2023/05/24 07:49:50 - mmengine - INFO - ------------------------------------------------------------ System environment: sys.platform: linux Python: 3.10.0 (default, Mar 3 2022, 09:58:08) [GCC 7.5.0] CUDA available: True numpy_random_seed: 1295130573 GPU 0: NVIDIA A10 CUDA_HOME: /usr/local/cuda NVCC: Cuda compilation tools, release 11.7, V11.7.99 GCC: gcc (Ubuntu 9.4.0-1ubuntu1~20.04.1) 9.4.0 PyTorch: 2.0.0+cu117 PyTorch compiling details: PyTorch built with: - GCC 9.3 - C++ Version: 201703 - Intel(R) oneAPI Math Kernel Library Version 2022.2-Product Build 20220804 for Intel(R) 64 architecture applications - Intel(R) MKL-DNN v2.7.3 (Git Hash 6dbeffbae1f23cbbeae17adb7b5b13f1f37c080e) - OpenMP 201511 (a.k.a. OpenMP 4.5) - LAPACK is enabled (usually provided by MKL) - NNPACK is enabled - CPU capability usage: AVX2 - CUDA Runtime 11.7 - NVCC architecture flags: -gencode;arch=compute_37,code=sm_37;-gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-gencode;arch=compute_80,code=sm_80;-gencode;arch=compute_86,code=sm_86 - CuDNN 8.5 - Magma 2.6.1 - Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.7, CUDNN_VERSION=8.5.0, CXX_COMPILER=/opt/rh/devtoolset-9/root/usr/bin/c++, CXX_FLAGS= -D_GLIBCXX_USE_CXX11_ABI=0 -fabi-version=11 -Wno-deprecated -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -DNDEBUG -DUSE_KINETO -DLIBKINETO_NOROCTRACER -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DSYMBOLICATE_MOBILE_DEBUG_HANDLE -O2 -fPIC -Wall -Wextra -Werror=return-type -Werror=non-virtual-dtor -Werror=bool-operation -Wnarrowing -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wunused-local-typedefs -Wno-unused-parameter -Wno-unused-function -Wno-unused-result -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_DISABLE_GPU_ASSERTS=ON, TORCH_VERSION=2.0.0, USE_CUDA=ON, USE_CUDNN=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=1, USE_NNPACK=ON, USE_OPENMP=ON, USE_ROCM=OFF, TorchVision: 0.15.1+cu117 OpenCV: 4.7.0 MMEngine: 0.7.3 Runtime environment: cudnn_benchmark: False mp_cfg: {'mp_start_method': 'fork', 'opencv_num_threads': 0} dist_cfg: {'backend': 'nccl'} seed: None Distributed launcher: none Distributed training: False GPU number: 1 ------------------------------------------------------------ 2023/05/24 07:49:50 - mmengine - INFO - Config: default_scope = 'mmpose' default_hooks = dict( timer=dict(type='IterTimerHook', _scope_='mmpose'), logger=dict(type='LoggerHook', interval=50, _scope_='mmpose'), param_scheduler=dict(type='ParamSchedulerHook', _scope_='mmpose'), checkpoint=dict( type='CheckpointHook', interval=1, _scope_='mmpose', save_best='NME', rule='less'), sampler_seed=dict(type='DistSamplerSeedHook', _scope_='mmpose'), visualization=dict( type='PoseVisualizationHook', enable=False, _scope_='mmpose')) custom_hooks = [dict(type='SyncBuffersHook', _scope_='mmpose')] 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', _scope_='mmpose')] visualizer = dict( type='PoseLocalVisualizer', vis_backends=[dict(type='LocalVisBackend')], name='visualizer', _scope_='mmpose') log_processor = dict( type='LogProcessor', window_size=50, by_epoch=True, num_digits=6, _scope_='mmpose') log_level = 'INFO' load_from = None resume = False backend_args = dict(backend='local') train_cfg = dict(by_epoch=True, max_epochs=160, val_interval=1) val_cfg = dict() test_cfg = dict() custom_imports = dict(imports=['codecs2', 'models']) optim_wrapper = dict( optimizer=dict(type='AdamW', lr=0.002, weight_decay=0.0005), type='AmpOptimWrapper', loss_scale='dynamic') param_scheduler = [ dict( type='LinearLR', begin=0, end=500, start_factor=0.001, by_epoch=False), dict( type='MultiStepLR', begin=0, end=160, milestones=[80, 120], gamma=0.1, by_epoch=True) ] auto_scale_lr = dict(base_batch_size=512) codec = dict( type='SKPSHeatmap', input_size=(256, 256), heatmap_size=(64, 64), sigma=2) model = dict( type='TopdownPoseEstimator', data_preprocessor=dict( type='PoseDataPreprocessor', mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], bgr_to_rgb=True), backbone=dict( type='HRNet', in_channels=3, extra=dict( stage1=dict( num_modules=1, num_branches=1, block='BOTTLENECK', num_blocks=(4, ), num_channels=(64, )), stage2=dict( num_modules=1, num_branches=2, block='BASIC', num_blocks=(4, 4), num_channels=(18, 36)), stage3=dict( num_modules=4, num_branches=3, block='BASIC', num_blocks=(4, 4, 4), num_channels=(18, 36, 72)), stage4=dict( num_modules=3, num_branches=4, block='BASIC', num_blocks=(4, 4, 4, 4), num_channels=(18, 36, 72, 144), multiscale_output=True), upsample=dict(mode='bilinear', align_corners=False)), init_cfg=dict( type='Pretrained', checkpoint='open-mmlab://msra/hrnetv2_w18')), neck=dict(type='FeatureMapProcessor', concat=True), head=dict( type='SKPSHead', in_channels=270, out_channels=29, conv_out_channels=(270, ), conv_kernel_sizes=(1, ), heatmap_loss=dict(type='AdaptiveWingLoss', use_target_weight=True), offside_loss=dict(type='AdaptiveWingLoss', use_target_weight=True), decoder=dict( type='SKPSHeatmap', input_size=(256, 256), heatmap_size=(64, 64), sigma=2)), test_cfg=dict(flip_test=True, flip_mode='heatmap', shift_heatmap=True)) dataset_type = 'COFWDataset' data_mode = 'topdown' data_root = 'data/cofw/' train_pipeline = [ dict(type='LoadImage'), dict(type='GetBBoxCenterScale', padding=1), dict(type='RandomFlip', direction='horizontal'), dict( type='Albumentation', transforms=[ dict(type='RandomBrightnessContrast', p=0.5), dict(type='HueSaturationValue', p=0.5), dict(type='GaussianBlur', p=0.5), dict(type='GaussNoise', p=0.1), dict( type='CoarseDropout', max_holes=8, max_height=0.2, max_width=0.2, min_holes=1, min_height=0.1, min_width=0.1, p=0.5) ]), dict( type='RandomBBoxTransform', shift_prob=0.0, rotate_factor=45, scale_factor=(0.75, 1.25), scale_prob=0), dict(type='TopdownAffine', input_size=(256, 256)), dict( type='GenerateTarget', encoder=dict( type='SKPSHeatmap', input_size=(256, 256), heatmap_size=(64, 64), sigma=2)), dict(type='PackPoseInputs') ] val_pipeline = [ dict(type='LoadImage'), dict(type='GetBBoxCenterScale', padding=1), dict(type='TopdownAffine', input_size=(256, 256)), dict(type='PackPoseInputs') ] train_dataloader = dict( batch_size=16, num_workers=4, persistent_workers=True, sampler=dict(type='DefaultSampler', shuffle=True), dataset=dict( type='COFWDataset', data_root='data/cofw/', data_mode='topdown', ann_file='annotations/cofw_train.json', data_prefix=dict(img='images/'), pipeline=[ dict(type='LoadImage'), dict(type='GetBBoxCenterScale', padding=1), dict(type='RandomFlip', direction='horizontal'), dict( type='Albumentation', transforms=[ dict(type='RandomBrightnessContrast', p=0.5), dict(type='HueSaturationValue', p=0.5), dict(type='GaussianBlur', p=0.5), dict(type='GaussNoise', p=0.1), dict( type='CoarseDropout', max_holes=8, max_height=0.2, max_width=0.2, min_holes=1, min_height=0.1, min_width=0.1, p=0.5) ]), dict( type='RandomBBoxTransform', shift_prob=0.0, rotate_factor=45, scale_factor=(0.75, 1.25), scale_prob=0), dict(type='TopdownAffine', input_size=(256, 256)), dict( type='GenerateTarget', encoder=dict( type='SKPSHeatmap', input_size=(256, 256), heatmap_size=(64, 64), sigma=2)), dict(type='PackPoseInputs') ])) val_dataloader = dict( batch_size=32, num_workers=4, persistent_workers=True, drop_last=False, sampler=dict(type='DefaultSampler', shuffle=False, round_up=False), dataset=dict( type='COFWDataset', data_root='data/cofw/', data_mode='topdown', ann_file='annotations/cofw_test.json', data_prefix=dict(img='images/'), test_mode=True, pipeline=[ dict(type='LoadImage'), dict(type='GetBBoxCenterScale', padding=1), dict(type='TopdownAffine', input_size=(256, 256)), dict(type='PackPoseInputs') ])) test_dataloader = dict( batch_size=32, num_workers=4, persistent_workers=True, drop_last=False, sampler=dict(type='DefaultSampler', shuffle=False, round_up=False), dataset=dict( type='COFWDataset', data_root='data/cofw/', data_mode='topdown', ann_file='annotations/cofw_test.json', data_prefix=dict(img='images/'), test_mode=True, pipeline=[ dict(type='LoadImage'), dict(type='GetBBoxCenterScale', padding=1), dict(type='TopdownAffine', input_size=(256, 256)), dict(type='PackPoseInputs') ])) val_evaluator = dict(type='NME', norm_mode='keypoint_distance') test_evaluator = dict(type='NME', norm_mode='keypoint_distance') launcher = 'none' work_dir = './work_dirs/td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256' 2023/05/24 07:49:52 - mmengine - INFO - Distributed training is not used, all SyncBatchNorm (SyncBN) layers in the model will be automatically reverted to BatchNormXd layers if they are used. 2023/05/24 07:49:52 - mmengine - INFO - Hooks will be executed in the following order: before_run: (VERY_HIGH ) RuntimeInfoHook (BELOW_NORMAL) LoggerHook -------------------- before_train: (VERY_HIGH ) RuntimeInfoHook (NORMAL ) IterTimerHook (VERY_LOW ) CheckpointHook -------------------- before_train_epoch: (VERY_HIGH ) RuntimeInfoHook (NORMAL ) IterTimerHook (NORMAL ) DistSamplerSeedHook -------------------- before_train_iter: (VERY_HIGH ) RuntimeInfoHook (NORMAL ) IterTimerHook -------------------- after_train_iter: (VERY_HIGH ) RuntimeInfoHook (NORMAL ) IterTimerHook (BELOW_NORMAL) LoggerHook (LOW ) ParamSchedulerHook (VERY_LOW ) CheckpointHook -------------------- after_train_epoch: (NORMAL ) IterTimerHook (NORMAL ) SyncBuffersHook (LOW ) ParamSchedulerHook (VERY_LOW ) CheckpointHook -------------------- before_val_epoch: (NORMAL ) IterTimerHook (NORMAL ) SyncBuffersHook -------------------- before_val_iter: (NORMAL ) IterTimerHook -------------------- after_val_iter: (NORMAL ) IterTimerHook (NORMAL ) PoseVisualizationHook (BELOW_NORMAL) LoggerHook -------------------- after_val_epoch: (VERY_HIGH ) RuntimeInfoHook (NORMAL ) IterTimerHook (BELOW_NORMAL) LoggerHook (LOW ) ParamSchedulerHook (VERY_LOW ) CheckpointHook -------------------- after_train: (VERY_LOW ) CheckpointHook -------------------- before_test_epoch: (NORMAL ) IterTimerHook -------------------- before_test_iter: (NORMAL ) IterTimerHook -------------------- after_test_iter: (NORMAL ) IterTimerHook (NORMAL ) PoseVisualizationHook (BELOW_NORMAL) LoggerHook -------------------- after_test_epoch: (VERY_HIGH ) RuntimeInfoHook (NORMAL ) IterTimerHook (BELOW_NORMAL) LoggerHook -------------------- after_run: (BELOW_NORMAL) LoggerHook -------------------- 2023/05/24 07:49:53 - mmengine - WARNING - The prefix is not set in metric class NME. 2023/05/24 07:49:53 - mmengine - INFO - load model from: open-mmlab://msra/hrnetv2_w18 2023/05/24 07:49:53 - mmengine - INFO - Loads checkpoint by openmmlab backend from path: open-mmlab://msra/hrnetv2_w18 2023/05/24 07:49:53 - mmengine - WARNING - The model and loaded state dict do not match exactly unexpected key in source state_dict: incre_modules.0.0.conv1.weight, incre_modules.0.0.bn1.weight, incre_modules.0.0.bn1.bias, incre_modules.0.0.bn1.running_mean, incre_modules.0.0.bn1.running_var, incre_modules.0.0.bn1.num_batches_tracked, incre_modules.0.0.conv2.weight, incre_modules.0.0.bn2.weight, incre_modules.0.0.bn2.bias, incre_modules.0.0.bn2.running_mean, incre_modules.0.0.bn2.running_var, incre_modules.0.0.bn2.num_batches_tracked, incre_modules.0.0.conv3.weight, incre_modules.0.0.bn3.weight, incre_modules.0.0.bn3.bias, incre_modules.0.0.bn3.running_mean, incre_modules.0.0.bn3.running_var, incre_modules.0.0.bn3.num_batches_tracked, incre_modules.0.0.downsample.0.weight, incre_modules.0.0.downsample.1.weight, incre_modules.0.0.downsample.1.bias, incre_modules.0.0.downsample.1.running_mean, incre_modules.0.0.downsample.1.running_var, incre_modules.0.0.downsample.1.num_batches_tracked, incre_modules.1.0.conv1.weight, incre_modules.1.0.bn1.weight, incre_modules.1.0.bn1.bias, incre_modules.1.0.bn1.running_mean, incre_modules.1.0.bn1.running_var, incre_modules.1.0.bn1.num_batches_tracked, incre_modules.1.0.conv2.weight, incre_modules.1.0.bn2.weight, incre_modules.1.0.bn2.bias, incre_modules.1.0.bn2.running_mean, incre_modules.1.0.bn2.running_var, incre_modules.1.0.bn2.num_batches_tracked, incre_modules.1.0.conv3.weight, incre_modules.1.0.bn3.weight, incre_modules.1.0.bn3.bias, incre_modules.1.0.bn3.running_mean, incre_modules.1.0.bn3.running_var, incre_modules.1.0.bn3.num_batches_tracked, incre_modules.1.0.downsample.0.weight, incre_modules.1.0.downsample.1.weight, incre_modules.1.0.downsample.1.bias, incre_modules.1.0.downsample.1.running_mean, incre_modules.1.0.downsample.1.running_var, incre_modules.1.0.downsample.1.num_batches_tracked, incre_modules.2.0.conv1.weight, incre_modules.2.0.bn1.weight, incre_modules.2.0.bn1.bias, incre_modules.2.0.bn1.running_mean, incre_modules.2.0.bn1.running_var, incre_modules.2.0.bn1.num_batches_tracked, incre_modules.2.0.conv2.weight, incre_modules.2.0.bn2.weight, incre_modules.2.0.bn2.bias, incre_modules.2.0.bn2.running_mean, incre_modules.2.0.bn2.running_var, incre_modules.2.0.bn2.num_batches_tracked, incre_modules.2.0.conv3.weight, incre_modules.2.0.bn3.weight, incre_modules.2.0.bn3.bias, incre_modules.2.0.bn3.running_mean, incre_modules.2.0.bn3.running_var, incre_modules.2.0.bn3.num_batches_tracked, incre_modules.2.0.downsample.0.weight, incre_modules.2.0.downsample.1.weight, incre_modules.2.0.downsample.1.bias, incre_modules.2.0.downsample.1.running_mean, incre_modules.2.0.downsample.1.running_var, incre_modules.2.0.downsample.1.num_batches_tracked, incre_modules.3.0.conv1.weight, incre_modules.3.0.bn1.weight, incre_modules.3.0.bn1.bias, incre_modules.3.0.bn1.running_mean, incre_modules.3.0.bn1.running_var, incre_modules.3.0.bn1.num_batches_tracked, incre_modules.3.0.conv2.weight, incre_modules.3.0.bn2.weight, incre_modules.3.0.bn2.bias, incre_modules.3.0.bn2.running_mean, incre_modules.3.0.bn2.running_var, incre_modules.3.0.bn2.num_batches_tracked, incre_modules.3.0.conv3.weight, incre_modules.3.0.bn3.weight, incre_modules.3.0.bn3.bias, incre_modules.3.0.bn3.running_mean, incre_modules.3.0.bn3.running_var, incre_modules.3.0.bn3.num_batches_tracked, incre_modules.3.0.downsample.0.weight, incre_modules.3.0.downsample.1.weight, incre_modules.3.0.downsample.1.bias, incre_modules.3.0.downsample.1.running_mean, incre_modules.3.0.downsample.1.running_var, incre_modules.3.0.downsample.1.num_batches_tracked, downsamp_modules.0.0.weight, downsamp_modules.0.0.bias, downsamp_modules.0.1.weight, downsamp_modules.0.1.bias, downsamp_modules.0.1.running_mean, downsamp_modules.0.1.running_var, downsamp_modules.0.1.num_batches_tracked, downsamp_modules.1.0.weight, downsamp_modules.1.0.bias, downsamp_modules.1.1.weight, downsamp_modules.1.1.bias, downsamp_modules.1.1.running_mean, downsamp_modules.1.1.running_var, downsamp_modules.1.1.num_batches_tracked, downsamp_modules.2.0.weight, downsamp_modules.2.0.bias, downsamp_modules.2.1.weight, downsamp_modules.2.1.bias, downsamp_modules.2.1.running_mean, downsamp_modules.2.1.running_var, downsamp_modules.2.1.num_batches_tracked, final_layer.0.weight, final_layer.0.bias, final_layer.1.weight, final_layer.1.bias, final_layer.1.running_mean, final_layer.1.running_var, final_layer.1.num_batches_tracked, classifier.weight, classifier.bias Name of parameter - Initialization information backbone.conv1.weight - torch.Size([64, 3, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.bn1.weight - torch.Size([64]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.bn1.bias - torch.Size([64]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.bn2.weight - torch.Size([64]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.bn2.bias - torch.Size([64]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.layer1.0.conv1.weight - torch.Size([64, 64, 1, 1]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.layer1.0.bn1.weight - torch.Size([64]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.layer1.0.bn1.bias - torch.Size([64]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.layer1.0.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.layer1.0.bn2.weight - torch.Size([64]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.layer1.0.bn2.bias - torch.Size([64]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.layer1.0.conv3.weight - torch.Size([256, 64, 1, 1]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.layer1.0.bn3.weight - torch.Size([256]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.layer1.0.bn3.bias - torch.Size([256]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.layer1.0.downsample.0.weight - torch.Size([256, 64, 1, 1]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.layer1.0.downsample.1.weight - torch.Size([256]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.layer1.0.downsample.1.bias - torch.Size([256]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.layer1.1.conv1.weight - torch.Size([64, 256, 1, 1]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.layer1.1.bn1.weight - torch.Size([64]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.layer1.1.bn1.bias - torch.Size([64]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.layer1.1.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.layer1.1.bn2.weight - torch.Size([64]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.layer1.1.bn2.bias - torch.Size([64]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.layer1.1.conv3.weight - torch.Size([256, 64, 1, 1]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.layer1.1.bn3.weight - torch.Size([256]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.layer1.1.bn3.bias - torch.Size([256]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.layer1.2.conv1.weight - torch.Size([64, 256, 1, 1]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.layer1.2.bn1.weight - torch.Size([64]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.layer1.2.bn1.bias - torch.Size([64]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.layer1.2.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.layer1.2.bn2.weight - torch.Size([64]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.layer1.2.bn2.bias - torch.Size([64]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.layer1.2.conv3.weight - torch.Size([256, 64, 1, 1]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.layer1.2.bn3.weight - torch.Size([256]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.layer1.2.bn3.bias - torch.Size([256]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.layer1.3.conv1.weight - torch.Size([64, 256, 1, 1]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.layer1.3.bn1.weight - torch.Size([64]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.layer1.3.bn1.bias - torch.Size([64]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.layer1.3.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.layer1.3.bn2.weight - torch.Size([64]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.layer1.3.bn2.bias - torch.Size([64]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.layer1.3.conv3.weight - torch.Size([256, 64, 1, 1]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.layer1.3.bn3.weight - torch.Size([256]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.layer1.3.bn3.bias - torch.Size([256]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.transition1.0.0.weight - torch.Size([18, 256, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.transition1.0.1.weight - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.transition1.0.1.bias - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.transition1.1.0.0.weight - torch.Size([36, 256, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.transition1.1.0.1.weight - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.transition1.1.0.1.bias - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage2.0.branches.0.0.conv1.weight - torch.Size([18, 18, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage2.0.branches.0.0.bn1.weight - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage2.0.branches.0.0.bn1.bias - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage2.0.branches.0.0.conv2.weight - torch.Size([18, 18, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage2.0.branches.0.0.bn2.weight - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage2.0.branches.0.0.bn2.bias - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage2.0.branches.0.1.conv1.weight - torch.Size([18, 18, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage2.0.branches.0.1.bn1.weight - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage2.0.branches.0.1.bn1.bias - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage2.0.branches.0.1.conv2.weight - torch.Size([18, 18, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage2.0.branches.0.1.bn2.weight - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage2.0.branches.0.1.bn2.bias - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage2.0.branches.0.2.conv1.weight - torch.Size([18, 18, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage2.0.branches.0.2.bn1.weight - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage2.0.branches.0.2.bn1.bias - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage2.0.branches.0.2.conv2.weight - torch.Size([18, 18, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage2.0.branches.0.2.bn2.weight - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage2.0.branches.0.2.bn2.bias - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage2.0.branches.0.3.conv1.weight - torch.Size([18, 18, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage2.0.branches.0.3.bn1.weight - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage2.0.branches.0.3.bn1.bias - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage2.0.branches.0.3.conv2.weight - torch.Size([18, 18, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage2.0.branches.0.3.bn2.weight - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage2.0.branches.0.3.bn2.bias - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage2.0.branches.1.0.conv1.weight - torch.Size([36, 36, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage2.0.branches.1.0.bn1.weight - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage2.0.branches.1.0.bn1.bias - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage2.0.branches.1.0.conv2.weight - torch.Size([36, 36, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage2.0.branches.1.0.bn2.weight - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage2.0.branches.1.0.bn2.bias - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage2.0.branches.1.1.conv1.weight - torch.Size([36, 36, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage2.0.branches.1.1.bn1.weight - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage2.0.branches.1.1.bn1.bias - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage2.0.branches.1.1.conv2.weight - torch.Size([36, 36, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage2.0.branches.1.1.bn2.weight - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage2.0.branches.1.1.bn2.bias - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage2.0.branches.1.2.conv1.weight - torch.Size([36, 36, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage2.0.branches.1.2.bn1.weight - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage2.0.branches.1.2.bn1.bias - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage2.0.branches.1.2.conv2.weight - torch.Size([36, 36, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage2.0.branches.1.2.bn2.weight - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage2.0.branches.1.2.bn2.bias - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage2.0.branches.1.3.conv1.weight - torch.Size([36, 36, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage2.0.branches.1.3.bn1.weight - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage2.0.branches.1.3.bn1.bias - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage2.0.branches.1.3.conv2.weight - torch.Size([36, 36, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage2.0.branches.1.3.bn2.weight - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage2.0.branches.1.3.bn2.bias - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage2.0.fuse_layers.0.1.0.weight - torch.Size([18, 36, 1, 1]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage2.0.fuse_layers.0.1.1.weight - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage2.0.fuse_layers.0.1.1.bias - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage2.0.fuse_layers.1.0.0.0.weight - torch.Size([36, 18, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage2.0.fuse_layers.1.0.0.1.weight - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage2.0.fuse_layers.1.0.0.1.bias - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.transition2.2.0.0.weight - torch.Size([72, 36, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.transition2.2.0.1.weight - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.transition2.2.0.1.bias - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.0.branches.0.0.conv1.weight - torch.Size([18, 18, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.0.branches.0.0.bn1.weight - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.0.branches.0.0.bn1.bias - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.0.branches.0.0.conv2.weight - torch.Size([18, 18, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.0.branches.0.0.bn2.weight - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.0.branches.0.0.bn2.bias - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.0.branches.0.1.conv1.weight - torch.Size([18, 18, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.0.branches.0.1.bn1.weight - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.0.branches.0.1.bn1.bias - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.0.branches.0.1.conv2.weight - torch.Size([18, 18, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.0.branches.0.1.bn2.weight - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.0.branches.0.1.bn2.bias - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.0.branches.0.2.conv1.weight - torch.Size([18, 18, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.0.branches.0.2.bn1.weight - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.0.branches.0.2.bn1.bias - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.0.branches.0.2.conv2.weight - torch.Size([18, 18, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.0.branches.0.2.bn2.weight - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.0.branches.0.2.bn2.bias - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.0.branches.0.3.conv1.weight - torch.Size([18, 18, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.0.branches.0.3.bn1.weight - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.0.branches.0.3.bn1.bias - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.0.branches.0.3.conv2.weight - torch.Size([18, 18, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.0.branches.0.3.bn2.weight - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.0.branches.0.3.bn2.bias - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.0.branches.1.0.conv1.weight - torch.Size([36, 36, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.0.branches.1.0.bn1.weight - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.0.branches.1.0.bn1.bias - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.0.branches.1.0.conv2.weight - torch.Size([36, 36, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.0.branches.1.0.bn2.weight - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.0.branches.1.0.bn2.bias - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.0.branches.1.1.conv1.weight - torch.Size([36, 36, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.0.branches.1.1.bn1.weight - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.0.branches.1.1.bn1.bias - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.0.branches.1.1.conv2.weight - torch.Size([36, 36, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.0.branches.1.1.bn2.weight - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.0.branches.1.1.bn2.bias - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.0.branches.1.2.conv1.weight - torch.Size([36, 36, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.0.branches.1.2.bn1.weight - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.0.branches.1.2.bn1.bias - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.0.branches.1.2.conv2.weight - torch.Size([36, 36, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.0.branches.1.2.bn2.weight - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.0.branches.1.2.bn2.bias - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.0.branches.1.3.conv1.weight - torch.Size([36, 36, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.0.branches.1.3.bn1.weight - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.0.branches.1.3.bn1.bias - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.0.branches.1.3.conv2.weight - torch.Size([36, 36, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.0.branches.1.3.bn2.weight - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.0.branches.1.3.bn2.bias - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.0.branches.2.0.conv1.weight - torch.Size([72, 72, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.0.branches.2.0.bn1.weight - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.0.branches.2.0.bn1.bias - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.0.branches.2.0.conv2.weight - torch.Size([72, 72, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.0.branches.2.0.bn2.weight - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.0.branches.2.0.bn2.bias - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.0.branches.2.1.conv1.weight - torch.Size([72, 72, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.0.branches.2.1.bn1.weight - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.0.branches.2.1.bn1.bias - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.0.branches.2.1.conv2.weight - torch.Size([72, 72, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.0.branches.2.1.bn2.weight - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.0.branches.2.1.bn2.bias - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.0.branches.2.2.conv1.weight - torch.Size([72, 72, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.0.branches.2.2.bn1.weight - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.0.branches.2.2.bn1.bias - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.0.branches.2.2.conv2.weight - torch.Size([72, 72, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.0.branches.2.2.bn2.weight - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.0.branches.2.2.bn2.bias - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.0.branches.2.3.conv1.weight - torch.Size([72, 72, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.0.branches.2.3.bn1.weight - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.0.branches.2.3.bn1.bias - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.0.branches.2.3.conv2.weight - torch.Size([72, 72, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.0.branches.2.3.bn2.weight - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.0.branches.2.3.bn2.bias - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.0.fuse_layers.0.1.0.weight - torch.Size([18, 36, 1, 1]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.0.fuse_layers.0.1.1.weight - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.0.fuse_layers.0.1.1.bias - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.0.fuse_layers.0.2.0.weight - torch.Size([18, 72, 1, 1]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.0.fuse_layers.0.2.1.weight - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.0.fuse_layers.0.2.1.bias - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.0.fuse_layers.1.0.0.0.weight - torch.Size([36, 18, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.0.fuse_layers.1.0.0.1.weight - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.0.fuse_layers.1.0.0.1.bias - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.0.fuse_layers.1.2.0.weight - torch.Size([36, 72, 1, 1]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.0.fuse_layers.1.2.1.weight - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.0.fuse_layers.1.2.1.bias - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.0.fuse_layers.2.0.0.0.weight - torch.Size([18, 18, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.0.fuse_layers.2.0.0.1.weight - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.0.fuse_layers.2.0.0.1.bias - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.0.fuse_layers.2.0.1.0.weight - torch.Size([72, 18, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.0.fuse_layers.2.0.1.1.weight - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.0.fuse_layers.2.0.1.1.bias - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.0.fuse_layers.2.1.0.0.weight - torch.Size([72, 36, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.0.fuse_layers.2.1.0.1.weight - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.0.fuse_layers.2.1.0.1.bias - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.1.branches.0.0.conv1.weight - torch.Size([18, 18, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.1.branches.0.0.bn1.weight - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.1.branches.0.0.bn1.bias - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.1.branches.0.0.conv2.weight - torch.Size([18, 18, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.1.branches.0.0.bn2.weight - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.1.branches.0.0.bn2.bias - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.1.branches.0.1.conv1.weight - torch.Size([18, 18, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.1.branches.0.1.bn1.weight - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.1.branches.0.1.bn1.bias - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.1.branches.0.1.conv2.weight - torch.Size([18, 18, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.1.branches.0.1.bn2.weight - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.1.branches.0.1.bn2.bias - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.1.branches.0.2.conv1.weight - torch.Size([18, 18, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.1.branches.0.2.bn1.weight - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.1.branches.0.2.bn1.bias - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.1.branches.0.2.conv2.weight - torch.Size([18, 18, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.1.branches.0.2.bn2.weight - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.1.branches.0.2.bn2.bias - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.1.branches.0.3.conv1.weight - torch.Size([18, 18, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.1.branches.0.3.bn1.weight - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.1.branches.0.3.bn1.bias - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.1.branches.0.3.conv2.weight - torch.Size([18, 18, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.1.branches.0.3.bn2.weight - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.1.branches.0.3.bn2.bias - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.1.branches.1.0.conv1.weight - torch.Size([36, 36, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.1.branches.1.0.bn1.weight - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.1.branches.1.0.bn1.bias - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.1.branches.1.0.conv2.weight - torch.Size([36, 36, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.1.branches.1.0.bn2.weight - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.1.branches.1.0.bn2.bias - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.1.branches.1.1.conv1.weight - torch.Size([36, 36, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.1.branches.1.1.bn1.weight - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.1.branches.1.1.bn1.bias - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.1.branches.1.1.conv2.weight - torch.Size([36, 36, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.1.branches.1.1.bn2.weight - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.1.branches.1.1.bn2.bias - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.1.branches.1.2.conv1.weight - torch.Size([36, 36, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.1.branches.1.2.bn1.weight - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.1.branches.1.2.bn1.bias - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.1.branches.1.2.conv2.weight - torch.Size([36, 36, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.1.branches.1.2.bn2.weight - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.1.branches.1.2.bn2.bias - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.1.branches.1.3.conv1.weight - torch.Size([36, 36, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.1.branches.1.3.bn1.weight - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.1.branches.1.3.bn1.bias - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.1.branches.1.3.conv2.weight - torch.Size([36, 36, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.1.branches.1.3.bn2.weight - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.1.branches.1.3.bn2.bias - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.1.branches.2.0.conv1.weight - torch.Size([72, 72, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.1.branches.2.0.bn1.weight - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.1.branches.2.0.bn1.bias - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.1.branches.2.0.conv2.weight - torch.Size([72, 72, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.1.branches.2.0.bn2.weight - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.1.branches.2.0.bn2.bias - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.1.branches.2.1.conv1.weight - torch.Size([72, 72, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.1.branches.2.1.bn1.weight - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.1.branches.2.1.bn1.bias - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.1.branches.2.1.conv2.weight - torch.Size([72, 72, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.1.branches.2.1.bn2.weight - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.1.branches.2.1.bn2.bias - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.1.branches.2.2.conv1.weight - torch.Size([72, 72, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.1.branches.2.2.bn1.weight - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.1.branches.2.2.bn1.bias - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.1.branches.2.2.conv2.weight - torch.Size([72, 72, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.1.branches.2.2.bn2.weight - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.1.branches.2.2.bn2.bias - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.1.branches.2.3.conv1.weight - torch.Size([72, 72, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.1.branches.2.3.bn1.weight - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.1.branches.2.3.bn1.bias - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.1.branches.2.3.conv2.weight - torch.Size([72, 72, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.1.branches.2.3.bn2.weight - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.1.branches.2.3.bn2.bias - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.1.fuse_layers.0.1.0.weight - torch.Size([18, 36, 1, 1]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.1.fuse_layers.0.1.1.weight - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.1.fuse_layers.0.1.1.bias - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.1.fuse_layers.0.2.0.weight - torch.Size([18, 72, 1, 1]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.1.fuse_layers.0.2.1.weight - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.1.fuse_layers.0.2.1.bias - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.1.fuse_layers.1.0.0.0.weight - torch.Size([36, 18, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.1.fuse_layers.1.0.0.1.weight - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.1.fuse_layers.1.0.0.1.bias - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.1.fuse_layers.1.2.0.weight - torch.Size([36, 72, 1, 1]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.1.fuse_layers.1.2.1.weight - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.1.fuse_layers.1.2.1.bias - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.1.fuse_layers.2.0.0.0.weight - torch.Size([18, 18, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.1.fuse_layers.2.0.0.1.weight - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.1.fuse_layers.2.0.0.1.bias - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.1.fuse_layers.2.0.1.0.weight - torch.Size([72, 18, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.1.fuse_layers.2.0.1.1.weight - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.1.fuse_layers.2.0.1.1.bias - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.1.fuse_layers.2.1.0.0.weight - torch.Size([72, 36, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.1.fuse_layers.2.1.0.1.weight - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.1.fuse_layers.2.1.0.1.bias - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.2.branches.0.0.conv1.weight - torch.Size([18, 18, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.2.branches.0.0.bn1.weight - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.2.branches.0.0.bn1.bias - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.2.branches.0.0.conv2.weight - torch.Size([18, 18, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.2.branches.0.0.bn2.weight - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.2.branches.0.0.bn2.bias - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.2.branches.0.1.conv1.weight - torch.Size([18, 18, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.2.branches.0.1.bn1.weight - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.2.branches.0.1.bn1.bias - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.2.branches.0.1.conv2.weight - torch.Size([18, 18, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.2.branches.0.1.bn2.weight - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.2.branches.0.1.bn2.bias - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.2.branches.0.2.conv1.weight - torch.Size([18, 18, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.2.branches.0.2.bn1.weight - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.2.branches.0.2.bn1.bias - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.2.branches.0.2.conv2.weight - torch.Size([18, 18, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.2.branches.0.2.bn2.weight - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.2.branches.0.2.bn2.bias - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.2.branches.0.3.conv1.weight - torch.Size([18, 18, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.2.branches.0.3.bn1.weight - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.2.branches.0.3.bn1.bias - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.2.branches.0.3.conv2.weight - torch.Size([18, 18, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.2.branches.0.3.bn2.weight - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.2.branches.0.3.bn2.bias - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.2.branches.1.0.conv1.weight - torch.Size([36, 36, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.2.branches.1.0.bn1.weight - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.2.branches.1.0.bn1.bias - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.2.branches.1.0.conv2.weight - torch.Size([36, 36, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.2.branches.1.0.bn2.weight - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.2.branches.1.0.bn2.bias - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.2.branches.1.1.conv1.weight - torch.Size([36, 36, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.2.branches.1.1.bn1.weight - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.2.branches.1.1.bn1.bias - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.2.branches.1.1.conv2.weight - torch.Size([36, 36, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.2.branches.1.1.bn2.weight - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.2.branches.1.1.bn2.bias - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.2.branches.1.2.conv1.weight - torch.Size([36, 36, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.2.branches.1.2.bn1.weight - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.2.branches.1.2.bn1.bias - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.2.branches.1.2.conv2.weight - torch.Size([36, 36, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.2.branches.1.2.bn2.weight - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.2.branches.1.2.bn2.bias - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.2.branches.1.3.conv1.weight - torch.Size([36, 36, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.2.branches.1.3.bn1.weight - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.2.branches.1.3.bn1.bias - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.2.branches.1.3.conv2.weight - torch.Size([36, 36, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.2.branches.1.3.bn2.weight - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.2.branches.1.3.bn2.bias - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.2.branches.2.0.conv1.weight - torch.Size([72, 72, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.2.branches.2.0.bn1.weight - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.2.branches.2.0.bn1.bias - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.2.branches.2.0.conv2.weight - torch.Size([72, 72, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.2.branches.2.0.bn2.weight - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.2.branches.2.0.bn2.bias - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.2.branches.2.1.conv1.weight - torch.Size([72, 72, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.2.branches.2.1.bn1.weight - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.2.branches.2.1.bn1.bias - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.2.branches.2.1.conv2.weight - torch.Size([72, 72, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.2.branches.2.1.bn2.weight - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.2.branches.2.1.bn2.bias - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.2.branches.2.2.conv1.weight - torch.Size([72, 72, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.2.branches.2.2.bn1.weight - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.2.branches.2.2.bn1.bias - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.2.branches.2.2.conv2.weight - torch.Size([72, 72, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.2.branches.2.2.bn2.weight - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.2.branches.2.2.bn2.bias - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.2.branches.2.3.conv1.weight - torch.Size([72, 72, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.2.branches.2.3.bn1.weight - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.2.branches.2.3.bn1.bias - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.2.branches.2.3.conv2.weight - torch.Size([72, 72, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.2.branches.2.3.bn2.weight - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.2.branches.2.3.bn2.bias - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.2.fuse_layers.0.1.0.weight - torch.Size([18, 36, 1, 1]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.2.fuse_layers.0.1.1.weight - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.2.fuse_layers.0.1.1.bias - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.2.fuse_layers.0.2.0.weight - torch.Size([18, 72, 1, 1]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.2.fuse_layers.0.2.1.weight - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.2.fuse_layers.0.2.1.bias - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.2.fuse_layers.1.0.0.0.weight - torch.Size([36, 18, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.2.fuse_layers.1.0.0.1.weight - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.2.fuse_layers.1.0.0.1.bias - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.2.fuse_layers.1.2.0.weight - torch.Size([36, 72, 1, 1]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.2.fuse_layers.1.2.1.weight - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.2.fuse_layers.1.2.1.bias - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.2.fuse_layers.2.0.0.0.weight - torch.Size([18, 18, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.2.fuse_layers.2.0.0.1.weight - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.2.fuse_layers.2.0.0.1.bias - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.2.fuse_layers.2.0.1.0.weight - torch.Size([72, 18, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.2.fuse_layers.2.0.1.1.weight - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.2.fuse_layers.2.0.1.1.bias - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.2.fuse_layers.2.1.0.0.weight - torch.Size([72, 36, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.2.fuse_layers.2.1.0.1.weight - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.2.fuse_layers.2.1.0.1.bias - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.3.branches.0.0.conv1.weight - torch.Size([18, 18, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.3.branches.0.0.bn1.weight - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.3.branches.0.0.bn1.bias - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.3.branches.0.0.conv2.weight - torch.Size([18, 18, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.3.branches.0.0.bn2.weight - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.3.branches.0.0.bn2.bias - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.3.branches.0.1.conv1.weight - torch.Size([18, 18, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.3.branches.0.1.bn1.weight - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.3.branches.0.1.bn1.bias - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.3.branches.0.1.conv2.weight - torch.Size([18, 18, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.3.branches.0.1.bn2.weight - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.3.branches.0.1.bn2.bias - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.3.branches.0.2.conv1.weight - torch.Size([18, 18, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.3.branches.0.2.bn1.weight - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.3.branches.0.2.bn1.bias - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.3.branches.0.2.conv2.weight - torch.Size([18, 18, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.3.branches.0.2.bn2.weight - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.3.branches.0.2.bn2.bias - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.3.branches.0.3.conv1.weight - torch.Size([18, 18, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.3.branches.0.3.bn1.weight - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.3.branches.0.3.bn1.bias - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.3.branches.0.3.conv2.weight - torch.Size([18, 18, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.3.branches.0.3.bn2.weight - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.3.branches.0.3.bn2.bias - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.3.branches.1.0.conv1.weight - torch.Size([36, 36, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.3.branches.1.0.bn1.weight - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.3.branches.1.0.bn1.bias - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.3.branches.1.0.conv2.weight - torch.Size([36, 36, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.3.branches.1.0.bn2.weight - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.3.branches.1.0.bn2.bias - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.3.branches.1.1.conv1.weight - torch.Size([36, 36, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.3.branches.1.1.bn1.weight - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.3.branches.1.1.bn1.bias - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.3.branches.1.1.conv2.weight - torch.Size([36, 36, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.3.branches.1.1.bn2.weight - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.3.branches.1.1.bn2.bias - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.3.branches.1.2.conv1.weight - torch.Size([36, 36, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.3.branches.1.2.bn1.weight - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.3.branches.1.2.bn1.bias - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.3.branches.1.2.conv2.weight - torch.Size([36, 36, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.3.branches.1.2.bn2.weight - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.3.branches.1.2.bn2.bias - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.3.branches.1.3.conv1.weight - torch.Size([36, 36, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.3.branches.1.3.bn1.weight - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.3.branches.1.3.bn1.bias - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.3.branches.1.3.conv2.weight - torch.Size([36, 36, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.3.branches.1.3.bn2.weight - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.3.branches.1.3.bn2.bias - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.3.branches.2.0.conv1.weight - torch.Size([72, 72, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.3.branches.2.0.bn1.weight - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.3.branches.2.0.bn1.bias - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.3.branches.2.0.conv2.weight - torch.Size([72, 72, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.3.branches.2.0.bn2.weight - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.3.branches.2.0.bn2.bias - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.3.branches.2.1.conv1.weight - torch.Size([72, 72, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.3.branches.2.1.bn1.weight - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.3.branches.2.1.bn1.bias - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.3.branches.2.1.conv2.weight - torch.Size([72, 72, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.3.branches.2.1.bn2.weight - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.3.branches.2.1.bn2.bias - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.3.branches.2.2.conv1.weight - torch.Size([72, 72, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.3.branches.2.2.bn1.weight - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.3.branches.2.2.bn1.bias - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.3.branches.2.2.conv2.weight - torch.Size([72, 72, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.3.branches.2.2.bn2.weight - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.3.branches.2.2.bn2.bias - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.3.branches.2.3.conv1.weight - torch.Size([72, 72, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.3.branches.2.3.bn1.weight - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.3.branches.2.3.bn1.bias - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.3.branches.2.3.conv2.weight - torch.Size([72, 72, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.3.branches.2.3.bn2.weight - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.3.branches.2.3.bn2.bias - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.3.fuse_layers.0.1.0.weight - torch.Size([18, 36, 1, 1]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.3.fuse_layers.0.1.1.weight - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.3.fuse_layers.0.1.1.bias - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.3.fuse_layers.0.2.0.weight - torch.Size([18, 72, 1, 1]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.3.fuse_layers.0.2.1.weight - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.3.fuse_layers.0.2.1.bias - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.3.fuse_layers.1.0.0.0.weight - torch.Size([36, 18, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.3.fuse_layers.1.0.0.1.weight - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.3.fuse_layers.1.0.0.1.bias - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.3.fuse_layers.1.2.0.weight - torch.Size([36, 72, 1, 1]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.3.fuse_layers.1.2.1.weight - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.3.fuse_layers.1.2.1.bias - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.3.fuse_layers.2.0.0.0.weight - torch.Size([18, 18, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.3.fuse_layers.2.0.0.1.weight - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.3.fuse_layers.2.0.0.1.bias - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.3.fuse_layers.2.0.1.0.weight - torch.Size([72, 18, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.3.fuse_layers.2.0.1.1.weight - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.3.fuse_layers.2.0.1.1.bias - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.3.fuse_layers.2.1.0.0.weight - torch.Size([72, 36, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.3.fuse_layers.2.1.0.1.weight - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage3.3.fuse_layers.2.1.0.1.bias - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.transition3.3.0.0.weight - torch.Size([144, 72, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.transition3.3.0.1.weight - torch.Size([144]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.transition3.3.0.1.bias - torch.Size([144]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.branches.0.0.conv1.weight - torch.Size([18, 18, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.branches.0.0.bn1.weight - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.branches.0.0.bn1.bias - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.branches.0.0.conv2.weight - torch.Size([18, 18, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.branches.0.0.bn2.weight - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.branches.0.0.bn2.bias - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.branches.0.1.conv1.weight - torch.Size([18, 18, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.branches.0.1.bn1.weight - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.branches.0.1.bn1.bias - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.branches.0.1.conv2.weight - torch.Size([18, 18, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.branches.0.1.bn2.weight - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.branches.0.1.bn2.bias - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.branches.0.2.conv1.weight - torch.Size([18, 18, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.branches.0.2.bn1.weight - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.branches.0.2.bn1.bias - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.branches.0.2.conv2.weight - torch.Size([18, 18, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.branches.0.2.bn2.weight - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.branches.0.2.bn2.bias - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.branches.0.3.conv1.weight - torch.Size([18, 18, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.branches.0.3.bn1.weight - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.branches.0.3.bn1.bias - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.branches.0.3.conv2.weight - torch.Size([18, 18, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.branches.0.3.bn2.weight - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.branches.0.3.bn2.bias - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.branches.1.0.conv1.weight - torch.Size([36, 36, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.branches.1.0.bn1.weight - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.branches.1.0.bn1.bias - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.branches.1.0.conv2.weight - torch.Size([36, 36, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.branches.1.0.bn2.weight - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.branches.1.0.bn2.bias - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.branches.1.1.conv1.weight - torch.Size([36, 36, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.branches.1.1.bn1.weight - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.branches.1.1.bn1.bias - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.branches.1.1.conv2.weight - torch.Size([36, 36, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.branches.1.1.bn2.weight - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.branches.1.1.bn2.bias - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.branches.1.2.conv1.weight - torch.Size([36, 36, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.branches.1.2.bn1.weight - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.branches.1.2.bn1.bias - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.branches.1.2.conv2.weight - torch.Size([36, 36, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.branches.1.2.bn2.weight - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.branches.1.2.bn2.bias - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.branches.1.3.conv1.weight - torch.Size([36, 36, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.branches.1.3.bn1.weight - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.branches.1.3.bn1.bias - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.branches.1.3.conv2.weight - torch.Size([36, 36, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.branches.1.3.bn2.weight - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.branches.1.3.bn2.bias - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.branches.2.0.conv1.weight - torch.Size([72, 72, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.branches.2.0.bn1.weight - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.branches.2.0.bn1.bias - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.branches.2.0.conv2.weight - torch.Size([72, 72, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.branches.2.0.bn2.weight - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.branches.2.0.bn2.bias - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.branches.2.1.conv1.weight - torch.Size([72, 72, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.branches.2.1.bn1.weight - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.branches.2.1.bn1.bias - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.branches.2.1.conv2.weight - torch.Size([72, 72, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.branches.2.1.bn2.weight - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.branches.2.1.bn2.bias - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.branches.2.2.conv1.weight - torch.Size([72, 72, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.branches.2.2.bn1.weight - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.branches.2.2.bn1.bias - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.branches.2.2.conv2.weight - torch.Size([72, 72, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.branches.2.2.bn2.weight - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.branches.2.2.bn2.bias - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.branches.2.3.conv1.weight - torch.Size([72, 72, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.branches.2.3.bn1.weight - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.branches.2.3.bn1.bias - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.branches.2.3.conv2.weight - torch.Size([72, 72, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.branches.2.3.bn2.weight - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.branches.2.3.bn2.bias - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.branches.3.0.conv1.weight - torch.Size([144, 144, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.branches.3.0.bn1.weight - torch.Size([144]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.branches.3.0.bn1.bias - torch.Size([144]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.branches.3.0.conv2.weight - torch.Size([144, 144, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.branches.3.0.bn2.weight - torch.Size([144]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.branches.3.0.bn2.bias - torch.Size([144]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.branches.3.1.conv1.weight - torch.Size([144, 144, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.branches.3.1.bn1.weight - torch.Size([144]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.branches.3.1.bn1.bias - torch.Size([144]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.branches.3.1.conv2.weight - torch.Size([144, 144, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.branches.3.1.bn2.weight - torch.Size([144]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.branches.3.1.bn2.bias - torch.Size([144]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.branches.3.2.conv1.weight - torch.Size([144, 144, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.branches.3.2.bn1.weight - torch.Size([144]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.branches.3.2.bn1.bias - torch.Size([144]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.branches.3.2.conv2.weight - torch.Size([144, 144, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.branches.3.2.bn2.weight - torch.Size([144]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.branches.3.2.bn2.bias - torch.Size([144]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.branches.3.3.conv1.weight - torch.Size([144, 144, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.branches.3.3.bn1.weight - torch.Size([144]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.branches.3.3.bn1.bias - torch.Size([144]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.branches.3.3.conv2.weight - torch.Size([144, 144, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.branches.3.3.bn2.weight - torch.Size([144]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.branches.3.3.bn2.bias - torch.Size([144]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.fuse_layers.0.1.0.weight - torch.Size([18, 36, 1, 1]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.fuse_layers.0.1.1.weight - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.fuse_layers.0.1.1.bias - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.fuse_layers.0.2.0.weight - torch.Size([18, 72, 1, 1]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.fuse_layers.0.2.1.weight - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.fuse_layers.0.2.1.bias - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.fuse_layers.0.3.0.weight - torch.Size([18, 144, 1, 1]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.fuse_layers.0.3.1.weight - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.fuse_layers.0.3.1.bias - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.fuse_layers.1.0.0.0.weight - torch.Size([36, 18, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.fuse_layers.1.0.0.1.weight - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.fuse_layers.1.0.0.1.bias - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.fuse_layers.1.2.0.weight - torch.Size([36, 72, 1, 1]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.fuse_layers.1.2.1.weight - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.fuse_layers.1.2.1.bias - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.fuse_layers.1.3.0.weight - torch.Size([36, 144, 1, 1]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.fuse_layers.1.3.1.weight - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.fuse_layers.1.3.1.bias - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.fuse_layers.2.0.0.0.weight - torch.Size([18, 18, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.fuse_layers.2.0.0.1.weight - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.fuse_layers.2.0.0.1.bias - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.fuse_layers.2.0.1.0.weight - torch.Size([72, 18, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.fuse_layers.2.0.1.1.weight - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.fuse_layers.2.0.1.1.bias - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.fuse_layers.2.1.0.0.weight - torch.Size([72, 36, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.fuse_layers.2.1.0.1.weight - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.fuse_layers.2.1.0.1.bias - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.fuse_layers.2.3.0.weight - torch.Size([72, 144, 1, 1]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.fuse_layers.2.3.1.weight - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.fuse_layers.2.3.1.bias - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.fuse_layers.3.0.0.0.weight - torch.Size([18, 18, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.fuse_layers.3.0.0.1.weight - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.fuse_layers.3.0.0.1.bias - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.fuse_layers.3.0.1.0.weight - torch.Size([18, 18, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.fuse_layers.3.0.1.1.weight - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.fuse_layers.3.0.1.1.bias - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.fuse_layers.3.0.2.0.weight - torch.Size([144, 18, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.fuse_layers.3.0.2.1.weight - torch.Size([144]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.fuse_layers.3.0.2.1.bias - torch.Size([144]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.fuse_layers.3.1.0.0.weight - torch.Size([36, 36, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.fuse_layers.3.1.0.1.weight - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.fuse_layers.3.1.0.1.bias - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.fuse_layers.3.1.1.0.weight - torch.Size([144, 36, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.fuse_layers.3.1.1.1.weight - torch.Size([144]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.fuse_layers.3.1.1.1.bias - torch.Size([144]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.fuse_layers.3.2.0.0.weight - torch.Size([144, 72, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.fuse_layers.3.2.0.1.weight - torch.Size([144]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.0.fuse_layers.3.2.0.1.bias - torch.Size([144]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.branches.0.0.conv1.weight - torch.Size([18, 18, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.branches.0.0.bn1.weight - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.branches.0.0.bn1.bias - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.branches.0.0.conv2.weight - torch.Size([18, 18, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.branches.0.0.bn2.weight - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.branches.0.0.bn2.bias - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.branches.0.1.conv1.weight - torch.Size([18, 18, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.branches.0.1.bn1.weight - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.branches.0.1.bn1.bias - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.branches.0.1.conv2.weight - torch.Size([18, 18, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.branches.0.1.bn2.weight - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.branches.0.1.bn2.bias - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.branches.0.2.conv1.weight - torch.Size([18, 18, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.branches.0.2.bn1.weight - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.branches.0.2.bn1.bias - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.branches.0.2.conv2.weight - torch.Size([18, 18, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.branches.0.2.bn2.weight - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.branches.0.2.bn2.bias - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.branches.0.3.conv1.weight - torch.Size([18, 18, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.branches.0.3.bn1.weight - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.branches.0.3.bn1.bias - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.branches.0.3.conv2.weight - torch.Size([18, 18, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.branches.0.3.bn2.weight - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.branches.0.3.bn2.bias - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.branches.1.0.conv1.weight - torch.Size([36, 36, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.branches.1.0.bn1.weight - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.branches.1.0.bn1.bias - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.branches.1.0.conv2.weight - torch.Size([36, 36, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.branches.1.0.bn2.weight - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.branches.1.0.bn2.bias - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.branches.1.1.conv1.weight - torch.Size([36, 36, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.branches.1.1.bn1.weight - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.branches.1.1.bn1.bias - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.branches.1.1.conv2.weight - torch.Size([36, 36, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.branches.1.1.bn2.weight - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.branches.1.1.bn2.bias - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.branches.1.2.conv1.weight - torch.Size([36, 36, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.branches.1.2.bn1.weight - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.branches.1.2.bn1.bias - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.branches.1.2.conv2.weight - torch.Size([36, 36, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.branches.1.2.bn2.weight - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.branches.1.2.bn2.bias - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.branches.1.3.conv1.weight - torch.Size([36, 36, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.branches.1.3.bn1.weight - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.branches.1.3.bn1.bias - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.branches.1.3.conv2.weight - torch.Size([36, 36, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.branches.1.3.bn2.weight - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.branches.1.3.bn2.bias - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.branches.2.0.conv1.weight - torch.Size([72, 72, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.branches.2.0.bn1.weight - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.branches.2.0.bn1.bias - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.branches.2.0.conv2.weight - torch.Size([72, 72, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.branches.2.0.bn2.weight - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.branches.2.0.bn2.bias - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.branches.2.1.conv1.weight - torch.Size([72, 72, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.branches.2.1.bn1.weight - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.branches.2.1.bn1.bias - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.branches.2.1.conv2.weight - torch.Size([72, 72, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.branches.2.1.bn2.weight - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.branches.2.1.bn2.bias - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.branches.2.2.conv1.weight - torch.Size([72, 72, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.branches.2.2.bn1.weight - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.branches.2.2.bn1.bias - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.branches.2.2.conv2.weight - torch.Size([72, 72, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.branches.2.2.bn2.weight - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.branches.2.2.bn2.bias - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.branches.2.3.conv1.weight - torch.Size([72, 72, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.branches.2.3.bn1.weight - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.branches.2.3.bn1.bias - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.branches.2.3.conv2.weight - torch.Size([72, 72, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.branches.2.3.bn2.weight - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.branches.2.3.bn2.bias - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.branches.3.0.conv1.weight - torch.Size([144, 144, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.branches.3.0.bn1.weight - torch.Size([144]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.branches.3.0.bn1.bias - torch.Size([144]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.branches.3.0.conv2.weight - torch.Size([144, 144, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.branches.3.0.bn2.weight - torch.Size([144]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.branches.3.0.bn2.bias - torch.Size([144]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.branches.3.1.conv1.weight - torch.Size([144, 144, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.branches.3.1.bn1.weight - torch.Size([144]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.branches.3.1.bn1.bias - torch.Size([144]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.branches.3.1.conv2.weight - torch.Size([144, 144, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.branches.3.1.bn2.weight - torch.Size([144]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.branches.3.1.bn2.bias - torch.Size([144]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.branches.3.2.conv1.weight - torch.Size([144, 144, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.branches.3.2.bn1.weight - torch.Size([144]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.branches.3.2.bn1.bias - torch.Size([144]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.branches.3.2.conv2.weight - torch.Size([144, 144, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.branches.3.2.bn2.weight - torch.Size([144]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.branches.3.2.bn2.bias - torch.Size([144]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.branches.3.3.conv1.weight - torch.Size([144, 144, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.branches.3.3.bn1.weight - torch.Size([144]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.branches.3.3.bn1.bias - torch.Size([144]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.branches.3.3.conv2.weight - torch.Size([144, 144, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.branches.3.3.bn2.weight - torch.Size([144]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.branches.3.3.bn2.bias - torch.Size([144]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.fuse_layers.0.1.0.weight - torch.Size([18, 36, 1, 1]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.fuse_layers.0.1.1.weight - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.fuse_layers.0.1.1.bias - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.fuse_layers.0.2.0.weight - torch.Size([18, 72, 1, 1]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.fuse_layers.0.2.1.weight - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.fuse_layers.0.2.1.bias - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.fuse_layers.0.3.0.weight - torch.Size([18, 144, 1, 1]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.fuse_layers.0.3.1.weight - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.fuse_layers.0.3.1.bias - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.fuse_layers.1.0.0.0.weight - torch.Size([36, 18, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.fuse_layers.1.0.0.1.weight - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.fuse_layers.1.0.0.1.bias - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.fuse_layers.1.2.0.weight - torch.Size([36, 72, 1, 1]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.fuse_layers.1.2.1.weight - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.fuse_layers.1.2.1.bias - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.fuse_layers.1.3.0.weight - torch.Size([36, 144, 1, 1]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.fuse_layers.1.3.1.weight - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.fuse_layers.1.3.1.bias - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.fuse_layers.2.0.0.0.weight - torch.Size([18, 18, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.fuse_layers.2.0.0.1.weight - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.fuse_layers.2.0.0.1.bias - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.fuse_layers.2.0.1.0.weight - torch.Size([72, 18, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.fuse_layers.2.0.1.1.weight - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.fuse_layers.2.0.1.1.bias - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.fuse_layers.2.1.0.0.weight - torch.Size([72, 36, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.fuse_layers.2.1.0.1.weight - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.fuse_layers.2.1.0.1.bias - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.fuse_layers.2.3.0.weight - torch.Size([72, 144, 1, 1]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.fuse_layers.2.3.1.weight - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.fuse_layers.2.3.1.bias - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.fuse_layers.3.0.0.0.weight - torch.Size([18, 18, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.fuse_layers.3.0.0.1.weight - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.fuse_layers.3.0.0.1.bias - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.fuse_layers.3.0.1.0.weight - torch.Size([18, 18, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.fuse_layers.3.0.1.1.weight - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.fuse_layers.3.0.1.1.bias - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.fuse_layers.3.0.2.0.weight - torch.Size([144, 18, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.fuse_layers.3.0.2.1.weight - torch.Size([144]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.fuse_layers.3.0.2.1.bias - torch.Size([144]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.fuse_layers.3.1.0.0.weight - torch.Size([36, 36, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.fuse_layers.3.1.0.1.weight - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.fuse_layers.3.1.0.1.bias - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.fuse_layers.3.1.1.0.weight - torch.Size([144, 36, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.fuse_layers.3.1.1.1.weight - torch.Size([144]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.fuse_layers.3.1.1.1.bias - torch.Size([144]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.fuse_layers.3.2.0.0.weight - torch.Size([144, 72, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.fuse_layers.3.2.0.1.weight - torch.Size([144]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.1.fuse_layers.3.2.0.1.bias - torch.Size([144]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.branches.0.0.conv1.weight - torch.Size([18, 18, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.branches.0.0.bn1.weight - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.branches.0.0.bn1.bias - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.branches.0.0.conv2.weight - torch.Size([18, 18, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.branches.0.0.bn2.weight - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.branches.0.0.bn2.bias - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.branches.0.1.conv1.weight - torch.Size([18, 18, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.branches.0.1.bn1.weight - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.branches.0.1.bn1.bias - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.branches.0.1.conv2.weight - torch.Size([18, 18, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.branches.0.1.bn2.weight - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.branches.0.1.bn2.bias - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.branches.0.2.conv1.weight - torch.Size([18, 18, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.branches.0.2.bn1.weight - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.branches.0.2.bn1.bias - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.branches.0.2.conv2.weight - torch.Size([18, 18, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.branches.0.2.bn2.weight - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.branches.0.2.bn2.bias - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.branches.0.3.conv1.weight - torch.Size([18, 18, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.branches.0.3.bn1.weight - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.branches.0.3.bn1.bias - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.branches.0.3.conv2.weight - torch.Size([18, 18, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.branches.0.3.bn2.weight - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.branches.0.3.bn2.bias - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.branches.1.0.conv1.weight - torch.Size([36, 36, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.branches.1.0.bn1.weight - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.branches.1.0.bn1.bias - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.branches.1.0.conv2.weight - torch.Size([36, 36, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.branches.1.0.bn2.weight - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.branches.1.0.bn2.bias - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.branches.1.1.conv1.weight - torch.Size([36, 36, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.branches.1.1.bn1.weight - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.branches.1.1.bn1.bias - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.branches.1.1.conv2.weight - torch.Size([36, 36, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.branches.1.1.bn2.weight - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.branches.1.1.bn2.bias - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.branches.1.2.conv1.weight - torch.Size([36, 36, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.branches.1.2.bn1.weight - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.branches.1.2.bn1.bias - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.branches.1.2.conv2.weight - torch.Size([36, 36, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.branches.1.2.bn2.weight - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.branches.1.2.bn2.bias - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.branches.1.3.conv1.weight - torch.Size([36, 36, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.branches.1.3.bn1.weight - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.branches.1.3.bn1.bias - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.branches.1.3.conv2.weight - torch.Size([36, 36, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.branches.1.3.bn2.weight - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.branches.1.3.bn2.bias - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.branches.2.0.conv1.weight - torch.Size([72, 72, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.branches.2.0.bn1.weight - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.branches.2.0.bn1.bias - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.branches.2.0.conv2.weight - torch.Size([72, 72, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.branches.2.0.bn2.weight - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.branches.2.0.bn2.bias - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.branches.2.1.conv1.weight - torch.Size([72, 72, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.branches.2.1.bn1.weight - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.branches.2.1.bn1.bias - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.branches.2.1.conv2.weight - torch.Size([72, 72, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.branches.2.1.bn2.weight - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.branches.2.1.bn2.bias - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.branches.2.2.conv1.weight - torch.Size([72, 72, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.branches.2.2.bn1.weight - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.branches.2.2.bn1.bias - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.branches.2.2.conv2.weight - torch.Size([72, 72, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.branches.2.2.bn2.weight - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.branches.2.2.bn2.bias - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.branches.2.3.conv1.weight - torch.Size([72, 72, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.branches.2.3.bn1.weight - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.branches.2.3.bn1.bias - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.branches.2.3.conv2.weight - torch.Size([72, 72, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.branches.2.3.bn2.weight - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.branches.2.3.bn2.bias - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.branches.3.0.conv1.weight - torch.Size([144, 144, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.branches.3.0.bn1.weight - torch.Size([144]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.branches.3.0.bn1.bias - torch.Size([144]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.branches.3.0.conv2.weight - torch.Size([144, 144, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.branches.3.0.bn2.weight - torch.Size([144]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.branches.3.0.bn2.bias - torch.Size([144]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.branches.3.1.conv1.weight - torch.Size([144, 144, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.branches.3.1.bn1.weight - torch.Size([144]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.branches.3.1.bn1.bias - torch.Size([144]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.branches.3.1.conv2.weight - torch.Size([144, 144, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.branches.3.1.bn2.weight - torch.Size([144]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.branches.3.1.bn2.bias - torch.Size([144]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.branches.3.2.conv1.weight - torch.Size([144, 144, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.branches.3.2.bn1.weight - torch.Size([144]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.branches.3.2.bn1.bias - torch.Size([144]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.branches.3.2.conv2.weight - torch.Size([144, 144, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.branches.3.2.bn2.weight - torch.Size([144]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.branches.3.2.bn2.bias - torch.Size([144]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.branches.3.3.conv1.weight - torch.Size([144, 144, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.branches.3.3.bn1.weight - torch.Size([144]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.branches.3.3.bn1.bias - torch.Size([144]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.branches.3.3.conv2.weight - torch.Size([144, 144, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.branches.3.3.bn2.weight - torch.Size([144]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.branches.3.3.bn2.bias - torch.Size([144]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.fuse_layers.0.1.0.weight - torch.Size([18, 36, 1, 1]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.fuse_layers.0.1.1.weight - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.fuse_layers.0.1.1.bias - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.fuse_layers.0.2.0.weight - torch.Size([18, 72, 1, 1]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.fuse_layers.0.2.1.weight - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.fuse_layers.0.2.1.bias - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.fuse_layers.0.3.0.weight - torch.Size([18, 144, 1, 1]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.fuse_layers.0.3.1.weight - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.fuse_layers.0.3.1.bias - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.fuse_layers.1.0.0.0.weight - torch.Size([36, 18, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.fuse_layers.1.0.0.1.weight - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.fuse_layers.1.0.0.1.bias - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.fuse_layers.1.2.0.weight - torch.Size([36, 72, 1, 1]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.fuse_layers.1.2.1.weight - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.fuse_layers.1.2.1.bias - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.fuse_layers.1.3.0.weight - torch.Size([36, 144, 1, 1]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.fuse_layers.1.3.1.weight - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.fuse_layers.1.3.1.bias - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.fuse_layers.2.0.0.0.weight - torch.Size([18, 18, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.fuse_layers.2.0.0.1.weight - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.fuse_layers.2.0.0.1.bias - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.fuse_layers.2.0.1.0.weight - torch.Size([72, 18, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.fuse_layers.2.0.1.1.weight - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.fuse_layers.2.0.1.1.bias - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.fuse_layers.2.1.0.0.weight - torch.Size([72, 36, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.fuse_layers.2.1.0.1.weight - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.fuse_layers.2.1.0.1.bias - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.fuse_layers.2.3.0.weight - torch.Size([72, 144, 1, 1]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.fuse_layers.2.3.1.weight - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.fuse_layers.2.3.1.bias - torch.Size([72]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.fuse_layers.3.0.0.0.weight - torch.Size([18, 18, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.fuse_layers.3.0.0.1.weight - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.fuse_layers.3.0.0.1.bias - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.fuse_layers.3.0.1.0.weight - torch.Size([18, 18, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.fuse_layers.3.0.1.1.weight - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.fuse_layers.3.0.1.1.bias - torch.Size([18]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.fuse_layers.3.0.2.0.weight - torch.Size([144, 18, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.fuse_layers.3.0.2.1.weight - torch.Size([144]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.fuse_layers.3.0.2.1.bias - torch.Size([144]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.fuse_layers.3.1.0.0.weight - torch.Size([36, 36, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.fuse_layers.3.1.0.1.weight - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.fuse_layers.3.1.0.1.bias - torch.Size([36]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.fuse_layers.3.1.1.0.weight - torch.Size([144, 36, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.fuse_layers.3.1.1.1.weight - torch.Size([144]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.fuse_layers.3.1.1.1.bias - torch.Size([144]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.fuse_layers.3.2.0.0.weight - torch.Size([144, 72, 3, 3]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.fuse_layers.3.2.0.1.weight - torch.Size([144]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 backbone.stage4.2.fuse_layers.3.2.0.1.bias - torch.Size([144]): PretrainedInit: load from open-mmlab://msra/hrnetv2_w18 head.conv_layers.0.weight - torch.Size([270, 270, 1, 1]): NormalInit: mean=0, std=0.01, bias=0 head.conv_layers.0.bias - torch.Size([270]): NormalInit: mean=0, std=0.01, bias=0 head.conv_layers.1.weight - torch.Size([270]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator head.conv_layers.1.bias - torch.Size([270]): The value is the same before and after calling `init_weights` of TopdownPoseEstimator head.final_layer.weight - torch.Size([87, 270, 1, 1]): NormalInit: mean=0, std=0.01, bias=0 head.final_layer.bias - torch.Size([87]): NormalInit: mean=0, std=0.01, bias=0 2023/05/24 07:49:54 - mmengine - WARNING - "FileClient" will be deprecated in future. Please use io functions in https://mmengine.readthedocs.io/en/latest/api/fileio.html#file-io 2023/05/24 07:49:54 - mmengine - WARNING - "HardDiskBackend" is the alias of "LocalBackend" and the former will be deprecated in future. 2023/05/24 07:49:54 - mmengine - INFO - Checkpoints will be saved to /root/mmpose/projects/skps/work_dirs/td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256. 2023/05/24 07:50:10 - mmengine - INFO - Epoch(train) [1][50/85] lr: 1.981964e-04 eta: 1:13:27 time: 0.325282 data_time: 0.038087 memory: 1767 loss: 0.142363 loss/heatmap: 0.088369 loss/offside: 0.053994 acc_pose: 0.447291 2023/05/24 07:50:19 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 07:50:19 - mmengine - INFO - Saving checkpoint at 1 epochs 2023/05/24 07:50:25 - mmengine - INFO - Evaluating NME... 2023/05/24 07:50:25 - mmengine - INFO - Epoch(val) [1][16/16] NME: 0.096561 data_time: 0.052312 time: 0.291762 2023/05/24 07:50:25 - mmengine - INFO - The best checkpoint with 0.0966 NME at 1 epoch is saved to best_NME_epoch_1.pth. 2023/05/24 07:50:38 - mmengine - INFO - Epoch(train) [2][50/85] lr: 5.385371e-04 eta: 1:04:39 time: 0.263192 data_time: 0.028964 memory: 1767 loss: 0.061163 loss/heatmap: 0.025312 loss/offside: 0.035851 acc_pose: 0.837315 2023/05/24 07:50:48 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 07:50:48 - mmengine - INFO - Saving checkpoint at 2 epochs 2023/05/24 07:50:52 - mmengine - INFO - Evaluating NME... 2023/05/24 07:50:52 - mmengine - INFO - Epoch(val) [2][16/16] NME: 0.057970 data_time: 0.021018 time: 0.255080 2023/05/24 07:50:52 - mmengine - INFO - The previous best checkpoint /root/mmpose/projects/skps/work_dirs/td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256/best_NME_epoch_1.pth is removed 2023/05/24 07:50:53 - mmengine - INFO - The best checkpoint with 0.0580 NME at 2 epoch is saved to best_NME_epoch_2.pth. 2023/05/24 07:51:06 - mmengine - INFO - Epoch(train) [3][50/85] lr: 8.788778e-04 eta: 1:02:07 time: 0.264465 data_time: 0.031051 memory: 1767 loss: 0.045977 loss/heatmap: 0.019154 loss/offside: 0.026823 acc_pose: 0.874117 2023/05/24 07:51:15 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 07:51:15 - mmengine - INFO - Saving checkpoint at 3 epochs 2023/05/24 07:51:20 - mmengine - INFO - Evaluating NME... 2023/05/24 07:51:20 - mmengine - INFO - Epoch(val) [3][16/16] NME: 0.043969 data_time: 0.017952 time: 0.248856 2023/05/24 07:51:20 - mmengine - INFO - The previous best checkpoint /root/mmpose/projects/skps/work_dirs/td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256/best_NME_epoch_2.pth is removed 2023/05/24 07:51:21 - mmengine - INFO - The best checkpoint with 0.0440 NME at 3 epoch is saved to best_NME_epoch_3.pth. 2023/05/24 07:51:34 - mmengine - INFO - Epoch(train) [4][50/85] lr: 1.219218e-03 eta: 1:00:32 time: 0.261031 data_time: 0.028420 memory: 1767 loss: 0.041556 loss/heatmap: 0.017117 loss/offside: 0.024439 acc_pose: 0.888760 2023/05/24 07:51:43 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 07:51:43 - mmengine - INFO - Saving checkpoint at 4 epochs 2023/05/24 07:51:48 - mmengine - INFO - Evaluating NME... 2023/05/24 07:51:48 - mmengine - INFO - Epoch(val) [4][16/16] NME: 0.043338 data_time: 0.017980 time: 0.245051 2023/05/24 07:51:48 - mmengine - INFO - The previous best checkpoint /root/mmpose/projects/skps/work_dirs/td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256/best_NME_epoch_3.pth is removed 2023/05/24 07:51:48 - mmengine - INFO - The best checkpoint with 0.0433 NME at 4 epoch is saved to best_NME_epoch_4.pth. 2023/05/24 07:52:01 - mmengine - INFO - Epoch(train) [5][50/85] lr: 1.559559e-03 eta: 0:59:35 time: 0.262537 data_time: 0.030183 memory: 1767 loss: 0.039663 loss/heatmap: 0.016230 loss/offside: 0.023433 acc_pose: 0.801573 2023/05/24 07:52:10 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 07:52:10 - mmengine - INFO - Saving checkpoint at 5 epochs 2023/05/24 07:52:15 - mmengine - INFO - Evaluating NME... 2023/05/24 07:52:15 - mmengine - INFO - Epoch(val) [5][16/16] NME: 0.041108 data_time: 0.017625 time: 0.243395 2023/05/24 07:52:15 - mmengine - INFO - The previous best checkpoint /root/mmpose/projects/skps/work_dirs/td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256/best_NME_epoch_4.pth is removed 2023/05/24 07:52:16 - mmengine - INFO - The best checkpoint with 0.0411 NME at 5 epoch is saved to best_NME_epoch_5.pth. 2023/05/24 07:52:29 - mmengine - INFO - Epoch(train) [6][50/85] lr: 1.899900e-03 eta: 0:58:49 time: 0.261826 data_time: 0.029336 memory: 1767 loss: 0.039429 loss/heatmap: 0.016055 loss/offside: 0.023374 acc_pose: 0.884195 2023/05/24 07:52:38 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 07:52:38 - mmengine - INFO - Saving checkpoint at 6 epochs 2023/05/24 07:52:43 - mmengine - INFO - Evaluating NME... 2023/05/24 07:52:43 - mmengine - INFO - Epoch(val) [6][16/16] NME: 0.040975 data_time: 0.017326 time: 0.256105 2023/05/24 07:52:43 - mmengine - INFO - The previous best checkpoint /root/mmpose/projects/skps/work_dirs/td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256/best_NME_epoch_5.pth is removed 2023/05/24 07:52:43 - mmengine - INFO - The best checkpoint with 0.0410 NME at 6 epoch is saved to best_NME_epoch_6.pth. 2023/05/24 07:52:56 - mmengine - INFO - Epoch(train) [7][50/85] lr: 2.000000e-03 eta: 0:58:09 time: 0.260398 data_time: 0.027821 memory: 1767 loss: 0.037419 loss/heatmap: 0.014973 loss/offside: 0.022446 acc_pose: 0.935057 2023/05/24 07:53:05 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 07:53:05 - mmengine - INFO - Saving checkpoint at 7 epochs 2023/05/24 07:53:10 - mmengine - INFO - Evaluating NME... 2023/05/24 07:53:10 - mmengine - INFO - Epoch(val) [7][16/16] NME: 0.043520 data_time: 0.017208 time: 0.250176 2023/05/24 07:53:23 - mmengine - INFO - Epoch(train) [8][50/85] lr: 2.000000e-03 eta: 0:57:27 time: 0.261604 data_time: 0.028693 memory: 1767 loss: 0.036305 loss/heatmap: 0.014486 loss/offside: 0.021819 acc_pose: 0.931958 2023/05/24 07:53:32 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 07:53:32 - mmengine - INFO - Saving checkpoint at 8 epochs 2023/05/24 07:53:36 - mmengine - INFO - Evaluating NME... 2023/05/24 07:53:36 - mmengine - INFO - Epoch(val) [8][16/16] NME: 0.039654 data_time: 0.017272 time: 0.248834 2023/05/24 07:53:36 - mmengine - INFO - The previous best checkpoint /root/mmpose/projects/skps/work_dirs/td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256/best_NME_epoch_6.pth is removed 2023/05/24 07:53:37 - mmengine - INFO - The best checkpoint with 0.0397 NME at 8 epoch is saved to best_NME_epoch_8.pth. 2023/05/24 07:53:50 - mmengine - INFO - Epoch(train) [9][50/85] lr: 2.000000e-03 eta: 0:56:49 time: 0.258419 data_time: 0.028221 memory: 1767 loss: 0.035655 loss/heatmap: 0.014081 loss/offside: 0.021574 acc_pose: 0.942611 2023/05/24 07:53:59 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 07:53:59 - mmengine - INFO - Saving checkpoint at 9 epochs 2023/05/24 07:54:04 - mmengine - INFO - Evaluating NME... 2023/05/24 07:54:04 - mmengine - INFO - Epoch(val) [9][16/16] NME: 0.040408 data_time: 0.016500 time: 0.247378 2023/05/24 07:54:17 - mmengine - INFO - Epoch(train) [10][50/85] lr: 2.000000e-03 eta: 0:56:20 time: 0.265252 data_time: 0.029568 memory: 1767 loss: 0.034279 loss/heatmap: 0.013471 loss/offside: 0.020809 acc_pose: 0.967672 2023/05/24 07:54:26 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 07:54:26 - mmengine - INFO - Saving checkpoint at 10 epochs 2023/05/24 07:54:31 - mmengine - INFO - Evaluating NME... 2023/05/24 07:54:31 - mmengine - INFO - Epoch(val) [10][16/16] NME: 0.036993 data_time: 0.017856 time: 0.246160 2023/05/24 07:54:31 - mmengine - INFO - The previous best checkpoint /root/mmpose/projects/skps/work_dirs/td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256/best_NME_epoch_8.pth is removed 2023/05/24 07:54:31 - mmengine - INFO - The best checkpoint with 0.0370 NME at 10 epoch is saved to best_NME_epoch_10.pth. 2023/05/24 07:54:44 - mmengine - INFO - Epoch(train) [11][50/85] lr: 2.000000e-03 eta: 0:55:50 time: 0.263162 data_time: 0.030137 memory: 1767 loss: 0.032056 loss/heatmap: 0.012509 loss/offside: 0.019546 acc_pose: 0.938732 2023/05/24 07:54:53 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 07:54:53 - mmengine - INFO - Saving checkpoint at 11 epochs 2023/05/24 07:54:58 - mmengine - INFO - Evaluating NME... 2023/05/24 07:54:58 - mmengine - INFO - Epoch(val) [11][16/16] NME: 0.036420 data_time: 0.019853 time: 0.247185 2023/05/24 07:54:58 - mmengine - INFO - The previous best checkpoint /root/mmpose/projects/skps/work_dirs/td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256/best_NME_epoch_10.pth is removed 2023/05/24 07:54:59 - mmengine - INFO - The best checkpoint with 0.0364 NME at 11 epoch is saved to best_NME_epoch_11.pth. 2023/05/24 07:55:12 - mmengine - INFO - Epoch(train) [12][50/85] lr: 2.000000e-03 eta: 0:55:25 time: 0.263351 data_time: 0.031532 memory: 1767 loss: 0.031909 loss/heatmap: 0.012470 loss/offside: 0.019439 acc_pose: 0.951355 2023/05/24 07:55:16 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 07:55:21 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 07:55:21 - mmengine - INFO - Saving checkpoint at 12 epochs 2023/05/24 07:55:25 - mmengine - INFO - Evaluating NME... 2023/05/24 07:55:25 - mmengine - INFO - Epoch(val) [12][16/16] NME: 0.038368 data_time: 0.016314 time: 0.243372 2023/05/24 07:55:39 - mmengine - INFO - Epoch(train) [13][50/85] lr: 2.000000e-03 eta: 0:55:05 time: 0.270631 data_time: 0.030762 memory: 1767 loss: 0.031752 loss/heatmap: 0.012306 loss/offside: 0.019445 acc_pose: 0.954454 2023/05/24 07:55:48 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 07:55:48 - mmengine - INFO - Saving checkpoint at 13 epochs 2023/05/24 07:55:53 - mmengine - INFO - Evaluating NME... 2023/05/24 07:55:53 - mmengine - INFO - Epoch(val) [13][16/16] NME: 0.039123 data_time: 0.017974 time: 0.243792 2023/05/24 07:56:06 - mmengine - INFO - Epoch(train) [14][50/85] lr: 2.000000e-03 eta: 0:54:38 time: 0.261894 data_time: 0.030583 memory: 1767 loss: 0.032286 loss/heatmap: 0.012523 loss/offside: 0.019762 acc_pose: 0.960422 2023/05/24 07:56:15 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 07:56:15 - mmengine - INFO - Saving checkpoint at 14 epochs 2023/05/24 07:56:20 - mmengine - INFO - Evaluating NME... 2023/05/24 07:56:20 - mmengine - INFO - Epoch(val) [14][16/16] NME: 0.036783 data_time: 0.017282 time: 0.252801 2023/05/24 07:56:33 - mmengine - INFO - Epoch(train) [15][50/85] lr: 2.000000e-03 eta: 0:54:17 time: 0.267975 data_time: 0.029806 memory: 1767 loss: 0.030859 loss/heatmap: 0.012000 loss/offside: 0.018859 acc_pose: 0.934298 2023/05/24 07:56:42 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 07:56:42 - mmengine - INFO - Saving checkpoint at 15 epochs 2023/05/24 07:56:47 - mmengine - INFO - Evaluating NME... 2023/05/24 07:56:47 - mmengine - INFO - Epoch(val) [15][16/16] NME: 0.036356 data_time: 0.017227 time: 0.243437 2023/05/24 07:56:47 - mmengine - INFO - The previous best checkpoint /root/mmpose/projects/skps/work_dirs/td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256/best_NME_epoch_11.pth is removed 2023/05/24 07:56:47 - mmengine - INFO - The best checkpoint with 0.0364 NME at 15 epoch is saved to best_NME_epoch_15.pth. 2023/05/24 07:57:00 - mmengine - INFO - Epoch(train) [16][50/85] lr: 2.000000e-03 eta: 0:53:49 time: 0.261089 data_time: 0.028694 memory: 1767 loss: 0.031218 loss/heatmap: 0.012148 loss/offside: 0.019070 acc_pose: 0.930979 2023/05/24 07:57:09 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 07:57:09 - mmengine - INFO - Saving checkpoint at 16 epochs 2023/05/24 07:57:14 - mmengine - INFO - Evaluating NME... 2023/05/24 07:57:14 - mmengine - INFO - Epoch(val) [16][16/16] NME: 0.037009 data_time: 0.018730 time: 0.247121 2023/05/24 07:57:27 - mmengine - INFO - Epoch(train) [17][50/85] lr: 2.000000e-03 eta: 0:53:23 time: 0.262860 data_time: 0.029762 memory: 1767 loss: 0.029946 loss/heatmap: 0.011566 loss/offside: 0.018380 acc_pose: 0.934914 2023/05/24 07:57:36 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 07:57:36 - mmengine - INFO - Saving checkpoint at 17 epochs 2023/05/24 07:57:41 - mmengine - INFO - Evaluating NME... 2023/05/24 07:57:41 - mmengine - INFO - Epoch(val) [17][16/16] NME: 0.036806 data_time: 0.016651 time: 0.250113 2023/05/24 07:57:54 - mmengine - INFO - Epoch(train) [18][50/85] lr: 2.000000e-03 eta: 0:52:59 time: 0.264791 data_time: 0.029607 memory: 1767 loss: 0.029678 loss/heatmap: 0.011420 loss/offside: 0.018258 acc_pose: 0.929085 2023/05/24 07:58:03 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 07:58:03 - mmengine - INFO - Saving checkpoint at 18 epochs 2023/05/24 07:58:08 - mmengine - INFO - Evaluating NME... 2023/05/24 07:58:08 - mmengine - INFO - Epoch(val) [18][16/16] NME: 0.037081 data_time: 0.016402 time: 0.243835 2023/05/24 07:58:21 - mmengine - INFO - Epoch(train) [19][50/85] lr: 2.000000e-03 eta: 0:52:34 time: 0.259220 data_time: 0.029254 memory: 1767 loss: 0.029520 loss/heatmap: 0.011338 loss/offside: 0.018181 acc_pose: 0.971983 2023/05/24 07:58:30 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 07:58:30 - mmengine - INFO - Saving checkpoint at 19 epochs 2023/05/24 07:58:36 - mmengine - INFO - Evaluating NME... 2023/05/24 07:58:36 - mmengine - INFO - Epoch(val) [19][16/16] NME: 0.036903 data_time: 0.055213 time: 0.283102 2023/05/24 07:58:49 - mmengine - INFO - Epoch(train) [20][50/85] lr: 2.000000e-03 eta: 0:52:10 time: 0.261061 data_time: 0.028260 memory: 1767 loss: 0.031729 loss/heatmap: 0.012361 loss/offside: 0.019368 acc_pose: 0.932328 2023/05/24 07:58:57 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 07:58:57 - mmengine - INFO - Saving checkpoint at 20 epochs 2023/05/24 07:59:02 - mmengine - INFO - Evaluating NME... 2023/05/24 07:59:02 - mmengine - INFO - Epoch(val) [20][16/16] NME: 0.038395 data_time: 0.017371 time: 0.242824 2023/05/24 07:59:15 - mmengine - INFO - Epoch(train) [21][50/85] lr: 2.000000e-03 eta: 0:51:46 time: 0.263525 data_time: 0.029896 memory: 1767 loss: 0.029866 loss/heatmap: 0.011512 loss/offside: 0.018354 acc_pose: 0.956137 2023/05/24 07:59:24 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 07:59:24 - mmengine - INFO - Saving checkpoint at 21 epochs 2023/05/24 07:59:29 - mmengine - INFO - Evaluating NME... 2023/05/24 07:59:29 - mmengine - INFO - Epoch(val) [21][16/16] NME: 0.037154 data_time: 0.017505 time: 0.251227 2023/05/24 07:59:42 - mmengine - INFO - Epoch(train) [22][50/85] lr: 2.000000e-03 eta: 0:51:24 time: 0.265547 data_time: 0.031128 memory: 1767 loss: 0.029313 loss/heatmap: 0.011258 loss/offside: 0.018055 acc_pose: 0.960468 2023/05/24 07:59:51 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 07:59:51 - mmengine - INFO - Saving checkpoint at 22 epochs 2023/05/24 07:59:56 - mmengine - INFO - Evaluating NME... 2023/05/24 07:59:56 - mmengine - INFO - Epoch(val) [22][16/16] NME: 0.036212 data_time: 0.016577 time: 0.244081 2023/05/24 07:59:56 - mmengine - INFO - The previous best checkpoint /root/mmpose/projects/skps/work_dirs/td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256/best_NME_epoch_15.pth is removed 2023/05/24 07:59:57 - mmengine - INFO - The best checkpoint with 0.0362 NME at 22 epoch is saved to best_NME_epoch_22.pth. 2023/05/24 08:00:10 - mmengine - INFO - Epoch(train) [23][50/85] lr: 2.000000e-03 eta: 0:50:59 time: 0.260922 data_time: 0.028530 memory: 1767 loss: 0.028869 loss/heatmap: 0.011056 loss/offside: 0.017813 acc_pose: 0.909195 2023/05/24 08:00:19 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:00:19 - mmengine - INFO - Saving checkpoint at 23 epochs 2023/05/24 08:00:24 - mmengine - INFO - Evaluating NME... 2023/05/24 08:00:24 - mmengine - INFO - Epoch(val) [23][16/16] NME: 0.035064 data_time: 0.017262 time: 0.250013 2023/05/24 08:00:24 - mmengine - INFO - The previous best checkpoint /root/mmpose/projects/skps/work_dirs/td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256/best_NME_epoch_22.pth is removed 2023/05/24 08:00:24 - mmengine - INFO - The best checkpoint with 0.0351 NME at 23 epoch is saved to best_NME_epoch_23.pth. 2023/05/24 08:00:37 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:00:38 - mmengine - INFO - Epoch(train) [24][50/85] lr: 2.000000e-03 eta: 0:50:40 time: 0.270925 data_time: 0.031056 memory: 1767 loss: 0.028341 loss/heatmap: 0.010884 loss/offside: 0.017457 acc_pose: 0.916892 2023/05/24 08:00:47 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:00:47 - mmengine - INFO - Saving checkpoint at 24 epochs 2023/05/24 08:00:52 - mmengine - INFO - Evaluating NME... 2023/05/24 08:00:52 - mmengine - INFO - Epoch(val) [24][16/16] NME: 0.035369 data_time: 0.016785 time: 0.245015 2023/05/24 08:01:05 - mmengine - INFO - Epoch(train) [25][50/85] lr: 2.000000e-03 eta: 0:50:17 time: 0.265574 data_time: 0.029369 memory: 1767 loss: 0.030055 loss/heatmap: 0.011661 loss/offside: 0.018394 acc_pose: 0.975862 2023/05/24 08:01:14 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:01:14 - mmengine - INFO - Saving checkpoint at 25 epochs 2023/05/24 08:01:19 - mmengine - INFO - Evaluating NME... 2023/05/24 08:01:19 - mmengine - INFO - Epoch(val) [25][16/16] NME: 0.037593 data_time: 0.016828 time: 0.244279 2023/05/24 08:01:32 - mmengine - INFO - Epoch(train) [26][50/85] lr: 2.000000e-03 eta: 0:49:56 time: 0.274140 data_time: 0.030477 memory: 1767 loss: 0.029102 loss/heatmap: 0.011111 loss/offside: 0.017990 acc_pose: 0.938727 2023/05/24 08:01:41 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:01:41 - mmengine - INFO - Saving checkpoint at 26 epochs 2023/05/24 08:01:46 - mmengine - INFO - Evaluating NME... 2023/05/24 08:01:46 - mmengine - INFO - Epoch(val) [26][16/16] NME: 0.036170 data_time: 0.016629 time: 0.248405 2023/05/24 08:02:00 - mmengine - INFO - Epoch(train) [27][50/85] lr: 2.000000e-03 eta: 0:49:35 time: 0.271762 data_time: 0.030320 memory: 1767 loss: 0.030931 loss/heatmap: 0.011963 loss/offside: 0.018967 acc_pose: 0.957062 2023/05/24 08:02:09 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:02:09 - mmengine - INFO - Saving checkpoint at 27 epochs 2023/05/24 08:02:14 - mmengine - INFO - Evaluating NME... 2023/05/24 08:02:14 - mmengine - INFO - Epoch(val) [27][16/16] NME: 0.035820 data_time: 0.017723 time: 0.247123 2023/05/24 08:02:27 - mmengine - INFO - Epoch(train) [28][50/85] lr: 2.000000e-03 eta: 0:49:13 time: 0.261481 data_time: 0.029050 memory: 1767 loss: 0.029368 loss/heatmap: 0.011270 loss/offside: 0.018098 acc_pose: 0.936074 2023/05/24 08:02:36 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:02:36 - mmengine - INFO - Saving checkpoint at 28 epochs 2023/05/24 08:02:41 - mmengine - INFO - Evaluating NME... 2023/05/24 08:02:41 - mmengine - INFO - Epoch(val) [28][16/16] NME: 0.034836 data_time: 0.018347 time: 0.248969 2023/05/24 08:02:41 - mmengine - INFO - The previous best checkpoint /root/mmpose/projects/skps/work_dirs/td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256/best_NME_epoch_23.pth is removed 2023/05/24 08:02:42 - mmengine - INFO - The best checkpoint with 0.0348 NME at 28 epoch is saved to best_NME_epoch_28.pth. 2023/05/24 08:02:55 - mmengine - INFO - Epoch(train) [29][50/85] lr: 2.000000e-03 eta: 0:48:51 time: 0.266046 data_time: 0.030714 memory: 1767 loss: 0.029629 loss/heatmap: 0.011455 loss/offside: 0.018174 acc_pose: 0.935550 2023/05/24 08:03:04 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:03:04 - mmengine - INFO - Saving checkpoint at 29 epochs 2023/05/24 08:03:09 - mmengine - INFO - Evaluating NME... 2023/05/24 08:03:09 - mmengine - INFO - Epoch(val) [29][16/16] NME: 0.035471 data_time: 0.017288 time: 0.241797 2023/05/24 08:03:22 - mmengine - INFO - Epoch(train) [30][50/85] lr: 2.000000e-03 eta: 0:48:29 time: 0.271462 data_time: 0.032158 memory: 1767 loss: 0.027946 loss/heatmap: 0.010591 loss/offside: 0.017356 acc_pose: 0.967672 2023/05/24 08:03:31 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:03:31 - mmengine - INFO - Saving checkpoint at 30 epochs 2023/05/24 08:03:36 - mmengine - INFO - Evaluating NME... 2023/05/24 08:03:36 - mmengine - INFO - Epoch(val) [30][16/16] NME: 0.036434 data_time: 0.017706 time: 0.256984 2023/05/24 08:03:49 - mmengine - INFO - Epoch(train) [31][50/85] lr: 2.000000e-03 eta: 0:48:07 time: 0.267161 data_time: 0.032167 memory: 1767 loss: 0.028134 loss/heatmap: 0.010763 loss/offside: 0.017370 acc_pose: 0.969068 2023/05/24 08:03:58 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:03:58 - mmengine - INFO - Saving checkpoint at 31 epochs 2023/05/24 08:04:03 - mmengine - INFO - Evaluating NME... 2023/05/24 08:04:03 - mmengine - INFO - Epoch(val) [31][16/16] NME: 0.035091 data_time: 0.017174 time: 0.242628 2023/05/24 08:04:17 - mmengine - INFO - Epoch(train) [32][50/85] lr: 2.000000e-03 eta: 0:47:45 time: 0.269312 data_time: 0.030794 memory: 1767 loss: 0.027956 loss/heatmap: 0.010627 loss/offside: 0.017329 acc_pose: 0.906404 2023/05/24 08:04:26 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:04:26 - mmengine - INFO - Saving checkpoint at 32 epochs 2023/05/24 08:04:31 - mmengine - INFO - Evaluating NME... 2023/05/24 08:04:31 - mmengine - INFO - Epoch(val) [32][16/16] NME: 0.036891 data_time: 0.017591 time: 0.245754 2023/05/24 08:04:44 - mmengine - INFO - Epoch(train) [33][50/85] lr: 2.000000e-03 eta: 0:47:23 time: 0.265583 data_time: 0.029471 memory: 1767 loss: 0.028269 loss/heatmap: 0.010736 loss/offside: 0.017532 acc_pose: 0.916678 2023/05/24 08:04:53 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:04:53 - mmengine - INFO - Saving checkpoint at 33 epochs 2023/05/24 08:04:58 - mmengine - INFO - Evaluating NME... 2023/05/24 08:04:58 - mmengine - INFO - Epoch(val) [33][16/16] NME: 0.035704 data_time: 0.017819 time: 0.241455 2023/05/24 08:05:11 - mmengine - INFO - Epoch(train) [34][50/85] lr: 2.000000e-03 eta: 0:47:01 time: 0.267483 data_time: 0.031441 memory: 1767 loss: 0.026925 loss/heatmap: 0.010162 loss/offside: 0.016763 acc_pose: 0.978305 2023/05/24 08:05:20 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:05:20 - mmengine - INFO - Saving checkpoint at 34 epochs 2023/05/24 08:05:25 - mmengine - INFO - Evaluating NME... 2023/05/24 08:05:25 - mmengine - INFO - Epoch(val) [34][16/16] NME: 0.035097 data_time: 0.017206 time: 0.261030 2023/05/24 08:05:39 - mmengine - INFO - Epoch(train) [35][50/85] lr: 2.000000e-03 eta: 0:46:40 time: 0.268086 data_time: 0.030286 memory: 1767 loss: 0.027197 loss/heatmap: 0.010294 loss/offside: 0.016903 acc_pose: 0.862224 2023/05/24 08:05:48 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:05:48 - mmengine - INFO - Saving checkpoint at 35 epochs 2023/05/24 08:05:53 - mmengine - INFO - Evaluating NME... 2023/05/24 08:05:53 - mmengine - INFO - Epoch(val) [35][16/16] NME: 0.034486 data_time: 0.016426 time: 0.247443 2023/05/24 08:05:53 - mmengine - INFO - The previous best checkpoint /root/mmpose/projects/skps/work_dirs/td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256/best_NME_epoch_28.pth is removed 2023/05/24 08:05:53 - mmengine - INFO - The best checkpoint with 0.0345 NME at 35 epoch is saved to best_NME_epoch_35.pth. 2023/05/24 08:06:00 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:06:06 - mmengine - INFO - Epoch(train) [36][50/85] lr: 2.000000e-03 eta: 0:46:17 time: 0.265698 data_time: 0.030138 memory: 1767 loss: 0.026593 loss/heatmap: 0.010030 loss/offside: 0.016563 acc_pose: 0.973994 2023/05/24 08:06:16 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:06:16 - mmengine - INFO - Saving checkpoint at 36 epochs 2023/05/24 08:06:21 - mmengine - INFO - Evaluating NME... 2023/05/24 08:06:21 - mmengine - INFO - Epoch(val) [36][16/16] NME: 0.034833 data_time: 0.017464 time: 0.255891 2023/05/24 08:06:34 - mmengine - INFO - Epoch(train) [37][50/85] lr: 2.000000e-03 eta: 0:45:56 time: 0.270575 data_time: 0.029170 memory: 1767 loss: 0.025939 loss/heatmap: 0.009777 loss/offside: 0.016163 acc_pose: 0.975985 2023/05/24 08:06:43 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:06:43 - mmengine - INFO - Saving checkpoint at 37 epochs 2023/05/24 08:06:48 - mmengine - INFO - Evaluating NME... 2023/05/24 08:06:48 - mmengine - INFO - Epoch(val) [37][16/16] NME: 0.035778 data_time: 0.016630 time: 0.260108 2023/05/24 08:07:02 - mmengine - INFO - Epoch(train) [38][50/85] lr: 2.000000e-03 eta: 0:45:33 time: 0.262041 data_time: 0.030236 memory: 1767 loss: 0.025805 loss/heatmap: 0.009692 loss/offside: 0.016113 acc_pose: 0.954454 2023/05/24 08:07:10 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:07:10 - mmengine - INFO - Saving checkpoint at 38 epochs 2023/05/24 08:07:15 - mmengine - INFO - Evaluating NME... 2023/05/24 08:07:15 - mmengine - INFO - Epoch(val) [38][16/16] NME: 0.033189 data_time: 0.016249 time: 0.252381 2023/05/24 08:07:15 - mmengine - INFO - The previous best checkpoint /root/mmpose/projects/skps/work_dirs/td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256/best_NME_epoch_35.pth is removed 2023/05/24 08:07:16 - mmengine - INFO - The best checkpoint with 0.0332 NME at 38 epoch is saved to best_NME_epoch_38.pth. 2023/05/24 08:07:29 - mmengine - INFO - Epoch(train) [39][50/85] lr: 2.000000e-03 eta: 0:45:09 time: 0.265929 data_time: 0.030458 memory: 1767 loss: 0.026430 loss/heatmap: 0.009966 loss/offside: 0.016464 acc_pose: 0.933046 2023/05/24 08:07:38 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:07:38 - mmengine - INFO - Saving checkpoint at 39 epochs 2023/05/24 08:07:43 - mmengine - INFO - Evaluating NME... 2023/05/24 08:07:43 - mmengine - INFO - Epoch(val) [39][16/16] NME: 0.035097 data_time: 0.016653 time: 0.250858 2023/05/24 08:07:57 - mmengine - INFO - Epoch(train) [40][50/85] lr: 2.000000e-03 eta: 0:44:48 time: 0.275388 data_time: 0.030612 memory: 1767 loss: 0.026611 loss/heatmap: 0.010038 loss/offside: 0.016573 acc_pose: 0.955665 2023/05/24 08:08:06 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:08:06 - mmengine - INFO - Saving checkpoint at 40 epochs 2023/05/24 08:08:11 - mmengine - INFO - Evaluating NME... 2023/05/24 08:08:11 - mmengine - INFO - Epoch(val) [40][16/16] NME: 0.035123 data_time: 0.018134 time: 0.249608 2023/05/24 08:08:24 - mmengine - INFO - Epoch(train) [41][50/85] lr: 2.000000e-03 eta: 0:44:26 time: 0.269394 data_time: 0.030731 memory: 1767 loss: 0.028944 loss/heatmap: 0.011197 loss/offside: 0.017747 acc_pose: 0.958436 2023/05/24 08:08:34 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:08:34 - mmengine - INFO - Saving checkpoint at 41 epochs 2023/05/24 08:08:38 - mmengine - INFO - Evaluating NME... 2023/05/24 08:08:38 - mmengine - INFO - Epoch(val) [41][16/16] NME: 0.037122 data_time: 0.016900 time: 0.252883 2023/05/24 08:08:52 - mmengine - INFO - Epoch(train) [42][50/85] lr: 2.000000e-03 eta: 0:44:05 time: 0.274142 data_time: 0.033864 memory: 1767 loss: 0.029304 loss/heatmap: 0.011216 loss/offside: 0.018088 acc_pose: 0.976293 2023/05/24 08:09:01 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:09:01 - mmengine - INFO - Saving checkpoint at 42 epochs 2023/05/24 08:09:06 - mmengine - INFO - Evaluating NME... 2023/05/24 08:09:06 - mmengine - INFO - Epoch(val) [42][16/16] NME: 0.033781 data_time: 0.017027 time: 0.243803 2023/05/24 08:09:19 - mmengine - INFO - Epoch(train) [43][50/85] lr: 2.000000e-03 eta: 0:43:42 time: 0.262606 data_time: 0.029934 memory: 1767 loss: 0.027134 loss/heatmap: 0.010253 loss/offside: 0.016882 acc_pose: 0.946983 2023/05/24 08:09:28 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:09:28 - mmengine - INFO - Saving checkpoint at 43 epochs 2023/05/24 08:09:33 - mmengine - INFO - Evaluating NME... 2023/05/24 08:09:33 - mmengine - INFO - Epoch(val) [43][16/16] NME: 0.034175 data_time: 0.016924 time: 0.248066 2023/05/24 08:09:46 - mmengine - INFO - Epoch(train) [44][50/85] lr: 2.000000e-03 eta: 0:43:20 time: 0.272137 data_time: 0.030354 memory: 1767 loss: 0.027074 loss/heatmap: 0.010263 loss/offside: 0.016811 acc_pose: 0.981999 2023/05/24 08:09:56 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:09:56 - mmengine - INFO - Saving checkpoint at 44 epochs 2023/05/24 08:10:00 - mmengine - INFO - Evaluating NME... 2023/05/24 08:10:00 - mmengine - INFO - Epoch(val) [44][16/16] NME: 0.034401 data_time: 0.016309 time: 0.242757 2023/05/24 08:10:14 - mmengine - INFO - Epoch(train) [45][50/85] lr: 2.000000e-03 eta: 0:42:58 time: 0.265547 data_time: 0.031246 memory: 1767 loss: 0.025986 loss/heatmap: 0.009870 loss/offside: 0.016116 acc_pose: 0.977730 2023/05/24 08:10:23 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:10:23 - mmengine - INFO - Saving checkpoint at 45 epochs 2023/05/24 08:10:28 - mmengine - INFO - Evaluating NME... 2023/05/24 08:10:28 - mmengine - INFO - Epoch(val) [45][16/16] NME: 0.034147 data_time: 0.017409 time: 0.249099 2023/05/24 08:10:41 - mmengine - INFO - Epoch(train) [46][50/85] lr: 2.000000e-03 eta: 0:42:36 time: 0.271938 data_time: 0.030597 memory: 1767 loss: 0.025422 loss/heatmap: 0.009537 loss/offside: 0.015884 acc_pose: 0.963218 2023/05/24 08:10:50 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:10:50 - mmengine - INFO - Saving checkpoint at 46 epochs 2023/05/24 08:10:56 - mmengine - INFO - Evaluating NME... 2023/05/24 08:10:56 - mmengine - INFO - Epoch(val) [46][16/16] NME: 0.033420 data_time: 0.017979 time: 0.260311 2023/05/24 08:11:09 - mmengine - INFO - Epoch(train) [47][50/85] lr: 2.000000e-03 eta: 0:42:15 time: 0.272706 data_time: 0.031483 memory: 1767 loss: 0.025466 loss/heatmap: 0.009559 loss/offside: 0.015907 acc_pose: 0.949672 2023/05/24 08:11:18 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:11:18 - mmengine - INFO - Saving checkpoint at 47 epochs 2023/05/24 08:11:23 - mmengine - INFO - Evaluating NME... 2023/05/24 08:11:23 - mmengine - INFO - Epoch(val) [47][16/16] NME: 0.033413 data_time: 0.018391 time: 0.257322 2023/05/24 08:11:25 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:11:37 - mmengine - INFO - Epoch(train) [48][50/85] lr: 2.000000e-03 eta: 0:41:54 time: 0.270090 data_time: 0.029597 memory: 1767 loss: 0.026037 loss/heatmap: 0.009812 loss/offside: 0.016226 acc_pose: 0.954598 2023/05/24 08:11:46 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:11:46 - mmengine - INFO - Saving checkpoint at 48 epochs 2023/05/24 08:11:51 - mmengine - INFO - Evaluating NME... 2023/05/24 08:11:51 - mmengine - INFO - Epoch(val) [48][16/16] NME: 0.033920 data_time: 0.016932 time: 0.246967 2023/05/24 08:12:04 - mmengine - INFO - Epoch(train) [49][50/85] lr: 2.000000e-03 eta: 0:41:31 time: 0.263977 data_time: 0.030583 memory: 1767 loss: 0.026092 loss/heatmap: 0.009881 loss/offside: 0.016211 acc_pose: 0.981835 2023/05/24 08:12:13 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:12:13 - mmengine - INFO - Saving checkpoint at 49 epochs 2023/05/24 08:12:18 - mmengine - INFO - Evaluating NME... 2023/05/24 08:12:18 - mmengine - INFO - Epoch(val) [49][16/16] NME: 0.034097 data_time: 0.016494 time: 0.242774 2023/05/24 08:12:31 - mmengine - INFO - Epoch(train) [50][50/85] lr: 2.000000e-03 eta: 0:41:09 time: 0.268647 data_time: 0.033690 memory: 1767 loss: 0.025388 loss/heatmap: 0.009497 loss/offside: 0.015891 acc_pose: 0.962865 2023/05/24 08:12:40 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:12:40 - mmengine - INFO - Saving checkpoint at 50 epochs 2023/05/24 08:12:45 - mmengine - INFO - Evaluating NME... 2023/05/24 08:12:45 - mmengine - INFO - Epoch(val) [50][16/16] NME: 0.033324 data_time: 0.017073 time: 0.248117 2023/05/24 08:12:58 - mmengine - INFO - Epoch(train) [51][50/85] lr: 2.000000e-03 eta: 0:40:46 time: 0.263098 data_time: 0.030694 memory: 1767 loss: 0.024507 loss/heatmap: 0.009137 loss/offside: 0.015369 acc_pose: 0.931876 2023/05/24 08:13:08 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:13:08 - mmengine - INFO - Saving checkpoint at 51 epochs 2023/05/24 08:13:13 - mmengine - INFO - Evaluating NME... 2023/05/24 08:13:13 - mmengine - INFO - Epoch(val) [51][16/16] NME: 0.034749 data_time: 0.026604 time: 0.264498 2023/05/24 08:13:26 - mmengine - INFO - Epoch(train) [52][50/85] lr: 2.000000e-03 eta: 0:40:24 time: 0.266638 data_time: 0.030799 memory: 1767 loss: 0.026246 loss/heatmap: 0.009941 loss/offside: 0.016306 acc_pose: 0.965020 2023/05/24 08:13:35 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:13:35 - mmengine - INFO - Saving checkpoint at 52 epochs 2023/05/24 08:13:40 - mmengine - INFO - Evaluating NME... 2023/05/24 08:13:40 - mmengine - INFO - Epoch(val) [52][16/16] NME: 0.033503 data_time: 0.018113 time: 0.254820 2023/05/24 08:13:53 - mmengine - INFO - Epoch(train) [53][50/85] lr: 2.000000e-03 eta: 0:40:01 time: 0.265638 data_time: 0.030286 memory: 1767 loss: 0.025190 loss/heatmap: 0.009434 loss/offside: 0.015756 acc_pose: 0.977951 2023/05/24 08:14:02 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:14:02 - mmengine - INFO - Saving checkpoint at 53 epochs 2023/05/24 08:14:07 - mmengine - INFO - Evaluating NME... 2023/05/24 08:14:07 - mmengine - INFO - Epoch(val) [53][16/16] NME: 0.034722 data_time: 0.016661 time: 0.244603 2023/05/24 08:14:21 - mmengine - INFO - Epoch(train) [54][50/85] lr: 2.000000e-03 eta: 0:39:39 time: 0.268383 data_time: 0.029208 memory: 1767 loss: 0.024889 loss/heatmap: 0.009352 loss/offside: 0.015537 acc_pose: 0.941523 2023/05/24 08:14:30 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:14:30 - mmengine - INFO - Saving checkpoint at 54 epochs 2023/05/24 08:14:35 - mmengine - INFO - Evaluating NME... 2023/05/24 08:14:35 - mmengine - INFO - Epoch(val) [54][16/16] NME: 0.034354 data_time: 0.016697 time: 0.253323 2023/05/24 08:14:48 - mmengine - INFO - Epoch(train) [55][50/85] lr: 2.000000e-03 eta: 0:39:18 time: 0.272151 data_time: 0.033169 memory: 1767 loss: 0.026325 loss/heatmap: 0.010034 loss/offside: 0.016291 acc_pose: 0.969540 2023/05/24 08:14:58 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:14:58 - mmengine - INFO - Saving checkpoint at 55 epochs 2023/05/24 08:15:02 - mmengine - INFO - Evaluating NME... 2023/05/24 08:15:02 - mmengine - INFO - Epoch(val) [55][16/16] NME: 0.035294 data_time: 0.016797 time: 0.241021 2023/05/24 08:15:16 - mmengine - INFO - Epoch(train) [56][50/85] lr: 2.000000e-03 eta: 0:38:56 time: 0.268548 data_time: 0.032671 memory: 1767 loss: 0.025774 loss/heatmap: 0.009727 loss/offside: 0.016047 acc_pose: 0.928571 2023/05/24 08:15:25 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:15:25 - mmengine - INFO - Saving checkpoint at 56 epochs 2023/05/24 08:15:30 - mmengine - INFO - Evaluating NME... 2023/05/24 08:15:30 - mmengine - INFO - Epoch(val) [56][16/16] NME: 0.034151 data_time: 0.017350 time: 0.246061 2023/05/24 08:15:43 - mmengine - INFO - Epoch(train) [57][50/85] lr: 2.000000e-03 eta: 0:38:33 time: 0.266062 data_time: 0.030843 memory: 1767 loss: 0.025904 loss/heatmap: 0.009705 loss/offside: 0.016199 acc_pose: 0.982184 2023/05/24 08:15:52 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:15:52 - mmengine - INFO - Saving checkpoint at 57 epochs 2023/05/24 08:15:57 - mmengine - INFO - Evaluating NME... 2023/05/24 08:15:57 - mmengine - INFO - Epoch(val) [57][16/16] NME: 0.034298 data_time: 0.017511 time: 0.248498 2023/05/24 08:16:10 - mmengine - INFO - Epoch(train) [58][50/85] lr: 2.000000e-03 eta: 0:38:11 time: 0.266828 data_time: 0.031510 memory: 1767 loss: 0.024977 loss/heatmap: 0.009400 loss/offside: 0.015577 acc_pose: 0.971367 2023/05/24 08:16:20 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:16:20 - mmengine - INFO - Saving checkpoint at 58 epochs 2023/05/24 08:16:24 - mmengine - INFO - Evaluating NME... 2023/05/24 08:16:24 - mmengine - INFO - Epoch(val) [58][16/16] NME: 0.033807 data_time: 0.017822 time: 0.246520 2023/05/24 08:16:38 - mmengine - INFO - Epoch(train) [59][50/85] lr: 2.000000e-03 eta: 0:37:50 time: 0.272874 data_time: 0.030773 memory: 1767 loss: 0.024623 loss/heatmap: 0.009232 loss/offside: 0.015390 acc_pose: 0.978161 2023/05/24 08:16:43 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:16:47 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:16:47 - mmengine - INFO - Saving checkpoint at 59 epochs 2023/05/24 08:16:52 - mmengine - INFO - Evaluating NME... 2023/05/24 08:16:52 - mmengine - INFO - Epoch(val) [59][16/16] NME: 0.033721 data_time: 0.017896 time: 0.251061 2023/05/24 08:17:06 - mmengine - INFO - Epoch(train) [60][50/85] lr: 2.000000e-03 eta: 0:37:28 time: 0.271747 data_time: 0.031334 memory: 1767 loss: 0.023819 loss/heatmap: 0.008903 loss/offside: 0.014916 acc_pose: 0.974334 2023/05/24 08:17:15 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:17:15 - mmengine - INFO - Saving checkpoint at 60 epochs 2023/05/24 08:17:20 - mmengine - INFO - Evaluating NME... 2023/05/24 08:17:20 - mmengine - INFO - Epoch(val) [60][16/16] NME: 0.034203 data_time: 0.017985 time: 0.245366 2023/05/24 08:17:33 - mmengine - INFO - Epoch(train) [61][50/85] lr: 2.000000e-03 eta: 0:37:06 time: 0.267038 data_time: 0.031549 memory: 1767 loss: 0.024285 loss/heatmap: 0.009112 loss/offside: 0.015172 acc_pose: 0.967529 2023/05/24 08:17:42 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:17:42 - mmengine - INFO - Saving checkpoint at 61 epochs 2023/05/24 08:17:47 - mmengine - INFO - Evaluating NME... 2023/05/24 08:17:47 - mmengine - INFO - Epoch(val) [61][16/16] NME: 0.033992 data_time: 0.017812 time: 0.251337 2023/05/24 08:18:01 - mmengine - INFO - Epoch(train) [62][50/85] lr: 2.000000e-03 eta: 0:36:44 time: 0.270787 data_time: 0.034244 memory: 1767 loss: 0.024497 loss/heatmap: 0.009138 loss/offside: 0.015359 acc_pose: 0.976006 2023/05/24 08:18:10 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:18:10 - mmengine - INFO - Saving checkpoint at 62 epochs 2023/05/24 08:18:15 - mmengine - INFO - Evaluating NME... 2023/05/24 08:18:15 - mmengine - INFO - Epoch(val) [62][16/16] NME: 0.033854 data_time: 0.017996 time: 0.250068 2023/05/24 08:18:28 - mmengine - INFO - Epoch(train) [63][50/85] lr: 2.000000e-03 eta: 0:36:21 time: 0.264446 data_time: 0.030571 memory: 1767 loss: 0.024307 loss/heatmap: 0.009077 loss/offside: 0.015230 acc_pose: 0.980008 2023/05/24 08:18:37 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:18:37 - mmengine - INFO - Saving checkpoint at 63 epochs 2023/05/24 08:18:42 - mmengine - INFO - Evaluating NME... 2023/05/24 08:18:42 - mmengine - INFO - Epoch(val) [63][16/16] NME: 0.034521 data_time: 0.017818 time: 0.248675 2023/05/24 08:18:56 - mmengine - INFO - Epoch(train) [64][50/85] lr: 2.000000e-03 eta: 0:35:59 time: 0.273209 data_time: 0.030909 memory: 1767 loss: 0.024635 loss/heatmap: 0.009280 loss/offside: 0.015354 acc_pose: 0.982328 2023/05/24 08:19:05 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:19:05 - mmengine - INFO - Saving checkpoint at 64 epochs 2023/05/24 08:19:10 - mmengine - INFO - Evaluating NME... 2023/05/24 08:19:10 - mmengine - INFO - Epoch(val) [64][16/16] NME: 0.033540 data_time: 0.018017 time: 0.253990 2023/05/24 08:19:23 - mmengine - INFO - Epoch(train) [65][50/85] lr: 2.000000e-03 eta: 0:35:37 time: 0.268774 data_time: 0.029972 memory: 1767 loss: 0.024775 loss/heatmap: 0.009290 loss/offside: 0.015486 acc_pose: 0.967672 2023/05/24 08:19:32 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:19:32 - mmengine - INFO - Saving checkpoint at 65 epochs 2023/05/24 08:19:37 - mmengine - INFO - Evaluating NME... 2023/05/24 08:19:37 - mmengine - INFO - Epoch(val) [65][16/16] NME: 0.034240 data_time: 0.017464 time: 0.252248 2023/05/24 08:19:51 - mmengine - INFO - Epoch(train) [66][50/85] lr: 2.000000e-03 eta: 0:35:15 time: 0.271513 data_time: 0.032127 memory: 1767 loss: 0.024679 loss/heatmap: 0.009244 loss/offside: 0.015435 acc_pose: 0.966646 2023/05/24 08:20:00 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:20:00 - mmengine - INFO - Saving checkpoint at 66 epochs 2023/05/24 08:20:05 - mmengine - INFO - Evaluating NME... 2023/05/24 08:20:05 - mmengine - INFO - Epoch(val) [66][16/16] NME: 0.033928 data_time: 0.017689 time: 0.249315 2023/05/24 08:20:19 - mmengine - INFO - Epoch(train) [67][50/85] lr: 2.000000e-03 eta: 0:34:53 time: 0.272227 data_time: 0.030432 memory: 1767 loss: 0.024049 loss/heatmap: 0.009018 loss/offside: 0.015030 acc_pose: 0.937048 2023/05/24 08:20:28 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:20:28 - mmengine - INFO - Saving checkpoint at 67 epochs 2023/05/24 08:20:33 - mmengine - INFO - Evaluating NME... 2023/05/24 08:20:33 - mmengine - INFO - Epoch(val) [67][16/16] NME: 0.033545 data_time: 0.019511 time: 0.249705 2023/05/24 08:20:46 - mmengine - INFO - Epoch(train) [68][50/85] lr: 2.000000e-03 eta: 0:34:30 time: 0.264347 data_time: 0.030425 memory: 1767 loss: 0.023626 loss/heatmap: 0.008781 loss/offside: 0.014846 acc_pose: 0.993534 2023/05/24 08:20:55 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:20:55 - mmengine - INFO - Saving checkpoint at 68 epochs 2023/05/24 08:21:00 - mmengine - INFO - Evaluating NME... 2023/05/24 08:21:00 - mmengine - INFO - Epoch(val) [68][16/16] NME: 0.033513 data_time: 0.030938 time: 0.264822 2023/05/24 08:21:13 - mmengine - INFO - Epoch(train) [69][50/85] lr: 2.000000e-03 eta: 0:34:08 time: 0.267368 data_time: 0.030580 memory: 1767 loss: 0.023166 loss/heatmap: 0.008647 loss/offside: 0.014519 acc_pose: 0.939060 2023/05/24 08:21:22 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:21:22 - mmengine - INFO - Saving checkpoint at 69 epochs 2023/05/24 08:21:27 - mmengine - INFO - Evaluating NME... 2023/05/24 08:21:27 - mmengine - INFO - Epoch(val) [69][16/16] NME: 0.034311 data_time: 0.017362 time: 0.244826 2023/05/24 08:21:41 - mmengine - INFO - Epoch(train) [70][50/85] lr: 2.000000e-03 eta: 0:33:46 time: 0.267384 data_time: 0.030340 memory: 1767 loss: 0.026163 loss/heatmap: 0.009987 loss/offside: 0.016177 acc_pose: 0.991236 2023/05/24 08:21:50 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:21:50 - mmengine - INFO - Saving checkpoint at 70 epochs 2023/05/24 08:21:55 - mmengine - INFO - Evaluating NME... 2023/05/24 08:21:55 - mmengine - INFO - Epoch(val) [70][16/16] NME: 0.033534 data_time: 0.017180 time: 0.247118 2023/05/24 08:22:08 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:22:08 - mmengine - INFO - Epoch(train) [71][50/85] lr: 2.000000e-03 eta: 0:33:23 time: 0.263312 data_time: 0.030238 memory: 1767 loss: 0.025146 loss/heatmap: 0.009478 loss/offside: 0.015668 acc_pose: 0.984914 2023/05/24 08:22:17 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:22:17 - mmengine - INFO - Saving checkpoint at 71 epochs 2023/05/24 08:22:22 - mmengine - INFO - Evaluating NME... 2023/05/24 08:22:22 - mmengine - INFO - Epoch(val) [71][16/16] NME: 0.035119 data_time: 0.018133 time: 0.252027 2023/05/24 08:22:35 - mmengine - INFO - Epoch(train) [72][50/85] lr: 2.000000e-03 eta: 0:33:01 time: 0.267549 data_time: 0.029939 memory: 1767 loss: 0.023513 loss/heatmap: 0.008730 loss/offside: 0.014783 acc_pose: 0.960279 2023/05/24 08:22:44 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:22:44 - mmengine - INFO - Saving checkpoint at 72 epochs 2023/05/24 08:22:49 - mmengine - INFO - Evaluating NME... 2023/05/24 08:22:49 - mmengine - INFO - Epoch(val) [72][16/16] NME: 0.032828 data_time: 0.018417 time: 0.248104 2023/05/24 08:22:49 - mmengine - INFO - The previous best checkpoint /root/mmpose/projects/skps/work_dirs/td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256/best_NME_epoch_38.pth is removed 2023/05/24 08:22:50 - mmengine - INFO - The best checkpoint with 0.0328 NME at 72 epoch is saved to best_NME_epoch_72.pth. 2023/05/24 08:23:03 - mmengine - INFO - Epoch(train) [73][50/85] lr: 2.000000e-03 eta: 0:32:38 time: 0.269495 data_time: 0.029788 memory: 1767 loss: 0.023574 loss/heatmap: 0.008784 loss/offside: 0.014791 acc_pose: 0.914368 2023/05/24 08:23:12 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:23:12 - mmengine - INFO - Saving checkpoint at 73 epochs 2023/05/24 08:23:17 - mmengine - INFO - Evaluating NME... 2023/05/24 08:23:17 - mmengine - INFO - Epoch(val) [73][16/16] NME: 0.034295 data_time: 0.017374 time: 0.252011 2023/05/24 08:23:30 - mmengine - INFO - Epoch(train) [74][50/85] lr: 2.000000e-03 eta: 0:32:15 time: 0.262315 data_time: 0.029301 memory: 1767 loss: 0.023679 loss/heatmap: 0.008828 loss/offside: 0.014850 acc_pose: 0.977833 2023/05/24 08:23:39 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:23:39 - mmengine - INFO - Saving checkpoint at 74 epochs 2023/05/24 08:23:44 - mmengine - INFO - Evaluating NME... 2023/05/24 08:23:44 - mmengine - INFO - Epoch(val) [74][16/16] NME: 0.033477 data_time: 0.017239 time: 0.248254 2023/05/24 08:23:58 - mmengine - INFO - Epoch(train) [75][50/85] lr: 2.000000e-03 eta: 0:31:53 time: 0.266794 data_time: 0.031143 memory: 1767 loss: 0.023689 loss/heatmap: 0.008873 loss/offside: 0.014816 acc_pose: 0.964302 2023/05/24 08:24:07 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:24:07 - mmengine - INFO - Saving checkpoint at 75 epochs 2023/05/24 08:24:12 - mmengine - INFO - Evaluating NME... 2023/05/24 08:24:12 - mmengine - INFO - Epoch(val) [75][16/16] NME: 0.033732 data_time: 0.018445 time: 0.253663 2023/05/24 08:24:25 - mmengine - INFO - Epoch(train) [76][50/85] lr: 2.000000e-03 eta: 0:31:31 time: 0.269755 data_time: 0.031911 memory: 1767 loss: 0.023083 loss/heatmap: 0.008548 loss/offside: 0.014535 acc_pose: 0.967365 2023/05/24 08:24:35 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:24:35 - mmengine - INFO - Saving checkpoint at 76 epochs 2023/05/24 08:24:39 - mmengine - INFO - Evaluating NME... 2023/05/24 08:24:39 - mmengine - INFO - Epoch(val) [76][16/16] NME: 0.033295 data_time: 0.018224 time: 0.251586 2023/05/24 08:24:53 - mmengine - INFO - Epoch(train) [77][50/85] lr: 2.000000e-03 eta: 0:31:09 time: 0.264485 data_time: 0.029886 memory: 1767 loss: 0.023664 loss/heatmap: 0.008810 loss/offside: 0.014854 acc_pose: 0.993534 2023/05/24 08:25:02 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:25:02 - mmengine - INFO - Saving checkpoint at 77 epochs 2023/05/24 08:25:07 - mmengine - INFO - Evaluating NME... 2023/05/24 08:25:07 - mmengine - INFO - Epoch(val) [77][16/16] NME: 0.034009 data_time: 0.017471 time: 0.250510 2023/05/24 08:25:20 - mmengine - INFO - Epoch(train) [78][50/85] lr: 2.000000e-03 eta: 0:30:46 time: 0.266163 data_time: 0.030163 memory: 1767 loss: 0.023456 loss/heatmap: 0.008770 loss/offside: 0.014686 acc_pose: 0.986925 2023/05/24 08:25:29 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:25:29 - mmengine - INFO - Saving checkpoint at 78 epochs 2023/05/24 08:25:34 - mmengine - INFO - Evaluating NME... 2023/05/24 08:25:34 - mmengine - INFO - Epoch(val) [78][16/16] NME: 0.033064 data_time: 0.017512 time: 0.255405 2023/05/24 08:25:48 - mmengine - INFO - Epoch(train) [79][50/85] lr: 2.000000e-03 eta: 0:30:25 time: 0.276532 data_time: 0.032087 memory: 1767 loss: 0.023293 loss/heatmap: 0.008679 loss/offside: 0.014614 acc_pose: 0.993534 2023/05/24 08:25:57 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:25:57 - mmengine - INFO - Saving checkpoint at 79 epochs 2023/05/24 08:26:02 - mmengine - INFO - Evaluating NME... 2023/05/24 08:26:02 - mmengine - INFO - Epoch(val) [79][16/16] NME: 0.033704 data_time: 0.018104 time: 0.252302 2023/05/24 08:26:16 - mmengine - INFO - Epoch(train) [80][50/85] lr: 2.000000e-03 eta: 0:30:03 time: 0.275487 data_time: 0.033445 memory: 1767 loss: 0.023436 loss/heatmap: 0.008728 loss/offside: 0.014708 acc_pose: 0.947557 2023/05/24 08:26:25 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:26:25 - mmengine - INFO - Saving checkpoint at 80 epochs 2023/05/24 08:26:30 - mmengine - INFO - Evaluating NME... 2023/05/24 08:26:30 - mmengine - INFO - Epoch(val) [80][16/16] NME: 0.033635 data_time: 0.017165 time: 0.253314 2023/05/24 08:26:44 - mmengine - INFO - Epoch(train) [81][50/85] lr: 2.000000e-04 eta: 0:29:40 time: 0.269184 data_time: 0.030046 memory: 1767 loss: 0.021824 loss/heatmap: 0.008070 loss/offside: 0.013754 acc_pose: 0.973255 2023/05/24 08:26:53 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:26:53 - mmengine - INFO - Saving checkpoint at 81 epochs 2023/05/24 08:26:58 - mmengine - INFO - Evaluating NME... 2023/05/24 08:26:58 - mmengine - INFO - Epoch(val) [81][16/16] NME: 0.032573 data_time: 0.017869 time: 0.252245 2023/05/24 08:26:58 - mmengine - INFO - The previous best checkpoint /root/mmpose/projects/skps/work_dirs/td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256/best_NME_epoch_72.pth is removed 2023/05/24 08:26:58 - mmengine - INFO - The best checkpoint with 0.0326 NME at 81 epoch is saved to best_NME_epoch_81.pth. 2023/05/24 08:27:12 - mmengine - INFO - Epoch(train) [82][50/85] lr: 2.000000e-04 eta: 0:29:18 time: 0.266563 data_time: 0.030617 memory: 1767 loss: 0.020420 loss/heatmap: 0.007515 loss/offside: 0.012905 acc_pose: 0.971367 2023/05/24 08:27:21 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:27:21 - mmengine - INFO - Saving checkpoint at 82 epochs 2023/05/24 08:27:25 - mmengine - INFO - Evaluating NME... 2023/05/24 08:27:26 - mmengine - INFO - Epoch(val) [82][16/16] NME: 0.032535 data_time: 0.017951 time: 0.249025 2023/05/24 08:27:26 - mmengine - INFO - The previous best checkpoint /root/mmpose/projects/skps/work_dirs/td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256/best_NME_epoch_81.pth is removed 2023/05/24 08:27:26 - mmengine - INFO - The best checkpoint with 0.0325 NME at 82 epoch is saved to best_NME_epoch_82.pth. 2023/05/24 08:27:34 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:27:39 - mmengine - INFO - Epoch(train) [83][50/85] lr: 2.000000e-04 eta: 0:28:55 time: 0.271367 data_time: 0.031126 memory: 1767 loss: 0.020377 loss/heatmap: 0.007525 loss/offside: 0.012853 acc_pose: 0.997845 2023/05/24 08:27:49 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:27:49 - mmengine - INFO - Saving checkpoint at 83 epochs 2023/05/24 08:27:54 - mmengine - INFO - Evaluating NME... 2023/05/24 08:27:54 - mmengine - INFO - Epoch(val) [83][16/16] NME: 0.032379 data_time: 0.018288 time: 0.252738 2023/05/24 08:27:54 - mmengine - INFO - The previous best checkpoint /root/mmpose/projects/skps/work_dirs/td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256/best_NME_epoch_82.pth is removed 2023/05/24 08:27:54 - mmengine - INFO - The best checkpoint with 0.0324 NME at 83 epoch is saved to best_NME_epoch_83.pth. 2023/05/24 08:28:08 - mmengine - INFO - Epoch(train) [84][50/85] lr: 2.000000e-04 eta: 0:28:33 time: 0.271258 data_time: 0.034219 memory: 1767 loss: 0.020251 loss/heatmap: 0.007442 loss/offside: 0.012809 acc_pose: 0.988937 2023/05/24 08:28:17 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:28:17 - mmengine - INFO - Saving checkpoint at 84 epochs 2023/05/24 08:28:22 - mmengine - INFO - Evaluating NME... 2023/05/24 08:28:22 - mmengine - INFO - Epoch(val) [84][16/16] NME: 0.032589 data_time: 0.018102 time: 0.250655 2023/05/24 08:28:35 - mmengine - INFO - Epoch(train) [85][50/85] lr: 2.000000e-04 eta: 0:28:11 time: 0.265905 data_time: 0.030235 memory: 1767 loss: 0.019955 loss/heatmap: 0.007349 loss/offside: 0.012606 acc_pose: 0.985931 2023/05/24 08:28:44 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:28:44 - mmengine - INFO - Saving checkpoint at 85 epochs 2023/05/24 08:28:49 - mmengine - INFO - Evaluating NME... 2023/05/24 08:28:49 - mmengine - INFO - Epoch(val) [85][16/16] NME: 0.032254 data_time: 0.018602 time: 0.256064 2023/05/24 08:28:49 - mmengine - INFO - The previous best checkpoint /root/mmpose/projects/skps/work_dirs/td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256/best_NME_epoch_83.pth is removed 2023/05/24 08:28:50 - mmengine - INFO - The best checkpoint with 0.0323 NME at 85 epoch is saved to best_NME_epoch_85.pth. 2023/05/24 08:29:03 - mmengine - INFO - Epoch(train) [86][50/85] lr: 2.000000e-04 eta: 0:27:48 time: 0.267529 data_time: 0.030064 memory: 1767 loss: 0.019457 loss/heatmap: 0.007151 loss/offside: 0.012306 acc_pose: 0.986572 2023/05/24 08:29:12 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:29:12 - mmengine - INFO - Saving checkpoint at 86 epochs 2023/05/24 08:29:17 - mmengine - INFO - Evaluating NME... 2023/05/24 08:29:17 - mmengine - INFO - Epoch(val) [86][16/16] NME: 0.032614 data_time: 0.017592 time: 0.248886 2023/05/24 08:29:31 - mmengine - INFO - Epoch(train) [87][50/85] lr: 2.000000e-04 eta: 0:27:26 time: 0.273211 data_time: 0.033245 memory: 1767 loss: 0.019980 loss/heatmap: 0.007362 loss/offside: 0.012619 acc_pose: 0.960920 2023/05/24 08:29:40 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:29:40 - mmengine - INFO - Saving checkpoint at 87 epochs 2023/05/24 08:29:45 - mmengine - INFO - Evaluating NME... 2023/05/24 08:29:45 - mmengine - INFO - Epoch(val) [87][16/16] NME: 0.032500 data_time: 0.017855 time: 0.252103 2023/05/24 08:29:58 - mmengine - INFO - Epoch(train) [88][50/85] lr: 2.000000e-04 eta: 0:27:04 time: 0.270417 data_time: 0.030809 memory: 1767 loss: 0.019661 loss/heatmap: 0.007236 loss/offside: 0.012425 acc_pose: 0.978305 2023/05/24 08:30:07 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:30:07 - mmengine - INFO - Saving checkpoint at 88 epochs 2023/05/24 08:30:12 - mmengine - INFO - Evaluating NME... 2023/05/24 08:30:12 - mmengine - INFO - Epoch(val) [88][16/16] NME: 0.032203 data_time: 0.017812 time: 0.249667 2023/05/24 08:30:12 - mmengine - INFO - The previous best checkpoint /root/mmpose/projects/skps/work_dirs/td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256/best_NME_epoch_85.pth is removed 2023/05/24 08:30:13 - mmengine - INFO - The best checkpoint with 0.0322 NME at 88 epoch is saved to best_NME_epoch_88.pth. 2023/05/24 08:30:27 - mmengine - INFO - Epoch(train) [89][50/85] lr: 2.000000e-04 eta: 0:26:42 time: 0.278028 data_time: 0.034376 memory: 1767 loss: 0.019062 loss/heatmap: 0.007004 loss/offside: 0.012059 acc_pose: 0.986453 2023/05/24 08:30:36 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:30:36 - mmengine - INFO - Saving checkpoint at 89 epochs 2023/05/24 08:30:41 - mmengine - INFO - Evaluating NME... 2023/05/24 08:30:41 - mmengine - INFO - Epoch(val) [89][16/16] NME: 0.032373 data_time: 0.018256 time: 0.252342 2023/05/24 08:30:54 - mmengine - INFO - Epoch(train) [90][50/85] lr: 2.000000e-04 eta: 0:26:20 time: 0.273425 data_time: 0.030840 memory: 1767 loss: 0.019207 loss/heatmap: 0.007025 loss/offside: 0.012182 acc_pose: 0.957410 2023/05/24 08:31:04 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:31:04 - mmengine - INFO - Saving checkpoint at 90 epochs 2023/05/24 08:31:09 - mmengine - INFO - Evaluating NME... 2023/05/24 08:31:09 - mmengine - INFO - Epoch(val) [90][16/16] NME: 0.032115 data_time: 0.017615 time: 0.251600 2023/05/24 08:31:09 - mmengine - INFO - The previous best checkpoint /root/mmpose/projects/skps/work_dirs/td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256/best_NME_epoch_88.pth is removed 2023/05/24 08:31:09 - mmengine - INFO - The best checkpoint with 0.0321 NME at 90 epoch is saved to best_NME_epoch_90.pth. 2023/05/24 08:31:22 - mmengine - INFO - Epoch(train) [91][50/85] lr: 2.000000e-04 eta: 0:25:58 time: 0.268153 data_time: 0.030857 memory: 1767 loss: 0.019233 loss/heatmap: 0.007067 loss/offside: 0.012166 acc_pose: 0.989080 2023/05/24 08:31:32 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:31:32 - mmengine - INFO - Saving checkpoint at 91 epochs 2023/05/24 08:31:37 - mmengine - INFO - Evaluating NME... 2023/05/24 08:31:37 - mmengine - INFO - Epoch(val) [91][16/16] NME: 0.032378 data_time: 0.017554 time: 0.263506 2023/05/24 08:31:50 - mmengine - INFO - Epoch(train) [92][50/85] lr: 2.000000e-04 eta: 0:25:35 time: 0.268039 data_time: 0.030861 memory: 1767 loss: 0.019224 loss/heatmap: 0.007045 loss/offside: 0.012179 acc_pose: 0.993534 2023/05/24 08:31:59 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:31:59 - mmengine - INFO - Saving checkpoint at 92 epochs 2023/05/24 08:32:04 - mmengine - INFO - Evaluating NME... 2023/05/24 08:32:04 - mmengine - INFO - Epoch(val) [92][16/16] NME: 0.032312 data_time: 0.017928 time: 0.251116 2023/05/24 08:32:18 - mmengine - INFO - Epoch(train) [93][50/85] lr: 2.000000e-04 eta: 0:25:13 time: 0.272568 data_time: 0.030706 memory: 1767 loss: 0.019130 loss/heatmap: 0.007020 loss/offside: 0.012109 acc_pose: 0.969540 2023/05/24 08:32:27 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:32:27 - mmengine - INFO - Saving checkpoint at 93 epochs 2023/05/24 08:32:32 - mmengine - INFO - Evaluating NME... 2023/05/24 08:32:32 - mmengine - INFO - Epoch(val) [93][16/16] NME: 0.032271 data_time: 0.018314 time: 0.253851 2023/05/24 08:32:46 - mmengine - INFO - Epoch(train) [94][50/85] lr: 2.000000e-04 eta: 0:24:51 time: 0.273545 data_time: 0.031770 memory: 1767 loss: 0.019148 loss/heatmap: 0.007002 loss/offside: 0.012146 acc_pose: 0.984770 2023/05/24 08:32:55 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:32:55 - mmengine - INFO - Saving checkpoint at 94 epochs 2023/05/24 08:33:00 - mmengine - INFO - Evaluating NME... 2023/05/24 08:33:00 - mmengine - INFO - Epoch(val) [94][16/16] NME: 0.032296 data_time: 0.017538 time: 0.249290 2023/05/24 08:33:03 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:33:13 - mmengine - INFO - Epoch(train) [95][50/85] lr: 2.000000e-04 eta: 0:24:29 time: 0.271666 data_time: 0.031097 memory: 1767 loss: 0.018444 loss/heatmap: 0.006729 loss/offside: 0.011715 acc_pose: 0.982184 2023/05/24 08:33:23 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:33:23 - mmengine - INFO - Saving checkpoint at 95 epochs 2023/05/24 08:33:28 - mmengine - INFO - Evaluating NME... 2023/05/24 08:33:28 - mmengine - INFO - Epoch(val) [95][16/16] NME: 0.032248 data_time: 0.018344 time: 0.254553 2023/05/24 08:33:41 - mmengine - INFO - Epoch(train) [96][50/85] lr: 2.000000e-04 eta: 0:24:06 time: 0.264243 data_time: 0.029899 memory: 1767 loss: 0.018485 loss/heatmap: 0.006758 loss/offside: 0.011727 acc_pose: 0.991379 2023/05/24 08:33:50 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:33:50 - mmengine - INFO - Saving checkpoint at 96 epochs 2023/05/24 08:33:55 - mmengine - INFO - Evaluating NME... 2023/05/24 08:33:55 - mmengine - INFO - Epoch(val) [96][16/16] NME: 0.032290 data_time: 0.018419 time: 0.246946 2023/05/24 08:34:08 - mmengine - INFO - Epoch(train) [97][50/85] lr: 2.000000e-04 eta: 0:23:44 time: 0.266962 data_time: 0.033290 memory: 1767 loss: 0.019016 loss/heatmap: 0.006984 loss/offside: 0.012033 acc_pose: 0.980603 2023/05/24 08:34:17 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:34:17 - mmengine - INFO - Saving checkpoint at 97 epochs 2023/05/24 08:34:22 - mmengine - INFO - Evaluating NME... 2023/05/24 08:34:22 - mmengine - INFO - Epoch(val) [97][16/16] NME: 0.032435 data_time: 0.017384 time: 0.249186 2023/05/24 08:34:36 - mmengine - INFO - Epoch(train) [98][50/85] lr: 2.000000e-04 eta: 0:23:22 time: 0.271211 data_time: 0.029741 memory: 1767 loss: 0.018667 loss/heatmap: 0.006833 loss/offside: 0.011833 acc_pose: 0.991236 2023/05/24 08:34:45 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:34:45 - mmengine - INFO - Saving checkpoint at 98 epochs 2023/05/24 08:34:50 - mmengine - INFO - Evaluating NME... 2023/05/24 08:34:50 - mmengine - INFO - Epoch(val) [98][16/16] NME: 0.032291 data_time: 0.016912 time: 0.244859 2023/05/24 08:35:03 - mmengine - INFO - Epoch(train) [99][50/85] lr: 2.000000e-04 eta: 0:22:59 time: 0.265903 data_time: 0.029803 memory: 1767 loss: 0.019030 loss/heatmap: 0.006984 loss/offside: 0.012046 acc_pose: 0.990209 2023/05/24 08:35:12 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:35:12 - mmengine - INFO - Saving checkpoint at 99 epochs 2023/05/24 08:35:17 - mmengine - INFO - Evaluating NME... 2023/05/24 08:35:17 - mmengine - INFO - Epoch(val) [99][16/16] NME: 0.032220 data_time: 0.017227 time: 0.244444 2023/05/24 08:35:30 - mmengine - INFO - Epoch(train) [100][50/85] lr: 2.000000e-04 eta: 0:22:36 time: 0.264652 data_time: 0.032897 memory: 1767 loss: 0.018507 loss/heatmap: 0.006771 loss/offside: 0.011736 acc_pose: 0.989080 2023/05/24 08:35:39 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:35:39 - mmengine - INFO - Saving checkpoint at 100 epochs 2023/05/24 08:35:44 - mmengine - INFO - Evaluating NME... 2023/05/24 08:35:44 - mmengine - INFO - Epoch(val) [100][16/16] NME: 0.032172 data_time: 0.016989 time: 0.247879 2023/05/24 08:35:57 - mmengine - INFO - Epoch(train) [101][50/85] lr: 2.000000e-04 eta: 0:22:14 time: 0.272756 data_time: 0.030722 memory: 1767 loss: 0.018347 loss/heatmap: 0.006719 loss/offside: 0.011628 acc_pose: 0.995690 2023/05/24 08:36:06 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:36:06 - mmengine - INFO - Saving checkpoint at 101 epochs 2023/05/24 08:36:11 - mmengine - INFO - Evaluating NME... 2023/05/24 08:36:11 - mmengine - INFO - Epoch(val) [101][16/16] NME: 0.032323 data_time: 0.017188 time: 0.249307 2023/05/24 08:36:25 - mmengine - INFO - Epoch(train) [102][50/85] lr: 2.000000e-04 eta: 0:21:52 time: 0.270069 data_time: 0.030083 memory: 1767 loss: 0.018125 loss/heatmap: 0.006650 loss/offside: 0.011476 acc_pose: 0.989080 2023/05/24 08:36:34 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:36:34 - mmengine - INFO - Saving checkpoint at 102 epochs 2023/05/24 08:36:39 - mmengine - INFO - Evaluating NME... 2023/05/24 08:36:39 - mmengine - INFO - Epoch(val) [102][16/16] NME: 0.032169 data_time: 0.017018 time: 0.247569 2023/05/24 08:36:52 - mmengine - INFO - Epoch(train) [103][50/85] lr: 2.000000e-04 eta: 0:21:29 time: 0.264006 data_time: 0.029668 memory: 1767 loss: 0.018608 loss/heatmap: 0.006843 loss/offside: 0.011765 acc_pose: 0.974138 2023/05/24 08:37:01 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:37:01 - mmengine - INFO - Saving checkpoint at 103 epochs 2023/05/24 08:37:06 - mmengine - INFO - Evaluating NME... 2023/05/24 08:37:06 - mmengine - INFO - Epoch(val) [103][16/16] NME: 0.032489 data_time: 0.018285 time: 0.245897 2023/05/24 08:37:19 - mmengine - INFO - Epoch(train) [104][50/85] lr: 2.000000e-04 eta: 0:21:07 time: 0.263732 data_time: 0.030498 memory: 1767 loss: 0.017862 loss/heatmap: 0.006522 loss/offside: 0.011341 acc_pose: 1.000000 2023/05/24 08:37:28 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:37:28 - mmengine - INFO - Saving checkpoint at 104 epochs 2023/05/24 08:37:33 - mmengine - INFO - Evaluating NME... 2023/05/24 08:37:33 - mmengine - INFO - Epoch(val) [104][16/16] NME: 0.032333 data_time: 0.016867 time: 0.244071 2023/05/24 08:37:46 - mmengine - INFO - Epoch(train) [105][50/85] lr: 2.000000e-04 eta: 0:20:44 time: 0.263871 data_time: 0.029143 memory: 1767 loss: 0.018262 loss/heatmap: 0.006703 loss/offside: 0.011559 acc_pose: 0.982759 2023/05/24 08:37:55 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:37:55 - mmengine - INFO - Saving checkpoint at 105 epochs 2023/05/24 08:38:00 - mmengine - INFO - Evaluating NME... 2023/05/24 08:38:00 - mmengine - INFO - Epoch(val) [105][16/16] NME: 0.032096 data_time: 0.025242 time: 0.258144 2023/05/24 08:38:00 - mmengine - INFO - The previous best checkpoint /root/mmpose/projects/skps/work_dirs/td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256/best_NME_epoch_90.pth is removed 2023/05/24 08:38:00 - mmengine - INFO - The best checkpoint with 0.0321 NME at 105 epoch is saved to best_NME_epoch_105.pth. 2023/05/24 08:38:13 - mmengine - INFO - Epoch(train) [106][50/85] lr: 2.000000e-04 eta: 0:20:21 time: 0.261167 data_time: 0.029603 memory: 1767 loss: 0.018080 loss/heatmap: 0.006636 loss/offside: 0.011444 acc_pose: 0.980603 2023/05/24 08:38:20 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:38:22 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:38:22 - mmengine - INFO - Saving checkpoint at 106 epochs 2023/05/24 08:38:27 - mmengine - INFO - Evaluating NME... 2023/05/24 08:38:27 - mmengine - INFO - Epoch(val) [106][16/16] NME: 0.032276 data_time: 0.017146 time: 0.249994 2023/05/24 08:38:40 - mmengine - INFO - Epoch(train) [107][50/85] lr: 2.000000e-04 eta: 0:19:59 time: 0.268584 data_time: 0.033806 memory: 1767 loss: 0.017956 loss/heatmap: 0.006559 loss/offside: 0.011397 acc_pose: 0.978448 2023/05/24 08:38:49 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:38:49 - mmengine - INFO - Saving checkpoint at 107 epochs 2023/05/24 08:38:54 - mmengine - INFO - Evaluating NME... 2023/05/24 08:38:54 - mmengine - INFO - Epoch(val) [107][16/16] NME: 0.032347 data_time: 0.017826 time: 0.254887 2023/05/24 08:39:08 - mmengine - INFO - Epoch(train) [108][50/85] lr: 2.000000e-04 eta: 0:19:36 time: 0.271731 data_time: 0.032072 memory: 1767 loss: 0.018039 loss/heatmap: 0.006602 loss/offside: 0.011437 acc_pose: 0.989224 2023/05/24 08:39:17 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:39:17 - mmengine - INFO - Saving checkpoint at 108 epochs 2023/05/24 08:39:22 - mmengine - INFO - Evaluating NME... 2023/05/24 08:39:22 - mmengine - INFO - Epoch(val) [108][16/16] NME: 0.032053 data_time: 0.017618 time: 0.246485 2023/05/24 08:39:22 - mmengine - INFO - The previous best checkpoint /root/mmpose/projects/skps/work_dirs/td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256/best_NME_epoch_105.pth is removed 2023/05/24 08:39:22 - mmengine - INFO - The best checkpoint with 0.0321 NME at 108 epoch is saved to best_NME_epoch_108.pth. 2023/05/24 08:39:36 - mmengine - INFO - Epoch(train) [109][50/85] lr: 2.000000e-04 eta: 0:19:14 time: 0.276922 data_time: 0.031256 memory: 1767 loss: 0.017827 loss/heatmap: 0.006526 loss/offside: 0.011301 acc_pose: 0.991236 2023/05/24 08:39:46 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:39:46 - mmengine - INFO - Saving checkpoint at 109 epochs 2023/05/24 08:39:50 - mmengine - INFO - Evaluating NME... 2023/05/24 08:39:50 - mmengine - INFO - Epoch(val) [109][16/16] NME: 0.032206 data_time: 0.018382 time: 0.247735 2023/05/24 08:40:04 - mmengine - INFO - Epoch(train) [110][50/85] lr: 2.000000e-04 eta: 0:18:52 time: 0.277615 data_time: 0.031652 memory: 1767 loss: 0.017563 loss/heatmap: 0.006405 loss/offside: 0.011158 acc_pose: 0.984914 2023/05/24 08:40:13 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:40:13 - mmengine - INFO - Saving checkpoint at 110 epochs 2023/05/24 08:40:18 - mmengine - INFO - Evaluating NME... 2023/05/24 08:40:18 - mmengine - INFO - Epoch(val) [110][16/16] NME: 0.032290 data_time: 0.017132 time: 0.249792 2023/05/24 08:40:32 - mmengine - INFO - Epoch(train) [111][50/85] lr: 2.000000e-04 eta: 0:18:29 time: 0.268368 data_time: 0.031382 memory: 1767 loss: 0.017999 loss/heatmap: 0.006590 loss/offside: 0.011409 acc_pose: 0.967365 2023/05/24 08:40:41 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:40:41 - mmengine - INFO - Saving checkpoint at 111 epochs 2023/05/24 08:40:46 - mmengine - INFO - Evaluating NME... 2023/05/24 08:40:46 - mmengine - INFO - Epoch(val) [111][16/16] NME: 0.032229 data_time: 0.017609 time: 0.245087 2023/05/24 08:41:00 - mmengine - INFO - Epoch(train) [112][50/85] lr: 2.000000e-04 eta: 0:18:07 time: 0.277058 data_time: 0.032796 memory: 1767 loss: 0.017951 loss/heatmap: 0.006577 loss/offside: 0.011374 acc_pose: 0.991236 2023/05/24 08:41:09 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:41:09 - mmengine - INFO - Saving checkpoint at 112 epochs 2023/05/24 08:41:13 - mmengine - INFO - Evaluating NME... 2023/05/24 08:41:13 - mmengine - INFO - Epoch(val) [112][16/16] NME: 0.032024 data_time: 0.017342 time: 0.246830 2023/05/24 08:41:13 - mmengine - INFO - The previous best checkpoint /root/mmpose/projects/skps/work_dirs/td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256/best_NME_epoch_108.pth is removed 2023/05/24 08:41:14 - mmengine - INFO - The best checkpoint with 0.0320 NME at 112 epoch is saved to best_NME_epoch_112.pth. 2023/05/24 08:41:27 - mmengine - INFO - Epoch(train) [113][50/85] lr: 2.000000e-04 eta: 0:17:45 time: 0.268579 data_time: 0.030768 memory: 1767 loss: 0.017620 loss/heatmap: 0.006458 loss/offside: 0.011163 acc_pose: 0.984914 2023/05/24 08:41:36 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:41:36 - mmengine - INFO - Saving checkpoint at 113 epochs 2023/05/24 08:41:41 - mmengine - INFO - Evaluating NME... 2023/05/24 08:41:41 - mmengine - INFO - Epoch(val) [113][16/16] NME: 0.031960 data_time: 0.017909 time: 0.250372 2023/05/24 08:41:41 - mmengine - INFO - The previous best checkpoint /root/mmpose/projects/skps/work_dirs/td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256/best_NME_epoch_112.pth is removed 2023/05/24 08:41:42 - mmengine - INFO - The best checkpoint with 0.0320 NME at 113 epoch is saved to best_NME_epoch_113.pth. 2023/05/24 08:41:55 - mmengine - INFO - Epoch(train) [114][50/85] lr: 2.000000e-04 eta: 0:17:22 time: 0.267852 data_time: 0.031188 memory: 1767 loss: 0.017535 loss/heatmap: 0.006382 loss/offside: 0.011153 acc_pose: 0.997845 2023/05/24 08:42:04 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:42:04 - mmengine - INFO - Saving checkpoint at 114 epochs 2023/05/24 08:42:09 - mmengine - INFO - Evaluating NME... 2023/05/24 08:42:09 - mmengine - INFO - Epoch(val) [114][16/16] NME: 0.032362 data_time: 0.017924 time: 0.248280 2023/05/24 08:42:23 - mmengine - INFO - Epoch(train) [115][50/85] lr: 2.000000e-04 eta: 0:17:00 time: 0.266860 data_time: 0.031145 memory: 1767 loss: 0.017961 loss/heatmap: 0.006586 loss/offside: 0.011375 acc_pose: 0.986925 2023/05/24 08:42:32 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:42:32 - mmengine - INFO - Saving checkpoint at 115 epochs 2023/05/24 08:42:37 - mmengine - INFO - Evaluating NME... 2023/05/24 08:42:37 - mmengine - INFO - Epoch(val) [115][16/16] NME: 0.032056 data_time: 0.018167 time: 0.253645 2023/05/24 08:42:50 - mmengine - INFO - Epoch(train) [116][50/85] lr: 2.000000e-04 eta: 0:16:37 time: 0.261847 data_time: 0.029639 memory: 1767 loss: 0.017881 loss/heatmap: 0.006537 loss/offside: 0.011345 acc_pose: 1.000000 2023/05/24 08:42:59 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:42:59 - mmengine - INFO - Saving checkpoint at 116 epochs 2023/05/24 08:43:03 - mmengine - INFO - Evaluating NME... 2023/05/24 08:43:03 - mmengine - INFO - Epoch(val) [116][16/16] NME: 0.032271 data_time: 0.016391 time: 0.244326 2023/05/24 08:43:17 - mmengine - INFO - Epoch(train) [117][50/85] lr: 2.000000e-04 eta: 0:16:15 time: 0.265028 data_time: 0.030014 memory: 1767 loss: 0.017469 loss/heatmap: 0.006386 loss/offside: 0.011083 acc_pose: 0.993391 2023/05/24 08:43:26 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:43:26 - mmengine - INFO - Saving checkpoint at 117 epochs 2023/05/24 08:43:31 - mmengine - INFO - Evaluating NME... 2023/05/24 08:43:31 - mmengine - INFO - Epoch(val) [117][16/16] NME: 0.032405 data_time: 0.017827 time: 0.260565 2023/05/24 08:43:44 - mmengine - INFO - Epoch(train) [118][50/85] lr: 2.000000e-04 eta: 0:15:52 time: 0.266043 data_time: 0.030859 memory: 1767 loss: 0.017937 loss/heatmap: 0.006585 loss/offside: 0.011352 acc_pose: 0.991236 2023/05/24 08:43:45 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:43:53 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:43:53 - mmengine - INFO - Saving checkpoint at 118 epochs 2023/05/24 08:43:58 - mmengine - INFO - Evaluating NME... 2023/05/24 08:43:58 - mmengine - INFO - Epoch(val) [118][16/16] NME: 0.032150 data_time: 0.018489 time: 0.253779 2023/05/24 08:44:11 - mmengine - INFO - Epoch(train) [119][50/85] lr: 2.000000e-04 eta: 0:15:30 time: 0.266417 data_time: 0.031039 memory: 1767 loss: 0.017332 loss/heatmap: 0.006326 loss/offside: 0.011006 acc_pose: 0.989080 2023/05/24 08:44:20 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:44:20 - mmengine - INFO - Saving checkpoint at 119 epochs 2023/05/24 08:44:25 - mmengine - INFO - Evaluating NME... 2023/05/24 08:44:25 - mmengine - INFO - Epoch(val) [119][16/16] NME: 0.032093 data_time: 0.018509 time: 0.247529 2023/05/24 08:44:39 - mmengine - INFO - Epoch(train) [120][50/85] lr: 2.000000e-04 eta: 0:15:07 time: 0.266926 data_time: 0.030765 memory: 1767 loss: 0.017227 loss/heatmap: 0.006312 loss/offside: 0.010914 acc_pose: 0.997537 2023/05/24 08:44:48 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:44:48 - mmengine - INFO - Saving checkpoint at 120 epochs 2023/05/24 08:44:53 - mmengine - INFO - Evaluating NME... 2023/05/24 08:44:53 - mmengine - INFO - Epoch(val) [120][16/16] NME: 0.032198 data_time: 0.018364 time: 0.251909 2023/05/24 08:45:06 - mmengine - INFO - Epoch(train) [121][50/85] lr: 2.000000e-05 eta: 0:14:45 time: 0.267254 data_time: 0.031379 memory: 1767 loss: 0.017184 loss/heatmap: 0.006261 loss/offside: 0.010923 acc_pose: 0.982759 2023/05/24 08:45:15 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:45:15 - mmengine - INFO - Saving checkpoint at 121 epochs 2023/05/24 08:45:20 - mmengine - INFO - Evaluating NME... 2023/05/24 08:45:20 - mmengine - INFO - Epoch(val) [121][16/16] NME: 0.032041 data_time: 0.017584 time: 0.245198 2023/05/24 08:45:34 - mmengine - INFO - Epoch(train) [122][50/85] lr: 2.000000e-05 eta: 0:14:22 time: 0.279648 data_time: 0.035828 memory: 1767 loss: 0.017427 loss/heatmap: 0.006403 loss/offside: 0.011024 acc_pose: 0.979844 2023/05/24 08:45:43 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:45:43 - mmengine - INFO - Saving checkpoint at 122 epochs 2023/05/24 08:45:48 - mmengine - INFO - Evaluating NME... 2023/05/24 08:45:48 - mmengine - INFO - Epoch(val) [122][16/16] NME: 0.032024 data_time: 0.017864 time: 0.251949 2023/05/24 08:46:01 - mmengine - INFO - Epoch(train) [123][50/85] lr: 2.000000e-05 eta: 0:14:00 time: 0.265965 data_time: 0.029939 memory: 1767 loss: 0.017252 loss/heatmap: 0.006353 loss/offside: 0.010898 acc_pose: 0.993534 2023/05/24 08:46:10 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:46:10 - mmengine - INFO - Saving checkpoint at 123 epochs 2023/05/24 08:46:15 - mmengine - INFO - Evaluating NME... 2023/05/24 08:46:15 - mmengine - INFO - Epoch(val) [123][16/16] NME: 0.032145 data_time: 0.018194 time: 0.245198 2023/05/24 08:46:29 - mmengine - INFO - Epoch(train) [124][50/85] lr: 2.000000e-05 eta: 0:13:38 time: 0.271844 data_time: 0.032406 memory: 1767 loss: 0.017098 loss/heatmap: 0.006304 loss/offside: 0.010794 acc_pose: 0.954937 2023/05/24 08:46:38 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:46:38 - mmengine - INFO - Saving checkpoint at 124 epochs 2023/05/24 08:46:43 - mmengine - INFO - Evaluating NME... 2023/05/24 08:46:43 - mmengine - INFO - Epoch(val) [124][16/16] NME: 0.032232 data_time: 0.018424 time: 0.255425 2023/05/24 08:46:57 - mmengine - INFO - Epoch(train) [125][50/85] lr: 2.000000e-05 eta: 0:13:15 time: 0.272731 data_time: 0.031270 memory: 1767 loss: 0.017251 loss/heatmap: 0.006333 loss/offside: 0.010917 acc_pose: 0.978448 2023/05/24 08:47:06 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:47:06 - mmengine - INFO - Saving checkpoint at 125 epochs 2023/05/24 08:47:11 - mmengine - INFO - Evaluating NME... 2023/05/24 08:47:11 - mmengine - INFO - Epoch(val) [125][16/16] NME: 0.032051 data_time: 0.017107 time: 0.259995 2023/05/24 08:47:25 - mmengine - INFO - Epoch(train) [126][50/85] lr: 2.000000e-05 eta: 0:12:53 time: 0.270563 data_time: 0.030288 memory: 1767 loss: 0.017298 loss/heatmap: 0.006344 loss/offside: 0.010954 acc_pose: 0.971552 2023/05/24 08:47:34 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:47:34 - mmengine - INFO - Saving checkpoint at 126 epochs 2023/05/24 08:47:39 - mmengine - INFO - Evaluating NME... 2023/05/24 08:47:39 - mmengine - INFO - Epoch(val) [126][16/16] NME: 0.032128 data_time: 0.017250 time: 0.244473 2023/05/24 08:47:52 - mmengine - INFO - Epoch(train) [127][50/85] lr: 2.000000e-05 eta: 0:12:30 time: 0.261935 data_time: 0.028828 memory: 1767 loss: 0.017024 loss/heatmap: 0.006249 loss/offside: 0.010775 acc_pose: 0.995546 2023/05/24 08:48:01 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:48:01 - mmengine - INFO - Saving checkpoint at 127 epochs 2023/05/24 08:48:06 - mmengine - INFO - Evaluating NME... 2023/05/24 08:48:06 - mmengine - INFO - Epoch(val) [127][16/16] NME: 0.032219 data_time: 0.018972 time: 0.246537 2023/05/24 08:48:19 - mmengine - INFO - Epoch(train) [128][50/85] lr: 2.000000e-05 eta: 0:12:08 time: 0.266104 data_time: 0.030157 memory: 1767 loss: 0.016928 loss/heatmap: 0.006198 loss/offside: 0.010730 acc_pose: 0.973707 2023/05/24 08:48:28 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:48:28 - mmengine - INFO - Saving checkpoint at 128 epochs 2023/05/24 08:48:32 - mmengine - INFO - Evaluating NME... 2023/05/24 08:48:32 - mmengine - INFO - Epoch(val) [128][16/16] NME: 0.032089 data_time: 0.017114 time: 0.242517 2023/05/24 08:48:45 - mmengine - INFO - Epoch(train) [129][50/85] lr: 2.000000e-05 eta: 0:11:45 time: 0.260509 data_time: 0.030580 memory: 1767 loss: 0.017325 loss/heatmap: 0.006358 loss/offside: 0.010967 acc_pose: 0.986925 2023/05/24 08:48:54 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:48:54 - mmengine - INFO - Saving checkpoint at 129 epochs 2023/05/24 08:48:59 - mmengine - INFO - Evaluating NME... 2023/05/24 08:48:59 - mmengine - INFO - Epoch(val) [129][16/16] NME: 0.032094 data_time: 0.017198 time: 0.251383 2023/05/24 08:49:09 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:49:13 - mmengine - INFO - Epoch(train) [130][50/85] lr: 2.000000e-05 eta: 0:11:23 time: 0.271562 data_time: 0.034552 memory: 1767 loss: 0.016948 loss/heatmap: 0.006199 loss/offside: 0.010750 acc_pose: 0.960755 2023/05/24 08:49:22 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:49:22 - mmengine - INFO - Saving checkpoint at 130 epochs 2023/05/24 08:49:26 - mmengine - INFO - Evaluating NME... 2023/05/24 08:49:26 - mmengine - INFO - Epoch(val) [130][16/16] NME: 0.032178 data_time: 0.017375 time: 0.247228 2023/05/24 08:49:40 - mmengine - INFO - Epoch(train) [131][50/85] lr: 2.000000e-05 eta: 0:11:00 time: 0.267857 data_time: 0.034029 memory: 1767 loss: 0.016833 loss/heatmap: 0.006144 loss/offside: 0.010690 acc_pose: 0.979844 2023/05/24 08:49:49 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:49:49 - mmengine - INFO - Saving checkpoint at 131 epochs 2023/05/24 08:49:53 - mmengine - INFO - Evaluating NME... 2023/05/24 08:49:53 - mmengine - INFO - Epoch(val) [131][16/16] NME: 0.032134 data_time: 0.017758 time: 0.248389 2023/05/24 08:50:07 - mmengine - INFO - Epoch(train) [132][50/85] lr: 2.000000e-05 eta: 0:10:38 time: 0.260260 data_time: 0.029068 memory: 1767 loss: 0.016970 loss/heatmap: 0.006204 loss/offside: 0.010767 acc_pose: 0.959052 2023/05/24 08:50:15 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:50:15 - mmengine - INFO - Saving checkpoint at 132 epochs 2023/05/24 08:50:20 - mmengine - INFO - Evaluating NME... 2023/05/24 08:50:20 - mmengine - INFO - Epoch(val) [132][16/16] NME: 0.032219 data_time: 0.017182 time: 0.245133 2023/05/24 08:50:33 - mmengine - INFO - Epoch(train) [133][50/85] lr: 2.000000e-05 eta: 0:10:15 time: 0.264110 data_time: 0.029410 memory: 1767 loss: 0.017281 loss/heatmap: 0.006329 loss/offside: 0.010952 acc_pose: 0.971552 2023/05/24 08:50:42 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:50:42 - mmengine - INFO - Saving checkpoint at 133 epochs 2023/05/24 08:50:47 - mmengine - INFO - Evaluating NME... 2023/05/24 08:50:47 - mmengine - INFO - Epoch(val) [133][16/16] NME: 0.032072 data_time: 0.018616 time: 0.254682 2023/05/24 08:51:01 - mmengine - INFO - Epoch(train) [134][50/85] lr: 2.000000e-05 eta: 0:09:53 time: 0.270148 data_time: 0.031010 memory: 1767 loss: 0.016583 loss/heatmap: 0.006057 loss/offside: 0.010526 acc_pose: 0.989080 2023/05/24 08:51:10 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:51:10 - mmengine - INFO - Saving checkpoint at 134 epochs 2023/05/24 08:51:15 - mmengine - INFO - Evaluating NME... 2023/05/24 08:51:15 - mmengine - INFO - Epoch(val) [134][16/16] NME: 0.032039 data_time: 0.017956 time: 0.249723 2023/05/24 08:51:28 - mmengine - INFO - Epoch(train) [135][50/85] lr: 2.000000e-05 eta: 0:09:30 time: 0.266929 data_time: 0.029476 memory: 1767 loss: 0.017330 loss/heatmap: 0.006363 loss/offside: 0.010968 acc_pose: 0.991379 2023/05/24 08:51:37 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:51:37 - mmengine - INFO - Saving checkpoint at 135 epochs 2023/05/24 08:51:42 - mmengine - INFO - Evaluating NME... 2023/05/24 08:51:42 - mmengine - INFO - Epoch(val) [135][16/16] NME: 0.032165 data_time: 0.016819 time: 0.245400 2023/05/24 08:51:55 - mmengine - INFO - Epoch(train) [136][50/85] lr: 2.000000e-05 eta: 0:09:08 time: 0.263022 data_time: 0.029678 memory: 1767 loss: 0.016868 loss/heatmap: 0.006170 loss/offside: 0.010698 acc_pose: 0.988608 2023/05/24 08:52:04 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:52:04 - mmengine - INFO - Saving checkpoint at 136 epochs 2023/05/24 08:52:09 - mmengine - INFO - Evaluating NME... 2023/05/24 08:52:09 - mmengine - INFO - Epoch(val) [136][16/16] NME: 0.032043 data_time: 0.016339 time: 0.241849 2023/05/24 08:52:22 - mmengine - INFO - Epoch(train) [137][50/85] lr: 2.000000e-05 eta: 0:08:45 time: 0.262640 data_time: 0.031812 memory: 1767 loss: 0.016533 loss/heatmap: 0.006054 loss/offside: 0.010479 acc_pose: 0.956445 2023/05/24 08:52:31 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:52:31 - mmengine - INFO - Saving checkpoint at 137 epochs 2023/05/24 08:52:36 - mmengine - INFO - Evaluating NME... 2023/05/24 08:52:36 - mmengine - INFO - Epoch(val) [137][16/16] NME: 0.032179 data_time: 0.017030 time: 0.242888 2023/05/24 08:52:49 - mmengine - INFO - Epoch(train) [138][50/85] lr: 2.000000e-05 eta: 0:08:23 time: 0.261936 data_time: 0.031538 memory: 1767 loss: 0.016763 loss/heatmap: 0.006142 loss/offside: 0.010621 acc_pose: 1.000000 2023/05/24 08:52:57 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:52:57 - mmengine - INFO - Saving checkpoint at 138 epochs 2023/05/24 08:53:02 - mmengine - INFO - Evaluating NME... 2023/05/24 08:53:02 - mmengine - INFO - Epoch(val) [138][16/16] NME: 0.032108 data_time: 0.017607 time: 0.243715 2023/05/24 08:53:15 - mmengine - INFO - Epoch(train) [139][50/85] lr: 2.000000e-05 eta: 0:08:00 time: 0.262181 data_time: 0.032134 memory: 1767 loss: 0.016898 loss/heatmap: 0.006186 loss/offside: 0.010712 acc_pose: 0.989080 2023/05/24 08:53:24 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:53:24 - mmengine - INFO - Saving checkpoint at 139 epochs 2023/05/24 08:53:29 - mmengine - INFO - Evaluating NME... 2023/05/24 08:53:29 - mmengine - INFO - Epoch(val) [139][16/16] NME: 0.032167 data_time: 0.016955 time: 0.246466 2023/05/24 08:53:42 - mmengine - INFO - Epoch(train) [140][50/85] lr: 2.000000e-05 eta: 0:07:38 time: 0.261929 data_time: 0.029347 memory: 1767 loss: 0.016775 loss/heatmap: 0.006127 loss/offside: 0.010649 acc_pose: 0.973830 2023/05/24 08:53:51 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:53:51 - mmengine - INFO - Saving checkpoint at 140 epochs 2023/05/24 08:53:56 - mmengine - INFO - Evaluating NME... 2023/05/24 08:53:56 - mmengine - INFO - Epoch(val) [140][16/16] NME: 0.032161 data_time: 0.016975 time: 0.243882 2023/05/24 08:54:09 - mmengine - INFO - Epoch(train) [141][50/85] lr: 2.000000e-05 eta: 0:07:15 time: 0.270499 data_time: 0.035014 memory: 1767 loss: 0.016562 loss/heatmap: 0.006059 loss/offside: 0.010503 acc_pose: 0.995546 2023/05/24 08:54:18 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:54:18 - mmengine - INFO - Saving checkpoint at 141 epochs 2023/05/24 08:54:23 - mmengine - INFO - Evaluating NME... 2023/05/24 08:54:23 - mmengine - INFO - Epoch(val) [141][16/16] NME: 0.032193 data_time: 0.016949 time: 0.245590 2023/05/24 08:54:27 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:54:36 - mmengine - INFO - Epoch(train) [142][50/85] lr: 2.000000e-05 eta: 0:06:53 time: 0.260091 data_time: 0.029561 memory: 1767 loss: 0.016752 loss/heatmap: 0.006155 loss/offside: 0.010597 acc_pose: 0.984914 2023/05/24 08:54:45 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:54:45 - mmengine - INFO - Saving checkpoint at 142 epochs 2023/05/24 08:54:50 - mmengine - INFO - Evaluating NME... 2023/05/24 08:54:50 - mmengine - INFO - Epoch(val) [142][16/16] NME: 0.032065 data_time: 0.017104 time: 0.246230 2023/05/24 08:55:03 - mmengine - INFO - Epoch(train) [143][50/85] lr: 2.000000e-05 eta: 0:06:30 time: 0.264953 data_time: 0.030031 memory: 1767 loss: 0.016826 loss/heatmap: 0.006164 loss/offside: 0.010662 acc_pose: 0.995690 2023/05/24 08:55:12 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:55:12 - mmengine - INFO - Saving checkpoint at 143 epochs 2023/05/24 08:55:17 - mmengine - INFO - Evaluating NME... 2023/05/24 08:55:17 - mmengine - INFO - Epoch(val) [143][16/16] NME: 0.032080 data_time: 0.018418 time: 0.259224 2023/05/24 08:55:30 - mmengine - INFO - Epoch(train) [144][50/85] lr: 2.000000e-05 eta: 0:06:08 time: 0.260584 data_time: 0.029807 memory: 1767 loss: 0.017167 loss/heatmap: 0.006307 loss/offside: 0.010860 acc_pose: 0.982471 2023/05/24 08:55:39 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:55:39 - mmengine - INFO - Saving checkpoint at 144 epochs 2023/05/24 08:55:44 - mmengine - INFO - Evaluating NME... 2023/05/24 08:55:44 - mmengine - INFO - Epoch(val) [144][16/16] NME: 0.032097 data_time: 0.016756 time: 0.247307 2023/05/24 08:55:57 - mmengine - INFO - Epoch(train) [145][50/85] lr: 2.000000e-05 eta: 0:05:45 time: 0.264971 data_time: 0.029439 memory: 1767 loss: 0.016926 loss/heatmap: 0.006194 loss/offside: 0.010733 acc_pose: 0.982471 2023/05/24 08:56:06 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:56:06 - mmengine - INFO - Saving checkpoint at 145 epochs 2023/05/24 08:56:10 - mmengine - INFO - Evaluating NME... 2023/05/24 08:56:10 - mmengine - INFO - Epoch(val) [145][16/16] NME: 0.032151 data_time: 0.016734 time: 0.241839 2023/05/24 08:56:23 - mmengine - INFO - Epoch(train) [146][50/85] lr: 2.000000e-05 eta: 0:05:23 time: 0.258327 data_time: 0.028799 memory: 1767 loss: 0.016722 loss/heatmap: 0.006108 loss/offside: 0.010614 acc_pose: 0.995402 2023/05/24 08:56:32 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:56:32 - mmengine - INFO - Saving checkpoint at 146 epochs 2023/05/24 08:56:37 - mmengine - INFO - Evaluating NME... 2023/05/24 08:56:37 - mmengine - INFO - Epoch(val) [146][16/16] NME: 0.032133 data_time: 0.018127 time: 0.248173 2023/05/24 08:56:50 - mmengine - INFO - Epoch(train) [147][50/85] lr: 2.000000e-05 eta: 0:05:00 time: 0.260920 data_time: 0.031803 memory: 1767 loss: 0.016530 loss/heatmap: 0.006054 loss/offside: 0.010476 acc_pose: 0.973830 2023/05/24 08:56:59 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:56:59 - mmengine - INFO - Saving checkpoint at 147 epochs 2023/05/24 08:57:04 - mmengine - INFO - Evaluating NME... 2023/05/24 08:57:04 - mmengine - INFO - Epoch(val) [147][16/16] NME: 0.032091 data_time: 0.016996 time: 0.245521 2023/05/24 08:57:17 - mmengine - INFO - Epoch(train) [148][50/85] lr: 2.000000e-05 eta: 0:04:38 time: 0.264287 data_time: 0.033293 memory: 1767 loss: 0.016588 loss/heatmap: 0.006061 loss/offside: 0.010527 acc_pose: 0.993391 2023/05/24 08:57:26 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:57:26 - mmengine - INFO - Saving checkpoint at 148 epochs 2023/05/24 08:57:31 - mmengine - INFO - Evaluating NME... 2023/05/24 08:57:31 - mmengine - INFO - Epoch(val) [148][16/16] NME: 0.032123 data_time: 0.017198 time: 0.249589 2023/05/24 08:57:44 - mmengine - INFO - Epoch(train) [149][50/85] lr: 2.000000e-05 eta: 0:04:15 time: 0.269605 data_time: 0.031360 memory: 1767 loss: 0.016612 loss/heatmap: 0.006078 loss/offside: 0.010534 acc_pose: 0.986310 2023/05/24 08:57:53 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:57:53 - mmengine - INFO - Saving checkpoint at 149 epochs 2023/05/24 08:57:58 - mmengine - INFO - Evaluating NME... 2023/05/24 08:57:58 - mmengine - INFO - Epoch(val) [149][16/16] NME: 0.032132 data_time: 0.017899 time: 0.254212 2023/05/24 08:58:12 - mmengine - INFO - Epoch(train) [150][50/85] lr: 2.000000e-05 eta: 0:03:53 time: 0.276000 data_time: 0.031114 memory: 1767 loss: 0.016934 loss/heatmap: 0.006212 loss/offside: 0.010721 acc_pose: 0.993227 2023/05/24 08:58:21 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:58:21 - mmengine - INFO - Saving checkpoint at 150 epochs 2023/05/24 08:58:26 - mmengine - INFO - Evaluating NME... 2023/05/24 08:58:26 - mmengine - INFO - Epoch(val) [150][16/16] NME: 0.032250 data_time: 0.016730 time: 0.248865 2023/05/24 08:58:40 - mmengine - INFO - Epoch(train) [151][50/85] lr: 2.000000e-05 eta: 0:03:31 time: 0.269214 data_time: 0.031483 memory: 1767 loss: 0.017033 loss/heatmap: 0.006257 loss/offside: 0.010776 acc_pose: 0.984606 2023/05/24 08:58:49 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:58:49 - mmengine - INFO - Saving checkpoint at 151 epochs 2023/05/24 08:58:54 - mmengine - INFO - Evaluating NME... 2023/05/24 08:58:54 - mmengine - INFO - Epoch(val) [151][16/16] NME: 0.032167 data_time: 0.017945 time: 0.252346 2023/05/24 08:59:07 - mmengine - INFO - Epoch(train) [152][50/85] lr: 2.000000e-05 eta: 0:03:08 time: 0.270052 data_time: 0.028937 memory: 1767 loss: 0.017060 loss/heatmap: 0.006258 loss/offside: 0.010802 acc_pose: 0.993227 2023/05/24 08:59:16 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:59:16 - mmengine - INFO - Saving checkpoint at 152 epochs 2023/05/24 08:59:21 - mmengine - INFO - Evaluating NME... 2023/05/24 08:59:21 - mmengine - INFO - Epoch(val) [152][16/16] NME: 0.032085 data_time: 0.018964 time: 0.247140 2023/05/24 08:59:34 - mmengine - INFO - Epoch(train) [153][50/85] lr: 2.000000e-05 eta: 0:02:46 time: 0.265042 data_time: 0.031510 memory: 1767 loss: 0.016919 loss/heatmap: 0.006212 loss/offside: 0.010707 acc_pose: 0.987069 2023/05/24 08:59:42 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:59:43 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 08:59:43 - mmengine - INFO - Saving checkpoint at 153 epochs 2023/05/24 08:59:48 - mmengine - INFO - Evaluating NME... 2023/05/24 08:59:48 - mmengine - INFO - Epoch(val) [153][16/16] NME: 0.032129 data_time: 0.017558 time: 0.247625 2023/05/24 09:00:02 - mmengine - INFO - Epoch(train) [154][50/85] lr: 2.000000e-05 eta: 0:02:23 time: 0.272305 data_time: 0.030281 memory: 1767 loss: 0.016986 loss/heatmap: 0.006247 loss/offside: 0.010739 acc_pose: 0.986925 2023/05/24 09:00:11 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 09:00:11 - mmengine - INFO - Saving checkpoint at 154 epochs 2023/05/24 09:00:16 - mmengine - INFO - Evaluating NME... 2023/05/24 09:00:16 - mmengine - INFO - Epoch(val) [154][16/16] NME: 0.032134 data_time: 0.018098 time: 0.250771 2023/05/24 09:00:30 - mmengine - INFO - Epoch(train) [155][50/85] lr: 2.000000e-05 eta: 0:02:01 time: 0.270730 data_time: 0.031330 memory: 1767 loss: 0.016854 loss/heatmap: 0.006204 loss/offside: 0.010650 acc_pose: 0.991092 2023/05/24 09:00:39 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 09:00:39 - mmengine - INFO - Saving checkpoint at 155 epochs 2023/05/24 09:00:44 - mmengine - INFO - Evaluating NME... 2023/05/24 09:00:44 - mmengine - INFO - Epoch(val) [155][16/16] NME: 0.032128 data_time: 0.017547 time: 0.247426 2023/05/24 09:00:57 - mmengine - INFO - Epoch(train) [156][50/85] lr: 2.000000e-05 eta: 0:01:38 time: 0.275783 data_time: 0.031843 memory: 1767 loss: 0.016626 loss/heatmap: 0.006088 loss/offside: 0.010539 acc_pose: 0.976293 2023/05/24 09:01:06 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 09:01:06 - mmengine - INFO - Saving checkpoint at 156 epochs 2023/05/24 09:01:11 - mmengine - INFO - Evaluating NME... 2023/05/24 09:01:11 - mmengine - INFO - Epoch(val) [156][16/16] NME: 0.032188 data_time: 0.018051 time: 0.252268 2023/05/24 09:01:25 - mmengine - INFO - Epoch(train) [157][50/85] lr: 2.000000e-05 eta: 0:01:16 time: 0.267444 data_time: 0.032518 memory: 1767 loss: 0.017213 loss/heatmap: 0.006322 loss/offside: 0.010891 acc_pose: 0.981999 2023/05/24 09:01:34 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 09:01:34 - mmengine - INFO - Saving checkpoint at 157 epochs 2023/05/24 09:01:39 - mmengine - INFO - Evaluating NME... 2023/05/24 09:01:39 - mmengine - INFO - Epoch(val) [157][16/16] NME: 0.032085 data_time: 0.018409 time: 0.243480 2023/05/24 09:01:52 - mmengine - INFO - Epoch(train) [158][50/85] lr: 2.000000e-05 eta: 0:00:54 time: 0.276644 data_time: 0.030850 memory: 1767 loss: 0.016804 loss/heatmap: 0.006160 loss/offside: 0.010644 acc_pose: 0.984770 2023/05/24 09:02:02 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 09:02:02 - mmengine - INFO - Saving checkpoint at 158 epochs 2023/05/24 09:02:06 - mmengine - INFO - Evaluating NME... 2023/05/24 09:02:06 - mmengine - INFO - Epoch(val) [158][16/16] NME: 0.032185 data_time: 0.017820 time: 0.249426 2023/05/24 09:02:20 - mmengine - INFO - Epoch(train) [159][50/85] lr: 2.000000e-05 eta: 0:00:31 time: 0.270019 data_time: 0.031083 memory: 1767 loss: 0.017039 loss/heatmap: 0.006269 loss/offside: 0.010770 acc_pose: 0.997845 2023/05/24 09:02:29 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 09:02:29 - mmengine - INFO - Saving checkpoint at 159 epochs 2023/05/24 09:02:34 - mmengine - INFO - Evaluating NME... 2023/05/24 09:02:34 - mmengine - INFO - Epoch(val) [159][16/16] NME: 0.032018 data_time: 0.018046 time: 0.250100 2023/05/24 09:02:48 - mmengine - INFO - Epoch(train) [160][50/85] lr: 2.000000e-05 eta: 0:00:09 time: 0.269490 data_time: 0.029697 memory: 1767 loss: 0.016274 loss/heatmap: 0.005958 loss/offside: 0.010316 acc_pose: 0.997845 2023/05/24 09:02:57 - mmengine - INFO - Exp name: td-hm_hrnetv2-w18_skps-1xb64-80e_cofw-256x256_20230524_074949 2023/05/24 09:02:57 - mmengine - INFO - Saving checkpoint at 160 epochs 2023/05/24 09:03:02 - mmengine - INFO - Evaluating NME... 2023/05/24 09:03:02 - mmengine - INFO - Epoch(val) [160][16/16] NME: 0.032155 data_time: 0.017325 time: 0.248020