2022/12/25 20:24:02 - mmengine - INFO - ------------------------------------------------------------ System environment: sys.platform: linux Python: 3.9.13 (main, Aug 25 2022, 23:26:10) [GCC 11.2.0] CUDA available: True numpy_random_seed: 1466011479 GPU 0,1,2,3,4,5,6,7: NVIDIA A100-SXM4-80GB CUDA_HOME: /mnt/petrelfs/share/cuda-11.3 NVCC: Cuda compilation tools, release 11.3, V11.3.109 GCC: gcc (GCC) 5.4.0 PyTorch: 1.11.0 PyTorch compiling details: PyTorch built with: - GCC 7.3 - C++ Version: 201402 - Intel(R) oneAPI Math Kernel Library Version 2021.4-Product Build 20210904 for Intel(R) 64 architecture applications - Intel(R) MKL-DNN v2.5.2 (Git Hash a9302535553c73243c632ad3c4c80beec3d19a1e) - OpenMP 201511 (a.k.a. OpenMP 4.5) - LAPACK is enabled (usually provided by MKL) - NNPACK is enabled - CPU capability usage: AVX2 - CUDA Runtime 11.3 - NVCC architecture flags: -gencode;arch=compute_37,code=sm_37;-gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_61,code=sm_61;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-gencode;arch=compute_80,code=sm_80;-gencode;arch=compute_86,code=sm_86;-gencode;arch=compute_37,code=compute_37 - CuDNN 8.2 - Magma 2.5.2 - Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.3, CUDNN_VERSION=8.2.0, CXX_COMPILER=/opt/rh/devtoolset-7/root/usr/bin/c++, CXX_FLAGS= -Wno-deprecated -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -fopenmp -DNDEBUG -DUSE_KINETO -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DSYMBOLICATE_MOBILE_DEBUG_HANDLE -DEDGE_PROFILER_USE_KINETO -O2 -fPIC -Wno-narrowing -Wall -Wextra -Werror=return-type -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wno-sign-compare -Wno-unused-parameter -Wno-unused-function -Wno-unused-result -Wno-unused-local-typedefs -Wno-strict-overflow -Wno-strict-aliasing -Wno-error=deprecated-declarations -Wno-stringop-overflow -Wno-psabi -Wno-error=pedantic -Wno-error=redundant-decls -Wno-error=old-style-cast -fdiagnostics-color=always -faligned-new -Wno-unused-but-set-variable -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Werror=format -Wno-stringop-overflow, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, TORCH_VERSION=1.11.0, USE_CUDA=ON, USE_CUDNN=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=OFF, USE_MPI=OFF, USE_NCCL=ON, USE_NNPACK=ON, USE_OPENMP=ON, USE_ROCM=OFF, TorchVision: 0.12.0 OpenCV: 4.6.0 MMEngine: 0.3.2 Runtime environment: cudnn_benchmark: False mp_cfg: {'mp_start_method': 'fork', 'opencv_num_threads': 0} dist_cfg: {'backend': 'nccl'} seed: None diff_rank_seed: False deterministic: False Distributed launcher: pytorch Distributed training: True GPU number: 8 ------------------------------------------------------------ 2022/12/25 20:24:02 - mmengine - INFO - Config: default_scope = 'mmaction' default_hooks = dict( runtime_info=dict(type='RuntimeInfoHook'), timer=dict(type='IterTimerHook'), logger=dict(type='LoggerHook', interval=100, ignore_last=False), param_scheduler=dict(type='ParamSchedulerHook'), checkpoint=dict(type='CheckpointHook', interval=1, save_best='auto'), sampler_seed=dict(type='DistSamplerSeedHook'), sync_buffers=dict(type='SyncBuffersHook')) env_cfg = dict( cudnn_benchmark=False, mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0), dist_cfg=dict(backend='nccl')) log_processor = dict(type='LogProcessor', window_size=20, by_epoch=True) vis_backends = [dict(type='LocalVisBackend')] visualizer = dict( type='ActionVisualizer', vis_backends=[dict(type='LocalVisBackend')]) log_level = 'INFO' load_from = None resume = False model = dict( type='RecognizerGCN', backbone=dict( type='STGCN', gcn_adaptive='init', gcn_with_res=True, tcn_type='mstcn', graph_cfg=dict(layout='coco', mode='spatial')), cls_head=dict(type='GCNHead', num_classes=60, in_channels=256)) dataset_type = 'PoseDataset' ann_file = 'data/skeleton/ntu60_2d.pkl' train_pipeline = [ dict(type='PreNormalize2D'), dict(type='GenSkeFeat', dataset='coco', feats=['bm']), dict(type='UniformSampleFrames', clip_len=100), dict(type='PoseDecode'), dict(type='FormatGCNInput', num_person=2), dict(type='PackActionInputs') ] val_pipeline = [ dict(type='PreNormalize2D'), dict(type='GenSkeFeat', dataset='coco', feats=['bm']), dict( type='UniformSampleFrames', clip_len=100, num_clips=1, test_mode=True), dict(type='PoseDecode'), dict(type='FormatGCNInput', num_person=2), dict(type='PackActionInputs') ] test_pipeline = [ dict(type='PreNormalize2D'), dict(type='GenSkeFeat', dataset='coco', feats=['bm']), dict( type='UniformSampleFrames', clip_len=100, num_clips=10, test_mode=True), dict(type='PoseDecode'), dict(type='FormatGCNInput', num_person=2), dict(type='PackActionInputs') ] train_dataloader = dict( batch_size=16, num_workers=2, persistent_workers=True, sampler=dict(type='DefaultSampler', shuffle=True), dataset=dict( type='RepeatDataset', times=5, dataset=dict( type='PoseDataset', ann_file='data/skeleton/ntu60_2d.pkl', pipeline=[ dict(type='PreNormalize2D'), dict(type='GenSkeFeat', dataset='coco', feats=['bm']), dict(type='UniformSampleFrames', clip_len=100), dict(type='PoseDecode'), dict(type='FormatGCNInput', num_person=2), dict(type='PackActionInputs') ], split='xsub_train'))) val_dataloader = dict( batch_size=16, num_workers=2, persistent_workers=True, sampler=dict(type='DefaultSampler', shuffle=False), dataset=dict( type='PoseDataset', ann_file='data/skeleton/ntu60_2d.pkl', pipeline=[ dict(type='PreNormalize2D'), dict(type='GenSkeFeat', dataset='coco', feats=['bm']), dict( type='UniformSampleFrames', clip_len=100, num_clips=1, test_mode=True), dict(type='PoseDecode'), dict(type='FormatGCNInput', num_person=2), dict(type='PackActionInputs') ], split='xsub_val', test_mode=True)) test_dataloader = dict( batch_size=1, num_workers=2, persistent_workers=True, sampler=dict(type='DefaultSampler', shuffle=False), dataset=dict( type='PoseDataset', ann_file='data/skeleton/ntu60_2d.pkl', pipeline=[ dict(type='PreNormalize2D'), dict(type='GenSkeFeat', dataset='coco', feats=['bm']), dict( type='UniformSampleFrames', clip_len=100, num_clips=10, test_mode=True), dict(type='PoseDecode'), dict(type='FormatGCNInput', num_person=2), dict(type='PackActionInputs') ], split='xsub_val', test_mode=True)) val_evaluator = [dict(type='AccMetric')] test_evaluator = [dict(type='AccMetric')] train_cfg = dict( type='EpochBasedTrainLoop', max_epochs=16, val_begin=1, val_interval=1) val_cfg = dict(type='ValLoop') test_cfg = dict(type='TestLoop') param_scheduler = [ dict( type='CosineAnnealingLR', eta_min=0, T_max=16, by_epoch=True, convert_to_iter_based=True) ] optim_wrapper = dict( optimizer=dict( type='SGD', lr=0.1, momentum=0.9, weight_decay=0.0005, nesterov=True)) auto_scale_lr = dict(enable=False, base_batch_size=128) launcher = 'pytorch' work_dir = './work_dirs/stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d' randomness = dict(seed=None, diff_rank_seed=False, deterministic=False) 2022/12/25 20:24:02 - mmengine - INFO - Result has been saved to /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d/modules_statistic_results.json 2022/12/25 20:24:02 - 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 -------------------- before_val_iter: (NORMAL ) IterTimerHook -------------------- after_val_iter: (NORMAL ) IterTimerHook (BELOW_NORMAL) LoggerHook -------------------- after_val_epoch: (VERY_HIGH ) RuntimeInfoHook (NORMAL ) IterTimerHook (BELOW_NORMAL) LoggerHook (VERY_LOW ) CheckpointHook -------------------- before_test_epoch: (NORMAL ) IterTimerHook -------------------- before_test_iter: (NORMAL ) IterTimerHook -------------------- after_test_iter: (NORMAL ) IterTimerHook (BELOW_NORMAL) LoggerHook -------------------- after_test_epoch: (VERY_HIGH ) RuntimeInfoHook (NORMAL ) IterTimerHook (BELOW_NORMAL) LoggerHook -------------------- after_run: (BELOW_NORMAL) LoggerHook -------------------- Name of parameter - Initialization information backbone.data_bn.weight - torch.Size([51]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.data_bn.bias - torch.Size([51]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.gcn.A - torch.Size([3, 17, 17]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.gcn.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.gcn.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.gcn.conv.weight - torch.Size([192, 3, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.gcn.conv.bias - torch.Size([192]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.gcn.down.0.weight - torch.Size([64, 3, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.gcn.down.0.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.gcn.down.1.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.gcn.down.1.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.tcn.branches.0.0.weight - torch.Size([14, 64, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.tcn.branches.0.0.bias - torch.Size([14]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.tcn.branches.0.1.weight - torch.Size([14]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.tcn.branches.0.1.bias - torch.Size([14]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.tcn.branches.0.3.conv.weight - torch.Size([14, 14, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.tcn.branches.0.3.conv.bias - torch.Size([14]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.tcn.branches.1.0.weight - torch.Size([10, 64, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.tcn.branches.1.0.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.tcn.branches.1.1.weight - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.tcn.branches.1.1.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.tcn.branches.1.3.conv.weight - torch.Size([10, 10, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.tcn.branches.1.3.conv.bias - torch.Size([10]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.tcn.branches.2.0.weight - torch.Size([10, 64, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.tcn.branches.2.0.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.tcn.branches.2.1.weight - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.tcn.branches.2.1.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.tcn.branches.2.3.conv.weight - torch.Size([10, 10, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.tcn.branches.2.3.conv.bias - torch.Size([10]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.tcn.branches.3.0.weight - torch.Size([10, 64, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.tcn.branches.3.0.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.tcn.branches.3.1.weight - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.tcn.branches.3.1.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.tcn.branches.3.3.conv.weight - torch.Size([10, 10, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.tcn.branches.3.3.conv.bias - torch.Size([10]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.tcn.branches.4.0.weight - torch.Size([10, 64, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.tcn.branches.4.0.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.tcn.branches.4.1.weight - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.tcn.branches.4.1.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.tcn.branches.5.weight - torch.Size([10, 64, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.tcn.branches.5.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.tcn.transform.0.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.tcn.transform.0.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.tcn.transform.2.weight - torch.Size([64, 64, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.tcn.transform.2.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.tcn.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.tcn.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.gcn.A - torch.Size([3, 17, 17]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.gcn.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.gcn.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.gcn.conv.weight - torch.Size([192, 64, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.gcn.conv.bias - torch.Size([192]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.tcn.branches.0.0.weight - torch.Size([14, 64, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.tcn.branches.0.0.bias - torch.Size([14]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.tcn.branches.0.1.weight - torch.Size([14]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.tcn.branches.0.1.bias - torch.Size([14]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.tcn.branches.0.3.conv.weight - torch.Size([14, 14, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.1.tcn.branches.0.3.conv.bias - torch.Size([14]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.1.tcn.branches.1.0.weight - torch.Size([10, 64, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.tcn.branches.1.0.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.tcn.branches.1.1.weight - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.tcn.branches.1.1.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.tcn.branches.1.3.conv.weight - torch.Size([10, 10, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.1.tcn.branches.1.3.conv.bias - torch.Size([10]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.1.tcn.branches.2.0.weight - torch.Size([10, 64, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.tcn.branches.2.0.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.tcn.branches.2.1.weight - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.tcn.branches.2.1.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.tcn.branches.2.3.conv.weight - torch.Size([10, 10, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.1.tcn.branches.2.3.conv.bias - torch.Size([10]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.1.tcn.branches.3.0.weight - torch.Size([10, 64, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.tcn.branches.3.0.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.tcn.branches.3.1.weight - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.tcn.branches.3.1.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.tcn.branches.3.3.conv.weight - torch.Size([10, 10, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.1.tcn.branches.3.3.conv.bias - torch.Size([10]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.1.tcn.branches.4.0.weight - torch.Size([10, 64, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.tcn.branches.4.0.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.tcn.branches.4.1.weight - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.tcn.branches.4.1.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.tcn.branches.5.weight - torch.Size([10, 64, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.tcn.branches.5.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.tcn.transform.0.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.tcn.transform.0.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.tcn.transform.2.weight - torch.Size([64, 64, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.tcn.transform.2.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.tcn.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.tcn.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.gcn.A - torch.Size([3, 17, 17]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.gcn.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.gcn.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.gcn.conv.weight - torch.Size([192, 64, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.gcn.conv.bias - torch.Size([192]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.tcn.branches.0.0.weight - torch.Size([14, 64, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.tcn.branches.0.0.bias - torch.Size([14]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.tcn.branches.0.1.weight - torch.Size([14]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.tcn.branches.0.1.bias - torch.Size([14]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.tcn.branches.0.3.conv.weight - torch.Size([14, 14, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.2.tcn.branches.0.3.conv.bias - torch.Size([14]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.2.tcn.branches.1.0.weight - torch.Size([10, 64, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.tcn.branches.1.0.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.tcn.branches.1.1.weight - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.tcn.branches.1.1.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.tcn.branches.1.3.conv.weight - torch.Size([10, 10, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.2.tcn.branches.1.3.conv.bias - torch.Size([10]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.2.tcn.branches.2.0.weight - torch.Size([10, 64, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.tcn.branches.2.0.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.tcn.branches.2.1.weight - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.tcn.branches.2.1.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.tcn.branches.2.3.conv.weight - torch.Size([10, 10, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.2.tcn.branches.2.3.conv.bias - torch.Size([10]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.2.tcn.branches.3.0.weight - torch.Size([10, 64, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.tcn.branches.3.0.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.tcn.branches.3.1.weight - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.tcn.branches.3.1.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.tcn.branches.3.3.conv.weight - torch.Size([10, 10, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.2.tcn.branches.3.3.conv.bias - torch.Size([10]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.2.tcn.branches.4.0.weight - torch.Size([10, 64, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.tcn.branches.4.0.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.tcn.branches.4.1.weight - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.tcn.branches.4.1.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.tcn.branches.5.weight - torch.Size([10, 64, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.tcn.branches.5.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.tcn.transform.0.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.tcn.transform.0.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.tcn.transform.2.weight - torch.Size([64, 64, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.tcn.transform.2.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.tcn.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.tcn.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.gcn.A - torch.Size([3, 17, 17]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.gcn.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.gcn.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.gcn.conv.weight - torch.Size([192, 64, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.gcn.conv.bias - torch.Size([192]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.tcn.branches.0.0.weight - torch.Size([14, 64, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.tcn.branches.0.0.bias - torch.Size([14]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.tcn.branches.0.1.weight - torch.Size([14]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.tcn.branches.0.1.bias - torch.Size([14]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.tcn.branches.0.3.conv.weight - torch.Size([14, 14, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.3.tcn.branches.0.3.conv.bias - torch.Size([14]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.3.tcn.branches.1.0.weight - torch.Size([10, 64, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.tcn.branches.1.0.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.tcn.branches.1.1.weight - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.tcn.branches.1.1.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.tcn.branches.1.3.conv.weight - torch.Size([10, 10, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.3.tcn.branches.1.3.conv.bias - torch.Size([10]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.3.tcn.branches.2.0.weight - torch.Size([10, 64, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.tcn.branches.2.0.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.tcn.branches.2.1.weight - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.tcn.branches.2.1.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.tcn.branches.2.3.conv.weight - torch.Size([10, 10, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.3.tcn.branches.2.3.conv.bias - torch.Size([10]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.3.tcn.branches.3.0.weight - torch.Size([10, 64, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.tcn.branches.3.0.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.tcn.branches.3.1.weight - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.tcn.branches.3.1.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.tcn.branches.3.3.conv.weight - torch.Size([10, 10, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.3.tcn.branches.3.3.conv.bias - torch.Size([10]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.3.tcn.branches.4.0.weight - torch.Size([10, 64, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.tcn.branches.4.0.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.tcn.branches.4.1.weight - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.tcn.branches.4.1.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.tcn.branches.5.weight - torch.Size([10, 64, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.tcn.branches.5.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.tcn.transform.0.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.tcn.transform.0.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.tcn.transform.2.weight - torch.Size([64, 64, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.tcn.transform.2.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.tcn.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.tcn.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.gcn.A - torch.Size([3, 17, 17]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.gcn.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.gcn.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.gcn.conv.weight - torch.Size([384, 64, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.gcn.conv.bias - torch.Size([384]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.gcn.down.0.weight - torch.Size([128, 64, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.gcn.down.0.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.gcn.down.1.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.gcn.down.1.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.tcn.branches.0.0.weight - torch.Size([23, 128, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.tcn.branches.0.0.bias - torch.Size([23]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.tcn.branches.0.1.weight - torch.Size([23]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.tcn.branches.0.1.bias - torch.Size([23]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.tcn.branches.0.3.conv.weight - torch.Size([23, 23, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.tcn.branches.0.3.conv.bias - torch.Size([23]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.tcn.branches.1.0.weight - torch.Size([21, 128, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.tcn.branches.1.0.bias - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.tcn.branches.1.1.weight - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.tcn.branches.1.1.bias - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.tcn.branches.1.3.conv.weight - torch.Size([21, 21, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.tcn.branches.1.3.conv.bias - torch.Size([21]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.tcn.branches.2.0.weight - torch.Size([21, 128, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.tcn.branches.2.0.bias - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.tcn.branches.2.1.weight - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.tcn.branches.2.1.bias - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.tcn.branches.2.3.conv.weight - torch.Size([21, 21, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.tcn.branches.2.3.conv.bias - torch.Size([21]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.tcn.branches.3.0.weight - torch.Size([21, 128, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.tcn.branches.3.0.bias - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.tcn.branches.3.1.weight - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.tcn.branches.3.1.bias - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.tcn.branches.3.3.conv.weight - torch.Size([21, 21, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.tcn.branches.3.3.conv.bias - torch.Size([21]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.tcn.branches.4.0.weight - torch.Size([21, 128, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.tcn.branches.4.0.bias - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.tcn.branches.4.1.weight - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.tcn.branches.4.1.bias - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.tcn.branches.5.weight - torch.Size([21, 128, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.tcn.branches.5.bias - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.tcn.transform.0.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.tcn.transform.0.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.tcn.transform.2.weight - torch.Size([128, 128, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.tcn.transform.2.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.tcn.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.tcn.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.residual.conv.weight - torch.Size([128, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.residual.conv.bias - torch.Size([128]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.residual.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.residual.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.gcn.A - torch.Size([3, 17, 17]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.gcn.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.gcn.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.gcn.conv.weight - torch.Size([384, 128, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.gcn.conv.bias - torch.Size([384]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.tcn.branches.0.0.weight - torch.Size([23, 128, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.tcn.branches.0.0.bias - torch.Size([23]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.tcn.branches.0.1.weight - torch.Size([23]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.tcn.branches.0.1.bias - torch.Size([23]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.tcn.branches.0.3.conv.weight - torch.Size([23, 23, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.5.tcn.branches.0.3.conv.bias - torch.Size([23]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.5.tcn.branches.1.0.weight - torch.Size([21, 128, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.tcn.branches.1.0.bias - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.tcn.branches.1.1.weight - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.tcn.branches.1.1.bias - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.tcn.branches.1.3.conv.weight - torch.Size([21, 21, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.5.tcn.branches.1.3.conv.bias - torch.Size([21]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.5.tcn.branches.2.0.weight - torch.Size([21, 128, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.tcn.branches.2.0.bias - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.tcn.branches.2.1.weight - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.tcn.branches.2.1.bias - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.tcn.branches.2.3.conv.weight - torch.Size([21, 21, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.5.tcn.branches.2.3.conv.bias - torch.Size([21]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.5.tcn.branches.3.0.weight - torch.Size([21, 128, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.tcn.branches.3.0.bias - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.tcn.branches.3.1.weight - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.tcn.branches.3.1.bias - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.tcn.branches.3.3.conv.weight - torch.Size([21, 21, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.5.tcn.branches.3.3.conv.bias - torch.Size([21]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.5.tcn.branches.4.0.weight - torch.Size([21, 128, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.tcn.branches.4.0.bias - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.tcn.branches.4.1.weight - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.tcn.branches.4.1.bias - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.tcn.branches.5.weight - torch.Size([21, 128, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.tcn.branches.5.bias - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.tcn.transform.0.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.tcn.transform.0.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.tcn.transform.2.weight - torch.Size([128, 128, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.tcn.transform.2.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.tcn.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.tcn.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.gcn.A - torch.Size([3, 17, 17]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.gcn.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.gcn.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.gcn.conv.weight - torch.Size([384, 128, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.gcn.conv.bias - torch.Size([384]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.tcn.branches.0.0.weight - torch.Size([23, 128, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.tcn.branches.0.0.bias - torch.Size([23]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.tcn.branches.0.1.weight - torch.Size([23]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.tcn.branches.0.1.bias - torch.Size([23]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.tcn.branches.0.3.conv.weight - torch.Size([23, 23, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.6.tcn.branches.0.3.conv.bias - torch.Size([23]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.6.tcn.branches.1.0.weight - torch.Size([21, 128, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.tcn.branches.1.0.bias - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.tcn.branches.1.1.weight - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.tcn.branches.1.1.bias - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.tcn.branches.1.3.conv.weight - torch.Size([21, 21, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.6.tcn.branches.1.3.conv.bias - torch.Size([21]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.6.tcn.branches.2.0.weight - torch.Size([21, 128, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.tcn.branches.2.0.bias - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.tcn.branches.2.1.weight - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.tcn.branches.2.1.bias - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.tcn.branches.2.3.conv.weight - torch.Size([21, 21, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.6.tcn.branches.2.3.conv.bias - torch.Size([21]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.6.tcn.branches.3.0.weight - torch.Size([21, 128, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.tcn.branches.3.0.bias - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.tcn.branches.3.1.weight - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.tcn.branches.3.1.bias - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.tcn.branches.3.3.conv.weight - torch.Size([21, 21, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.6.tcn.branches.3.3.conv.bias - torch.Size([21]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.6.tcn.branches.4.0.weight - torch.Size([21, 128, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.tcn.branches.4.0.bias - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.tcn.branches.4.1.weight - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.tcn.branches.4.1.bias - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.tcn.branches.5.weight - torch.Size([21, 128, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.tcn.branches.5.bias - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.tcn.transform.0.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.tcn.transform.0.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.tcn.transform.2.weight - torch.Size([128, 128, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.tcn.transform.2.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.tcn.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.tcn.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.gcn.A - torch.Size([3, 17, 17]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.gcn.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.gcn.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.gcn.conv.weight - torch.Size([768, 128, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.gcn.conv.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.gcn.down.0.weight - torch.Size([256, 128, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.gcn.down.0.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.gcn.down.1.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.gcn.down.1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.tcn.branches.0.0.weight - torch.Size([46, 256, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.tcn.branches.0.0.bias - torch.Size([46]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.tcn.branches.0.1.weight - torch.Size([46]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.tcn.branches.0.1.bias - torch.Size([46]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.tcn.branches.0.3.conv.weight - torch.Size([46, 46, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.tcn.branches.0.3.conv.bias - torch.Size([46]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.tcn.branches.1.0.weight - torch.Size([42, 256, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.tcn.branches.1.0.bias - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.tcn.branches.1.1.weight - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.tcn.branches.1.1.bias - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.tcn.branches.1.3.conv.weight - torch.Size([42, 42, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.tcn.branches.1.3.conv.bias - torch.Size([42]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.tcn.branches.2.0.weight - torch.Size([42, 256, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.tcn.branches.2.0.bias - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.tcn.branches.2.1.weight - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.tcn.branches.2.1.bias - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.tcn.branches.2.3.conv.weight - torch.Size([42, 42, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.tcn.branches.2.3.conv.bias - torch.Size([42]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.tcn.branches.3.0.weight - torch.Size([42, 256, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.tcn.branches.3.0.bias - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.tcn.branches.3.1.weight - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.tcn.branches.3.1.bias - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.tcn.branches.3.3.conv.weight - torch.Size([42, 42, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.tcn.branches.3.3.conv.bias - torch.Size([42]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.tcn.branches.4.0.weight - torch.Size([42, 256, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.tcn.branches.4.0.bias - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.tcn.branches.4.1.weight - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.tcn.branches.4.1.bias - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.tcn.branches.5.weight - torch.Size([42, 256, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.tcn.branches.5.bias - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.tcn.transform.0.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.tcn.transform.0.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.tcn.transform.2.weight - torch.Size([256, 256, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.tcn.transform.2.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.tcn.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.tcn.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.residual.conv.weight - torch.Size([256, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.residual.conv.bias - torch.Size([256]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.residual.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.residual.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.gcn.A - torch.Size([3, 17, 17]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.gcn.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.gcn.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.gcn.conv.weight - torch.Size([768, 256, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.gcn.conv.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.tcn.branches.0.0.weight - torch.Size([46, 256, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.tcn.branches.0.0.bias - torch.Size([46]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.tcn.branches.0.1.weight - torch.Size([46]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.tcn.branches.0.1.bias - torch.Size([46]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.tcn.branches.0.3.conv.weight - torch.Size([46, 46, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.8.tcn.branches.0.3.conv.bias - torch.Size([46]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.8.tcn.branches.1.0.weight - torch.Size([42, 256, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.tcn.branches.1.0.bias - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.tcn.branches.1.1.weight - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.tcn.branches.1.1.bias - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.tcn.branches.1.3.conv.weight - torch.Size([42, 42, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.8.tcn.branches.1.3.conv.bias - torch.Size([42]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.8.tcn.branches.2.0.weight - torch.Size([42, 256, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.tcn.branches.2.0.bias - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.tcn.branches.2.1.weight - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.tcn.branches.2.1.bias - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.tcn.branches.2.3.conv.weight - torch.Size([42, 42, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.8.tcn.branches.2.3.conv.bias - torch.Size([42]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.8.tcn.branches.3.0.weight - torch.Size([42, 256, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.tcn.branches.3.0.bias - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.tcn.branches.3.1.weight - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.tcn.branches.3.1.bias - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.tcn.branches.3.3.conv.weight - torch.Size([42, 42, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.8.tcn.branches.3.3.conv.bias - torch.Size([42]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.8.tcn.branches.4.0.weight - torch.Size([42, 256, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.tcn.branches.4.0.bias - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.tcn.branches.4.1.weight - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.tcn.branches.4.1.bias - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.tcn.branches.5.weight - torch.Size([42, 256, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.tcn.branches.5.bias - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.tcn.transform.0.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.tcn.transform.0.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.tcn.transform.2.weight - torch.Size([256, 256, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.tcn.transform.2.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.tcn.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.tcn.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.gcn.A - torch.Size([3, 17, 17]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.gcn.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.gcn.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.gcn.conv.weight - torch.Size([768, 256, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.gcn.conv.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.tcn.branches.0.0.weight - torch.Size([46, 256, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.tcn.branches.0.0.bias - torch.Size([46]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.tcn.branches.0.1.weight - torch.Size([46]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.tcn.branches.0.1.bias - torch.Size([46]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.tcn.branches.0.3.conv.weight - torch.Size([46, 46, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.9.tcn.branches.0.3.conv.bias - torch.Size([46]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.9.tcn.branches.1.0.weight - torch.Size([42, 256, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.tcn.branches.1.0.bias - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.tcn.branches.1.1.weight - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.tcn.branches.1.1.bias - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.tcn.branches.1.3.conv.weight - torch.Size([42, 42, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.9.tcn.branches.1.3.conv.bias - torch.Size([42]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.9.tcn.branches.2.0.weight - torch.Size([42, 256, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.tcn.branches.2.0.bias - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.tcn.branches.2.1.weight - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.tcn.branches.2.1.bias - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.tcn.branches.2.3.conv.weight - torch.Size([42, 42, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.9.tcn.branches.2.3.conv.bias - torch.Size([42]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.9.tcn.branches.3.0.weight - torch.Size([42, 256, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.tcn.branches.3.0.bias - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.tcn.branches.3.1.weight - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.tcn.branches.3.1.bias - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.tcn.branches.3.3.conv.weight - torch.Size([42, 42, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.9.tcn.branches.3.3.conv.bias - torch.Size([42]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.9.tcn.branches.4.0.weight - torch.Size([42, 256, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.tcn.branches.4.0.bias - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.tcn.branches.4.1.weight - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.tcn.branches.4.1.bias - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.tcn.branches.5.weight - torch.Size([42, 256, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.tcn.branches.5.bias - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.tcn.transform.0.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.tcn.transform.0.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.tcn.transform.2.weight - torch.Size([256, 256, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.tcn.transform.2.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.tcn.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.tcn.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN cls_head.fc.weight - torch.Size([60, 256]): NormalInit: mean=0, std=0.01, bias=0 cls_head.fc.bias - torch.Size([60]): NormalInit: mean=0, std=0.01, bias=0 2022/12/25 20:24:34 - mmengine - INFO - Checkpoints will be saved to /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d. 2022/12/25 20:24:46 - mmengine - INFO - Epoch(train) [1][ 100/1567] lr: 9.9996e-02 eta: 0:46:38 time: 0.0882 data_time: 0.0062 memory: 1827 loss: 3.0624 top1_acc: 0.1250 top5_acc: 0.3125 loss_cls: 3.0624 2022/12/25 20:24:54 - mmengine - INFO - Epoch(train) [1][ 200/1567] lr: 9.9984e-02 eta: 0:40:57 time: 0.0863 data_time: 0.0069 memory: 1827 loss: 1.8880 top1_acc: 0.5000 top5_acc: 0.8750 loss_cls: 1.8880 2022/12/25 20:25:03 - mmengine - INFO - Epoch(train) [1][ 300/1567] lr: 9.9965e-02 eta: 0:39:11 time: 0.0851 data_time: 0.0065 memory: 1827 loss: 1.3460 top1_acc: 0.4375 top5_acc: 1.0000 loss_cls: 1.3460 2022/12/25 20:25:11 - mmengine - INFO - Epoch(train) [1][ 400/1567] lr: 9.9938e-02 eta: 0:38:13 time: 0.0871 data_time: 0.0063 memory: 1827 loss: 1.0693 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 1.0693 2022/12/25 20:25:20 - mmengine - INFO - Epoch(train) [1][ 500/1567] lr: 9.9902e-02 eta: 0:37:25 time: 0.0865 data_time: 0.0065 memory: 1827 loss: 1.0670 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.0670 2022/12/25 20:25:29 - mmengine - INFO - Epoch(train) [1][ 600/1567] lr: 9.9859e-02 eta: 0:36:53 time: 0.0853 data_time: 0.0063 memory: 1827 loss: 0.9107 top1_acc: 0.6250 top5_acc: 1.0000 loss_cls: 0.9107 2022/12/25 20:25:37 - mmengine - INFO - Epoch(train) [1][ 700/1567] lr: 9.9808e-02 eta: 0:36:25 time: 0.0854 data_time: 0.0064 memory: 1827 loss: 0.8449 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.8449 2022/12/25 20:25:46 - mmengine - INFO - Epoch(train) [1][ 800/1567] lr: 9.9750e-02 eta: 0:36:11 time: 0.0861 data_time: 0.0063 memory: 1827 loss: 0.7628 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.7628 2022/12/25 20:25:55 - mmengine - INFO - Epoch(train) [1][ 900/1567] lr: 9.9683e-02 eta: 0:35:54 time: 0.0876 data_time: 0.0064 memory: 1827 loss: 0.8310 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 0.8310 2022/12/25 20:26:03 - mmengine - INFO - Exp name: stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d_20221225_202355 2022/12/25 20:26:03 - mmengine - INFO - Epoch(train) [1][1000/1567] lr: 9.9609e-02 eta: 0:35:35 time: 0.0847 data_time: 0.0069 memory: 1827 loss: 0.6596 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.6596 2022/12/25 20:26:12 - mmengine - INFO - Epoch(train) [1][1100/1567] lr: 9.9527e-02 eta: 0:35:21 time: 0.0888 data_time: 0.0067 memory: 1827 loss: 0.6160 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.6160 2022/12/25 20:26:20 - mmengine - INFO - Epoch(train) [1][1200/1567] lr: 9.9437e-02 eta: 0:35:10 time: 0.0856 data_time: 0.0061 memory: 1827 loss: 0.6472 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.6472 2022/12/25 20:26:29 - mmengine - INFO - Epoch(train) [1][1300/1567] lr: 9.9339e-02 eta: 0:35:02 time: 0.0892 data_time: 0.0067 memory: 1827 loss: 0.6343 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.6343 2022/12/25 20:26:38 - mmengine - INFO - Epoch(train) [1][1400/1567] lr: 9.9234e-02 eta: 0:34:51 time: 0.0884 data_time: 0.0069 memory: 1827 loss: 0.5772 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.5772 2022/12/25 20:26:47 - mmengine - INFO - Epoch(train) [1][1500/1567] lr: 9.9121e-02 eta: 0:34:39 time: 0.0884 data_time: 0.0068 memory: 1827 loss: 0.5735 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.5735 2022/12/25 20:26:53 - mmengine - INFO - Exp name: stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d_20221225_202355 2022/12/25 20:26:53 - mmengine - INFO - Epoch(train) [1][1567/1567] lr: 9.9040e-02 eta: 0:34:32 time: 0.0891 data_time: 0.0064 memory: 1827 loss: 0.8287 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.8287 2022/12/25 20:26:53 - mmengine - INFO - Saving checkpoint at 1 epochs 2022/12/25 20:26:56 - mmengine - INFO - Epoch(val) [1][100/129] eta: 0:00:00 time: 0.0263 data_time: 0.0061 memory: 263 2022/12/25 20:26:57 - mmengine - INFO - Epoch(val) [1][129/129] acc/top1: 0.5510 acc/top5: 0.8925 acc/mean1: 0.5508 2022/12/25 20:26:57 - mmengine - INFO - The best checkpoint with 0.5510 acc/top1 at 1 epoch is saved to best_acc/top1_epoch_1.pth. 2022/12/25 20:27:06 - mmengine - INFO - Epoch(train) [2][ 100/1567] lr: 9.8914e-02 eta: 0:34:24 time: 0.0870 data_time: 0.0072 memory: 1827 loss: 0.6802 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.6802 2022/12/25 20:27:15 - mmengine - INFO - Epoch(train) [2][ 200/1567] lr: 9.8781e-02 eta: 0:34:15 time: 0.0893 data_time: 0.0068 memory: 1827 loss: 0.4867 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4867 2022/12/25 20:27:24 - mmengine - INFO - Epoch(train) [2][ 300/1567] lr: 9.8639e-02 eta: 0:34:06 time: 0.0865 data_time: 0.0069 memory: 1827 loss: 0.5011 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 0.5011 2022/12/25 20:27:32 - mmengine - INFO - Epoch(train) [2][ 400/1567] lr: 9.8491e-02 eta: 0:33:56 time: 0.0862 data_time: 0.0067 memory: 1827 loss: 0.5622 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.5622 2022/12/25 20:27:35 - mmengine - INFO - Exp name: stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d_20221225_202355 2022/12/25 20:27:41 - mmengine - INFO - Epoch(train) [2][ 500/1567] lr: 9.8334e-02 eta: 0:33:49 time: 0.0896 data_time: 0.0066 memory: 1827 loss: 0.4930 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.4930 2022/12/25 20:27:50 - mmengine - INFO - Epoch(train) [2][ 600/1567] lr: 9.8170e-02 eta: 0:33:40 time: 0.0890 data_time: 0.0068 memory: 1827 loss: 0.5742 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.5742 2022/12/25 20:27:59 - mmengine - INFO - Epoch(train) [2][ 700/1567] lr: 9.7998e-02 eta: 0:33:30 time: 0.0855 data_time: 0.0065 memory: 1827 loss: 0.4745 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.4745 2022/12/25 20:28:07 - mmengine - INFO - Epoch(train) [2][ 800/1567] lr: 9.7819e-02 eta: 0:33:18 time: 0.0857 data_time: 0.0066 memory: 1827 loss: 0.4890 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.4890 2022/12/25 20:28:16 - mmengine - INFO - Epoch(train) [2][ 900/1567] lr: 9.7632e-02 eta: 0:33:07 time: 0.0854 data_time: 0.0067 memory: 1827 loss: 0.5369 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.5369 2022/12/25 20:28:25 - mmengine - INFO - Epoch(train) [2][1000/1567] lr: 9.7438e-02 eta: 0:32:57 time: 0.0853 data_time: 0.0065 memory: 1827 loss: 0.4083 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.4083 2022/12/25 20:28:33 - mmengine - INFO - Epoch(train) [2][1100/1567] lr: 9.7236e-02 eta: 0:32:47 time: 0.0845 data_time: 0.0068 memory: 1827 loss: 0.4506 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4506 2022/12/25 20:28:42 - mmengine - INFO - Epoch(train) [2][1200/1567] lr: 9.7027e-02 eta: 0:32:37 time: 0.0862 data_time: 0.0068 memory: 1827 loss: 0.4846 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4846 2022/12/25 20:28:51 - mmengine - INFO - Epoch(train) [2][1300/1567] lr: 9.6810e-02 eta: 0:32:28 time: 0.0872 data_time: 0.0074 memory: 1827 loss: 0.5433 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.5433 2022/12/25 20:28:59 - mmengine - INFO - Epoch(train) [2][1400/1567] lr: 9.6587e-02 eta: 0:32:19 time: 0.0885 data_time: 0.0064 memory: 1827 loss: 0.3974 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3974 2022/12/25 20:29:02 - mmengine - INFO - Exp name: stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d_20221225_202355 2022/12/25 20:29:08 - mmengine - INFO - Epoch(train) [2][1500/1567] lr: 9.6355e-02 eta: 0:32:11 time: 0.0916 data_time: 0.0063 memory: 1827 loss: 0.4644 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.4644 2022/12/25 20:29:14 - mmengine - INFO - Exp name: stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d_20221225_202355 2022/12/25 20:29:14 - mmengine - INFO - Epoch(train) [2][1567/1567] lr: 9.6196e-02 eta: 0:32:06 time: 0.0873 data_time: 0.0060 memory: 1827 loss: 0.6296 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.6296 2022/12/25 20:29:14 - mmengine - INFO - Saving checkpoint at 2 epochs 2022/12/25 20:29:17 - mmengine - INFO - Epoch(val) [2][100/129] eta: 0:00:00 time: 0.0267 data_time: 0.0060 memory: 263 2022/12/25 20:29:18 - mmengine - INFO - Epoch(val) [2][129/129] acc/top1: 0.6705 acc/top5: 0.9483 acc/mean1: 0.6706 2022/12/25 20:29:18 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_1.pth is removed 2022/12/25 20:29:19 - mmengine - INFO - The best checkpoint with 0.6705 acc/top1 at 2 epoch is saved to best_acc/top1_epoch_2.pth. 2022/12/25 20:29:28 - mmengine - INFO - Epoch(train) [3][ 100/1567] lr: 9.5953e-02 eta: 0:31:58 time: 0.0874 data_time: 0.0064 memory: 1827 loss: 0.3578 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.3578 2022/12/25 20:29:36 - mmengine - INFO - Epoch(train) [3][ 200/1567] lr: 9.5703e-02 eta: 0:31:48 time: 0.0880 data_time: 0.0063 memory: 1827 loss: 0.4854 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4854 2022/12/25 20:29:45 - mmengine - INFO - Epoch(train) [3][ 300/1567] lr: 9.5445e-02 eta: 0:31:39 time: 0.0872 data_time: 0.0062 memory: 1827 loss: 0.4526 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.4526 2022/12/25 20:29:54 - mmengine - INFO - Epoch(train) [3][ 400/1567] lr: 9.5180e-02 eta: 0:31:30 time: 0.0851 data_time: 0.0067 memory: 1827 loss: 0.4206 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4206 2022/12/25 20:30:02 - mmengine - INFO - Epoch(train) [3][ 500/1567] lr: 9.4908e-02 eta: 0:31:20 time: 0.0872 data_time: 0.0063 memory: 1827 loss: 0.4454 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4454 2022/12/25 20:30:11 - mmengine - INFO - Epoch(train) [3][ 600/1567] lr: 9.4629e-02 eta: 0:31:11 time: 0.0847 data_time: 0.0061 memory: 1827 loss: 0.4401 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.4401 2022/12/25 20:30:20 - mmengine - INFO - Epoch(train) [3][ 700/1567] lr: 9.4343e-02 eta: 0:31:01 time: 0.0855 data_time: 0.0062 memory: 1827 loss: 0.3760 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3760 2022/12/25 20:30:28 - mmengine - INFO - Epoch(train) [3][ 800/1567] lr: 9.4050e-02 eta: 0:30:52 time: 0.0915 data_time: 0.0062 memory: 1827 loss: 0.4392 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.4392 2022/12/25 20:30:34 - mmengine - INFO - Exp name: stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d_20221225_202355 2022/12/25 20:30:37 - mmengine - INFO - Epoch(train) [3][ 900/1567] lr: 9.3750e-02 eta: 0:30:43 time: 0.0871 data_time: 0.0088 memory: 1827 loss: 0.4628 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.4628 2022/12/25 20:30:46 - mmengine - INFO - Epoch(train) [3][1000/1567] lr: 9.3444e-02 eta: 0:30:33 time: 0.0877 data_time: 0.0061 memory: 1827 loss: 0.3297 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3297 2022/12/25 20:30:54 - mmengine - INFO - Epoch(train) [3][1100/1567] lr: 9.3130e-02 eta: 0:30:24 time: 0.0842 data_time: 0.0075 memory: 1827 loss: 0.3481 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3481 2022/12/25 20:31:03 - mmengine - INFO - Epoch(train) [3][1200/1567] lr: 9.2810e-02 eta: 0:30:14 time: 0.0841 data_time: 0.0062 memory: 1827 loss: 0.3056 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3056 2022/12/25 20:31:11 - mmengine - INFO - Epoch(train) [3][1300/1567] lr: 9.2483e-02 eta: 0:30:04 time: 0.0861 data_time: 0.0061 memory: 1827 loss: 0.4396 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.4396 2022/12/25 20:31:20 - mmengine - INFO - Epoch(train) [3][1400/1567] lr: 9.2149e-02 eta: 0:29:55 time: 0.0847 data_time: 0.0063 memory: 1827 loss: 0.4539 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.4539 2022/12/25 20:31:28 - mmengine - INFO - Epoch(train) [3][1500/1567] lr: 9.1809e-02 eta: 0:29:45 time: 0.0845 data_time: 0.0063 memory: 1827 loss: 0.4026 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4026 2022/12/25 20:31:34 - mmengine - INFO - Exp name: stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d_20221225_202355 2022/12/25 20:31:34 - mmengine - INFO - Epoch(train) [3][1567/1567] lr: 9.1577e-02 eta: 0:29:38 time: 0.0840 data_time: 0.0060 memory: 1827 loss: 0.4520 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.4520 2022/12/25 20:31:34 - mmengine - INFO - Saving checkpoint at 3 epochs 2022/12/25 20:31:37 - mmengine - INFO - Epoch(val) [3][100/129] eta: 0:00:00 time: 0.0259 data_time: 0.0058 memory: 263 2022/12/25 20:31:38 - mmengine - INFO - Epoch(val) [3][129/129] acc/top1: 0.5914 acc/top5: 0.8644 acc/mean1: 0.5915 2022/12/25 20:31:47 - mmengine - INFO - Epoch(train) [4][ 100/1567] lr: 9.1226e-02 eta: 0:29:30 time: 0.0898 data_time: 0.0063 memory: 1827 loss: 0.4118 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4118 2022/12/25 20:31:56 - mmengine - INFO - Epoch(train) [4][ 200/1567] lr: 9.0868e-02 eta: 0:29:22 time: 0.0891 data_time: 0.0062 memory: 1827 loss: 0.3764 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.3764 2022/12/25 20:32:04 - mmengine - INFO - Exp name: stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d_20221225_202355 2022/12/25 20:32:05 - mmengine - INFO - Epoch(train) [4][ 300/1567] lr: 9.0504e-02 eta: 0:29:14 time: 0.0869 data_time: 0.0063 memory: 1827 loss: 0.4219 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4219 2022/12/25 20:32:13 - mmengine - INFO - Epoch(train) [4][ 400/1567] lr: 9.0133e-02 eta: 0:29:05 time: 0.0870 data_time: 0.0061 memory: 1827 loss: 0.4125 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.4125 2022/12/25 20:32:22 - mmengine - INFO - Epoch(train) [4][ 500/1567] lr: 8.9756e-02 eta: 0:28:56 time: 0.0880 data_time: 0.0063 memory: 1827 loss: 0.3851 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3851 2022/12/25 20:32:31 - mmengine - INFO - Epoch(train) [4][ 600/1567] lr: 8.9373e-02 eta: 0:28:47 time: 0.0874 data_time: 0.0062 memory: 1827 loss: 0.3901 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3901 2022/12/25 20:32:40 - mmengine - INFO - Epoch(train) [4][ 700/1567] lr: 8.8984e-02 eta: 0:28:39 time: 0.0878 data_time: 0.0061 memory: 1827 loss: 0.3869 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.3869 2022/12/25 20:32:48 - mmengine - INFO - Epoch(train) [4][ 800/1567] lr: 8.8589e-02 eta: 0:28:30 time: 0.0844 data_time: 0.0064 memory: 1827 loss: 0.3243 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.3243 2022/12/25 20:32:57 - mmengine - INFO - Epoch(train) [4][ 900/1567] lr: 8.8187e-02 eta: 0:28:20 time: 0.0843 data_time: 0.0062 memory: 1827 loss: 0.4007 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4007 2022/12/25 20:33:05 - mmengine - INFO - Epoch(train) [4][1000/1567] lr: 8.7780e-02 eta: 0:28:10 time: 0.0848 data_time: 0.0061 memory: 1827 loss: 0.2997 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.2997 2022/12/25 20:33:14 - mmengine - INFO - Epoch(train) [4][1100/1567] lr: 8.7367e-02 eta: 0:28:01 time: 0.0851 data_time: 0.0062 memory: 1827 loss: 0.3501 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3501 2022/12/25 20:33:22 - mmengine - INFO - Epoch(train) [4][1200/1567] lr: 8.6947e-02 eta: 0:27:51 time: 0.0883 data_time: 0.0063 memory: 1827 loss: 0.3244 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.3244 2022/12/25 20:33:31 - mmengine - INFO - Exp name: stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d_20221225_202355 2022/12/25 20:33:31 - mmengine - INFO - Epoch(train) [4][1300/1567] lr: 8.6522e-02 eta: 0:27:42 time: 0.0845 data_time: 0.0062 memory: 1827 loss: 0.3545 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.3545 2022/12/25 20:33:39 - mmengine - INFO - Epoch(train) [4][1400/1567] lr: 8.6092e-02 eta: 0:27:33 time: 0.0858 data_time: 0.0062 memory: 1827 loss: 0.2648 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2648 2022/12/25 20:33:48 - mmengine - INFO - Epoch(train) [4][1500/1567] lr: 8.5655e-02 eta: 0:27:24 time: 0.0855 data_time: 0.0061 memory: 1827 loss: 0.2925 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2925 2022/12/25 20:33:54 - mmengine - INFO - Exp name: stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d_20221225_202355 2022/12/25 20:33:54 - mmengine - INFO - Epoch(train) [4][1567/1567] lr: 8.5360e-02 eta: 0:27:18 time: 0.0856 data_time: 0.0059 memory: 1827 loss: 0.5280 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.5280 2022/12/25 20:33:54 - mmengine - INFO - Saving checkpoint at 4 epochs 2022/12/25 20:33:57 - mmengine - INFO - Epoch(val) [4][100/129] eta: 0:00:00 time: 0.0253 data_time: 0.0057 memory: 263 2022/12/25 20:33:58 - mmengine - INFO - Epoch(val) [4][129/129] acc/top1: 0.7126 acc/top5: 0.9324 acc/mean1: 0.7127 2022/12/25 20:33:58 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_2.pth is removed 2022/12/25 20:33:58 - mmengine - INFO - The best checkpoint with 0.7126 acc/top1 at 4 epoch is saved to best_acc/top1_epoch_4.pth. 2022/12/25 20:34:07 - mmengine - INFO - Epoch(train) [5][ 100/1567] lr: 8.4914e-02 eta: 0:27:10 time: 0.0893 data_time: 0.0062 memory: 1827 loss: 0.2829 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2829 2022/12/25 20:34:15 - mmengine - INFO - Epoch(train) [5][ 200/1567] lr: 8.4463e-02 eta: 0:27:00 time: 0.0836 data_time: 0.0065 memory: 1827 loss: 0.3746 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3746 2022/12/25 20:34:24 - mmengine - INFO - Epoch(train) [5][ 300/1567] lr: 8.4006e-02 eta: 0:26:50 time: 0.0844 data_time: 0.0063 memory: 1827 loss: 0.3591 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.3591 2022/12/25 20:34:32 - mmengine - INFO - Epoch(train) [5][ 400/1567] lr: 8.3544e-02 eta: 0:26:41 time: 0.0861 data_time: 0.0062 memory: 1827 loss: 0.3435 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.3435 2022/12/25 20:34:41 - mmengine - INFO - Epoch(train) [5][ 500/1567] lr: 8.3077e-02 eta: 0:26:32 time: 0.0843 data_time: 0.0063 memory: 1827 loss: 0.3831 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.3831 2022/12/25 20:34:49 - mmengine - INFO - Epoch(train) [5][ 600/1567] lr: 8.2605e-02 eta: 0:26:23 time: 0.0863 data_time: 0.0064 memory: 1827 loss: 0.3393 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3393 2022/12/25 20:34:58 - mmengine - INFO - Epoch(train) [5][ 700/1567] lr: 8.2127e-02 eta: 0:26:14 time: 0.0833 data_time: 0.0063 memory: 1827 loss: 0.3355 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3355 2022/12/25 20:35:01 - mmengine - INFO - Exp name: stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d_20221225_202355 2022/12/25 20:35:06 - mmengine - INFO - Epoch(train) [5][ 800/1567] lr: 8.1645e-02 eta: 0:26:04 time: 0.0853 data_time: 0.0065 memory: 1827 loss: 0.3179 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3179 2022/12/25 20:35:15 - mmengine - INFO - Epoch(train) [5][ 900/1567] lr: 8.1157e-02 eta: 0:25:56 time: 0.0873 data_time: 0.0065 memory: 1827 loss: 0.3925 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3925 2022/12/25 20:35:24 - mmengine - INFO - Epoch(train) [5][1000/1567] lr: 8.0665e-02 eta: 0:25:47 time: 0.0887 data_time: 0.0064 memory: 1827 loss: 0.4094 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.4094 2022/12/25 20:35:32 - mmengine - INFO - Epoch(train) [5][1100/1567] lr: 8.0167e-02 eta: 0:25:38 time: 0.0851 data_time: 0.0064 memory: 1827 loss: 0.3162 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3162 2022/12/25 20:35:41 - mmengine - INFO - Epoch(train) [5][1200/1567] lr: 7.9665e-02 eta: 0:25:29 time: 0.0840 data_time: 0.0065 memory: 1827 loss: 0.2450 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2450 2022/12/25 20:35:50 - mmengine - INFO - Epoch(train) [5][1300/1567] lr: 7.9159e-02 eta: 0:25:20 time: 0.0858 data_time: 0.0064 memory: 1827 loss: 0.3645 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3645 2022/12/25 20:35:58 - mmengine - INFO - Epoch(train) [5][1400/1567] lr: 7.8647e-02 eta: 0:25:11 time: 0.0835 data_time: 0.0064 memory: 1827 loss: 0.3575 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3575 2022/12/25 20:36:06 - mmengine - INFO - Epoch(train) [5][1500/1567] lr: 7.8132e-02 eta: 0:25:02 time: 0.0859 data_time: 0.0068 memory: 1827 loss: 0.3096 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3096 2022/12/25 20:36:12 - mmengine - INFO - Exp name: stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d_20221225_202355 2022/12/25 20:36:12 - mmengine - INFO - Epoch(train) [5][1567/1567] lr: 7.7784e-02 eta: 0:24:56 time: 0.0851 data_time: 0.0062 memory: 1827 loss: 0.5889 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.5889 2022/12/25 20:36:12 - mmengine - INFO - Saving checkpoint at 5 epochs 2022/12/25 20:36:15 - mmengine - INFO - Epoch(val) [5][100/129] eta: 0:00:00 time: 0.0263 data_time: 0.0059 memory: 263 2022/12/25 20:36:16 - mmengine - INFO - Epoch(val) [5][129/129] acc/top1: 0.7362 acc/top5: 0.9607 acc/mean1: 0.7361 2022/12/25 20:36:16 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_4.pth is removed 2022/12/25 20:36:17 - mmengine - INFO - The best checkpoint with 0.7362 acc/top1 at 5 epoch is saved to best_acc/top1_epoch_5.pth. 2022/12/25 20:36:25 - mmengine - INFO - Epoch(train) [6][ 100/1567] lr: 7.7261e-02 eta: 0:24:47 time: 0.0891 data_time: 0.0064 memory: 1827 loss: 0.2947 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2947 2022/12/25 20:36:31 - mmengine - INFO - Exp name: stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d_20221225_202355 2022/12/25 20:36:34 - mmengine - INFO - Epoch(train) [6][ 200/1567] lr: 7.6733e-02 eta: 0:24:38 time: 0.0836 data_time: 0.0064 memory: 1827 loss: 0.2468 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2468 2022/12/25 20:36:42 - mmengine - INFO - Epoch(train) [6][ 300/1567] lr: 7.6202e-02 eta: 0:24:29 time: 0.0865 data_time: 0.0069 memory: 1827 loss: 0.3094 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3094 2022/12/25 20:36:51 - mmengine - INFO - Epoch(train) [6][ 400/1567] lr: 7.5666e-02 eta: 0:24:20 time: 0.0872 data_time: 0.0067 memory: 1827 loss: 0.3764 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.3764 2022/12/25 20:36:59 - mmengine - INFO - Epoch(train) [6][ 500/1567] lr: 7.5126e-02 eta: 0:24:11 time: 0.0834 data_time: 0.0064 memory: 1827 loss: 0.3145 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3145 2022/12/25 20:37:08 - mmengine - INFO - Epoch(train) [6][ 600/1567] lr: 7.4583e-02 eta: 0:24:02 time: 0.0841 data_time: 0.0069 memory: 1827 loss: 0.3296 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3296 2022/12/25 20:37:16 - mmengine - INFO - Epoch(train) [6][ 700/1567] lr: 7.4035e-02 eta: 0:23:53 time: 0.0866 data_time: 0.0065 memory: 1827 loss: 0.3296 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.3296 2022/12/25 20:37:25 - mmengine - INFO - Epoch(train) [6][ 800/1567] lr: 7.3484e-02 eta: 0:23:44 time: 0.0839 data_time: 0.0064 memory: 1827 loss: 0.2600 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2600 2022/12/25 20:37:33 - mmengine - INFO - Epoch(train) [6][ 900/1567] lr: 7.2929e-02 eta: 0:23:35 time: 0.0867 data_time: 0.0064 memory: 1827 loss: 0.3212 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.3212 2022/12/25 20:37:42 - mmengine - INFO - Epoch(train) [6][1000/1567] lr: 7.2371e-02 eta: 0:23:26 time: 0.0859 data_time: 0.0063 memory: 1827 loss: 0.2823 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2823 2022/12/25 20:37:51 - mmengine - INFO - Epoch(train) [6][1100/1567] lr: 7.1809e-02 eta: 0:23:18 time: 0.0855 data_time: 0.0064 memory: 1827 loss: 0.3382 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.3382 2022/12/25 20:37:56 - mmengine - INFO - Exp name: stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d_20221225_202355 2022/12/25 20:37:59 - mmengine - INFO - Epoch(train) [6][1200/1567] lr: 7.1243e-02 eta: 0:23:09 time: 0.0851 data_time: 0.0065 memory: 1827 loss: 0.2371 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2371 2022/12/25 20:38:09 - mmengine - INFO - Epoch(train) [6][1300/1567] lr: 7.0674e-02 eta: 0:23:01 time: 0.0856 data_time: 0.0077 memory: 1827 loss: 0.2791 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2791 2022/12/25 20:38:17 - mmengine - INFO - Epoch(train) [6][1400/1567] lr: 7.0102e-02 eta: 0:22:53 time: 0.0891 data_time: 0.0065 memory: 1827 loss: 0.2496 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2496 2022/12/25 20:38:26 - mmengine - INFO - Epoch(train) [6][1500/1567] lr: 6.9527e-02 eta: 0:22:44 time: 0.0867 data_time: 0.0070 memory: 1827 loss: 0.2676 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2676 2022/12/25 20:38:32 - mmengine - INFO - Exp name: stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d_20221225_202355 2022/12/25 20:38:32 - mmengine - INFO - Epoch(train) [6][1567/1567] lr: 6.9140e-02 eta: 0:22:38 time: 0.0847 data_time: 0.0064 memory: 1827 loss: 0.4986 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.4986 2022/12/25 20:38:32 - mmengine - INFO - Saving checkpoint at 6 epochs 2022/12/25 20:38:35 - mmengine - INFO - Epoch(val) [6][100/129] eta: 0:00:00 time: 0.0264 data_time: 0.0059 memory: 263 2022/12/25 20:38:36 - mmengine - INFO - Epoch(val) [6][129/129] acc/top1: 0.6931 acc/top5: 0.9354 acc/mean1: 0.6931 2022/12/25 20:38:45 - mmengine - INFO - Epoch(train) [7][ 100/1567] lr: 6.8560e-02 eta: 0:22:30 time: 0.0846 data_time: 0.0063 memory: 1827 loss: 0.3398 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3398 2022/12/25 20:38:53 - mmengine - INFO - Epoch(train) [7][ 200/1567] lr: 6.7976e-02 eta: 0:22:21 time: 0.0836 data_time: 0.0065 memory: 1827 loss: 0.3656 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.3656 2022/12/25 20:39:02 - mmengine - INFO - Epoch(train) [7][ 300/1567] lr: 6.7390e-02 eta: 0:22:12 time: 0.0867 data_time: 0.0065 memory: 1827 loss: 0.1983 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.1983 2022/12/25 20:39:10 - mmengine - INFO - Epoch(train) [7][ 400/1567] lr: 6.6802e-02 eta: 0:22:03 time: 0.0851 data_time: 0.0068 memory: 1827 loss: 0.2890 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2890 2022/12/25 20:39:19 - mmengine - INFO - Epoch(train) [7][ 500/1567] lr: 6.6210e-02 eta: 0:21:54 time: 0.0843 data_time: 0.0064 memory: 1827 loss: 0.3402 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3402 2022/12/25 20:39:27 - mmengine - INFO - Exp name: stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d_20221225_202355 2022/12/25 20:39:27 - mmengine - INFO - Epoch(train) [7][ 600/1567] lr: 6.5616e-02 eta: 0:21:46 time: 0.0847 data_time: 0.0064 memory: 1827 loss: 0.2291 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2291 2022/12/25 20:39:36 - mmengine - INFO - Epoch(train) [7][ 700/1567] lr: 6.5020e-02 eta: 0:21:37 time: 0.0908 data_time: 0.0065 memory: 1827 loss: 0.2396 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2396 2022/12/25 20:39:45 - mmengine - INFO - Epoch(train) [7][ 800/1567] lr: 6.4421e-02 eta: 0:21:28 time: 0.0862 data_time: 0.0068 memory: 1827 loss: 0.2442 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2442 2022/12/25 20:39:53 - mmengine - INFO - Epoch(train) [7][ 900/1567] lr: 6.3820e-02 eta: 0:21:19 time: 0.0875 data_time: 0.0064 memory: 1827 loss: 0.2364 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2364 2022/12/25 20:40:02 - mmengine - INFO - Epoch(train) [7][1000/1567] lr: 6.3217e-02 eta: 0:21:10 time: 0.0847 data_time: 0.0063 memory: 1827 loss: 0.2618 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2618 2022/12/25 20:40:11 - mmengine - INFO - Epoch(train) [7][1100/1567] lr: 6.2612e-02 eta: 0:21:02 time: 0.0867 data_time: 0.0070 memory: 1827 loss: 0.1627 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1627 2022/12/25 20:40:19 - mmengine - INFO - Epoch(train) [7][1200/1567] lr: 6.2005e-02 eta: 0:20:53 time: 0.0886 data_time: 0.0064 memory: 1827 loss: 0.2500 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2500 2022/12/25 20:40:28 - mmengine - INFO - Epoch(train) [7][1300/1567] lr: 6.1396e-02 eta: 0:20:45 time: 0.0872 data_time: 0.0064 memory: 1827 loss: 0.2263 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2263 2022/12/25 20:40:37 - mmengine - INFO - Epoch(train) [7][1400/1567] lr: 6.0785e-02 eta: 0:20:36 time: 0.0879 data_time: 0.0067 memory: 1827 loss: 0.2609 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2609 2022/12/25 20:40:45 - mmengine - INFO - Epoch(train) [7][1500/1567] lr: 6.0172e-02 eta: 0:20:27 time: 0.0850 data_time: 0.0065 memory: 1827 loss: 0.2708 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 0.2708 2022/12/25 20:40:51 - mmengine - INFO - Exp name: stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d_20221225_202355 2022/12/25 20:40:51 - mmengine - INFO - Epoch(train) [7][1567/1567] lr: 5.9761e-02 eta: 0:20:21 time: 0.0850 data_time: 0.0065 memory: 1827 loss: 0.4204 top1_acc: 0.0000 top5_acc: 1.0000 loss_cls: 0.4204 2022/12/25 20:40:51 - mmengine - INFO - Saving checkpoint at 7 epochs 2022/12/25 20:40:54 - mmengine - INFO - Epoch(val) [7][100/129] eta: 0:00:00 time: 0.0259 data_time: 0.0059 memory: 263 2022/12/25 20:40:55 - mmengine - INFO - Epoch(val) [7][129/129] acc/top1: 0.7562 acc/top5: 0.9645 acc/mean1: 0.7561 2022/12/25 20:40:55 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_5.pth is removed 2022/12/25 20:40:55 - mmengine - INFO - The best checkpoint with 0.7562 acc/top1 at 7 epoch is saved to best_acc/top1_epoch_7.pth. 2022/12/25 20:40:58 - mmengine - INFO - Exp name: stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d_20221225_202355 2022/12/25 20:41:04 - mmengine - INFO - Epoch(train) [8][ 100/1567] lr: 5.9145e-02 eta: 0:20:12 time: 0.0846 data_time: 0.0065 memory: 1827 loss: 0.2578 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2578 2022/12/25 20:41:13 - mmengine - INFO - Epoch(train) [8][ 200/1567] lr: 5.8529e-02 eta: 0:20:04 time: 0.0840 data_time: 0.0064 memory: 1827 loss: 0.2673 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2673 2022/12/25 20:41:21 - mmengine - INFO - Epoch(train) [8][ 300/1567] lr: 5.7911e-02 eta: 0:19:55 time: 0.0922 data_time: 0.0075 memory: 1827 loss: 0.2251 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2251 2022/12/25 20:41:30 - mmengine - INFO - Epoch(train) [8][ 400/1567] lr: 5.7292e-02 eta: 0:19:47 time: 0.0905 data_time: 0.0066 memory: 1827 loss: 0.2594 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2594 2022/12/25 20:41:39 - mmengine - INFO - Epoch(train) [8][ 500/1567] lr: 5.6671e-02 eta: 0:19:39 time: 0.0889 data_time: 0.0064 memory: 1827 loss: 0.2194 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.2194 2022/12/25 20:41:48 - mmengine - INFO - Epoch(train) [8][ 600/1567] lr: 5.6050e-02 eta: 0:19:30 time: 0.0888 data_time: 0.0064 memory: 1827 loss: 0.1853 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1853 2022/12/25 20:41:57 - mmengine - INFO - Epoch(train) [8][ 700/1567] lr: 5.5427e-02 eta: 0:19:22 time: 0.0883 data_time: 0.0063 memory: 1827 loss: 0.3048 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3048 2022/12/25 20:42:06 - mmengine - INFO - Epoch(train) [8][ 800/1567] lr: 5.4804e-02 eta: 0:19:13 time: 0.0876 data_time: 0.0072 memory: 1827 loss: 0.2084 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.2084 2022/12/25 20:42:14 - mmengine - INFO - Epoch(train) [8][ 900/1567] lr: 5.4180e-02 eta: 0:19:04 time: 0.0859 data_time: 0.0072 memory: 1827 loss: 0.1596 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1596 2022/12/25 20:42:23 - mmengine - INFO - Epoch(train) [8][1000/1567] lr: 5.3556e-02 eta: 0:18:56 time: 0.0843 data_time: 0.0071 memory: 1827 loss: 0.2202 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2202 2022/12/25 20:42:26 - mmengine - INFO - Exp name: stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d_20221225_202355 2022/12/25 20:42:32 - mmengine - INFO - Epoch(train) [8][1100/1567] lr: 5.2930e-02 eta: 0:18:47 time: 0.0851 data_time: 0.0064 memory: 1827 loss: 0.1914 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.1914 2022/12/25 20:42:41 - mmengine - INFO - Epoch(train) [8][1200/1567] lr: 5.2305e-02 eta: 0:18:39 time: 0.0885 data_time: 0.0064 memory: 1827 loss: 0.2043 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2043 2022/12/25 20:42:49 - mmengine - INFO - Epoch(train) [8][1300/1567] lr: 5.1679e-02 eta: 0:18:30 time: 0.0842 data_time: 0.0064 memory: 1827 loss: 0.1871 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1871 2022/12/25 20:42:58 - mmengine - INFO - Epoch(train) [8][1400/1567] lr: 5.1052e-02 eta: 0:18:21 time: 0.0872 data_time: 0.0070 memory: 1827 loss: 0.2158 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2158 2022/12/25 20:43:07 - mmengine - INFO - Epoch(train) [8][1500/1567] lr: 5.0426e-02 eta: 0:18:12 time: 0.0882 data_time: 0.0065 memory: 1827 loss: 0.2384 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2384 2022/12/25 20:43:12 - mmengine - INFO - Exp name: stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d_20221225_202355 2022/12/25 20:43:12 - mmengine - INFO - Epoch(train) [8][1567/1567] lr: 5.0006e-02 eta: 0:18:07 time: 0.0848 data_time: 0.0063 memory: 1827 loss: 0.4220 top1_acc: 0.0000 top5_acc: 1.0000 loss_cls: 0.4220 2022/12/25 20:43:12 - mmengine - INFO - Saving checkpoint at 8 epochs 2022/12/25 20:43:15 - mmengine - INFO - Epoch(val) [8][100/129] eta: 0:00:00 time: 0.0265 data_time: 0.0059 memory: 263 2022/12/25 20:43:16 - mmengine - INFO - Epoch(val) [8][129/129] acc/top1: 0.7790 acc/top5: 0.9709 acc/mean1: 0.7788 2022/12/25 20:43:16 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_7.pth is removed 2022/12/25 20:43:17 - mmengine - INFO - The best checkpoint with 0.7790 acc/top1 at 8 epoch is saved to best_acc/top1_epoch_8.pth. 2022/12/25 20:43:25 - mmengine - INFO - Epoch(train) [9][ 100/1567] lr: 4.9380e-02 eta: 0:17:58 time: 0.0838 data_time: 0.0064 memory: 1827 loss: 0.2346 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2346 2022/12/25 20:43:34 - mmengine - INFO - Epoch(train) [9][ 200/1567] lr: 4.8753e-02 eta: 0:17:49 time: 0.0840 data_time: 0.0065 memory: 1827 loss: 0.2288 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2288 2022/12/25 20:43:42 - mmengine - INFO - Epoch(train) [9][ 300/1567] lr: 4.8127e-02 eta: 0:17:40 time: 0.0868 data_time: 0.0065 memory: 1827 loss: 0.2110 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2110 2022/12/25 20:43:51 - mmengine - INFO - Epoch(train) [9][ 400/1567] lr: 4.7501e-02 eta: 0:17:32 time: 0.0899 data_time: 0.0065 memory: 1827 loss: 0.2039 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2039 2022/12/25 20:43:57 - mmengine - INFO - Exp name: stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d_20221225_202355 2022/12/25 20:44:00 - mmengine - INFO - Epoch(train) [9][ 500/1567] lr: 4.6876e-02 eta: 0:17:23 time: 0.0877 data_time: 0.0070 memory: 1827 loss: 0.2086 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2086 2022/12/25 20:44:09 - mmengine - INFO - Epoch(train) [9][ 600/1567] lr: 4.6251e-02 eta: 0:17:15 time: 0.0874 data_time: 0.0065 memory: 1827 loss: 0.2206 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2206 2022/12/25 20:44:18 - mmengine - INFO - Epoch(train) [9][ 700/1567] lr: 4.5626e-02 eta: 0:17:06 time: 0.0885 data_time: 0.0065 memory: 1827 loss: 0.2069 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2069 2022/12/25 20:44:26 - mmengine - INFO - Epoch(train) [9][ 800/1567] lr: 4.5003e-02 eta: 0:16:58 time: 0.0880 data_time: 0.0076 memory: 1827 loss: 0.2874 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2874 2022/12/25 20:44:35 - mmengine - INFO - Epoch(train) [9][ 900/1567] lr: 4.4380e-02 eta: 0:16:49 time: 0.0885 data_time: 0.0066 memory: 1827 loss: 0.2019 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2019 2022/12/25 20:44:44 - mmengine - INFO - Epoch(train) [9][1000/1567] lr: 4.3757e-02 eta: 0:16:40 time: 0.0860 data_time: 0.0066 memory: 1827 loss: 0.1699 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1699 2022/12/25 20:44:53 - mmengine - INFO - Epoch(train) [9][1100/1567] lr: 4.3136e-02 eta: 0:16:32 time: 0.0888 data_time: 0.0065 memory: 1827 loss: 0.2428 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.2428 2022/12/25 20:45:01 - mmengine - INFO - Epoch(train) [9][1200/1567] lr: 4.2516e-02 eta: 0:16:23 time: 0.0850 data_time: 0.0067 memory: 1827 loss: 0.1652 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1652 2022/12/25 20:45:10 - mmengine - INFO - Epoch(train) [9][1300/1567] lr: 4.1897e-02 eta: 0:16:14 time: 0.0871 data_time: 0.0074 memory: 1827 loss: 0.1793 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1793 2022/12/25 20:45:18 - mmengine - INFO - Epoch(train) [9][1400/1567] lr: 4.1280e-02 eta: 0:16:05 time: 0.0876 data_time: 0.0065 memory: 1827 loss: 0.1595 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1595 2022/12/25 20:45:24 - mmengine - INFO - Exp name: stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d_20221225_202355 2022/12/25 20:45:27 - mmengine - INFO - Epoch(train) [9][1500/1567] lr: 4.0664e-02 eta: 0:15:57 time: 0.0881 data_time: 0.0065 memory: 1827 loss: 0.1743 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.1743 2022/12/25 20:45:33 - mmengine - INFO - Exp name: stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d_20221225_202355 2022/12/25 20:45:33 - mmengine - INFO - Epoch(train) [9][1567/1567] lr: 4.0252e-02 eta: 0:15:51 time: 0.0853 data_time: 0.0063 memory: 1827 loss: 0.3347 top1_acc: 0.0000 top5_acc: 1.0000 loss_cls: 0.3347 2022/12/25 20:45:33 - mmengine - INFO - Saving checkpoint at 9 epochs 2022/12/25 20:45:36 - mmengine - INFO - Epoch(val) [9][100/129] eta: 0:00:00 time: 0.0277 data_time: 0.0063 memory: 263 2022/12/25 20:45:37 - mmengine - INFO - Epoch(val) [9][129/129] acc/top1: 0.7749 acc/top5: 0.9674 acc/mean1: 0.7750 2022/12/25 20:45:46 - mmengine - INFO - Epoch(train) [10][ 100/1567] lr: 3.9638e-02 eta: 0:15:42 time: 0.0848 data_time: 0.0065 memory: 1827 loss: 0.1575 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1575 2022/12/25 20:45:54 - mmengine - INFO - Epoch(train) [10][ 200/1567] lr: 3.9026e-02 eta: 0:15:33 time: 0.0851 data_time: 0.0064 memory: 1827 loss: 0.1645 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1645 2022/12/25 20:46:03 - mmengine - INFO - Epoch(train) [10][ 300/1567] lr: 3.8415e-02 eta: 0:15:25 time: 0.0886 data_time: 0.0064 memory: 1827 loss: 0.1496 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1496 2022/12/25 20:46:12 - mmengine - INFO - Epoch(train) [10][ 400/1567] lr: 3.7807e-02 eta: 0:15:16 time: 0.0849 data_time: 0.0064 memory: 1827 loss: 0.1770 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1770 2022/12/25 20:46:20 - mmengine - INFO - Epoch(train) [10][ 500/1567] lr: 3.7200e-02 eta: 0:15:07 time: 0.0855 data_time: 0.0064 memory: 1827 loss: 0.1577 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1577 2022/12/25 20:46:29 - mmengine - INFO - Epoch(train) [10][ 600/1567] lr: 3.6596e-02 eta: 0:14:59 time: 0.0838 data_time: 0.0064 memory: 1827 loss: 0.1797 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1797 2022/12/25 20:46:37 - mmengine - INFO - Epoch(train) [10][ 700/1567] lr: 3.5993e-02 eta: 0:14:50 time: 0.0846 data_time: 0.0064 memory: 1827 loss: 0.1558 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1558 2022/12/25 20:46:46 - mmengine - INFO - Epoch(train) [10][ 800/1567] lr: 3.5393e-02 eta: 0:14:41 time: 0.0840 data_time: 0.0063 memory: 1827 loss: 0.1575 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.1575 2022/12/25 20:46:54 - mmengine - INFO - Exp name: stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d_20221225_202355 2022/12/25 20:46:54 - mmengine - INFO - Epoch(train) [10][ 900/1567] lr: 3.4795e-02 eta: 0:14:32 time: 0.0837 data_time: 0.0063 memory: 1827 loss: 0.1042 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1042 2022/12/25 20:47:03 - mmengine - INFO - Epoch(train) [10][1000/1567] lr: 3.4199e-02 eta: 0:14:24 time: 0.0833 data_time: 0.0062 memory: 1827 loss: 0.1682 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1682 2022/12/25 20:47:11 - mmengine - INFO - Epoch(train) [10][1100/1567] lr: 3.3606e-02 eta: 0:14:15 time: 0.0848 data_time: 0.0064 memory: 1827 loss: 0.1443 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1443 2022/12/25 20:47:20 - mmengine - INFO - Epoch(train) [10][1200/1567] lr: 3.3015e-02 eta: 0:14:06 time: 0.0856 data_time: 0.0064 memory: 1827 loss: 0.1612 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1612 2022/12/25 20:47:29 - mmengine - INFO - Epoch(train) [10][1300/1567] lr: 3.2428e-02 eta: 0:13:58 time: 0.0879 data_time: 0.0081 memory: 1827 loss: 0.1954 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.1954 2022/12/25 20:47:37 - mmengine - INFO - Epoch(train) [10][1400/1567] lr: 3.1842e-02 eta: 0:13:49 time: 0.0832 data_time: 0.0064 memory: 1827 loss: 0.1380 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1380 2022/12/25 20:47:46 - mmengine - INFO - Epoch(train) [10][1500/1567] lr: 3.1260e-02 eta: 0:13:40 time: 0.0833 data_time: 0.0063 memory: 1827 loss: 0.1341 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1341 2022/12/25 20:47:51 - mmengine - INFO - Exp name: stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d_20221225_202355 2022/12/25 20:47:51 - mmengine - INFO - Epoch(train) [10][1567/1567] lr: 3.0872e-02 eta: 0:13:34 time: 0.0854 data_time: 0.0062 memory: 1827 loss: 0.3585 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.3585 2022/12/25 20:47:51 - mmengine - INFO - Saving checkpoint at 10 epochs 2022/12/25 20:47:55 - mmengine - INFO - Epoch(val) [10][100/129] eta: 0:00:00 time: 0.0256 data_time: 0.0058 memory: 263 2022/12/25 20:47:56 - mmengine - INFO - Epoch(val) [10][129/129] acc/top1: 0.8082 acc/top5: 0.9754 acc/mean1: 0.8081 2022/12/25 20:47:56 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_8.pth is removed 2022/12/25 20:47:56 - mmengine - INFO - The best checkpoint with 0.8082 acc/top1 at 10 epoch is saved to best_acc/top1_epoch_10.pth. 2022/12/25 20:48:05 - mmengine - INFO - Epoch(train) [11][ 100/1567] lr: 3.0294e-02 eta: 0:13:25 time: 0.0866 data_time: 0.0065 memory: 1827 loss: 0.1212 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1212 2022/12/25 20:48:13 - mmengine - INFO - Epoch(train) [11][ 200/1567] lr: 2.9720e-02 eta: 0:13:17 time: 0.0833 data_time: 0.0064 memory: 1827 loss: 0.1568 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1568 2022/12/25 20:48:21 - mmengine - INFO - Epoch(train) [11][ 300/1567] lr: 2.9149e-02 eta: 0:13:08 time: 0.0856 data_time: 0.0064 memory: 1827 loss: 0.1514 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1514 2022/12/25 20:48:24 - mmengine - INFO - Exp name: stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d_20221225_202355 2022/12/25 20:48:30 - mmengine - INFO - Epoch(train) [11][ 400/1567] lr: 2.8581e-02 eta: 0:12:59 time: 0.0863 data_time: 0.0063 memory: 1827 loss: 0.1437 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.1437 2022/12/25 20:48:39 - mmengine - INFO - Epoch(train) [11][ 500/1567] lr: 2.8017e-02 eta: 0:12:50 time: 0.0862 data_time: 0.0063 memory: 1827 loss: 0.1636 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1636 2022/12/25 20:48:47 - mmengine - INFO - Epoch(train) [11][ 600/1567] lr: 2.7456e-02 eta: 0:12:42 time: 0.0862 data_time: 0.0064 memory: 1827 loss: 0.1108 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.1108 2022/12/25 20:48:56 - mmengine - INFO - Epoch(train) [11][ 700/1567] lr: 2.6898e-02 eta: 0:12:33 time: 0.0832 data_time: 0.0063 memory: 1827 loss: 0.1631 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1631 2022/12/25 20:49:04 - mmengine - INFO - Epoch(train) [11][ 800/1567] lr: 2.6345e-02 eta: 0:12:24 time: 0.0840 data_time: 0.0063 memory: 1827 loss: 0.2260 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 0.2260 2022/12/25 20:49:13 - mmengine - INFO - Epoch(train) [11][ 900/1567] lr: 2.5794e-02 eta: 0:12:15 time: 0.0841 data_time: 0.0063 memory: 1827 loss: 0.1297 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1297 2022/12/25 20:49:21 - mmengine - INFO - Epoch(train) [11][1000/1567] lr: 2.5248e-02 eta: 0:12:07 time: 0.0882 data_time: 0.0063 memory: 1827 loss: 0.1033 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.1033 2022/12/25 20:49:30 - mmengine - INFO - Epoch(train) [11][1100/1567] lr: 2.4706e-02 eta: 0:11:58 time: 0.0847 data_time: 0.0063 memory: 1827 loss: 0.1087 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1087 2022/12/25 20:49:38 - mmengine - INFO - Epoch(train) [11][1200/1567] lr: 2.4167e-02 eta: 0:11:49 time: 0.0870 data_time: 0.0064 memory: 1827 loss: 0.1274 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1274 2022/12/25 20:49:47 - mmengine - INFO - Epoch(train) [11][1300/1567] lr: 2.3633e-02 eta: 0:11:41 time: 0.0860 data_time: 0.0064 memory: 1827 loss: 0.1281 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.1281 2022/12/25 20:49:49 - mmengine - INFO - Exp name: stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d_20221225_202355 2022/12/25 20:49:56 - mmengine - INFO - Epoch(train) [11][1400/1567] lr: 2.3103e-02 eta: 0:11:32 time: 0.0873 data_time: 0.0069 memory: 1827 loss: 0.1003 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1003 2022/12/25 20:50:04 - mmengine - INFO - Epoch(train) [11][1500/1567] lr: 2.2577e-02 eta: 0:11:23 time: 0.0865 data_time: 0.0063 memory: 1827 loss: 0.0979 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0979 2022/12/25 20:50:10 - mmengine - INFO - Exp name: stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d_20221225_202355 2022/12/25 20:50:10 - mmengine - INFO - Epoch(train) [11][1567/1567] lr: 2.2227e-02 eta: 0:11:17 time: 0.0838 data_time: 0.0061 memory: 1827 loss: 0.2625 top1_acc: 0.0000 top5_acc: 1.0000 loss_cls: 0.2625 2022/12/25 20:50:10 - mmengine - INFO - Saving checkpoint at 11 epochs 2022/12/25 20:50:13 - mmengine - INFO - Epoch(val) [11][100/129] eta: 0:00:00 time: 0.0302 data_time: 0.0065 memory: 263 2022/12/25 20:50:14 - mmengine - INFO - Epoch(val) [11][129/129] acc/top1: 0.8491 acc/top5: 0.9825 acc/mean1: 0.8491 2022/12/25 20:50:14 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_10.pth is removed 2022/12/25 20:50:15 - mmengine - INFO - The best checkpoint with 0.8491 acc/top1 at 11 epoch is saved to best_acc/top1_epoch_11.pth. 2022/12/25 20:50:23 - mmengine - INFO - Epoch(train) [12][ 100/1567] lr: 2.1708e-02 eta: 0:11:09 time: 0.0848 data_time: 0.0063 memory: 1827 loss: 0.1028 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1028 2022/12/25 20:50:32 - mmengine - INFO - Epoch(train) [12][ 200/1567] lr: 2.1194e-02 eta: 0:11:00 time: 0.0843 data_time: 0.0064 memory: 1827 loss: 0.0737 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0737 2022/12/25 20:50:40 - mmengine - INFO - Epoch(train) [12][ 300/1567] lr: 2.0684e-02 eta: 0:10:51 time: 0.0845 data_time: 0.0063 memory: 1827 loss: 0.0699 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0699 2022/12/25 20:50:49 - mmengine - INFO - Epoch(train) [12][ 400/1567] lr: 2.0179e-02 eta: 0:10:43 time: 0.0847 data_time: 0.0063 memory: 1827 loss: 0.0889 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0889 2022/12/25 20:50:57 - mmengine - INFO - Epoch(train) [12][ 500/1567] lr: 1.9678e-02 eta: 0:10:34 time: 0.0884 data_time: 0.0064 memory: 1827 loss: 0.0911 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0911 2022/12/25 20:51:06 - mmengine - INFO - Epoch(train) [12][ 600/1567] lr: 1.9182e-02 eta: 0:10:25 time: 0.0895 data_time: 0.0068 memory: 1827 loss: 0.1202 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1202 2022/12/25 20:51:15 - mmengine - INFO - Epoch(train) [12][ 700/1567] lr: 1.8691e-02 eta: 0:10:17 time: 0.0850 data_time: 0.0063 memory: 1827 loss: 0.1009 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1009 2022/12/25 20:51:20 - mmengine - INFO - Exp name: stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d_20221225_202355 2022/12/25 20:51:23 - mmengine - INFO - Epoch(train) [12][ 800/1567] lr: 1.8205e-02 eta: 0:10:08 time: 0.0893 data_time: 0.0063 memory: 1827 loss: 0.0823 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0823 2022/12/25 20:51:32 - mmengine - INFO - Epoch(train) [12][ 900/1567] lr: 1.7724e-02 eta: 0:09:59 time: 0.0841 data_time: 0.0063 memory: 1827 loss: 0.0900 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0900 2022/12/25 20:51:41 - mmengine - INFO - Epoch(train) [12][1000/1567] lr: 1.7248e-02 eta: 0:09:51 time: 0.0888 data_time: 0.0072 memory: 1827 loss: 0.0866 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0866 2022/12/25 20:51:50 - mmengine - INFO - Epoch(train) [12][1100/1567] lr: 1.6778e-02 eta: 0:09:42 time: 0.0887 data_time: 0.0063 memory: 1827 loss: 0.0992 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0992 2022/12/25 20:51:58 - mmengine - INFO - Epoch(train) [12][1200/1567] lr: 1.6312e-02 eta: 0:09:34 time: 0.0845 data_time: 0.0063 memory: 1827 loss: 0.0598 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0598 2022/12/25 20:52:07 - mmengine - INFO - Epoch(train) [12][1300/1567] lr: 1.5852e-02 eta: 0:09:25 time: 0.0840 data_time: 0.0064 memory: 1827 loss: 0.0495 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0495 2022/12/25 20:52:15 - mmengine - INFO - Epoch(train) [12][1400/1567] lr: 1.5397e-02 eta: 0:09:16 time: 0.0836 data_time: 0.0063 memory: 1827 loss: 0.0707 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0707 2022/12/25 20:52:24 - mmengine - INFO - Epoch(train) [12][1500/1567] lr: 1.4947e-02 eta: 0:09:08 time: 0.0971 data_time: 0.0064 memory: 1827 loss: 0.0734 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0734 2022/12/25 20:52:30 - mmengine - INFO - Exp name: stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d_20221225_202355 2022/12/25 20:52:30 - mmengine - INFO - Epoch(train) [12][1567/1567] lr: 1.4649e-02 eta: 0:09:02 time: 0.0858 data_time: 0.0061 memory: 1827 loss: 0.2247 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2247 2022/12/25 20:52:30 - mmengine - INFO - Saving checkpoint at 12 epochs 2022/12/25 20:52:33 - mmengine - INFO - Epoch(val) [12][100/129] eta: 0:00:00 time: 0.0261 data_time: 0.0059 memory: 263 2022/12/25 20:52:34 - mmengine - INFO - Epoch(val) [12][129/129] acc/top1: 0.8578 acc/top5: 0.9848 acc/mean1: 0.8578 2022/12/25 20:52:34 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_11.pth is removed 2022/12/25 20:52:35 - mmengine - INFO - The best checkpoint with 0.8578 acc/top1 at 12 epoch is saved to best_acc/top1_epoch_12.pth. 2022/12/25 20:52:44 - mmengine - INFO - Epoch(train) [13][ 100/1567] lr: 1.4209e-02 eta: 0:08:53 time: 0.0879 data_time: 0.0062 memory: 1827 loss: 0.0651 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0651 2022/12/25 20:52:52 - mmengine - INFO - Exp name: stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d_20221225_202355 2022/12/25 20:52:52 - mmengine - INFO - Epoch(train) [13][ 200/1567] lr: 1.3774e-02 eta: 0:08:45 time: 0.0835 data_time: 0.0063 memory: 1827 loss: 0.0929 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0929 2022/12/25 20:53:01 - mmengine - INFO - Epoch(train) [13][ 300/1567] lr: 1.3345e-02 eta: 0:08:36 time: 0.0843 data_time: 0.0063 memory: 1827 loss: 0.0473 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0473 2022/12/25 20:53:10 - mmengine - INFO - Epoch(train) [13][ 400/1567] lr: 1.2922e-02 eta: 0:08:27 time: 0.0880 data_time: 0.0062 memory: 1827 loss: 0.0599 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0599 2022/12/25 20:53:18 - mmengine - INFO - Epoch(train) [13][ 500/1567] lr: 1.2505e-02 eta: 0:08:19 time: 0.0876 data_time: 0.0063 memory: 1827 loss: 0.0829 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0829 2022/12/25 20:53:27 - mmengine - INFO - Epoch(train) [13][ 600/1567] lr: 1.2093e-02 eta: 0:08:10 time: 0.0873 data_time: 0.0074 memory: 1827 loss: 0.0675 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0675 2022/12/25 20:53:36 - mmengine - INFO - Epoch(train) [13][ 700/1567] lr: 1.1687e-02 eta: 0:08:01 time: 0.0854 data_time: 0.0071 memory: 1827 loss: 0.0578 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0578 2022/12/25 20:53:44 - mmengine - INFO - Epoch(train) [13][ 800/1567] lr: 1.1288e-02 eta: 0:07:53 time: 0.0838 data_time: 0.0063 memory: 1827 loss: 0.0530 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0530 2022/12/25 20:53:53 - mmengine - INFO - Epoch(train) [13][ 900/1567] lr: 1.0894e-02 eta: 0:07:44 time: 0.0852 data_time: 0.0064 memory: 1827 loss: 0.0266 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0266 2022/12/25 20:54:01 - mmengine - INFO - Epoch(train) [13][1000/1567] lr: 1.0507e-02 eta: 0:07:35 time: 0.0841 data_time: 0.0063 memory: 1827 loss: 0.0317 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0317 2022/12/25 20:54:10 - mmengine - INFO - Epoch(train) [13][1100/1567] lr: 1.0126e-02 eta: 0:07:27 time: 0.0836 data_time: 0.0063 memory: 1827 loss: 0.0452 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0452 2022/12/25 20:54:18 - mmengine - INFO - Exp name: stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d_20221225_202355 2022/12/25 20:54:18 - mmengine - INFO - Epoch(train) [13][1200/1567] lr: 9.7512e-03 eta: 0:07:18 time: 0.0837 data_time: 0.0071 memory: 1827 loss: 0.0352 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0352 2022/12/25 20:54:26 - mmengine - INFO - Epoch(train) [13][1300/1567] lr: 9.3826e-03 eta: 0:07:09 time: 0.0843 data_time: 0.0063 memory: 1827 loss: 0.0523 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0523 2022/12/25 20:54:35 - mmengine - INFO - Epoch(train) [13][1400/1567] lr: 9.0204e-03 eta: 0:07:00 time: 0.0847 data_time: 0.0064 memory: 1827 loss: 0.0406 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0406 2022/12/25 20:54:44 - mmengine - INFO - Epoch(train) [13][1500/1567] lr: 8.6647e-03 eta: 0:06:52 time: 0.0880 data_time: 0.0067 memory: 1827 loss: 0.0433 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0433 2022/12/25 20:54:49 - mmengine - INFO - Exp name: stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d_20221225_202355 2022/12/25 20:54:49 - mmengine - INFO - Epoch(train) [13][1567/1567] lr: 8.4300e-03 eta: 0:06:46 time: 0.0854 data_time: 0.0061 memory: 1827 loss: 0.2050 top1_acc: 0.0000 top5_acc: 1.0000 loss_cls: 0.2050 2022/12/25 20:54:49 - mmengine - INFO - Saving checkpoint at 13 epochs 2022/12/25 20:54:53 - mmengine - INFO - Epoch(val) [13][100/129] eta: 0:00:00 time: 0.0261 data_time: 0.0059 memory: 263 2022/12/25 20:54:54 - mmengine - INFO - Epoch(val) [13][129/129] acc/top1: 0.8671 acc/top5: 0.9864 acc/mean1: 0.8671 2022/12/25 20:54:54 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_12.pth is removed 2022/12/25 20:54:54 - mmengine - INFO - The best checkpoint with 0.8671 acc/top1 at 13 epoch is saved to best_acc/top1_epoch_13.pth. 2022/12/25 20:55:02 - mmengine - INFO - Epoch(train) [14][ 100/1567] lr: 8.0851e-03 eta: 0:06:37 time: 0.0835 data_time: 0.0063 memory: 1827 loss: 0.0445 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0445 2022/12/25 20:55:11 - mmengine - INFO - Epoch(train) [14][ 200/1567] lr: 7.7469e-03 eta: 0:06:29 time: 0.0836 data_time: 0.0064 memory: 1827 loss: 0.0330 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0330 2022/12/25 20:55:19 - mmengine - INFO - Epoch(train) [14][ 300/1567] lr: 7.4152e-03 eta: 0:06:20 time: 0.0833 data_time: 0.0063 memory: 1827 loss: 0.0420 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0420 2022/12/25 20:55:28 - mmengine - INFO - Epoch(train) [14][ 400/1567] lr: 7.0902e-03 eta: 0:06:11 time: 0.0882 data_time: 0.0063 memory: 1827 loss: 0.0539 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0539 2022/12/25 20:55:37 - mmengine - INFO - Epoch(train) [14][ 500/1567] lr: 6.7720e-03 eta: 0:06:03 time: 0.0867 data_time: 0.0064 memory: 1827 loss: 0.0415 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0415 2022/12/25 20:55:45 - mmengine - INFO - Epoch(train) [14][ 600/1567] lr: 6.4606e-03 eta: 0:05:54 time: 0.0838 data_time: 0.0063 memory: 1827 loss: 0.0428 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0428 2022/12/25 20:55:47 - mmengine - INFO - Exp name: stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d_20221225_202355 2022/12/25 20:55:54 - mmengine - INFO - Epoch(train) [14][ 700/1567] lr: 6.1560e-03 eta: 0:05:45 time: 0.0881 data_time: 0.0063 memory: 1827 loss: 0.0419 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0419 2022/12/25 20:56:02 - mmengine - INFO - Epoch(train) [14][ 800/1567] lr: 5.8582e-03 eta: 0:05:37 time: 0.0880 data_time: 0.0063 memory: 1827 loss: 0.0391 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0391 2022/12/25 20:56:11 - mmengine - INFO - Epoch(train) [14][ 900/1567] lr: 5.5675e-03 eta: 0:05:28 time: 0.0844 data_time: 0.0064 memory: 1827 loss: 0.0251 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0251 2022/12/25 20:56:19 - mmengine - INFO - Epoch(train) [14][1000/1567] lr: 5.2836e-03 eta: 0:05:19 time: 0.0834 data_time: 0.0063 memory: 1827 loss: 0.0203 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0203 2022/12/25 20:56:28 - mmengine - INFO - Epoch(train) [14][1100/1567] lr: 5.0068e-03 eta: 0:05:11 time: 0.0843 data_time: 0.0063 memory: 1827 loss: 0.0264 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0264 2022/12/25 20:56:36 - mmengine - INFO - Epoch(train) [14][1200/1567] lr: 4.7371e-03 eta: 0:05:02 time: 0.0861 data_time: 0.0064 memory: 1827 loss: 0.0244 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0244 2022/12/25 20:56:45 - mmengine - INFO - Epoch(train) [14][1300/1567] lr: 4.4745e-03 eta: 0:04:53 time: 0.0883 data_time: 0.0063 memory: 1827 loss: 0.0444 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0444 2022/12/25 20:56:54 - mmengine - INFO - Epoch(train) [14][1400/1567] lr: 4.2190e-03 eta: 0:04:45 time: 0.0844 data_time: 0.0065 memory: 1827 loss: 0.0324 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0324 2022/12/25 20:57:02 - mmengine - INFO - Epoch(train) [14][1500/1567] lr: 3.9707e-03 eta: 0:04:36 time: 0.0875 data_time: 0.0064 memory: 1827 loss: 0.0173 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0173 2022/12/25 20:57:08 - mmengine - INFO - Exp name: stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d_20221225_202355 2022/12/25 20:57:08 - mmengine - INFO - Epoch(train) [14][1567/1567] lr: 3.8084e-03 eta: 0:04:30 time: 0.0853 data_time: 0.0061 memory: 1827 loss: 0.1895 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1895 2022/12/25 20:57:08 - mmengine - INFO - Saving checkpoint at 14 epochs 2022/12/25 20:57:11 - mmengine - INFO - Epoch(val) [14][100/129] eta: 0:00:00 time: 0.0263 data_time: 0.0059 memory: 263 2022/12/25 20:57:12 - mmengine - INFO - Epoch(val) [14][129/129] acc/top1: 0.8743 acc/top5: 0.9869 acc/mean1: 0.8743 2022/12/25 20:57:12 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_13.pth is removed 2022/12/25 20:57:13 - mmengine - INFO - The best checkpoint with 0.8743 acc/top1 at 14 epoch is saved to best_acc/top1_epoch_14.pth. 2022/12/25 20:57:18 - mmengine - INFO - Exp name: stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d_20221225_202355 2022/12/25 20:57:21 - mmengine - INFO - Epoch(train) [15][ 100/1567] lr: 3.5722e-03 eta: 0:04:22 time: 0.0857 data_time: 0.0064 memory: 1827 loss: 0.0203 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0203 2022/12/25 20:57:30 - mmengine - INFO - Epoch(train) [15][ 200/1567] lr: 3.3433e-03 eta: 0:04:13 time: 0.0833 data_time: 0.0063 memory: 1827 loss: 0.0587 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0587 2022/12/25 20:57:38 - mmengine - INFO - Epoch(train) [15][ 300/1567] lr: 3.1217e-03 eta: 0:04:04 time: 0.0839 data_time: 0.0070 memory: 1827 loss: 0.0252 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0252 2022/12/25 20:57:46 - mmengine - INFO - Epoch(train) [15][ 400/1567] lr: 2.9075e-03 eta: 0:03:56 time: 0.0833 data_time: 0.0064 memory: 1827 loss: 0.0214 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0214 2022/12/25 20:57:55 - mmengine - INFO - Epoch(train) [15][ 500/1567] lr: 2.7007e-03 eta: 0:03:47 time: 0.0834 data_time: 0.0064 memory: 1827 loss: 0.0285 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0285 2022/12/25 20:58:03 - mmengine - INFO - Epoch(train) [15][ 600/1567] lr: 2.5013e-03 eta: 0:03:38 time: 0.0834 data_time: 0.0063 memory: 1827 loss: 0.0363 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0363 2022/12/25 20:58:12 - mmengine - INFO - Epoch(train) [15][ 700/1567] lr: 2.3093e-03 eta: 0:03:30 time: 0.0855 data_time: 0.0063 memory: 1827 loss: 0.0233 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0233 2022/12/25 20:58:20 - mmengine - INFO - Epoch(train) [15][ 800/1567] lr: 2.1249e-03 eta: 0:03:21 time: 0.0885 data_time: 0.0065 memory: 1827 loss: 0.0253 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0253 2022/12/25 20:58:29 - mmengine - INFO - Epoch(train) [15][ 900/1567] lr: 1.9479e-03 eta: 0:03:12 time: 0.0866 data_time: 0.0064 memory: 1827 loss: 0.0285 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0285 2022/12/25 20:58:38 - mmengine - INFO - Epoch(train) [15][1000/1567] lr: 1.7785e-03 eta: 0:03:04 time: 0.0861 data_time: 0.0065 memory: 1827 loss: 0.0169 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0169 2022/12/25 20:58:43 - mmengine - INFO - Exp name: stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d_20221225_202355 2022/12/25 20:58:46 - mmengine - INFO - Epoch(train) [15][1100/1567] lr: 1.6167e-03 eta: 0:02:55 time: 0.0864 data_time: 0.0064 memory: 1827 loss: 0.0184 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0184 2022/12/25 20:58:55 - mmengine - INFO - Epoch(train) [15][1200/1567] lr: 1.4625e-03 eta: 0:02:47 time: 0.0874 data_time: 0.0063 memory: 1827 loss: 0.0364 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0364 2022/12/25 20:59:04 - mmengine - INFO - Epoch(train) [15][1300/1567] lr: 1.3159e-03 eta: 0:02:38 time: 0.0875 data_time: 0.0063 memory: 1827 loss: 0.0255 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0255 2022/12/25 20:59:13 - mmengine - INFO - Epoch(train) [15][1400/1567] lr: 1.1769e-03 eta: 0:02:29 time: 0.0872 data_time: 0.0064 memory: 1827 loss: 0.0208 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0208 2022/12/25 20:59:21 - mmengine - INFO - Epoch(train) [15][1500/1567] lr: 1.0456e-03 eta: 0:02:21 time: 0.0883 data_time: 0.0064 memory: 1827 loss: 0.0230 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0230 2022/12/25 20:59:27 - mmengine - INFO - Exp name: stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d_20221225_202355 2022/12/25 20:59:27 - mmengine - INFO - Epoch(train) [15][1567/1567] lr: 9.6196e-04 eta: 0:02:15 time: 0.0870 data_time: 0.0061 memory: 1827 loss: 0.1662 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1662 2022/12/25 20:59:27 - mmengine - INFO - Saving checkpoint at 15 epochs 2022/12/25 20:59:30 - mmengine - INFO - Epoch(val) [15][100/129] eta: 0:00:00 time: 0.0270 data_time: 0.0059 memory: 263 2022/12/25 20:59:31 - mmengine - INFO - Epoch(val) [15][129/129] acc/top1: 0.8764 acc/top5: 0.9871 acc/mean1: 0.8764 2022/12/25 20:59:31 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_14.pth is removed 2022/12/25 20:59:32 - mmengine - INFO - The best checkpoint with 0.8764 acc/top1 at 15 epoch is saved to best_acc/top1_epoch_15.pth. 2022/12/25 20:59:40 - mmengine - INFO - Epoch(train) [16][ 100/1567] lr: 8.4351e-04 eta: 0:02:06 time: 0.0832 data_time: 0.0062 memory: 1827 loss: 0.0211 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0211 2022/12/25 20:59:49 - mmengine - INFO - Epoch(train) [16][ 200/1567] lr: 7.3277e-04 eta: 0:01:58 time: 0.0841 data_time: 0.0063 memory: 1827 loss: 0.0274 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0274 2022/12/25 20:59:57 - mmengine - INFO - Epoch(train) [16][ 300/1567] lr: 6.2978e-04 eta: 0:01:49 time: 0.0834 data_time: 0.0063 memory: 1827 loss: 0.0200 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0200 2022/12/25 21:00:05 - mmengine - INFO - Epoch(train) [16][ 400/1567] lr: 5.3453e-04 eta: 0:01:40 time: 0.0850 data_time: 0.0063 memory: 1827 loss: 0.0262 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0262 2022/12/25 21:00:14 - mmengine - INFO - Exp name: stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d_20221225_202355 2022/12/25 21:00:14 - mmengine - INFO - Epoch(train) [16][ 500/1567] lr: 4.4705e-04 eta: 0:01:32 time: 0.0841 data_time: 0.0071 memory: 1827 loss: 0.0117 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0117 2022/12/25 21:00:22 - mmengine - INFO - Epoch(train) [16][ 600/1567] lr: 3.6735e-04 eta: 0:01:23 time: 0.0874 data_time: 0.0069 memory: 1827 loss: 0.0157 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0157 2022/12/25 21:00:31 - mmengine - INFO - Epoch(train) [16][ 700/1567] lr: 2.9544e-04 eta: 0:01:14 time: 0.0869 data_time: 0.0063 memory: 1827 loss: 0.0239 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0239 2022/12/25 21:00:40 - mmengine - INFO - Epoch(train) [16][ 800/1567] lr: 2.3134e-04 eta: 0:01:06 time: 0.0848 data_time: 0.0063 memory: 1827 loss: 0.0244 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0244 2022/12/25 21:00:48 - mmengine - INFO - Epoch(train) [16][ 900/1567] lr: 1.7505e-04 eta: 0:00:57 time: 0.0832 data_time: 0.0063 memory: 1827 loss: 0.0138 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0138 2022/12/25 21:00:57 - mmengine - INFO - Epoch(train) [16][1000/1567] lr: 1.2658e-04 eta: 0:00:48 time: 0.0877 data_time: 0.0071 memory: 1827 loss: 0.0305 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0305 2022/12/25 21:01:06 - mmengine - INFO - Epoch(train) [16][1100/1567] lr: 8.5947e-05 eta: 0:00:40 time: 0.0884 data_time: 0.0065 memory: 1827 loss: 0.0202 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0202 2022/12/25 21:01:14 - mmengine - INFO - Epoch(train) [16][1200/1567] lr: 5.3147e-05 eta: 0:00:31 time: 0.0841 data_time: 0.0064 memory: 1827 loss: 0.0336 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0336 2022/12/25 21:01:23 - mmengine - INFO - Epoch(train) [16][1300/1567] lr: 2.8190e-05 eta: 0:00:23 time: 0.0880 data_time: 0.0063 memory: 1827 loss: 0.0200 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0200 2022/12/25 21:01:32 - mmengine - INFO - Epoch(train) [16][1400/1567] lr: 1.1078e-05 eta: 0:00:14 time: 0.0880 data_time: 0.0063 memory: 1827 loss: 0.0293 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.0293 2022/12/25 21:01:40 - mmengine - INFO - Exp name: stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d_20221225_202355 2022/12/25 21:01:40 - mmengine - INFO - Epoch(train) [16][1500/1567] lr: 1.8150e-06 eta: 0:00:05 time: 0.0874 data_time: 0.0071 memory: 1827 loss: 0.0131 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0131 2022/12/25 21:01:46 - mmengine - INFO - Exp name: stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d_20221225_202355 2022/12/25 21:01:46 - mmengine - INFO - Epoch(train) [16][1567/1567] lr: 3.9252e-10 eta: 0:00:00 time: 0.0860 data_time: 0.0061 memory: 1827 loss: 0.1749 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1749 2022/12/25 21:01:46 - mmengine - INFO - Saving checkpoint at 16 epochs 2022/12/25 21:01:49 - mmengine - INFO - Epoch(val) [16][100/129] eta: 0:00:00 time: 0.0256 data_time: 0.0058 memory: 263 2022/12/25 21:01:50 - mmengine - INFO - Epoch(val) [16][129/129] acc/top1: 0.8783 acc/top5: 0.9864 acc/mean1: 0.8783 2022/12/25 21:01:50 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_15.pth is removed 2022/12/25 21:01:51 - mmengine - INFO - The best checkpoint with 0.8783 acc/top1 at 16 epoch is saved to best_acc/top1_epoch_16.pth.