2022/12/25 16:06:43 - 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: 1431546494 GPU 0,1,2,3,4,5,6,7: NVIDIA A100-SXM4-80GB CUDA_HOME: /mnt/petrelfs/share/cuda-11.3 NVCC: Cuda compilation tools, release 11.3, V11.3.109 GCC: gcc (GCC) 5.4.0 PyTorch: 1.11.0 PyTorch compiling details: PyTorch built with: - GCC 7.3 - C++ Version: 201402 - Intel(R) oneAPI Math Kernel Library Version 2021.4-Product Build 20210904 for Intel(R) 64 architecture applications - Intel(R) MKL-DNN v2.5.2 (Git Hash a9302535553c73243c632ad3c4c80beec3d19a1e) - OpenMP 201511 (a.k.a. OpenMP 4.5) - LAPACK is enabled (usually provided by MKL) - NNPACK is enabled - CPU capability usage: AVX2 - CUDA Runtime 11.3 - NVCC architecture flags: -gencode;arch=compute_37,code=sm_37;-gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_61,code=sm_61;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-gencode;arch=compute_80,code=sm_80;-gencode;arch=compute_86,code=sm_86;-gencode;arch=compute_37,code=compute_37 - CuDNN 8.2 - Magma 2.5.2 - Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.3, CUDNN_VERSION=8.2.0, CXX_COMPILER=/opt/rh/devtoolset-7/root/usr/bin/c++, CXX_FLAGS= -Wno-deprecated -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -fopenmp -DNDEBUG -DUSE_KINETO -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DSYMBOLICATE_MOBILE_DEBUG_HANDLE -DEDGE_PROFILER_USE_KINETO -O2 -fPIC -Wno-narrowing -Wall -Wextra -Werror=return-type -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wno-sign-compare -Wno-unused-parameter -Wno-unused-function -Wno-unused-result -Wno-unused-local-typedefs -Wno-strict-overflow -Wno-strict-aliasing -Wno-error=deprecated-declarations -Wno-stringop-overflow -Wno-psabi -Wno-error=pedantic -Wno-error=redundant-decls -Wno-error=old-style-cast -fdiagnostics-color=always -faligned-new -Wno-unused-but-set-variable -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Werror=format -Wno-stringop-overflow, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, TORCH_VERSION=1.11.0, USE_CUDA=ON, USE_CUDNN=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=OFF, USE_MPI=OFF, USE_NCCL=ON, USE_NNPACK=ON, USE_OPENMP=ON, USE_ROCM=OFF, TorchVision: 0.12.0 OpenCV: 4.6.0 MMEngine: 0.3.2 Runtime environment: cudnn_benchmark: False mp_cfg: {'mp_start_method': 'fork', 'opencv_num_threads': 0} dist_cfg: {'backend': 'nccl'} seed: None diff_rank_seed: False deterministic: False Distributed launcher: pytorch Distributed training: True GPU number: 8 ------------------------------------------------------------ 2022/12/25 16:06:43 - mmengine - INFO - Config: default_scope = 'mmaction' default_hooks = dict( runtime_info=dict(type='RuntimeInfoHook'), timer=dict(type='IterTimerHook'), logger=dict(type='LoggerHook', interval=100, ignore_last=False), param_scheduler=dict(type='ParamSchedulerHook'), checkpoint=dict(type='CheckpointHook', interval=1, save_best='auto'), sampler_seed=dict(type='DistSamplerSeedHook'), sync_buffers=dict(type='SyncBuffersHook')) env_cfg = dict( cudnn_benchmark=False, mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0), dist_cfg=dict(backend='nccl')) log_processor = dict(type='LogProcessor', window_size=20, by_epoch=True) vis_backends = [dict(type='LocalVisBackend')] visualizer = dict( type='ActionVisualizer', vis_backends=[dict(type='LocalVisBackend')]) log_level = 'INFO' load_from = None resume = False model = dict( type='RecognizerGCN', backbone=dict( type='STGCN', gcn_adaptive='init', gcn_with_res=True, tcn_type='mstcn', graph_cfg=dict(layout='coco', mode='spatial')), cls_head=dict(type='GCNHead', num_classes=60, in_channels=256)) dataset_type = 'PoseDataset' ann_file = 'data/skeleton/ntu60_2d.pkl' train_pipeline = [ dict(type='PreNormalize2D'), dict(type='GenSkeFeat', dataset='coco', feats=['jm']), dict(type='UniformSampleFrames', clip_len=100), dict(type='PoseDecode'), dict(type='FormatGCNInput', num_person=2), dict(type='PackActionInputs') ] val_pipeline = [ dict(type='PreNormalize2D'), dict(type='GenSkeFeat', dataset='coco', feats=['jm']), dict( type='UniformSampleFrames', clip_len=100, num_clips=1, test_mode=True), dict(type='PoseDecode'), dict(type='FormatGCNInput', num_person=2), dict(type='PackActionInputs') ] test_pipeline = [ dict(type='PreNormalize2D'), dict(type='GenSkeFeat', dataset='coco', feats=['jm']), dict( type='UniformSampleFrames', clip_len=100, num_clips=10, test_mode=True), dict(type='PoseDecode'), dict(type='FormatGCNInput', num_person=2), dict(type='PackActionInputs') ] train_dataloader = dict( batch_size=16, num_workers=2, persistent_workers=True, sampler=dict(type='DefaultSampler', shuffle=True), dataset=dict( type='RepeatDataset', times=5, dataset=dict( type='PoseDataset', ann_file='data/skeleton/ntu60_2d.pkl', pipeline=[ dict(type='PreNormalize2D'), dict(type='GenSkeFeat', dataset='coco', feats=['jm']), dict(type='UniformSampleFrames', clip_len=100), dict(type='PoseDecode'), dict(type='FormatGCNInput', num_person=2), dict(type='PackActionInputs') ], split='xsub_train'))) val_dataloader = dict( batch_size=16, num_workers=2, persistent_workers=True, sampler=dict(type='DefaultSampler', shuffle=False), dataset=dict( type='PoseDataset', ann_file='data/skeleton/ntu60_2d.pkl', pipeline=[ dict(type='PreNormalize2D'), dict(type='GenSkeFeat', dataset='coco', feats=['jm']), dict( type='UniformSampleFrames', clip_len=100, num_clips=1, test_mode=True), dict(type='PoseDecode'), dict(type='FormatGCNInput', num_person=2), dict(type='PackActionInputs') ], split='xsub_val', test_mode=True)) test_dataloader = dict( batch_size=1, num_workers=2, persistent_workers=True, sampler=dict(type='DefaultSampler', shuffle=False), dataset=dict( type='PoseDataset', ann_file='data/skeleton/ntu60_2d.pkl', pipeline=[ dict(type='PreNormalize2D'), dict(type='GenSkeFeat', dataset='coco', feats=['jm']), dict( type='UniformSampleFrames', clip_len=100, num_clips=10, test_mode=True), dict(type='PoseDecode'), dict(type='FormatGCNInput', num_person=2), dict(type='PackActionInputs') ], split='xsub_val', test_mode=True)) val_evaluator = [dict(type='AccMetric')] test_evaluator = [dict(type='AccMetric')] train_cfg = dict( type='EpochBasedTrainLoop', max_epochs=16, val_begin=1, val_interval=1) val_cfg = dict(type='ValLoop') test_cfg = dict(type='TestLoop') param_scheduler = [ dict( type='CosineAnnealingLR', eta_min=0, T_max=16, by_epoch=True, convert_to_iter_based=True) ] optim_wrapper = dict( optimizer=dict( type='SGD', lr=0.1, momentum=0.9, weight_decay=0.0005, nesterov=True)) auto_scale_lr = dict(enable=False, base_batch_size=128) launcher = 'pytorch' work_dir = './work_dirs/stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d' randomness = dict(seed=None, diff_rank_seed=False, deterministic=False) 2022/12/25 16:06:43 - mmengine - INFO - Result has been saved to /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d/modules_statistic_results.json 2022/12/25 16:06:43 - mmengine - INFO - Hooks will be executed in the following order: before_run: (VERY_HIGH ) RuntimeInfoHook (BELOW_NORMAL) LoggerHook -------------------- before_train: (VERY_HIGH ) RuntimeInfoHook (NORMAL ) IterTimerHook (VERY_LOW ) CheckpointHook -------------------- before_train_epoch: (VERY_HIGH ) RuntimeInfoHook (NORMAL ) IterTimerHook (NORMAL ) DistSamplerSeedHook -------------------- before_train_iter: (VERY_HIGH ) RuntimeInfoHook (NORMAL ) IterTimerHook -------------------- after_train_iter: (VERY_HIGH ) RuntimeInfoHook (NORMAL ) IterTimerHook (BELOW_NORMAL) LoggerHook (LOW ) ParamSchedulerHook (VERY_LOW ) CheckpointHook -------------------- after_train_epoch: (NORMAL ) IterTimerHook (NORMAL ) SyncBuffersHook (LOW ) ParamSchedulerHook (VERY_LOW ) CheckpointHook -------------------- before_val_epoch: (NORMAL ) IterTimerHook -------------------- before_val_iter: (NORMAL ) IterTimerHook -------------------- after_val_iter: (NORMAL ) IterTimerHook (BELOW_NORMAL) LoggerHook -------------------- after_val_epoch: (VERY_HIGH ) RuntimeInfoHook (NORMAL ) IterTimerHook (BELOW_NORMAL) LoggerHook (VERY_LOW ) CheckpointHook -------------------- before_test_epoch: (NORMAL ) IterTimerHook -------------------- before_test_iter: (NORMAL ) IterTimerHook -------------------- after_test_iter: (NORMAL ) IterTimerHook (BELOW_NORMAL) LoggerHook -------------------- after_test_epoch: (VERY_HIGH ) RuntimeInfoHook (NORMAL ) IterTimerHook (BELOW_NORMAL) LoggerHook -------------------- after_run: (BELOW_NORMAL) LoggerHook -------------------- Name of parameter - Initialization information backbone.data_bn.weight - torch.Size([51]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.data_bn.bias - torch.Size([51]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.gcn.A - torch.Size([3, 17, 17]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.gcn.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.gcn.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.gcn.conv.weight - torch.Size([192, 3, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.gcn.conv.bias - torch.Size([192]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.gcn.down.0.weight - torch.Size([64, 3, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.gcn.down.0.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.gcn.down.1.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.gcn.down.1.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.tcn.branches.0.0.weight - torch.Size([14, 64, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.tcn.branches.0.0.bias - torch.Size([14]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.tcn.branches.0.1.weight - torch.Size([14]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.tcn.branches.0.1.bias - torch.Size([14]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.tcn.branches.0.3.conv.weight - torch.Size([14, 14, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.tcn.branches.0.3.conv.bias - torch.Size([14]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.tcn.branches.1.0.weight - torch.Size([10, 64, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.tcn.branches.1.0.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.tcn.branches.1.1.weight - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.tcn.branches.1.1.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.tcn.branches.1.3.conv.weight - torch.Size([10, 10, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.tcn.branches.1.3.conv.bias - torch.Size([10]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.tcn.branches.2.0.weight - torch.Size([10, 64, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.tcn.branches.2.0.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.tcn.branches.2.1.weight - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.tcn.branches.2.1.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.tcn.branches.2.3.conv.weight - torch.Size([10, 10, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.tcn.branches.2.3.conv.bias - torch.Size([10]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.tcn.branches.3.0.weight - torch.Size([10, 64, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.tcn.branches.3.0.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.tcn.branches.3.1.weight - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.tcn.branches.3.1.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.tcn.branches.3.3.conv.weight - torch.Size([10, 10, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.tcn.branches.3.3.conv.bias - torch.Size([10]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.tcn.branches.4.0.weight - torch.Size([10, 64, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.tcn.branches.4.0.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.tcn.branches.4.1.weight - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.tcn.branches.4.1.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.tcn.branches.5.weight - torch.Size([10, 64, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.tcn.branches.5.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.tcn.transform.0.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.tcn.transform.0.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.tcn.transform.2.weight - torch.Size([64, 64, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.tcn.transform.2.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.tcn.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.tcn.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.gcn.A - torch.Size([3, 17, 17]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.gcn.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.gcn.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.gcn.conv.weight - torch.Size([192, 64, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.gcn.conv.bias - torch.Size([192]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.tcn.branches.0.0.weight - torch.Size([14, 64, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.tcn.branches.0.0.bias - torch.Size([14]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.tcn.branches.0.1.weight - torch.Size([14]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.tcn.branches.0.1.bias - torch.Size([14]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.tcn.branches.0.3.conv.weight - torch.Size([14, 14, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.1.tcn.branches.0.3.conv.bias - torch.Size([14]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.1.tcn.branches.1.0.weight - torch.Size([10, 64, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.tcn.branches.1.0.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.tcn.branches.1.1.weight - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.tcn.branches.1.1.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.tcn.branches.1.3.conv.weight - torch.Size([10, 10, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.1.tcn.branches.1.3.conv.bias - torch.Size([10]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.1.tcn.branches.2.0.weight - torch.Size([10, 64, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.tcn.branches.2.0.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.tcn.branches.2.1.weight - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.tcn.branches.2.1.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.tcn.branches.2.3.conv.weight - torch.Size([10, 10, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.1.tcn.branches.2.3.conv.bias - torch.Size([10]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.1.tcn.branches.3.0.weight - torch.Size([10, 64, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.tcn.branches.3.0.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.tcn.branches.3.1.weight - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.tcn.branches.3.1.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.tcn.branches.3.3.conv.weight - torch.Size([10, 10, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.1.tcn.branches.3.3.conv.bias - torch.Size([10]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.1.tcn.branches.4.0.weight - torch.Size([10, 64, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.tcn.branches.4.0.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.tcn.branches.4.1.weight - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.tcn.branches.4.1.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.tcn.branches.5.weight - torch.Size([10, 64, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.tcn.branches.5.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.tcn.transform.0.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.tcn.transform.0.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.tcn.transform.2.weight - torch.Size([64, 64, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.tcn.transform.2.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.tcn.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.tcn.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.gcn.A - torch.Size([3, 17, 17]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.gcn.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.gcn.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.gcn.conv.weight - torch.Size([192, 64, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.gcn.conv.bias - torch.Size([192]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.tcn.branches.0.0.weight - torch.Size([14, 64, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.tcn.branches.0.0.bias - torch.Size([14]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.tcn.branches.0.1.weight - torch.Size([14]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.tcn.branches.0.1.bias - torch.Size([14]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.tcn.branches.0.3.conv.weight - torch.Size([14, 14, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.2.tcn.branches.0.3.conv.bias - torch.Size([14]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.2.tcn.branches.1.0.weight - torch.Size([10, 64, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.tcn.branches.1.0.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.tcn.branches.1.1.weight - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.tcn.branches.1.1.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.tcn.branches.1.3.conv.weight - torch.Size([10, 10, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.2.tcn.branches.1.3.conv.bias - torch.Size([10]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.2.tcn.branches.2.0.weight - torch.Size([10, 64, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.tcn.branches.2.0.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.tcn.branches.2.1.weight - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.tcn.branches.2.1.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.tcn.branches.2.3.conv.weight - torch.Size([10, 10, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.2.tcn.branches.2.3.conv.bias - torch.Size([10]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.2.tcn.branches.3.0.weight - torch.Size([10, 64, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.tcn.branches.3.0.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.tcn.branches.3.1.weight - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.tcn.branches.3.1.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.tcn.branches.3.3.conv.weight - torch.Size([10, 10, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.2.tcn.branches.3.3.conv.bias - torch.Size([10]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.2.tcn.branches.4.0.weight - torch.Size([10, 64, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.tcn.branches.4.0.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.tcn.branches.4.1.weight - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.tcn.branches.4.1.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.tcn.branches.5.weight - torch.Size([10, 64, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.tcn.branches.5.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.tcn.transform.0.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.tcn.transform.0.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.tcn.transform.2.weight - torch.Size([64, 64, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.tcn.transform.2.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.tcn.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.tcn.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.gcn.A - torch.Size([3, 17, 17]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.gcn.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.gcn.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.gcn.conv.weight - torch.Size([192, 64, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.gcn.conv.bias - torch.Size([192]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.tcn.branches.0.0.weight - torch.Size([14, 64, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.tcn.branches.0.0.bias - torch.Size([14]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.tcn.branches.0.1.weight - torch.Size([14]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.tcn.branches.0.1.bias - torch.Size([14]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.tcn.branches.0.3.conv.weight - torch.Size([14, 14, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.3.tcn.branches.0.3.conv.bias - torch.Size([14]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.3.tcn.branches.1.0.weight - torch.Size([10, 64, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.tcn.branches.1.0.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.tcn.branches.1.1.weight - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.tcn.branches.1.1.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.tcn.branches.1.3.conv.weight - torch.Size([10, 10, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.3.tcn.branches.1.3.conv.bias - torch.Size([10]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.3.tcn.branches.2.0.weight - torch.Size([10, 64, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.tcn.branches.2.0.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.tcn.branches.2.1.weight - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.tcn.branches.2.1.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.tcn.branches.2.3.conv.weight - torch.Size([10, 10, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.3.tcn.branches.2.3.conv.bias - torch.Size([10]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.3.tcn.branches.3.0.weight - torch.Size([10, 64, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.tcn.branches.3.0.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.tcn.branches.3.1.weight - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.tcn.branches.3.1.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.tcn.branches.3.3.conv.weight - torch.Size([10, 10, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.3.tcn.branches.3.3.conv.bias - torch.Size([10]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.3.tcn.branches.4.0.weight - torch.Size([10, 64, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.tcn.branches.4.0.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.tcn.branches.4.1.weight - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.tcn.branches.4.1.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.tcn.branches.5.weight - torch.Size([10, 64, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.tcn.branches.5.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.tcn.transform.0.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.tcn.transform.0.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.tcn.transform.2.weight - torch.Size([64, 64, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.tcn.transform.2.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.tcn.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.tcn.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.gcn.A - torch.Size([3, 17, 17]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.gcn.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.gcn.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.gcn.conv.weight - torch.Size([384, 64, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.gcn.conv.bias - torch.Size([384]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.gcn.down.0.weight - torch.Size([128, 64, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.gcn.down.0.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.gcn.down.1.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.gcn.down.1.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.tcn.branches.0.0.weight - torch.Size([23, 128, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.tcn.branches.0.0.bias - torch.Size([23]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.tcn.branches.0.1.weight - torch.Size([23]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.tcn.branches.0.1.bias - torch.Size([23]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.tcn.branches.0.3.conv.weight - torch.Size([23, 23, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.tcn.branches.0.3.conv.bias - torch.Size([23]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.tcn.branches.1.0.weight - torch.Size([21, 128, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.tcn.branches.1.0.bias - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.tcn.branches.1.1.weight - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.tcn.branches.1.1.bias - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.tcn.branches.1.3.conv.weight - torch.Size([21, 21, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.tcn.branches.1.3.conv.bias - torch.Size([21]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.tcn.branches.2.0.weight - torch.Size([21, 128, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.tcn.branches.2.0.bias - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.tcn.branches.2.1.weight - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.tcn.branches.2.1.bias - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.tcn.branches.2.3.conv.weight - torch.Size([21, 21, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.tcn.branches.2.3.conv.bias - torch.Size([21]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.tcn.branches.3.0.weight - torch.Size([21, 128, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.tcn.branches.3.0.bias - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.tcn.branches.3.1.weight - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.tcn.branches.3.1.bias - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.tcn.branches.3.3.conv.weight - torch.Size([21, 21, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.tcn.branches.3.3.conv.bias - torch.Size([21]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.tcn.branches.4.0.weight - torch.Size([21, 128, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.tcn.branches.4.0.bias - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.tcn.branches.4.1.weight - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.tcn.branches.4.1.bias - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.tcn.branches.5.weight - torch.Size([21, 128, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.tcn.branches.5.bias - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.tcn.transform.0.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.tcn.transform.0.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.tcn.transform.2.weight - torch.Size([128, 128, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.tcn.transform.2.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.tcn.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.tcn.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.residual.conv.weight - torch.Size([128, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.residual.conv.bias - torch.Size([128]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.residual.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.residual.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.gcn.A - torch.Size([3, 17, 17]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.gcn.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.gcn.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.gcn.conv.weight - torch.Size([384, 128, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.gcn.conv.bias - torch.Size([384]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.tcn.branches.0.0.weight - torch.Size([23, 128, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.tcn.branches.0.0.bias - torch.Size([23]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.tcn.branches.0.1.weight - torch.Size([23]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.tcn.branches.0.1.bias - torch.Size([23]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.tcn.branches.0.3.conv.weight - torch.Size([23, 23, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.5.tcn.branches.0.3.conv.bias - torch.Size([23]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.5.tcn.branches.1.0.weight - torch.Size([21, 128, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.tcn.branches.1.0.bias - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.tcn.branches.1.1.weight - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.tcn.branches.1.1.bias - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.tcn.branches.1.3.conv.weight - torch.Size([21, 21, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.5.tcn.branches.1.3.conv.bias - torch.Size([21]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.5.tcn.branches.2.0.weight - torch.Size([21, 128, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.tcn.branches.2.0.bias - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.tcn.branches.2.1.weight - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.tcn.branches.2.1.bias - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.tcn.branches.2.3.conv.weight - torch.Size([21, 21, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.5.tcn.branches.2.3.conv.bias - torch.Size([21]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.5.tcn.branches.3.0.weight - torch.Size([21, 128, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.tcn.branches.3.0.bias - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.tcn.branches.3.1.weight - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.tcn.branches.3.1.bias - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.tcn.branches.3.3.conv.weight - torch.Size([21, 21, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.5.tcn.branches.3.3.conv.bias - torch.Size([21]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.5.tcn.branches.4.0.weight - torch.Size([21, 128, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.tcn.branches.4.0.bias - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.tcn.branches.4.1.weight - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.tcn.branches.4.1.bias - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.tcn.branches.5.weight - torch.Size([21, 128, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.tcn.branches.5.bias - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.tcn.transform.0.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.tcn.transform.0.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.tcn.transform.2.weight - torch.Size([128, 128, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.tcn.transform.2.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.tcn.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.tcn.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.gcn.A - torch.Size([3, 17, 17]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.gcn.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.gcn.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.gcn.conv.weight - torch.Size([384, 128, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.gcn.conv.bias - torch.Size([384]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.tcn.branches.0.0.weight - torch.Size([23, 128, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.tcn.branches.0.0.bias - torch.Size([23]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.tcn.branches.0.1.weight - torch.Size([23]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.tcn.branches.0.1.bias - torch.Size([23]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.tcn.branches.0.3.conv.weight - torch.Size([23, 23, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.6.tcn.branches.0.3.conv.bias - torch.Size([23]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.6.tcn.branches.1.0.weight - torch.Size([21, 128, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.tcn.branches.1.0.bias - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.tcn.branches.1.1.weight - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.tcn.branches.1.1.bias - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.tcn.branches.1.3.conv.weight - torch.Size([21, 21, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.6.tcn.branches.1.3.conv.bias - torch.Size([21]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.6.tcn.branches.2.0.weight - torch.Size([21, 128, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.tcn.branches.2.0.bias - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.tcn.branches.2.1.weight - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.tcn.branches.2.1.bias - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.tcn.branches.2.3.conv.weight - torch.Size([21, 21, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.6.tcn.branches.2.3.conv.bias - torch.Size([21]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.6.tcn.branches.3.0.weight - torch.Size([21, 128, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.tcn.branches.3.0.bias - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.tcn.branches.3.1.weight - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.tcn.branches.3.1.bias - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.tcn.branches.3.3.conv.weight - torch.Size([21, 21, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.6.tcn.branches.3.3.conv.bias - torch.Size([21]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.6.tcn.branches.4.0.weight - torch.Size([21, 128, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.tcn.branches.4.0.bias - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.tcn.branches.4.1.weight - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.tcn.branches.4.1.bias - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.tcn.branches.5.weight - torch.Size([21, 128, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.tcn.branches.5.bias - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.tcn.transform.0.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.tcn.transform.0.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.tcn.transform.2.weight - torch.Size([128, 128, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.tcn.transform.2.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.tcn.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.tcn.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.gcn.A - torch.Size([3, 17, 17]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.gcn.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.gcn.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.gcn.conv.weight - torch.Size([768, 128, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.gcn.conv.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.gcn.down.0.weight - torch.Size([256, 128, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.gcn.down.0.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.gcn.down.1.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.gcn.down.1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.tcn.branches.0.0.weight - torch.Size([46, 256, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.tcn.branches.0.0.bias - torch.Size([46]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.tcn.branches.0.1.weight - torch.Size([46]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.tcn.branches.0.1.bias - torch.Size([46]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.tcn.branches.0.3.conv.weight - torch.Size([46, 46, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.tcn.branches.0.3.conv.bias - torch.Size([46]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.tcn.branches.1.0.weight - torch.Size([42, 256, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.tcn.branches.1.0.bias - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.tcn.branches.1.1.weight - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.tcn.branches.1.1.bias - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.tcn.branches.1.3.conv.weight - torch.Size([42, 42, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.tcn.branches.1.3.conv.bias - torch.Size([42]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.tcn.branches.2.0.weight - torch.Size([42, 256, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.tcn.branches.2.0.bias - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.tcn.branches.2.1.weight - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.tcn.branches.2.1.bias - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.tcn.branches.2.3.conv.weight - torch.Size([42, 42, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.tcn.branches.2.3.conv.bias - torch.Size([42]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.tcn.branches.3.0.weight - torch.Size([42, 256, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.tcn.branches.3.0.bias - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.tcn.branches.3.1.weight - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.tcn.branches.3.1.bias - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.tcn.branches.3.3.conv.weight - torch.Size([42, 42, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.tcn.branches.3.3.conv.bias - torch.Size([42]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.tcn.branches.4.0.weight - torch.Size([42, 256, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.tcn.branches.4.0.bias - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.tcn.branches.4.1.weight - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.tcn.branches.4.1.bias - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.tcn.branches.5.weight - torch.Size([42, 256, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.tcn.branches.5.bias - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.tcn.transform.0.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.tcn.transform.0.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.tcn.transform.2.weight - torch.Size([256, 256, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.tcn.transform.2.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.tcn.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.tcn.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.residual.conv.weight - torch.Size([256, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.residual.conv.bias - torch.Size([256]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.residual.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.residual.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.gcn.A - torch.Size([3, 17, 17]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.gcn.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.gcn.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.gcn.conv.weight - torch.Size([768, 256, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.gcn.conv.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.tcn.branches.0.0.weight - torch.Size([46, 256, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.tcn.branches.0.0.bias - torch.Size([46]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.tcn.branches.0.1.weight - torch.Size([46]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.tcn.branches.0.1.bias - torch.Size([46]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.tcn.branches.0.3.conv.weight - torch.Size([46, 46, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.8.tcn.branches.0.3.conv.bias - torch.Size([46]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.8.tcn.branches.1.0.weight - torch.Size([42, 256, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.tcn.branches.1.0.bias - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.tcn.branches.1.1.weight - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.tcn.branches.1.1.bias - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.tcn.branches.1.3.conv.weight - torch.Size([42, 42, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.8.tcn.branches.1.3.conv.bias - torch.Size([42]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.8.tcn.branches.2.0.weight - torch.Size([42, 256, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.tcn.branches.2.0.bias - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.tcn.branches.2.1.weight - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.tcn.branches.2.1.bias - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.tcn.branches.2.3.conv.weight - torch.Size([42, 42, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.8.tcn.branches.2.3.conv.bias - torch.Size([42]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.8.tcn.branches.3.0.weight - torch.Size([42, 256, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.tcn.branches.3.0.bias - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.tcn.branches.3.1.weight - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.tcn.branches.3.1.bias - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.tcn.branches.3.3.conv.weight - torch.Size([42, 42, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.8.tcn.branches.3.3.conv.bias - torch.Size([42]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.8.tcn.branches.4.0.weight - torch.Size([42, 256, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.tcn.branches.4.0.bias - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.tcn.branches.4.1.weight - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.tcn.branches.4.1.bias - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.tcn.branches.5.weight - torch.Size([42, 256, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.tcn.branches.5.bias - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.tcn.transform.0.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.tcn.transform.0.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.tcn.transform.2.weight - torch.Size([256, 256, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.tcn.transform.2.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.tcn.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.tcn.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.gcn.A - torch.Size([3, 17, 17]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.gcn.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.gcn.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.gcn.conv.weight - torch.Size([768, 256, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.gcn.conv.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.tcn.branches.0.0.weight - torch.Size([46, 256, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.tcn.branches.0.0.bias - torch.Size([46]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.tcn.branches.0.1.weight - torch.Size([46]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.tcn.branches.0.1.bias - torch.Size([46]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.tcn.branches.0.3.conv.weight - torch.Size([46, 46, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.9.tcn.branches.0.3.conv.bias - torch.Size([46]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.9.tcn.branches.1.0.weight - torch.Size([42, 256, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.tcn.branches.1.0.bias - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.tcn.branches.1.1.weight - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.tcn.branches.1.1.bias - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.tcn.branches.1.3.conv.weight - torch.Size([42, 42, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.9.tcn.branches.1.3.conv.bias - torch.Size([42]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.9.tcn.branches.2.0.weight - torch.Size([42, 256, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.tcn.branches.2.0.bias - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.tcn.branches.2.1.weight - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.tcn.branches.2.1.bias - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.tcn.branches.2.3.conv.weight - torch.Size([42, 42, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.9.tcn.branches.2.3.conv.bias - torch.Size([42]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.9.tcn.branches.3.0.weight - torch.Size([42, 256, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.tcn.branches.3.0.bias - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.tcn.branches.3.1.weight - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.tcn.branches.3.1.bias - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.tcn.branches.3.3.conv.weight - torch.Size([42, 42, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.9.tcn.branches.3.3.conv.bias - torch.Size([42]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.9.tcn.branches.4.0.weight - torch.Size([42, 256, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.tcn.branches.4.0.bias - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.tcn.branches.4.1.weight - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.tcn.branches.4.1.bias - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.tcn.branches.5.weight - torch.Size([42, 256, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.tcn.branches.5.bias - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.tcn.transform.0.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.tcn.transform.0.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.tcn.transform.2.weight - torch.Size([256, 256, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.tcn.transform.2.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.tcn.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.tcn.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN cls_head.fc.weight - torch.Size([60, 256]): NormalInit: mean=0, std=0.01, bias=0 cls_head.fc.bias - torch.Size([60]): NormalInit: mean=0, std=0.01, bias=0 2022/12/25 16:07:16 - mmengine - INFO - Checkpoints will be saved to /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d. 2022/12/25 16:07:27 - mmengine - INFO - Epoch(train) [1][ 100/1567] lr: 9.9996e-02 eta: 0:46:10 time: 0.0828 data_time: 0.0064 memory: 1827 loss: 3.0681 top1_acc: 0.1875 top5_acc: 0.3750 loss_cls: 3.0681 2022/12/25 16:07:35 - mmengine - INFO - Epoch(train) [1][ 200/1567] lr: 9.9984e-02 eta: 0:40:17 time: 0.0845 data_time: 0.0063 memory: 1827 loss: 1.9254 top1_acc: 0.4375 top5_acc: 0.7500 loss_cls: 1.9254 2022/12/25 16:07:44 - mmengine - INFO - Epoch(train) [1][ 300/1567] lr: 9.9965e-02 eta: 0:38:19 time: 0.0832 data_time: 0.0062 memory: 1827 loss: 1.3748 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.3748 2022/12/25 16:07:52 - mmengine - INFO - Epoch(train) [1][ 400/1567] lr: 9.9938e-02 eta: 0:37:11 time: 0.0834 data_time: 0.0063 memory: 1827 loss: 1.1300 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.1300 2022/12/25 16:08:00 - mmengine - INFO - Epoch(train) [1][ 500/1567] lr: 9.9902e-02 eta: 0:36:21 time: 0.0822 data_time: 0.0064 memory: 1827 loss: 0.9897 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 0.9897 2022/12/25 16:08:08 - mmengine - INFO - Epoch(train) [1][ 600/1567] lr: 9.9859e-02 eta: 0:35:51 time: 0.0871 data_time: 0.0062 memory: 1827 loss: 0.9018 top1_acc: 0.5000 top5_acc: 0.9375 loss_cls: 0.9018 2022/12/25 16:08:17 - mmengine - INFO - Epoch(train) [1][ 700/1567] lr: 9.9808e-02 eta: 0:35:26 time: 0.0820 data_time: 0.0063 memory: 1827 loss: 0.8570 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.8570 2022/12/25 16:08:25 - mmengine - INFO - Epoch(train) [1][ 800/1567] lr: 9.9750e-02 eta: 0:35:06 time: 0.0851 data_time: 0.0063 memory: 1827 loss: 0.8225 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 0.8225 2022/12/25 16:08:33 - mmengine - INFO - Epoch(train) [1][ 900/1567] lr: 9.9683e-02 eta: 0:34:46 time: 0.0819 data_time: 0.0062 memory: 1827 loss: 0.8283 top1_acc: 0.6250 top5_acc: 1.0000 loss_cls: 0.8283 2022/12/25 16:08:42 - mmengine - INFO - Exp name: stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221225_160636 2022/12/25 16:08:42 - mmengine - INFO - Epoch(train) [1][1000/1567] lr: 9.9609e-02 eta: 0:34:33 time: 0.0848 data_time: 0.0064 memory: 1827 loss: 0.6767 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 0.6767 2022/12/25 16:08:50 - mmengine - INFO - Epoch(train) [1][1100/1567] lr: 9.9527e-02 eta: 0:34:19 time: 0.0857 data_time: 0.0063 memory: 1827 loss: 0.6840 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.6840 2022/12/25 16:08:58 - mmengine - INFO - Epoch(train) [1][1200/1567] lr: 9.9437e-02 eta: 0:34:04 time: 0.0827 data_time: 0.0061 memory: 1827 loss: 0.6800 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.6800 2022/12/25 16:09:07 - mmengine - INFO - Epoch(train) [1][1300/1567] lr: 9.9339e-02 eta: 0:33:51 time: 0.0827 data_time: 0.0062 memory: 1827 loss: 0.6498 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.6498 2022/12/25 16:09:15 - mmengine - INFO - Epoch(train) [1][1400/1567] lr: 9.9234e-02 eta: 0:33:37 time: 0.0819 data_time: 0.0062 memory: 1827 loss: 0.5013 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.5013 2022/12/25 16:09:23 - mmengine - INFO - Epoch(train) [1][1500/1567] lr: 9.9121e-02 eta: 0:33:25 time: 0.0822 data_time: 0.0063 memory: 1827 loss: 0.6274 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.6274 2022/12/25 16:09:29 - mmengine - INFO - Exp name: stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221225_160636 2022/12/25 16:09:29 - mmengine - INFO - Epoch(train) [1][1567/1567] lr: 9.9040e-02 eta: 0:33:18 time: 0.0854 data_time: 0.0066 memory: 1827 loss: 0.8339 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.8339 2022/12/25 16:09:29 - mmengine - INFO - Saving checkpoint at 1 epochs 2022/12/25 16:09:32 - mmengine - INFO - Epoch(val) [1][100/129] eta: 0:00:00 time: 0.0255 data_time: 0.0058 memory: 263 2022/12/25 16:09:33 - mmengine - INFO - Epoch(val) [1][129/129] acc/top1: 0.5687 acc/top5: 0.8866 acc/mean1: 0.5688 2022/12/25 16:09:33 - mmengine - INFO - The best checkpoint with 0.5687 acc/top1 at 1 epoch is saved to best_acc/top1_epoch_1.pth. 2022/12/25 16:09:42 - mmengine - INFO - Epoch(train) [2][ 100/1567] lr: 9.8914e-02 eta: 0:33:09 time: 0.0858 data_time: 0.0065 memory: 1827 loss: 0.5860 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.5860 2022/12/25 16:09:51 - mmengine - INFO - Epoch(train) [2][ 200/1567] lr: 9.8781e-02 eta: 0:33:02 time: 0.0861 data_time: 0.0064 memory: 1827 loss: 0.5056 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.5056 2022/12/25 16:09:59 - mmengine - INFO - Epoch(train) [2][ 300/1567] lr: 9.8639e-02 eta: 0:32:50 time: 0.0818 data_time: 0.0063 memory: 1827 loss: 0.5824 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.5824 2022/12/25 16:10:07 - mmengine - INFO - Epoch(train) [2][ 400/1567] lr: 9.8491e-02 eta: 0:32:40 time: 0.0914 data_time: 0.0064 memory: 1827 loss: 0.5527 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.5527 2022/12/25 16:10:10 - mmengine - INFO - Exp name: stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221225_160636 2022/12/25 16:10:15 - mmengine - INFO - Epoch(train) [2][ 500/1567] lr: 9.8334e-02 eta: 0:32:30 time: 0.0825 data_time: 0.0062 memory: 1827 loss: 0.4851 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.4851 2022/12/25 16:10:24 - mmengine - INFO - Epoch(train) [2][ 600/1567] lr: 9.8170e-02 eta: 0:32:20 time: 0.0824 data_time: 0.0064 memory: 1827 loss: 0.5351 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.5351 2022/12/25 16:10:32 - mmengine - INFO - Epoch(train) [2][ 700/1567] lr: 9.7998e-02 eta: 0:32:08 time: 0.0818 data_time: 0.0063 memory: 1827 loss: 0.5165 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.5165 2022/12/25 16:10:40 - mmengine - INFO - Epoch(train) [2][ 800/1567] lr: 9.7819e-02 eta: 0:32:00 time: 0.0854 data_time: 0.0063 memory: 1827 loss: 0.4845 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4845 2022/12/25 16:10:49 - mmengine - INFO - Epoch(train) [2][ 900/1567] lr: 9.7632e-02 eta: 0:31:50 time: 0.0818 data_time: 0.0064 memory: 1827 loss: 0.4415 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.4415 2022/12/25 16:10:57 - mmengine - INFO - Epoch(train) [2][1000/1567] lr: 9.7438e-02 eta: 0:31:40 time: 0.0825 data_time: 0.0063 memory: 1827 loss: 0.5169 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.5169 2022/12/25 16:11:05 - mmengine - INFO - Epoch(train) [2][1100/1567] lr: 9.7236e-02 eta: 0:31:30 time: 0.0835 data_time: 0.0064 memory: 1827 loss: 0.4939 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4939 2022/12/25 16:11:14 - mmengine - INFO - Epoch(train) [2][1200/1567] lr: 9.7027e-02 eta: 0:31:21 time: 0.0824 data_time: 0.0064 memory: 1827 loss: 0.4514 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4514 2022/12/25 16:11:22 - mmengine - INFO - Epoch(train) [2][1300/1567] lr: 9.6810e-02 eta: 0:31:12 time: 0.0860 data_time: 0.0067 memory: 1827 loss: 0.4310 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4310 2022/12/25 16:11:30 - mmengine - INFO - Epoch(train) [2][1400/1567] lr: 9.6587e-02 eta: 0:31:03 time: 0.0830 data_time: 0.0067 memory: 1827 loss: 0.4982 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.4982 2022/12/25 16:11:33 - mmengine - INFO - Exp name: stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221225_160636 2022/12/25 16:11:39 - mmengine - INFO - Epoch(train) [2][1500/1567] lr: 9.6355e-02 eta: 0:30:54 time: 0.0826 data_time: 0.0064 memory: 1827 loss: 0.4503 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4503 2022/12/25 16:11:44 - mmengine - INFO - Exp name: stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221225_160636 2022/12/25 16:11:44 - mmengine - INFO - Epoch(train) [2][1567/1567] lr: 9.6196e-02 eta: 0:30:47 time: 0.0824 data_time: 0.0062 memory: 1827 loss: 0.6594 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.6594 2022/12/25 16:11:44 - mmengine - INFO - Saving checkpoint at 2 epochs 2022/12/25 16:11:47 - mmengine - INFO - Epoch(val) [2][100/129] eta: 0:00:00 time: 0.0255 data_time: 0.0058 memory: 263 2022/12/25 16:11:48 - mmengine - INFO - Epoch(val) [2][129/129] acc/top1: 0.6141 acc/top5: 0.9199 acc/mean1: 0.6139 2022/12/25 16:11:48 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_1.pth is removed 2022/12/25 16:11:48 - mmengine - INFO - The best checkpoint with 0.6141 acc/top1 at 2 epoch is saved to best_acc/top1_epoch_2.pth. 2022/12/25 16:11:57 - mmengine - INFO - Epoch(train) [3][ 100/1567] lr: 9.5953e-02 eta: 0:30:39 time: 0.0823 data_time: 0.0064 memory: 1827 loss: 0.4348 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4348 2022/12/25 16:12:05 - mmengine - INFO - Epoch(train) [3][ 200/1567] lr: 9.5703e-02 eta: 0:30:30 time: 0.0832 data_time: 0.0064 memory: 1827 loss: 0.4855 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.4855 2022/12/25 16:12:14 - mmengine - INFO - Epoch(train) [3][ 300/1567] lr: 9.5445e-02 eta: 0:30:21 time: 0.0821 data_time: 0.0064 memory: 1827 loss: 0.4947 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4947 2022/12/25 16:12:22 - mmengine - INFO - Epoch(train) [3][ 400/1567] lr: 9.5180e-02 eta: 0:30:12 time: 0.0835 data_time: 0.0063 memory: 1827 loss: 0.4331 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4331 2022/12/25 16:12:30 - mmengine - INFO - Epoch(train) [3][ 500/1567] lr: 9.4908e-02 eta: 0:30:03 time: 0.0834 data_time: 0.0064 memory: 1827 loss: 0.3604 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.3604 2022/12/25 16:12:39 - mmengine - INFO - Epoch(train) [3][ 600/1567] lr: 9.4629e-02 eta: 0:29:54 time: 0.0829 data_time: 0.0064 memory: 1827 loss: 0.4494 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.4494 2022/12/25 16:12:47 - mmengine - INFO - Epoch(train) [3][ 700/1567] lr: 9.4343e-02 eta: 0:29:45 time: 0.0837 data_time: 0.0064 memory: 1827 loss: 0.4285 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.4285 2022/12/25 16:12:55 - mmengine - INFO - Epoch(train) [3][ 800/1567] lr: 9.4050e-02 eta: 0:29:38 time: 0.0837 data_time: 0.0063 memory: 1827 loss: 0.4378 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.4378 2022/12/25 16:13:01 - mmengine - INFO - Exp name: stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221225_160636 2022/12/25 16:13:04 - mmengine - INFO - Epoch(train) [3][ 900/1567] lr: 9.3750e-02 eta: 0:29:29 time: 0.0877 data_time: 0.0090 memory: 1827 loss: 0.3945 top1_acc: 0.6250 top5_acc: 1.0000 loss_cls: 0.3945 2022/12/25 16:13:12 - mmengine - INFO - Epoch(train) [3][1000/1567] lr: 9.3444e-02 eta: 0:29:20 time: 0.0825 data_time: 0.0064 memory: 1827 loss: 0.3841 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.3841 2022/12/25 16:13:21 - mmengine - INFO - Epoch(train) [3][1100/1567] lr: 9.3130e-02 eta: 0:29:13 time: 0.0871 data_time: 0.0064 memory: 1827 loss: 0.4849 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4849 2022/12/25 16:13:29 - mmengine - INFO - Epoch(train) [3][1200/1567] lr: 9.2810e-02 eta: 0:29:04 time: 0.0833 data_time: 0.0063 memory: 1827 loss: 0.3695 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.3695 2022/12/25 16:13:38 - mmengine - INFO - Epoch(train) [3][1300/1567] lr: 9.2483e-02 eta: 0:28:56 time: 0.0830 data_time: 0.0064 memory: 1827 loss: 0.4313 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.4313 2022/12/25 16:13:46 - mmengine - INFO - Epoch(train) [3][1400/1567] lr: 9.2149e-02 eta: 0:28:47 time: 0.0832 data_time: 0.0063 memory: 1827 loss: 0.3796 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3796 2022/12/25 16:13:54 - mmengine - INFO - Epoch(train) [3][1500/1567] lr: 9.1809e-02 eta: 0:28:38 time: 0.0829 data_time: 0.0063 memory: 1827 loss: 0.4378 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4378 2022/12/25 16:14:00 - mmengine - INFO - Exp name: stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221225_160636 2022/12/25 16:14:00 - mmengine - INFO - Epoch(train) [3][1567/1567] lr: 9.1577e-02 eta: 0:28:32 time: 0.0824 data_time: 0.0062 memory: 1827 loss: 0.5408 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.5408 2022/12/25 16:14:00 - mmengine - INFO - Saving checkpoint at 3 epochs 2022/12/25 16:14:03 - mmengine - INFO - Epoch(val) [3][100/129] eta: 0:00:00 time: 0.0279 data_time: 0.0062 memory: 263 2022/12/25 16:14:04 - mmengine - INFO - Epoch(val) [3][129/129] acc/top1: 0.6532 acc/top5: 0.9455 acc/mean1: 0.6532 2022/12/25 16:14:04 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_2.pth is removed 2022/12/25 16:14:04 - mmengine - INFO - The best checkpoint with 0.6532 acc/top1 at 3 epoch is saved to best_acc/top1_epoch_3.pth. 2022/12/25 16:14:13 - mmengine - INFO - Epoch(train) [4][ 100/1567] lr: 9.1226e-02 eta: 0:28:24 time: 0.0856 data_time: 0.0064 memory: 1827 loss: 0.4029 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4029 2022/12/25 16:14:21 - mmengine - INFO - Epoch(train) [4][ 200/1567] lr: 9.0868e-02 eta: 0:28:16 time: 0.0864 data_time: 0.0066 memory: 1827 loss: 0.4517 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.4517 2022/12/25 16:14:30 - mmengine - INFO - Exp name: stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221225_160636 2022/12/25 16:14:30 - mmengine - INFO - Epoch(train) [4][ 300/1567] lr: 9.0504e-02 eta: 0:28:09 time: 0.0868 data_time: 0.0064 memory: 1827 loss: 0.3681 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3681 2022/12/25 16:14:39 - mmengine - INFO - Epoch(train) [4][ 400/1567] lr: 9.0133e-02 eta: 0:28:02 time: 0.0866 data_time: 0.0064 memory: 1827 loss: 0.4520 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 0.4520 2022/12/25 16:14:47 - mmengine - INFO - Epoch(train) [4][ 500/1567] lr: 8.9756e-02 eta: 0:27:53 time: 0.0835 data_time: 0.0069 memory: 1827 loss: 0.3698 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.3698 2022/12/25 16:14:56 - mmengine - INFO - Epoch(train) [4][ 600/1567] lr: 8.9373e-02 eta: 0:27:45 time: 0.0839 data_time: 0.0063 memory: 1827 loss: 0.4094 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4094 2022/12/25 16:15:04 - mmengine - INFO - Epoch(train) [4][ 700/1567] lr: 8.8984e-02 eta: 0:27:36 time: 0.0839 data_time: 0.0067 memory: 1827 loss: 0.3497 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3497 2022/12/25 16:15:12 - mmengine - INFO - Epoch(train) [4][ 800/1567] lr: 8.8589e-02 eta: 0:27:28 time: 0.0828 data_time: 0.0062 memory: 1827 loss: 0.3603 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.3603 2022/12/25 16:15:21 - mmengine - INFO - Epoch(train) [4][ 900/1567] lr: 8.8187e-02 eta: 0:27:19 time: 0.0851 data_time: 0.0065 memory: 1827 loss: 0.3607 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3607 2022/12/25 16:15:29 - mmengine - INFO - Epoch(train) [4][1000/1567] lr: 8.7780e-02 eta: 0:27:10 time: 0.0816 data_time: 0.0064 memory: 1827 loss: 0.3840 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3840 2022/12/25 16:15:37 - mmengine - INFO - Epoch(train) [4][1100/1567] lr: 8.7367e-02 eta: 0:27:02 time: 0.0815 data_time: 0.0063 memory: 1827 loss: 0.3235 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.3235 2022/12/25 16:15:46 - mmengine - INFO - Epoch(train) [4][1200/1567] lr: 8.6947e-02 eta: 0:26:54 time: 0.0876 data_time: 0.0071 memory: 1827 loss: 0.2963 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.2963 2022/12/25 16:15:54 - mmengine - INFO - Exp name: stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221225_160636 2022/12/25 16:15:54 - mmengine - INFO - Epoch(train) [4][1300/1567] lr: 8.6522e-02 eta: 0:26:45 time: 0.0828 data_time: 0.0063 memory: 1827 loss: 0.3961 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3961 2022/12/25 16:16:03 - mmengine - INFO - Epoch(train) [4][1400/1567] lr: 8.6092e-02 eta: 0:26:37 time: 0.0838 data_time: 0.0064 memory: 1827 loss: 0.3388 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3388 2022/12/25 16:16:11 - mmengine - INFO - Epoch(train) [4][1500/1567] lr: 8.5655e-02 eta: 0:26:29 time: 0.0851 data_time: 0.0063 memory: 1827 loss: 0.3407 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3407 2022/12/25 16:16:17 - mmengine - INFO - Exp name: stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221225_160636 2022/12/25 16:16:17 - mmengine - INFO - Epoch(train) [4][1567/1567] lr: 8.5360e-02 eta: 0:26:23 time: 0.0819 data_time: 0.0062 memory: 1827 loss: 0.5618 top1_acc: 0.0000 top5_acc: 1.0000 loss_cls: 0.5618 2022/12/25 16:16:17 - mmengine - INFO - Saving checkpoint at 4 epochs 2022/12/25 16:16:20 - mmengine - INFO - Epoch(val) [4][100/129] eta: 0:00:00 time: 0.0276 data_time: 0.0065 memory: 263 2022/12/25 16:16:21 - mmengine - INFO - Epoch(val) [4][129/129] acc/top1: 0.5903 acc/top5: 0.9166 acc/mean1: 0.5903 2022/12/25 16:16:29 - mmengine - INFO - Epoch(train) [5][ 100/1567] lr: 8.4914e-02 eta: 0:26:15 time: 0.0838 data_time: 0.0071 memory: 1827 loss: 0.3479 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3479 2022/12/25 16:16:38 - mmengine - INFO - Epoch(train) [5][ 200/1567] lr: 8.4463e-02 eta: 0:26:06 time: 0.0822 data_time: 0.0066 memory: 1827 loss: 0.3625 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3625 2022/12/25 16:16:46 - mmengine - INFO - Epoch(train) [5][ 300/1567] lr: 8.4006e-02 eta: 0:25:58 time: 0.0839 data_time: 0.0064 memory: 1827 loss: 0.3717 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3717 2022/12/25 16:16:55 - mmengine - INFO - Epoch(train) [5][ 400/1567] lr: 8.3544e-02 eta: 0:25:49 time: 0.0824 data_time: 0.0071 memory: 1827 loss: 0.3057 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.3057 2022/12/25 16:17:03 - mmengine - INFO - Epoch(train) [5][ 500/1567] lr: 8.3077e-02 eta: 0:25:40 time: 0.0833 data_time: 0.0064 memory: 1827 loss: 0.2962 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2962 2022/12/25 16:17:12 - mmengine - INFO - Epoch(train) [5][ 600/1567] lr: 8.2605e-02 eta: 0:25:32 time: 0.0860 data_time: 0.0064 memory: 1827 loss: 0.3586 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.3586 2022/12/25 16:17:20 - mmengine - INFO - Epoch(train) [5][ 700/1567] lr: 8.2127e-02 eta: 0:25:24 time: 0.0870 data_time: 0.0064 memory: 1827 loss: 0.3600 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3600 2022/12/25 16:17:23 - mmengine - INFO - Exp name: stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221225_160636 2022/12/25 16:17:29 - mmengine - INFO - Epoch(train) [5][ 800/1567] lr: 8.1645e-02 eta: 0:25:17 time: 0.0856 data_time: 0.0064 memory: 1827 loss: 0.2799 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2799 2022/12/25 16:17:37 - mmengine - INFO - Epoch(train) [5][ 900/1567] lr: 8.1157e-02 eta: 0:25:09 time: 0.0873 data_time: 0.0066 memory: 1827 loss: 0.3077 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3077 2022/12/25 16:17:46 - mmengine - INFO - Epoch(train) [5][1000/1567] lr: 8.0665e-02 eta: 0:25:01 time: 0.0856 data_time: 0.0063 memory: 1827 loss: 0.3499 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3499 2022/12/25 16:17:55 - mmengine - INFO - Epoch(train) [5][1100/1567] lr: 8.0167e-02 eta: 0:24:53 time: 0.0862 data_time: 0.0064 memory: 1827 loss: 0.3424 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3424 2022/12/25 16:18:03 - mmengine - INFO - Epoch(train) [5][1200/1567] lr: 7.9665e-02 eta: 0:24:45 time: 0.0864 data_time: 0.0064 memory: 1827 loss: 0.3298 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3298 2022/12/25 16:18:12 - mmengine - INFO - Epoch(train) [5][1300/1567] lr: 7.9159e-02 eta: 0:24:36 time: 0.0842 data_time: 0.0075 memory: 1827 loss: 0.3665 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3665 2022/12/25 16:18:20 - mmengine - INFO - Epoch(train) [5][1400/1567] lr: 7.8647e-02 eta: 0:24:28 time: 0.0857 data_time: 0.0066 memory: 1827 loss: 0.3160 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3160 2022/12/25 16:18:28 - mmengine - INFO - Epoch(train) [5][1500/1567] lr: 7.8132e-02 eta: 0:24:19 time: 0.0826 data_time: 0.0065 memory: 1827 loss: 0.3286 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.3286 2022/12/25 16:18:34 - mmengine - INFO - Exp name: stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221225_160636 2022/12/25 16:18:34 - mmengine - INFO - Epoch(train) [5][1567/1567] lr: 7.7784e-02 eta: 0:24:13 time: 0.0829 data_time: 0.0062 memory: 1827 loss: 0.4756 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.4756 2022/12/25 16:18:34 - mmengine - INFO - Saving checkpoint at 5 epochs 2022/12/25 16:18:37 - mmengine - INFO - Epoch(val) [5][100/129] eta: 0:00:00 time: 0.0254 data_time: 0.0058 memory: 263 2022/12/25 16:18:38 - mmengine - INFO - Epoch(val) [5][129/129] acc/top1: 0.7568 acc/top5: 0.9621 acc/mean1: 0.7570 2022/12/25 16:18:38 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_3.pth is removed 2022/12/25 16:18:38 - mmengine - INFO - The best checkpoint with 0.7568 acc/top1 at 5 epoch is saved to best_acc/top1_epoch_5.pth. 2022/12/25 16:18:47 - mmengine - INFO - Epoch(train) [6][ 100/1567] lr: 7.7261e-02 eta: 0:24:05 time: 0.0833 data_time: 0.0064 memory: 1827 loss: 0.3204 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3204 2022/12/25 16:18:52 - mmengine - INFO - Exp name: stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221225_160636 2022/12/25 16:18:55 - mmengine - INFO - Epoch(train) [6][ 200/1567] lr: 7.6733e-02 eta: 0:23:56 time: 0.0821 data_time: 0.0064 memory: 1827 loss: 0.3156 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3156 2022/12/25 16:19:03 - mmengine - INFO - Epoch(train) [6][ 300/1567] lr: 7.6202e-02 eta: 0:23:47 time: 0.0822 data_time: 0.0064 memory: 1827 loss: 0.2933 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2933 2022/12/25 16:19:12 - mmengine - INFO - Epoch(train) [6][ 400/1567] lr: 7.5666e-02 eta: 0:23:38 time: 0.0824 data_time: 0.0063 memory: 1827 loss: 0.2978 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.2978 2022/12/25 16:19:20 - mmengine - INFO - Epoch(train) [6][ 500/1567] lr: 7.5126e-02 eta: 0:23:29 time: 0.0841 data_time: 0.0064 memory: 1827 loss: 0.3181 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3181 2022/12/25 16:19:28 - mmengine - INFO - Epoch(train) [6][ 600/1567] lr: 7.4583e-02 eta: 0:23:21 time: 0.0842 data_time: 0.0063 memory: 1827 loss: 0.3201 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.3201 2022/12/25 16:19:37 - mmengine - INFO - Epoch(train) [6][ 700/1567] lr: 7.4035e-02 eta: 0:23:12 time: 0.0875 data_time: 0.0064 memory: 1827 loss: 0.2460 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2460 2022/12/25 16:19:45 - mmengine - INFO - Epoch(train) [6][ 800/1567] lr: 7.3484e-02 eta: 0:23:04 time: 0.0830 data_time: 0.0064 memory: 1827 loss: 0.3528 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.3528 2022/12/25 16:19:53 - mmengine - INFO - Epoch(train) [6][ 900/1567] lr: 7.2929e-02 eta: 0:22:55 time: 0.0826 data_time: 0.0064 memory: 1827 loss: 0.3613 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3613 2022/12/25 16:20:02 - mmengine - INFO - Epoch(train) [6][1000/1567] lr: 7.2371e-02 eta: 0:22:47 time: 0.0862 data_time: 0.0063 memory: 1827 loss: 0.2790 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2790 2022/12/25 16:20:10 - mmengine - INFO - Epoch(train) [6][1100/1567] lr: 7.1809e-02 eta: 0:22:38 time: 0.0841 data_time: 0.0064 memory: 1827 loss: 0.3028 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 0.3028 2022/12/25 16:20:15 - mmengine - INFO - Exp name: stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221225_160636 2022/12/25 16:20:18 - mmengine - INFO - Epoch(train) [6][1200/1567] lr: 7.1243e-02 eta: 0:22:30 time: 0.0818 data_time: 0.0064 memory: 1827 loss: 0.2865 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2865 2022/12/25 16:20:27 - mmengine - INFO - Epoch(train) [6][1300/1567] lr: 7.0674e-02 eta: 0:22:21 time: 0.0825 data_time: 0.0064 memory: 1827 loss: 0.2217 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2217 2022/12/25 16:20:35 - mmengine - INFO - Epoch(train) [6][1400/1567] lr: 7.0102e-02 eta: 0:22:12 time: 0.0832 data_time: 0.0066 memory: 1827 loss: 0.2651 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.2651 2022/12/25 16:20:43 - mmengine - INFO - Epoch(train) [6][1500/1567] lr: 6.9527e-02 eta: 0:22:04 time: 0.0821 data_time: 0.0064 memory: 1827 loss: 0.3075 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3075 2022/12/25 16:20:49 - mmengine - INFO - Exp name: stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221225_160636 2022/12/25 16:20:49 - mmengine - INFO - Epoch(train) [6][1567/1567] lr: 6.9140e-02 eta: 0:21:58 time: 0.0813 data_time: 0.0062 memory: 1827 loss: 0.4604 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.4604 2022/12/25 16:20:49 - mmengine - INFO - Saving checkpoint at 6 epochs 2022/12/25 16:20:52 - mmengine - INFO - Epoch(val) [6][100/129] eta: 0:00:00 time: 0.0254 data_time: 0.0058 memory: 263 2022/12/25 16:20:53 - mmengine - INFO - Epoch(val) [6][129/129] acc/top1: 0.7394 acc/top5: 0.9652 acc/mean1: 0.7394 2022/12/25 16:21:01 - mmengine - INFO - Epoch(train) [7][ 100/1567] lr: 6.8560e-02 eta: 0:21:50 time: 0.0857 data_time: 0.0063 memory: 1827 loss: 0.2569 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2569 2022/12/25 16:21:10 - mmengine - INFO - Epoch(train) [7][ 200/1567] lr: 6.7976e-02 eta: 0:21:42 time: 0.0860 data_time: 0.0064 memory: 1827 loss: 0.2842 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2842 2022/12/25 16:21:18 - mmengine - INFO - Epoch(train) [7][ 300/1567] lr: 6.7390e-02 eta: 0:21:33 time: 0.0846 data_time: 0.0064 memory: 1827 loss: 0.2939 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2939 2022/12/25 16:21:27 - mmengine - INFO - Epoch(train) [7][ 400/1567] lr: 6.6802e-02 eta: 0:21:25 time: 0.0825 data_time: 0.0065 memory: 1827 loss: 0.3148 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 0.3148 2022/12/25 16:21:35 - mmengine - INFO - Epoch(train) [7][ 500/1567] lr: 6.6210e-02 eta: 0:21:16 time: 0.0821 data_time: 0.0064 memory: 1827 loss: 0.3429 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3429 2022/12/25 16:21:43 - mmengine - INFO - Exp name: stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221225_160636 2022/12/25 16:21:43 - mmengine - INFO - Epoch(train) [7][ 600/1567] lr: 6.5616e-02 eta: 0:21:07 time: 0.0819 data_time: 0.0064 memory: 1827 loss: 0.2355 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2355 2022/12/25 16:21:51 - mmengine - INFO - Epoch(train) [7][ 700/1567] lr: 6.5020e-02 eta: 0:20:59 time: 0.0838 data_time: 0.0069 memory: 1827 loss: 0.3017 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3017 2022/12/25 16:22:00 - mmengine - INFO - Epoch(train) [7][ 800/1567] lr: 6.4421e-02 eta: 0:20:50 time: 0.0859 data_time: 0.0064 memory: 1827 loss: 0.2207 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2207 2022/12/25 16:22:08 - mmengine - INFO - Epoch(train) [7][ 900/1567] lr: 6.3820e-02 eta: 0:20:42 time: 0.0826 data_time: 0.0064 memory: 1827 loss: 0.2284 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2284 2022/12/25 16:22:16 - mmengine - INFO - Epoch(train) [7][1000/1567] lr: 6.3217e-02 eta: 0:20:33 time: 0.0827 data_time: 0.0063 memory: 1827 loss: 0.3055 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.3055 2022/12/25 16:22:25 - mmengine - INFO - Epoch(train) [7][1100/1567] lr: 6.2612e-02 eta: 0:20:25 time: 0.0829 data_time: 0.0067 memory: 1827 loss: 0.2428 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2428 2022/12/25 16:22:33 - mmengine - INFO - Epoch(train) [7][1200/1567] lr: 6.2005e-02 eta: 0:20:16 time: 0.0820 data_time: 0.0064 memory: 1827 loss: 0.1882 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1882 2022/12/25 16:22:41 - mmengine - INFO - Epoch(train) [7][1300/1567] lr: 6.1396e-02 eta: 0:20:07 time: 0.0836 data_time: 0.0063 memory: 1827 loss: 0.2300 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2300 2022/12/25 16:22:50 - mmengine - INFO - Epoch(train) [7][1400/1567] lr: 6.0785e-02 eta: 0:19:59 time: 0.0836 data_time: 0.0064 memory: 1827 loss: 0.2449 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2449 2022/12/25 16:22:58 - mmengine - INFO - Epoch(train) [7][1500/1567] lr: 6.0172e-02 eta: 0:19:51 time: 0.0853 data_time: 0.0064 memory: 1827 loss: 0.1686 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1686 2022/12/25 16:23:04 - mmengine - INFO - Exp name: stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221225_160636 2022/12/25 16:23:04 - mmengine - INFO - Epoch(train) [7][1567/1567] lr: 5.9761e-02 eta: 0:19:45 time: 0.0850 data_time: 0.0061 memory: 1827 loss: 0.4578 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.4578 2022/12/25 16:23:04 - mmengine - INFO - Saving checkpoint at 7 epochs 2022/12/25 16:23:07 - mmengine - INFO - Epoch(val) [7][100/129] eta: 0:00:00 time: 0.0273 data_time: 0.0060 memory: 263 2022/12/25 16:23:08 - mmengine - INFO - Epoch(val) [7][129/129] acc/top1: 0.7819 acc/top5: 0.9714 acc/mean1: 0.7819 2022/12/25 16:23:08 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_5.pth is removed 2022/12/25 16:23:08 - mmengine - INFO - The best checkpoint with 0.7819 acc/top1 at 7 epoch is saved to best_acc/top1_epoch_7.pth. 2022/12/25 16:23:11 - mmengine - INFO - Exp name: stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221225_160636 2022/12/25 16:23:17 - mmengine - INFO - Epoch(train) [8][ 100/1567] lr: 5.9145e-02 eta: 0:19:37 time: 0.0833 data_time: 0.0065 memory: 1827 loss: 0.2345 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2345 2022/12/25 16:23:25 - mmengine - INFO - Epoch(train) [8][ 200/1567] lr: 5.8529e-02 eta: 0:19:28 time: 0.0817 data_time: 0.0065 memory: 1827 loss: 0.1872 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1872 2022/12/25 16:23:33 - mmengine - INFO - Epoch(train) [8][ 300/1567] lr: 5.7911e-02 eta: 0:19:19 time: 0.0817 data_time: 0.0064 memory: 1827 loss: 0.2432 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2432 2022/12/25 16:23:41 - mmengine - INFO - Epoch(train) [8][ 400/1567] lr: 5.7292e-02 eta: 0:19:11 time: 0.0825 data_time: 0.0063 memory: 1827 loss: 0.2472 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2472 2022/12/25 16:23:50 - mmengine - INFO - Epoch(train) [8][ 500/1567] lr: 5.6671e-02 eta: 0:19:02 time: 0.0851 data_time: 0.0064 memory: 1827 loss: 0.2323 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2323 2022/12/25 16:23:58 - mmengine - INFO - Epoch(train) [8][ 600/1567] lr: 5.6050e-02 eta: 0:18:54 time: 0.0828 data_time: 0.0064 memory: 1827 loss: 0.2462 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2462 2022/12/25 16:24:06 - mmengine - INFO - Epoch(train) [8][ 700/1567] lr: 5.5427e-02 eta: 0:18:45 time: 0.0846 data_time: 0.0066 memory: 1827 loss: 0.2358 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.2358 2022/12/25 16:24:15 - mmengine - INFO - Epoch(train) [8][ 800/1567] lr: 5.4804e-02 eta: 0:18:37 time: 0.0847 data_time: 0.0064 memory: 1827 loss: 0.2094 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2094 2022/12/25 16:24:23 - mmengine - INFO - Epoch(train) [8][ 900/1567] lr: 5.4180e-02 eta: 0:18:29 time: 0.0829 data_time: 0.0065 memory: 1827 loss: 0.2681 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.2681 2022/12/25 16:24:32 - mmengine - INFO - Epoch(train) [8][1000/1567] lr: 5.3556e-02 eta: 0:18:20 time: 0.0827 data_time: 0.0069 memory: 1827 loss: 0.1695 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.1695 2022/12/25 16:24:34 - mmengine - INFO - Exp name: stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221225_160636 2022/12/25 16:24:40 - mmengine - INFO - Epoch(train) [8][1100/1567] lr: 5.2930e-02 eta: 0:18:12 time: 0.0830 data_time: 0.0064 memory: 1827 loss: 0.1930 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1930 2022/12/25 16:24:48 - mmengine - INFO - Epoch(train) [8][1200/1567] lr: 5.2305e-02 eta: 0:18:03 time: 0.0828 data_time: 0.0064 memory: 1827 loss: 0.2399 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2399 2022/12/25 16:24:57 - mmengine - INFO - Epoch(train) [8][1300/1567] lr: 5.1679e-02 eta: 0:17:55 time: 0.0825 data_time: 0.0064 memory: 1827 loss: 0.2187 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2187 2022/12/25 16:25:05 - mmengine - INFO - Epoch(train) [8][1400/1567] lr: 5.1052e-02 eta: 0:17:46 time: 0.0841 data_time: 0.0071 memory: 1827 loss: 0.2764 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.2764 2022/12/25 16:25:13 - mmengine - INFO - Epoch(train) [8][1500/1567] lr: 5.0426e-02 eta: 0:17:38 time: 0.0824 data_time: 0.0064 memory: 1827 loss: 0.1834 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.1834 2022/12/25 16:25:19 - mmengine - INFO - Exp name: stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221225_160636 2022/12/25 16:25:19 - mmengine - INFO - Epoch(train) [8][1567/1567] lr: 5.0006e-02 eta: 0:17:32 time: 0.0822 data_time: 0.0061 memory: 1827 loss: 0.3704 top1_acc: 0.0000 top5_acc: 1.0000 loss_cls: 0.3704 2022/12/25 16:25:19 - mmengine - INFO - Saving checkpoint at 8 epochs 2022/12/25 16:25:22 - mmengine - INFO - Epoch(val) [8][100/129] eta: 0:00:00 time: 0.0257 data_time: 0.0058 memory: 263 2022/12/25 16:25:23 - mmengine - INFO - Epoch(val) [8][129/129] acc/top1: 0.7983 acc/top5: 0.9717 acc/mean1: 0.7983 2022/12/25 16:25:23 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_7.pth is removed 2022/12/25 16:25:23 - mmengine - INFO - The best checkpoint with 0.7983 acc/top1 at 8 epoch is saved to best_acc/top1_epoch_8.pth. 2022/12/25 16:25:32 - mmengine - INFO - Epoch(train) [9][ 100/1567] lr: 4.9380e-02 eta: 0:17:24 time: 0.0818 data_time: 0.0063 memory: 1827 loss: 0.2099 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2099 2022/12/25 16:25:40 - mmengine - INFO - Epoch(train) [9][ 200/1567] lr: 4.8753e-02 eta: 0:17:15 time: 0.0817 data_time: 0.0066 memory: 1827 loss: 0.2107 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2107 2022/12/25 16:25:48 - mmengine - INFO - Epoch(train) [9][ 300/1567] lr: 4.8127e-02 eta: 0:17:07 time: 0.0822 data_time: 0.0064 memory: 1827 loss: 0.1884 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1884 2022/12/25 16:25:56 - mmengine - INFO - Epoch(train) [9][ 400/1567] lr: 4.7501e-02 eta: 0:16:58 time: 0.0824 data_time: 0.0064 memory: 1827 loss: 0.2008 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2008 2022/12/25 16:26:02 - mmengine - INFO - Exp name: stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221225_160636 2022/12/25 16:26:05 - mmengine - INFO - Epoch(train) [9][ 500/1567] lr: 4.6876e-02 eta: 0:16:50 time: 0.0824 data_time: 0.0066 memory: 1827 loss: 0.1943 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1943 2022/12/25 16:26:13 - mmengine - INFO - Epoch(train) [9][ 600/1567] lr: 4.6251e-02 eta: 0:16:41 time: 0.0823 data_time: 0.0065 memory: 1827 loss: 0.1416 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1416 2022/12/25 16:26:22 - mmengine - INFO - Epoch(train) [9][ 700/1567] lr: 4.5626e-02 eta: 0:16:33 time: 0.0837 data_time: 0.0065 memory: 1827 loss: 0.1770 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1770 2022/12/25 16:26:30 - mmengine - INFO - Epoch(train) [9][ 800/1567] lr: 4.5003e-02 eta: 0:16:24 time: 0.0824 data_time: 0.0065 memory: 1827 loss: 0.2385 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2385 2022/12/25 16:26:38 - mmengine - INFO - Epoch(train) [9][ 900/1567] lr: 4.4380e-02 eta: 0:16:16 time: 0.0829 data_time: 0.0064 memory: 1827 loss: 0.1936 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1936 2022/12/25 16:26:46 - mmengine - INFO - Epoch(train) [9][1000/1567] lr: 4.3757e-02 eta: 0:16:08 time: 0.0827 data_time: 0.0064 memory: 1827 loss: 0.1615 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1615 2022/12/25 16:26:55 - mmengine - INFO - Epoch(train) [9][1100/1567] lr: 4.3136e-02 eta: 0:15:59 time: 0.0833 data_time: 0.0065 memory: 1827 loss: 0.2126 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2126 2022/12/25 16:27:03 - mmengine - INFO - Epoch(train) [9][1200/1567] lr: 4.2516e-02 eta: 0:15:51 time: 0.0843 data_time: 0.0065 memory: 1827 loss: 0.2080 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2080 2022/12/25 16:27:12 - mmengine - INFO - Epoch(train) [9][1300/1567] lr: 4.1897e-02 eta: 0:15:42 time: 0.0849 data_time: 0.0066 memory: 1827 loss: 0.2286 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2286 2022/12/25 16:27:20 - mmengine - INFO - Epoch(train) [9][1400/1567] lr: 4.1280e-02 eta: 0:15:34 time: 0.0848 data_time: 0.0071 memory: 1827 loss: 0.1950 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1950 2022/12/25 16:27:26 - mmengine - INFO - Exp name: stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221225_160636 2022/12/25 16:27:29 - mmengine - INFO - Epoch(train) [9][1500/1567] lr: 4.0664e-02 eta: 0:15:26 time: 0.0830 data_time: 0.0065 memory: 1827 loss: 0.1959 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1959 2022/12/25 16:27:34 - mmengine - INFO - Exp name: stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221225_160636 2022/12/25 16:27:34 - mmengine - INFO - Epoch(train) [9][1567/1567] lr: 4.0252e-02 eta: 0:15:20 time: 0.0830 data_time: 0.0063 memory: 1827 loss: 0.3072 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3072 2022/12/25 16:27:34 - mmengine - INFO - Saving checkpoint at 9 epochs 2022/12/25 16:27:38 - mmengine - INFO - Epoch(val) [9][100/129] eta: 0:00:00 time: 0.0262 data_time: 0.0059 memory: 263 2022/12/25 16:27:39 - mmengine - INFO - Epoch(val) [9][129/129] acc/top1: 0.7581 acc/top5: 0.9683 acc/mean1: 0.7580 2022/12/25 16:27:47 - mmengine - INFO - Epoch(train) [10][ 100/1567] lr: 3.9638e-02 eta: 0:15:12 time: 0.0818 data_time: 0.0065 memory: 1827 loss: 0.1755 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1755 2022/12/25 16:27:55 - mmengine - INFO - Epoch(train) [10][ 200/1567] lr: 3.9026e-02 eta: 0:15:03 time: 0.0836 data_time: 0.0064 memory: 1827 loss: 0.1831 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1831 2022/12/25 16:28:04 - mmengine - INFO - Epoch(train) [10][ 300/1567] lr: 3.8415e-02 eta: 0:14:55 time: 0.0832 data_time: 0.0064 memory: 1827 loss: 0.1579 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1579 2022/12/25 16:28:12 - mmengine - INFO - Epoch(train) [10][ 400/1567] lr: 3.7807e-02 eta: 0:14:46 time: 0.0840 data_time: 0.0067 memory: 1827 loss: 0.1632 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1632 2022/12/25 16:28:20 - mmengine - INFO - Epoch(train) [10][ 500/1567] lr: 3.7200e-02 eta: 0:14:38 time: 0.0863 data_time: 0.0074 memory: 1827 loss: 0.1430 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1430 2022/12/25 16:28:29 - mmengine - INFO - Epoch(train) [10][ 600/1567] lr: 3.6596e-02 eta: 0:14:30 time: 0.0835 data_time: 0.0064 memory: 1827 loss: 0.2204 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2204 2022/12/25 16:28:37 - mmengine - INFO - Epoch(train) [10][ 700/1567] lr: 3.5993e-02 eta: 0:14:21 time: 0.0874 data_time: 0.0064 memory: 1827 loss: 0.1911 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1911 2022/12/25 16:28:46 - mmengine - INFO - Epoch(train) [10][ 800/1567] lr: 3.5393e-02 eta: 0:14:13 time: 0.0871 data_time: 0.0065 memory: 1827 loss: 0.1378 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1378 2022/12/25 16:28:54 - mmengine - INFO - Exp name: stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221225_160636 2022/12/25 16:28:54 - mmengine - INFO - Epoch(train) [10][ 900/1567] lr: 3.4795e-02 eta: 0:14:05 time: 0.0828 data_time: 0.0064 memory: 1827 loss: 0.1208 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1208 2022/12/25 16:29:03 - mmengine - INFO - Epoch(train) [10][1000/1567] lr: 3.4199e-02 eta: 0:13:56 time: 0.0832 data_time: 0.0063 memory: 1827 loss: 0.1576 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1576 2022/12/25 16:29:11 - mmengine - INFO - Epoch(train) [10][1100/1567] lr: 3.3606e-02 eta: 0:13:48 time: 0.0824 data_time: 0.0063 memory: 1827 loss: 0.1188 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1188 2022/12/25 16:29:19 - mmengine - INFO - Epoch(train) [10][1200/1567] lr: 3.3015e-02 eta: 0:13:40 time: 0.0825 data_time: 0.0064 memory: 1827 loss: 0.1208 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1208 2022/12/25 16:29:28 - mmengine - INFO - Epoch(train) [10][1300/1567] lr: 3.2428e-02 eta: 0:13:31 time: 0.0823 data_time: 0.0063 memory: 1827 loss: 0.1441 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1441 2022/12/25 16:29:36 - mmengine - INFO - Epoch(train) [10][1400/1567] lr: 3.1842e-02 eta: 0:13:23 time: 0.0839 data_time: 0.0064 memory: 1827 loss: 0.1424 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1424 2022/12/25 16:29:44 - mmengine - INFO - Epoch(train) [10][1500/1567] lr: 3.1260e-02 eta: 0:13:14 time: 0.0828 data_time: 0.0064 memory: 1827 loss: 0.1220 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1220 2022/12/25 16:29:50 - mmengine - INFO - Exp name: stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221225_160636 2022/12/25 16:29:50 - mmengine - INFO - Epoch(train) [10][1567/1567] lr: 3.0872e-02 eta: 0:13:08 time: 0.0826 data_time: 0.0069 memory: 1827 loss: 0.2441 top1_acc: 0.0000 top5_acc: 1.0000 loss_cls: 0.2441 2022/12/25 16:29:50 - mmengine - INFO - Saving checkpoint at 10 epochs 2022/12/25 16:29:53 - mmengine - INFO - Epoch(val) [10][100/129] eta: 0:00:00 time: 0.0262 data_time: 0.0060 memory: 263 2022/12/25 16:29:54 - mmengine - INFO - Epoch(val) [10][129/129] acc/top1: 0.8344 acc/top5: 0.9807 acc/mean1: 0.8343 2022/12/25 16:29:54 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_8.pth is removed 2022/12/25 16:29:54 - mmengine - INFO - The best checkpoint with 0.8344 acc/top1 at 10 epoch is saved to best_acc/top1_epoch_10.pth. 2022/12/25 16:30:03 - mmengine - INFO - Epoch(train) [11][ 100/1567] lr: 3.0294e-02 eta: 0:13:00 time: 0.0856 data_time: 0.0064 memory: 1827 loss: 0.1078 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1078 2022/12/25 16:30:11 - mmengine - INFO - Epoch(train) [11][ 200/1567] lr: 2.9720e-02 eta: 0:12:52 time: 0.0824 data_time: 0.0073 memory: 1827 loss: 0.1477 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1477 2022/12/25 16:30:20 - mmengine - INFO - Epoch(train) [11][ 300/1567] lr: 2.9149e-02 eta: 0:12:43 time: 0.0852 data_time: 0.0068 memory: 1827 loss: 0.0991 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0991 2022/12/25 16:30:22 - mmengine - INFO - Exp name: stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221225_160636 2022/12/25 16:30:28 - mmengine - INFO - Epoch(train) [11][ 400/1567] lr: 2.8581e-02 eta: 0:12:35 time: 0.0836 data_time: 0.0067 memory: 1827 loss: 0.1102 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1102 2022/12/25 16:30:36 - mmengine - INFO - Epoch(train) [11][ 500/1567] lr: 2.8017e-02 eta: 0:12:27 time: 0.0857 data_time: 0.0071 memory: 1827 loss: 0.1324 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1324 2022/12/25 16:30:45 - mmengine - INFO - Epoch(train) [11][ 600/1567] lr: 2.7456e-02 eta: 0:12:18 time: 0.0837 data_time: 0.0065 memory: 1827 loss: 0.0869 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0869 2022/12/25 16:30:53 - mmengine - INFO - Epoch(train) [11][ 700/1567] lr: 2.6898e-02 eta: 0:12:10 time: 0.0838 data_time: 0.0064 memory: 1827 loss: 0.1137 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1137 2022/12/25 16:31:01 - mmengine - INFO - Epoch(train) [11][ 800/1567] lr: 2.6345e-02 eta: 0:12:01 time: 0.0836 data_time: 0.0064 memory: 1827 loss: 0.1410 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1410 2022/12/25 16:31:10 - mmengine - INFO - Epoch(train) [11][ 900/1567] lr: 2.5794e-02 eta: 0:11:53 time: 0.0863 data_time: 0.0065 memory: 1827 loss: 0.0833 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0833 2022/12/25 16:31:19 - mmengine - INFO - Epoch(train) [11][1000/1567] lr: 2.5248e-02 eta: 0:11:45 time: 0.0860 data_time: 0.0064 memory: 1827 loss: 0.0925 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0925 2022/12/25 16:31:27 - mmengine - INFO - Epoch(train) [11][1100/1567] lr: 2.4706e-02 eta: 0:11:37 time: 0.0865 data_time: 0.0064 memory: 1827 loss: 0.1056 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1056 2022/12/25 16:31:36 - mmengine - INFO - Epoch(train) [11][1200/1567] lr: 2.4167e-02 eta: 0:11:28 time: 0.0857 data_time: 0.0071 memory: 1827 loss: 0.1078 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1078 2022/12/25 16:31:44 - mmengine - INFO - Epoch(train) [11][1300/1567] lr: 2.3633e-02 eta: 0:11:20 time: 0.0817 data_time: 0.0064 memory: 1827 loss: 0.0974 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.0974 2022/12/25 16:31:46 - mmengine - INFO - Exp name: stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221225_160636 2022/12/25 16:31:52 - mmengine - INFO - Epoch(train) [11][1400/1567] lr: 2.3103e-02 eta: 0:11:11 time: 0.0830 data_time: 0.0065 memory: 1827 loss: 0.1348 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.1348 2022/12/25 16:32:01 - mmengine - INFO - Epoch(train) [11][1500/1567] lr: 2.2577e-02 eta: 0:11:03 time: 0.0853 data_time: 0.0064 memory: 1827 loss: 0.0768 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0768 2022/12/25 16:32:06 - mmengine - INFO - Exp name: stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221225_160636 2022/12/25 16:32:06 - mmengine - INFO - Epoch(train) [11][1567/1567] lr: 2.2227e-02 eta: 0:10:57 time: 0.0839 data_time: 0.0063 memory: 1827 loss: 0.2148 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2148 2022/12/25 16:32:06 - mmengine - INFO - Saving checkpoint at 11 epochs 2022/12/25 16:32:10 - mmengine - INFO - Epoch(val) [11][100/129] eta: 0:00:00 time: 0.0299 data_time: 0.0066 memory: 263 2022/12/25 16:32:11 - mmengine - INFO - Epoch(val) [11][129/129] acc/top1: 0.8467 acc/top5: 0.9819 acc/mean1: 0.8466 2022/12/25 16:32:11 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_10.pth is removed 2022/12/25 16:32:11 - mmengine - INFO - The best checkpoint with 0.8467 acc/top1 at 11 epoch is saved to best_acc/top1_epoch_11.pth. 2022/12/25 16:32:19 - mmengine - INFO - Epoch(train) [12][ 100/1567] lr: 2.1708e-02 eta: 0:10:49 time: 0.0822 data_time: 0.0064 memory: 1827 loss: 0.0739 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0739 2022/12/25 16:32:28 - mmengine - INFO - Epoch(train) [12][ 200/1567] lr: 2.1194e-02 eta: 0:10:40 time: 0.0829 data_time: 0.0065 memory: 1827 loss: 0.0933 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0933 2022/12/25 16:32:36 - mmengine - INFO - Epoch(train) [12][ 300/1567] lr: 2.0684e-02 eta: 0:10:32 time: 0.0844 data_time: 0.0067 memory: 1827 loss: 0.0966 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0966 2022/12/25 16:32:44 - mmengine - INFO - Epoch(train) [12][ 400/1567] lr: 2.0179e-02 eta: 0:10:24 time: 0.0831 data_time: 0.0064 memory: 1827 loss: 0.0844 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0844 2022/12/25 16:32:53 - mmengine - INFO - Epoch(train) [12][ 500/1567] lr: 1.9678e-02 eta: 0:10:15 time: 0.0830 data_time: 0.0072 memory: 1827 loss: 0.0769 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0769 2022/12/25 16:33:01 - mmengine - INFO - Epoch(train) [12][ 600/1567] lr: 1.9182e-02 eta: 0:10:07 time: 0.0853 data_time: 0.0064 memory: 1827 loss: 0.0769 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0769 2022/12/25 16:33:10 - mmengine - INFO - Epoch(train) [12][ 700/1567] lr: 1.8691e-02 eta: 0:09:58 time: 0.0834 data_time: 0.0064 memory: 1827 loss: 0.0813 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0813 2022/12/25 16:33:15 - mmengine - INFO - Exp name: stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221225_160636 2022/12/25 16:33:18 - mmengine - INFO - Epoch(train) [12][ 800/1567] lr: 1.8205e-02 eta: 0:09:50 time: 0.0838 data_time: 0.0064 memory: 1827 loss: 0.0761 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0761 2022/12/25 16:33:27 - mmengine - INFO - Epoch(train) [12][ 900/1567] lr: 1.7724e-02 eta: 0:09:42 time: 0.0834 data_time: 0.0065 memory: 1827 loss: 0.0997 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0997 2022/12/25 16:33:35 - mmengine - INFO - Epoch(train) [12][1000/1567] lr: 1.7248e-02 eta: 0:09:33 time: 0.0852 data_time: 0.0064 memory: 1827 loss: 0.0822 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0822 2022/12/25 16:33:43 - mmengine - INFO - Epoch(train) [12][1100/1567] lr: 1.6778e-02 eta: 0:09:25 time: 0.0835 data_time: 0.0065 memory: 1827 loss: 0.0845 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0845 2022/12/25 16:33:52 - mmengine - INFO - Epoch(train) [12][1200/1567] lr: 1.6312e-02 eta: 0:09:16 time: 0.0835 data_time: 0.0069 memory: 1827 loss: 0.0728 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0728 2022/12/25 16:34:00 - mmengine - INFO - Epoch(train) [12][1300/1567] lr: 1.5852e-02 eta: 0:09:08 time: 0.0827 data_time: 0.0064 memory: 1827 loss: 0.0530 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0530 2022/12/25 16:34:08 - mmengine - INFO - Epoch(train) [12][1400/1567] lr: 1.5397e-02 eta: 0:09:00 time: 0.0846 data_time: 0.0064 memory: 1827 loss: 0.0963 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0963 2022/12/25 16:34:17 - mmengine - INFO - Epoch(train) [12][1500/1567] lr: 1.4947e-02 eta: 0:08:51 time: 0.0851 data_time: 0.0066 memory: 1827 loss: 0.0571 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0571 2022/12/25 16:34:22 - mmengine - INFO - Exp name: stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221225_160636 2022/12/25 16:34:22 - mmengine - INFO - Epoch(train) [12][1567/1567] lr: 1.4649e-02 eta: 0:08:46 time: 0.0816 data_time: 0.0062 memory: 1827 loss: 0.2856 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.2856 2022/12/25 16:34:22 - mmengine - INFO - Saving checkpoint at 12 epochs 2022/12/25 16:34:25 - mmengine - INFO - Epoch(val) [12][100/129] eta: 0:00:00 time: 0.0264 data_time: 0.0062 memory: 263 2022/12/25 16:34:26 - mmengine - INFO - Epoch(val) [12][129/129] acc/top1: 0.8481 acc/top5: 0.9829 acc/mean1: 0.8481 2022/12/25 16:34:26 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_11.pth is removed 2022/12/25 16:34:27 - mmengine - INFO - The best checkpoint with 0.8481 acc/top1 at 12 epoch is saved to best_acc/top1_epoch_12.pth. 2022/12/25 16:34:35 - mmengine - INFO - Epoch(train) [13][ 100/1567] lr: 1.4209e-02 eta: 0:08:37 time: 0.0864 data_time: 0.0064 memory: 1827 loss: 0.0471 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0471 2022/12/25 16:34:44 - mmengine - INFO - Exp name: stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221225_160636 2022/12/25 16:34:44 - mmengine - INFO - Epoch(train) [13][ 200/1567] lr: 1.3774e-02 eta: 0:08:29 time: 0.0850 data_time: 0.0069 memory: 1827 loss: 0.0620 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0620 2022/12/25 16:34:52 - mmengine - INFO - Epoch(train) [13][ 300/1567] lr: 1.3345e-02 eta: 0:08:21 time: 0.0822 data_time: 0.0064 memory: 1827 loss: 0.0459 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0459 2022/12/25 16:35:01 - mmengine - INFO - Epoch(train) [13][ 400/1567] lr: 1.2922e-02 eta: 0:08:12 time: 0.0812 data_time: 0.0064 memory: 1827 loss: 0.0474 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0474 2022/12/25 16:35:09 - mmengine - INFO - Epoch(train) [13][ 500/1567] lr: 1.2505e-02 eta: 0:08:04 time: 0.0818 data_time: 0.0064 memory: 1827 loss: 0.0670 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0670 2022/12/25 16:35:17 - mmengine - INFO - Epoch(train) [13][ 600/1567] lr: 1.2093e-02 eta: 0:07:55 time: 0.0864 data_time: 0.0065 memory: 1827 loss: 0.0591 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0591 2022/12/25 16:35:26 - mmengine - INFO - Epoch(train) [13][ 700/1567] lr: 1.1687e-02 eta: 0:07:47 time: 0.0856 data_time: 0.0064 memory: 1827 loss: 0.0419 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0419 2022/12/25 16:35:35 - mmengine - INFO - Epoch(train) [13][ 800/1567] lr: 1.1288e-02 eta: 0:07:39 time: 0.0853 data_time: 0.0065 memory: 1827 loss: 0.0359 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0359 2022/12/25 16:35:43 - mmengine - INFO - Epoch(train) [13][ 900/1567] lr: 1.0894e-02 eta: 0:07:30 time: 0.0858 data_time: 0.0067 memory: 1827 loss: 0.0541 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0541 2022/12/25 16:35:52 - mmengine - INFO - Epoch(train) [13][1000/1567] lr: 1.0507e-02 eta: 0:07:22 time: 0.0824 data_time: 0.0065 memory: 1827 loss: 0.0578 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0578 2022/12/25 16:36:00 - mmengine - INFO - Epoch(train) [13][1100/1567] lr: 1.0126e-02 eta: 0:07:14 time: 0.0822 data_time: 0.0064 memory: 1827 loss: 0.0529 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0529 2022/12/25 16:36:08 - mmengine - INFO - Exp name: stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221225_160636 2022/12/25 16:36:08 - mmengine - INFO - Epoch(train) [13][1200/1567] lr: 9.7512e-03 eta: 0:07:05 time: 0.0831 data_time: 0.0064 memory: 1827 loss: 0.0268 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0268 2022/12/25 16:36:17 - mmengine - INFO - Epoch(train) [13][1300/1567] lr: 9.3826e-03 eta: 0:06:57 time: 0.0854 data_time: 0.0064 memory: 1827 loss: 0.0458 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0458 2022/12/25 16:36:25 - mmengine - INFO - Epoch(train) [13][1400/1567] lr: 9.0204e-03 eta: 0:06:48 time: 0.0859 data_time: 0.0065 memory: 1827 loss: 0.0336 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0336 2022/12/25 16:36:34 - mmengine - INFO - Epoch(train) [13][1500/1567] lr: 8.6647e-03 eta: 0:06:40 time: 0.0835 data_time: 0.0065 memory: 1827 loss: 0.0366 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0366 2022/12/25 16:36:39 - mmengine - INFO - Exp name: stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221225_160636 2022/12/25 16:36:39 - mmengine - INFO - Epoch(train) [13][1567/1567] lr: 8.4300e-03 eta: 0:06:34 time: 0.0831 data_time: 0.0061 memory: 1827 loss: 0.2170 top1_acc: 0.0000 top5_acc: 1.0000 loss_cls: 0.2170 2022/12/25 16:36:39 - mmengine - INFO - Saving checkpoint at 13 epochs 2022/12/25 16:36:42 - mmengine - INFO - Epoch(val) [13][100/129] eta: 0:00:00 time: 0.0260 data_time: 0.0060 memory: 263 2022/12/25 16:36:43 - mmengine - INFO - Epoch(val) [13][129/129] acc/top1: 0.8432 acc/top5: 0.9838 acc/mean1: 0.8432 2022/12/25 16:36:52 - mmengine - INFO - Epoch(train) [14][ 100/1567] lr: 8.0851e-03 eta: 0:06:26 time: 0.0842 data_time: 0.0065 memory: 1827 loss: 0.0300 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0300 2022/12/25 16:37:00 - mmengine - INFO - Epoch(train) [14][ 200/1567] lr: 7.7469e-03 eta: 0:06:18 time: 0.0838 data_time: 0.0065 memory: 1827 loss: 0.0304 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0304 2022/12/25 16:37:09 - mmengine - INFO - Epoch(train) [14][ 300/1567] lr: 7.4152e-03 eta: 0:06:09 time: 0.0827 data_time: 0.0065 memory: 1827 loss: 0.0318 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0318 2022/12/25 16:37:17 - mmengine - INFO - Epoch(train) [14][ 400/1567] lr: 7.0902e-03 eta: 0:06:01 time: 0.0834 data_time: 0.0065 memory: 1827 loss: 0.0172 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0172 2022/12/25 16:37:25 - mmengine - INFO - Epoch(train) [14][ 500/1567] lr: 6.7720e-03 eta: 0:05:52 time: 0.0859 data_time: 0.0067 memory: 1827 loss: 0.0413 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0413 2022/12/25 16:37:34 - mmengine - INFO - Epoch(train) [14][ 600/1567] lr: 6.4606e-03 eta: 0:05:44 time: 0.0838 data_time: 0.0064 memory: 1827 loss: 0.0349 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0349 2022/12/25 16:37:36 - mmengine - INFO - Exp name: stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221225_160636 2022/12/25 16:37:42 - mmengine - INFO - Epoch(train) [14][ 700/1567] lr: 6.1560e-03 eta: 0:05:36 time: 0.0858 data_time: 0.0065 memory: 1827 loss: 0.0203 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0203 2022/12/25 16:37:51 - mmengine - INFO - Epoch(train) [14][ 800/1567] lr: 5.8582e-03 eta: 0:05:27 time: 0.0875 data_time: 0.0066 memory: 1827 loss: 0.0166 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0166 2022/12/25 16:38:00 - mmengine - INFO - Epoch(train) [14][ 900/1567] lr: 5.5675e-03 eta: 0:05:19 time: 0.0866 data_time: 0.0064 memory: 1827 loss: 0.0146 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0146 2022/12/25 16:38:09 - mmengine - INFO - Epoch(train) [14][1000/1567] lr: 5.2836e-03 eta: 0:05:11 time: 0.1016 data_time: 0.0064 memory: 1827 loss: 0.0278 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0278 2022/12/25 16:38:18 - mmengine - INFO - Epoch(train) [14][1100/1567] lr: 5.0068e-03 eta: 0:05:02 time: 0.0833 data_time: 0.0065 memory: 1827 loss: 0.0234 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0234 2022/12/25 16:38:26 - mmengine - INFO - Epoch(train) [14][1200/1567] lr: 4.7371e-03 eta: 0:04:54 time: 0.0833 data_time: 0.0064 memory: 1827 loss: 0.0248 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0248 2022/12/25 16:38:34 - mmengine - INFO - Epoch(train) [14][1300/1567] lr: 4.4745e-03 eta: 0:04:45 time: 0.0836 data_time: 0.0064 memory: 1827 loss: 0.0222 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0222 2022/12/25 16:38:43 - mmengine - INFO - Epoch(train) [14][1400/1567] lr: 4.2190e-03 eta: 0:04:37 time: 0.0869 data_time: 0.0064 memory: 1827 loss: 0.0110 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0110 2022/12/25 16:38:51 - mmengine - INFO - Epoch(train) [14][1500/1567] lr: 3.9707e-03 eta: 0:04:29 time: 0.0850 data_time: 0.0073 memory: 1827 loss: 0.0437 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0437 2022/12/25 16:38:57 - mmengine - INFO - Exp name: stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221225_160636 2022/12/25 16:38:57 - mmengine - INFO - Epoch(train) [14][1567/1567] lr: 3.8084e-03 eta: 0:04:23 time: 0.0824 data_time: 0.0063 memory: 1827 loss: 0.1783 top1_acc: 0.0000 top5_acc: 1.0000 loss_cls: 0.1783 2022/12/25 16:38:57 - mmengine - INFO - Saving checkpoint at 14 epochs 2022/12/25 16:39:00 - mmengine - INFO - Epoch(val) [14][100/129] eta: 0:00:00 time: 0.0260 data_time: 0.0058 memory: 263 2022/12/25 16:39:01 - mmengine - INFO - Epoch(val) [14][129/129] acc/top1: 0.8673 acc/top5: 0.9857 acc/mean1: 0.8672 2022/12/25 16:39:01 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_12.pth is removed 2022/12/25 16:39:01 - mmengine - INFO - The best checkpoint with 0.8673 acc/top1 at 14 epoch is saved to best_acc/top1_epoch_14.pth. 2022/12/25 16:39:07 - mmengine - INFO - Exp name: stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221225_160636 2022/12/25 16:39:10 - mmengine - INFO - Epoch(train) [15][ 100/1567] lr: 3.5722e-03 eta: 0:04:15 time: 0.0823 data_time: 0.0071 memory: 1827 loss: 0.0151 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0151 2022/12/25 16:39:18 - mmengine - INFO - Epoch(train) [15][ 200/1567] lr: 3.3433e-03 eta: 0:04:06 time: 0.0835 data_time: 0.0065 memory: 1827 loss: 0.0190 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0190 2022/12/25 16:39:26 - mmengine - INFO - Epoch(train) [15][ 300/1567] lr: 3.1217e-03 eta: 0:03:58 time: 0.0834 data_time: 0.0065 memory: 1827 loss: 0.0148 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0148 2022/12/25 16:39:35 - mmengine - INFO - Epoch(train) [15][ 400/1567] lr: 2.9075e-03 eta: 0:03:49 time: 0.0831 data_time: 0.0073 memory: 1827 loss: 0.0114 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0114 2022/12/25 16:39:43 - mmengine - INFO - Epoch(train) [15][ 500/1567] lr: 2.7007e-03 eta: 0:03:41 time: 0.0832 data_time: 0.0072 memory: 1827 loss: 0.0180 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0180 2022/12/25 16:39:51 - mmengine - INFO - Epoch(train) [15][ 600/1567] lr: 2.5013e-03 eta: 0:03:32 time: 0.0888 data_time: 0.0066 memory: 1827 loss: 0.0173 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0173 2022/12/25 16:40:00 - mmengine - INFO - Epoch(train) [15][ 700/1567] lr: 2.3093e-03 eta: 0:03:24 time: 0.0853 data_time: 0.0071 memory: 1827 loss: 0.0183 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0183 2022/12/25 16:40:08 - mmengine - INFO - Epoch(train) [15][ 800/1567] lr: 2.1249e-03 eta: 0:03:16 time: 0.0832 data_time: 0.0064 memory: 1827 loss: 0.0153 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0153 2022/12/25 16:40:17 - mmengine - INFO - Epoch(train) [15][ 900/1567] lr: 1.9479e-03 eta: 0:03:07 time: 0.0845 data_time: 0.0073 memory: 1827 loss: 0.0248 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0248 2022/12/25 16:40:25 - mmengine - INFO - Epoch(train) [15][1000/1567] lr: 1.7785e-03 eta: 0:02:59 time: 0.0823 data_time: 0.0064 memory: 1827 loss: 0.0129 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0129 2022/12/25 16:40:30 - mmengine - INFO - Exp name: stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221225_160636 2022/12/25 16:40:34 - mmengine - INFO - Epoch(train) [15][1100/1567] lr: 1.6167e-03 eta: 0:02:50 time: 0.0836 data_time: 0.0064 memory: 1827 loss: 0.0141 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0141 2022/12/25 16:40:42 - mmengine - INFO - Epoch(train) [15][1200/1567] lr: 1.4625e-03 eta: 0:02:42 time: 0.0829 data_time: 0.0064 memory: 1827 loss: 0.0128 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0128 2022/12/25 16:40:50 - mmengine - INFO - Epoch(train) [15][1300/1567] lr: 1.3159e-03 eta: 0:02:34 time: 0.0844 data_time: 0.0065 memory: 1827 loss: 0.0292 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0292 2022/12/25 16:40:59 - mmengine - INFO - Epoch(train) [15][1400/1567] lr: 1.1769e-03 eta: 0:02:25 time: 0.0833 data_time: 0.0064 memory: 1827 loss: 0.0134 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0134 2022/12/25 16:41:07 - mmengine - INFO - Epoch(train) [15][1500/1567] lr: 1.0456e-03 eta: 0:02:17 time: 0.0847 data_time: 0.0066 memory: 1827 loss: 0.0126 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0126 2022/12/25 16:41:13 - mmengine - INFO - Exp name: stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221225_160636 2022/12/25 16:41:13 - mmengine - INFO - Epoch(train) [15][1567/1567] lr: 9.6196e-04 eta: 0:02:11 time: 0.0843 data_time: 0.0062 memory: 1827 loss: 0.1924 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1924 2022/12/25 16:41:13 - mmengine - INFO - Saving checkpoint at 15 epochs 2022/12/25 16:41:16 - mmengine - INFO - Epoch(val) [15][100/129] eta: 0:00:00 time: 0.0263 data_time: 0.0059 memory: 263 2022/12/25 16:41:17 - mmengine - INFO - Epoch(val) [15][129/129] acc/top1: 0.8630 acc/top5: 0.9854 acc/mean1: 0.8630 2022/12/25 16:41:25 - mmengine - INFO - Epoch(train) [16][ 100/1567] lr: 8.4351e-04 eta: 0:02:03 time: 0.0846 data_time: 0.0065 memory: 1827 loss: 0.0258 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0258 2022/12/25 16:41:34 - mmengine - INFO - Epoch(train) [16][ 200/1567] lr: 7.3277e-04 eta: 0:01:54 time: 0.0864 data_time: 0.0065 memory: 1827 loss: 0.0188 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0188 2022/12/25 16:41:43 - mmengine - INFO - Epoch(train) [16][ 300/1567] lr: 6.2978e-04 eta: 0:01:46 time: 0.0826 data_time: 0.0064 memory: 1827 loss: 0.0221 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0221 2022/12/25 16:41:51 - mmengine - INFO - Epoch(train) [16][ 400/1567] lr: 5.3453e-04 eta: 0:01:38 time: 0.0851 data_time: 0.0067 memory: 1827 loss: 0.0151 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0151 2022/12/25 16:41:59 - mmengine - INFO - Exp name: stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221225_160636 2022/12/25 16:42:00 - mmengine - INFO - Epoch(train) [16][ 500/1567] lr: 4.4705e-04 eta: 0:01:29 time: 0.0831 data_time: 0.0064 memory: 1827 loss: 0.0196 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0196 2022/12/25 16:42:08 - mmengine - INFO - Epoch(train) [16][ 600/1567] lr: 3.6735e-04 eta: 0:01:21 time: 0.0868 data_time: 0.0064 memory: 1827 loss: 0.0096 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0096 2022/12/25 16:42:17 - mmengine - INFO - Epoch(train) [16][ 700/1567] lr: 2.9544e-04 eta: 0:01:12 time: 0.0868 data_time: 0.0064 memory: 1827 loss: 0.0144 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0144 2022/12/25 16:42:25 - mmengine - INFO - Epoch(train) [16][ 800/1567] lr: 2.3134e-04 eta: 0:01:04 time: 0.0866 data_time: 0.0064 memory: 1827 loss: 0.0127 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0127 2022/12/25 16:42:34 - mmengine - INFO - Epoch(train) [16][ 900/1567] lr: 1.7505e-04 eta: 0:00:56 time: 0.0831 data_time: 0.0065 memory: 1827 loss: 0.0158 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0158 2022/12/25 16:42:42 - mmengine - INFO - Epoch(train) [16][1000/1567] lr: 1.2658e-04 eta: 0:00:47 time: 0.0849 data_time: 0.0064 memory: 1827 loss: 0.0140 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0140 2022/12/25 16:42:51 - mmengine - INFO - Epoch(train) [16][1100/1567] lr: 8.5947e-05 eta: 0:00:39 time: 0.0851 data_time: 0.0069 memory: 1827 loss: 0.0212 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0212 2022/12/25 16:42:59 - mmengine - INFO - Epoch(train) [16][1200/1567] lr: 5.3147e-05 eta: 0:00:30 time: 0.0846 data_time: 0.0072 memory: 1827 loss: 0.0160 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0160 2022/12/25 16:43:08 - mmengine - INFO - Epoch(train) [16][1300/1567] lr: 2.8190e-05 eta: 0:00:22 time: 0.0825 data_time: 0.0065 memory: 1827 loss: 0.0210 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0210 2022/12/25 16:43:16 - mmengine - INFO - Epoch(train) [16][1400/1567] lr: 1.1078e-05 eta: 0:00:14 time: 0.0832 data_time: 0.0068 memory: 1827 loss: 0.0154 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0154 2022/12/25 16:43:24 - mmengine - INFO - Exp name: stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221225_160636 2022/12/25 16:43:24 - mmengine - INFO - Epoch(train) [16][1500/1567] lr: 1.8150e-06 eta: 0:00:05 time: 0.0828 data_time: 0.0065 memory: 1827 loss: 0.0274 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0274 2022/12/25 16:43:30 - mmengine - INFO - Exp name: stgcn++_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-2d_20221225_160636 2022/12/25 16:43:30 - mmengine - INFO - Epoch(train) [16][1567/1567] lr: 3.9252e-10 eta: 0:00:00 time: 0.0822 data_time: 0.0061 memory: 1827 loss: 0.1928 top1_acc: 0.0000 top5_acc: 1.0000 loss_cls: 0.1928 2022/12/25 16:43:30 - mmengine - INFO - Saving checkpoint at 16 epochs 2022/12/25 16:43:33 - mmengine - INFO - Epoch(val) [16][100/129] eta: 0:00:00 time: 0.0294 data_time: 0.0064 memory: 263 2022/12/25 16:43:34 - mmengine - INFO - Epoch(val) [16][129/129] acc/top1: 0.8640 acc/top5: 0.9857 acc/mean1: 0.8640