2022/12/30 13:05:19 - 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: 405014706 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 13:05:19 - 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=['bm']), 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=['bm']), dict( type='UniformSampleFrames', clip_len=100, num_clips=1, test_mode=True), dict(type='PoseDecode'), dict(type='FormatGCNInput', num_person=2), dict(type='PackActionInputs') ] test_pipeline = [ dict(type='PreNormalize3D'), dict(type='GenSkeFeat', dataset='nturgb+d', feats=['bm']), dict( type='UniformSampleFrames', clip_len=100, num_clips=10, test_mode=True), dict(type='PoseDecode'), dict(type='FormatGCNInput', num_person=2), dict(type='PackActionInputs') ] train_dataloader = dict( batch_size=16, num_workers=2, persistent_workers=True, sampler=dict(type='DefaultSampler', shuffle=True), dataset=dict( type='RepeatDataset', times=5, dataset=dict( type='PoseDataset', ann_file='data/skeleton/ntu60_3d.pkl', pipeline=[ dict(type='PreNormalize3D'), dict(type='GenSkeFeat', dataset='nturgb+d', feats=['bm']), dict(type='UniformSampleFrames', clip_len=100), dict(type='PoseDecode'), dict(type='FormatGCNInput', num_person=2), dict(type='PackActionInputs') ], split='xsub_train'))) val_dataloader = dict( batch_size=16, num_workers=2, persistent_workers=True, sampler=dict(type='DefaultSampler', shuffle=False), dataset=dict( type='PoseDataset', ann_file='data/skeleton/ntu60_3d.pkl', pipeline=[ dict(type='PreNormalize3D'), dict(type='GenSkeFeat', dataset='nturgb+d', feats=['bm']), dict( type='UniformSampleFrames', clip_len=100, num_clips=1, test_mode=True), dict(type='PoseDecode'), dict(type='FormatGCNInput', num_person=2), dict(type='PackActionInputs') ], split='xsub_val', test_mode=True)) test_dataloader = dict( batch_size=1, num_workers=2, persistent_workers=True, sampler=dict(type='DefaultSampler', shuffle=False), dataset=dict( type='PoseDataset', ann_file='data/skeleton/ntu60_3d.pkl', pipeline=[ dict(type='PreNormalize3D'), dict(type='GenSkeFeat', dataset='nturgb+d', feats=['bm']), dict( type='UniformSampleFrames', clip_len=100, num_clips=10, test_mode=True), dict(type='PoseDecode'), dict(type='FormatGCNInput', num_person=2), dict(type='PackActionInputs') ], split='xsub_val', test_mode=True)) val_evaluator = [dict(type='AccMetric')] test_evaluator = [dict(type='AccMetric')] train_cfg = dict( type='EpochBasedTrainLoop', max_epochs=16, val_begin=1, val_interval=1) val_cfg = dict(type='ValLoop') test_cfg = dict(type='TestLoop') param_scheduler = [ dict( type='CosineAnnealingLR', eta_min=0, T_max=16, by_epoch=True, convert_to_iter_based=True) ] optim_wrapper = dict( optimizer=dict( type='SGD', lr=0.1, momentum=0.9, weight_decay=0.0005, nesterov=True)) auto_scale_lr = dict(enable=False, base_batch_size=128) launcher = 'pytorch' work_dir = './work_dirs/stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d' randomness = dict(seed=None, diff_rank_seed=False, deterministic=False) 2022/12/30 13:05:19 - mmengine - INFO - Result has been saved to /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d/modules_statistic_results.json 2022/12/30 13:05:19 - 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 13:06:13 - mmengine - INFO - Checkpoints will be saved to /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d. 2022/12/30 13:06:36 - mmengine - INFO - Epoch(train) [1][ 100/1567] lr: 9.9996e-02 eta: 1:33:37 time: 0.1881 data_time: 0.0065 memory: 2656 loss: 3.1338 top1_acc: 0.1875 top5_acc: 0.6250 loss_cls: 3.1338 2022/12/30 13:06:54 - mmengine - INFO - Epoch(train) [1][ 200/1567] lr: 9.9984e-02 eta: 1:24:48 time: 0.1830 data_time: 0.0067 memory: 2656 loss: 2.1791 top1_acc: 0.5000 top5_acc: 0.8125 loss_cls: 2.1791 2022/12/30 13:07:13 - mmengine - INFO - Epoch(train) [1][ 300/1567] lr: 9.9965e-02 eta: 1:22:15 time: 0.1824 data_time: 0.0066 memory: 2656 loss: 1.6619 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 1.6619 2022/12/30 13:07:32 - mmengine - INFO - Epoch(train) [1][ 400/1567] lr: 9.9938e-02 eta: 1:20:43 time: 0.1885 data_time: 0.0066 memory: 2656 loss: 1.3684 top1_acc: 0.6250 top5_acc: 1.0000 loss_cls: 1.3684 2022/12/30 13:07:51 - mmengine - INFO - Epoch(train) [1][ 500/1567] lr: 9.9902e-02 eta: 1:19:32 time: 0.1868 data_time: 0.0066 memory: 2656 loss: 1.1500 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 1.1500 2022/12/30 13:08:09 - mmengine - INFO - Epoch(train) [1][ 600/1567] lr: 9.9859e-02 eta: 1:18:43 time: 0.1817 data_time: 0.0068 memory: 2656 loss: 1.0673 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 1.0673 2022/12/30 13:08:28 - mmengine - INFO - Epoch(train) [1][ 700/1567] lr: 9.9808e-02 eta: 1:18:06 time: 0.1970 data_time: 0.0064 memory: 2656 loss: 1.1007 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.1007 2022/12/30 13:08:46 - mmengine - INFO - Epoch(train) [1][ 800/1567] lr: 9.9750e-02 eta: 1:17:13 time: 0.1840 data_time: 0.0067 memory: 2656 loss: 0.9957 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.9957 2022/12/30 13:09:05 - mmengine - INFO - Epoch(train) [1][ 900/1567] lr: 9.9683e-02 eta: 1:16:44 time: 0.1874 data_time: 0.0070 memory: 2656 loss: 0.8826 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.8826 2022/12/30 13:09:23 - mmengine - INFO - Exp name: stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221230_130509 2022/12/30 13:09:23 - mmengine - INFO - Epoch(train) [1][1000/1567] lr: 9.9609e-02 eta: 1:16:11 time: 0.1887 data_time: 0.0066 memory: 2656 loss: 1.0352 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 1.0352 2022/12/30 13:09:42 - mmengine - INFO - Epoch(train) [1][1100/1567] lr: 9.9527e-02 eta: 1:15:40 time: 0.1787 data_time: 0.0066 memory: 2656 loss: 0.8478 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.8478 2022/12/30 13:10:00 - mmengine - INFO - Epoch(train) [1][1200/1567] lr: 9.9437e-02 eta: 1:15:11 time: 0.1814 data_time: 0.0066 memory: 2656 loss: 0.7437 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.7437 2022/12/30 13:10:19 - mmengine - INFO - Epoch(train) [1][1300/1567] lr: 9.9339e-02 eta: 1:14:50 time: 0.1802 data_time: 0.0073 memory: 2656 loss: 0.7094 top1_acc: 0.6250 top5_acc: 1.0000 loss_cls: 0.7094 2022/12/30 13:10:37 - mmengine - INFO - Epoch(train) [1][1400/1567] lr: 9.9234e-02 eta: 1:14:18 time: 0.1797 data_time: 0.0066 memory: 2656 loss: 0.7343 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 0.7343 2022/12/30 13:10:56 - mmengine - INFO - Epoch(train) [1][1500/1567] lr: 9.9121e-02 eta: 1:13:56 time: 0.1886 data_time: 0.0067 memory: 2656 loss: 0.6395 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.6395 2022/12/30 13:11:08 - mmengine - INFO - Exp name: stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221230_130509 2022/12/30 13:11:08 - mmengine - INFO - Epoch(train) [1][1567/1567] lr: 9.9040e-02 eta: 1:13:33 time: 0.1742 data_time: 0.0064 memory: 2656 loss: 0.8983 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.8983 2022/12/30 13:11:08 - mmengine - INFO - Saving checkpoint at 1 epochs 2022/12/30 13:11:13 - mmengine - INFO - Epoch(val) [1][100/129] eta: 0:00:01 time: 0.0420 data_time: 0.0065 memory: 378 2022/12/30 13:11:15 - mmengine - INFO - Epoch(val) [1][129/129] acc/top1: 0.6063 acc/top5: 0.8950 acc/mean1: 0.6063 2022/12/30 13:11:15 - mmengine - INFO - The best checkpoint with 0.6063 acc/top1 at 1 epoch is saved to best_acc/top1_epoch_1.pth. 2022/12/30 13:11:34 - mmengine - INFO - Epoch(train) [2][ 100/1567] lr: 9.8914e-02 eta: 1:13:15 time: 0.1830 data_time: 0.0066 memory: 2656 loss: 0.7567 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.7567 2022/12/30 13:11:52 - mmengine - INFO - Epoch(train) [2][ 200/1567] lr: 9.8781e-02 eta: 1:12:45 time: 0.1765 data_time: 0.0066 memory: 2656 loss: 0.6220 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.6220 2022/12/30 13:12:10 - mmengine - INFO - Epoch(train) [2][ 300/1567] lr: 9.8639e-02 eta: 1:12:17 time: 0.1871 data_time: 0.0066 memory: 2656 loss: 0.6181 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.6181 2022/12/30 13:12:28 - mmengine - INFO - Epoch(train) [2][ 400/1567] lr: 9.8491e-02 eta: 1:11:48 time: 0.1786 data_time: 0.0075 memory: 2656 loss: 0.7500 top1_acc: 0.5000 top5_acc: 1.0000 loss_cls: 0.7500 2022/12/30 13:12:33 - mmengine - INFO - Exp name: stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221230_130509 2022/12/30 13:12:45 - mmengine - INFO - Epoch(train) [2][ 500/1567] lr: 9.8334e-02 eta: 1:11:21 time: 0.1859 data_time: 0.0067 memory: 2656 loss: 0.6150 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.6150 2022/12/30 13:13:04 - mmengine - INFO - Epoch(train) [2][ 600/1567] lr: 9.8170e-02 eta: 1:11:02 time: 0.1869 data_time: 0.0079 memory: 2656 loss: 0.7105 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.7105 2022/12/30 13:13:23 - mmengine - INFO - Epoch(train) [2][ 700/1567] lr: 9.7998e-02 eta: 1:10:44 time: 0.1846 data_time: 0.0076 memory: 2656 loss: 0.6969 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.6969 2022/12/30 13:13:42 - mmengine - INFO - Epoch(train) [2][ 800/1567] lr: 9.7819e-02 eta: 1:10:30 time: 0.1901 data_time: 0.0069 memory: 2656 loss: 0.6088 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.6088 2022/12/30 13:14:00 - mmengine - INFO - Epoch(train) [2][ 900/1567] lr: 9.7632e-02 eta: 1:10:10 time: 0.1874 data_time: 0.0066 memory: 2656 loss: 0.6240 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.6240 2022/12/30 13:14:19 - mmengine - INFO - Epoch(train) [2][1000/1567] lr: 9.7438e-02 eta: 1:09:50 time: 0.1851 data_time: 0.0065 memory: 2656 loss: 0.6063 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.6063 2022/12/30 13:14:37 - mmengine - INFO - Epoch(train) [2][1100/1567] lr: 9.7236e-02 eta: 1:09:31 time: 0.1763 data_time: 0.0066 memory: 2656 loss: 0.5605 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 0.5605 2022/12/30 13:14:56 - mmengine - INFO - Epoch(train) [2][1200/1567] lr: 9.7027e-02 eta: 1:09:13 time: 0.1858 data_time: 0.0067 memory: 2656 loss: 0.5212 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.5212 2022/12/30 13:15:15 - mmengine - INFO - Epoch(train) [2][1300/1567] lr: 9.6810e-02 eta: 1:08:55 time: 0.1870 data_time: 0.0067 memory: 2656 loss: 0.5573 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.5573 2022/12/30 13:15:33 - mmengine - INFO - Epoch(train) [2][1400/1567] lr: 9.6587e-02 eta: 1:08:34 time: 0.1772 data_time: 0.0068 memory: 2656 loss: 0.5962 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.5962 2022/12/30 13:15:39 - mmengine - INFO - Exp name: stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221230_130509 2022/12/30 13:15:52 - mmengine - INFO - Epoch(train) [2][1500/1567] lr: 9.6355e-02 eta: 1:08:16 time: 0.1862 data_time: 0.0067 memory: 2656 loss: 0.5772 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.5772 2022/12/30 13:16:04 - mmengine - INFO - Exp name: stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221230_130509 2022/12/30 13:16:04 - mmengine - INFO - Epoch(train) [2][1567/1567] lr: 9.6196e-02 eta: 1:08:03 time: 0.1787 data_time: 0.0065 memory: 2656 loss: 0.5485 top1_acc: 0.0000 top5_acc: 1.0000 loss_cls: 0.5485 2022/12/30 13:16:04 - mmengine - INFO - Saving checkpoint at 2 epochs 2022/12/30 13:16:09 - mmengine - INFO - Epoch(val) [2][100/129] eta: 0:00:01 time: 0.0414 data_time: 0.0106 memory: 378 2022/12/30 13:16:11 - mmengine - INFO - Epoch(val) [2][129/129] acc/top1: 0.4871 acc/top5: 0.7988 acc/mean1: 0.4870 2022/12/30 13:16:29 - mmengine - INFO - Epoch(train) [3][ 100/1567] lr: 9.5953e-02 eta: 1:07:43 time: 0.1887 data_time: 0.0067 memory: 2656 loss: 0.5490 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.5490 2022/12/30 13:16:47 - mmengine - INFO - Epoch(train) [3][ 200/1567] lr: 9.5703e-02 eta: 1:07:22 time: 0.1783 data_time: 0.0068 memory: 2656 loss: 0.5219 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.5219 2022/12/30 13:17:06 - mmengine - INFO - Epoch(train) [3][ 300/1567] lr: 9.5445e-02 eta: 1:07:05 time: 0.1979 data_time: 0.0066 memory: 2656 loss: 0.5251 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.5251 2022/12/30 13:17:25 - mmengine - INFO - Epoch(train) [3][ 400/1567] lr: 9.5180e-02 eta: 1:06:45 time: 0.1819 data_time: 0.0066 memory: 2656 loss: 0.6313 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.6313 2022/12/30 13:17:43 - mmengine - INFO - Epoch(train) [3][ 500/1567] lr: 9.4908e-02 eta: 1:06:26 time: 0.1784 data_time: 0.0067 memory: 2656 loss: 0.5894 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.5894 2022/12/30 13:18:02 - mmengine - INFO - Epoch(train) [3][ 600/1567] lr: 9.4629e-02 eta: 1:06:08 time: 0.1904 data_time: 0.0067 memory: 2656 loss: 0.6015 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.6015 2022/12/30 13:18:20 - mmengine - INFO - Epoch(train) [3][ 700/1567] lr: 9.4343e-02 eta: 1:05:49 time: 0.1864 data_time: 0.0066 memory: 2656 loss: 0.5436 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.5436 2022/12/30 13:18:39 - mmengine - INFO - Epoch(train) [3][ 800/1567] lr: 9.4050e-02 eta: 1:05:31 time: 0.1870 data_time: 0.0068 memory: 2656 loss: 0.5298 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.5298 2022/12/30 13:18:52 - mmengine - INFO - Exp name: stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221230_130509 2022/12/30 13:18:58 - mmengine - INFO - Epoch(train) [3][ 900/1567] lr: 9.3750e-02 eta: 1:05:15 time: 0.1932 data_time: 0.0068 memory: 2656 loss: 0.5643 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.5643 2022/12/30 13:19:17 - mmengine - INFO - Epoch(train) [3][1000/1567] lr: 9.3444e-02 eta: 1:04:57 time: 0.1927 data_time: 0.0066 memory: 2656 loss: 0.4920 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 0.4920 2022/12/30 13:19:36 - mmengine - INFO - Epoch(train) [3][1100/1567] lr: 9.3130e-02 eta: 1:04:41 time: 0.1897 data_time: 0.0066 memory: 2656 loss: 0.4921 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.4921 2022/12/30 13:19:54 - mmengine - INFO - Epoch(train) [3][1200/1567] lr: 9.2810e-02 eta: 1:04:19 time: 0.1751 data_time: 0.0066 memory: 2656 loss: 0.5488 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.5488 2022/12/30 13:20:13 - mmengine - INFO - Epoch(train) [3][1300/1567] lr: 9.2483e-02 eta: 1:04:01 time: 0.1905 data_time: 0.0065 memory: 2656 loss: 0.5193 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 0.5193 2022/12/30 13:20:32 - mmengine - INFO - Epoch(train) [3][1400/1567] lr: 9.2149e-02 eta: 1:03:44 time: 0.1897 data_time: 0.0067 memory: 2656 loss: 0.6024 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.6024 2022/12/30 13:20:50 - mmengine - INFO - Epoch(train) [3][1500/1567] lr: 9.1809e-02 eta: 1:03:25 time: 0.1835 data_time: 0.0067 memory: 2656 loss: 0.4682 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.4682 2022/12/30 13:21:02 - mmengine - INFO - Exp name: stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221230_130509 2022/12/30 13:21:02 - mmengine - INFO - Epoch(train) [3][1567/1567] lr: 9.1577e-02 eta: 1:03:11 time: 0.1708 data_time: 0.0067 memory: 2656 loss: 0.7169 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.7169 2022/12/30 13:21:02 - mmengine - INFO - Saving checkpoint at 3 epochs 2022/12/30 13:21:07 - mmengine - INFO - Epoch(val) [3][100/129] eta: 0:00:01 time: 0.0406 data_time: 0.0087 memory: 378 2022/12/30 13:21:09 - mmengine - INFO - Epoch(val) [3][129/129] acc/top1: 0.7473 acc/top5: 0.9477 acc/mean1: 0.7472 2022/12/30 13:21:09 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_1.pth is removed 2022/12/30 13:21:09 - mmengine - INFO - The best checkpoint with 0.7473 acc/top1 at 3 epoch is saved to best_acc/top1_epoch_3.pth. 2022/12/30 13:21:28 - mmengine - INFO - Epoch(train) [4][ 100/1567] lr: 9.1226e-02 eta: 1:02:52 time: 0.1852 data_time: 0.0066 memory: 2656 loss: 0.5197 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.5197 2022/12/30 13:21:46 - mmengine - INFO - Epoch(train) [4][ 200/1567] lr: 9.0868e-02 eta: 1:02:33 time: 0.1856 data_time: 0.0068 memory: 2656 loss: 0.5224 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.5224 2022/12/30 13:22:04 - mmengine - INFO - Exp name: stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221230_130509 2022/12/30 13:22:05 - mmengine - INFO - Epoch(train) [4][ 300/1567] lr: 9.0504e-02 eta: 1:02:14 time: 0.1724 data_time: 0.0067 memory: 2656 loss: 0.4115 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4115 2022/12/30 13:22:23 - mmengine - INFO - Epoch(train) [4][ 400/1567] lr: 9.0133e-02 eta: 1:01:54 time: 0.1744 data_time: 0.0066 memory: 2656 loss: 0.4964 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 0.4964 2022/12/30 13:22:42 - mmengine - INFO - Epoch(train) [4][ 500/1567] lr: 8.9756e-02 eta: 1:01:37 time: 0.1837 data_time: 0.0067 memory: 2656 loss: 0.4763 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4763 2022/12/30 13:23:00 - mmengine - INFO - Epoch(train) [4][ 600/1567] lr: 8.9373e-02 eta: 1:01:18 time: 0.1894 data_time: 0.0067 memory: 2656 loss: 0.5432 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.5432 2022/12/30 13:23:18 - mmengine - INFO - Epoch(train) [4][ 700/1567] lr: 8.8984e-02 eta: 1:00:58 time: 0.1794 data_time: 0.0066 memory: 2656 loss: 0.4435 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.4435 2022/12/30 13:23:37 - mmengine - INFO - Epoch(train) [4][ 800/1567] lr: 8.8589e-02 eta: 1:00:38 time: 0.1800 data_time: 0.0066 memory: 2656 loss: 0.5571 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.5571 2022/12/30 13:23:55 - mmengine - INFO - Epoch(train) [4][ 900/1567] lr: 8.8187e-02 eta: 1:00:18 time: 0.1805 data_time: 0.0069 memory: 2656 loss: 0.4376 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4376 2022/12/30 13:24:14 - mmengine - INFO - Epoch(train) [4][1000/1567] lr: 8.7780e-02 eta: 1:00:00 time: 0.1819 data_time: 0.0074 memory: 2656 loss: 0.5669 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.5669 2022/12/30 13:24:33 - mmengine - INFO - Epoch(train) [4][1100/1567] lr: 8.7367e-02 eta: 0:59:42 time: 0.1863 data_time: 0.0067 memory: 2656 loss: 0.5074 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.5074 2022/12/30 13:24:50 - mmengine - INFO - Epoch(train) [4][1200/1567] lr: 8.6947e-02 eta: 0:59:21 time: 0.1805 data_time: 0.0066 memory: 2656 loss: 0.3974 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3974 2022/12/30 13:25:08 - mmengine - INFO - Exp name: stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221230_130509 2022/12/30 13:25:09 - mmengine - INFO - Epoch(train) [4][1300/1567] lr: 8.6522e-02 eta: 0:59:02 time: 0.1885 data_time: 0.0067 memory: 2656 loss: 0.4600 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.4600 2022/12/30 13:25:28 - mmengine - INFO - Epoch(train) [4][1400/1567] lr: 8.6092e-02 eta: 0:58:45 time: 0.1929 data_time: 0.0069 memory: 2656 loss: 0.5586 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.5586 2022/12/30 13:25:47 - mmengine - INFO - Epoch(train) [4][1500/1567] lr: 8.5655e-02 eta: 0:58:27 time: 0.1894 data_time: 0.0068 memory: 2656 loss: 0.3859 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.3859 2022/12/30 13:25:59 - mmengine - INFO - Exp name: stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221230_130509 2022/12/30 13:25:59 - mmengine - INFO - Epoch(train) [4][1567/1567] lr: 8.5360e-02 eta: 0:58:16 time: 0.1781 data_time: 0.0070 memory: 2656 loss: 0.6059 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.6059 2022/12/30 13:25:59 - mmengine - INFO - Saving checkpoint at 4 epochs 2022/12/30 13:26:04 - mmengine - INFO - Epoch(val) [4][100/129] eta: 0:00:01 time: 0.0377 data_time: 0.0113 memory: 378 2022/12/30 13:26:06 - mmengine - INFO - Epoch(val) [4][129/129] acc/top1: 0.7163 acc/top5: 0.9416 acc/mean1: 0.7162 2022/12/30 13:26:25 - mmengine - INFO - Epoch(train) [5][ 100/1567] lr: 8.4914e-02 eta: 0:57:57 time: 0.1848 data_time: 0.0066 memory: 2656 loss: 0.3662 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3662 2022/12/30 13:26:44 - mmengine - INFO - Epoch(train) [5][ 200/1567] lr: 8.4463e-02 eta: 0:57:39 time: 0.1908 data_time: 0.0066 memory: 2656 loss: 0.4896 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 0.4896 2022/12/30 13:27:02 - mmengine - INFO - Epoch(train) [5][ 300/1567] lr: 8.4006e-02 eta: 0:57:19 time: 0.1789 data_time: 0.0068 memory: 2656 loss: 0.4946 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.4946 2022/12/30 13:27:21 - mmengine - INFO - Epoch(train) [5][ 400/1567] lr: 8.3544e-02 eta: 0:57:02 time: 0.1908 data_time: 0.0068 memory: 2656 loss: 0.4467 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4467 2022/12/30 13:27:39 - mmengine - INFO - Epoch(train) [5][ 500/1567] lr: 8.3077e-02 eta: 0:56:42 time: 0.1829 data_time: 0.0067 memory: 2656 loss: 0.4979 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.4979 2022/12/30 13:27:57 - mmengine - INFO - Epoch(train) [5][ 600/1567] lr: 8.2605e-02 eta: 0:56:23 time: 0.1889 data_time: 0.0066 memory: 2656 loss: 0.4645 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.4645 2022/12/30 13:28:16 - mmengine - INFO - Epoch(train) [5][ 700/1567] lr: 8.2127e-02 eta: 0:56:05 time: 0.1858 data_time: 0.0067 memory: 2656 loss: 0.5082 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.5082 2022/12/30 13:28:22 - mmengine - INFO - Exp name: stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221230_130509 2022/12/30 13:28:35 - mmengine - INFO - Epoch(train) [5][ 800/1567] lr: 8.1645e-02 eta: 0:55:47 time: 0.1965 data_time: 0.0068 memory: 2656 loss: 0.4328 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.4328 2022/12/30 13:28:55 - mmengine - INFO - Epoch(train) [5][ 900/1567] lr: 8.1157e-02 eta: 0:55:31 time: 0.1904 data_time: 0.0070 memory: 2656 loss: 0.4685 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4685 2022/12/30 13:29:13 - mmengine - INFO - Epoch(train) [5][1000/1567] lr: 8.0665e-02 eta: 0:55:10 time: 0.1758 data_time: 0.0068 memory: 2656 loss: 0.4529 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.4529 2022/12/30 13:29:31 - mmengine - INFO - Epoch(train) [5][1100/1567] lr: 8.0167e-02 eta: 0:54:52 time: 0.1811 data_time: 0.0067 memory: 2656 loss: 0.5371 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.5371 2022/12/30 13:29:49 - mmengine - INFO - Epoch(train) [5][1200/1567] lr: 7.9665e-02 eta: 0:54:32 time: 0.1857 data_time: 0.0067 memory: 2656 loss: 0.3905 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3905 2022/12/30 13:30:07 - mmengine - INFO - Epoch(train) [5][1300/1567] lr: 7.9159e-02 eta: 0:54:13 time: 0.1858 data_time: 0.0067 memory: 2656 loss: 0.4392 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4392 2022/12/30 13:30:26 - mmengine - INFO - Epoch(train) [5][1400/1567] lr: 7.8647e-02 eta: 0:53:54 time: 0.1939 data_time: 0.0067 memory: 2656 loss: 0.4748 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4748 2022/12/30 13:30:44 - mmengine - INFO - Epoch(train) [5][1500/1567] lr: 7.8132e-02 eta: 0:53:35 time: 0.1776 data_time: 0.0066 memory: 2656 loss: 0.4256 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4256 2022/12/30 13:30:56 - mmengine - INFO - Exp name: stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221230_130509 2022/12/30 13:30:56 - mmengine - INFO - Epoch(train) [5][1567/1567] lr: 7.7784e-02 eta: 0:53:22 time: 0.1703 data_time: 0.0065 memory: 2656 loss: 0.5476 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.5476 2022/12/30 13:30:56 - mmengine - INFO - Saving checkpoint at 5 epochs 2022/12/30 13:31:01 - mmengine - INFO - Epoch(val) [5][100/129] eta: 0:00:01 time: 0.0418 data_time: 0.0064 memory: 378 2022/12/30 13:31:03 - mmengine - INFO - Epoch(val) [5][129/129] acc/top1: 0.7080 acc/top5: 0.9353 acc/mean1: 0.7079 2022/12/30 13:31:22 - mmengine - INFO - Epoch(train) [6][ 100/1567] lr: 7.7261e-02 eta: 0:53:03 time: 0.1867 data_time: 0.0066 memory: 2656 loss: 0.4984 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.4984 2022/12/30 13:31:34 - mmengine - INFO - Exp name: stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221230_130509 2022/12/30 13:31:40 - mmengine - INFO - Epoch(train) [6][ 200/1567] lr: 7.6733e-02 eta: 0:52:44 time: 0.1876 data_time: 0.0069 memory: 2656 loss: 0.4499 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.4499 2022/12/30 13:31:58 - mmengine - INFO - Epoch(train) [6][ 300/1567] lr: 7.6202e-02 eta: 0:52:24 time: 0.1696 data_time: 0.0067 memory: 2656 loss: 0.4619 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.4619 2022/12/30 13:32:16 - mmengine - INFO - Epoch(train) [6][ 400/1567] lr: 7.5666e-02 eta: 0:52:05 time: 0.1837 data_time: 0.0068 memory: 2656 loss: 0.4743 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4743 2022/12/30 13:32:35 - mmengine - INFO - Epoch(train) [6][ 500/1567] lr: 7.5126e-02 eta: 0:51:46 time: 0.1865 data_time: 0.0068 memory: 2656 loss: 0.3893 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3893 2022/12/30 13:32:53 - mmengine - INFO - Epoch(train) [6][ 600/1567] lr: 7.4583e-02 eta: 0:51:27 time: 0.1772 data_time: 0.0066 memory: 2656 loss: 0.4028 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.4028 2022/12/30 13:33:11 - mmengine - INFO - Epoch(train) [6][ 700/1567] lr: 7.4035e-02 eta: 0:51:08 time: 0.1877 data_time: 0.0067 memory: 2656 loss: 0.3598 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3598 2022/12/30 13:33:30 - mmengine - INFO - Epoch(train) [6][ 800/1567] lr: 7.3484e-02 eta: 0:50:49 time: 0.1974 data_time: 0.0066 memory: 2656 loss: 0.3181 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.3181 2022/12/30 13:33:48 - mmengine - INFO - Epoch(train) [6][ 900/1567] lr: 7.2929e-02 eta: 0:50:31 time: 0.1784 data_time: 0.0068 memory: 2656 loss: 0.4415 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.4415 2022/12/30 13:34:07 - mmengine - INFO - Epoch(train) [6][1000/1567] lr: 7.2371e-02 eta: 0:50:12 time: 0.1850 data_time: 0.0070 memory: 2656 loss: 0.3506 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.3506 2022/12/30 13:34:25 - mmengine - INFO - Epoch(train) [6][1100/1567] lr: 7.1809e-02 eta: 0:49:53 time: 0.1867 data_time: 0.0068 memory: 2656 loss: 0.3632 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.3632 2022/12/30 13:34:37 - mmengine - INFO - Exp name: stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221230_130509 2022/12/30 13:34:44 - mmengine - INFO - Epoch(train) [6][1200/1567] lr: 7.1243e-02 eta: 0:49:35 time: 0.1844 data_time: 0.0068 memory: 2656 loss: 0.3713 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3713 2022/12/30 13:35:03 - mmengine - INFO - Epoch(train) [6][1300/1567] lr: 7.0674e-02 eta: 0:49:17 time: 0.1935 data_time: 0.0069 memory: 2656 loss: 0.4299 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.4299 2022/12/30 13:35:21 - mmengine - INFO - Epoch(train) [6][1400/1567] lr: 7.0102e-02 eta: 0:48:57 time: 0.1799 data_time: 0.0068 memory: 2656 loss: 0.4659 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.4659 2022/12/30 13:35:39 - mmengine - INFO - Epoch(train) [6][1500/1567] lr: 6.9527e-02 eta: 0:48:38 time: 0.1943 data_time: 0.0067 memory: 2656 loss: 0.3688 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3688 2022/12/30 13:35:51 - mmengine - INFO - Exp name: stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221230_130509 2022/12/30 13:35:51 - mmengine - INFO - Epoch(train) [6][1567/1567] lr: 6.9140e-02 eta: 0:48:25 time: 0.1685 data_time: 0.0064 memory: 2656 loss: 0.4891 top1_acc: 0.0000 top5_acc: 1.0000 loss_cls: 0.4891 2022/12/30 13:35:51 - mmengine - INFO - Saving checkpoint at 6 epochs 2022/12/30 13:35:56 - mmengine - INFO - Epoch(val) [6][100/129] eta: 0:00:01 time: 0.0414 data_time: 0.0063 memory: 378 2022/12/30 13:35:58 - mmengine - INFO - Epoch(val) [6][129/129] acc/top1: 0.7625 acc/top5: 0.9588 acc/mean1: 0.7624 2022/12/30 13:35:58 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_3.pth is removed 2022/12/30 13:35:59 - mmengine - INFO - The best checkpoint with 0.7625 acc/top1 at 6 epoch is saved to best_acc/top1_epoch_6.pth. 2022/12/30 13:36:18 - mmengine - INFO - Epoch(train) [7][ 100/1567] lr: 6.8560e-02 eta: 0:48:07 time: 0.1854 data_time: 0.0069 memory: 2656 loss: 0.3343 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3343 2022/12/30 13:36:36 - mmengine - INFO - Epoch(train) [7][ 200/1567] lr: 6.7976e-02 eta: 0:47:49 time: 0.1942 data_time: 0.0083 memory: 2656 loss: 0.3492 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3492 2022/12/30 13:36:55 - mmengine - INFO - Epoch(train) [7][ 300/1567] lr: 6.7390e-02 eta: 0:47:30 time: 0.1835 data_time: 0.0069 memory: 2656 loss: 0.3102 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3102 2022/12/30 13:37:13 - mmengine - INFO - Epoch(train) [7][ 400/1567] lr: 6.6802e-02 eta: 0:47:11 time: 0.1808 data_time: 0.0072 memory: 2656 loss: 0.3540 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3540 2022/12/30 13:37:32 - mmengine - INFO - Epoch(train) [7][ 500/1567] lr: 6.6210e-02 eta: 0:46:53 time: 0.1789 data_time: 0.0067 memory: 2656 loss: 0.3165 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3165 2022/12/30 13:37:50 - mmengine - INFO - Exp name: stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221230_130509 2022/12/30 13:37:50 - mmengine - INFO - Epoch(train) [7][ 600/1567] lr: 6.5616e-02 eta: 0:46:34 time: 0.1901 data_time: 0.0067 memory: 2656 loss: 0.4235 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 0.4235 2022/12/30 13:38:08 - mmengine - INFO - Epoch(train) [7][ 700/1567] lr: 6.5020e-02 eta: 0:46:15 time: 0.1774 data_time: 0.0066 memory: 2656 loss: 0.2945 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.2945 2022/12/30 13:38:27 - mmengine - INFO - Epoch(train) [7][ 800/1567] lr: 6.4421e-02 eta: 0:45:57 time: 0.1844 data_time: 0.0066 memory: 2656 loss: 0.3346 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3346 2022/12/30 13:38:45 - mmengine - INFO - Epoch(train) [7][ 900/1567] lr: 6.3820e-02 eta: 0:45:38 time: 0.1773 data_time: 0.0072 memory: 2656 loss: 0.3717 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3717 2022/12/30 13:39:03 - mmengine - INFO - Epoch(train) [7][1000/1567] lr: 6.3217e-02 eta: 0:45:18 time: 0.1984 data_time: 0.0067 memory: 2656 loss: 0.3537 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3537 2022/12/30 13:39:22 - mmengine - INFO - Epoch(train) [7][1100/1567] lr: 6.2612e-02 eta: 0:45:00 time: 0.1778 data_time: 0.0067 memory: 2656 loss: 0.3839 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 0.3839 2022/12/30 13:39:40 - mmengine - INFO - Epoch(train) [7][1200/1567] lr: 6.2005e-02 eta: 0:44:40 time: 0.1785 data_time: 0.0070 memory: 2656 loss: 0.3878 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.3878 2022/12/30 13:39:58 - mmengine - INFO - Epoch(train) [7][1300/1567] lr: 6.1396e-02 eta: 0:44:21 time: 0.1724 data_time: 0.0066 memory: 2656 loss: 0.3607 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3607 2022/12/30 13:40:16 - mmengine - INFO - Epoch(train) [7][1400/1567] lr: 6.0785e-02 eta: 0:44:02 time: 0.1800 data_time: 0.0067 memory: 2656 loss: 0.3776 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.3776 2022/12/30 13:40:35 - mmengine - INFO - Epoch(train) [7][1500/1567] lr: 6.0172e-02 eta: 0:43:44 time: 0.1769 data_time: 0.0071 memory: 2656 loss: 0.3332 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 0.3332 2022/12/30 13:40:46 - mmengine - INFO - Exp name: stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221230_130509 2022/12/30 13:40:46 - mmengine - INFO - Epoch(train) [7][1567/1567] lr: 5.9761e-02 eta: 0:43:30 time: 0.1519 data_time: 0.0065 memory: 2656 loss: 0.4920 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.4920 2022/12/30 13:40:46 - mmengine - INFO - Saving checkpoint at 7 epochs 2022/12/30 13:40:50 - mmengine - INFO - Epoch(val) [7][100/129] eta: 0:00:01 time: 0.0412 data_time: 0.0062 memory: 378 2022/12/30 13:40:53 - mmengine - INFO - Epoch(val) [7][129/129] acc/top1: 0.7294 acc/top5: 0.9421 acc/mean1: 0.7293 2022/12/30 13:40:59 - mmengine - INFO - Exp name: stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221230_130509 2022/12/30 13:41:12 - mmengine - INFO - Epoch(train) [8][ 100/1567] lr: 5.9145e-02 eta: 0:43:11 time: 0.1803 data_time: 0.0066 memory: 2656 loss: 0.3587 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3587 2022/12/30 13:41:30 - mmengine - INFO - Epoch(train) [8][ 200/1567] lr: 5.8529e-02 eta: 0:42:53 time: 0.1920 data_time: 0.0067 memory: 2656 loss: 0.2727 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.2727 2022/12/30 13:41:48 - mmengine - INFO - Epoch(train) [8][ 300/1567] lr: 5.7911e-02 eta: 0:42:34 time: 0.1901 data_time: 0.0069 memory: 2656 loss: 0.3201 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3201 2022/12/30 13:42:06 - mmengine - INFO - Epoch(train) [8][ 400/1567] lr: 5.7292e-02 eta: 0:42:15 time: 0.1782 data_time: 0.0066 memory: 2656 loss: 0.2665 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2665 2022/12/30 13:42:25 - mmengine - INFO - Epoch(train) [8][ 500/1567] lr: 5.6671e-02 eta: 0:41:56 time: 0.1764 data_time: 0.0069 memory: 2656 loss: 0.3030 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3030 2022/12/30 13:42:43 - mmengine - INFO - Epoch(train) [8][ 600/1567] lr: 5.6050e-02 eta: 0:41:37 time: 0.1848 data_time: 0.0067 memory: 2656 loss: 0.3867 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.3867 2022/12/30 13:43:01 - mmengine - INFO - Epoch(train) [8][ 700/1567] lr: 5.5427e-02 eta: 0:41:18 time: 0.1859 data_time: 0.0067 memory: 2656 loss: 0.3202 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3202 2022/12/30 13:43:20 - mmengine - INFO - Epoch(train) [8][ 800/1567] lr: 5.4804e-02 eta: 0:41:00 time: 0.1833 data_time: 0.0067 memory: 2656 loss: 0.2940 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 0.2940 2022/12/30 13:43:38 - mmengine - INFO - Epoch(train) [8][ 900/1567] lr: 5.4180e-02 eta: 0:40:41 time: 0.1711 data_time: 0.0069 memory: 2656 loss: 0.3032 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3032 2022/12/30 13:43:57 - mmengine - INFO - Epoch(train) [8][1000/1567] lr: 5.3556e-02 eta: 0:40:23 time: 0.1876 data_time: 0.0067 memory: 2656 loss: 0.3366 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.3366 2022/12/30 13:44:02 - mmengine - INFO - Exp name: stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221230_130509 2022/12/30 13:44:15 - mmengine - INFO - Epoch(train) [8][1100/1567] lr: 5.2930e-02 eta: 0:40:05 time: 0.1918 data_time: 0.0073 memory: 2656 loss: 0.3038 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3038 2022/12/30 13:44:34 - mmengine - INFO - Epoch(train) [8][1200/1567] lr: 5.2305e-02 eta: 0:39:46 time: 0.1788 data_time: 0.0067 memory: 2656 loss: 0.2606 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.2606 2022/12/30 13:44:52 - mmengine - INFO - Epoch(train) [8][1300/1567] lr: 5.1679e-02 eta: 0:39:27 time: 0.1852 data_time: 0.0067 memory: 2656 loss: 0.3003 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3003 2022/12/30 13:45:11 - mmengine - INFO - Epoch(train) [8][1400/1567] lr: 5.1052e-02 eta: 0:39:09 time: 0.1807 data_time: 0.0077 memory: 2656 loss: 0.2522 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2522 2022/12/30 13:45:28 - mmengine - INFO - Epoch(train) [8][1500/1567] lr: 5.0426e-02 eta: 0:38:50 time: 0.1826 data_time: 0.0067 memory: 2656 loss: 0.3236 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3236 2022/12/30 13:45:40 - mmengine - INFO - Exp name: stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221230_130509 2022/12/30 13:45:40 - mmengine - INFO - Epoch(train) [8][1567/1567] lr: 5.0006e-02 eta: 0:38:36 time: 0.1496 data_time: 0.0068 memory: 2656 loss: 0.5306 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.5306 2022/12/30 13:45:40 - mmengine - INFO - Saving checkpoint at 8 epochs 2022/12/30 13:45:44 - mmengine - INFO - Epoch(val) [8][100/129] eta: 0:00:01 time: 0.0408 data_time: 0.0066 memory: 378 2022/12/30 13:45:47 - mmengine - INFO - Epoch(val) [8][129/129] acc/top1: 0.8017 acc/top5: 0.9603 acc/mean1: 0.8016 2022/12/30 13:45:47 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_6.pth is removed 2022/12/30 13:45:48 - mmengine - INFO - The best checkpoint with 0.8017 acc/top1 at 8 epoch is saved to best_acc/top1_epoch_8.pth. 2022/12/30 13:46:06 - mmengine - INFO - Epoch(train) [9][ 100/1567] lr: 4.9380e-02 eta: 0:38:18 time: 0.1771 data_time: 0.0067 memory: 2656 loss: 0.2351 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.2351 2022/12/30 13:46:25 - mmengine - INFO - Epoch(train) [9][ 200/1567] lr: 4.8753e-02 eta: 0:38:00 time: 0.1936 data_time: 0.0067 memory: 2656 loss: 0.3590 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 0.3590 2022/12/30 13:46:43 - mmengine - INFO - Epoch(train) [9][ 300/1567] lr: 4.8127e-02 eta: 0:37:41 time: 0.1783 data_time: 0.0069 memory: 2656 loss: 0.3073 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3073 2022/12/30 13:47:01 - mmengine - INFO - Epoch(train) [9][ 400/1567] lr: 4.7501e-02 eta: 0:37:21 time: 0.1863 data_time: 0.0071 memory: 2656 loss: 0.2482 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2482 2022/12/30 13:47:13 - mmengine - INFO - Exp name: stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221230_130509 2022/12/30 13:47:20 - mmengine - INFO - Epoch(train) [9][ 500/1567] lr: 4.6876e-02 eta: 0:37:03 time: 0.1887 data_time: 0.0067 memory: 2656 loss: 0.3097 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.3097 2022/12/30 13:47:38 - mmengine - INFO - Epoch(train) [9][ 600/1567] lr: 4.6251e-02 eta: 0:36:45 time: 0.1837 data_time: 0.0067 memory: 2656 loss: 0.2935 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2935 2022/12/30 13:47:57 - mmengine - INFO - Epoch(train) [9][ 700/1567] lr: 4.5626e-02 eta: 0:36:27 time: 0.1913 data_time: 0.0067 memory: 2656 loss: 0.3267 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.3267 2022/12/30 13:48:15 - mmengine - INFO - Epoch(train) [9][ 800/1567] lr: 4.5003e-02 eta: 0:36:08 time: 0.1908 data_time: 0.0071 memory: 2656 loss: 0.3057 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3057 2022/12/30 13:48:33 - mmengine - INFO - Epoch(train) [9][ 900/1567] lr: 4.4380e-02 eta: 0:35:49 time: 0.1825 data_time: 0.0068 memory: 2656 loss: 0.3017 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3017 2022/12/30 13:48:52 - mmengine - INFO - Epoch(train) [9][1000/1567] lr: 4.3757e-02 eta: 0:35:31 time: 0.1926 data_time: 0.0066 memory: 2656 loss: 0.2180 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2180 2022/12/30 13:49:10 - mmengine - INFO - Epoch(train) [9][1100/1567] lr: 4.3136e-02 eta: 0:35:12 time: 0.1842 data_time: 0.0068 memory: 2656 loss: 0.1964 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1964 2022/12/30 13:49:29 - mmengine - INFO - Epoch(train) [9][1200/1567] lr: 4.2516e-02 eta: 0:34:54 time: 0.1828 data_time: 0.0067 memory: 2656 loss: 0.2912 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2912 2022/12/30 13:49:48 - mmengine - INFO - Epoch(train) [9][1300/1567] lr: 4.1897e-02 eta: 0:34:36 time: 0.1857 data_time: 0.0074 memory: 2656 loss: 0.2677 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2677 2022/12/30 13:50:06 - mmengine - INFO - Epoch(train) [9][1400/1567] lr: 4.1280e-02 eta: 0:34:17 time: 0.1864 data_time: 0.0068 memory: 2656 loss: 0.2494 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2494 2022/12/30 13:50:18 - mmengine - INFO - Exp name: stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221230_130509 2022/12/30 13:50:25 - mmengine - INFO - Epoch(train) [9][1500/1567] lr: 4.0664e-02 eta: 0:33:59 time: 0.1832 data_time: 0.0068 memory: 2656 loss: 0.2390 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2390 2022/12/30 13:50:36 - mmengine - INFO - Exp name: stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221230_130509 2022/12/30 13:50:36 - mmengine - INFO - Epoch(train) [9][1567/1567] lr: 4.0252e-02 eta: 0:33:46 time: 0.1430 data_time: 0.0067 memory: 2656 loss: 0.4189 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.4189 2022/12/30 13:50:36 - mmengine - INFO - Saving checkpoint at 9 epochs 2022/12/30 13:50:41 - mmengine - INFO - Epoch(val) [9][100/129] eta: 0:00:01 time: 0.0383 data_time: 0.0084 memory: 378 2022/12/30 13:50:43 - mmengine - INFO - Epoch(val) [9][129/129] acc/top1: 0.7952 acc/top5: 0.9582 acc/mean1: 0.7952 2022/12/30 13:51:02 - mmengine - INFO - Epoch(train) [10][ 100/1567] lr: 3.9638e-02 eta: 0:33:28 time: 0.1814 data_time: 0.0074 memory: 2656 loss: 0.2710 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2710 2022/12/30 13:51:21 - mmengine - INFO - Epoch(train) [10][ 200/1567] lr: 3.9026e-02 eta: 0:33:09 time: 0.1856 data_time: 0.0079 memory: 2656 loss: 0.2960 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.2960 2022/12/30 13:51:39 - mmengine - INFO - Epoch(train) [10][ 300/1567] lr: 3.8415e-02 eta: 0:32:51 time: 0.1940 data_time: 0.0073 memory: 2656 loss: 0.1977 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1977 2022/12/30 13:51:57 - mmengine - INFO - Epoch(train) [10][ 400/1567] lr: 3.7807e-02 eta: 0:32:32 time: 0.1810 data_time: 0.0067 memory: 2656 loss: 0.2701 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2701 2022/12/30 13:52:16 - mmengine - INFO - Epoch(train) [10][ 500/1567] lr: 3.7200e-02 eta: 0:32:13 time: 0.1880 data_time: 0.0067 memory: 2656 loss: 0.2154 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2154 2022/12/30 13:52:34 - mmengine - INFO - Epoch(train) [10][ 600/1567] lr: 3.6596e-02 eta: 0:31:55 time: 0.1903 data_time: 0.0068 memory: 2656 loss: 0.2561 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2561 2022/12/30 13:52:52 - mmengine - INFO - Epoch(train) [10][ 700/1567] lr: 3.5993e-02 eta: 0:31:36 time: 0.1829 data_time: 0.0066 memory: 2656 loss: 0.2728 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2728 2022/12/30 13:53:11 - mmengine - INFO - Epoch(train) [10][ 800/1567] lr: 3.5393e-02 eta: 0:31:18 time: 0.1906 data_time: 0.0071 memory: 2656 loss: 0.2047 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2047 2022/12/30 13:53:28 - mmengine - INFO - Exp name: stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221230_130509 2022/12/30 13:53:29 - mmengine - INFO - Epoch(train) [10][ 900/1567] lr: 3.4795e-02 eta: 0:30:59 time: 0.1711 data_time: 0.0069 memory: 2656 loss: 0.2478 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2478 2022/12/30 13:53:46 - mmengine - INFO - Epoch(train) [10][1000/1567] lr: 3.4199e-02 eta: 0:30:40 time: 0.1772 data_time: 0.0068 memory: 2656 loss: 0.2500 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2500 2022/12/30 13:54:04 - mmengine - INFO - Epoch(train) [10][1100/1567] lr: 3.3606e-02 eta: 0:30:20 time: 0.1774 data_time: 0.0068 memory: 2656 loss: 0.1875 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.1875 2022/12/30 13:54:22 - mmengine - INFO - Epoch(train) [10][1200/1567] lr: 3.3015e-02 eta: 0:30:02 time: 0.1860 data_time: 0.0068 memory: 2656 loss: 0.2527 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2527 2022/12/30 13:54:41 - mmengine - INFO - Epoch(train) [10][1300/1567] lr: 3.2428e-02 eta: 0:29:44 time: 0.1847 data_time: 0.0071 memory: 2656 loss: 0.1820 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.1820 2022/12/30 13:55:00 - mmengine - INFO - Epoch(train) [10][1400/1567] lr: 3.1842e-02 eta: 0:29:26 time: 0.1894 data_time: 0.0067 memory: 2656 loss: 0.2257 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2257 2022/12/30 13:55:18 - mmengine - INFO - Epoch(train) [10][1500/1567] lr: 3.1260e-02 eta: 0:29:07 time: 0.1884 data_time: 0.0068 memory: 2656 loss: 0.2133 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2133 2022/12/30 13:55:30 - mmengine - INFO - Exp name: stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221230_130509 2022/12/30 13:55:30 - mmengine - INFO - Epoch(train) [10][1567/1567] lr: 3.0872e-02 eta: 0:28:54 time: 0.1457 data_time: 0.0065 memory: 2656 loss: 0.3910 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.3910 2022/12/30 13:55:30 - mmengine - INFO - Saving checkpoint at 10 epochs 2022/12/30 13:55:34 - mmengine - INFO - Epoch(val) [10][100/129] eta: 0:00:01 time: 0.0379 data_time: 0.0107 memory: 378 2022/12/30 13:55:37 - mmengine - INFO - Epoch(val) [10][129/129] acc/top1: 0.8115 acc/top5: 0.9595 acc/mean1: 0.8114 2022/12/30 13:55:37 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_8.pth is removed 2022/12/30 13:55:38 - mmengine - INFO - The best checkpoint with 0.8115 acc/top1 at 10 epoch is saved to best_acc/top1_epoch_10.pth. 2022/12/30 13:55:57 - mmengine - INFO - Epoch(train) [11][ 100/1567] lr: 3.0294e-02 eta: 0:28:36 time: 0.1929 data_time: 0.0079 memory: 2656 loss: 0.1461 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1461 2022/12/30 13:56:15 - mmengine - INFO - Epoch(train) [11][ 200/1567] lr: 2.9720e-02 eta: 0:28:18 time: 0.1850 data_time: 0.0076 memory: 2656 loss: 0.1595 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1595 2022/12/30 13:56:34 - mmengine - INFO - Epoch(train) [11][ 300/1567] lr: 2.9149e-02 eta: 0:27:59 time: 0.1812 data_time: 0.0074 memory: 2656 loss: 0.1059 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1059 2022/12/30 13:56:39 - mmengine - INFO - Exp name: stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221230_130509 2022/12/30 13:56:52 - mmengine - INFO - Epoch(train) [11][ 400/1567] lr: 2.8581e-02 eta: 0:27:41 time: 0.1797 data_time: 0.0079 memory: 2656 loss: 0.1506 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1506 2022/12/30 13:57:10 - mmengine - INFO - Epoch(train) [11][ 500/1567] lr: 2.8017e-02 eta: 0:27:22 time: 0.1846 data_time: 0.0083 memory: 2656 loss: 0.1410 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1410 2022/12/30 13:57:29 - mmengine - INFO - Epoch(train) [11][ 600/1567] lr: 2.7456e-02 eta: 0:27:04 time: 0.1859 data_time: 0.0072 memory: 2656 loss: 0.1359 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.1359 2022/12/30 13:57:47 - mmengine - INFO - Epoch(train) [11][ 700/1567] lr: 2.6898e-02 eta: 0:26:45 time: 0.1897 data_time: 0.0068 memory: 2656 loss: 0.1787 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.1787 2022/12/30 13:58:06 - mmengine - INFO - Epoch(train) [11][ 800/1567] lr: 2.6345e-02 eta: 0:26:27 time: 0.1825 data_time: 0.0076 memory: 2656 loss: 0.1684 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.1684 2022/12/30 13:58:25 - mmengine - INFO - Epoch(train) [11][ 900/1567] lr: 2.5794e-02 eta: 0:26:09 time: 0.1837 data_time: 0.0067 memory: 2656 loss: 0.1529 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.1529 2022/12/30 13:58:43 - mmengine - INFO - Epoch(train) [11][1000/1567] lr: 2.5248e-02 eta: 0:25:50 time: 0.1813 data_time: 0.0073 memory: 2656 loss: 0.1375 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.1375 2022/12/30 13:59:02 - mmengine - INFO - Epoch(train) [11][1100/1567] lr: 2.4706e-02 eta: 0:25:32 time: 0.1892 data_time: 0.0068 memory: 2656 loss: 0.1034 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1034 2022/12/30 13:59:19 - mmengine - INFO - Epoch(train) [11][1200/1567] lr: 2.4167e-02 eta: 0:25:13 time: 0.1899 data_time: 0.0067 memory: 2656 loss: 0.1111 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1111 2022/12/30 13:59:37 - mmengine - INFO - Epoch(train) [11][1300/1567] lr: 2.3633e-02 eta: 0:24:54 time: 0.1766 data_time: 0.0070 memory: 2656 loss: 0.1742 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.1742 2022/12/30 13:59:43 - mmengine - INFO - Exp name: stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221230_130509 2022/12/30 13:59:56 - mmengine - INFO - Epoch(train) [11][1400/1567] lr: 2.3103e-02 eta: 0:24:36 time: 0.1828 data_time: 0.0067 memory: 2656 loss: 0.1298 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1298 2022/12/30 14:00:14 - mmengine - INFO - Epoch(train) [11][1500/1567] lr: 2.2577e-02 eta: 0:24:17 time: 0.1804 data_time: 0.0066 memory: 2656 loss: 0.1311 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1311 2022/12/30 14:00:25 - mmengine - INFO - Exp name: stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221230_130509 2022/12/30 14:00:25 - mmengine - INFO - Epoch(train) [11][1567/1567] lr: 2.2227e-02 eta: 0:24:04 time: 0.1364 data_time: 0.0067 memory: 2656 loss: 0.3232 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.3232 2022/12/30 14:00:25 - mmengine - INFO - Saving checkpoint at 11 epochs 2022/12/30 14:00:30 - mmengine - INFO - Epoch(val) [11][100/129] eta: 0:00:01 time: 0.0423 data_time: 0.0098 memory: 378 2022/12/30 14:00:32 - mmengine - INFO - Epoch(val) [11][129/129] acc/top1: 0.8364 acc/top5: 0.9682 acc/mean1: 0.8363 2022/12/30 14:00:32 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_10.pth is removed 2022/12/30 14:00:32 - mmengine - INFO - The best checkpoint with 0.8364 acc/top1 at 11 epoch is saved to best_acc/top1_epoch_11.pth. 2022/12/30 14:00:51 - mmengine - INFO - Epoch(train) [12][ 100/1567] lr: 2.1708e-02 eta: 0:23:46 time: 0.1818 data_time: 0.0071 memory: 2656 loss: 0.1028 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1028 2022/12/30 14:01:09 - mmengine - INFO - Epoch(train) [12][ 200/1567] lr: 2.1194e-02 eta: 0:23:27 time: 0.1848 data_time: 0.0073 memory: 2656 loss: 0.1172 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1172 2022/12/30 14:01:28 - mmengine - INFO - Epoch(train) [12][ 300/1567] lr: 2.0684e-02 eta: 0:23:09 time: 0.1814 data_time: 0.0079 memory: 2656 loss: 0.1275 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1275 2022/12/30 14:01:46 - mmengine - INFO - Epoch(train) [12][ 400/1567] lr: 2.0179e-02 eta: 0:22:50 time: 0.1863 data_time: 0.0080 memory: 2656 loss: 0.1229 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1229 2022/12/30 14:02:04 - mmengine - INFO - Epoch(train) [12][ 500/1567] lr: 1.9678e-02 eta: 0:22:32 time: 0.1818 data_time: 0.0075 memory: 2656 loss: 0.0735 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0735 2022/12/30 14:02:23 - mmengine - INFO - Epoch(train) [12][ 600/1567] lr: 1.9182e-02 eta: 0:22:13 time: 0.1821 data_time: 0.0071 memory: 2656 loss: 0.0720 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0720 2022/12/30 14:02:41 - mmengine - INFO - Epoch(train) [12][ 700/1567] lr: 1.8691e-02 eta: 0:21:55 time: 0.1754 data_time: 0.0075 memory: 2656 loss: 0.1111 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1111 2022/12/30 14:02:54 - mmengine - INFO - Exp name: stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221230_130509 2022/12/30 14:03:01 - mmengine - INFO - Epoch(train) [12][ 800/1567] lr: 1.8205e-02 eta: 0:21:37 time: 0.1924 data_time: 0.0076 memory: 2656 loss: 0.1130 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.1130 2022/12/30 14:03:20 - mmengine - INFO - Epoch(train) [12][ 900/1567] lr: 1.7724e-02 eta: 0:21:19 time: 0.1894 data_time: 0.0075 memory: 2656 loss: 0.0819 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0819 2022/12/30 14:03:38 - mmengine - INFO - Epoch(train) [12][1000/1567] lr: 1.7248e-02 eta: 0:21:00 time: 0.1769 data_time: 0.0072 memory: 2656 loss: 0.1142 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1142 2022/12/30 14:03:57 - mmengine - INFO - Epoch(train) [12][1100/1567] lr: 1.6778e-02 eta: 0:20:42 time: 0.1878 data_time: 0.0071 memory: 2656 loss: 0.1054 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1054 2022/12/30 14:04:15 - mmengine - INFO - Epoch(train) [12][1200/1567] lr: 1.6312e-02 eta: 0:20:23 time: 0.1844 data_time: 0.0072 memory: 2656 loss: 0.1124 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.1124 2022/12/30 14:04:33 - mmengine - INFO - Epoch(train) [12][1300/1567] lr: 1.5852e-02 eta: 0:20:05 time: 0.1844 data_time: 0.0076 memory: 2656 loss: 0.1192 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1192 2022/12/30 14:04:52 - mmengine - INFO - Epoch(train) [12][1400/1567] lr: 1.5397e-02 eta: 0:19:46 time: 0.1816 data_time: 0.0074 memory: 2656 loss: 0.0670 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0670 2022/12/30 14:05:10 - mmengine - INFO - Epoch(train) [12][1500/1567] lr: 1.4947e-02 eta: 0:19:28 time: 0.1835 data_time: 0.0069 memory: 2656 loss: 0.0856 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0856 2022/12/30 14:05:21 - mmengine - INFO - Exp name: stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221230_130509 2022/12/30 14:05:21 - mmengine - INFO - Epoch(train) [12][1567/1567] lr: 1.4649e-02 eta: 0:19:15 time: 0.1337 data_time: 0.0068 memory: 2656 loss: 0.2480 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2480 2022/12/30 14:05:21 - mmengine - INFO - Saving checkpoint at 12 epochs 2022/12/30 14:05:26 - mmengine - INFO - Epoch(val) [12][100/129] eta: 0:00:01 time: 0.0366 data_time: 0.0121 memory: 378 2022/12/30 14:05:29 - mmengine - INFO - Epoch(val) [12][129/129] acc/top1: 0.8424 acc/top5: 0.9711 acc/mean1: 0.8422 2022/12/30 14:05:29 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_11.pth is removed 2022/12/30 14:05:29 - mmengine - INFO - The best checkpoint with 0.8424 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: 0:18:57 time: 0.1830 data_time: 0.0070 memory: 2656 loss: 0.0774 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0774 2022/12/30 14:06:05 - mmengine - INFO - Exp name: stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221230_130509 2022/12/30 14:06:06 - mmengine - INFO - Epoch(train) [13][ 200/1567] lr: 1.3774e-02 eta: 0:18:38 time: 0.1784 data_time: 0.0072 memory: 2656 loss: 0.0964 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.0964 2022/12/30 14:06:23 - mmengine - INFO - Epoch(train) [13][ 300/1567] lr: 1.3345e-02 eta: 0:18:20 time: 0.1789 data_time: 0.0073 memory: 2656 loss: 0.0551 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0551 2022/12/30 14:06:42 - mmengine - INFO - Epoch(train) [13][ 400/1567] lr: 1.2922e-02 eta: 0:18:01 time: 0.1849 data_time: 0.0071 memory: 2656 loss: 0.0613 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0613 2022/12/30 14:07:00 - mmengine - INFO - Epoch(train) [13][ 500/1567] lr: 1.2505e-02 eta: 0:17:43 time: 0.1817 data_time: 0.0070 memory: 2656 loss: 0.0476 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0476 2022/12/30 14:07:19 - mmengine - INFO - Epoch(train) [13][ 600/1567] lr: 1.2093e-02 eta: 0:17:24 time: 0.1794 data_time: 0.0069 memory: 2656 loss: 0.0543 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0543 2022/12/30 14:07:37 - mmengine - INFO - Epoch(train) [13][ 700/1567] lr: 1.1687e-02 eta: 0:17:06 time: 0.1842 data_time: 0.0067 memory: 2656 loss: 0.0572 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0572 2022/12/30 14:07:55 - mmengine - INFO - Epoch(train) [13][ 800/1567] lr: 1.1288e-02 eta: 0:16:47 time: 0.1798 data_time: 0.0069 memory: 2656 loss: 0.0617 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0617 2022/12/30 14:08:14 - mmengine - INFO - Epoch(train) [13][ 900/1567] lr: 1.0894e-02 eta: 0:16:29 time: 0.1844 data_time: 0.0070 memory: 2656 loss: 0.0450 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0450 2022/12/30 14:08:32 - mmengine - INFO - Epoch(train) [13][1000/1567] lr: 1.0507e-02 eta: 0:16:10 time: 0.1735 data_time: 0.0066 memory: 2656 loss: 0.0584 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0584 2022/12/30 14:08:50 - mmengine - INFO - Epoch(train) [13][1100/1567] lr: 1.0126e-02 eta: 0:15:52 time: 0.1901 data_time: 0.0069 memory: 2656 loss: 0.0513 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0513 2022/12/30 14:09:08 - mmengine - INFO - Exp name: stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221230_130509 2022/12/30 14:09:08 - mmengine - INFO - Epoch(train) [13][1200/1567] lr: 9.7512e-03 eta: 0:15:33 time: 0.1753 data_time: 0.0068 memory: 2656 loss: 0.0400 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0400 2022/12/30 14:09:27 - mmengine - INFO - Epoch(train) [13][1300/1567] lr: 9.3826e-03 eta: 0:15:15 time: 0.1915 data_time: 0.0068 memory: 2656 loss: 0.0388 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0388 2022/12/30 14:09:45 - mmengine - INFO - Epoch(train) [13][1400/1567] lr: 9.0204e-03 eta: 0:14:57 time: 0.1878 data_time: 0.0072 memory: 2656 loss: 0.0431 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0431 2022/12/30 14:10:04 - mmengine - INFO - Epoch(train) [13][1500/1567] lr: 8.6647e-03 eta: 0:14:38 time: 0.1804 data_time: 0.0070 memory: 2656 loss: 0.0297 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0297 2022/12/30 14:10:16 - mmengine - INFO - Exp name: stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221230_130509 2022/12/30 14:10:16 - mmengine - INFO - Epoch(train) [13][1567/1567] lr: 8.4300e-03 eta: 0:14:26 time: 0.1375 data_time: 0.0074 memory: 2656 loss: 0.2121 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.2121 2022/12/30 14:10:16 - mmengine - INFO - Saving checkpoint at 13 epochs 2022/12/30 14:10:21 - mmengine - INFO - Epoch(val) [13][100/129] eta: 0:00:01 time: 0.0372 data_time: 0.0123 memory: 378 2022/12/30 14:10:23 - mmengine - INFO - Epoch(val) [13][129/129] acc/top1: 0.8522 acc/top5: 0.9724 acc/mean1: 0.8522 2022/12/30 14:10:23 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_12.pth is removed 2022/12/30 14:10:23 - mmengine - INFO - The best checkpoint with 0.8522 acc/top1 at 13 epoch is saved to best_acc/top1_epoch_13.pth. 2022/12/30 14:10:42 - mmengine - INFO - Epoch(train) [14][ 100/1567] lr: 8.0851e-03 eta: 0:14:07 time: 0.1787 data_time: 0.0073 memory: 2656 loss: 0.0413 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0413 2022/12/30 14:11:01 - mmengine - INFO - Epoch(train) [14][ 200/1567] lr: 7.7469e-03 eta: 0:13:49 time: 0.1939 data_time: 0.0068 memory: 2656 loss: 0.0317 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0317 2022/12/30 14:11:19 - mmengine - INFO - Epoch(train) [14][ 300/1567] lr: 7.4152e-03 eta: 0:13:31 time: 0.1706 data_time: 0.0067 memory: 2656 loss: 0.0351 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0351 2022/12/30 14:11:37 - mmengine - INFO - Epoch(train) [14][ 400/1567] lr: 7.0902e-03 eta: 0:13:12 time: 0.1825 data_time: 0.0076 memory: 2656 loss: 0.0330 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0330 2022/12/30 14:11:55 - mmengine - INFO - Epoch(train) [14][ 500/1567] lr: 6.7720e-03 eta: 0:12:54 time: 0.1866 data_time: 0.0068 memory: 2656 loss: 0.0334 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0334 2022/12/30 14:12:13 - mmengine - INFO - Epoch(train) [14][ 600/1567] lr: 6.4606e-03 eta: 0:12:35 time: 0.1888 data_time: 0.0077 memory: 2656 loss: 0.0288 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0288 2022/12/30 14:12:19 - mmengine - INFO - Exp name: stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221230_130509 2022/12/30 14:12:31 - mmengine - INFO - Epoch(train) [14][ 700/1567] lr: 6.1560e-03 eta: 0:12:17 time: 0.1844 data_time: 0.0068 memory: 2656 loss: 0.0436 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.0436 2022/12/30 14:12:49 - mmengine - INFO - Epoch(train) [14][ 800/1567] lr: 5.8582e-03 eta: 0:11:58 time: 0.1729 data_time: 0.0067 memory: 2656 loss: 0.0361 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0361 2022/12/30 14:13:07 - mmengine - INFO - Epoch(train) [14][ 900/1567] lr: 5.5675e-03 eta: 0:11:40 time: 0.1818 data_time: 0.0068 memory: 2656 loss: 0.0239 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0239 2022/12/30 14:13:26 - mmengine - INFO - Epoch(train) [14][1000/1567] lr: 5.2836e-03 eta: 0:11:21 time: 0.1945 data_time: 0.0069 memory: 2656 loss: 0.0248 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0248 2022/12/30 14:13:44 - mmengine - INFO - Epoch(train) [14][1100/1567] lr: 5.0068e-03 eta: 0:11:03 time: 0.1854 data_time: 0.0067 memory: 2656 loss: 0.0294 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0294 2022/12/30 14:14:02 - mmengine - INFO - Epoch(train) [14][1200/1567] lr: 4.7371e-03 eta: 0:10:44 time: 0.1827 data_time: 0.0068 memory: 2656 loss: 0.0198 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0198 2022/12/30 14:14:21 - mmengine - INFO - Epoch(train) [14][1300/1567] lr: 4.4745e-03 eta: 0:10:26 time: 0.1816 data_time: 0.0068 memory: 2656 loss: 0.0279 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0279 2022/12/30 14:14:39 - mmengine - INFO - Epoch(train) [14][1400/1567] lr: 4.2190e-03 eta: 0:10:07 time: 0.1852 data_time: 0.0076 memory: 2656 loss: 0.0159 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0159 2022/12/30 14:14:57 - mmengine - INFO - Epoch(train) [14][1500/1567] lr: 3.9707e-03 eta: 0:09:49 time: 0.1879 data_time: 0.0070 memory: 2656 loss: 0.0197 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0197 2022/12/30 14:15:09 - mmengine - INFO - Exp name: stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221230_130509 2022/12/30 14:15:09 - mmengine - INFO - Epoch(train) [14][1567/1567] lr: 3.8084e-03 eta: 0:09:37 time: 0.1367 data_time: 0.0068 memory: 2656 loss: 0.2359 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.2359 2022/12/30 14:15:09 - mmengine - INFO - Saving checkpoint at 14 epochs 2022/12/30 14:15:14 - mmengine - INFO - Epoch(val) [14][100/129] eta: 0:00:01 time: 0.0371 data_time: 0.0114 memory: 378 2022/12/30 14:15:16 - mmengine - INFO - Epoch(val) [14][129/129] acc/top1: 0.8652 acc/top5: 0.9748 acc/mean1: 0.8651 2022/12/30 14:15:16 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_13.pth is removed 2022/12/30 14:15:17 - mmengine - INFO - The best checkpoint with 0.8652 acc/top1 at 14 epoch is saved to best_acc/top1_epoch_14.pth. 2022/12/30 14:15:28 - mmengine - INFO - Exp name: stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221230_130509 2022/12/30 14:15:35 - mmengine - INFO - Epoch(train) [15][ 100/1567] lr: 3.5722e-03 eta: 0:09:18 time: 0.1804 data_time: 0.0067 memory: 2656 loss: 0.0182 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0182 2022/12/30 14:15:53 - mmengine - INFO - Epoch(train) [15][ 200/1567] lr: 3.3433e-03 eta: 0:09:00 time: 0.1817 data_time: 0.0072 memory: 2656 loss: 0.0176 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0176 2022/12/30 14:16:11 - mmengine - INFO - Epoch(train) [15][ 300/1567] lr: 3.1217e-03 eta: 0:08:41 time: 0.1776 data_time: 0.0068 memory: 2656 loss: 0.0187 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0187 2022/12/30 14:16:30 - mmengine - INFO - Epoch(train) [15][ 400/1567] lr: 2.9075e-03 eta: 0:08:23 time: 0.1871 data_time: 0.0072 memory: 2656 loss: 0.0243 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0243 2022/12/30 14:16:48 - mmengine - INFO - Epoch(train) [15][ 500/1567] lr: 2.7007e-03 eta: 0:08:04 time: 0.1793 data_time: 0.0068 memory: 2656 loss: 0.0355 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0355 2022/12/30 14:17:06 - mmengine - INFO - Epoch(train) [15][ 600/1567] lr: 2.5013e-03 eta: 0:07:46 time: 0.1837 data_time: 0.0071 memory: 2656 loss: 0.0215 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0215 2022/12/30 14:17:25 - mmengine - INFO - Epoch(train) [15][ 700/1567] lr: 2.3093e-03 eta: 0:07:28 time: 0.1834 data_time: 0.0067 memory: 2656 loss: 0.0170 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0170 2022/12/30 14:17:43 - mmengine - INFO - Epoch(train) [15][ 800/1567] lr: 2.1249e-03 eta: 0:07:09 time: 0.1736 data_time: 0.0068 memory: 2656 loss: 0.0228 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0228 2022/12/30 14:18:00 - mmengine - INFO - Epoch(train) [15][ 900/1567] lr: 1.9479e-03 eta: 0:06:51 time: 0.1829 data_time: 0.0072 memory: 2656 loss: 0.0296 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0296 2022/12/30 14:18:18 - mmengine - INFO - Epoch(train) [15][1000/1567] lr: 1.7785e-03 eta: 0:06:32 time: 0.1810 data_time: 0.0069 memory: 2656 loss: 0.0210 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0210 2022/12/30 14:18:30 - mmengine - INFO - Exp name: stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221230_130509 2022/12/30 14:18:37 - mmengine - INFO - Epoch(train) [15][1100/1567] lr: 1.6167e-03 eta: 0:06:14 time: 0.1844 data_time: 0.0068 memory: 2656 loss: 0.0217 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0217 2022/12/30 14:18:55 - mmengine - INFO - Epoch(train) [15][1200/1567] lr: 1.4625e-03 eta: 0:05:55 time: 0.1786 data_time: 0.0068 memory: 2656 loss: 0.0176 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0176 2022/12/30 14:19:13 - mmengine - INFO - Epoch(train) [15][1300/1567] lr: 1.3159e-03 eta: 0:05:37 time: 0.1823 data_time: 0.0067 memory: 2656 loss: 0.0178 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0178 2022/12/30 14:19:31 - mmengine - INFO - Epoch(train) [15][1400/1567] lr: 1.1769e-03 eta: 0:05:19 time: 0.1878 data_time: 0.0075 memory: 2656 loss: 0.0129 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0129 2022/12/30 14:19:50 - mmengine - INFO - Epoch(train) [15][1500/1567] lr: 1.0456e-03 eta: 0:05:00 time: 0.1914 data_time: 0.0068 memory: 2656 loss: 0.0215 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0215 2022/12/30 14:20:02 - mmengine - INFO - Exp name: stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221230_130509 2022/12/30 14:20:02 - mmengine - INFO - Epoch(train) [15][1567/1567] lr: 9.6196e-04 eta: 0:04:48 time: 0.1303 data_time: 0.0068 memory: 2656 loss: 0.2144 top1_acc: 0.0000 top5_acc: 1.0000 loss_cls: 0.2144 2022/12/30 14:20:02 - mmengine - INFO - Saving checkpoint at 15 epochs 2022/12/30 14:20:06 - mmengine - INFO - Epoch(val) [15][100/129] eta: 0:00:01 time: 0.0413 data_time: 0.0106 memory: 378 2022/12/30 14:20:09 - mmengine - INFO - Epoch(val) [15][129/129] acc/top1: 0.8663 acc/top5: 0.9747 acc/mean1: 0.8662 2022/12/30 14:20:09 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_14.pth is removed 2022/12/30 14:20:10 - mmengine - INFO - The best checkpoint with 0.8663 acc/top1 at 15 epoch is saved to best_acc/top1_epoch_15.pth. 2022/12/30 14:20:29 - mmengine - INFO - Epoch(train) [16][ 100/1567] lr: 8.4351e-04 eta: 0:04:29 time: 0.1876 data_time: 0.0067 memory: 2656 loss: 0.0195 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0195 2022/12/30 14:20:47 - mmengine - INFO - Epoch(train) [16][ 200/1567] lr: 7.3277e-04 eta: 0:04:11 time: 0.1877 data_time: 0.0076 memory: 2656 loss: 0.0144 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0144 2022/12/30 14:21:05 - mmengine - INFO - Epoch(train) [16][ 300/1567] lr: 6.2978e-04 eta: 0:03:53 time: 0.1784 data_time: 0.0068 memory: 2656 loss: 0.0161 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0161 2022/12/30 14:21:24 - mmengine - INFO - Epoch(train) [16][ 400/1567] lr: 5.3453e-04 eta: 0:03:34 time: 0.1896 data_time: 0.0068 memory: 2656 loss: 0.0295 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0295 2022/12/30 14:21:42 - mmengine - INFO - Exp name: stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221230_130509 2022/12/30 14:21:42 - mmengine - INFO - Epoch(train) [16][ 500/1567] lr: 4.4705e-04 eta: 0:03:16 time: 0.1861 data_time: 0.0073 memory: 2656 loss: 0.0135 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0135 2022/12/30 14:22:01 - mmengine - INFO - Epoch(train) [16][ 600/1567] lr: 3.6735e-04 eta: 0:02:57 time: 0.1940 data_time: 0.0068 memory: 2656 loss: 0.0149 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0149 2022/12/30 14:22:19 - mmengine - INFO - Epoch(train) [16][ 700/1567] lr: 2.9544e-04 eta: 0:02:39 time: 0.1803 data_time: 0.0067 memory: 2656 loss: 0.0122 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0122 2022/12/30 14:22:38 - mmengine - INFO - Epoch(train) [16][ 800/1567] lr: 2.3134e-04 eta: 0:02:21 time: 0.1882 data_time: 0.0080 memory: 2656 loss: 0.0145 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0145 2022/12/30 14:22:56 - mmengine - INFO - Epoch(train) [16][ 900/1567] lr: 1.7505e-04 eta: 0:02:02 time: 0.1810 data_time: 0.0068 memory: 2656 loss: 0.0188 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0188 2022/12/30 14:23:14 - mmengine - INFO - Epoch(train) [16][1000/1567] lr: 1.2658e-04 eta: 0:01:44 time: 0.1801 data_time: 0.0070 memory: 2656 loss: 0.0138 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0138 2022/12/30 14:23:33 - mmengine - INFO - Epoch(train) [16][1100/1567] lr: 8.5947e-05 eta: 0:01:25 time: 0.1888 data_time: 0.0070 memory: 2656 loss: 0.0128 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0128 2022/12/30 14:23:52 - mmengine - INFO - Epoch(train) [16][1200/1567] lr: 5.3147e-05 eta: 0:01:07 time: 0.1841 data_time: 0.0068 memory: 2656 loss: 0.0125 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0125 2022/12/30 14:24:11 - mmengine - INFO - Epoch(train) [16][1300/1567] lr: 2.8190e-05 eta: 0:00:49 time: 0.1866 data_time: 0.0070 memory: 2656 loss: 0.0142 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0142 2022/12/30 14:24:29 - mmengine - INFO - Epoch(train) [16][1400/1567] lr: 1.1078e-05 eta: 0:00:30 time: 0.1821 data_time: 0.0067 memory: 2656 loss: 0.0144 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0144 2022/12/30 14:24:47 - mmengine - INFO - Exp name: stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221230_130509 2022/12/30 14:24:48 - mmengine - INFO - Epoch(train) [16][1500/1567] lr: 1.8150e-06 eta: 0:00:12 time: 0.1862 data_time: 0.0077 memory: 2656 loss: 0.0181 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0181 2022/12/30 14:24:59 - mmengine - INFO - Exp name: stgcn++_8xb16-bone-motion-u100-80e_ntu60-xsub-keypoint-3d_20221230_130509 2022/12/30 14:24:59 - mmengine - INFO - Epoch(train) [16][1567/1567] lr: 3.9252e-10 eta: 0:00:00 time: 0.1347 data_time: 0.0068 memory: 2656 loss: 0.1966 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.1966 2022/12/30 14:24:59 - mmengine - INFO - Saving checkpoint at 16 epochs 2022/12/30 14:25:04 - mmengine - INFO - Epoch(val) [16][100/129] eta: 0:00:01 time: 0.0465 data_time: 0.0162 memory: 378 2022/12/30 14:25:05 - mmengine - INFO - Epoch(val) [16][129/129] acc/top1: 0.8649 acc/top5: 0.9733 acc/mean1: 0.8648