2022/12/30 13:04:06 - 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: 675889030 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 ------------------------------------------------------------ 2022/12/30 13:04:06 - 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='nturgb+d', mode='spatial')), cls_head=dict(type='GCNHead', num_classes=60, in_channels=256)) dataset_type = 'PoseDataset' ann_file = 'data/skeleton/ntu60_3d.pkl' train_pipeline = [ dict(type='PreNormalize3D'), dict(type='GenSkeFeat', dataset='nturgb+d', feats=['jm']), dict(type='UniformSampleFrames', clip_len=100), dict(type='PoseDecode'), dict(type='FormatGCNInput', num_person=2), dict(type='PackActionInputs') ] val_pipeline = [ dict(type='PreNormalize3D'), dict(type='GenSkeFeat', dataset='nturgb+d', feats=['jm']), 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='PreNormalize3D'), dict(type='GenSkeFeat', dataset='nturgb+d', feats=['jm']), 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_3d.pkl', pipeline=[ dict(type='PreNormalize3D'), dict(type='GenSkeFeat', dataset='nturgb+d', feats=['jm']), 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_3d.pkl', pipeline=[ dict(type='PreNormalize3D'), dict(type='GenSkeFeat', dataset='nturgb+d', feats=['jm']), 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_3d.pkl', pipeline=[ dict(type='PreNormalize3D'), dict(type='GenSkeFeat', dataset='nturgb+d', feats=['jm']), 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-joint-motion-u100-80e_ntu60-xsub-keypoint-3d' randomness = dict(seed=None, diff_rank_seed=False, deterministic=False) 2022/12/30 13:04:06 - mmengine - INFO - Result has been saved to /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d/modules_statistic_results.json 2022/12/30 13:04:07 - 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([75]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.data_bn.bias - torch.Size([75]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.gcn.A - torch.Size([3, 25, 25]): 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, 25, 25]): 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, 25, 25]): 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, 25, 25]): 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, 25, 25]): 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, 25, 25]): 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, 25, 25]): 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, 25, 25]): 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, 25, 25]): 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, 25, 25]): 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 2022/12/30 13:05:03 - mmengine - INFO - Checkpoints will be saved to /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d. 2022/12/30 13:05:25 - mmengine - INFO - Epoch(train) [1][ 100/1567] lr: 9.9996e-02 eta: 1:31:36 time: 0.1887 data_time: 0.0066 memory: 2656 loss: 2.9647 top1_acc: 0.2500 top5_acc: 0.4375 loss_cls: 2.9647 2022/12/30 13:05:44 - mmengine - INFO - Epoch(train) [1][ 200/1567] lr: 9.9984e-02 eta: 1:25:26 time: 0.1914 data_time: 0.0064 memory: 2656 loss: 1.8819 top1_acc: 0.3125 top5_acc: 0.7500 loss_cls: 1.8819 2022/12/30 13:06:03 - mmengine - INFO - Epoch(train) [1][ 300/1567] lr: 9.9965e-02 eta: 1:22:47 time: 0.1872 data_time: 0.0066 memory: 2656 loss: 1.5703 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.5703 2022/12/30 13:06:22 - mmengine - INFO - Epoch(train) [1][ 400/1567] lr: 9.9938e-02 eta: 1:21:36 time: 0.1944 data_time: 0.0065 memory: 2656 loss: 1.2306 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 1.2306 2022/12/30 13:06:41 - mmengine - INFO - Epoch(train) [1][ 500/1567] lr: 9.9902e-02 eta: 1:20:26 time: 0.1892 data_time: 0.0070 memory: 2656 loss: 1.1790 top1_acc: 0.6250 top5_acc: 1.0000 loss_cls: 1.1790 2022/12/30 13:07:00 - mmengine - INFO - Epoch(train) [1][ 600/1567] lr: 9.9859e-02 eta: 1:19:35 time: 0.1895 data_time: 0.0065 memory: 2656 loss: 0.9846 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.9846 2022/12/30 13:07:19 - mmengine - INFO - Epoch(train) [1][ 700/1567] lr: 9.9808e-02 eta: 1:18:53 time: 0.1884 data_time: 0.0067 memory: 2656 loss: 0.9400 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 0.9400 2022/12/30 13:07:38 - mmengine - INFO - Epoch(train) [1][ 800/1567] lr: 9.9750e-02 eta: 1:18:24 time: 0.1889 data_time: 0.0068 memory: 2656 loss: 0.7867 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.7867 2022/12/30 13:07:57 - mmengine - INFO - Epoch(train) [1][ 900/1567] lr: 9.9683e-02 eta: 1:18:06 time: 0.1938 data_time: 0.0066 memory: 2656 loss: 0.8663 top1_acc: 0.4375 top5_acc: 0.9375 loss_cls: 0.8663 2022/12/30 13:08:16 - mmengine - INFO - Exp name: stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221230_130356 2022/12/30 13:08:16 - mmengine - INFO - Epoch(train) [1][1000/1567] lr: 9.9609e-02 eta: 1:17:43 time: 0.1901 data_time: 0.0068 memory: 2656 loss: 0.7624 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.7624 2022/12/30 13:08:35 - mmengine - INFO - Epoch(train) [1][1100/1567] lr: 9.9527e-02 eta: 1:17:11 time: 0.1906 data_time: 0.0068 memory: 2656 loss: 0.7278 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.7278 2022/12/30 13:08:54 - mmengine - INFO - Epoch(train) [1][1200/1567] lr: 9.9437e-02 eta: 1:16:42 time: 0.1854 data_time: 0.0070 memory: 2656 loss: 0.7909 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.7909 2022/12/30 13:09:13 - mmengine - INFO - Epoch(train) [1][1300/1567] lr: 9.9339e-02 eta: 1:16:17 time: 0.1900 data_time: 0.0065 memory: 2656 loss: 0.6483 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.6483 2022/12/30 13:09:32 - mmengine - INFO - Epoch(train) [1][1400/1567] lr: 9.9234e-02 eta: 1:15:55 time: 0.1928 data_time: 0.0066 memory: 2656 loss: 0.8048 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.8048 2022/12/30 13:09:51 - mmengine - INFO - Epoch(train) [1][1500/1567] lr: 9.9121e-02 eta: 1:15:30 time: 0.1859 data_time: 0.0067 memory: 2656 loss: 0.7396 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 0.7396 2022/12/30 13:10:03 - mmengine - INFO - Exp name: stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221230_130356 2022/12/30 13:10:03 - mmengine - INFO - Epoch(train) [1][1567/1567] lr: 9.9040e-02 eta: 1:15:08 time: 0.1805 data_time: 0.0068 memory: 2656 loss: 0.8483 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.8483 2022/12/30 13:10:03 - mmengine - INFO - Saving checkpoint at 1 epochs 2022/12/30 13:10:08 - mmengine - INFO - Epoch(val) [1][100/129] eta: 0:00:01 time: 0.0410 data_time: 0.0066 memory: 378 2022/12/30 13:10:10 - mmengine - INFO - Epoch(val) [1][129/129] acc/top1: 0.5521 acc/top5: 0.8469 acc/mean1: 0.5525 2022/12/30 13:10:10 - mmengine - INFO - The best checkpoint with 0.5521 acc/top1 at 1 epoch is saved to best_acc/top1_epoch_1.pth. 2022/12/30 13:10:30 - mmengine - INFO - Epoch(train) [2][ 100/1567] lr: 9.8914e-02 eta: 1:14:52 time: 0.1860 data_time: 0.0065 memory: 2656 loss: 0.6733 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.6733 2022/12/30 13:10:49 - mmengine - INFO - Epoch(train) [2][ 200/1567] lr: 9.8781e-02 eta: 1:14:32 time: 0.1854 data_time: 0.0066 memory: 2656 loss: 0.4921 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.4921 2022/12/30 13:11:08 - mmengine - INFO - Epoch(train) [2][ 300/1567] lr: 9.8639e-02 eta: 1:14:17 time: 0.1865 data_time: 0.0068 memory: 2656 loss: 0.7039 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.7039 2022/12/30 13:11:27 - mmengine - INFO - Epoch(train) [2][ 400/1567] lr: 9.8491e-02 eta: 1:13:56 time: 0.1917 data_time: 0.0069 memory: 2656 loss: 0.6331 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.6331 2022/12/30 13:11:33 - mmengine - INFO - Exp name: stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221230_130356 2022/12/30 13:11:46 - mmengine - INFO - Epoch(train) [2][ 500/1567] lr: 9.8334e-02 eta: 1:13:34 time: 0.1901 data_time: 0.0068 memory: 2656 loss: 0.4779 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4779 2022/12/30 13:12:05 - mmengine - INFO - Epoch(train) [2][ 600/1567] lr: 9.8170e-02 eta: 1:13:10 time: 0.1878 data_time: 0.0068 memory: 2656 loss: 0.6380 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.6380 2022/12/30 13:12:24 - mmengine - INFO - Epoch(train) [2][ 700/1567] lr: 9.7998e-02 eta: 1:12:46 time: 0.1857 data_time: 0.0065 memory: 2656 loss: 0.6635 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.6635 2022/12/30 13:12:42 - mmengine - INFO - Epoch(train) [2][ 800/1567] lr: 9.7819e-02 eta: 1:12:21 time: 0.1800 data_time: 0.0066 memory: 2656 loss: 0.5393 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.5393 2022/12/30 13:13:01 - mmengine - INFO - Epoch(train) [2][ 900/1567] lr: 9.7632e-02 eta: 1:11:56 time: 0.1832 data_time: 0.0068 memory: 2656 loss: 0.6614 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.6614 2022/12/30 13:13:19 - mmengine - INFO - Epoch(train) [2][1000/1567] lr: 9.7438e-02 eta: 1:11:32 time: 0.1901 data_time: 0.0069 memory: 2656 loss: 0.6530 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 0.6530 2022/12/30 13:13:38 - mmengine - INFO - Epoch(train) [2][1100/1567] lr: 9.7236e-02 eta: 1:11:11 time: 0.1872 data_time: 0.0066 memory: 2656 loss: 0.4503 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4503 2022/12/30 13:13:57 - mmengine - INFO - Epoch(train) [2][1200/1567] lr: 9.7027e-02 eta: 1:10:53 time: 0.1958 data_time: 0.0067 memory: 2656 loss: 0.6587 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.6587 2022/12/30 13:14:16 - mmengine - INFO - Epoch(train) [2][1300/1567] lr: 9.6810e-02 eta: 1:10:33 time: 0.1937 data_time: 0.0065 memory: 2656 loss: 0.4265 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4265 2022/12/30 13:14:35 - mmengine - INFO - Epoch(train) [2][1400/1567] lr: 9.6587e-02 eta: 1:10:14 time: 0.1906 data_time: 0.0066 memory: 2656 loss: 0.5180 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 0.5180 2022/12/30 13:14:42 - mmengine - INFO - Exp name: stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221230_130356 2022/12/30 13:14:54 - mmengine - INFO - Epoch(train) [2][1500/1567] lr: 9.6355e-02 eta: 1:09:55 time: 0.1857 data_time: 0.0065 memory: 2656 loss: 0.6151 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.6151 2022/12/30 13:15:06 - mmengine - INFO - Exp name: stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221230_130356 2022/12/30 13:15:06 - mmengine - INFO - Epoch(train) [2][1567/1567] lr: 9.6196e-02 eta: 1:09:37 time: 0.1768 data_time: 0.0064 memory: 2656 loss: 0.7774 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.7774 2022/12/30 13:15:06 - mmengine - INFO - Saving checkpoint at 2 epochs 2022/12/30 13:15:11 - mmengine - INFO - Epoch(val) [2][100/129] eta: 0:00:01 time: 0.0421 data_time: 0.0061 memory: 378 2022/12/30 13:15:13 - mmengine - INFO - Epoch(val) [2][129/129] acc/top1: 0.7512 acc/top5: 0.9450 acc/mean1: 0.7512 2022/12/30 13:15:13 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_1.pth is removed 2022/12/30 13:15:13 - mmengine - INFO - The best checkpoint with 0.7512 acc/top1 at 2 epoch is saved to best_acc/top1_epoch_2.pth. 2022/12/30 13:15:32 - mmengine - INFO - Epoch(train) [3][ 100/1567] lr: 9.5953e-02 eta: 1:09:17 time: 0.1789 data_time: 0.0067 memory: 2656 loss: 0.5780 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.5780 2022/12/30 13:15:51 - mmengine - INFO - Epoch(train) [3][ 200/1567] lr: 9.5703e-02 eta: 1:09:00 time: 0.1850 data_time: 0.0068 memory: 2656 loss: 0.4892 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.4892 2022/12/30 13:16:10 - mmengine - INFO - Epoch(train) [3][ 300/1567] lr: 9.5445e-02 eta: 1:08:38 time: 0.1805 data_time: 0.0065 memory: 2656 loss: 0.5799 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.5799 2022/12/30 13:16:30 - mmengine - INFO - Epoch(train) [3][ 400/1567] lr: 9.5180e-02 eta: 1:08:22 time: 0.1956 data_time: 0.0066 memory: 2656 loss: 0.5669 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.5669 2022/12/30 13:16:48 - mmengine - INFO - Epoch(train) [3][ 500/1567] lr: 9.4908e-02 eta: 1:07:58 time: 0.1745 data_time: 0.0066 memory: 2656 loss: 0.4732 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.4732 2022/12/30 13:17:06 - mmengine - INFO - Epoch(train) [3][ 600/1567] lr: 9.4629e-02 eta: 1:07:36 time: 0.1946 data_time: 0.0066 memory: 2656 loss: 0.5140 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.5140 2022/12/30 13:17:25 - mmengine - INFO - Epoch(train) [3][ 700/1567] lr: 9.4343e-02 eta: 1:07:18 time: 0.1925 data_time: 0.0066 memory: 2656 loss: 0.5066 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.5066 2022/12/30 13:17:44 - mmengine - INFO - Epoch(train) [3][ 800/1567] lr: 9.4050e-02 eta: 1:06:56 time: 0.1867 data_time: 0.0066 memory: 2656 loss: 0.5230 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.5230 2022/12/30 13:17:56 - mmengine - INFO - Exp name: stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221230_130356 2022/12/30 13:18:03 - mmengine - INFO - Epoch(train) [3][ 900/1567] lr: 9.3750e-02 eta: 1:06:36 time: 0.1916 data_time: 0.0067 memory: 2656 loss: 0.5411 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.5411 2022/12/30 13:18:21 - mmengine - INFO - Epoch(train) [3][1000/1567] lr: 9.3444e-02 eta: 1:06:15 time: 0.1816 data_time: 0.0069 memory: 2656 loss: 0.4968 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.4968 2022/12/30 13:18:40 - mmengine - INFO - Epoch(train) [3][1100/1567] lr: 9.3130e-02 eta: 1:05:53 time: 0.1826 data_time: 0.0065 memory: 2656 loss: 0.4859 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4859 2022/12/30 13:18:58 - mmengine - INFO - Epoch(train) [3][1200/1567] lr: 9.2810e-02 eta: 1:05:29 time: 0.1724 data_time: 0.0066 memory: 2656 loss: 0.4804 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.4804 2022/12/30 13:19:16 - mmengine - INFO - Epoch(train) [3][1300/1567] lr: 9.2483e-02 eta: 1:05:07 time: 0.1813 data_time: 0.0067 memory: 2656 loss: 0.5164 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.5164 2022/12/30 13:19:34 - mmengine - INFO - Epoch(train) [3][1400/1567] lr: 9.2149e-02 eta: 1:04:44 time: 0.1872 data_time: 0.0067 memory: 2656 loss: 0.4968 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.4968 2022/12/30 13:19:52 - mmengine - INFO - Epoch(train) [3][1500/1567] lr: 9.1809e-02 eta: 1:04:23 time: 0.1732 data_time: 0.0071 memory: 2656 loss: 0.4858 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4858 2022/12/30 13:20:05 - mmengine - INFO - Exp name: stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221230_130356 2022/12/30 13:20:05 - mmengine - INFO - Epoch(train) [3][1567/1567] lr: 9.1577e-02 eta: 1:04:11 time: 0.1863 data_time: 0.0067 memory: 2656 loss: 0.5645 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.5645 2022/12/30 13:20:05 - mmengine - INFO - Saving checkpoint at 3 epochs 2022/12/30 13:20:10 - mmengine - INFO - Epoch(val) [3][100/129] eta: 0:00:01 time: 0.0424 data_time: 0.0063 memory: 378 2022/12/30 13:20:11 - mmengine - INFO - Epoch(val) [3][129/129] acc/top1: 0.4980 acc/top5: 0.7496 acc/mean1: 0.4980 2022/12/30 13:20:30 - mmengine - INFO - Epoch(train) [4][ 100/1567] lr: 9.1226e-02 eta: 1:03:53 time: 0.1839 data_time: 0.0065 memory: 2656 loss: 0.4720 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.4720 2022/12/30 13:20:49 - mmengine - INFO - Epoch(train) [4][ 200/1567] lr: 9.0868e-02 eta: 1:03:34 time: 0.1887 data_time: 0.0065 memory: 2656 loss: 0.5715 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.5715 2022/12/30 13:21:09 - mmengine - INFO - Exp name: stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221230_130356 2022/12/30 13:21:09 - mmengine - INFO - Epoch(train) [4][ 300/1567] lr: 9.0504e-02 eta: 1:03:18 time: 0.1929 data_time: 0.0067 memory: 2656 loss: 0.5339 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.5339 2022/12/30 13:21:28 - mmengine - INFO - Epoch(train) [4][ 400/1567] lr: 9.0133e-02 eta: 1:03:00 time: 0.1860 data_time: 0.0066 memory: 2656 loss: 0.5439 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.5439 2022/12/30 13:21:47 - mmengine - INFO - Epoch(train) [4][ 500/1567] lr: 8.9756e-02 eta: 1:02:40 time: 0.1826 data_time: 0.0068 memory: 2656 loss: 0.3471 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.3471 2022/12/30 13:22:06 - mmengine - INFO - Epoch(train) [4][ 600/1567] lr: 8.9373e-02 eta: 1:02:22 time: 0.1930 data_time: 0.0066 memory: 2656 loss: 0.4407 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4407 2022/12/30 13:22:24 - mmengine - INFO - Epoch(train) [4][ 700/1567] lr: 8.8984e-02 eta: 1:02:01 time: 0.1739 data_time: 0.0067 memory: 2656 loss: 0.4155 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4155 2022/12/30 13:22:43 - mmengine - INFO - Epoch(train) [4][ 800/1567] lr: 8.8589e-02 eta: 1:01:41 time: 0.1981 data_time: 0.0065 memory: 2656 loss: 0.3964 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3964 2022/12/30 13:23:02 - mmengine - INFO - Epoch(train) [4][ 900/1567] lr: 8.8187e-02 eta: 1:01:23 time: 0.1839 data_time: 0.0066 memory: 2656 loss: 0.4250 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 0.4250 2022/12/30 13:23:21 - mmengine - INFO - Epoch(train) [4][1000/1567] lr: 8.7780e-02 eta: 1:01:05 time: 0.1958 data_time: 0.0065 memory: 2656 loss: 0.4076 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4076 2022/12/30 13:23:40 - mmengine - INFO - Epoch(train) [4][1100/1567] lr: 8.7367e-02 eta: 1:00:45 time: 0.1843 data_time: 0.0067 memory: 2656 loss: 0.4076 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4076 2022/12/30 13:23:58 - mmengine - INFO - Epoch(train) [4][1200/1567] lr: 8.6947e-02 eta: 1:00:24 time: 0.1849 data_time: 0.0067 memory: 2656 loss: 0.5141 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.5141 2022/12/30 13:24:17 - mmengine - INFO - Exp name: stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221230_130356 2022/12/30 13:24:17 - mmengine - INFO - Epoch(train) [4][1300/1567] lr: 8.6522e-02 eta: 1:00:06 time: 0.1880 data_time: 0.0066 memory: 2656 loss: 0.4410 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.4410 2022/12/30 13:24:36 - mmengine - INFO - Epoch(train) [4][1400/1567] lr: 8.6092e-02 eta: 0:59:45 time: 0.1788 data_time: 0.0066 memory: 2656 loss: 0.4374 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4374 2022/12/30 13:24:54 - mmengine - INFO - Epoch(train) [4][1500/1567] lr: 8.5655e-02 eta: 0:59:23 time: 0.1855 data_time: 0.0066 memory: 2656 loss: 0.3786 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3786 2022/12/30 13:25:06 - mmengine - INFO - Exp name: stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221230_130356 2022/12/30 13:25:06 - mmengine - INFO - Epoch(train) [4][1567/1567] lr: 8.5360e-02 eta: 0:59:10 time: 0.1829 data_time: 0.0071 memory: 2656 loss: 0.6240 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.6240 2022/12/30 13:25:06 - mmengine - INFO - Saving checkpoint at 4 epochs 2022/12/30 13:25:11 - mmengine - INFO - Epoch(val) [4][100/129] eta: 0:00:01 time: 0.0400 data_time: 0.0082 memory: 378 2022/12/30 13:25:12 - mmengine - INFO - Epoch(val) [4][129/129] acc/top1: 0.7713 acc/top5: 0.9518 acc/mean1: 0.7712 2022/12/30 13:25:12 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_2.pth is removed 2022/12/30 13:25:13 - mmengine - INFO - The best checkpoint with 0.7713 acc/top1 at 4 epoch is saved to best_acc/top1_epoch_4.pth. 2022/12/30 13:25:32 - mmengine - INFO - Epoch(train) [5][ 100/1567] lr: 8.4914e-02 eta: 0:58:53 time: 0.1865 data_time: 0.0067 memory: 2656 loss: 0.4113 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.4113 2022/12/30 13:25:51 - mmengine - INFO - Epoch(train) [5][ 200/1567] lr: 8.4463e-02 eta: 0:58:33 time: 0.1912 data_time: 0.0068 memory: 2656 loss: 0.3705 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3705 2022/12/30 13:26:09 - mmengine - INFO - Epoch(train) [5][ 300/1567] lr: 8.4006e-02 eta: 0:58:14 time: 0.1898 data_time: 0.0066 memory: 2656 loss: 0.3406 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.3406 2022/12/30 13:26:28 - mmengine - INFO - Epoch(train) [5][ 400/1567] lr: 8.3544e-02 eta: 0:57:56 time: 0.1960 data_time: 0.0066 memory: 2656 loss: 0.3738 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3738 2022/12/30 13:26:47 - mmengine - INFO - Epoch(train) [5][ 500/1567] lr: 8.3077e-02 eta: 0:57:35 time: 0.1851 data_time: 0.0066 memory: 2656 loss: 0.4456 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4456 2022/12/30 13:27:06 - mmengine - INFO - Epoch(train) [5][ 600/1567] lr: 8.2605e-02 eta: 0:57:16 time: 0.1927 data_time: 0.0067 memory: 2656 loss: 0.4127 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.4127 2022/12/30 13:27:24 - mmengine - INFO - Epoch(train) [5][ 700/1567] lr: 8.2127e-02 eta: 0:56:57 time: 0.2045 data_time: 0.0078 memory: 2656 loss: 0.3459 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3459 2022/12/30 13:27:30 - mmengine - INFO - Exp name: stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221230_130356 2022/12/30 13:27:43 - mmengine - INFO - Epoch(train) [5][ 800/1567] lr: 8.1645e-02 eta: 0:56:38 time: 0.1936 data_time: 0.0066 memory: 2656 loss: 0.3825 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3825 2022/12/30 13:28:02 - mmengine - INFO - Epoch(train) [5][ 900/1567] lr: 8.1157e-02 eta: 0:56:20 time: 0.2023 data_time: 0.0066 memory: 2656 loss: 0.3834 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3834 2022/12/30 13:28:21 - mmengine - INFO - Epoch(train) [5][1000/1567] lr: 8.0665e-02 eta: 0:56:01 time: 0.1823 data_time: 0.0070 memory: 2656 loss: 0.4491 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4491 2022/12/30 13:28:40 - mmengine - INFO - Epoch(train) [5][1100/1567] lr: 8.0167e-02 eta: 0:55:42 time: 0.1914 data_time: 0.0066 memory: 2656 loss: 0.4308 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4308 2022/12/30 13:28:58 - mmengine - INFO - Epoch(train) [5][1200/1567] lr: 7.9665e-02 eta: 0:55:21 time: 0.1859 data_time: 0.0066 memory: 2656 loss: 0.3296 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3296 2022/12/30 13:29:16 - mmengine - INFO - Epoch(train) [5][1300/1567] lr: 7.9159e-02 eta: 0:55:00 time: 0.1801 data_time: 0.0065 memory: 2656 loss: 0.4223 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.4223 2022/12/30 13:29:36 - mmengine - INFO - Epoch(train) [5][1400/1567] lr: 7.8647e-02 eta: 0:54:43 time: 0.1972 data_time: 0.0066 memory: 2656 loss: 0.3471 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3471 2022/12/30 13:29:55 - mmengine - INFO - Epoch(train) [5][1500/1567] lr: 7.8132e-02 eta: 0:54:25 time: 0.1846 data_time: 0.0066 memory: 2656 loss: 0.3810 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.3810 2022/12/30 13:30:07 - mmengine - INFO - Exp name: stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221230_130356 2022/12/30 13:30:07 - mmengine - INFO - Epoch(train) [5][1567/1567] lr: 7.7784e-02 eta: 0:54:12 time: 0.1817 data_time: 0.0065 memory: 2656 loss: 0.5121 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.5121 2022/12/30 13:30:07 - mmengine - INFO - Saving checkpoint at 5 epochs 2022/12/30 13:30:12 - mmengine - INFO - Epoch(val) [5][100/129] eta: 0:00:01 time: 0.0402 data_time: 0.0078 memory: 378 2022/12/30 13:30:14 - mmengine - INFO - Epoch(val) [5][129/129] acc/top1: 0.7707 acc/top5: 0.9517 acc/mean1: 0.7707 2022/12/30 13:30:33 - mmengine - INFO - Epoch(train) [6][ 100/1567] lr: 7.7261e-02 eta: 0:53:54 time: 0.1858 data_time: 0.0066 memory: 2656 loss: 0.3291 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3291 2022/12/30 13:30:46 - mmengine - INFO - Exp name: stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221230_130356 2022/12/30 13:30:52 - mmengine - INFO - Epoch(train) [6][ 200/1567] lr: 7.6733e-02 eta: 0:53:35 time: 0.1899 data_time: 0.0065 memory: 2656 loss: 0.3798 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.3798 2022/12/30 13:31:11 - mmengine - INFO - Epoch(train) [6][ 300/1567] lr: 7.6202e-02 eta: 0:53:17 time: 0.1898 data_time: 0.0066 memory: 2656 loss: 0.3712 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3712 2022/12/30 13:31:30 - mmengine - INFO - Epoch(train) [6][ 400/1567] lr: 7.5666e-02 eta: 0:52:58 time: 0.1927 data_time: 0.0065 memory: 2656 loss: 0.4022 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4022 2022/12/30 13:31:49 - mmengine - INFO - Epoch(train) [6][ 500/1567] lr: 7.5126e-02 eta: 0:52:40 time: 0.1830 data_time: 0.0073 memory: 2656 loss: 0.3199 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.3199 2022/12/30 13:32:08 - mmengine - INFO - Epoch(train) [6][ 600/1567] lr: 7.4583e-02 eta: 0:52:20 time: 0.1734 data_time: 0.0066 memory: 2656 loss: 0.3753 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.3753 2022/12/30 13:32:26 - mmengine - INFO - Epoch(train) [6][ 700/1567] lr: 7.4035e-02 eta: 0:52:00 time: 0.1797 data_time: 0.0077 memory: 2656 loss: 0.3050 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3050 2022/12/30 13:32:45 - mmengine - INFO - Epoch(train) [6][ 800/1567] lr: 7.3484e-02 eta: 0:51:41 time: 0.1820 data_time: 0.0071 memory: 2656 loss: 0.4552 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 0.4552 2022/12/30 13:33:04 - mmengine - INFO - Epoch(train) [6][ 900/1567] lr: 7.2929e-02 eta: 0:51:22 time: 0.1842 data_time: 0.0069 memory: 2656 loss: 0.3926 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3926 2022/12/30 13:33:23 - mmengine - INFO - Epoch(train) [6][1000/1567] lr: 7.2371e-02 eta: 0:51:04 time: 0.1996 data_time: 0.0065 memory: 2656 loss: 0.4231 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4231 2022/12/30 13:33:42 - mmengine - INFO - Epoch(train) [6][1100/1567] lr: 7.1809e-02 eta: 0:50:46 time: 0.1798 data_time: 0.0066 memory: 2656 loss: 0.3476 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3476 2022/12/30 13:33:55 - mmengine - INFO - Exp name: stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221230_130356 2022/12/30 13:34:01 - mmengine - INFO - Epoch(train) [6][1200/1567] lr: 7.1243e-02 eta: 0:50:27 time: 0.1905 data_time: 0.0066 memory: 2656 loss: 0.3178 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3178 2022/12/30 13:34:19 - mmengine - INFO - Epoch(train) [6][1300/1567] lr: 7.0674e-02 eta: 0:50:07 time: 0.1861 data_time: 0.0068 memory: 2656 loss: 0.4233 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 0.4233 2022/12/30 13:34:38 - mmengine - INFO - Epoch(train) [6][1400/1567] lr: 7.0102e-02 eta: 0:49:48 time: 0.1792 data_time: 0.0066 memory: 2656 loss: 0.3886 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.3886 2022/12/30 13:34:57 - mmengine - INFO - Epoch(train) [6][1500/1567] lr: 6.9527e-02 eta: 0:49:29 time: 0.1880 data_time: 0.0067 memory: 2656 loss: 0.3390 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.3390 2022/12/30 13:35:09 - mmengine - INFO - Exp name: stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221230_130356 2022/12/30 13:35:09 - mmengine - INFO - Epoch(train) [6][1567/1567] lr: 6.9140e-02 eta: 0:49:16 time: 0.1819 data_time: 0.0063 memory: 2656 loss: 0.6241 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.6241 2022/12/30 13:35:09 - mmengine - INFO - Saving checkpoint at 6 epochs 2022/12/30 13:35:14 - mmengine - INFO - Epoch(val) [6][100/129] eta: 0:00:01 time: 0.0410 data_time: 0.0062 memory: 378 2022/12/30 13:35:15 - mmengine - INFO - Epoch(val) [6][129/129] acc/top1: 0.7033 acc/top5: 0.9202 acc/mean1: 0.7034 2022/12/30 13:35:34 - mmengine - INFO - Epoch(train) [7][ 100/1567] lr: 6.8560e-02 eta: 0:48:56 time: 0.1819 data_time: 0.0068 memory: 2656 loss: 0.3533 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3533 2022/12/30 13:35:53 - mmengine - INFO - Epoch(train) [7][ 200/1567] lr: 6.7976e-02 eta: 0:48:37 time: 0.1905 data_time: 0.0065 memory: 2656 loss: 0.3060 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3060 2022/12/30 13:36:12 - mmengine - INFO - Epoch(train) [7][ 300/1567] lr: 6.7390e-02 eta: 0:48:18 time: 0.1868 data_time: 0.0069 memory: 2656 loss: 0.3436 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3436 2022/12/30 13:36:30 - mmengine - INFO - Epoch(train) [7][ 400/1567] lr: 6.6802e-02 eta: 0:47:59 time: 0.1854 data_time: 0.0067 memory: 2656 loss: 0.2933 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2933 2022/12/30 13:36:49 - mmengine - INFO - Epoch(train) [7][ 500/1567] lr: 6.6210e-02 eta: 0:47:39 time: 0.1858 data_time: 0.0067 memory: 2656 loss: 0.2902 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2902 2022/12/30 13:37:06 - mmengine - INFO - Exp name: stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221230_130356 2022/12/30 13:37:07 - mmengine - INFO - Epoch(train) [7][ 600/1567] lr: 6.5616e-02 eta: 0:47:19 time: 0.1818 data_time: 0.0066 memory: 2656 loss: 0.2620 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2620 2022/12/30 13:37:25 - mmengine - INFO - Epoch(train) [7][ 700/1567] lr: 6.5020e-02 eta: 0:47:00 time: 0.1750 data_time: 0.0064 memory: 2656 loss: 0.3282 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3282 2022/12/30 13:37:44 - mmengine - INFO - Epoch(train) [7][ 800/1567] lr: 6.4421e-02 eta: 0:46:41 time: 0.1992 data_time: 0.0066 memory: 2656 loss: 0.3002 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 0.3002 2022/12/30 13:38:03 - mmengine - INFO - Epoch(train) [7][ 900/1567] lr: 6.3820e-02 eta: 0:46:22 time: 0.1924 data_time: 0.0067 memory: 2656 loss: 0.3127 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3127 2022/12/30 13:38:21 - mmengine - INFO - Epoch(train) [7][1000/1567] lr: 6.3217e-02 eta: 0:46:02 time: 0.1831 data_time: 0.0068 memory: 2656 loss: 0.3712 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3712 2022/12/30 13:38:39 - mmengine - INFO - Epoch(train) [7][1100/1567] lr: 6.2612e-02 eta: 0:45:43 time: 0.1809 data_time: 0.0065 memory: 2656 loss: 0.3300 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3300 2022/12/30 13:38:58 - mmengine - INFO - Epoch(train) [7][1200/1567] lr: 6.2005e-02 eta: 0:45:24 time: 0.1713 data_time: 0.0074 memory: 2656 loss: 0.3860 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3860 2022/12/30 13:39:17 - mmengine - INFO - Epoch(train) [7][1300/1567] lr: 6.1396e-02 eta: 0:45:06 time: 0.1961 data_time: 0.0066 memory: 2656 loss: 0.3003 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3003 2022/12/30 13:39:35 - mmengine - INFO - Epoch(train) [7][1400/1567] lr: 6.0785e-02 eta: 0:44:46 time: 0.1777 data_time: 0.0065 memory: 2656 loss: 0.2545 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.2545 2022/12/30 13:39:54 - mmengine - INFO - Epoch(train) [7][1500/1567] lr: 6.0172e-02 eta: 0:44:27 time: 0.1956 data_time: 0.0065 memory: 2656 loss: 0.2568 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 0.2568 2022/12/30 13:40:07 - mmengine - INFO - Exp name: stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221230_130356 2022/12/30 13:40:07 - mmengine - INFO - Epoch(train) [7][1567/1567] lr: 5.9761e-02 eta: 0:44:14 time: 0.1690 data_time: 0.0063 memory: 2656 loss: 0.4944 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.4944 2022/12/30 13:40:07 - mmengine - INFO - Saving checkpoint at 7 epochs 2022/12/30 13:40:11 - mmengine - INFO - Epoch(val) [7][100/129] eta: 0:00:01 time: 0.0414 data_time: 0.0062 memory: 378 2022/12/30 13:40:13 - mmengine - INFO - Epoch(val) [7][129/129] acc/top1: 0.7841 acc/top5: 0.9554 acc/mean1: 0.7840 2022/12/30 13:40:13 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_4.pth is removed 2022/12/30 13:40:13 - mmengine - INFO - The best checkpoint with 0.7841 acc/top1 at 7 epoch is saved to best_acc/top1_epoch_7.pth. 2022/12/30 13:40:19 - mmengine - INFO - Exp name: stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221230_130356 2022/12/30 13:40:33 - mmengine - INFO - Epoch(train) [8][ 100/1567] lr: 5.9145e-02 eta: 0:43:56 time: 0.1963 data_time: 0.0069 memory: 2656 loss: 0.2940 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2940 2022/12/30 13:40:51 - mmengine - INFO - Epoch(train) [8][ 200/1567] lr: 5.8529e-02 eta: 0:43:36 time: 0.1839 data_time: 0.0066 memory: 2656 loss: 0.3203 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.3203 2022/12/30 13:41:10 - mmengine - INFO - Epoch(train) [8][ 300/1567] lr: 5.7911e-02 eta: 0:43:17 time: 0.1948 data_time: 0.0066 memory: 2656 loss: 0.2806 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.2806 2022/12/30 13:41:28 - mmengine - INFO - Epoch(train) [8][ 400/1567] lr: 5.7292e-02 eta: 0:42:58 time: 0.1833 data_time: 0.0065 memory: 2656 loss: 0.2642 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2642 2022/12/30 13:41:47 - mmengine - INFO - Epoch(train) [8][ 500/1567] lr: 5.6671e-02 eta: 0:42:39 time: 0.1863 data_time: 0.0072 memory: 2656 loss: 0.2507 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2507 2022/12/30 13:42:06 - mmengine - INFO - Epoch(train) [8][ 600/1567] lr: 5.6050e-02 eta: 0:42:21 time: 0.2020 data_time: 0.0074 memory: 2656 loss: 0.3725 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.3725 2022/12/30 13:42:24 - mmengine - INFO - Epoch(train) [8][ 700/1567] lr: 5.5427e-02 eta: 0:42:02 time: 0.1839 data_time: 0.0065 memory: 2656 loss: 0.2995 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2995 2022/12/30 13:42:43 - mmengine - INFO - Epoch(train) [8][ 800/1567] lr: 5.4804e-02 eta: 0:41:42 time: 0.1976 data_time: 0.0065 memory: 2656 loss: 0.3119 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3119 2022/12/30 13:43:02 - mmengine - INFO - Epoch(train) [8][ 900/1567] lr: 5.4180e-02 eta: 0:41:24 time: 0.1853 data_time: 0.0069 memory: 2656 loss: 0.3209 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.3209 2022/12/30 13:43:20 - mmengine - INFO - Epoch(train) [8][1000/1567] lr: 5.3556e-02 eta: 0:41:04 time: 0.1881 data_time: 0.0065 memory: 2656 loss: 0.2587 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2587 2022/12/30 13:43:26 - mmengine - INFO - Exp name: stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221230_130356 2022/12/30 13:43:39 - mmengine - INFO - Epoch(train) [8][1100/1567] lr: 5.2930e-02 eta: 0:40:45 time: 0.1758 data_time: 0.0066 memory: 2656 loss: 0.2773 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.2773 2022/12/30 13:43:57 - mmengine - INFO - Epoch(train) [8][1200/1567] lr: 5.2305e-02 eta: 0:40:26 time: 0.1884 data_time: 0.0067 memory: 2656 loss: 0.3141 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.3141 2022/12/30 13:44:16 - mmengine - INFO - Epoch(train) [8][1300/1567] lr: 5.1679e-02 eta: 0:40:07 time: 0.1877 data_time: 0.0066 memory: 2656 loss: 0.2480 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.2480 2022/12/30 13:44:35 - mmengine - INFO - Epoch(train) [8][1400/1567] lr: 5.1052e-02 eta: 0:39:48 time: 0.1894 data_time: 0.0066 memory: 2656 loss: 0.2021 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2021 2022/12/30 13:44:53 - mmengine - INFO - Epoch(train) [8][1500/1567] lr: 5.0426e-02 eta: 0:39:29 time: 0.1820 data_time: 0.0066 memory: 2656 loss: 0.3576 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3576 2022/12/30 13:45:05 - mmengine - INFO - Exp name: stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221230_130356 2022/12/30 13:45:05 - mmengine - INFO - Epoch(train) [8][1567/1567] lr: 5.0006e-02 eta: 0:39:16 time: 0.1726 data_time: 0.0065 memory: 2656 loss: 0.4014 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.4014 2022/12/30 13:45:05 - mmengine - INFO - Saving checkpoint at 8 epochs 2022/12/30 13:45:10 - mmengine - INFO - Epoch(val) [8][100/129] eta: 0:00:01 time: 0.0394 data_time: 0.0069 memory: 378 2022/12/30 13:45:12 - mmengine - INFO - Epoch(val) [8][129/129] acc/top1: 0.8188 acc/top5: 0.9673 acc/mean1: 0.8187 2022/12/30 13:45:12 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_7.pth is removed 2022/12/30 13:45:12 - mmengine - INFO - The best checkpoint with 0.8188 acc/top1 at 8 epoch is saved to best_acc/top1_epoch_8.pth. 2022/12/30 13:45:31 - mmengine - INFO - Epoch(train) [9][ 100/1567] lr: 4.9380e-02 eta: 0:38:57 time: 0.1813 data_time: 0.0066 memory: 2656 loss: 0.1911 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1911 2022/12/30 13:45:49 - mmengine - INFO - Epoch(train) [9][ 200/1567] lr: 4.8753e-02 eta: 0:38:38 time: 0.1808 data_time: 0.0065 memory: 2656 loss: 0.2933 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.2933 2022/12/30 13:46:09 - mmengine - INFO - Epoch(train) [9][ 300/1567] lr: 4.8127e-02 eta: 0:38:20 time: 0.1847 data_time: 0.0070 memory: 2656 loss: 0.3140 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3140 2022/12/30 13:46:27 - mmengine - INFO - Epoch(train) [9][ 400/1567] lr: 4.7501e-02 eta: 0:38:00 time: 0.1812 data_time: 0.0065 memory: 2656 loss: 0.2805 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2805 2022/12/30 13:46:38 - mmengine - INFO - Exp name: stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221230_130356 2022/12/30 13:46:45 - mmengine - INFO - Epoch(train) [9][ 500/1567] lr: 4.6876e-02 eta: 0:37:41 time: 0.2003 data_time: 0.0069 memory: 2656 loss: 0.2082 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 0.2082 2022/12/30 13:47:04 - mmengine - INFO - Epoch(train) [9][ 600/1567] lr: 4.6251e-02 eta: 0:37:22 time: 0.1856 data_time: 0.0067 memory: 2656 loss: 0.2282 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2282 2022/12/30 13:47:22 - mmengine - INFO - Epoch(train) [9][ 700/1567] lr: 4.5626e-02 eta: 0:37:03 time: 0.1801 data_time: 0.0066 memory: 2656 loss: 0.2406 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2406 2022/12/30 13:47:41 - mmengine - INFO - Epoch(train) [9][ 800/1567] lr: 4.5003e-02 eta: 0:36:44 time: 0.1868 data_time: 0.0067 memory: 2656 loss: 0.2430 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2430 2022/12/30 13:48:00 - mmengine - INFO - Epoch(train) [9][ 900/1567] lr: 4.4380e-02 eta: 0:36:25 time: 0.1860 data_time: 0.0066 memory: 2656 loss: 0.2692 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.2692 2022/12/30 13:48:18 - mmengine - INFO - Epoch(train) [9][1000/1567] lr: 4.3757e-02 eta: 0:36:06 time: 0.1932 data_time: 0.0066 memory: 2656 loss: 0.2263 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.2263 2022/12/30 13:48:36 - mmengine - INFO - Epoch(train) [9][1100/1567] lr: 4.3136e-02 eta: 0:35:47 time: 0.1760 data_time: 0.0066 memory: 2656 loss: 0.2181 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2181 2022/12/30 13:48:54 - mmengine - INFO - Epoch(train) [9][1200/1567] lr: 4.2516e-02 eta: 0:35:27 time: 0.1831 data_time: 0.0070 memory: 2656 loss: 0.2328 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2328 2022/12/30 13:49:13 - mmengine - INFO - Epoch(train) [9][1300/1567] lr: 4.1897e-02 eta: 0:35:09 time: 0.1846 data_time: 0.0065 memory: 2656 loss: 0.2228 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2228 2022/12/30 13:49:32 - mmengine - INFO - Epoch(train) [9][1400/1567] lr: 4.1280e-02 eta: 0:34:50 time: 0.1936 data_time: 0.0066 memory: 2656 loss: 0.1962 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1962 2022/12/30 13:49:44 - mmengine - INFO - Exp name: stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221230_130356 2022/12/30 13:49:50 - mmengine - INFO - Epoch(train) [9][1500/1567] lr: 4.0664e-02 eta: 0:34:31 time: 0.1817 data_time: 0.0071 memory: 2656 loss: 0.2094 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2094 2022/12/30 13:50:02 - mmengine - INFO - Exp name: stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221230_130356 2022/12/30 13:50:02 - mmengine - INFO - Epoch(train) [9][1567/1567] lr: 4.0252e-02 eta: 0:34:18 time: 0.1626 data_time: 0.0068 memory: 2656 loss: 0.3809 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.3809 2022/12/30 13:50:02 - mmengine - INFO - Saving checkpoint at 9 epochs 2022/12/30 13:50:07 - mmengine - INFO - Epoch(val) [9][100/129] eta: 0:00:01 time: 0.0408 data_time: 0.0073 memory: 378 2022/12/30 13:50:09 - mmengine - INFO - Epoch(val) [9][129/129] acc/top1: 0.8286 acc/top5: 0.9654 acc/mean1: 0.8285 2022/12/30 13:50:09 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_8.pth is removed 2022/12/30 13:50:10 - mmengine - INFO - The best checkpoint with 0.8286 acc/top1 at 9 epoch is saved to best_acc/top1_epoch_9.pth. 2022/12/30 13:50:28 - mmengine - INFO - Epoch(train) [10][ 100/1567] lr: 3.9638e-02 eta: 0:33:59 time: 0.1856 data_time: 0.0065 memory: 2656 loss: 0.1816 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1816 2022/12/30 13:50:47 - mmengine - INFO - Epoch(train) [10][ 200/1567] lr: 3.9026e-02 eta: 0:33:40 time: 0.1797 data_time: 0.0070 memory: 2656 loss: 0.1974 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1974 2022/12/30 13:51:05 - mmengine - INFO - Epoch(train) [10][ 300/1567] lr: 3.8415e-02 eta: 0:33:21 time: 0.1839 data_time: 0.0081 memory: 2656 loss: 0.2035 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2035 2022/12/30 13:51:24 - mmengine - INFO - Epoch(train) [10][ 400/1567] lr: 3.7807e-02 eta: 0:33:02 time: 0.1872 data_time: 0.0068 memory: 2656 loss: 0.2562 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2562 2022/12/30 13:51:43 - mmengine - INFO - Epoch(train) [10][ 500/1567] lr: 3.7200e-02 eta: 0:32:44 time: 0.1890 data_time: 0.0074 memory: 2656 loss: 0.1917 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1917 2022/12/30 13:52:02 - mmengine - INFO - Epoch(train) [10][ 600/1567] lr: 3.6596e-02 eta: 0:32:25 time: 0.1950 data_time: 0.0073 memory: 2656 loss: 0.1993 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1993 2022/12/30 13:52:21 - mmengine - INFO - Epoch(train) [10][ 700/1567] lr: 3.5993e-02 eta: 0:32:07 time: 0.1921 data_time: 0.0070 memory: 2656 loss: 0.2145 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 0.2145 2022/12/30 13:52:41 - mmengine - INFO - Epoch(train) [10][ 800/1567] lr: 3.5393e-02 eta: 0:31:48 time: 0.1892 data_time: 0.0068 memory: 2656 loss: 0.2041 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2041 2022/12/30 13:52:59 - mmengine - INFO - Exp name: stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221230_130356 2022/12/30 13:53:00 - mmengine - INFO - Epoch(train) [10][ 900/1567] lr: 3.4795e-02 eta: 0:31:30 time: 0.1892 data_time: 0.0068 memory: 2656 loss: 0.1798 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1798 2022/12/30 13:53:19 - mmengine - INFO - Epoch(train) [10][1000/1567] lr: 3.4199e-02 eta: 0:31:11 time: 0.1905 data_time: 0.0075 memory: 2656 loss: 0.1442 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1442 2022/12/30 13:53:38 - mmengine - INFO - Epoch(train) [10][1100/1567] lr: 3.3606e-02 eta: 0:30:52 time: 0.1845 data_time: 0.0070 memory: 2656 loss: 0.1426 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1426 2022/12/30 13:53:57 - mmengine - INFO - Epoch(train) [10][1200/1567] lr: 3.3015e-02 eta: 0:30:34 time: 0.1955 data_time: 0.0068 memory: 2656 loss: 0.2054 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2054 2022/12/30 13:54:16 - mmengine - INFO - Epoch(train) [10][1300/1567] lr: 3.2428e-02 eta: 0:30:15 time: 0.1896 data_time: 0.0066 memory: 2656 loss: 0.1742 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1742 2022/12/30 13:54:35 - mmengine - INFO - Epoch(train) [10][1400/1567] lr: 3.1842e-02 eta: 0:29:56 time: 0.1828 data_time: 0.0069 memory: 2656 loss: 0.1621 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1621 2022/12/30 13:54:53 - mmengine - INFO - Epoch(train) [10][1500/1567] lr: 3.1260e-02 eta: 0:29:38 time: 0.1852 data_time: 0.0069 memory: 2656 loss: 0.1808 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1808 2022/12/30 13:55:05 - mmengine - INFO - Exp name: stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221230_130356 2022/12/30 13:55:05 - mmengine - INFO - Epoch(train) [10][1567/1567] lr: 3.0872e-02 eta: 0:29:25 time: 0.1586 data_time: 0.0065 memory: 2656 loss: 0.3474 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.3474 2022/12/30 13:55:05 - mmengine - INFO - Saving checkpoint at 10 epochs 2022/12/30 13:55:10 - mmengine - INFO - Epoch(val) [10][100/129] eta: 0:00:01 time: 0.0426 data_time: 0.0088 memory: 378 2022/12/30 13:55:12 - mmengine - INFO - Epoch(val) [10][129/129] acc/top1: 0.8222 acc/top5: 0.9642 acc/mean1: 0.8222 2022/12/30 13:55:31 - mmengine - INFO - Epoch(train) [11][ 100/1567] lr: 3.0294e-02 eta: 0:29:06 time: 0.1892 data_time: 0.0066 memory: 2656 loss: 0.1177 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1177 2022/12/30 13:55:50 - mmengine - INFO - Epoch(train) [11][ 200/1567] lr: 2.9720e-02 eta: 0:28:47 time: 0.1884 data_time: 0.0067 memory: 2656 loss: 0.1119 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1119 2022/12/30 13:56:09 - mmengine - INFO - Epoch(train) [11][ 300/1567] lr: 2.9149e-02 eta: 0:28:29 time: 0.1932 data_time: 0.0074 memory: 2656 loss: 0.1281 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1281 2022/12/30 13:56:15 - mmengine - INFO - Exp name: stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221230_130356 2022/12/30 13:56:29 - mmengine - INFO - Epoch(train) [11][ 400/1567] lr: 2.8581e-02 eta: 0:28:10 time: 0.1946 data_time: 0.0068 memory: 2656 loss: 0.1487 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1487 2022/12/30 13:56:48 - mmengine - INFO - Epoch(train) [11][ 500/1567] lr: 2.8017e-02 eta: 0:27:52 time: 0.1993 data_time: 0.0067 memory: 2656 loss: 0.1202 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1202 2022/12/30 13:57:07 - mmengine - INFO - Epoch(train) [11][ 600/1567] lr: 2.7456e-02 eta: 0:27:34 time: 0.1957 data_time: 0.0076 memory: 2656 loss: 0.1422 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1422 2022/12/30 13:57:27 - mmengine - INFO - Epoch(train) [11][ 700/1567] lr: 2.6898e-02 eta: 0:27:15 time: 0.1899 data_time: 0.0068 memory: 2656 loss: 0.1010 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1010 2022/12/30 13:57:46 - mmengine - INFO - Epoch(train) [11][ 800/1567] lr: 2.6345e-02 eta: 0:26:56 time: 0.2020 data_time: 0.0067 memory: 2656 loss: 0.1512 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1512 2022/12/30 13:58:05 - mmengine - INFO - Epoch(train) [11][ 900/1567] lr: 2.5794e-02 eta: 0:26:38 time: 0.1940 data_time: 0.0071 memory: 2656 loss: 0.1148 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1148 2022/12/30 13:58:25 - mmengine - INFO - Epoch(train) [11][1000/1567] lr: 2.5248e-02 eta: 0:26:20 time: 0.1983 data_time: 0.0073 memory: 2656 loss: 0.1514 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1514 2022/12/30 13:58:44 - mmengine - INFO - Epoch(train) [11][1100/1567] lr: 2.4706e-02 eta: 0:26:01 time: 0.1924 data_time: 0.0069 memory: 2656 loss: 0.1220 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1220 2022/12/30 13:59:04 - mmengine - INFO - Epoch(train) [11][1200/1567] lr: 2.4167e-02 eta: 0:25:43 time: 0.1977 data_time: 0.0069 memory: 2656 loss: 0.1066 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1066 2022/12/30 13:59:24 - mmengine - INFO - Epoch(train) [11][1300/1567] lr: 2.3633e-02 eta: 0:25:24 time: 0.1959 data_time: 0.0067 memory: 2656 loss: 0.1471 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1471 2022/12/30 13:59:30 - mmengine - INFO - Exp name: stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221230_130356 2022/12/30 13:59:43 - mmengine - INFO - Epoch(train) [11][1400/1567] lr: 2.3103e-02 eta: 0:25:06 time: 0.1926 data_time: 0.0067 memory: 2656 loss: 0.1696 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1696 2022/12/30 14:00:02 - mmengine - INFO - Epoch(train) [11][1500/1567] lr: 2.2577e-02 eta: 0:24:47 time: 0.1920 data_time: 0.0068 memory: 2656 loss: 0.1647 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1647 2022/12/30 14:00:15 - mmengine - INFO - Exp name: stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221230_130356 2022/12/30 14:00:15 - mmengine - INFO - Epoch(train) [11][1567/1567] lr: 2.2227e-02 eta: 0:24:34 time: 0.1611 data_time: 0.0067 memory: 2656 loss: 0.2766 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.2766 2022/12/30 14:00:15 - mmengine - INFO - Saving checkpoint at 11 epochs 2022/12/30 14:00:19 - mmengine - INFO - Epoch(val) [11][100/129] eta: 0:00:01 time: 0.0416 data_time: 0.0064 memory: 378 2022/12/30 14:00:22 - mmengine - INFO - Epoch(val) [11][129/129] acc/top1: 0.8234 acc/top5: 0.9658 acc/mean1: 0.8233 2022/12/30 14:00:42 - mmengine - INFO - Epoch(train) [12][ 100/1567] lr: 2.1708e-02 eta: 0:24:16 time: 0.2025 data_time: 0.0077 memory: 2656 loss: 0.1382 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1382 2022/12/30 14:01:01 - mmengine - INFO - Epoch(train) [12][ 200/1567] lr: 2.1194e-02 eta: 0:23:57 time: 0.1895 data_time: 0.0068 memory: 2656 loss: 0.0763 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0763 2022/12/30 14:01:20 - mmengine - INFO - Epoch(train) [12][ 300/1567] lr: 2.0684e-02 eta: 0:23:38 time: 0.1915 data_time: 0.0067 memory: 2656 loss: 0.0935 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0935 2022/12/30 14:01:39 - mmengine - INFO - Epoch(train) [12][ 400/1567] lr: 2.0179e-02 eta: 0:23:20 time: 0.1962 data_time: 0.0069 memory: 2656 loss: 0.1194 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1194 2022/12/30 14:01:59 - mmengine - INFO - Epoch(train) [12][ 500/1567] lr: 1.9678e-02 eta: 0:23:01 time: 0.1959 data_time: 0.0067 memory: 2656 loss: 0.0637 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0637 2022/12/30 14:02:18 - mmengine - INFO - Epoch(train) [12][ 600/1567] lr: 1.9182e-02 eta: 0:22:43 time: 0.1892 data_time: 0.0069 memory: 2656 loss: 0.1160 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1160 2022/12/30 14:02:38 - mmengine - INFO - Epoch(train) [12][ 700/1567] lr: 1.8691e-02 eta: 0:22:24 time: 0.1909 data_time: 0.0070 memory: 2656 loss: 0.0910 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0910 2022/12/30 14:02:50 - mmengine - INFO - Exp name: stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221230_130356 2022/12/30 14:02:57 - mmengine - INFO - Epoch(train) [12][ 800/1567] lr: 1.8205e-02 eta: 0:22:05 time: 0.1835 data_time: 0.0067 memory: 2656 loss: 0.0924 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0924 2022/12/30 14:03:16 - mmengine - INFO - Epoch(train) [12][ 900/1567] lr: 1.7724e-02 eta: 0:21:46 time: 0.1869 data_time: 0.0066 memory: 2656 loss: 0.1042 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1042 2022/12/30 14:03:34 - mmengine - INFO - Epoch(train) [12][1000/1567] lr: 1.7248e-02 eta: 0:21:28 time: 0.1814 data_time: 0.0073 memory: 2656 loss: 0.0637 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0637 2022/12/30 14:03:54 - mmengine - INFO - Epoch(train) [12][1100/1567] lr: 1.6778e-02 eta: 0:21:09 time: 0.1861 data_time: 0.0067 memory: 2656 loss: 0.0880 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.0880 2022/12/30 14:04:13 - mmengine - INFO - Epoch(train) [12][1200/1567] lr: 1.6312e-02 eta: 0:20:50 time: 0.1878 data_time: 0.0068 memory: 2656 loss: 0.0519 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0519 2022/12/30 14:04:32 - mmengine - INFO - Epoch(train) [12][1300/1567] lr: 1.5852e-02 eta: 0:20:31 time: 0.1913 data_time: 0.0077 memory: 2656 loss: 0.0556 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0556 2022/12/30 14:04:51 - mmengine - INFO - Epoch(train) [12][1400/1567] lr: 1.5397e-02 eta: 0:20:13 time: 0.1837 data_time: 0.0068 memory: 2656 loss: 0.0521 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0521 2022/12/30 14:05:10 - mmengine - INFO - Epoch(train) [12][1500/1567] lr: 1.4947e-02 eta: 0:19:54 time: 0.1954 data_time: 0.0069 memory: 2656 loss: 0.0680 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0680 2022/12/30 14:05:22 - mmengine - INFO - Exp name: stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221230_130356 2022/12/30 14:05:22 - mmengine - INFO - Epoch(train) [12][1567/1567] lr: 1.4649e-02 eta: 0:19:41 time: 0.1565 data_time: 0.0065 memory: 2656 loss: 0.2152 top1_acc: 0.0000 top5_acc: 1.0000 loss_cls: 0.2152 2022/12/30 14:05:22 - mmengine - INFO - Saving checkpoint at 12 epochs 2022/12/30 14:05:27 - mmengine - INFO - Epoch(val) [12][100/129] eta: 0:00:01 time: 0.0414 data_time: 0.0066 memory: 378 2022/12/30 14:05:29 - mmengine - INFO - Epoch(val) [12][129/129] acc/top1: 0.8527 acc/top5: 0.9708 acc/mean1: 0.8526 2022/12/30 14:05:29 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_9.pth is removed 2022/12/30 14:05:29 - mmengine - INFO - The best checkpoint with 0.8527 acc/top1 at 12 epoch is saved to best_acc/top1_epoch_12.pth. 2022/12/30 14:05:48 - mmengine - INFO - Epoch(train) [13][ 100/1567] lr: 1.4209e-02 eta: 0:19:22 time: 0.1846 data_time: 0.0070 memory: 2656 loss: 0.0384 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0384 2022/12/30 14:06:07 - mmengine - INFO - Exp name: stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221230_130356 2022/12/30 14:06:08 - mmengine - INFO - Epoch(train) [13][ 200/1567] lr: 1.3774e-02 eta: 0:19:03 time: 0.1827 data_time: 0.0067 memory: 2656 loss: 0.0552 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0552 2022/12/30 14:06:27 - mmengine - INFO - Epoch(train) [13][ 300/1567] lr: 1.3345e-02 eta: 0:18:45 time: 0.1959 data_time: 0.0067 memory: 2656 loss: 0.0458 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0458 2022/12/30 14:06:45 - mmengine - INFO - Epoch(train) [13][ 400/1567] lr: 1.2922e-02 eta: 0:18:26 time: 0.1779 data_time: 0.0068 memory: 2656 loss: 0.0423 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0423 2022/12/30 14:07:04 - mmengine - INFO - Epoch(train) [13][ 500/1567] lr: 1.2505e-02 eta: 0:18:07 time: 0.1831 data_time: 0.0069 memory: 2656 loss: 0.0298 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0298 2022/12/30 14:07:22 - mmengine - INFO - Epoch(train) [13][ 600/1567] lr: 1.2093e-02 eta: 0:17:48 time: 0.1809 data_time: 0.0068 memory: 2656 loss: 0.0528 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0528 2022/12/30 14:07:41 - mmengine - INFO - Epoch(train) [13][ 700/1567] lr: 1.1687e-02 eta: 0:17:29 time: 0.1860 data_time: 0.0067 memory: 2656 loss: 0.0551 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0551 2022/12/30 14:08:00 - mmengine - INFO - Epoch(train) [13][ 800/1567] lr: 1.1288e-02 eta: 0:17:10 time: 0.1924 data_time: 0.0067 memory: 2656 loss: 0.0297 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0297 2022/12/30 14:08:19 - mmengine - INFO - Epoch(train) [13][ 900/1567] lr: 1.0894e-02 eta: 0:16:51 time: 0.1999 data_time: 0.0070 memory: 2656 loss: 0.0328 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0328 2022/12/30 14:08:38 - mmengine - INFO - Epoch(train) [13][1000/1567] lr: 1.0507e-02 eta: 0:16:33 time: 0.1856 data_time: 0.0067 memory: 2656 loss: 0.0287 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0287 2022/12/30 14:08:56 - mmengine - INFO - Epoch(train) [13][1100/1567] lr: 1.0126e-02 eta: 0:16:13 time: 0.1889 data_time: 0.0078 memory: 2656 loss: 0.0205 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0205 2022/12/30 14:09:15 - mmengine - INFO - Exp name: stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221230_130356 2022/12/30 14:09:16 - mmengine - INFO - Epoch(train) [13][1200/1567] lr: 9.7512e-03 eta: 0:15:55 time: 0.1984 data_time: 0.0071 memory: 2656 loss: 0.0370 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0370 2022/12/30 14:09:35 - mmengine - INFO - Epoch(train) [13][1300/1567] lr: 9.3826e-03 eta: 0:15:36 time: 0.1893 data_time: 0.0071 memory: 2656 loss: 0.0310 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0310 2022/12/30 14:09:53 - mmengine - INFO - Epoch(train) [13][1400/1567] lr: 9.0204e-03 eta: 0:15:17 time: 0.1778 data_time: 0.0067 memory: 2656 loss: 0.0275 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0275 2022/12/30 14:10:11 - mmengine - INFO - Epoch(train) [13][1500/1567] lr: 8.6647e-03 eta: 0:14:58 time: 0.1749 data_time: 0.0075 memory: 2656 loss: 0.0190 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0190 2022/12/30 14:10:23 - mmengine - INFO - Exp name: stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221230_130356 2022/12/30 14:10:23 - mmengine - INFO - Epoch(train) [13][1567/1567] lr: 8.4300e-03 eta: 0:14:45 time: 0.1614 data_time: 0.0067 memory: 2656 loss: 0.1715 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1715 2022/12/30 14:10:23 - mmengine - INFO - Saving checkpoint at 13 epochs 2022/12/30 14:10:28 - mmengine - INFO - Epoch(val) [13][100/129] eta: 0:00:01 time: 0.0431 data_time: 0.0065 memory: 378 2022/12/30 14:10:29 - mmengine - INFO - Epoch(val) [13][129/129] acc/top1: 0.8646 acc/top5: 0.9737 acc/mean1: 0.8645 2022/12/30 14:10:29 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_12.pth is removed 2022/12/30 14:10:30 - mmengine - INFO - The best checkpoint with 0.8646 acc/top1 at 13 epoch is saved to best_acc/top1_epoch_13.pth. 2022/12/30 14:10:49 - mmengine - INFO - Epoch(train) [14][ 100/1567] lr: 8.0851e-03 eta: 0:14:26 time: 0.1927 data_time: 0.0069 memory: 2656 loss: 0.0203 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0203 2022/12/30 14:11:08 - mmengine - INFO - Epoch(train) [14][ 200/1567] lr: 7.7469e-03 eta: 0:14:08 time: 0.1886 data_time: 0.0073 memory: 2656 loss: 0.0134 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0134 2022/12/30 14:11:26 - mmengine - INFO - Epoch(train) [14][ 300/1567] lr: 7.4152e-03 eta: 0:13:49 time: 0.1794 data_time: 0.0069 memory: 2656 loss: 0.0491 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.0491 2022/12/30 14:11:45 - mmengine - INFO - Epoch(train) [14][ 400/1567] lr: 7.0902e-03 eta: 0:13:30 time: 0.1864 data_time: 0.0067 memory: 2656 loss: 0.0227 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0227 2022/12/30 14:12:04 - mmengine - INFO - Epoch(train) [14][ 500/1567] lr: 6.7720e-03 eta: 0:13:11 time: 0.1816 data_time: 0.0071 memory: 2656 loss: 0.0277 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0277 2022/12/30 14:12:22 - mmengine - INFO - Epoch(train) [14][ 600/1567] lr: 6.4606e-03 eta: 0:12:52 time: 0.1865 data_time: 0.0067 memory: 2656 loss: 0.0195 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0195 2022/12/30 14:12:28 - mmengine - INFO - Exp name: stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221230_130356 2022/12/30 14:12:41 - mmengine - INFO - Epoch(train) [14][ 700/1567] lr: 6.1560e-03 eta: 0:12:33 time: 0.1886 data_time: 0.0068 memory: 2656 loss: 0.0221 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0221 2022/12/30 14:12:59 - mmengine - INFO - Epoch(train) [14][ 800/1567] lr: 5.8582e-03 eta: 0:12:14 time: 0.1879 data_time: 0.0069 memory: 2656 loss: 0.0224 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0224 2022/12/30 14:13:19 - mmengine - INFO - Epoch(train) [14][ 900/1567] lr: 5.5675e-03 eta: 0:11:56 time: 0.2037 data_time: 0.0067 memory: 2656 loss: 0.0141 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0141 2022/12/30 14:13:38 - mmengine - INFO - Epoch(train) [14][1000/1567] lr: 5.2836e-03 eta: 0:11:37 time: 0.1901 data_time: 0.0066 memory: 2656 loss: 0.0131 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0131 2022/12/30 14:13:57 - mmengine - INFO - Epoch(train) [14][1100/1567] lr: 5.0068e-03 eta: 0:11:18 time: 0.1924 data_time: 0.0069 memory: 2656 loss: 0.0179 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0179 2022/12/30 14:14:16 - mmengine - INFO - Epoch(train) [14][1200/1567] lr: 4.7371e-03 eta: 0:10:59 time: 0.1847 data_time: 0.0069 memory: 2656 loss: 0.0131 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0131 2022/12/30 14:14:34 - mmengine - INFO - Epoch(train) [14][1300/1567] lr: 4.4745e-03 eta: 0:10:40 time: 0.1964 data_time: 0.0067 memory: 2656 loss: 0.0141 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0141 2022/12/30 14:14:54 - mmengine - INFO - Epoch(train) [14][1400/1567] lr: 4.2190e-03 eta: 0:10:21 time: 0.1932 data_time: 0.0067 memory: 2656 loss: 0.0195 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0195 2022/12/30 14:15:13 - mmengine - INFO - Epoch(train) [14][1500/1567] lr: 3.9707e-03 eta: 0:10:03 time: 0.1990 data_time: 0.0068 memory: 2656 loss: 0.0196 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0196 2022/12/30 14:15:25 - mmengine - INFO - Exp name: stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221230_130356 2022/12/30 14:15:25 - mmengine - INFO - Epoch(train) [14][1567/1567] lr: 3.8084e-03 eta: 0:09:50 time: 0.1644 data_time: 0.0071 memory: 2656 loss: 0.1986 top1_acc: 0.0000 top5_acc: 1.0000 loss_cls: 0.1986 2022/12/30 14:15:25 - mmengine - INFO - Saving checkpoint at 14 epochs 2022/12/30 14:15:30 - mmengine - INFO - Epoch(val) [14][100/129] eta: 0:00:01 time: 0.0426 data_time: 0.0106 memory: 378 2022/12/30 14:15:33 - mmengine - INFO - Epoch(val) [14][129/129] acc/top1: 0.8575 acc/top5: 0.9736 acc/mean1: 0.8575 2022/12/30 14:15:44 - mmengine - INFO - Exp name: stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221230_130356 2022/12/30 14:15:51 - mmengine - INFO - Epoch(train) [15][ 100/1567] lr: 3.5722e-03 eta: 0:09:31 time: 0.1890 data_time: 0.0069 memory: 2656 loss: 0.0197 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0197 2022/12/30 14:16:10 - mmengine - INFO - Epoch(train) [15][ 200/1567] lr: 3.3433e-03 eta: 0:09:12 time: 0.1858 data_time: 0.0067 memory: 2656 loss: 0.0124 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0124 2022/12/30 14:16:29 - mmengine - INFO - Epoch(train) [15][ 300/1567] lr: 3.1217e-03 eta: 0:08:53 time: 0.1838 data_time: 0.0080 memory: 2656 loss: 0.0124 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0124 2022/12/30 14:16:48 - mmengine - INFO - Epoch(train) [15][ 400/1567] lr: 2.9075e-03 eta: 0:08:35 time: 0.1935 data_time: 0.0067 memory: 2656 loss: 0.0138 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0138 2022/12/30 14:17:07 - mmengine - INFO - Epoch(train) [15][ 500/1567] lr: 2.7007e-03 eta: 0:08:16 time: 0.1708 data_time: 0.0071 memory: 2656 loss: 0.0204 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0204 2022/12/30 14:17:25 - mmengine - INFO - Epoch(train) [15][ 600/1567] lr: 2.5013e-03 eta: 0:07:57 time: 0.1843 data_time: 0.0068 memory: 2656 loss: 0.0133 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0133 2022/12/30 14:17:44 - mmengine - INFO - Epoch(train) [15][ 700/1567] lr: 2.3093e-03 eta: 0:07:38 time: 0.1851 data_time: 0.0067 memory: 2656 loss: 0.0116 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0116 2022/12/30 14:18:03 - mmengine - INFO - Epoch(train) [15][ 800/1567] lr: 2.1249e-03 eta: 0:07:19 time: 0.1761 data_time: 0.0067 memory: 2656 loss: 0.0108 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0108 2022/12/30 14:18:22 - mmengine - INFO - Epoch(train) [15][ 900/1567] lr: 1.9479e-03 eta: 0:07:00 time: 0.1862 data_time: 0.0067 memory: 2656 loss: 0.0184 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0184 2022/12/30 14:18:41 - mmengine - INFO - Epoch(train) [15][1000/1567] lr: 1.7785e-03 eta: 0:06:42 time: 0.1850 data_time: 0.0070 memory: 2656 loss: 0.0145 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0145 2022/12/30 14:18:52 - mmengine - INFO - Exp name: stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221230_130356 2022/12/30 14:19:00 - mmengine - INFO - Epoch(train) [15][1100/1567] lr: 1.6167e-03 eta: 0:06:23 time: 0.2002 data_time: 0.0068 memory: 2656 loss: 0.0106 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0106 2022/12/30 14:19:18 - mmengine - INFO - Epoch(train) [15][1200/1567] lr: 1.4625e-03 eta: 0:06:04 time: 0.1932 data_time: 0.0069 memory: 2656 loss: 0.0201 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0201 2022/12/30 14:19:37 - mmengine - INFO - Epoch(train) [15][1300/1567] lr: 1.3159e-03 eta: 0:05:45 time: 0.2033 data_time: 0.0067 memory: 2656 loss: 0.0181 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0181 2022/12/30 14:19:56 - mmengine - INFO - Epoch(train) [15][1400/1567] lr: 1.1769e-03 eta: 0:05:26 time: 0.1746 data_time: 0.0067 memory: 2656 loss: 0.0146 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0146 2022/12/30 14:20:16 - mmengine - INFO - Epoch(train) [15][1500/1567] lr: 1.0456e-03 eta: 0:05:07 time: 0.1875 data_time: 0.0067 memory: 2656 loss: 0.0093 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0093 2022/12/30 14:20:28 - mmengine - INFO - Exp name: stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221230_130356 2022/12/30 14:20:28 - mmengine - INFO - Epoch(train) [15][1567/1567] lr: 9.6196e-04 eta: 0:04:55 time: 0.1516 data_time: 0.0066 memory: 2656 loss: 0.1946 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.1946 2022/12/30 14:20:28 - mmengine - INFO - Saving checkpoint at 15 epochs 2022/12/30 14:20:33 - mmengine - INFO - Epoch(val) [15][100/129] eta: 0:00:01 time: 0.0447 data_time: 0.0101 memory: 378 2022/12/30 14:20:35 - mmengine - INFO - Epoch(val) [15][129/129] acc/top1: 0.8716 acc/top5: 0.9757 acc/mean1: 0.8715 2022/12/30 14:20:35 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_13.pth is removed 2022/12/30 14:20:35 - mmengine - INFO - The best checkpoint with 0.8716 acc/top1 at 15 epoch is saved to best_acc/top1_epoch_15.pth. 2022/12/30 14:20:54 - mmengine - INFO - Epoch(train) [16][ 100/1567] lr: 8.4351e-04 eta: 0:04:36 time: 0.1949 data_time: 0.0069 memory: 2656 loss: 0.0134 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0134 2022/12/30 14:21:13 - mmengine - INFO - Epoch(train) [16][ 200/1567] lr: 7.3277e-04 eta: 0:04:17 time: 0.1965 data_time: 0.0068 memory: 2656 loss: 0.0267 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0267 2022/12/30 14:21:32 - mmengine - INFO - Epoch(train) [16][ 300/1567] lr: 6.2978e-04 eta: 0:03:58 time: 0.1890 data_time: 0.0069 memory: 2656 loss: 0.0147 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0147 2022/12/30 14:21:51 - mmengine - INFO - Epoch(train) [16][ 400/1567] lr: 5.3453e-04 eta: 0:03:39 time: 0.1828 data_time: 0.0068 memory: 2656 loss: 0.0172 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0172 2022/12/30 14:22:08 - mmengine - INFO - Exp name: stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221230_130356 2022/12/30 14:22:09 - mmengine - INFO - Epoch(train) [16][ 500/1567] lr: 4.4705e-04 eta: 0:03:21 time: 0.1820 data_time: 0.0072 memory: 2656 loss: 0.0104 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0104 2022/12/30 14:22:27 - mmengine - INFO - Epoch(train) [16][ 600/1567] lr: 3.6735e-04 eta: 0:03:02 time: 0.1876 data_time: 0.0069 memory: 2656 loss: 0.0100 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0100 2022/12/30 14:22:46 - mmengine - INFO - Epoch(train) [16][ 700/1567] lr: 2.9544e-04 eta: 0:02:43 time: 0.1836 data_time: 0.0067 memory: 2656 loss: 0.0121 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0121 2022/12/30 14:23:05 - mmengine - INFO - Epoch(train) [16][ 800/1567] lr: 2.3134e-04 eta: 0:02:24 time: 0.1925 data_time: 0.0068 memory: 2656 loss: 0.0107 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0107 2022/12/30 14:23:24 - mmengine - INFO - Epoch(train) [16][ 900/1567] lr: 1.7505e-04 eta: 0:02:05 time: 0.1914 data_time: 0.0069 memory: 2656 loss: 0.0123 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0123 2022/12/30 14:23:42 - mmengine - INFO - Epoch(train) [16][1000/1567] lr: 1.2658e-04 eta: 0:01:46 time: 0.1894 data_time: 0.0066 memory: 2656 loss: 0.0133 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0133 2022/12/30 14:24:01 - mmengine - INFO - Epoch(train) [16][1100/1567] lr: 8.5947e-05 eta: 0:01:27 time: 0.1813 data_time: 0.0068 memory: 2656 loss: 0.0150 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0150 2022/12/30 14:24:19 - mmengine - INFO - Epoch(train) [16][1200/1567] lr: 5.3147e-05 eta: 0:01:09 time: 0.1764 data_time: 0.0067 memory: 2656 loss: 0.0193 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0193 2022/12/30 14:24:37 - mmengine - INFO - Epoch(train) [16][1300/1567] lr: 2.8190e-05 eta: 0:00:50 time: 0.1755 data_time: 0.0066 memory: 2656 loss: 0.0080 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0080 2022/12/30 14:24:56 - mmengine - INFO - Epoch(train) [16][1400/1567] lr: 1.1078e-05 eta: 0:00:31 time: 0.1817 data_time: 0.0066 memory: 2656 loss: 0.0098 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0098 2022/12/30 14:25:14 - mmengine - INFO - Exp name: stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221230_130356 2022/12/30 14:25:15 - mmengine - INFO - Epoch(train) [16][1500/1567] lr: 1.8150e-06 eta: 0:00:12 time: 0.1841 data_time: 0.0067 memory: 2656 loss: 0.0122 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0122 2022/12/30 14:25:27 - mmengine - INFO - Exp name: stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221230_130356 2022/12/30 14:25:27 - mmengine - INFO - Epoch(train) [16][1567/1567] lr: 3.9252e-10 eta: 0:00:00 time: 0.1661 data_time: 0.0066 memory: 2656 loss: 0.1819 top1_acc: 0.0000 top5_acc: 1.0000 loss_cls: 0.1819 2022/12/30 14:25:27 - mmengine - INFO - Saving checkpoint at 16 epochs 2022/12/30 14:25:32 - mmengine - INFO - Epoch(val) [16][100/129] eta: 0:00:01 time: 0.0474 data_time: 0.0128 memory: 378 2022/12/30 14:25:33 - mmengine - INFO - Epoch(val) [16][129/129] acc/top1: 0.8592 acc/top5: 0.9713 acc/mean1: 0.8591