kpt: 0.000615 acc_pose: 0.832650 loss: 0.000615 2022/09/23 12:35:08 - mmengine - INFO - Epoch(train) [140][200/293] lr: 5.000000e-04 eta: 5:17:59 time: 0.592281 data_time: 0.096691 memory: 14267 loss_kpt: 0.000618 acc_pose: 0.778124 loss: 0.000618 2022/09/23 12:35:37 - mmengine - INFO - Epoch(train) [140][250/293] lr: 5.000000e-04 eta: 5:17:04 time: 0.573648 data_time: 0.087897 memory: 14267 loss_kpt: 0.000609 acc_pose: 0.797581 loss: 0.000609 2022/09/23 12:35:50 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 12:36:01 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 12:36:01 - mmengine - INFO - Saving checkpoint at 140 epochs 2022/09/23 12:36:24 - mmengine - INFO - Epoch(val) [140][50/407] eta: 0:01:59 time: 0.335808 data_time: 0.157346 memory: 14267 2022/09/23 12:36:40 - mmengine - INFO - Epoch(val) [140][100/407] eta: 0:01:38 time: 0.320143 data_time: 0.153194 memory: 1464 2022/09/23 12:36:55 - mmengine - INFO - Epoch(val) [140][150/407] eta: 0:01:17 time: 0.300292 data_time: 0.127495 memory: 1464 2022/09/23 12:37:11 - mmengine - INFO - Epoch(val) [140][200/407] eta: 0:01:06 time: 0.321543 data_time: 0.156411 memory: 1464 2022/09/23 12:37:27 - mmengine - INFO - Epoch(val) [140][250/407] eta: 0:00:48 time: 0.310290 data_time: 0.137872 memory: 1464 2022/09/23 12:37:44 - mmengine - INFO - Epoch(val) [140][300/407] eta: 0:00:35 time: 0.334912 data_time: 0.170601 memory: 1464 2022/09/23 12:37:59 - mmengine - INFO - Epoch(val) [140][350/407] eta: 0:00:17 time: 0.302505 data_time: 0.147745 memory: 1464 2022/09/23 12:38:11 - mmengine - INFO - Epoch(val) [140][400/407] eta: 0:00:01 time: 0.235221 data_time: 0.119245 memory: 1464 2022/09/23 12:38:44 - mmengine - INFO - Evaluating CocoMetric... 2022/09/23 12:38:58 - mmengine - INFO - Epoch(val) [140][407/407] coco/AP: 0.714542 coco/AP .5: 0.894280 coco/AP .75: 0.780910 coco/AP (M): 0.668423 coco/AP (L): 0.790006 coco/AR: 0.767380 coco/AR .5: 0.931675 coco/AR .75: 0.827456 coco/AR (M): 0.717263 coco/AR (L): 0.839019 2022/09/23 12:39:30 - mmengine - INFO - Epoch(train) [141][50/293] lr: 5.000000e-04 eta: 5:15:11 time: 0.642210 data_time: 0.133131 memory: 14267 loss_kpt: 0.000635 acc_pose: 0.818659 loss: 0.000635 2022/09/23 12:40:01 - mmengine - INFO - Epoch(train) [141][100/293] lr: 5.000000e-04 eta: 5:14:17 time: 0.620720 data_time: 0.097181 memory: 14267 loss_kpt: 0.000612 acc_pose: 0.800418 loss: 0.000612 2022/09/23 12:40:30 - mmengine - INFO - Epoch(train) [141][150/293] lr: 5.000000e-04 eta: 5:13:23 time: 0.588040 data_time: 0.097822 memory: 14267 loss_kpt: 0.000614 acc_pose: 0.815154 loss: 0.000614 2022/09/23 12:41:01 - mmengine - INFO - Epoch(train) [141][200/293] lr: 5.000000e-04 eta: 5:12:29 time: 0.605183 data_time: 0.089339 memory: 14267 loss_kpt: 0.000615 acc_pose: 0.832300 loss: 0.000615 2022/09/23 12:41:29 - mmengine - INFO - Epoch(train) [141][250/293] lr: 5.000000e-04 eta: 5:11:34 time: 0.576108 data_time: 0.086347 memory: 14267 loss_kpt: 0.000608 acc_pose: 0.888962 loss: 0.000608 2022/09/23 12:41:55 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 12:42:25 - mmengine - INFO - Epoch(train) [142][50/293] lr: 5.000000e-04 eta: 5:09:41 time: 0.593794 data_time: 0.095383 memory: 14267 loss_kpt: 0.000618 acc_pose: 0.790816 loss: 0.000618 2022/09/23 12:42:55 - mmengine - INFO - Epoch(train) [142][100/293] lr: 5.000000e-04 eta: 5:08:47 time: 0.597365 data_time: 0.091114 memory: 14267 loss_kpt: 0.000606 acc_pose: 0.839221 loss: 0.000606 2022/09/23 12:43:24 - mmengine - INFO - Epoch(train) [142][150/293] lr: 5.000000e-04 eta: 5:07:53 time: 0.585259 data_time: 0.099998 memory: 14267 loss_kpt: 0.000613 acc_pose: 0.847179 loss: 0.000613 2022/09/23 12:43:54 - mmengine - INFO - Epoch(train) [142][200/293] lr: 5.000000e-04 eta: 5:06:59 time: 0.606024 data_time: 0.112923 memory: 14267 loss_kpt: 0.000615 acc_pose: 0.813351 loss: 0.000615 2022/09/23 12:44:24 - mmengine - INFO - Epoch(train) [142][250/293] lr: 5.000000e-04 eta: 5:06:05 time: 0.603636 data_time: 0.098253 memory: 14267 loss_kpt: 0.000622 acc_pose: 0.836717 loss: 0.000622 2022/09/23 12:44:50 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 12:45:21 - mmengine - INFO - Epoch(train) [143][50/293] lr: 5.000000e-04 eta: 5:04:14 time: 0.609637 data_time: 0.108321 memory: 14267 loss_kpt: 0.000628 acc_pose: 0.799023 loss: 0.000628 2022/09/23 12:45:50 - mmengine - INFO - Epoch(train) [143][100/293] lr: 5.000000e-04 eta: 5:03:20 time: 0.581520 data_time: 0.087361 memory: 14267 loss_kpt: 0.000615 acc_pose: 0.831627 loss: 0.000615 2022/09/23 12:46:20 - mmengine - INFO - Epoch(train) [143][150/293] lr: 5.000000e-04 eta: 5:02:26 time: 0.611303 data_time: 0.112120 memory: 14267 loss_kpt: 0.000622 acc_pose: 0.857146 loss: 0.000622 2022/09/23 12:46:49 - mmengine - INFO - Epoch(train) [143][200/293] lr: 5.000000e-04 eta: 5:01:32 time: 0.573491 data_time: 0.092200 memory: 14267 loss_kpt: 0.000613 acc_pose: 0.885924 loss: 0.000613 2022/09/23 12:47:18 - mmengine - INFO - Epoch(train) [143][250/293] lr: 5.000000e-04 eta: 5:00:39 time: 0.574194 data_time: 0.087981 memory: 14267 loss_kpt: 0.000621 acc_pose: 0.833707 loss: 0.000621 2022/09/23 12:47:43 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 12:48:13 - mmengine - INFO - Epoch(train) [144][50/293] lr: 5.000000e-04 eta: 4:58:47 time: 0.599080 data_time: 0.105557 memory: 14267 loss_kpt: 0.000610 acc_pose: 0.840894 loss: 0.000610 2022/09/23 12:48:42 - mmengine - INFO - Epoch(train) [144][100/293] lr: 5.000000e-04 eta: 4:57:54 time: 0.589777 data_time: 0.071885 memory: 14267 loss_kpt: 0.000617 acc_pose: 0.845052 loss: 0.000617 2022/09/23 12:48:43 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 12:49:12 - mmengine - INFO - Epoch(train) [144][150/293] lr: 5.000000e-04 eta: 4:57:01 time: 0.582305 data_time: 0.090865 memory: 14267 loss_kpt: 0.000614 acc_pose: 0.832793 loss: 0.000614 2022/09/23 12:49:42 - mmengine - INFO - Epoch(train) [144][200/293] lr: 5.000000e-04 eta: 4:56:08 time: 0.605402 data_time: 0.097608 memory: 14267 loss_kpt: 0.000624 acc_pose: 0.785960 loss: 0.000624 2022/09/23 12:50:12 - mmengine - INFO - Epoch(train) [144][250/293] lr: 5.000000e-04 eta: 4:55:15 time: 0.600355 data_time: 0.106421 memory: 14267 loss_kpt: 0.000629 acc_pose: 0.830704 loss: 0.000629 2022/09/23 12:50:37 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 12:51:08 - mmengine - INFO - Epoch(train) [145][50/293] lr: 5.000000e-04 eta: 4:53:25 time: 0.608597 data_time: 0.110646 memory: 14267 loss_kpt: 0.000620 acc_pose: 0.819151 loss: 0.000620 2022/09/23 12:51:37 - mmengine - INFO - Epoch(train) [145][100/293] lr: 5.000000e-04 eta: 4:52:32 time: 0.593725 data_time: 0.094839 memory: 14267 loss_kpt: 0.000609 acc_pose: 0.835798 loss: 0.000609 2022/09/23 12:52:07 - mmengine - INFO - Epoch(train) [145][150/293] lr: 5.000000e-04 eta: 4:51:39 time: 0.586133 data_time: 0.095765 memory: 14267 loss_kpt: 0.000618 acc_pose: 0.858039 loss: 0.000618 2022/09/23 12:52:37 - mmengine - INFO - Epoch(train) [145][200/293] lr: 5.000000e-04 eta: 4:50:46 time: 0.602017 data_time: 0.099037 memory: 14267 loss_kpt: 0.000619 acc_pose: 0.815334 loss: 0.000619 2022/09/23 12:53:06 - mmengine - INFO - Epoch(train) [145][250/293] lr: 5.000000e-04 eta: 4:49:54 time: 0.592312 data_time: 0.096511 memory: 14267 loss_kpt: 0.000619 acc_pose: 0.824654 loss: 0.000619 2022/09/23 12:53:32 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 12:54:01 - mmengine - INFO - Epoch(train) [146][50/293] lr: 5.000000e-04 eta: 4:48:04 time: 0.597233 data_time: 0.097646 memory: 14267 loss_kpt: 0.000620 acc_pose: 0.800156 loss: 0.000620 2022/09/23 12:54:31 - mmengine - INFO - Epoch(train) [146][100/293] lr: 5.000000e-04 eta: 4:47:12 time: 0.592871 data_time: 0.109710 memory: 14267 loss_kpt: 0.000616 acc_pose: 0.812491 loss: 0.000616 2022/09/23 12:55:01 - mmengine - INFO - Epoch(train) [146][150/293] lr: 5.000000e-04 eta: 4:46:19 time: 0.588968 data_time: 0.102860 memory: 14267 loss_kpt: 0.000613 acc_pose: 0.854567 loss: 0.000613 2022/09/23 12:55:30 - mmengine - INFO - Epoch(train) [146][200/293] lr: 5.000000e-04 eta: 4:45:27 time: 0.580747 data_time: 0.094446 memory: 14267 loss_kpt: 0.000618 acc_pose: 0.840301 loss: 0.000618 2022/09/23 12:55:58 - mmengine - INFO - Epoch(train) [146][250/293] lr: 5.000000e-04 eta: 4:44:34 time: 0.564481 data_time: 0.087503 memory: 14267 loss_kpt: 0.000622 acc_pose: 0.825976 loss: 0.000622 2022/09/23 12:56:23 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 12:56:52 - mmengine - INFO - Epoch(train) [147][50/293] lr: 5.000000e-04 eta: 4:42:45 time: 0.594453 data_time: 0.100192 memory: 14267 loss_kpt: 0.000612 acc_pose: 0.805988 loss: 0.000612 2022/09/23 12:57:23 - mmengine - INFO - Epoch(train) [147][100/293] lr: 5.000000e-04 eta: 4:41:53 time: 0.605164 data_time: 0.098132 memory: 14267 loss_kpt: 0.000608 acc_pose: 0.892996 loss: 0.000608 2022/09/23 12:57:52 - mmengine - INFO - Epoch(train) [147][150/293] lr: 5.000000e-04 eta: 4:41:01 time: 0.592006 data_time: 0.091765 memory: 14267 loss_kpt: 0.000614 acc_pose: 0.792255 loss: 0.000614 2022/09/23 12:58:20 - mmengine - INFO - Epoch(train) [147][200/293] lr: 5.000000e-04 eta: 4:40:08 time: 0.552691 data_time: 0.090916 memory: 14267 loss_kpt: 0.000615 acc_pose: 0.803026 loss: 0.000615 2022/09/23 12:58:33 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 12:58:49 - mmengine - INFO - Epoch(train) [147][250/293] lr: 5.000000e-04 eta: 4:39:16 time: 0.590240 data_time: 0.107255 memory: 14267 loss_kpt: 0.000622 acc_pose: 0.803468 loss: 0.000622 2022/09/23 12:59:14 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 12:59:45 - mmengine - INFO - Epoch(train) [148][50/293] lr: 5.000000e-04 eta: 4:37:29 time: 0.617443 data_time: 0.119112 memory: 14267 loss_kpt: 0.000593 acc_pose: 0.819249 loss: 0.000593 2022/09/23 13:00:14 - mmengine - INFO - Epoch(train) [148][100/293] lr: 5.000000e-04 eta: 4:36:37 time: 0.582594 data_time: 0.095759 memory: 14267 loss_kpt: 0.000615 acc_pose: 0.825429 loss: 0.000615 2022/09/23 13:00:43 - mmengine - INFO - Epoch(train) [148][150/293] lr: 5.000000e-04 eta: 4:35:45 time: 0.579980 data_time: 0.091447 memory: 14267 loss_kpt: 0.000608 acc_pose: 0.826118 loss: 0.000608 2022/09/23 13:01:13 - mmengine - INFO - Epoch(train) [148][200/293] lr: 5.000000e-04 eta: 4:34:53 time: 0.596400 data_time: 0.089915 memory: 14267 loss_kpt: 0.000611 acc_pose: 0.853836 loss: 0.000611 2022/09/23 13:01:42 - mmengine - INFO - Epoch(train) [148][250/293] lr: 5.000000e-04 eta: 4:34:01 time: 0.592043 data_time: 0.081979 memory: 14267 loss_kpt: 0.000620 acc_pose: 0.832126 loss: 0.000620 2022/09/23 13:02:06 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 13:02:36 - mmengine - INFO - Epoch(train) [149][50/293] lr: 5.000000e-04 eta: 4:32:15 time: 0.594161 data_time: 0.101781 memory: 14267 loss_kpt: 0.000608 acc_pose: 0.839838 loss: 0.000608 2022/09/23 13:03:05 - mmengine - INFO - Epoch(train) [149][100/293] lr: 5.000000e-04 eta: 4:31:23 time: 0.580717 data_time: 0.094014 memory: 14267 loss_kpt: 0.000621 acc_pose: 0.822283 loss: 0.000621 2022/09/23 13:03:34 - mmengine - INFO - Epoch(train) [149][150/293] lr: 5.000000e-04 eta: 4:30:31 time: 0.581189 data_time: 0.097265 memory: 14267 loss_kpt: 0.000615 acc_pose: 0.816060 loss: 0.000615 2022/09/23 13:04:03 - mmengine - INFO - Epoch(train) [149][200/293] lr: 5.000000e-04 eta: 4:29:40 time: 0.583348 data_time: 0.107028 memory: 14267 loss_kpt: 0.000615 acc_pose: 0.833703 loss: 0.000615 2022/09/23 13:04:33 - mmengine - INFO - Epoch(train) [149][250/293] lr: 5.000000e-04 eta: 4:28:49 time: 0.601251 data_time: 0.102713 memory: 14267 loss_kpt: 0.000614 acc_pose: 0.836219 loss: 0.000614 2022/09/23 13:04:58 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 13:05:28 - mmengine - INFO - Epoch(train) [150][50/293] lr: 5.000000e-04 eta: 4:27:03 time: 0.592028 data_time: 0.102619 memory: 14267 loss_kpt: 0.000597 acc_pose: 0.835433 loss: 0.000597 2022/09/23 13:05:57 - mmengine - INFO - Epoch(train) [150][100/293] lr: 5.000000e-04 eta: 4:26:12 time: 0.587562 data_time: 0.093151 memory: 14267 loss_kpt: 0.000614 acc_pose: 0.856829 loss: 0.000614 2022/09/23 13:06:25 - mmengine - INFO - Epoch(train) [150][150/293] lr: 5.000000e-04 eta: 4:25:20 time: 0.559174 data_time: 0.090881 memory: 14267 loss_kpt: 0.000610 acc_pose: 0.805048 loss: 0.000610 2022/09/23 13:06:54 - mmengine - INFO - Epoch(train) [150][200/293] lr: 5.000000e-04 eta: 4:24:28 time: 0.576162 data_time: 0.091404 memory: 14267 loss_kpt: 0.000592 acc_pose: 0.842612 loss: 0.000592 2022/09/23 13:07:23 - mmengine - INFO - Epoch(train) [150][250/293] lr: 5.000000e-04 eta: 4:23:37 time: 0.577224 data_time: 0.104413 memory: 14267 loss_kpt: 0.000615 acc_pose: 0.835473 loss: 0.000615 2022/09/23 13:07:48 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 13:07:48 - mmengine - INFO - Saving checkpoint at 150 epochs 2022/09/23 13:08:09 - mmengine - INFO - Epoch(val) [150][50/407] eta: 0:01:58 time: 0.332508 data_time: 0.153456 memory: 14267 2022/09/23 13:08:25 - mmengine - INFO - Epoch(val) [150][100/407] eta: 0:01:35 time: 0.311718 data_time: 0.155805 memory: 1464 2022/09/23 13:08:40 - mmengine - INFO - Epoch(val) [150][150/407] eta: 0:01:18 time: 0.304986 data_time: 0.136872 memory: 1464 2022/09/23 13:08:55 - mmengine - INFO - Epoch(val) [150][200/407] eta: 0:01:02 time: 0.299771 data_time: 0.134909 memory: 1464 2022/09/23 13:09:10 - mmengine - INFO - Epoch(val) [150][250/407] eta: 0:00:47 time: 0.303562 data_time: 0.130521 memory: 1464 2022/09/23 13:09:25 - mmengine - INFO - Epoch(val) [150][300/407] eta: 0:00:32 time: 0.300251 data_time: 0.125353 memory: 1464 2022/09/23 13:09:41 - mmengine - INFO - Epoch(val) [150][350/407] eta: 0:00:17 time: 0.313990 data_time: 0.153763 memory: 1464 2022/09/23 13:09:55 - mmengine - INFO - Epoch(val) [150][400/407] eta: 0:00:01 time: 0.282716 data_time: 0.126677 memory: 1464 2022/09/23 13:10:29 - mmengine - INFO - Evaluating CocoMetric... 2022/09/23 13:10:42 - mmengine - INFO - Epoch(val) [150][407/407] coco/AP: 0.715675 coco/AP .5: 0.895083 coco/AP .75: 0.780796 coco/AP (M): 0.671385 coco/AP (L): 0.789372 coco/AR: 0.768482 coco/AR .5: 0.932147 coco/AR .75: 0.828558 coco/AR (M): 0.720377 coco/AR (L): 0.837570 2022/09/23 13:10:42 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220922/res50_384_2/best_coco/AP_epoch_120.pth is removed 2022/09/23 13:10:45 - mmengine - INFO - The best checkpoint with 0.7157 coco/AP at 150 epoch is saved to best_coco/AP_epoch_150.pth. 2022/09/23 13:11:15 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 13:11:15 - mmengine - INFO - Epoch(train) [151][50/293] lr: 5.000000e-04 eta: 4:21:52 time: 0.594604 data_time: 0.103134 memory: 14267 loss_kpt: 0.000602 acc_pose: 0.832337 loss: 0.000602 2022/09/23 13:11:44 - mmengine - INFO - Epoch(train) [151][100/293] lr: 5.000000e-04 eta: 4:21:01 time: 0.595057 data_time: 0.101576 memory: 14267 loss_kpt: 0.000616 acc_pose: 0.877717 loss: 0.000616 2022/09/23 13:12:13 - mmengine - INFO - Epoch(train) [151][150/293] lr: 5.000000e-04 eta: 4:20:10 time: 0.571654 data_time: 0.112674 memory: 14267 loss_kpt: 0.000618 acc_pose: 0.796088 loss: 0.000618 2022/09/23 13:12:43 - mmengine - INFO - Epoch(train) [151][200/293] lr: 5.000000e-04 eta: 4:19:20 time: 0.606489 data_time: 0.091853 memory: 14267 loss_kpt: 0.000625 acc_pose: 0.809677 loss: 0.000625 2022/09/23 13:13:13 - mmengine - INFO - Epoch(train) [151][250/293] lr: 5.000000e-04 eta: 4:18:29 time: 0.586532 data_time: 0.099093 memory: 14267 loss_kpt: 0.000616 acc_pose: 0.868357 loss: 0.000616 2022/09/23 13:13:39 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 13:14:09 - mmengine - INFO - Epoch(train) [152][50/293] lr: 5.000000e-04 eta: 4:16:45 time: 0.601091 data_time: 0.120437 memory: 14267 loss_kpt: 0.000603 acc_pose: 0.869745 loss: 0.000603 2022/09/23 13:14:38 - mmengine - INFO - Epoch(train) [152][100/293] lr: 5.000000e-04 eta: 4:15:54 time: 0.590943 data_time: 0.103006 memory: 14267 loss_kpt: 0.000616 acc_pose: 0.857332 loss: 0.000616 2022/09/23 13:15:08 - mmengine - INFO - Epoch(train) [152][150/293] lr: 5.000000e-04 eta: 4:15:04 time: 0.597935 data_time: 0.103606 memory: 14267 loss_kpt: 0.000611 acc_pose: 0.842167 loss: 0.000611 2022/09/23 13:15:38 - mmengine - INFO - Epoch(train) [152][200/293] lr: 5.000000e-04 eta: 4:14:14 time: 0.596344 data_time: 0.089579 memory: 14267 loss_kpt: 0.000609 acc_pose: 0.792546 loss: 0.000609 2022/09/23 13:16:08 - mmengine - INFO - Epoch(train) [152][250/293] lr: 5.000000e-04 eta: 4:13:23 time: 0.595265 data_time: 0.103352 memory: 14267 loss_kpt: 0.000608 acc_pose: 0.832766 loss: 0.000608 2022/09/23 13:16:33 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 13:17:03 - mmengine - INFO - Epoch(train) [153][50/293] lr: 5.000000e-04 eta: 4:11:40 time: 0.599345 data_time: 0.112151 memory: 14267 loss_kpt: 0.000619 acc_pose: 0.794003 loss: 0.000619 2022/09/23 13:17:33 - mmengine - INFO - Epoch(train) [153][100/293] lr: 5.000000e-04 eta: 4:10:50 time: 0.591577 data_time: 0.103979 memory: 14267 loss_kpt: 0.000616 acc_pose: 0.817835 loss: 0.000616 2022/09/23 13:18:03 - mmengine - INFO - Epoch(train) [153][150/293] lr: 5.000000e-04 eta: 4:10:00 time: 0.596084 data_time: 0.107925 memory: 14267 loss_kpt: 0.000615 acc_pose: 0.831826 loss: 0.000615 2022/09/23 13:18:32 - mmengine - INFO - Epoch(train) [153][200/293] lr: 5.000000e-04 eta: 4:09:10 time: 0.584474 data_time: 0.113368 memory: 14267 loss_kpt: 0.000603 acc_pose: 0.851713 loss: 0.000603 2022/09/23 13:19:02 - mmengine - INFO - Epoch(train) [153][250/293] lr: 5.000000e-04 eta: 4:08:20 time: 0.606898 data_time: 0.100187 memory: 14267 loss_kpt: 0.000616 acc_pose: 0.829237 loss: 0.000616 2022/09/23 13:19:28 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 13:19:57 - mmengine - INFO - Epoch(train) [154][50/293] lr: 5.000000e-04 eta: 4:06:37 time: 0.586894 data_time: 0.100910 memory: 14267 loss_kpt: 0.000599 acc_pose: 0.834710 loss: 0.000599 2022/09/23 13:20:27 - mmengine - INFO - Epoch(train) [154][100/293] lr: 5.000000e-04 eta: 4:05:47 time: 0.583584 data_time: 0.104542 memory: 14267 loss_kpt: 0.000620 acc_pose: 0.829856 loss: 0.000620 2022/09/23 13:20:55 - mmengine - INFO - Epoch(train) [154][150/293] lr: 5.000000e-04 eta: 4:04:57 time: 0.575875 data_time: 0.095630 memory: 14267 loss_kpt: 0.000608 acc_pose: 0.845469 loss: 0.000608 2022/09/23 13:21:08 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 13:21:25 - mmengine - INFO - Epoch(train) [154][200/293] lr: 5.000000e-04 eta: 4:04:07 time: 0.585411 data_time: 0.102815 memory: 14267 loss_kpt: 0.000615 acc_pose: 0.819864 loss: 0.000615 2022/09/23 13:21:54 - mmengine - INFO - Epoch(train) [154][250/293] lr: 5.000000e-04 eta: 4:03:17 time: 0.581171 data_time: 0.091984 memory: 14267 loss_kpt: 0.000615 acc_pose: 0.835892 loss: 0.000615 2022/09/23 13:22:19 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 13:22:50 - mmengine - INFO - Epoch(train) [155][50/293] lr: 5.000000e-04 eta: 4:01:36 time: 0.616385 data_time: 0.117526 memory: 14267 loss_kpt: 0.000614 acc_pose: 0.825797 loss: 0.000614 2022/09/23 13:23:20 - mmengine - INFO - Epoch(train) [155][100/293] lr: 5.000000e-04 eta: 4:00:46 time: 0.591304 data_time: 0.103967 memory: 14267 loss_kpt: 0.000611 acc_pose: 0.754937 loss: 0.000611 2022/09/23 13:23:49 - mmengine - INFO - Epoch(train) [155][150/293] lr: 5.000000e-04 eta: 3:59:57 time: 0.596038 data_time: 0.093113 memory: 14267 loss_kpt: 0.000618 acc_pose: 0.814901 loss: 0.000618 2022/09/23 13:24:19 - mmengine - INFO - Epoch(train) [155][200/293] lr: 5.000000e-04 eta: 3:59:07 time: 0.590902 data_time: 0.106697 memory: 14267 loss_kpt: 0.000611 acc_pose: 0.853701 loss: 0.000611 2022/09/23 13:24:48 - mmengine - INFO - Epoch(train) [155][250/293] lr: 5.000000e-04 eta: 3:58:17 time: 0.581701 data_time: 0.101233 memory: 14267 loss_kpt: 0.000607 acc_pose: 0.834394 loss: 0.000607 2022/09/23 13:25:13 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 13:25:42 - mmengine - INFO - Epoch(train) [156][50/293] lr: 5.000000e-04 eta: 3:56:36 time: 0.588221 data_time: 0.108494 memory: 14267 loss_kpt: 0.000608 acc_pose: 0.865502 loss: 0.000608 2022/09/23 13:26:12 - mmengine - INFO - Epoch(train) [156][100/293] lr: 5.000000e-04 eta: 3:55:47 time: 0.583219 data_time: 0.090243 memory: 14267 loss_kpt: 0.000601 acc_pose: 0.832143 loss: 0.000601 2022/09/23 13:26:41 - mmengine - INFO - Epoch(train) [156][150/293] lr: 5.000000e-04 eta: 3:54:58 time: 0.590662 data_time: 0.098676 memory: 14267 loss_kpt: 0.000613 acc_pose: 0.845869 loss: 0.000613 2022/09/23 13:27:11 - mmengine - INFO - Epoch(train) [156][200/293] lr: 5.000000e-04 eta: 3:54:09 time: 0.599181 data_time: 0.106326 memory: 14267 loss_kpt: 0.000610 acc_pose: 0.811885 loss: 0.000610 2022/09/23 13:27:42 - mmengine - INFO - Epoch(train) [156][250/293] lr: 5.000000e-04 eta: 3:53:20 time: 0.621376 data_time: 0.114154 memory: 14267 loss_kpt: 0.000602 acc_pose: 0.794534 loss: 0.000602 2022/09/23 13:28:07 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 13:28:38 - mmengine - INFO - Epoch(train) [157][50/293] lr: 5.000000e-04 eta: 3:51:40 time: 0.621534 data_time: 0.121422 memory: 14267 loss_kpt: 0.000610 acc_pose: 0.809133 loss: 0.000610 2022/09/23 13:29:07 - mmengine - INFO - Epoch(train) [157][100/293] lr: 5.000000e-04 eta: 3:50:51 time: 0.569457 data_time: 0.100423 memory: 14267 loss_kpt: 0.000605 acc_pose: 0.831976 loss: 0.000605 2022/09/23 13:29:36 - mmengine - INFO - Epoch(train) [157][150/293] lr: 5.000000e-04 eta: 3:50:02 time: 0.588352 data_time: 0.098054 memory: 14267 loss_kpt: 0.000608 acc_pose: 0.814440 loss: 0.000608 2022/09/23 13:30:06 - mmengine - INFO - Epoch(train) [157][200/293] lr: 5.000000e-04 eta: 3:49:13 time: 0.597899 data_time: 0.092825 memory: 14267 loss_kpt: 0.000617 acc_pose: 0.819364 loss: 0.000617 2022/09/23 13:30:36 - mmengine - INFO - Epoch(train) [157][250/293] lr: 5.000000e-04 eta: 3:48:24 time: 0.600950 data_time: 0.105321 memory: 14267 loss_kpt: 0.000610 acc_pose: 0.806552 loss: 0.000610 2022/09/23 13:31:01 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 13:31:02 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 13:31:32 - mmengine - INFO - Epoch(train) [158][50/293] lr: 5.000000e-04 eta: 3:46:45 time: 0.603232 data_time: 0.104948 memory: 14267 loss_kpt: 0.000603 acc_pose: 0.845638 loss: 0.000603 2022/09/23 13:32:02 - mmengine - INFO - Epoch(train) [158][100/293] lr: 5.000000e-04 eta: 3:45:56 time: 0.607463 data_time: 0.101650 memory: 14267 loss_kpt: 0.000612 acc_pose: 0.839233 loss: 0.000612 2022/09/23 13:32:32 - mmengine - INFO - Epoch(train) [158][150/293] lr: 5.000000e-04 eta: 3:45:08 time: 0.600887 data_time: 0.103191 memory: 14267 loss_kpt: 0.000609 acc_pose: 0.836796 loss: 0.000609 2022/09/23 13:33:03 - mmengine - INFO - Epoch(train) [158][200/293] lr: 5.000000e-04 eta: 3:44:20 time: 0.615203 data_time: 0.104949 memory: 14267 loss_kpt: 0.000607 acc_pose: 0.825757 loss: 0.000607 2022/09/23 13:33:32 - mmengine - INFO - Epoch(train) [158][250/293] lr: 5.000000e-04 eta: 3:43:31 time: 0.573376 data_time: 0.108198 memory: 14267 loss_kpt: 0.000592 acc_pose: 0.833467 loss: 0.000592 2022/09/23 13:33:56 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 13:34:27 - mmengine - INFO - Epoch(train) [159][50/293] lr: 5.000000e-04 eta: 3:41:52 time: 0.612980 data_time: 0.122361 memory: 14267 loss_kpt: 0.000602 acc_pose: 0.813357 loss: 0.000602 2022/09/23 13:34:56 - mmengine - INFO - Epoch(train) [159][100/293] lr: 5.000000e-04 eta: 3:41:04 time: 0.573342 data_time: 0.099768 memory: 14267 loss_kpt: 0.000609 acc_pose: 0.786161 loss: 0.000609 2022/09/23 13:35:25 - mmengine - INFO - Epoch(train) [159][150/293] lr: 5.000000e-04 eta: 3:40:15 time: 0.578979 data_time: 0.108587 memory: 14267 loss_kpt: 0.000611 acc_pose: 0.838862 loss: 0.000611 2022/09/23 13:35:54 - mmengine - INFO - Epoch(train) [159][200/293] lr: 5.000000e-04 eta: 3:39:26 time: 0.577604 data_time: 0.092920 memory: 14267 loss_kpt: 0.000621 acc_pose: 0.874005 loss: 0.000621 2022/09/23 13:36:23 - mmengine - INFO - Epoch(train) [159][250/293] lr: 5.000000e-04 eta: 3:38:38 time: 0.577183 data_time: 0.084734 memory: 14267 loss_kpt: 0.000602 acc_pose: 0.824762 loss: 0.000602 2022/09/23 13:36:48 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 13:37:19 - mmengine - INFO - Epoch(train) [160][50/293] lr: 5.000000e-04 eta: 3:37:00 time: 0.623668 data_time: 0.121528 memory: 14267 loss_kpt: 0.000605 acc_pose: 0.863774 loss: 0.000605 2022/09/23 13:37:48 - mmengine - INFO - Epoch(train) [160][100/293] lr: 5.000000e-04 eta: 3:36:12 time: 0.579359 data_time: 0.098417 memory: 14267 loss_kpt: 0.000615 acc_pose: 0.881255 loss: 0.000615 2022/09/23 13:38:18 - mmengine - INFO - Epoch(train) [160][150/293] lr: 5.000000e-04 eta: 3:35:24 time: 0.593074 data_time: 0.107491 memory: 14267 loss_kpt: 0.000621 acc_pose: 0.813437 loss: 0.000621 2022/09/23 13:38:48 - mmengine - INFO - Epoch(train) [160][200/293] lr: 5.000000e-04 eta: 3:34:36 time: 0.603962 data_time: 0.109401 memory: 14267 loss_kpt: 0.000596 acc_pose: 0.849923 loss: 0.000596 2022/09/23 13:39:18 - mmengine - INFO - Epoch(train) [160][250/293] lr: 5.000000e-04 eta: 3:33:48 time: 0.591253 data_time: 0.092132 memory: 14267 loss_kpt: 0.000601 acc_pose: 0.879984 loss: 0.000601 2022/09/23 13:39:43 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 13:39:43 - mmengine - INFO - Saving checkpoint at 160 epochs 2022/09/23 13:40:05 - mmengine - INFO - Epoch(val) [160][50/407] eta: 0:01:57 time: 0.328394 data_time: 0.159224 memory: 14267 2022/09/23 13:40:20 - mmengine - INFO - Epoch(val) [160][100/407] eta: 0:01:31 time: 0.298742 data_time: 0.142005 memory: 1464 2022/09/23 13:40:36 - mmengine - INFO - Epoch(val) [160][150/407] eta: 0:01:21 time: 0.315621 data_time: 0.152510 memory: 1464 2022/09/23 13:40:52 - mmengine - INFO - Epoch(val) [160][200/407] eta: 0:01:05 time: 0.316002 data_time: 0.153480 memory: 1464 2022/09/23 13:41:08 - mmengine - INFO - Epoch(val) [160][250/407] eta: 0:00:48 time: 0.311623 data_time: 0.144690 memory: 1464 2022/09/23 13:41:23 - mmengine - INFO - Epoch(val) [160][300/407] eta: 0:00:33 time: 0.312214 data_time: 0.147441 memory: 1464 2022/09/23 13:41:39 - mmengine - INFO - Epoch(val) [160][350/407] eta: 0:00:17 time: 0.307280 data_time: 0.157580 memory: 1464 2022/09/23 13:41:51 - mmengine - INFO - Epoch(val) [160][400/407] eta: 0:00:01 time: 0.253588 data_time: 0.110175 memory: 1464 2022/09/23 13:42:25 - mmengine - INFO - Evaluating CocoMetric... 2022/09/23 13:42:39 - mmengine - INFO - Epoch(val) [160][407/407] coco/AP: 0.719039 coco/AP .5: 0.897385 coco/AP .75: 0.788153 coco/AP (M): 0.674003 coco/AP (L): 0.794751 coco/AR: 0.771300 coco/AR .5: 0.933722 coco/AR .75: 0.833753 coco/AR (M): 0.721770 coco/AR (L): 0.842140 2022/09/23 13:42:39 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220922/res50_384_2/best_coco/AP_epoch_150.pth is removed 2022/09/23 13:42:41 - mmengine - INFO - The best checkpoint with 0.7190 coco/AP at 160 epoch is saved to best_coco/AP_epoch_160.pth. 2022/09/23 13:43:12 - mmengine - INFO - Epoch(train) [161][50/293] lr: 5.000000e-04 eta: 3:32:11 time: 0.618191 data_time: 0.121829 memory: 14267 loss_kpt: 0.000601 acc_pose: 0.797100 loss: 0.000601 2022/09/23 13:43:42 - mmengine - INFO - Epoch(train) [161][100/293] lr: 5.000000e-04 eta: 3:31:23 time: 0.593099 data_time: 0.082983 memory: 14267 loss_kpt: 0.000609 acc_pose: 0.856491 loss: 0.000609 2022/09/23 13:43:53 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 13:44:11 - mmengine - INFO - Epoch(train) [161][150/293] lr: 5.000000e-04 eta: 3:30:35 time: 0.577063 data_time: 0.094916 memory: 14267 loss_kpt: 0.000611 acc_pose: 0.809827 loss: 0.000611 2022/09/23 13:44:40 - mmengine - INFO - Epoch(train) [161][200/293] lr: 5.000000e-04 eta: 3:29:47 time: 0.590070 data_time: 0.098956 memory: 14267 loss_kpt: 0.000603 acc_pose: 0.821222 loss: 0.000603 2022/09/23 13:45:11 - mmengine - INFO - Epoch(train) [161][250/293] lr: 5.000000e-04 eta: 3:28:59 time: 0.615830 data_time: 0.096684 memory: 14267 loss_kpt: 0.000605 acc_pose: 0.853857 loss: 0.000605 2022/09/23 13:45:36 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 13:46:08 - mmengine - INFO - Epoch(train) [162][50/293] lr: 5.000000e-04 eta: 3:27:23 time: 0.632084 data_time: 0.124612 memory: 14267 loss_kpt: 0.000600 acc_pose: 0.858130 loss: 0.000600 2022/09/23 13:46:38 - mmengine - INFO - Epoch(train) [162][100/293] lr: 5.000000e-04 eta: 3:26:36 time: 0.593971 data_time: 0.085688 memory: 14267 loss_kpt: 0.000610 acc_pose: 0.834708 loss: 0.000610 2022/09/23 13:47:08 - mmengine - INFO - Epoch(train) [162][150/293] lr: 5.000000e-04 eta: 3:25:48 time: 0.604498 data_time: 0.103338 memory: 14267 loss_kpt: 0.000600 acc_pose: 0.801111 loss: 0.000600 2022/09/23 13:47:37 - mmengine - INFO - Epoch(train) [162][200/293] lr: 5.000000e-04 eta: 3:25:01 time: 0.574717 data_time: 0.108548 memory: 14267 loss_kpt: 0.000609 acc_pose: 0.838681 loss: 0.000609 2022/09/23 13:48:06 - mmengine - INFO - Epoch(train) [162][250/293] lr: 5.000000e-04 eta: 3:24:13 time: 0.590984 data_time: 0.095842 memory: 14267 loss_kpt: 0.000604 acc_pose: 0.879074 loss: 0.000604 2022/09/23 13:48:31 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 13:49:01 - mmengine - INFO - Epoch(train) [163][50/293] lr: 5.000000e-04 eta: 3:22:37 time: 0.605927 data_time: 0.103527 memory: 14267 loss_kpt: 0.000612 acc_pose: 0.861801 loss: 0.000612 2022/09/23 13:49:31 - mmengine - INFO - Epoch(train) [163][100/293] lr: 5.000000e-04 eta: 3:21:50 time: 0.599450 data_time: 0.106883 memory: 14267 loss_kpt: 0.000603 acc_pose: 0.843181 loss: 0.000603 2022/09/23 13:50:01 - mmengine - INFO - Epoch(train) [163][150/293] lr: 5.000000e-04 eta: 3:21:03 time: 0.589732 data_time: 0.097061 memory: 14267 loss_kpt: 0.000589 acc_pose: 0.842751 loss: 0.000589 2022/09/23 13:50:30 - mmengine - INFO - Epoch(train) [163][200/293] lr: 5.000000e-04 eta: 3:20:15 time: 0.585960 data_time: 0.099367 memory: 14267 loss_kpt: 0.000612 acc_pose: 0.802404 loss: 0.000612 2022/09/23 13:50:58 - mmengine - INFO - Epoch(train) [163][250/293] lr: 5.000000e-04 eta: 3:19:27 time: 0.569149 data_time: 0.098720 memory: 14267 loss_kpt: 0.000602 acc_pose: 0.831051 loss: 0.000602 2022/09/23 13:51:24 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 13:51:55 - mmengine - INFO - Epoch(train) [164][50/293] lr: 5.000000e-04 eta: 3:17:53 time: 0.627559 data_time: 0.128030 memory: 14267 loss_kpt: 0.000587 acc_pose: 0.880652 loss: 0.000587 2022/09/23 13:52:26 - mmengine - INFO - Epoch(train) [164][100/293] lr: 5.000000e-04 eta: 3:17:06 time: 0.603005 data_time: 0.094703 memory: 14267 loss_kpt: 0.000615 acc_pose: 0.865379 loss: 0.000615 2022/09/23 13:52:55 - mmengine - INFO - Epoch(train) [164][150/293] lr: 5.000000e-04 eta: 3:16:19 time: 0.582933 data_time: 0.093006 memory: 14267 loss_kpt: 0.000617 acc_pose: 0.869734 loss: 0.000617 2022/09/23 13:53:24 - mmengine - INFO - Epoch(train) [164][200/293] lr: 5.000000e-04 eta: 3:15:31 time: 0.591529 data_time: 0.092866 memory: 14267 loss_kpt: 0.000610 acc_pose: 0.832678 loss: 0.000610 2022/09/23 13:53:49 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 13:53:54 - mmengine - INFO - Epoch(train) [164][250/293] lr: 5.000000e-04 eta: 3:14:44 time: 0.586918 data_time: 0.114030 memory: 14267 loss_kpt: 0.000614 acc_pose: 0.820231 loss: 0.000614 2022/09/23 13:54:19 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 13:54:50 - mmengine - INFO - Epoch(train) [165][50/293] lr: 5.000000e-04 eta: 3:13:10 time: 0.607549 data_time: 0.105982 memory: 14267 loss_kpt: 0.000599 acc_pose: 0.837946 loss: 0.000599 2022/09/23 13:55:19 - mmengine - INFO - Epoch(train) [165][100/293] lr: 5.000000e-04 eta: 3:12:23 time: 0.577474 data_time: 0.104367 memory: 14267 loss_kpt: 0.000598 acc_pose: 0.832322 loss: 0.000598 2022/09/23 13:55:48 - mmengine - INFO - Epoch(train) [165][150/293] lr: 5.000000e-04 eta: 3:11:36 time: 0.590314 data_time: 0.102805 memory: 14267 loss_kpt: 0.000604 acc_pose: 0.853118 loss: 0.000604 2022/09/23 13:56:18 - mmengine - INFO - Epoch(train) [165][200/293] lr: 5.000000e-04 eta: 3:10:49 time: 0.590506 data_time: 0.103763 memory: 14267 loss_kpt: 0.000597 acc_pose: 0.825080 loss: 0.000597 2022/09/23 13:56:47 - mmengine - INFO - Epoch(train) [165][250/293] lr: 5.000000e-04 eta: 3:10:02 time: 0.584426 data_time: 0.098859 memory: 14267 loss_kpt: 0.000606 acc_pose: 0.821472 loss: 0.000606 2022/09/23 13:57:12 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 13:57:42 - mmengine - INFO - Epoch(train) [166][50/293] lr: 5.000000e-04 eta: 3:08:28 time: 0.602238 data_time: 0.098564 memory: 14267 loss_kpt: 0.000594 acc_pose: 0.794353 loss: 0.000594 2022/09/23 13:58:10 - mmengine - INFO - Epoch(train) [166][100/293] lr: 5.000000e-04 eta: 3:07:41 time: 0.560328 data_time: 0.084239 memory: 14267 loss_kpt: 0.000604 acc_pose: 0.832327 loss: 0.000604 2022/09/23 13:58:40 - mmengine - INFO - Epoch(train) [166][150/293] lr: 5.000000e-04 eta: 3:06:55 time: 0.600998 data_time: 0.092802 memory: 14267 loss_kpt: 0.000599 acc_pose: 0.869667 loss: 0.000599 2022/09/23 13:59:10 - mmengine - INFO - Epoch(train) [166][200/293] lr: 5.000000e-04 eta: 3:06:08 time: 0.593121 data_time: 0.089677 memory: 14267 loss_kpt: 0.000608 acc_pose: 0.877294 loss: 0.000608 2022/09/23 13:59:40 - mmengine - INFO - Epoch(train) [166][250/293] lr: 5.000000e-04 eta: 3:05:22 time: 0.601524 data_time: 0.096690 memory: 14267 loss_kpt: 0.000610 acc_pose: 0.843580 loss: 0.000610 2022/09/23 14:00:04 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 14:00:35 - mmengine - INFO - Epoch(train) [167][50/293] lr: 5.000000e-04 eta: 3:03:49 time: 0.605964 data_time: 0.122437 memory: 14267 loss_kpt: 0.000596 acc_pose: 0.805161 loss: 0.000596 2022/09/23 14:01:04 - mmengine - INFO - Epoch(train) [167][100/293] lr: 5.000000e-04 eta: 3:03:02 time: 0.595512 data_time: 0.080089 memory: 14267 loss_kpt: 0.000617 acc_pose: 0.868244 loss: 0.000617 2022/09/23 14:01:34 - mmengine - INFO - Epoch(train) [167][150/293] lr: 5.000000e-04 eta: 3:02:16 time: 0.588618 data_time: 0.082676 memory: 14267 loss_kpt: 0.000602 acc_pose: 0.826238 loss: 0.000602 2022/09/23 14:02:03 - mmengine - INFO - Epoch(train) [167][200/293] lr: 5.000000e-04 eta: 3:01:29 time: 0.581324 data_time: 0.102607 memory: 14267 loss_kpt: 0.000608 acc_pose: 0.829766 loss: 0.000608 2022/09/23 14:02:32 - mmengine - INFO - Epoch(train) [167][250/293] lr: 5.000000e-04 eta: 3:00:43 time: 0.589425 data_time: 0.104733 memory: 14267 loss_kpt: 0.000604 acc_pose: 0.863727 loss: 0.000604 2022/09/23 14:02:57 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 14:03:27 - mmengine - INFO - Epoch(train) [168][50/293] lr: 5.000000e-04 eta: 2:59:10 time: 0.606625 data_time: 0.117454 memory: 14267 loss_kpt: 0.000598 acc_pose: 0.843795 loss: 0.000598 2022/09/23 14:03:38 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 14:03:56 - mmengine - INFO - Epoch(train) [168][100/293] lr: 5.000000e-04 eta: 2:58:24 time: 0.581157 data_time: 0.108812 memory: 14267 loss_kpt: 0.000596 acc_pose: 0.877661 loss: 0.000596 2022/09/23 14:04:26 - mmengine - INFO - Epoch(train) [168][150/293] lr: 5.000000e-04 eta: 2:57:38 time: 0.596173 data_time: 0.101226 memory: 14267 loss_kpt: 0.000603 acc_pose: 0.840038 loss: 0.000603 2022/09/23 14:04:56 - mmengine - INFO - Epoch(train) [168][200/293] lr: 5.000000e-04 eta: 2:56:52 time: 0.588122 data_time: 0.104609 memory: 14267 loss_kpt: 0.000607 acc_pose: 0.846006 loss: 0.000607 2022/09/23 14:05:25 - mmengine - INFO - Epoch(train) [168][250/293] lr: 5.000000e-04 eta: 2:56:06 time: 0.594414 data_time: 0.095470 memory: 14267 loss_kpt: 0.000602 acc_pose: 0.815320 loss: 0.000602 2022/09/23 14:05:51 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 14:06:21 - mmengine - INFO - Epoch(train) [169][50/293] lr: 5.000000e-04 eta: 2:54:34 time: 0.595603 data_time: 0.120011 memory: 14267 loss_kpt: 0.000598 acc_pose: 0.848281 loss: 0.000598 2022/09/23 14:06:51 - mmengine - INFO - Epoch(train) [169][100/293] lr: 5.000000e-04 eta: 2:53:48 time: 0.614199 data_time: 0.103419 memory: 14267 loss_kpt: 0.000600 acc_pose: 0.866211 loss: 0.000600 2022/09/23 14:07:23 - mmengine - INFO - Epoch(train) [169][150/293] lr: 5.000000e-04 eta: 2:53:03 time: 0.636922 data_time: 0.090164 memory: 14267 loss_kpt: 0.000590 acc_pose: 0.840349 loss: 0.000590 2022/09/23 14:07:54 - mmengine - INFO - Epoch(train) [169][200/293] lr: 5.000000e-04 eta: 2:52:17 time: 0.610072 data_time: 0.084123 memory: 14267 loss_kpt: 0.000611 acc_pose: 0.811830 loss: 0.000611 2022/09/23 14:08:22 - mmengine - INFO - Epoch(train) [169][250/293] lr: 5.000000e-04 eta: 2:51:31 time: 0.575256 data_time: 0.110399 memory: 14267 loss_kpt: 0.000611 acc_pose: 0.791791 loss: 0.000611 2022/09/23 14:08:47 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 14:09:17 - mmengine - INFO - Epoch(train) [170][50/293] lr: 5.000000e-04 eta: 2:50:00 time: 0.604371 data_time: 0.107423 memory: 14267 loss_kpt: 0.000613 acc_pose: 0.804562 loss: 0.000613 2022/09/23 14:09:45 - mmengine - INFO - Epoch(train) [170][100/293] lr: 5.000000e-04 eta: 2:49:13 time: 0.557657 data_time: 0.087776 memory: 14267 loss_kpt: 0.000597 acc_pose: 0.855730 loss: 0.000597 2022/09/23 14:10:15 - mmengine - INFO - Epoch(train) [170][150/293] lr: 5.000000e-04 eta: 2:48:28 time: 0.601889 data_time: 0.113504 memory: 14267 loss_kpt: 0.000590 acc_pose: 0.846715 loss: 0.000590 2022/09/23 14:10:44 - mmengine - INFO - Epoch(train) [170][200/293] lr: 5.000000e-04 eta: 2:47:42 time: 0.580670 data_time: 0.098418 memory: 14267 loss_kpt: 0.000591 acc_pose: 0.848938 loss: 0.000591 2022/09/23 14:11:14 - mmengine - INFO - Epoch(train) [170][250/293] lr: 5.000000e-04 eta: 2:46:56 time: 0.585935 data_time: 0.098966 memory: 14267 loss_kpt: 0.000619 acc_pose: 0.801281 loss: 0.000619 2022/09/23 14:11:39 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 14:11:39 - mmengine - INFO - Saving checkpoint at 170 epochs 2022/09/23 14:12:02 - mmengine - INFO - Epoch(val) [170][50/407] eta: 0:01:56 time: 0.325357 data_time: 0.159898 memory: 14267 2022/09/23 14:12:17 - mmengine - INFO - Epoch(val) [170][100/407] eta: 0:01:34 time: 0.307592 data_time: 0.143665 memory: 1464 2022/09/23 14:12:33 - mmengine - INFO - Epoch(val) [170][150/407] eta: 0:01:23 time: 0.325028 data_time: 0.164510 memory: 1464 2022/09/23 14:12:48 - mmengine - INFO - Epoch(val) [170][200/407] eta: 0:00:59 time: 0.286487 data_time: 0.137045 memory: 1464 2022/09/23 14:13:03 - mmengine - INFO - Epoch(val) [170][250/407] eta: 0:00:47 time: 0.303211 data_time: 0.125085 memory: 1464 2022/09/23 14:13:19 - mmengine - INFO - Epoch(val) [170][300/407] eta: 0:00:34 time: 0.319172 data_time: 0.155942 memory: 1464 2022/09/23 14:13:35 - mmengine - INFO - Epoch(val) [170][350/407] eta: 0:00:17 time: 0.315118 data_time: 0.133141 memory: 1464 2022/09/23 14:13:48 - mmengine - INFO - Epoch(val) [170][400/407] eta: 0:00:01 time: 0.259917 data_time: 0.119397 memory: 1464 2022/09/23 14:14:21 - mmengine - INFO - Evaluating CocoMetric... 2022/09/23 14:14:35 - mmengine - INFO - Epoch(val) [170][407/407] coco/AP: 0.718063 coco/AP .5: 0.895968 coco/AP .75: 0.786650 coco/AP (M): 0.675023 coco/AP (L): 0.791800 coco/AR: 0.771363 coco/AR .5: 0.933722 coco/AR .75: 0.831864 coco/AR (M): 0.723026 coco/AR (L): 0.840357 2022/09/23 14:15:05 - mmengine - INFO - Epoch(train) [171][50/293] lr: 5.000000e-05 eta: 2:45:26 time: 0.604217 data_time: 0.106749 memory: 14267 loss_kpt: 0.000598 acc_pose: 0.824758 loss: 0.000598 2022/09/23 14:15:35 - mmengine - INFO - Epoch(train) [171][100/293] lr: 5.000000e-05 eta: 2:44:40 time: 0.592625 data_time: 0.128374 memory: 14267 loss_kpt: 0.000587 acc_pose: 0.792146 loss: 0.000587 2022/09/23 14:16:04 - mmengine - INFO - Epoch(train) [171][150/293] lr: 5.000000e-05 eta: 2:43:55 time: 0.594342 data_time: 0.094621 memory: 14267 loss_kpt: 0.000582 acc_pose: 0.854895 loss: 0.000582 2022/09/23 14:16:29 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 14:16:35 - mmengine - INFO - Epoch(train) [171][200/293] lr: 5.000000e-05 eta: 2:43:09 time: 0.607116 data_time: 0.105899 memory: 14267 loss_kpt: 0.000582 acc_pose: 0.847178 loss: 0.000582 2022/09/23 14:17:05 - mmengine - INFO - Epoch(train) [171][250/293] lr: 5.000000e-05 eta: 2:42:24 time: 0.601566 data_time: 0.096818 memory: 14267 loss_kpt: 0.000574 acc_pose: 0.852982 loss: 0.000574 2022/09/23 14:17:30 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 14:18:01 - mmengine - INFO - Epoch(train) [172][50/293] lr: 5.000000e-05 eta: 2:40:54 time: 0.615910 data_time: 0.088887 memory: 14267 loss_kpt: 0.000595 acc_pose: 0.850808 loss: 0.000595 2022/09/23 14:18:30 - mmengine - INFO - Epoch(train) [172][100/293] lr: 5.000000e-05 eta: 2:40:09 time: 0.576255 data_time: 0.092689 memory: 14267 loss_kpt: 0.000579 acc_pose: 0.828698 loss: 0.000579 2022/09/23 14:19:00 - mmengine - INFO - Epoch(train) [172][150/293] lr: 5.000000e-05 eta: 2:39:23 time: 0.603550 data_time: 0.094698 memory: 14267 loss_kpt: 0.000600 acc_pose: 0.870432 loss: 0.000600 2022/09/23 14:19:30 - mmengine - INFO - Epoch(train) [172][200/293] lr: 5.000000e-05 eta: 2:38:38 time: 0.602013 data_time: 0.093777 memory: 14267 loss_kpt: 0.000592 acc_pose: 0.873788 loss: 0.000592 2022/09/23 14:19:59 - mmengine - INFO - Epoch(train) [172][250/293] lr: 5.000000e-05 eta: 2:37:53 time: 0.574261 data_time: 0.087052 memory: 14267 loss_kpt: 0.000578 acc_pose: 0.859057 loss: 0.000578 2022/09/23 14:20:24 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 14:20:54 - mmengine - INFO - Epoch(train) [173][50/293] lr: 5.000000e-05 eta: 2:36:23 time: 0.603570 data_time: 0.107283 memory: 14267 loss_kpt: 0.000580 acc_pose: 0.804433 loss: 0.000580 2022/09/23 14:21:23 - mmengine - INFO - Epoch(train) [173][100/293] lr: 5.000000e-05 eta: 2:35:38 time: 0.588625 data_time: 0.096674 memory: 14267 loss_kpt: 0.000581 acc_pose: 0.840557 loss: 0.000581 2022/09/23 14:21:53 - mmengine - INFO - Epoch(train) [173][150/293] lr: 5.000000e-05 eta: 2:34:53 time: 0.584346 data_time: 0.112923 memory: 14267 loss_kpt: 0.000572 acc_pose: 0.795502 loss: 0.000572 2022/09/23 14:22:21 - mmengine - INFO - Epoch(train) [173][200/293] lr: 5.000000e-05 eta: 2:34:08 time: 0.572502 data_time: 0.091181 memory: 14267 loss_kpt: 0.000576 acc_pose: 0.823872 loss: 0.000576 2022/09/23 14:22:51 - mmengine - INFO - Epoch(train) [173][250/293] lr: 5.000000e-05 eta: 2:33:23 time: 0.590978 data_time: 0.107661 memory: 14267 loss_kpt: 0.000569 acc_pose: 0.888436 loss: 0.000569 2022/09/23 14:23:15 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 14:23:46 - mmengine - INFO - Epoch(train) [174][50/293] lr: 5.000000e-05 eta: 2:31:54 time: 0.611785 data_time: 0.121548 memory: 14267 loss_kpt: 0.000575 acc_pose: 0.898680 loss: 0.000575 2022/09/23 14:24:16 - mmengine - INFO - Epoch(train) [174][100/293] lr: 5.000000e-05 eta: 2:31:09 time: 0.606287 data_time: 0.095143 memory: 14267 loss_kpt: 0.000579 acc_pose: 0.863650 loss: 0.000579 2022/09/23 14:24:46 - mmengine - INFO - Epoch(train) [174][150/293] lr: 5.000000e-05 eta: 2:30:24 time: 0.593094 data_time: 0.106872 memory: 14267 loss_kpt: 0.000576 acc_pose: 0.786692 loss: 0.000576 2022/09/23 14:25:15 - mmengine - INFO - Epoch(train) [174][200/293] lr: 5.000000e-05 eta: 2:29:39 time: 0.593159 data_time: 0.088826 memory: 14267 loss_kpt: 0.000575 acc_pose: 0.856077 loss: 0.000575 2022/09/23 14:25:45 - mmengine - INFO - Epoch(train) [174][250/293] lr: 5.000000e-05 eta: 2:28:55 time: 0.600485 data_time: 0.106952 memory: 14267 loss_kpt: 0.000578 acc_pose: 0.861355 loss: 0.000578 2022/09/23 14:26:10 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 14:26:22 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 14:26:40 - mmengine - INFO - Epoch(train) [175][50/293] lr: 5.000000e-05 eta: 2:27:26 time: 0.612425 data_time: 0.101995 memory: 14267 loss_kpt: 0.000576 acc_pose: 0.842687 loss: 0.000576 2022/09/23 14:27:10 - mmengine - INFO - Epoch(train) [175][100/293] lr: 5.000000e-05 eta: 2:26:42 time: 0.586979 data_time: 0.085939 memory: 14267 loss_kpt: 0.000585 acc_pose: 0.858248 loss: 0.000585 2022/09/23 14:27:41 - mmengine - INFO - Epoch(train) [175][150/293] lr: 5.000000e-05 eta: 2:25:57 time: 0.616664 data_time: 0.083692 memory: 14267 loss_kpt: 0.000571 acc_pose: 0.872940 loss: 0.000571 2022/09/23 14:28:10 - mmengine - INFO - Epoch(train) [175][200/293] lr: 5.000000e-05 eta: 2:25:13 time: 0.590990 data_time: 0.084503 memory: 14267 loss_kpt: 0.000576 acc_pose: 0.868138 loss: 0.000576 2022/09/23 14:28:40 - mmengine - INFO - Epoch(train) [175][250/293] lr: 5.000000e-05 eta: 2:24:28 time: 0.598195 data_time: 0.091139 memory: 14267 loss_kpt: 0.000579 acc_pose: 0.796642 loss: 0.000579 2022/09/23 14:29:05 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 14:29:37 - mmengine - INFO - Epoch(train) [176][50/293] lr: 5.000000e-05 eta: 2:23:00 time: 0.631011 data_time: 0.110318 memory: 14267 loss_kpt: 0.000570 acc_pose: 0.857082 loss: 0.000570 2022/09/23 14:30:09 - mmengine - INFO - Epoch(train) [176][100/293] lr: 5.000000e-05 eta: 2:22:16 time: 0.630000 data_time: 0.100990 memory: 14267 loss_kpt: 0.000567 acc_pose: 0.843306 loss: 0.000567 2022/09/23 14:30:38 - mmengine - INFO - Epoch(train) [176][150/293] lr: 5.000000e-05 eta: 2:21:32 time: 0.579048 data_time: 0.086271 memory: 14267 loss_kpt: 0.000572 acc_pose: 0.852183 loss: 0.000572 2022/09/23 14:31:07 - mmengine - INFO - Epoch(train) [176][200/293] lr: 5.000000e-05 eta: 2:20:47 time: 0.581321 data_time: 0.083387 memory: 14267 loss_kpt: 0.000570 acc_pose: 0.847636 loss: 0.000570 2022/09/23 14:31:37 - mmengine - INFO - Epoch(train) [176][250/293] lr: 5.000000e-05 eta: 2:20:03 time: 0.614922 data_time: 0.087048 memory: 14267 loss_kpt: 0.000574 acc_pose: 0.825369 loss: 0.000574 2022/09/23 14:32:03 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 14:32:34 - mmengine - INFO - Epoch(train) [177][50/293] lr: 5.000000e-05 eta: 2:18:36 time: 0.628868 data_time: 0.112882 memory: 14267 loss_kpt: 0.000559 acc_pose: 0.846516 loss: 0.000559 2022/09/23 14:33:05 - mmengine - INFO - Epoch(train) [177][100/293] lr: 5.000000e-05 eta: 2:17:52 time: 0.609335 data_time: 0.114265 memory: 14267 loss_kpt: 0.000569 acc_pose: 0.854387 loss: 0.000569 2022/09/23 14:33:35 - mmengine - INFO - Epoch(train) [177][150/293] lr: 5.000000e-05 eta: 2:17:08 time: 0.606935 data_time: 0.085466 memory: 14267 loss_kpt: 0.000580 acc_pose: 0.815368 loss: 0.000580 2022/09/23 14:34:04 - mmengine - INFO - Epoch(train) [177][200/293] lr: 5.000000e-05 eta: 2:16:23 time: 0.577016 data_time: 0.081969 memory: 14267 loss_kpt: 0.000567 acc_pose: 0.843607 loss: 0.000567 2022/09/23 14:34:33 - mmengine - INFO - Epoch(train) [177][250/293] lr: 5.000000e-05 eta: 2:15:39 time: 0.583018 data_time: 0.087393 memory: 14267 loss_kpt: 0.000565 acc_pose: 0.910881 loss: 0.000565 2022/09/23 14:34:59 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 14:35:31 - mmengine - INFO - Epoch(train) [178][50/293] lr: 5.000000e-05 eta: 2:14:12 time: 0.635478 data_time: 0.111683 memory: 14267 loss_kpt: 0.000555 acc_pose: 0.826490 loss: 0.000555 2022/09/23 14:36:00 - mmengine - INFO - Epoch(train) [178][100/293] lr: 5.000000e-05 eta: 2:13:28 time: 0.589782 data_time: 0.083961 memory: 14267 loss_kpt: 0.000572 acc_pose: 0.861543 loss: 0.000572 2022/09/23 14:36:22 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 14:36:29 - mmengine - INFO - Epoch(train) [178][150/293] lr: 5.000000e-05 eta: 2:12:44 time: 0.572469 data_time: 0.074199 memory: 14267 loss_kpt: 0.000558 acc_pose: 0.874051 loss: 0.000558 2022/09/23 14:36:58 - mmengine - INFO - Epoch(train) [178][200/293] lr: 5.000000e-05 eta: 2:12:00 time: 0.588200 data_time: 0.085749 memory: 14267 loss_kpt: 0.000565 acc_pose: 0.870885 loss: 0.000565 2022/09/23 14:37:27 - mmengine - INFO - Epoch(train) [178][250/293] lr: 5.000000e-05 eta: 2:11:16 time: 0.575607 data_time: 0.098021 memory: 14267 loss_kpt: 0.000583 acc_pose: 0.873846 loss: 0.000583 2022/09/23 14:37:52 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 14:38:24 - mmengine - INFO - Epoch(train) [179][50/293] lr: 5.000000e-05 eta: 2:09:50 time: 0.628847 data_time: 0.111890 memory: 14267 loss_kpt: 0.000569 acc_pose: 0.835541 loss: 0.000569 2022/09/23 14:38:53 - mmengine - INFO - Epoch(train) [179][100/293] lr: 5.000000e-05 eta: 2:09:06 time: 0.585698 data_time: 0.081630 memory: 14267 loss_kpt: 0.000574 acc_pose: 0.833579 loss: 0.000574 2022/09/23 14:39:23 - mmengine - INFO - Epoch(train) [179][150/293] lr: 5.000000e-05 eta: 2:08:22 time: 0.597023 data_time: 0.100842 memory: 14267 loss_kpt: 0.000573 acc_pose: 0.856086 loss: 0.000573 2022/09/23 14:39:51 - mmengine - INFO - Epoch(train) [179][200/293] lr: 5.000000e-05 eta: 2:07:38 time: 0.568457 data_time: 0.084161 memory: 14267 loss_kpt: 0.000575 acc_pose: 0.813168 loss: 0.000575 2022/09/23 14:40:20 - mmengine - INFO - Epoch(train) [179][250/293] lr: 5.000000e-05 eta: 2:06:54 time: 0.580166 data_time: 0.085167 memory: 14267 loss_kpt: 0.000565 acc_pose: 0.818815 loss: 0.000565 2022/09/23 14:40:45 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 14:41:16 - mmengine - INFO - Epoch(train) [180][50/293] lr: 5.000000e-05 eta: 2:05:28 time: 0.614145 data_time: 0.102693 memory: 14267 loss_kpt: 0.000564 acc_pose: 0.861542 loss: 0.000564 2022/09/23 14:41:45 - mmengine - INFO - Epoch(train) [180][100/293] lr: 5.000000e-05 eta: 2:04:44 time: 0.581975 data_time: 0.087317 memory: 14267 loss_kpt: 0.000569 acc_pose: 0.860796 loss: 0.000569 2022/09/23 14:42:14 - mmengine - INFO - Epoch(train) [180][150/293] lr: 5.000000e-05 eta: 2:04:01 time: 0.582258 data_time: 0.105696 memory: 14267 loss_kpt: 0.000559 acc_pose: 0.910785 loss: 0.000559 2022/09/23 14:42:44 - mmengine - INFO - Epoch(train) [180][200/293] lr: 5.000000e-05 eta: 2:03:17 time: 0.604797 data_time: 0.105824 memory: 14267 loss_kpt: 0.000562 acc_pose: 0.850881 loss: 0.000562 2022/09/23 14:43:14 - mmengine - INFO - Epoch(train) [180][250/293] lr: 5.000000e-05 eta: 2:02:33 time: 0.587843 data_time: 0.103950 memory: 14267 loss_kpt: 0.000576 acc_pose: 0.831356 loss: 0.000576 2022/09/23 14:43:38 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 14:43:38 - mmengine - INFO - Saving checkpoint at 180 epochs 2022/09/23 14:44:01 - mmengine - INFO - Epoch(val) [180][50/407] eta: 0:01:59 time: 0.333531 data_time: 0.189245 memory: 14267 2022/09/23 14:44:17 - mmengine - INFO - Epoch(val) [180][100/407] eta: 0:01:38 time: 0.321773 data_time: 0.154437 memory: 1464 2022/09/23 14:44:33 - mmengine - INFO - Epoch(val) [180][150/407] eta: 0:01:22 time: 0.322686 data_time: 0.181447 memory: 1464 2022/09/23 14:44:50 - mmengine - INFO - Epoch(val) [180][200/407] eta: 0:01:06 time: 0.322909 data_time: 0.177643 memory: 1464 2022/09/23 14:45:05 - mmengine - INFO - Epoch(val) [180][250/407] eta: 0:00:47 time: 0.301832 data_time: 0.146128 memory: 1464 2022/09/23 14:45:21 - mmengine - INFO - Epoch(val) [180][300/407] eta: 0:00:35 time: 0.328427 data_time: 0.169867 memory: 1464 2022/09/23 14:45:38 - mmengine - INFO - Epoch(val) [180][350/407] eta: 0:00:18 time: 0.331149 data_time: 0.171236 memory: 1464 2022/09/23 14:45:51 - mmengine - INFO - Epoch(val) [180][400/407] eta: 0:00:01 time: 0.257846 data_time: 0.121111 memory: 1464 2022/09/23 14:46:24 - mmengine - INFO - Evaluating CocoMetric... 2022/09/23 14:46:36 - mmengine - INFO - Epoch(val) [180][407/407] coco/AP: 0.729034 coco/AP .5: 0.899016 coco/AP .75: 0.794649 coco/AP (M): 0.685363 coco/AP (L): 0.803468 coco/AR: 0.780290 coco/AR .5: 0.934666 coco/AR .75: 0.839893 coco/AR (M): 0.731631 coco/AR (L): 0.850093 2022/09/23 14:46:37 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220922/res50_384_2/best_coco/AP_epoch_160.pth is removed 2022/09/23 14:46:39 - mmengine - INFO - The best checkpoint with 0.7290 coco/AP at 180 epoch is saved to best_coco/AP_epoch_180.pth. 2022/09/23 14:47:09 - mmengine - INFO - Epoch(train) [181][50/293] lr: 5.000000e-05 eta: 2:01:08 time: 0.599125 data_time: 0.096751 memory: 14267 loss_kpt: 0.000582 acc_pose: 0.858637 loss: 0.000582 2022/09/23 14:47:38 - mmengine - INFO - Epoch(train) [181][100/293] lr: 5.000000e-05 eta: 2:00:24 time: 0.581274 data_time: 0.088878 memory: 14267 loss_kpt: 0.000586 acc_pose: 0.841406 loss: 0.000586 2022/09/23 14:48:07 - mmengine - INFO - Epoch(train) [181][150/293] lr: 5.000000e-05 eta: 1:59:41 time: 0.575091 data_time: 0.090653 memory: 14267 loss_kpt: 0.000570 acc_pose: 0.811708 loss: 0.000570 2022/09/23 14:48:37 - mmengine - INFO - Epoch(train) [181][200/293] lr: 5.000000e-05 eta: 1:58:57 time: 0.601933 data_time: 0.097247 memory: 14267 loss_kpt: 0.000555 acc_pose: 0.858521 loss: 0.000555 2022/09/23 14:49:06 - mmengine - INFO - Epoch(train) [181][250/293] lr: 5.000000e-05 eta: 1:58:14 time: 0.586294 data_time: 0.096096 memory: 14267 loss_kpt: 0.000540 acc_pose: 0.856858 loss: 0.000540 2022/09/23 14:49:12 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 14:49:31 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 14:50:00 - mmengine - INFO - Epoch(train) [182][50/293] lr: 5.000000e-05 eta: 1:56:49 time: 0.590085 data_time: 0.116469 memory: 14267 loss_kpt: 0.000565 acc_pose: 0.870070 loss: 0.000565 2022/09/23 14:50:29 - mmengine - INFO - Epoch(train) [182][100/293] lr: 5.000000e-05 eta: 1:56:05 time: 0.577298 data_time: 0.094640 memory: 14267 loss_kpt: 0.000575 acc_pose: 0.872900 loss: 0.000575 2022/09/23 14:50:59 - mmengine - INFO - Epoch(train) [182][150/293] lr: 5.000000e-05 eta: 1:55:22 time: 0.595059 data_time: 0.101366 memory: 14267 loss_kpt: 0.000557 acc_pose: 0.861624 loss: 0.000557 2022/09/23 14:51:28 - mmengine - INFO - Epoch(train) [182][200/293] lr: 5.000000e-05 eta: 1:54:39 time: 0.573571 data_time: 0.095451 memory: 14267 loss_kpt: 0.000564 acc_pose: 0.846391 loss: 0.000564 2022/09/23 14:51:57 - mmengine - INFO - Epoch(train) [182][250/293] lr: 5.000000e-05 eta: 1:53:55 time: 0.598175 data_time: 0.089171 memory: 14267 loss_kpt: 0.000580 acc_pose: 0.842313 loss: 0.000580 2022/09/23 14:52:22 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 14:52:52 - mmengine - INFO - Epoch(train) [183][50/293] lr: 5.000000e-05 eta: 1:52:31 time: 0.600172 data_time: 0.112845 memory: 14267 loss_kpt: 0.000573 acc_pose: 0.892227 loss: 0.000573 2022/09/23 14:53:22 - mmengine - INFO - Epoch(train) [183][100/293] lr: 5.000000e-05 eta: 1:51:48 time: 0.603995 data_time: 0.098041 memory: 14267 loss_kpt: 0.000567 acc_pose: 0.848875 loss: 0.000567 2022/09/23 14:53:51 - mmengine - INFO - Epoch(train) [183][150/293] lr: 5.000000e-05 eta: 1:51:05 time: 0.585957 data_time: 0.098542 memory: 14267 loss_kpt: 0.000562 acc_pose: 0.847908 loss: 0.000562 2022/09/23 14:54:21 - mmengine - INFO - Epoch(train) [183][200/293] lr: 5.000000e-05 eta: 1:50:22 time: 0.602526 data_time: 0.105262 memory: 14267 loss_kpt: 0.000563 acc_pose: 0.899167 loss: 0.000563 2022/09/23 14:54:50 - mmengine - INFO - Epoch(train) [183][250/293] lr: 5.000000e-05 eta: 1:49:38 time: 0.576457 data_time: 0.076186 memory: 14267 loss_kpt: 0.000561 acc_pose: 0.832751 loss: 0.000561 2022/09/23 14:55:15 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 14:55:46 - mmengine - INFO - Epoch(train) [184][50/293] lr: 5.000000e-05 eta: 1:48:15 time: 0.619436 data_time: 0.105591 memory: 14267 loss_kpt: 0.000565 acc_pose: 0.847575 loss: 0.000565 2022/09/23 14:56:16 - mmengine - INFO - Epoch(train) [184][100/293] lr: 5.000000e-05 eta: 1:47:32 time: 0.600337 data_time: 0.100778 memory: 14267 loss_kpt: 0.000557 acc_pose: 0.811322 loss: 0.000557 2022/09/23 14:56:45 - mmengine - INFO - Epoch(train) [184][150/293] lr: 5.000000e-05 eta: 1:46:49 time: 0.588949 data_time: 0.099891 memory: 14267 loss_kpt: 0.000548 acc_pose: 0.844285 loss: 0.000548 2022/09/23 14:57:16 - mmengine - INFO - Epoch(train) [184][200/293] lr: 5.000000e-05 eta: 1:46:06 time: 0.610515 data_time: 0.086423 memory: 14267 loss_kpt: 0.000566 acc_pose: 0.850268 loss: 0.000566 2022/09/23 14:57:45 - mmengine - INFO - Epoch(train) [184][250/293] lr: 5.000000e-05 eta: 1:45:23 time: 0.588699 data_time: 0.110365 memory: 14267 loss_kpt: 0.000559 acc_pose: 0.820921 loss: 0.000559 2022/09/23 14:58:11 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 14:58:41 - mmengine - INFO - Epoch(train) [185][50/293] lr: 5.000000e-05 eta: 1:44:00 time: 0.613437 data_time: 0.139868 memory: 14267 loss_kpt: 0.000563 acc_pose: 0.835384 loss: 0.000563 2022/09/23 14:59:03 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 14:59:09 - mmengine - INFO - Epoch(train) [185][100/293] lr: 5.000000e-05 eta: 1:43:17 time: 0.555334 data_time: 0.078560 memory: 14267 loss_kpt: 0.000576 acc_pose: 0.815795 loss: 0.000576 2022/09/23 14:59:39 - mmengine - INFO - Epoch(train) [185][150/293] lr: 5.000000e-05 eta: 1:42:34 time: 0.586844 data_time: 0.090757 memory: 14267 loss_kpt: 0.000565 acc_pose: 0.859616 loss: 0.000565 2022/09/23 15:00:08 - mmengine - INFO - Epoch(train) [185][200/293] lr: 5.000000e-05 eta: 1:41:51 time: 0.581888 data_time: 0.094424 memory: 14267 loss_kpt: 0.000581 acc_pose: 0.851625 loss: 0.000581 2022/09/23 15:00:36 - mmengine - INFO - Epoch(train) [185][250/293] lr: 5.000000e-05 eta: 1:41:08 time: 0.573123 data_time: 0.095098 memory: 14267 loss_kpt: 0.000560 acc_pose: 0.827380 loss: 0.000560 2022/09/23 15:01:02 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 15:01:32 - mmengine - INFO - Epoch(train) [186][50/293] lr: 5.000000e-05 eta: 1:39:45 time: 0.616173 data_time: 0.112645 memory: 14267 loss_kpt: 0.000553 acc_pose: 0.838829 loss: 0.000553 2022/09/23 15:02:02 - mmengine - INFO - Epoch(train) [186][100/293] lr: 5.000000e-05 eta: 1:39:03 time: 0.592135 data_time: 0.095174 memory: 14267 loss_kpt: 0.000555 acc_pose: 0.809597 loss: 0.000555 2022/09/23 15:02:31 - mmengine - INFO - Epoch(train) [186][150/293] lr: 5.000000e-05 eta: 1:38:20 time: 0.584399 data_time: 0.102767 memory: 14267 loss_kpt: 0.000561 acc_pose: 0.862503 loss: 0.000561 2022/09/23 15:03:01 - mmengine - INFO - Epoch(train) [186][200/293] lr: 5.000000e-05 eta: 1:37:37 time: 0.587257 data_time: 0.099313 memory: 14267 loss_kpt: 0.000548 acc_pose: 0.843004 loss: 0.000548 2022/09/23 15:03:29 - mmengine - INFO - Epoch(train) [186][250/293] lr: 5.000000e-05 eta: 1:36:55 time: 0.578571 data_time: 0.087085 memory: 14267 loss_kpt: 0.000564 acc_pose: 0.860059 loss: 0.000564 2022/09/23 15:03:54 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 15:04:25 - mmengine - INFO - Epoch(train) [187][50/293] lr: 5.000000e-05 eta: 1:35:32 time: 0.603678 data_time: 0.110216 memory: 14267 loss_kpt: 0.000553 acc_pose: 0.891445 loss: 0.000553 2022/09/23 15:04:54 - mmengine - INFO - Epoch(train) [187][100/293] lr: 5.000000e-05 eta: 1:34:50 time: 0.591210 data_time: 0.108027 memory: 14267 loss_kpt: 0.000553 acc_pose: 0.880202 loss: 0.000553 2022/09/23 15:05:23 - mmengine - INFO - Epoch(train) [187][150/293] lr: 5.000000e-05 eta: 1:34:07 time: 0.568165 data_time: 0.099758 memory: 14267 loss_kpt: 0.000547 acc_pose: 0.848023 loss: 0.000547 2022/09/23 15:05:51 - mmengine - INFO - Epoch(train) [187][200/293] lr: 5.000000e-05 eta: 1:33:25 time: 0.572278 data_time: 0.088369 memory: 14267 loss_kpt: 0.000559 acc_pose: 0.867332 loss: 0.000559 2022/09/23 15:06:21 - mmengine - INFO - Epoch(train) [187][250/293] lr: 5.000000e-05 eta: 1:32:42 time: 0.590301 data_time: 0.094950 memory: 14267 loss_kpt: 0.000557 acc_pose: 0.851861 loss: 0.000557 2022/09/23 15:06:45 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 15:07:16 - mmengine - INFO - Epoch(train) [188][50/293] lr: 5.000000e-05 eta: 1:31:20 time: 0.614936 data_time: 0.109548 memory: 14267 loss_kpt: 0.000562 acc_pose: 0.882664 loss: 0.000562 2022/09/23 15:07:45 - mmengine - INFO - Epoch(train) [188][100/293] lr: 5.000000e-05 eta: 1:30:38 time: 0.583612 data_time: 0.101572 memory: 14267 loss_kpt: 0.000562 acc_pose: 0.856028 loss: 0.000562 2022/09/23 15:08:15 - mmengine - INFO - Epoch(train) [188][150/293] lr: 5.000000e-05 eta: 1:29:56 time: 0.600779 data_time: 0.108577 memory: 14267 loss_kpt: 0.000556 acc_pose: 0.830555 loss: 0.000556 2022/09/23 15:08:44 - mmengine - INFO - Epoch(train) [188][200/293] lr: 5.000000e-05 eta: 1:29:13 time: 0.575879 data_time: 0.100247 memory: 14267 loss_kpt: 0.000567 acc_pose: 0.865369 loss: 0.000567 2022/09/23 15:08:49 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 15:09:12 - mmengine - INFO - Epoch(train) [188][250/293] lr: 5.000000e-05 eta: 1:28:31 time: 0.567503 data_time: 0.085601 memory: 14267 loss_kpt: 0.000561 acc_pose: 0.876893 loss: 0.000561 2022/09/23 15:09:37 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 15:10:08 - mmengine - INFO - Epoch(train) [189][50/293] lr: 5.000000e-05 eta: 1:27:09 time: 0.614127 data_time: 0.105758 memory: 14267 loss_kpt: 0.000568 acc_pose: 0.880221 loss: 0.000568 2022/09/23 15:10:37 - mmengine - INFO - Epoch(train) [189][100/293] lr: 5.000000e-05 eta: 1:26:27 time: 0.579662 data_time: 0.107882 memory: 14267 loss_kpt: 0.000561 acc_pose: 0.888588 loss: 0.000561 2022/09/23 15:11:07 - mmengine - INFO - Epoch(train) [189][150/293] lr: 5.000000e-05 eta: 1:25:45 time: 0.586350 data_time: 0.103072 memory: 14267 loss_kpt: 0.000561 acc_pose: 0.835253 loss: 0.000561 2022/09/23 15:11:36 - mmengine - INFO - Epoch(train) [189][200/293] lr: 5.000000e-05 eta: 1:25:03 time: 0.586566 data_time: 0.100746 memory: 14267 loss_kpt: 0.000556 acc_pose: 0.855091 loss: 0.000556 2022/09/23 15:12:06 - mmengine - INFO - Epoch(train) [189][250/293] lr: 5.000000e-05 eta: 1:24:21 time: 0.592880 data_time: 0.094560 memory: 14267 loss_kpt: 0.000559 acc_pose: 0.830740 loss: 0.000559 2022/09/23 15:12:31 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 15:13:01 - mmengine - INFO - Epoch(train) [190][50/293] lr: 5.000000e-05 eta: 1:23:00 time: 0.604454 data_time: 0.120920 memory: 14267 loss_kpt: 0.000560 acc_pose: 0.881313 loss: 0.000560 2022/09/23 15:13:30 - mmengine - INFO - Epoch(train) [190][100/293] lr: 5.000000e-05 eta: 1:22:18 time: 0.579125 data_time: 0.104043 memory: 14267 loss_kpt: 0.000567 acc_pose: 0.845505 loss: 0.000567 2022/09/23 15:13:59 - mmengine - INFO - Epoch(train) [190][150/293] lr: 5.000000e-05 eta: 1:21:35 time: 0.573540 data_time: 0.099453 memory: 14267 loss_kpt: 0.000567 acc_pose: 0.835022 loss: 0.000567 2022/09/23 15:14:29 - mmengine - INFO - Epoch(train) [190][200/293] lr: 5.000000e-05 eta: 1:20:54 time: 0.600325 data_time: 0.097451 memory: 14267 loss_kpt: 0.000560 acc_pose: 0.836672 loss: 0.000560 2022/09/23 15:14:59 - mmengine - INFO - Epoch(train) [190][250/293] lr: 5.000000e-05 eta: 1:20:12 time: 0.598030 data_time: 0.096962 memory: 14267 loss_kpt: 0.000554 acc_pose: 0.839818 loss: 0.000554 2022/09/23 15:15:24 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 15:15:24 - mmengine - INFO - Saving checkpoint at 190 epochs 2022/09/23 15:15:46 - mmengine - INFO - Epoch(val) [190][50/407] eta: 0:01:59 time: 0.335287 data_time: 0.172424 memory: 14267 2022/09/23 15:16:02 - mmengine - INFO - Epoch(val) [190][100/407] eta: 0:01:36 time: 0.313547 data_time: 0.152316 memory: 1464 2022/09/23 15:16:16 - mmengine - INFO - Epoch(val) [190][150/407] eta: 0:01:14 time: 0.291550 data_time: 0.131917 memory: 1464 2022/09/23 15:16:31 - mmengine - INFO - Epoch(val) [190][200/407] eta: 0:01:00 time: 0.293689 data_time: 0.141343 memory: 1464 2022/09/23 15:16:46 - mmengine - INFO - Epoch(val) [190][250/407] eta: 0:00:47 time: 0.300513 data_time: 0.137551 memory: 1464 2022/09/23 15:17:02 - mmengine - INFO - Epoch(val) [190][300/407] eta: 0:00:34 time: 0.325587 data_time: 0.157381 memory: 1464 2022/09/23 15:17:17 - mmengine - INFO - Epoch(val) [190][350/407] eta: 0:00:17 time: 0.304699 data_time: 0.146959 memory: 1464 2022/09/23 15:17:31 - mmengine - INFO - Epoch(val) [190][400/407] eta: 0:00:01 time: 0.277979 data_time: 0.134463 memory: 1464 2022/09/23 15:18:05 - mmengine - INFO - Evaluating CocoMetric... 2022/09/23 15:18:18 - mmengine - INFO - Epoch(val) [190][407/407] coco/AP: 0.730743 coco/AP .5: 0.900191 coco/AP .75: 0.798674 coco/AP (M): 0.686778 coco/AP (L): 0.805354 coco/AR: 0.781817 coco/AR .5: 0.936555 coco/AR .75: 0.842097 coco/AR (M): 0.733215 coco/AR (L): 0.851468 2022/09/23 15:18:18 - mmengine - INFO - The previous best checkpoint /mnt/lustre/liqikai/work_dirs/20220922/res50_384_2/best_coco/AP_epoch_180.pth is removed 2022/09/23 15:18:20 - mmengine - INFO - The best checkpoint with 0.7307 coco/AP at 190 epoch is saved to best_coco/AP_epoch_190.pth. 2022/09/23 15:18:50 - mmengine - INFO - Epoch(train) [191][50/293] lr: 5.000000e-05 eta: 1:18:51 time: 0.595215 data_time: 0.097623 memory: 14267 loss_kpt: 0.000556 acc_pose: 0.851237 loss: 0.000556 2022/09/23 15:19:20 - mmengine - INFO - Epoch(train) [191][100/293] lr: 5.000000e-05 eta: 1:18:09 time: 0.594910 data_time: 0.096620 memory: 14267 loss_kpt: 0.000570 acc_pose: 0.845510 loss: 0.000570 2022/09/23 15:19:49 - mmengine - INFO - Epoch(train) [191][150/293] lr: 5.000000e-05 eta: 1:17:27 time: 0.578672 data_time: 0.091036 memory: 14267 loss_kpt: 0.000555 acc_pose: 0.876506 loss: 0.000555 2022/09/23 15:20:17 - mmengine - INFO - Epoch(train) [191][200/293] lr: 5.000000e-05 eta: 1:16:45 time: 0.564870 data_time: 0.110798 memory: 14267 loss_kpt: 0.000561 acc_pose: 0.834657 loss: 0.000561 2022/09/23 15:20:47 - mmengine - INFO - Epoch(train) [191][250/293] lr: 5.000000e-05 eta: 1:16:04 time: 0.594813 data_time: 0.098864 memory: 14267 loss_kpt: 0.000562 acc_pose: 0.860602 loss: 0.000562 2022/09/23 15:21:11 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 15:21:34 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 15:21:41 - mmengine - INFO - Epoch(train) [192][50/293] lr: 5.000000e-05 eta: 1:14:43 time: 0.606992 data_time: 0.112624 memory: 14267 loss_kpt: 0.000560 acc_pose: 0.837560 loss: 0.000560 2022/09/23 15:22:11 - mmengine - INFO - Epoch(train) [192][100/293] lr: 5.000000e-05 eta: 1:14:02 time: 0.591156 data_time: 0.102344 memory: 14267 loss_kpt: 0.000567 acc_pose: 0.832084 loss: 0.000567 2022/09/23 15:22:39 - mmengine - INFO - Epoch(train) [192][150/293] lr: 5.000000e-05 eta: 1:13:20 time: 0.570926 data_time: 0.117981 memory: 14267 loss_kpt: 0.000561 acc_pose: 0.879943 loss: 0.000561 2022/09/23 15:23:09 - mmengine - INFO - Epoch(train) [192][200/293] lr: 5.000000e-05 eta: 1:12:38 time: 0.586048 data_time: 0.114331 memory: 14267 loss_kpt: 0.000556 acc_pose: 0.866212 loss: 0.000556 2022/09/23 15:23:37 - mmengine - INFO - Epoch(train) [192][250/293] lr: 5.000000e-05 eta: 1:11:56 time: 0.575220 data_time: 0.098632 memory: 14267 loss_kpt: 0.000567 acc_pose: 0.847216 loss: 0.000567 2022/09/23 15:24:03 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 15:24:33 - mmengine - INFO - Epoch(train) [193][50/293] lr: 5.000000e-05 eta: 1:10:37 time: 0.598777 data_time: 0.115796 memory: 14267 loss_kpt: 0.000572 acc_pose: 0.866443 loss: 0.000572 2022/09/23 15:25:03 - mmengine - INFO - Epoch(train) [193][100/293] lr: 5.000000e-05 eta: 1:09:55 time: 0.597419 data_time: 0.112638 memory: 14267 loss_kpt: 0.000561 acc_pose: 0.837416 loss: 0.000561 2022/09/23 15:25:31 - mmengine - INFO - Epoch(train) [193][150/293] lr: 5.000000e-05 eta: 1:09:14 time: 0.569669 data_time: 0.108729 memory: 14267 loss_kpt: 0.000565 acc_pose: 0.841715 loss: 0.000565 2022/09/23 15:26:01 - mmengine - INFO - Epoch(train) [193][200/293] lr: 5.000000e-05 eta: 1:08:32 time: 0.597470 data_time: 0.104860 memory: 14267 loss_kpt: 0.000561 acc_pose: 0.841925 loss: 0.000561 2022/09/23 15:26:30 - mmengine - INFO - Epoch(train) [193][250/293] lr: 5.000000e-05 eta: 1:07:51 time: 0.587601 data_time: 0.100684 memory: 14267 loss_kpt: 0.000568 acc_pose: 0.818060 loss: 0.000568 2022/09/23 15:26:55 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 15:27:26 - mmengine - INFO - Epoch(train) [194][50/293] lr: 5.000000e-05 eta: 1:06:31 time: 0.610562 data_time: 0.117165 memory: 14267 loss_kpt: 0.000554 acc_pose: 0.820657 loss: 0.000554 2022/09/23 15:27:55 - mmengine - INFO - Epoch(train) [194][100/293] lr: 5.000000e-05 eta: 1:05:50 time: 0.592355 data_time: 0.099838 memory: 14267 loss_kpt: 0.000557 acc_pose: 0.862877 loss: 0.000557 2022/09/23 15:28:25 - mmengine - INFO - Epoch(train) [194][150/293] lr: 5.000000e-05 eta: 1:05:08 time: 0.588254 data_time: 0.107505 memory: 14267 loss_kpt: 0.000563 acc_pose: 0.912697 loss: 0.000563 2022/09/23 15:28:54 - mmengine - INFO - Epoch(train) [194][200/293] lr: 5.000000e-05 eta: 1:04:27 time: 0.590515 data_time: 0.102787 memory: 14267 loss_kpt: 0.000564 acc_pose: 0.840028 loss: 0.000564 2022/09/23 15:29:24 - mmengine - INFO - Epoch(train) [194][250/293] lr: 5.000000e-05 eta: 1:03:46 time: 0.594226 data_time: 0.099645 memory: 14267 loss_kpt: 0.000558 acc_pose: 0.805124 loss: 0.000558 2022/09/23 15:29:49 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 15:30:18 - mmengine - INFO - Epoch(train) [195][50/293] lr: 5.000000e-05 eta: 1:02:27 time: 0.595196 data_time: 0.114631 memory: 14267 loss_kpt: 0.000563 acc_pose: 0.867463 loss: 0.000563 2022/09/23 15:30:48 - mmengine - INFO - Epoch(train) [195][100/293] lr: 5.000000e-05 eta: 1:01:46 time: 0.593870 data_time: 0.105654 memory: 14267 loss_kpt: 0.000558 acc_pose: 0.835435 loss: 0.000558 2022/09/23 15:31:18 - mmengine - INFO - Epoch(train) [195][150/293] lr: 5.000000e-05 eta: 1:01:04 time: 0.591349 data_time: 0.086030 memory: 14267 loss_kpt: 0.000558 acc_pose: 0.819666 loss: 0.000558 2022/09/23 15:31:23 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 15:31:47 - mmengine - INFO - Epoch(train) [195][200/293] lr: 5.000000e-05 eta: 1:00:23 time: 0.579413 data_time: 0.109075 memory: 14267 loss_kpt: 0.000547 acc_pose: 0.824592 loss: 0.000547 2022/09/23 15:32:17 - mmengine - INFO - Epoch(train) [195][250/293] lr: 5.000000e-05 eta: 0:59:42 time: 0.596862 data_time: 0.114522 memory: 14267 loss_kpt: 0.000555 acc_pose: 0.815094 loss: 0.000555 2022/09/23 15:32:42 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 15:33:12 - mmengine - INFO - Epoch(train) [196][50/293] lr: 5.000000e-05 eta: 0:58:23 time: 0.608023 data_time: 0.104385 memory: 14267 loss_kpt: 0.000567 acc_pose: 0.897773 loss: 0.000567 2022/09/23 15:33:40 - mmengine - INFO - Epoch(train) [196][100/293] lr: 5.000000e-05 eta: 0:57:42 time: 0.568061 data_time: 0.085959 memory: 14267 loss_kpt: 0.000568 acc_pose: 0.857044 loss: 0.000568 2022/09/23 15:34:09 - mmengine - INFO - Epoch(train) [196][150/293] lr: 5.000000e-05 eta: 0:57:01 time: 0.576345 data_time: 0.092989 memory: 14267 loss_kpt: 0.000541 acc_pose: 0.857186 loss: 0.000541 2022/09/23 15:34:39 - mmengine - INFO - Epoch(train) [196][200/293] lr: 5.000000e-05 eta: 0:56:20 time: 0.584879 data_time: 0.107412 memory: 14267 loss_kpt: 0.000552 acc_pose: 0.882690 loss: 0.000552 2022/09/23 15:35:08 - mmengine - INFO - Epoch(train) [196][250/293] lr: 5.000000e-05 eta: 0:55:39 time: 0.582205 data_time: 0.099410 memory: 14267 loss_kpt: 0.000553 acc_pose: 0.902880 loss: 0.000553 2022/09/23 15:35:32 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 15:36:02 - mmengine - INFO - Epoch(train) [197][50/293] lr: 5.000000e-05 eta: 0:54:21 time: 0.601185 data_time: 0.118579 memory: 14267 loss_kpt: 0.000554 acc_pose: 0.897281 loss: 0.000554 2022/09/23 15:36:31 - mmengine - INFO - Epoch(train) [197][100/293] lr: 5.000000e-05 eta: 0:53:40 time: 0.580474 data_time: 0.110934 memory: 14267 loss_kpt: 0.000544 acc_pose: 0.871716 loss: 0.000544 2022/09/23 15:37:00 - mmengine - INFO - Epoch(train) [197][150/293] lr: 5.000000e-05 eta: 0:52:59 time: 0.585063 data_time: 0.097222 memory: 14267 loss_kpt: 0.000565 acc_pose: 0.847212 loss: 0.000565 2022/09/23 15:37:30 - mmengine - INFO - Epoch(train) [197][200/293] lr: 5.000000e-05 eta: 0:52:18 time: 0.586906 data_time: 0.106577 memory: 14267 loss_kpt: 0.000563 acc_pose: 0.809517 loss: 0.000563 2022/09/23 15:37:59 - mmengine - INFO - Epoch(train) [197][250/293] lr: 5.000000e-05 eta: 0:51:37 time: 0.581266 data_time: 0.108588 memory: 14267 loss_kpt: 0.000549 acc_pose: 0.844825 loss: 0.000549 2022/09/23 15:38:24 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 15:38:54 - mmengine - INFO - Epoch(train) [198][50/293] lr: 5.000000e-05 eta: 0:50:19 time: 0.599614 data_time: 0.105529 memory: 14267 loss_kpt: 0.000573 acc_pose: 0.836935 loss: 0.000573 2022/09/23 15:39:23 - mmengine - INFO - Epoch(train) [198][100/293] lr: 5.000000e-05 eta: 0:49:38 time: 0.576945 data_time: 0.110851 memory: 14267 loss_kpt: 0.000565 acc_pose: 0.867736 loss: 0.000565 2022/09/23 15:39:52 - mmengine - INFO - Epoch(train) [198][150/293] lr: 5.000000e-05 eta: 0:48:57 time: 0.573297 data_time: 0.088898 memory: 14267 loss_kpt: 0.000557 acc_pose: 0.822724 loss: 0.000557 2022/09/23 15:40:21 - mmengine - INFO - Epoch(train) [198][200/293] lr: 5.000000e-05 eta: 0:48:16 time: 0.589291 data_time: 0.106046 memory: 14267 loss_kpt: 0.000564 acc_pose: 0.822398 loss: 0.000564 2022/09/23 15:40:50 - mmengine - INFO - Epoch(train) [198][250/293] lr: 5.000000e-05 eta: 0:47:36 time: 0.582024 data_time: 0.085474 memory: 14267 loss_kpt: 0.000554 acc_pose: 0.883090 loss: 0.000554 2022/09/23 15:41:07 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 15:41:15 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 15:41:45 - mmengine - INFO - Epoch(train) [199][50/293] lr: 5.000000e-05 eta: 0:46:18 time: 0.610766 data_time: 0.108977 memory: 14267 loss_kpt: 0.000564 acc_pose: 0.868429 loss: 0.000564 2022/09/23 15:42:14 - mmengine - INFO - Epoch(train) [199][100/293] lr: 5.000000e-05 eta: 0:45:38 time: 0.576963 data_time: 0.104201 memory: 14267 loss_kpt: 0.000564 acc_pose: 0.851162 loss: 0.000564 2022/09/23 15:42:44 - mmengine - INFO - Epoch(train) [199][150/293] lr: 5.000000e-05 eta: 0:44:57 time: 0.594390 data_time: 0.093943 memory: 14267 loss_kpt: 0.000558 acc_pose: 0.876552 loss: 0.000558 2022/09/23 15:43:13 - mmengine - INFO - Epoch(train) [199][200/293] lr: 5.000000e-05 eta: 0:44:16 time: 0.582388 data_time: 0.101539 memory: 14267 loss_kpt: 0.000573 acc_pose: 0.838486 loss: 0.000573 2022/09/23 15:43:44 - mmengine - INFO - Epoch(train) [199][250/293] lr: 5.000000e-05 eta: 0:43:36 time: 0.615063 data_time: 0.106273 memory: 14267 loss_kpt: 0.000553 acc_pose: 0.876586 loss: 0.000553 2022/09/23 15:44:09 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 15:44:39 - mmengine - INFO - Epoch(train) [200][50/293] lr: 5.000000e-05 eta: 0:42:19 time: 0.600772 data_time: 0.099474 memory: 14267 loss_kpt: 0.000561 acc_pose: 0.792762 loss: 0.000561 2022/09/23 15:45:09 - mmengine - INFO - Epoch(train) [200][100/293] lr: 5.000000e-05 eta: 0:41:38 time: 0.596602 data_time: 0.096543 memory: 14267 loss_kpt: 0.000559 acc_pose: 0.835749 loss: 0.000559 2022/09/23 15:45:37 - mmengine - INFO - Epoch(train) [200][150/293] lr: 5.000000e-05 eta: 0:40:58 time: 0.573078 data_time: 0.095975 memory: 14267 loss_kpt: 0.000552 acc_pose: 0.865260 loss: 0.000552 2022/09/23 15:46:07 - mmengine - INFO - Epoch(train) [200][200/293] lr: 5.000000e-05 eta: 0:40:17 time: 0.596789 data_time: 0.105327 memory: 14267 loss_kpt: 0.000554 acc_pose: 0.813839 loss: 0.000554 2022/09/23 15:46:37 - mmengine - INFO - Epoch(train) [200][250/293] lr: 5.000000e-05 eta: 0:39:37 time: 0.585759 data_time: 0.101868 memory: 14267 loss_kpt: 0.000554 acc_pose: 0.852005 loss: 0.000554 2022/09/23 15:47:01 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 15:47:01 - mmengine - INFO - Saving checkpoint at 200 epochs 2022/09/23 15:47:23 - mmengine - INFO - Epoch(val) [200][50/407] eta: 0:01:59 time: 0.335431 data_time: 0.168759 memory: 14267 2022/09/23 15:47:38 - mmengine - INFO - Epoch(val) [200][100/407] eta: 0:01:30 time: 0.294162 data_time: 0.132083 memory: 1464 2022/09/23 15:47:55 - mmengine - INFO - Epoch(val) [200][150/407] eta: 0:01:24 time: 0.327539 data_time: 0.159154 memory: 1464 2022/09/23 15:48:12 - mmengine - INFO - Epoch(val) [200][200/407] eta: 0:01:11 time: 0.344232 data_time: 0.174328 memory: 1464 2022/09/23 15:48:28 - mmengine - INFO - Epoch(val) [200][250/407] eta: 0:00:49 time: 0.316404 data_time: 0.149985 memory: 1464 2022/09/23 15:48:44 - mmengine - INFO - Epoch(val) [200][300/407] eta: 0:00:33 time: 0.317290 data_time: 0.154324 memory: 1464 2022/09/23 15:48:59 - mmengine - INFO - Epoch(val) [200][350/407] eta: 0:00:17 time: 0.313636 data_time: 0.161133 memory: 1464 2022/09/23 15:49:12 - mmengine - INFO - Epoch(val) [200][400/407] eta: 0:00:01 time: 0.248873 data_time: 0.110406 memory: 1464 2022/09/23 15:49:45 - mmengine - INFO - Evaluating CocoMetric... 2022/09/23 15:49:59 - mmengine - INFO - Epoch(val) [200][407/407] coco/AP: 0.730285 coco/AP .5: 0.899981 coco/AP .75: 0.797738 coco/AP (M): 0.686524 coco/AP (L): 0.805124 coco/AR: 0.781612 coco/AR .5: 0.936241 coco/AR .75: 0.841152 coco/AR (M): 0.733270 coco/AR (L): 0.851765 2022/09/23 15:50:30 - mmengine - INFO - Epoch(train) [201][50/293] lr: 5.000000e-06 eta: 0:38:20 time: 0.617381 data_time: 0.105580 memory: 14267 loss_kpt: 0.000552 acc_pose: 0.849702 loss: 0.000552 2022/09/23 15:50:59 - mmengine - INFO - Epoch(train) [201][100/293] lr: 5.000000e-06 eta: 0:37:40 time: 0.583734 data_time: 0.105266 memory: 14267 loss_kpt: 0.000576 acc_pose: 0.836704 loss: 0.000576 2022/09/23 15:51:28 - mmengine - INFO - Epoch(train) [201][150/293] lr: 5.000000e-06 eta: 0:36:59 time: 0.589064 data_time: 0.101373 memory: 14267 loss_kpt: 0.000550 acc_pose: 0.889951 loss: 0.000550 2022/09/23 15:51:57 - mmengine - INFO - Epoch(train) [201][200/293] lr: 5.000000e-06 eta: 0:36:19 time: 0.575160 data_time: 0.097699 memory: 14267 loss_kpt: 0.000561 acc_pose: 0.833990 loss: 0.000561 2022/09/23 15:52:27 - mmengine - INFO - Epoch(train) [201][250/293] lr: 5.000000e-06 eta: 0:35:38 time: 0.592606 data_time: 0.094053 memory: 14267 loss_kpt: 0.000553 acc_pose: 0.893397 loss: 0.000553 2022/09/23 15:52:51 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 15:53:22 - mmengine - INFO - Epoch(train) [202][50/293] lr: 5.000000e-06 eta: 0:34:22 time: 0.612857 data_time: 0.106430 memory: 14267 loss_kpt: 0.000543 acc_pose: 0.853091 loss: 0.000543 2022/09/23 15:53:51 - mmengine - INFO - Epoch(train) [202][100/293] lr: 5.000000e-06 eta: 0:33:42 time: 0.578049 data_time: 0.100913 memory: 14267 loss_kpt: 0.000557 acc_pose: 0.848164 loss: 0.000557 2022/09/23 15:53:55 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 15:54:20 - mmengine - INFO - Epoch(train) [202][150/293] lr: 5.000000e-06 eta: 0:33:02 time: 0.570470 data_time: 0.083208 memory: 14267 loss_kpt: 0.000554 acc_pose: 0.840587 loss: 0.000554 2022/09/23 15:54:48 - mmengine - INFO - Epoch(train) [202][200/293] lr: 5.000000e-06 eta: 0:32:21 time: 0.573994 data_time: 0.089546 memory: 14267 loss_kpt: 0.000549 acc_pose: 0.820848 loss: 0.000549 2022/09/23 15:55:18 - mmengine - INFO - Epoch(train) [202][250/293] lr: 5.000000e-06 eta: 0:31:41 time: 0.594061 data_time: 0.094412 memory: 14267 loss_kpt: 0.000549 acc_pose: 0.788544 loss: 0.000549 2022/09/23 15:55:42 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 15:56:13 - mmengine - INFO - Epoch(train) [203][50/293] lr: 5.000000e-06 eta: 0:30:25 time: 0.610569 data_time: 0.103050 memory: 14267 loss_kpt: 0.000553 acc_pose: 0.860631 loss: 0.000553 2022/09/23 15:56:42 - mmengine - INFO - Epoch(train) [203][100/293] lr: 5.000000e-06 eta: 0:29:45 time: 0.592849 data_time: 0.091833 memory: 14267 loss_kpt: 0.000549 acc_pose: 0.835672 loss: 0.000549 2022/09/23 15:57:11 - mmengine - INFO - Epoch(train) [203][150/293] lr: 5.000000e-06 eta: 0:29:05 time: 0.575679 data_time: 0.086081 memory: 14267 loss_kpt: 0.000553 acc_pose: 0.853040 loss: 0.000553 2022/09/23 15:57:40 - mmengine - INFO - Epoch(train) [203][200/293] lr: 5.000000e-06 eta: 0:28:25 time: 0.589563 data_time: 0.099422 memory: 14267 loss_kpt: 0.000552 acc_pose: 0.833455 loss: 0.000552 2022/09/23 15:58:10 - mmengine - INFO - Epoch(train) [203][250/293] lr: 5.000000e-06 eta: 0:27:45 time: 0.592875 data_time: 0.101390 memory: 14267 loss_kpt: 0.000546 acc_pose: 0.867710 loss: 0.000546 2022/09/23 15:58:36 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 15:59:05 - mmengine - INFO - Epoch(train) [204][50/293] lr: 5.000000e-06 eta: 0:26:29 time: 0.592003 data_time: 0.108060 memory: 14267 loss_kpt: 0.000543 acc_pose: 0.867350 loss: 0.000543 2022/09/23 15:59:35 - mmengine - INFO - Epoch(train) [204][100/293] lr: 5.000000e-06 eta: 0:25:49 time: 0.587705 data_time: 0.095260 memory: 14267 loss_kpt: 0.000546 acc_pose: 0.866977 loss: 0.000546 2022/09/23 16:00:04 - mmengine - INFO - Epoch(train) [204][150/293] lr: 5.000000e-06 eta: 0:25:09 time: 0.591512 data_time: 0.101145 memory: 14267 loss_kpt: 0.000564 acc_pose: 0.830839 loss: 0.000564 2022/09/23 16:00:34 - mmengine - INFO - Epoch(train) [204][200/293] lr: 5.000000e-06 eta: 0:24:29 time: 0.582829 data_time: 0.111977 memory: 14267 loss_kpt: 0.000562 acc_pose: 0.862682 loss: 0.000562 2022/09/23 16:01:03 - mmengine - INFO - Epoch(train) [204][250/293] lr: 5.000000e-06 eta: 0:23:49 time: 0.580986 data_time: 0.096532 memory: 14267 loss_kpt: 0.000556 acc_pose: 0.867828 loss: 0.000556 2022/09/23 16:01:27 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 16:01:58 - mmengine - INFO - Epoch(train) [205][50/293] lr: 5.000000e-06 eta: 0:22:34 time: 0.610343 data_time: 0.111657 memory: 14267 loss_kpt: 0.000554 acc_pose: 0.847266 loss: 0.000554 2022/09/23 16:02:26 - mmengine - INFO - Epoch(train) [205][100/293] lr: 5.000000e-06 eta: 0:21:54 time: 0.577687 data_time: 0.099776 memory: 14267 loss_kpt: 0.000562 acc_pose: 0.874078 loss: 0.000562 2022/09/23 16:02:56 - mmengine - INFO - Epoch(train) [205][150/293] lr: 5.000000e-06 eta: 0:21:14 time: 0.581937 data_time: 0.093445 memory: 14267 loss_kpt: 0.000553 acc_pose: 0.885028 loss: 0.000553 2022/09/23 16:03:24 - mmengine - INFO - Epoch(train) [205][200/293] lr: 5.000000e-06 eta: 0:20:34 time: 0.578282 data_time: 0.103670 memory: 14267 loss_kpt: 0.000559 acc_pose: 0.856450 loss: 0.000559 2022/09/23 16:03:41 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 16:03:53 - mmengine - INFO - Epoch(train) [205][250/293] lr: 5.000000e-06 eta: 0:19:54 time: 0.580380 data_time: 0.088645 memory: 14267 loss_kpt: 0.000541 acc_pose: 0.830734 loss: 0.000541 2022/09/23 16:04:18 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 16:04:48 - mmengine - INFO - Epoch(train) [206][50/293] lr: 5.000000e-06 eta: 0:18:40 time: 0.597167 data_time: 0.103014 memory: 14267 loss_kpt: 0.000550 acc_pose: 0.833965 loss: 0.000550 2022/09/23 16:05:18 - mmengine - INFO - Epoch(train) [206][100/293] lr: 5.000000e-06 eta: 0:18:00 time: 0.586345 data_time: 0.098091 memory: 14267 loss_kpt: 0.000551 acc_pose: 0.840140 loss: 0.000551 2022/09/23 16:05:46 - mmengine - INFO - Epoch(train) [206][150/293] lr: 5.000000e-06 eta: 0:17:20 time: 0.572183 data_time: 0.098243 memory: 14267 loss_kpt: 0.000553 acc_pose: 0.880048 loss: 0.000553 2022/09/23 16:06:16 - mmengine - INFO - Epoch(train) [206][200/293] lr: 5.000000e-06 eta: 0:16:40 time: 0.589929 data_time: 0.110607 memory: 14267 loss_kpt: 0.000546 acc_pose: 0.892824 loss: 0.000546 2022/09/23 16:06:45 - mmengine - INFO - Epoch(train) [206][250/293] lr: 5.000000e-06 eta: 0:16:00 time: 0.579383 data_time: 0.103767 memory: 14267 loss_kpt: 0.000552 acc_pose: 0.875306 loss: 0.000552 2022/09/23 16:07:10 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 16:07:39 - mmengine - INFO - Epoch(train) [207][50/293] lr: 5.000000e-06 eta: 0:14:46 time: 0.597119 data_time: 0.108628 memory: 14267 loss_kpt: 0.000541 acc_pose: 0.813024 loss: 0.000541 2022/09/23 16:08:08 - mmengine - INFO - Epoch(train) [207][100/293] lr: 5.000000e-06 eta: 0:14:06 time: 0.573445 data_time: 0.098366 memory: 14267 loss_kpt: 0.000558 acc_pose: 0.813445 loss: 0.000558 2022/09/23 16:08:37 - mmengine - INFO - Epoch(train) [207][150/293] lr: 5.000000e-06 eta: 0:13:27 time: 0.569889 data_time: 0.106064 memory: 14267 loss_kpt: 0.000548 acc_pose: 0.841574 loss: 0.000548 2022/09/23 16:09:06 - mmengine - INFO - Epoch(train) [207][200/293] lr: 5.000000e-06 eta: 0:12:47 time: 0.587816 data_time: 0.099673 memory: 14267 loss_kpt: 0.000549 acc_pose: 0.890392 loss: 0.000549 2022/09/23 16:09:35 - mmengine - INFO - Epoch(train) [207][250/293] lr: 5.000000e-06 eta: 0:12:07 time: 0.572158 data_time: 0.103439 memory: 14267 loss_kpt: 0.000562 acc_pose: 0.852607 loss: 0.000562 2022/09/23 16:09:59 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 16:10:29 - mmengine - INFO - Epoch(train) [208][50/293] lr: 5.000000e-06 eta: 0:10:53 time: 0.602010 data_time: 0.117662 memory: 14267 loss_kpt: 0.000548 acc_pose: 0.863146 loss: 0.000548 2022/09/23 16:10:59 - mmengine - INFO - Epoch(train) [208][100/293] lr: 5.000000e-06 eta: 0:10:14 time: 0.584247 data_time: 0.096035 memory: 14267 loss_kpt: 0.000564 acc_pose: 0.857455 loss: 0.000564 2022/09/23 16:11:27 - mmengine - INFO - Epoch(train) [208][150/293] lr: 5.000000e-06 eta: 0:09:34 time: 0.573625 data_time: 0.103920 memory: 14267 loss_kpt: 0.000547 acc_pose: 0.813533 loss: 0.000547 2022/09/23 16:11:56 - mmengine - INFO - Epoch(train) [208][200/293] lr: 5.000000e-06 eta: 0:08:55 time: 0.575850 data_time: 0.109031 memory: 14267 loss_kpt: 0.000550 acc_pose: 0.822660 loss: 0.000550 2022/09/23 16:12:25 - mmengine - INFO - Epoch(train) [208][250/293] lr: 5.000000e-06 eta: 0:08:15 time: 0.570261 data_time: 0.102292 memory: 14267 loss_kpt: 0.000548 acc_pose: 0.844104 loss: 0.000548 2022/09/23 16:12:49 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 16:13:19 - mmengine - INFO - Epoch(train) [209][50/293] lr: 5.000000e-06 eta: 0:07:02 time: 0.607200 data_time: 0.118294 memory: 14267 loss_kpt: 0.000553 acc_pose: 0.877490 loss: 0.000553 2022/09/23 16:13:23 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 16:13:49 - mmengine - INFO - Epoch(train) [209][100/293] lr: 5.000000e-06 eta: 0:06:22 time: 0.581716 data_time: 0.110748 memory: 14267 loss_kpt: 0.000553 acc_pose: 0.872014 loss: 0.000553 2022/09/23 16:14:17 - mmengine - INFO - Epoch(train) [209][150/293] lr: 5.000000e-06 eta: 0:05:43 time: 0.574173 data_time: 0.106378 memory: 14267 loss_kpt: 0.000562 acc_pose: 0.858742 loss: 0.000562 2022/09/23 16:14:46 - mmengine - INFO - Epoch(train) [209][200/293] lr: 5.000000e-06 eta: 0:05:03 time: 0.581448 data_time: 0.095011 memory: 14267 loss_kpt: 0.000545 acc_pose: 0.891151 loss: 0.000545 2022/09/23 16:15:16 - mmengine - INFO - Epoch(train) [209][250/293] lr: 5.000000e-06 eta: 0:04:24 time: 0.593698 data_time: 0.114474 memory: 14267 loss_kpt: 0.000560 acc_pose: 0.853963 loss: 0.000560 2022/09/23 16:15:41 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 16:16:10 - mmengine - INFO - Epoch(train) [210][50/293] lr: 5.000000e-06 eta: 0:03:10 time: 0.590231 data_time: 0.092910 memory: 14267 loss_kpt: 0.000551 acc_pose: 0.815773 loss: 0.000551 2022/09/23 16:16:39 - mmengine - INFO - Epoch(train) [210][100/293] lr: 5.000000e-06 eta: 0:02:31 time: 0.579090 data_time: 0.087005 memory: 14267 loss_kpt: 0.000552 acc_pose: 0.852415 loss: 0.000552 2022/09/23 16:17:08 - mmengine - INFO - Epoch(train) [210][150/293] lr: 5.000000e-06 eta: 0:01:52 time: 0.581525 data_time: 0.090130 memory: 14267 loss_kpt: 0.000546 acc_pose: 0.859479 loss: 0.000546 2022/09/23 16:17:38 - mmengine - INFO - Epoch(train) [210][200/293] lr: 5.000000e-06 eta: 0:01:13 time: 0.591831 data_time: 0.117956 memory: 14267 loss_kpt: 0.000560 acc_pose: 0.844679 loss: 0.000560 2022/09/23 16:18:06 - mmengine - INFO - Epoch(train) [210][250/293] lr: 5.000000e-06 eta: 0:00:33 time: 0.575798 data_time: 0.108253 memory: 14267 loss_kpt: 0.000553 acc_pose: 0.862658 loss: 0.000553 2022/09/23 16:18:31 - mmengine - INFO - Exp name: td-hm_res50_8xb64-210e_coco-384x288_20220922_232753 2022/09/23 16:18:31 - mmengine - INFO - Saving checkpoint at 210 epochs 2022/09/23 16:18:52 - mmengine - INFO - Epoch(val) [210][50/407] eta: 0:01:54 time: 0.319335 data_time: 0.164626 memory: 14267 2022/09/23 16:19:07 - mmengine - INFO - Epoch(val) [210][100/407] eta: 0:01:32 time: 0.302450 data_time: 0.127953 memory: 1464 2022/09/23 16:19:23 - mmengine - INFO - Epoch(val) [210][150/407] eta: 0:01:21 time: 0.315537 data_time: 0.141888 memory: 1464 2022/09/23 16:19:40 - mmengine - INFO - Epoch(val) [210][200/407] eta: 0:01:08 time: 0.328516 data_time: 0.153522 memory: 1464 2022/09/23 16:19:55 - mmengine - INFO - Epoch(val) [210][250/407] eta: 0:00:47 time: 0.303305 data_time: 0.140977 memory: 1464 2022/09/23 16:20:11 - mmengine - INFO - Epoch(val) [210][300/407] eta: 0:00:34 time: 0.321475 data_time: 0.158266 memory: 1464 2022/09/23 16:20:27 - mmengine - INFO - Epoch(val) [210][350/407] eta: 0:00:18 time: 0.317747 data_time: 0.164558 memory: 1464 2022/09/23 16:20:39 - mmengine - INFO - Epoch(val) [210][400/407] eta: 0:00:01 time: 0.249163 data_time: 0.119823 memory: 1464 2022/09/23 16:21:13 - mmengine - INFO - Evaluating CocoMetric... 2022/09/23 16:21:27 - mmengine - INFO - Epoch(val) [210][407/407] coco/AP: 0.730729 coco/AP .5: 0.900855 coco/AP .75: 0.800114 coco/AP (M): 0.686632 coco/AP (L): 0.805508 coco/AR: 0.782163 coco/AR .5: 0.937815 coco/AR .75: 0.843514 coco/AR (M): 0.733543 coco/AR (L): 0.852062