2023/03/06 23:23:16 - 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: 2011814450 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: 0.6.0 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: slurm Distributed training: True GPU number: 8 ------------------------------------------------------------ 2023/03/06 23:23:16 - mmengine - INFO - Config: default_scope = 'mmaction' default_hooks = dict( runtime_info=dict(type='RuntimeInfoHook', _scope_='mmaction'), timer=dict(type='IterTimerHook', _scope_='mmaction'), logger=dict( type='LoggerHook', interval=100, ignore_last=False, _scope_='mmaction'), param_scheduler=dict(type='ParamSchedulerHook', _scope_='mmaction'), checkpoint=dict( type='CheckpointHook', interval=1, save_best='auto', _scope_='mmaction'), sampler_seed=dict(type='DistSamplerSeedHook', _scope_='mmaction'), sync_buffers=dict(type='SyncBuffersHook', _scope_='mmaction')) 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, _scope_='mmaction') vis_backends = [dict(type='LocalVisBackend', _scope_='mmaction')] visualizer = dict( type='ActionVisualizer', vis_backends=[dict(type='LocalVisBackend')], _scope_='mmaction') log_level = 'INFO' load_from = None resume = False custom_imports = dict(imports='models') model = dict( type='RecognizerGCN', backbone=dict( type='CTRGCN', 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=['j']), 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=['j']), 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=['j']), 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=['j']), 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=['j']), 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=['j']), 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 = 'slurm' work_dir = './work_dirs/ctrgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d' randomness = dict(seed=None, diff_rank_seed=False, deterministic=False) 2023/03/06 23:23:17 - 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 (LOW ) ParamSchedulerHook (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([102]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.data_bn.bias - torch.Size([102]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.0.gcn1.A - torch.Size([3, 17, 17]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.0.gcn1.alpha - torch.Size([1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.0.gcn1.convs.0.conv1.weight - torch.Size([8, 3, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.0.gcn1.convs.0.conv1.bias - torch.Size([8]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.0.gcn1.convs.0.conv2.weight - torch.Size([8, 3, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.0.gcn1.convs.0.conv2.bias - torch.Size([8]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.0.gcn1.convs.0.conv3.weight - torch.Size([64, 3, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.0.gcn1.convs.0.conv3.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.0.gcn1.convs.0.conv4.weight - torch.Size([64, 8, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.0.gcn1.convs.0.conv4.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.0.gcn1.convs.1.conv1.weight - torch.Size([8, 3, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.0.gcn1.convs.1.conv1.bias - torch.Size([8]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.0.gcn1.convs.1.conv2.weight - torch.Size([8, 3, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.0.gcn1.convs.1.conv2.bias - torch.Size([8]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.0.gcn1.convs.1.conv3.weight - torch.Size([64, 3, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.0.gcn1.convs.1.conv3.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.0.gcn1.convs.1.conv4.weight - torch.Size([64, 8, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.0.gcn1.convs.1.conv4.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.0.gcn1.convs.2.conv1.weight - torch.Size([8, 3, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.0.gcn1.convs.2.conv1.bias - torch.Size([8]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.0.gcn1.convs.2.conv2.weight - torch.Size([8, 3, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.0.gcn1.convs.2.conv2.bias - torch.Size([8]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.0.gcn1.convs.2.conv3.weight - torch.Size([64, 3, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.0.gcn1.convs.2.conv3.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.0.gcn1.convs.2.conv4.weight - torch.Size([64, 8, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.0.gcn1.convs.2.conv4.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.0.gcn1.down.0.weight - torch.Size([64, 3, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.0.gcn1.down.0.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.0.gcn1.down.1.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.0.gcn1.down.1.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.0.gcn1.bn.weight - torch.Size([64]): ConstantInit: val=1e-06, bias=0 backbone.net.0.gcn1.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.0.tcn1.branches.0.0.weight - torch.Size([16, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.0.tcn1.branches.0.0.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.0.tcn1.branches.0.1.weight - torch.Size([16]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.0.tcn1.branches.0.1.bias - torch.Size([16]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.0.tcn1.branches.0.3.conv.weight - torch.Size([16, 16, 5, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.0.tcn1.branches.0.3.conv.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.0.tcn1.branches.0.3.bn.weight - torch.Size([16]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.0.tcn1.branches.0.3.bn.bias - torch.Size([16]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.0.tcn1.branches.1.0.weight - torch.Size([16, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.0.tcn1.branches.1.0.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.0.tcn1.branches.1.1.weight - torch.Size([16]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.0.tcn1.branches.1.1.bias - torch.Size([16]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.0.tcn1.branches.1.3.conv.weight - torch.Size([16, 16, 5, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.0.tcn1.branches.1.3.conv.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.0.tcn1.branches.1.3.bn.weight - torch.Size([16]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.0.tcn1.branches.1.3.bn.bias - torch.Size([16]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.0.tcn1.branches.2.0.weight - torch.Size([16, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.0.tcn1.branches.2.0.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.0.tcn1.branches.2.1.weight - torch.Size([16]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.0.tcn1.branches.2.1.bias - torch.Size([16]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.0.tcn1.branches.2.4.weight - torch.Size([16]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.0.tcn1.branches.2.4.bias - torch.Size([16]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.0.tcn1.branches.3.0.weight - torch.Size([16, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.0.tcn1.branches.3.0.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.0.tcn1.branches.3.1.weight - torch.Size([16]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.0.tcn1.branches.3.1.bias - torch.Size([16]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.1.gcn1.A - torch.Size([3, 17, 17]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.1.gcn1.alpha - torch.Size([1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.1.gcn1.convs.0.conv1.weight - torch.Size([8, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.1.gcn1.convs.0.conv1.bias - torch.Size([8]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.1.gcn1.convs.0.conv2.weight - torch.Size([8, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.1.gcn1.convs.0.conv2.bias - torch.Size([8]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.1.gcn1.convs.0.conv3.weight - torch.Size([64, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.1.gcn1.convs.0.conv3.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.1.gcn1.convs.0.conv4.weight - torch.Size([64, 8, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.1.gcn1.convs.0.conv4.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.1.gcn1.convs.1.conv1.weight - torch.Size([8, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.1.gcn1.convs.1.conv1.bias - torch.Size([8]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.1.gcn1.convs.1.conv2.weight - torch.Size([8, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.1.gcn1.convs.1.conv2.bias - torch.Size([8]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.1.gcn1.convs.1.conv3.weight - torch.Size([64, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.1.gcn1.convs.1.conv3.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.1.gcn1.convs.1.conv4.weight - torch.Size([64, 8, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.1.gcn1.convs.1.conv4.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.1.gcn1.convs.2.conv1.weight - torch.Size([8, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.1.gcn1.convs.2.conv1.bias - torch.Size([8]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.1.gcn1.convs.2.conv2.weight - torch.Size([8, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.1.gcn1.convs.2.conv2.bias - torch.Size([8]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.1.gcn1.convs.2.conv3.weight - torch.Size([64, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.1.gcn1.convs.2.conv3.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.1.gcn1.convs.2.conv4.weight - torch.Size([64, 8, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.1.gcn1.convs.2.conv4.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.1.gcn1.bn.weight - torch.Size([64]): ConstantInit: val=1e-06, bias=0 backbone.net.1.gcn1.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.1.tcn1.branches.0.0.weight - torch.Size([16, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.1.tcn1.branches.0.0.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.1.tcn1.branches.0.1.weight - torch.Size([16]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.1.tcn1.branches.0.1.bias - torch.Size([16]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.1.tcn1.branches.0.3.conv.weight - torch.Size([16, 16, 5, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.1.tcn1.branches.0.3.conv.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.1.tcn1.branches.0.3.bn.weight - torch.Size([16]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.1.tcn1.branches.0.3.bn.bias - torch.Size([16]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.1.tcn1.branches.1.0.weight - torch.Size([16, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.1.tcn1.branches.1.0.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.1.tcn1.branches.1.1.weight - torch.Size([16]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.1.tcn1.branches.1.1.bias - torch.Size([16]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.1.tcn1.branches.1.3.conv.weight - torch.Size([16, 16, 5, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.1.tcn1.branches.1.3.conv.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.1.tcn1.branches.1.3.bn.weight - torch.Size([16]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.1.tcn1.branches.1.3.bn.bias - torch.Size([16]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.1.tcn1.branches.2.0.weight - torch.Size([16, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.1.tcn1.branches.2.0.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.1.tcn1.branches.2.1.weight - torch.Size([16]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.1.tcn1.branches.2.1.bias - torch.Size([16]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.1.tcn1.branches.2.4.weight - torch.Size([16]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.1.tcn1.branches.2.4.bias - torch.Size([16]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.1.tcn1.branches.3.0.weight - torch.Size([16, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.1.tcn1.branches.3.0.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.1.tcn1.branches.3.1.weight - torch.Size([16]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.1.tcn1.branches.3.1.bias - torch.Size([16]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.2.gcn1.A - torch.Size([3, 17, 17]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.2.gcn1.alpha - torch.Size([1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.2.gcn1.convs.0.conv1.weight - torch.Size([8, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.2.gcn1.convs.0.conv1.bias - torch.Size([8]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.2.gcn1.convs.0.conv2.weight - torch.Size([8, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.2.gcn1.convs.0.conv2.bias - torch.Size([8]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.2.gcn1.convs.0.conv3.weight - torch.Size([64, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.2.gcn1.convs.0.conv3.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.2.gcn1.convs.0.conv4.weight - torch.Size([64, 8, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.2.gcn1.convs.0.conv4.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.2.gcn1.convs.1.conv1.weight - torch.Size([8, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.2.gcn1.convs.1.conv1.bias - torch.Size([8]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.2.gcn1.convs.1.conv2.weight - torch.Size([8, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.2.gcn1.convs.1.conv2.bias - torch.Size([8]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.2.gcn1.convs.1.conv3.weight - torch.Size([64, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.2.gcn1.convs.1.conv3.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.2.gcn1.convs.1.conv4.weight - torch.Size([64, 8, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.2.gcn1.convs.1.conv4.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.2.gcn1.convs.2.conv1.weight - torch.Size([8, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.2.gcn1.convs.2.conv1.bias - torch.Size([8]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.2.gcn1.convs.2.conv2.weight - torch.Size([8, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.2.gcn1.convs.2.conv2.bias - torch.Size([8]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.2.gcn1.convs.2.conv3.weight - torch.Size([64, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.2.gcn1.convs.2.conv3.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.2.gcn1.convs.2.conv4.weight - torch.Size([64, 8, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.2.gcn1.convs.2.conv4.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.2.gcn1.bn.weight - torch.Size([64]): ConstantInit: val=1e-06, bias=0 backbone.net.2.gcn1.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.2.tcn1.branches.0.0.weight - torch.Size([16, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.2.tcn1.branches.0.0.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.2.tcn1.branches.0.1.weight - torch.Size([16]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.2.tcn1.branches.0.1.bias - torch.Size([16]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.2.tcn1.branches.0.3.conv.weight - torch.Size([16, 16, 5, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.2.tcn1.branches.0.3.conv.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.2.tcn1.branches.0.3.bn.weight - torch.Size([16]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.2.tcn1.branches.0.3.bn.bias - torch.Size([16]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.2.tcn1.branches.1.0.weight - torch.Size([16, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.2.tcn1.branches.1.0.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.2.tcn1.branches.1.1.weight - torch.Size([16]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.2.tcn1.branches.1.1.bias - torch.Size([16]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.2.tcn1.branches.1.3.conv.weight - torch.Size([16, 16, 5, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.2.tcn1.branches.1.3.conv.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.2.tcn1.branches.1.3.bn.weight - torch.Size([16]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.2.tcn1.branches.1.3.bn.bias - torch.Size([16]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.2.tcn1.branches.2.0.weight - torch.Size([16, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.2.tcn1.branches.2.0.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.2.tcn1.branches.2.1.weight - torch.Size([16]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.2.tcn1.branches.2.1.bias - torch.Size([16]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.2.tcn1.branches.2.4.weight - torch.Size([16]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.2.tcn1.branches.2.4.bias - torch.Size([16]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.2.tcn1.branches.3.0.weight - torch.Size([16, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.2.tcn1.branches.3.0.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.2.tcn1.branches.3.1.weight - torch.Size([16]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.2.tcn1.branches.3.1.bias - torch.Size([16]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.3.gcn1.A - torch.Size([3, 17, 17]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.3.gcn1.alpha - torch.Size([1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.3.gcn1.convs.0.conv1.weight - torch.Size([8, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.3.gcn1.convs.0.conv1.bias - torch.Size([8]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.3.gcn1.convs.0.conv2.weight - torch.Size([8, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.3.gcn1.convs.0.conv2.bias - torch.Size([8]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.3.gcn1.convs.0.conv3.weight - torch.Size([64, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.3.gcn1.convs.0.conv3.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.3.gcn1.convs.0.conv4.weight - torch.Size([64, 8, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.3.gcn1.convs.0.conv4.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.3.gcn1.convs.1.conv1.weight - torch.Size([8, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.3.gcn1.convs.1.conv1.bias - torch.Size([8]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.3.gcn1.convs.1.conv2.weight - torch.Size([8, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.3.gcn1.convs.1.conv2.bias - torch.Size([8]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.3.gcn1.convs.1.conv3.weight - torch.Size([64, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.3.gcn1.convs.1.conv3.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.3.gcn1.convs.1.conv4.weight - torch.Size([64, 8, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.3.gcn1.convs.1.conv4.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.3.gcn1.convs.2.conv1.weight - torch.Size([8, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.3.gcn1.convs.2.conv1.bias - torch.Size([8]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.3.gcn1.convs.2.conv2.weight - torch.Size([8, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.3.gcn1.convs.2.conv2.bias - torch.Size([8]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.3.gcn1.convs.2.conv3.weight - torch.Size([64, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.3.gcn1.convs.2.conv3.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.3.gcn1.convs.2.conv4.weight - torch.Size([64, 8, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.3.gcn1.convs.2.conv4.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.3.gcn1.bn.weight - torch.Size([64]): ConstantInit: val=1e-06, bias=0 backbone.net.3.gcn1.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.3.tcn1.branches.0.0.weight - torch.Size([16, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.3.tcn1.branches.0.0.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.3.tcn1.branches.0.1.weight - torch.Size([16]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.3.tcn1.branches.0.1.bias - torch.Size([16]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.3.tcn1.branches.0.3.conv.weight - torch.Size([16, 16, 5, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.3.tcn1.branches.0.3.conv.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.3.tcn1.branches.0.3.bn.weight - torch.Size([16]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.3.tcn1.branches.0.3.bn.bias - torch.Size([16]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.3.tcn1.branches.1.0.weight - torch.Size([16, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.3.tcn1.branches.1.0.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.3.tcn1.branches.1.1.weight - torch.Size([16]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.3.tcn1.branches.1.1.bias - torch.Size([16]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.3.tcn1.branches.1.3.conv.weight - torch.Size([16, 16, 5, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.3.tcn1.branches.1.3.conv.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.3.tcn1.branches.1.3.bn.weight - torch.Size([16]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.3.tcn1.branches.1.3.bn.bias - torch.Size([16]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.3.tcn1.branches.2.0.weight - torch.Size([16, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.3.tcn1.branches.2.0.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.3.tcn1.branches.2.1.weight - torch.Size([16]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.3.tcn1.branches.2.1.bias - torch.Size([16]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.3.tcn1.branches.2.4.weight - torch.Size([16]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.3.tcn1.branches.2.4.bias - torch.Size([16]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.3.tcn1.branches.3.0.weight - torch.Size([16, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.3.tcn1.branches.3.0.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.3.tcn1.branches.3.1.weight - torch.Size([16]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.3.tcn1.branches.3.1.bias - torch.Size([16]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.4.gcn1.A - torch.Size([3, 17, 17]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.4.gcn1.alpha - torch.Size([1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.4.gcn1.convs.0.conv1.weight - torch.Size([8, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.4.gcn1.convs.0.conv1.bias - torch.Size([8]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.4.gcn1.convs.0.conv2.weight - torch.Size([8, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.4.gcn1.convs.0.conv2.bias - torch.Size([8]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.4.gcn1.convs.0.conv3.weight - torch.Size([128, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.4.gcn1.convs.0.conv3.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.4.gcn1.convs.0.conv4.weight - torch.Size([128, 8, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.4.gcn1.convs.0.conv4.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.4.gcn1.convs.1.conv1.weight - torch.Size([8, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.4.gcn1.convs.1.conv1.bias - torch.Size([8]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.4.gcn1.convs.1.conv2.weight - torch.Size([8, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.4.gcn1.convs.1.conv2.bias - torch.Size([8]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.4.gcn1.convs.1.conv3.weight - torch.Size([128, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.4.gcn1.convs.1.conv3.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.4.gcn1.convs.1.conv4.weight - torch.Size([128, 8, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.4.gcn1.convs.1.conv4.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.4.gcn1.convs.2.conv1.weight - torch.Size([8, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.4.gcn1.convs.2.conv1.bias - torch.Size([8]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.4.gcn1.convs.2.conv2.weight - torch.Size([8, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.4.gcn1.convs.2.conv2.bias - torch.Size([8]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.4.gcn1.convs.2.conv3.weight - torch.Size([128, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.4.gcn1.convs.2.conv3.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.4.gcn1.convs.2.conv4.weight - torch.Size([128, 8, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.4.gcn1.convs.2.conv4.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.4.gcn1.down.0.weight - torch.Size([128, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.4.gcn1.down.0.bias - torch.Size([128]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.4.gcn1.down.1.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.4.gcn1.down.1.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.4.gcn1.bn.weight - torch.Size([128]): ConstantInit: val=1e-06, bias=0 backbone.net.4.gcn1.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.4.tcn1.branches.0.0.weight - torch.Size([32, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.4.tcn1.branches.0.0.bias - torch.Size([32]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.4.tcn1.branches.0.1.weight - torch.Size([32]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.4.tcn1.branches.0.1.bias - torch.Size([32]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.4.tcn1.branches.0.3.conv.weight - torch.Size([32, 32, 5, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.4.tcn1.branches.0.3.conv.bias - torch.Size([32]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.4.tcn1.branches.0.3.bn.weight - torch.Size([32]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.4.tcn1.branches.0.3.bn.bias - torch.Size([32]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.4.tcn1.branches.1.0.weight - torch.Size([32, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.4.tcn1.branches.1.0.bias - torch.Size([32]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.4.tcn1.branches.1.1.weight - torch.Size([32]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.4.tcn1.branches.1.1.bias - torch.Size([32]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.4.tcn1.branches.1.3.conv.weight - torch.Size([32, 32, 5, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.4.tcn1.branches.1.3.conv.bias - torch.Size([32]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.4.tcn1.branches.1.3.bn.weight - torch.Size([32]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.4.tcn1.branches.1.3.bn.bias - torch.Size([32]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.4.tcn1.branches.2.0.weight - torch.Size([32, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.4.tcn1.branches.2.0.bias - torch.Size([32]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.4.tcn1.branches.2.1.weight - torch.Size([32]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.4.tcn1.branches.2.1.bias - torch.Size([32]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.4.tcn1.branches.2.4.weight - torch.Size([32]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.4.tcn1.branches.2.4.bias - torch.Size([32]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.4.tcn1.branches.3.0.weight - torch.Size([32, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.4.tcn1.branches.3.0.bias - torch.Size([32]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.4.tcn1.branches.3.1.weight - torch.Size([32]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.4.tcn1.branches.3.1.bias - torch.Size([32]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.4.residual.conv.weight - torch.Size([128, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.4.residual.conv.bias - torch.Size([128]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.4.residual.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.4.residual.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.5.gcn1.A - torch.Size([3, 17, 17]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.5.gcn1.alpha - torch.Size([1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.5.gcn1.convs.0.conv1.weight - torch.Size([16, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.5.gcn1.convs.0.conv1.bias - torch.Size([16]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.5.gcn1.convs.0.conv2.weight - torch.Size([16, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.5.gcn1.convs.0.conv2.bias - torch.Size([16]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.5.gcn1.convs.0.conv3.weight - torch.Size([128, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.5.gcn1.convs.0.conv3.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.5.gcn1.convs.0.conv4.weight - torch.Size([128, 16, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.5.gcn1.convs.0.conv4.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.5.gcn1.convs.1.conv1.weight - torch.Size([16, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.5.gcn1.convs.1.conv1.bias - torch.Size([16]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.5.gcn1.convs.1.conv2.weight - torch.Size([16, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.5.gcn1.convs.1.conv2.bias - torch.Size([16]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.5.gcn1.convs.1.conv3.weight - torch.Size([128, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.5.gcn1.convs.1.conv3.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.5.gcn1.convs.1.conv4.weight - torch.Size([128, 16, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.5.gcn1.convs.1.conv4.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.5.gcn1.convs.2.conv1.weight - torch.Size([16, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.5.gcn1.convs.2.conv1.bias - torch.Size([16]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.5.gcn1.convs.2.conv2.weight - torch.Size([16, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.5.gcn1.convs.2.conv2.bias - torch.Size([16]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.5.gcn1.convs.2.conv3.weight - torch.Size([128, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.5.gcn1.convs.2.conv3.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.5.gcn1.convs.2.conv4.weight - torch.Size([128, 16, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.5.gcn1.convs.2.conv4.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.5.gcn1.bn.weight - torch.Size([128]): ConstantInit: val=1e-06, bias=0 backbone.net.5.gcn1.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.5.tcn1.branches.0.0.weight - torch.Size([32, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.5.tcn1.branches.0.0.bias - torch.Size([32]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.5.tcn1.branches.0.1.weight - torch.Size([32]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.5.tcn1.branches.0.1.bias - torch.Size([32]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.5.tcn1.branches.0.3.conv.weight - torch.Size([32, 32, 5, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.5.tcn1.branches.0.3.conv.bias - torch.Size([32]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.5.tcn1.branches.0.3.bn.weight - torch.Size([32]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.5.tcn1.branches.0.3.bn.bias - torch.Size([32]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.5.tcn1.branches.1.0.weight - torch.Size([32, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.5.tcn1.branches.1.0.bias - torch.Size([32]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.5.tcn1.branches.1.1.weight - torch.Size([32]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.5.tcn1.branches.1.1.bias - torch.Size([32]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.5.tcn1.branches.1.3.conv.weight - torch.Size([32, 32, 5, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.5.tcn1.branches.1.3.conv.bias - torch.Size([32]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.5.tcn1.branches.1.3.bn.weight - torch.Size([32]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.5.tcn1.branches.1.3.bn.bias - torch.Size([32]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.5.tcn1.branches.2.0.weight - torch.Size([32, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.5.tcn1.branches.2.0.bias - torch.Size([32]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.5.tcn1.branches.2.1.weight - torch.Size([32]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.5.tcn1.branches.2.1.bias - torch.Size([32]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.5.tcn1.branches.2.4.weight - torch.Size([32]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.5.tcn1.branches.2.4.bias - torch.Size([32]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.5.tcn1.branches.3.0.weight - torch.Size([32, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.5.tcn1.branches.3.0.bias - torch.Size([32]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.5.tcn1.branches.3.1.weight - torch.Size([32]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.5.tcn1.branches.3.1.bias - torch.Size([32]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.6.gcn1.A - torch.Size([3, 17, 17]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.6.gcn1.alpha - torch.Size([1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.6.gcn1.convs.0.conv1.weight - torch.Size([16, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.6.gcn1.convs.0.conv1.bias - torch.Size([16]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.6.gcn1.convs.0.conv2.weight - torch.Size([16, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.6.gcn1.convs.0.conv2.bias - torch.Size([16]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.6.gcn1.convs.0.conv3.weight - torch.Size([128, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.6.gcn1.convs.0.conv3.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.6.gcn1.convs.0.conv4.weight - torch.Size([128, 16, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.6.gcn1.convs.0.conv4.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.6.gcn1.convs.1.conv1.weight - torch.Size([16, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.6.gcn1.convs.1.conv1.bias - torch.Size([16]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.6.gcn1.convs.1.conv2.weight - torch.Size([16, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.6.gcn1.convs.1.conv2.bias - torch.Size([16]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.6.gcn1.convs.1.conv3.weight - torch.Size([128, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.6.gcn1.convs.1.conv3.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.6.gcn1.convs.1.conv4.weight - torch.Size([128, 16, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.6.gcn1.convs.1.conv4.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.6.gcn1.convs.2.conv1.weight - torch.Size([16, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.6.gcn1.convs.2.conv1.bias - torch.Size([16]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.6.gcn1.convs.2.conv2.weight - torch.Size([16, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.6.gcn1.convs.2.conv2.bias - torch.Size([16]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.6.gcn1.convs.2.conv3.weight - torch.Size([128, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.6.gcn1.convs.2.conv3.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.6.gcn1.convs.2.conv4.weight - torch.Size([128, 16, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.6.gcn1.convs.2.conv4.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.6.gcn1.bn.weight - torch.Size([128]): ConstantInit: val=1e-06, bias=0 backbone.net.6.gcn1.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.6.tcn1.branches.0.0.weight - torch.Size([32, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.6.tcn1.branches.0.0.bias - torch.Size([32]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.6.tcn1.branches.0.1.weight - torch.Size([32]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.6.tcn1.branches.0.1.bias - torch.Size([32]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.6.tcn1.branches.0.3.conv.weight - torch.Size([32, 32, 5, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.6.tcn1.branches.0.3.conv.bias - torch.Size([32]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.6.tcn1.branches.0.3.bn.weight - torch.Size([32]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.6.tcn1.branches.0.3.bn.bias - torch.Size([32]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.6.tcn1.branches.1.0.weight - torch.Size([32, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.6.tcn1.branches.1.0.bias - torch.Size([32]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.6.tcn1.branches.1.1.weight - torch.Size([32]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.6.tcn1.branches.1.1.bias - torch.Size([32]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.6.tcn1.branches.1.3.conv.weight - torch.Size([32, 32, 5, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.6.tcn1.branches.1.3.conv.bias - torch.Size([32]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.6.tcn1.branches.1.3.bn.weight - torch.Size([32]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.6.tcn1.branches.1.3.bn.bias - torch.Size([32]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.6.tcn1.branches.2.0.weight - torch.Size([32, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.6.tcn1.branches.2.0.bias - torch.Size([32]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.6.tcn1.branches.2.1.weight - torch.Size([32]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.6.tcn1.branches.2.1.bias - torch.Size([32]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.6.tcn1.branches.2.4.weight - torch.Size([32]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.6.tcn1.branches.2.4.bias - torch.Size([32]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.6.tcn1.branches.3.0.weight - torch.Size([32, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.6.tcn1.branches.3.0.bias - torch.Size([32]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.6.tcn1.branches.3.1.weight - torch.Size([32]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.6.tcn1.branches.3.1.bias - torch.Size([32]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.7.gcn1.A - torch.Size([3, 17, 17]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.7.gcn1.alpha - torch.Size([1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.7.gcn1.convs.0.conv1.weight - torch.Size([16, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.7.gcn1.convs.0.conv1.bias - torch.Size([16]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.7.gcn1.convs.0.conv2.weight - torch.Size([16, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.7.gcn1.convs.0.conv2.bias - torch.Size([16]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.7.gcn1.convs.0.conv3.weight - torch.Size([256, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.7.gcn1.convs.0.conv3.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.7.gcn1.convs.0.conv4.weight - torch.Size([256, 16, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.7.gcn1.convs.0.conv4.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.7.gcn1.convs.1.conv1.weight - torch.Size([16, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.7.gcn1.convs.1.conv1.bias - torch.Size([16]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.7.gcn1.convs.1.conv2.weight - torch.Size([16, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.7.gcn1.convs.1.conv2.bias - torch.Size([16]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.7.gcn1.convs.1.conv3.weight - torch.Size([256, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.7.gcn1.convs.1.conv3.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.7.gcn1.convs.1.conv4.weight - torch.Size([256, 16, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.7.gcn1.convs.1.conv4.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.7.gcn1.convs.2.conv1.weight - torch.Size([16, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.7.gcn1.convs.2.conv1.bias - torch.Size([16]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.7.gcn1.convs.2.conv2.weight - torch.Size([16, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.7.gcn1.convs.2.conv2.bias - torch.Size([16]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.7.gcn1.convs.2.conv3.weight - torch.Size([256, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.7.gcn1.convs.2.conv3.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.7.gcn1.convs.2.conv4.weight - torch.Size([256, 16, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.7.gcn1.convs.2.conv4.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.7.gcn1.down.0.weight - torch.Size([256, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.7.gcn1.down.0.bias - torch.Size([256]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.7.gcn1.down.1.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.7.gcn1.down.1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.7.gcn1.bn.weight - torch.Size([256]): ConstantInit: val=1e-06, bias=0 backbone.net.7.gcn1.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.7.tcn1.branches.0.0.weight - torch.Size([64, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.7.tcn1.branches.0.0.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.7.tcn1.branches.0.1.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.7.tcn1.branches.0.1.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.7.tcn1.branches.0.3.conv.weight - torch.Size([64, 64, 5, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.7.tcn1.branches.0.3.conv.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.7.tcn1.branches.0.3.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.7.tcn1.branches.0.3.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.7.tcn1.branches.1.0.weight - torch.Size([64, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.7.tcn1.branches.1.0.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.7.tcn1.branches.1.1.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.7.tcn1.branches.1.1.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.7.tcn1.branches.1.3.conv.weight - torch.Size([64, 64, 5, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.7.tcn1.branches.1.3.conv.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.7.tcn1.branches.1.3.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.7.tcn1.branches.1.3.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.7.tcn1.branches.2.0.weight - torch.Size([64, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.7.tcn1.branches.2.0.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.7.tcn1.branches.2.1.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.7.tcn1.branches.2.1.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.7.tcn1.branches.2.4.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.7.tcn1.branches.2.4.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.7.tcn1.branches.3.0.weight - torch.Size([64, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.7.tcn1.branches.3.0.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.7.tcn1.branches.3.1.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.7.tcn1.branches.3.1.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.7.residual.conv.weight - torch.Size([256, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.7.residual.conv.bias - torch.Size([256]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.7.residual.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.7.residual.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.8.gcn1.A - torch.Size([3, 17, 17]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.8.gcn1.alpha - torch.Size([1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.8.gcn1.convs.0.conv1.weight - torch.Size([32, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.8.gcn1.convs.0.conv1.bias - torch.Size([32]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.8.gcn1.convs.0.conv2.weight - torch.Size([32, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.8.gcn1.convs.0.conv2.bias - torch.Size([32]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.8.gcn1.convs.0.conv3.weight - torch.Size([256, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.8.gcn1.convs.0.conv3.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.8.gcn1.convs.0.conv4.weight - torch.Size([256, 32, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.8.gcn1.convs.0.conv4.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.8.gcn1.convs.1.conv1.weight - torch.Size([32, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.8.gcn1.convs.1.conv1.bias - torch.Size([32]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.8.gcn1.convs.1.conv2.weight - torch.Size([32, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.8.gcn1.convs.1.conv2.bias - torch.Size([32]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.8.gcn1.convs.1.conv3.weight - torch.Size([256, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.8.gcn1.convs.1.conv3.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.8.gcn1.convs.1.conv4.weight - torch.Size([256, 32, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.8.gcn1.convs.1.conv4.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.8.gcn1.convs.2.conv1.weight - torch.Size([32, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.8.gcn1.convs.2.conv1.bias - torch.Size([32]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.8.gcn1.convs.2.conv2.weight - torch.Size([32, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.8.gcn1.convs.2.conv2.bias - torch.Size([32]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.8.gcn1.convs.2.conv3.weight - torch.Size([256, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.8.gcn1.convs.2.conv3.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.8.gcn1.convs.2.conv4.weight - torch.Size([256, 32, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.8.gcn1.convs.2.conv4.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.8.gcn1.bn.weight - torch.Size([256]): ConstantInit: val=1e-06, bias=0 backbone.net.8.gcn1.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.8.tcn1.branches.0.0.weight - torch.Size([64, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.8.tcn1.branches.0.0.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.8.tcn1.branches.0.1.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.8.tcn1.branches.0.1.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.8.tcn1.branches.0.3.conv.weight - torch.Size([64, 64, 5, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.8.tcn1.branches.0.3.conv.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.8.tcn1.branches.0.3.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.8.tcn1.branches.0.3.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.8.tcn1.branches.1.0.weight - torch.Size([64, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.8.tcn1.branches.1.0.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.8.tcn1.branches.1.1.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.8.tcn1.branches.1.1.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.8.tcn1.branches.1.3.conv.weight - torch.Size([64, 64, 5, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.8.tcn1.branches.1.3.conv.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.8.tcn1.branches.1.3.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.8.tcn1.branches.1.3.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.8.tcn1.branches.2.0.weight - torch.Size([64, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.8.tcn1.branches.2.0.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.8.tcn1.branches.2.1.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.8.tcn1.branches.2.1.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.8.tcn1.branches.2.4.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.8.tcn1.branches.2.4.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.8.tcn1.branches.3.0.weight - torch.Size([64, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.8.tcn1.branches.3.0.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.8.tcn1.branches.3.1.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.8.tcn1.branches.3.1.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.9.gcn1.A - torch.Size([3, 17, 17]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.9.gcn1.alpha - torch.Size([1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.9.gcn1.convs.0.conv1.weight - torch.Size([32, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.9.gcn1.convs.0.conv1.bias - torch.Size([32]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.9.gcn1.convs.0.conv2.weight - torch.Size([32, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.9.gcn1.convs.0.conv2.bias - torch.Size([32]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.9.gcn1.convs.0.conv3.weight - torch.Size([256, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.9.gcn1.convs.0.conv3.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.9.gcn1.convs.0.conv4.weight - torch.Size([256, 32, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.9.gcn1.convs.0.conv4.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.9.gcn1.convs.1.conv1.weight - torch.Size([32, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.9.gcn1.convs.1.conv1.bias - torch.Size([32]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.9.gcn1.convs.1.conv2.weight - torch.Size([32, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.9.gcn1.convs.1.conv2.bias - torch.Size([32]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.9.gcn1.convs.1.conv3.weight - torch.Size([256, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.9.gcn1.convs.1.conv3.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.9.gcn1.convs.1.conv4.weight - torch.Size([256, 32, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.9.gcn1.convs.1.conv4.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.9.gcn1.convs.2.conv1.weight - torch.Size([32, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.9.gcn1.convs.2.conv1.bias - torch.Size([32]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.9.gcn1.convs.2.conv2.weight - torch.Size([32, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.9.gcn1.convs.2.conv2.bias - torch.Size([32]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.9.gcn1.convs.2.conv3.weight - torch.Size([256, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.9.gcn1.convs.2.conv3.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.9.gcn1.convs.2.conv4.weight - torch.Size([256, 32, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.9.gcn1.convs.2.conv4.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.9.gcn1.bn.weight - torch.Size([256]): ConstantInit: val=1e-06, bias=0 backbone.net.9.gcn1.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.9.tcn1.branches.0.0.weight - torch.Size([64, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.9.tcn1.branches.0.0.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.9.tcn1.branches.0.1.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.9.tcn1.branches.0.1.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.9.tcn1.branches.0.3.conv.weight - torch.Size([64, 64, 5, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.9.tcn1.branches.0.3.conv.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.9.tcn1.branches.0.3.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.9.tcn1.branches.0.3.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.9.tcn1.branches.1.0.weight - torch.Size([64, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.9.tcn1.branches.1.0.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.9.tcn1.branches.1.1.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.9.tcn1.branches.1.1.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.9.tcn1.branches.1.3.conv.weight - torch.Size([64, 64, 5, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.9.tcn1.branches.1.3.conv.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.9.tcn1.branches.1.3.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.9.tcn1.branches.1.3.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.9.tcn1.branches.2.0.weight - torch.Size([64, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.9.tcn1.branches.2.0.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.9.tcn1.branches.2.1.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.9.tcn1.branches.2.1.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.9.tcn1.branches.2.4.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.9.tcn1.branches.2.4.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.9.tcn1.branches.3.0.weight - torch.Size([64, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.9.tcn1.branches.3.0.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.net.9.tcn1.branches.3.1.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.net.9.tcn1.branches.3.1.bias - torch.Size([64]): 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 2023/03/06 23:23:26 - mmengine - INFO - Checkpoints will be saved to /mnt/petrelfs/daiwenxun/mmlab/mmaction2/projects/ctrgcn/work_dirs/ctrgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d. 2023/03/06 23:23:43 - mmengine - INFO - Epoch(train) [1][ 100/1567] lr: 9.9996e-02 eta: 1:11:17 time: 0.1146 data_time: 0.0064 memory: 1996 loss: 3.5638 top1_acc: 0.0625 top5_acc: 0.2500 loss_cls: 3.5638 2023/03/06 23:23:55 - mmengine - INFO - Epoch(train) [1][ 200/1567] lr: 9.9984e-02 eta: 0:59:37 time: 0.1146 data_time: 0.0072 memory: 1996 loss: 3.2507 top1_acc: 0.2500 top5_acc: 0.6250 loss_cls: 3.2507 2023/03/06 23:24:06 - mmengine - INFO - Epoch(train) [1][ 300/1567] lr: 9.9965e-02 eta: 0:55:29 time: 0.1183 data_time: 0.0070 memory: 1996 loss: 2.8632 top1_acc: 0.0625 top5_acc: 0.4375 loss_cls: 2.8632 2023/03/06 23:24:18 - mmengine - INFO - Epoch(train) [1][ 400/1567] lr: 9.9938e-02 eta: 0:53:13 time: 0.1129 data_time: 0.0064 memory: 1996 loss: 2.2790 top1_acc: 0.3750 top5_acc: 0.6875 loss_cls: 2.2790 2023/03/06 23:24:29 - mmengine - INFO - Epoch(train) [1][ 500/1567] lr: 9.9902e-02 eta: 0:51:42 time: 0.1124 data_time: 0.0064 memory: 1996 loss: 2.0425 top1_acc: 0.3750 top5_acc: 0.8750 loss_cls: 2.0425 2023/03/06 23:24:40 - mmengine - INFO - Epoch(train) [1][ 600/1567] lr: 9.9859e-02 eta: 0:50:42 time: 0.1131 data_time: 0.0065 memory: 1996 loss: 1.6998 top1_acc: 0.3750 top5_acc: 0.9375 loss_cls: 1.6998 2023/03/06 23:24:52 - mmengine - INFO - Epoch(train) [1][ 700/1567] lr: 9.9808e-02 eta: 0:49:53 time: 0.1166 data_time: 0.0074 memory: 1996 loss: 1.5935 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.5935 2023/03/06 23:25:03 - mmengine - INFO - Epoch(train) [1][ 800/1567] lr: 9.9750e-02 eta: 0:49:12 time: 0.1129 data_time: 0.0072 memory: 1996 loss: 1.2794 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 1.2794 2023/03/06 23:25:14 - mmengine - INFO - Epoch(train) [1][ 900/1567] lr: 9.9683e-02 eta: 0:48:37 time: 0.1140 data_time: 0.0065 memory: 1996 loss: 1.0846 top1_acc: 0.5625 top5_acc: 0.9375 loss_cls: 1.0846 2023/03/06 23:25:26 - mmengine - INFO - Exp name: ctrgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230306_232308 2023/03/06 23:25:26 - mmengine - INFO - Epoch(train) [1][1000/1567] lr: 9.9609e-02 eta: 0:48:13 time: 0.1160 data_time: 0.0064 memory: 1996 loss: 1.0481 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 1.0481 2023/03/06 23:25:38 - mmengine - INFO - Epoch(train) [1][1100/1567] lr: 9.9527e-02 eta: 0:47:50 time: 0.1145 data_time: 0.0073 memory: 1996 loss: 0.9336 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 0.9336 2023/03/06 23:25:49 - mmengine - INFO - Epoch(train) [1][1200/1567] lr: 9.9437e-02 eta: 0:47:27 time: 0.1129 data_time: 0.0063 memory: 1996 loss: 0.9093 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.9093 2023/03/06 23:26:00 - mmengine - INFO - Epoch(train) [1][1300/1567] lr: 9.9339e-02 eta: 0:47:05 time: 0.1136 data_time: 0.0064 memory: 1996 loss: 0.8508 top1_acc: 0.6250 top5_acc: 1.0000 loss_cls: 0.8508 2023/03/06 23:26:12 - mmengine - INFO - Epoch(train) [1][1400/1567] lr: 9.9234e-02 eta: 0:46:46 time: 0.1118 data_time: 0.0064 memory: 1996 loss: 0.8170 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 0.8170 2023/03/06 23:26:23 - mmengine - INFO - Epoch(train) [1][1500/1567] lr: 9.9121e-02 eta: 0:46:27 time: 0.1120 data_time: 0.0069 memory: 1996 loss: 0.6107 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.6107 2023/03/06 23:26:31 - mmengine - INFO - Exp name: ctrgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230306_232308 2023/03/06 23:26:31 - mmengine - INFO - Epoch(train) [1][1567/1567] lr: 9.9040e-02 eta: 0:46:17 time: 0.1166 data_time: 0.0062 memory: 1996 loss: 0.8441 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.8441 2023/03/06 23:26:31 - mmengine - INFO - Saving checkpoint at 1 epochs 2023/03/06 23:26:36 - mmengine - INFO - Epoch(val) [1][100/129] eta: 0:00:01 time: 0.0413 data_time: 0.0071 memory: 156 2023/03/06 23:26:37 - mmengine - INFO - Epoch(val) [1][129/129] acc/top1: 0.5221 acc/top5: 0.8867 acc/mean1: 0.5220 2023/03/06 23:26:37 - mmengine - INFO - The best checkpoint with 0.5221 acc/top1 at 1 epoch is saved to best_acc/top1_epoch_1.pth. 2023/03/06 23:26:49 - mmengine - INFO - Epoch(train) [2][ 100/1567] lr: 9.8914e-02 eta: 0:46:01 time: 0.1132 data_time: 0.0068 memory: 1996 loss: 0.5653 top1_acc: 0.5000 top5_acc: 1.0000 loss_cls: 0.5653 2023/03/06 23:27:01 - mmengine - INFO - Epoch(train) [2][ 200/1567] lr: 9.8781e-02 eta: 0:45:47 time: 0.1146 data_time: 0.0065 memory: 1996 loss: 0.6796 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.6796 2023/03/06 23:27:12 - mmengine - INFO - Epoch(train) [2][ 300/1567] lr: 9.8639e-02 eta: 0:45:31 time: 0.1139 data_time: 0.0064 memory: 1996 loss: 0.6950 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.6950 2023/03/06 23:27:24 - mmengine - INFO - Epoch(train) [2][ 400/1567] lr: 9.8491e-02 eta: 0:45:24 time: 0.1237 data_time: 0.0065 memory: 1996 loss: 0.5903 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.5903 2023/03/06 23:27:28 - mmengine - INFO - Exp name: ctrgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230306_232308 2023/03/06 23:27:36 - mmengine - INFO - Epoch(train) [2][ 500/1567] lr: 9.8334e-02 eta: 0:45:12 time: 0.1199 data_time: 0.0075 memory: 1996 loss: 0.5886 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.5886 2023/03/06 23:27:48 - mmengine - INFO - Epoch(train) [2][ 600/1567] lr: 9.8170e-02 eta: 0:45:00 time: 0.1182 data_time: 0.0073 memory: 1996 loss: 0.6247 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 0.6247 2023/03/06 23:27:59 - mmengine - INFO - Epoch(train) [2][ 700/1567] lr: 9.7998e-02 eta: 0:44:46 time: 0.1149 data_time: 0.0067 memory: 1996 loss: 0.4807 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.4807 2023/03/06 23:28:11 - mmengine - INFO - Epoch(train) [2][ 800/1567] lr: 9.7819e-02 eta: 0:44:31 time: 0.1141 data_time: 0.0065 memory: 1996 loss: 0.5047 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.5047 2023/03/06 23:28:22 - mmengine - INFO - Epoch(train) [2][ 900/1567] lr: 9.7632e-02 eta: 0:44:17 time: 0.1147 data_time: 0.0066 memory: 1996 loss: 0.5331 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.5331 2023/03/06 23:28:34 - mmengine - INFO - Epoch(train) [2][1000/1567] lr: 9.7438e-02 eta: 0:44:03 time: 0.1143 data_time: 0.0066 memory: 1996 loss: 0.5302 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.5302 2023/03/06 23:28:45 - mmengine - INFO - Epoch(train) [2][1100/1567] lr: 9.7236e-02 eta: 0:43:50 time: 0.1136 data_time: 0.0066 memory: 1996 loss: 0.5024 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.5024 2023/03/06 23:28:57 - mmengine - INFO - Epoch(train) [2][1200/1567] lr: 9.7027e-02 eta: 0:43:36 time: 0.1133 data_time: 0.0067 memory: 1996 loss: 0.5303 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.5303 2023/03/06 23:29:08 - mmengine - INFO - Epoch(train) [2][1300/1567] lr: 9.6810e-02 eta: 0:43:21 time: 0.1135 data_time: 0.0065 memory: 1996 loss: 0.5072 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.5072 2023/03/06 23:29:20 - mmengine - INFO - Epoch(train) [2][1400/1567] lr: 9.6587e-02 eta: 0:43:07 time: 0.1132 data_time: 0.0068 memory: 1996 loss: 0.5309 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.5309 2023/03/06 23:29:23 - mmengine - INFO - Exp name: ctrgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230306_232308 2023/03/06 23:29:31 - mmengine - INFO - Epoch(train) [2][1500/1567] lr: 9.6355e-02 eta: 0:42:53 time: 0.1133 data_time: 0.0072 memory: 1996 loss: 0.4985 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4985 2023/03/06 23:29:39 - mmengine - INFO - Exp name: ctrgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230306_232308 2023/03/06 23:29:39 - mmengine - INFO - Epoch(train) [2][1567/1567] lr: 9.6196e-02 eta: 0:42:44 time: 0.1132 data_time: 0.0063 memory: 1996 loss: 0.7135 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.7135 2023/03/06 23:29:39 - mmengine - INFO - Saving checkpoint at 2 epochs 2023/03/06 23:29:43 - mmengine - INFO - Epoch(val) [2][100/129] eta: 0:00:01 time: 0.0376 data_time: 0.0070 memory: 156 2023/03/06 23:29:44 - mmengine - INFO - Epoch(val) [2][129/129] acc/top1: 0.6350 acc/top5: 0.9262 acc/mean1: 0.6349 2023/03/06 23:29:44 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/projects/ctrgcn/work_dirs/ctrgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_1.pth is removed 2023/03/06 23:29:45 - mmengine - INFO - The best checkpoint with 0.6350 acc/top1 at 2 epoch is saved to best_acc/top1_epoch_2.pth. 2023/03/06 23:29:56 - mmengine - INFO - Epoch(train) [3][ 100/1567] lr: 9.5953e-02 eta: 0:42:32 time: 0.1133 data_time: 0.0065 memory: 1996 loss: 0.4132 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4132 2023/03/06 23:30:08 - mmengine - INFO - Epoch(train) [3][ 200/1567] lr: 9.5703e-02 eta: 0:42:20 time: 0.1134 data_time: 0.0066 memory: 1996 loss: 0.3792 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3792 2023/03/06 23:30:19 - mmengine - INFO - Epoch(train) [3][ 300/1567] lr: 9.5445e-02 eta: 0:42:07 time: 0.1181 data_time: 0.0068 memory: 1996 loss: 0.4440 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.4440 2023/03/06 23:30:31 - mmengine - INFO - Epoch(train) [3][ 400/1567] lr: 9.5180e-02 eta: 0:41:56 time: 0.1275 data_time: 0.0071 memory: 1996 loss: 0.4819 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.4819 2023/03/06 23:30:43 - mmengine - INFO - Epoch(train) [3][ 500/1567] lr: 9.4908e-02 eta: 0:41:46 time: 0.1139 data_time: 0.0065 memory: 1996 loss: 0.3739 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3739 2023/03/06 23:30:55 - mmengine - INFO - Epoch(train) [3][ 600/1567] lr: 9.4629e-02 eta: 0:41:34 time: 0.1139 data_time: 0.0065 memory: 1996 loss: 0.3432 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3432 2023/03/06 23:31:06 - mmengine - INFO - Epoch(train) [3][ 700/1567] lr: 9.4343e-02 eta: 0:41:21 time: 0.1158 data_time: 0.0068 memory: 1996 loss: 0.4548 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4548 2023/03/06 23:31:18 - mmengine - INFO - Epoch(train) [3][ 800/1567] lr: 9.4050e-02 eta: 0:41:08 time: 0.1137 data_time: 0.0074 memory: 1996 loss: 0.4366 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4366 2023/03/06 23:31:25 - mmengine - INFO - Exp name: ctrgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230306_232308 2023/03/06 23:31:29 - mmengine - INFO - Epoch(train) [3][ 900/1567] lr: 9.3750e-02 eta: 0:40:56 time: 0.1139 data_time: 0.0065 memory: 1996 loss: 0.3235 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3235 2023/03/06 23:31:41 - mmengine - INFO - Epoch(train) [3][1000/1567] lr: 9.3444e-02 eta: 0:40:43 time: 0.1153 data_time: 0.0065 memory: 1996 loss: 0.4234 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.4234 2023/03/06 23:31:53 - mmengine - INFO - Epoch(train) [3][1100/1567] lr: 9.3130e-02 eta: 0:40:32 time: 0.1144 data_time: 0.0072 memory: 1996 loss: 0.4255 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4255 2023/03/06 23:32:04 - mmengine - INFO - Epoch(train) [3][1200/1567] lr: 9.2810e-02 eta: 0:40:20 time: 0.1140 data_time: 0.0065 memory: 1996 loss: 0.3207 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3207 2023/03/06 23:32:16 - mmengine - INFO - Epoch(train) [3][1300/1567] lr: 9.2483e-02 eta: 0:40:07 time: 0.1140 data_time: 0.0066 memory: 1996 loss: 0.3963 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.3963 2023/03/06 23:32:27 - mmengine - INFO - Epoch(train) [3][1400/1567] lr: 9.2149e-02 eta: 0:39:55 time: 0.1131 data_time: 0.0066 memory: 1996 loss: 0.3103 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3103 2023/03/06 23:32:39 - mmengine - INFO - Epoch(train) [3][1500/1567] lr: 9.1809e-02 eta: 0:39:42 time: 0.1140 data_time: 0.0065 memory: 1996 loss: 0.3150 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3150 2023/03/06 23:32:46 - mmengine - INFO - Exp name: ctrgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230306_232308 2023/03/06 23:32:46 - mmengine - INFO - Epoch(train) [3][1567/1567] lr: 9.1577e-02 eta: 0:39:34 time: 0.1137 data_time: 0.0065 memory: 1996 loss: 0.6639 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.6639 2023/03/06 23:32:46 - mmengine - INFO - Saving checkpoint at 3 epochs 2023/03/06 23:32:51 - mmengine - INFO - Epoch(val) [3][100/129] eta: 0:00:01 time: 0.0382 data_time: 0.0063 memory: 156 2023/03/06 23:32:52 - mmengine - INFO - Epoch(val) [3][129/129] acc/top1: 0.7298 acc/top5: 0.9627 acc/mean1: 0.7296 2023/03/06 23:32:52 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/projects/ctrgcn/work_dirs/ctrgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_2.pth is removed 2023/03/06 23:32:52 - mmengine - INFO - The best checkpoint with 0.7298 acc/top1 at 3 epoch is saved to best_acc/top1_epoch_3.pth. 2023/03/06 23:33:04 - mmengine - INFO - Epoch(train) [4][ 100/1567] lr: 9.1226e-02 eta: 0:39:21 time: 0.1139 data_time: 0.0065 memory: 1996 loss: 0.3471 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3471 2023/03/06 23:33:15 - mmengine - INFO - Epoch(train) [4][ 200/1567] lr: 9.0868e-02 eta: 0:39:10 time: 0.1147 data_time: 0.0074 memory: 1996 loss: 0.4409 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.4409 2023/03/06 23:33:27 - mmengine - INFO - Exp name: ctrgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230306_232308 2023/03/06 23:33:27 - mmengine - INFO - Epoch(train) [4][ 300/1567] lr: 9.0504e-02 eta: 0:38:58 time: 0.1154 data_time: 0.0066 memory: 1996 loss: 0.2959 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2959 2023/03/06 23:33:38 - mmengine - INFO - Epoch(train) [4][ 400/1567] lr: 9.0133e-02 eta: 0:38:45 time: 0.1126 data_time: 0.0064 memory: 1996 loss: 0.2608 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2608 2023/03/06 23:33:50 - mmengine - INFO - Epoch(train) [4][ 500/1567] lr: 8.9756e-02 eta: 0:38:32 time: 0.1138 data_time: 0.0074 memory: 1996 loss: 0.3899 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.3899 2023/03/06 23:34:01 - mmengine - INFO - Epoch(train) [4][ 600/1567] lr: 8.9373e-02 eta: 0:38:20 time: 0.1141 data_time: 0.0066 memory: 1996 loss: 0.3096 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.3096 2023/03/06 23:34:13 - mmengine - INFO - Epoch(train) [4][ 700/1567] lr: 8.8984e-02 eta: 0:38:09 time: 0.1135 data_time: 0.0065 memory: 1996 loss: 0.2611 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2611 2023/03/06 23:34:25 - mmengine - INFO - Epoch(train) [4][ 800/1567] lr: 8.8589e-02 eta: 0:37:57 time: 0.1146 data_time: 0.0075 memory: 1996 loss: 0.3495 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3495 2023/03/06 23:34:36 - mmengine - INFO - Epoch(train) [4][ 900/1567] lr: 8.8187e-02 eta: 0:37:45 time: 0.1205 data_time: 0.0075 memory: 1996 loss: 0.2809 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2809 2023/03/06 23:34:48 - mmengine - INFO - Epoch(train) [4][1000/1567] lr: 8.7780e-02 eta: 0:37:34 time: 0.1148 data_time: 0.0065 memory: 1996 loss: 0.3148 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3148 2023/03/06 23:34:59 - mmengine - INFO - Epoch(train) [4][1100/1567] lr: 8.7367e-02 eta: 0:37:22 time: 0.1141 data_time: 0.0066 memory: 1996 loss: 0.3902 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.3902 2023/03/06 23:35:11 - mmengine - INFO - Epoch(train) [4][1200/1567] lr: 8.6947e-02 eta: 0:37:10 time: 0.1138 data_time: 0.0067 memory: 1996 loss: 0.3313 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.3313 2023/03/06 23:35:22 - mmengine - INFO - Exp name: ctrgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230306_232308 2023/03/06 23:35:22 - mmengine - INFO - Epoch(train) [4][1300/1567] lr: 8.6522e-02 eta: 0:36:58 time: 0.1154 data_time: 0.0079 memory: 1996 loss: 0.3146 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3146 2023/03/06 23:35:34 - mmengine - INFO - Epoch(train) [4][1400/1567] lr: 8.6092e-02 eta: 0:36:45 time: 0.1144 data_time: 0.0071 memory: 1996 loss: 0.2681 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2681 2023/03/06 23:35:45 - mmengine - INFO - Epoch(train) [4][1500/1567] lr: 8.5655e-02 eta: 0:36:33 time: 0.1134 data_time: 0.0081 memory: 1996 loss: 0.3206 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3206 2023/03/06 23:35:53 - mmengine - INFO - Exp name: ctrgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230306_232308 2023/03/06 23:35:53 - mmengine - INFO - Epoch(train) [4][1567/1567] lr: 8.5360e-02 eta: 0:36:25 time: 0.1124 data_time: 0.0064 memory: 1996 loss: 0.4893 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.4893 2023/03/06 23:35:53 - mmengine - INFO - Saving checkpoint at 4 epochs 2023/03/06 23:35:57 - mmengine - INFO - Epoch(val) [4][100/129] eta: 0:00:01 time: 0.0412 data_time: 0.0068 memory: 156 2023/03/06 23:35:58 - mmengine - INFO - Epoch(val) [4][129/129] acc/top1: 0.7336 acc/top5: 0.9624 acc/mean1: 0.7336 2023/03/06 23:35:58 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/projects/ctrgcn/work_dirs/ctrgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_3.pth is removed 2023/03/06 23:35:59 - mmengine - INFO - The best checkpoint with 0.7336 acc/top1 at 4 epoch is saved to best_acc/top1_epoch_4.pth. 2023/03/06 23:36:10 - mmengine - INFO - Epoch(train) [5][ 100/1567] lr: 8.4914e-02 eta: 0:36:14 time: 0.1136 data_time: 0.0064 memory: 1996 loss: 0.2956 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2956 2023/03/06 23:36:22 - mmengine - INFO - Epoch(train) [5][ 200/1567] lr: 8.4463e-02 eta: 0:36:01 time: 0.1149 data_time: 0.0070 memory: 1996 loss: 0.2977 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.2977 2023/03/06 23:36:33 - mmengine - INFO - Epoch(train) [5][ 300/1567] lr: 8.4006e-02 eta: 0:35:49 time: 0.1124 data_time: 0.0072 memory: 1996 loss: 0.2882 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2882 2023/03/06 23:36:45 - mmengine - INFO - Epoch(train) [5][ 400/1567] lr: 8.3544e-02 eta: 0:35:37 time: 0.1146 data_time: 0.0068 memory: 1996 loss: 0.3336 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.3336 2023/03/06 23:36:56 - mmengine - INFO - Epoch(train) [5][ 500/1567] lr: 8.3077e-02 eta: 0:35:25 time: 0.1132 data_time: 0.0081 memory: 1996 loss: 0.2783 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2783 2023/03/06 23:37:08 - mmengine - INFO - Epoch(train) [5][ 600/1567] lr: 8.2605e-02 eta: 0:35:14 time: 0.1171 data_time: 0.0067 memory: 1996 loss: 0.2778 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2778 2023/03/06 23:37:19 - mmengine - INFO - Epoch(train) [5][ 700/1567] lr: 8.2127e-02 eta: 0:35:02 time: 0.1135 data_time: 0.0064 memory: 1996 loss: 0.2992 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2992 2023/03/06 23:37:23 - mmengine - INFO - Exp name: ctrgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230306_232308 2023/03/06 23:37:31 - mmengine - INFO - Epoch(train) [5][ 800/1567] lr: 8.1645e-02 eta: 0:34:50 time: 0.1163 data_time: 0.0067 memory: 1996 loss: 0.2822 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.2822 2023/03/06 23:37:43 - mmengine - INFO - Epoch(train) [5][ 900/1567] lr: 8.1157e-02 eta: 0:34:39 time: 0.1178 data_time: 0.0065 memory: 1996 loss: 0.3444 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.3444 2023/03/06 23:37:54 - mmengine - INFO - Epoch(train) [5][1000/1567] lr: 8.0665e-02 eta: 0:34:28 time: 0.1168 data_time: 0.0065 memory: 1996 loss: 0.3069 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3069 2023/03/06 23:38:06 - mmengine - INFO - Epoch(train) [5][1100/1567] lr: 8.0167e-02 eta: 0:34:17 time: 0.1180 data_time: 0.0068 memory: 1996 loss: 0.2672 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2672 2023/03/06 23:38:18 - mmengine - INFO - Epoch(train) [5][1200/1567] lr: 7.9665e-02 eta: 0:34:05 time: 0.1134 data_time: 0.0073 memory: 1996 loss: 0.2745 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2745 2023/03/06 23:38:29 - mmengine - INFO - Epoch(train) [5][1300/1567] lr: 7.9159e-02 eta: 0:33:53 time: 0.1130 data_time: 0.0064 memory: 1996 loss: 0.2393 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2393 2023/03/06 23:38:41 - mmengine - INFO - Epoch(train) [5][1400/1567] lr: 7.8647e-02 eta: 0:33:41 time: 0.1125 data_time: 0.0064 memory: 1996 loss: 0.2590 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2590 2023/03/06 23:38:52 - mmengine - INFO - Epoch(train) [5][1500/1567] lr: 7.8132e-02 eta: 0:33:29 time: 0.1143 data_time: 0.0067 memory: 1996 loss: 0.2080 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2080 2023/03/06 23:39:00 - mmengine - INFO - Exp name: ctrgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230306_232308 2023/03/06 23:39:00 - mmengine - INFO - Epoch(train) [5][1567/1567] lr: 7.7784e-02 eta: 0:33:21 time: 0.1139 data_time: 0.0071 memory: 1996 loss: 0.5656 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.5656 2023/03/06 23:39:00 - mmengine - INFO - Saving checkpoint at 5 epochs 2023/03/06 23:39:04 - mmengine - INFO - Epoch(val) [5][100/129] eta: 0:00:01 time: 0.0367 data_time: 0.0068 memory: 156 2023/03/06 23:39:06 - mmengine - INFO - Epoch(val) [5][129/129] acc/top1: 0.7818 acc/top5: 0.9716 acc/mean1: 0.7819 2023/03/06 23:39:06 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/projects/ctrgcn/work_dirs/ctrgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_4.pth is removed 2023/03/06 23:39:06 - mmengine - INFO - The best checkpoint with 0.7818 acc/top1 at 5 epoch is saved to best_acc/top1_epoch_5.pth. 2023/03/06 23:39:17 - mmengine - INFO - Epoch(train) [6][ 100/1567] lr: 7.7261e-02 eta: 0:33:09 time: 0.1124 data_time: 0.0065 memory: 1996 loss: 0.2762 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2762 2023/03/06 23:39:25 - mmengine - INFO - Exp name: ctrgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230306_232308 2023/03/06 23:39:29 - mmengine - INFO - Epoch(train) [6][ 200/1567] lr: 7.6733e-02 eta: 0:32:57 time: 0.1135 data_time: 0.0065 memory: 1996 loss: 0.3240 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3240 2023/03/06 23:39:40 - mmengine - INFO - Epoch(train) [6][ 300/1567] lr: 7.6202e-02 eta: 0:32:45 time: 0.1161 data_time: 0.0083 memory: 1996 loss: 0.2167 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2167 2023/03/06 23:39:52 - mmengine - INFO - Epoch(train) [6][ 400/1567] lr: 7.5666e-02 eta: 0:32:34 time: 0.1185 data_time: 0.0074 memory: 1996 loss: 0.3764 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.3764 2023/03/06 23:40:04 - mmengine - INFO - Epoch(train) [6][ 500/1567] lr: 7.5126e-02 eta: 0:32:22 time: 0.1178 data_time: 0.0066 memory: 1996 loss: 0.2971 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2971 2023/03/06 23:40:15 - mmengine - INFO - Epoch(train) [6][ 600/1567] lr: 7.4583e-02 eta: 0:32:10 time: 0.1159 data_time: 0.0072 memory: 1996 loss: 0.3194 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3194 2023/03/06 23:40:27 - mmengine - INFO - Epoch(train) [6][ 700/1567] lr: 7.4035e-02 eta: 0:31:59 time: 0.1128 data_time: 0.0066 memory: 1996 loss: 0.2336 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2336 2023/03/06 23:40:38 - mmengine - INFO - Epoch(train) [6][ 800/1567] lr: 7.3484e-02 eta: 0:31:47 time: 0.1158 data_time: 0.0070 memory: 1996 loss: 0.2394 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2394 2023/03/06 23:40:50 - mmengine - INFO - Epoch(train) [6][ 900/1567] lr: 7.2929e-02 eta: 0:31:36 time: 0.1178 data_time: 0.0067 memory: 1996 loss: 0.2400 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2400 2023/03/06 23:41:02 - mmengine - INFO - Epoch(train) [6][1000/1567] lr: 7.2371e-02 eta: 0:31:24 time: 0.1136 data_time: 0.0065 memory: 1996 loss: 0.2898 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2898 2023/03/06 23:41:13 - mmengine - INFO - Epoch(train) [6][1100/1567] lr: 7.1809e-02 eta: 0:31:12 time: 0.1125 data_time: 0.0066 memory: 1996 loss: 0.2818 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2818 2023/03/06 23:41:20 - mmengine - INFO - Exp name: ctrgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230306_232308 2023/03/06 23:41:24 - mmengine - INFO - Epoch(train) [6][1200/1567] lr: 7.1243e-02 eta: 0:31:00 time: 0.1137 data_time: 0.0064 memory: 1996 loss: 0.2301 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.2301 2023/03/06 23:41:36 - mmengine - INFO - Epoch(train) [6][1300/1567] lr: 7.0674e-02 eta: 0:30:49 time: 0.1198 data_time: 0.0071 memory: 1996 loss: 0.2364 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2364 2023/03/06 23:41:48 - mmengine - INFO - Epoch(train) [6][1400/1567] lr: 7.0102e-02 eta: 0:30:37 time: 0.1155 data_time: 0.0066 memory: 1996 loss: 0.2559 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.2559 2023/03/06 23:42:00 - mmengine - INFO - Epoch(train) [6][1500/1567] lr: 6.9527e-02 eta: 0:30:26 time: 0.1246 data_time: 0.0081 memory: 1996 loss: 0.2413 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.2413 2023/03/06 23:42:07 - mmengine - INFO - Exp name: ctrgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230306_232308 2023/03/06 23:42:07 - mmengine - INFO - Epoch(train) [6][1567/1567] lr: 6.9140e-02 eta: 0:30:18 time: 0.1141 data_time: 0.0065 memory: 1996 loss: 0.4460 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.4460 2023/03/06 23:42:07 - mmengine - INFO - Saving checkpoint at 6 epochs 2023/03/06 23:42:12 - mmengine - INFO - Epoch(val) [6][100/129] eta: 0:00:01 time: 0.0375 data_time: 0.0064 memory: 156 2023/03/06 23:42:13 - mmengine - INFO - Epoch(val) [6][129/129] acc/top1: 0.6953 acc/top5: 0.9480 acc/mean1: 0.6952 2023/03/06 23:42:24 - mmengine - INFO - Epoch(train) [7][ 100/1567] lr: 6.8560e-02 eta: 0:30:06 time: 0.1133 data_time: 0.0065 memory: 1996 loss: 0.2676 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2676 2023/03/06 23:42:36 - mmengine - INFO - Epoch(train) [7][ 200/1567] lr: 6.7976e-02 eta: 0:29:55 time: 0.1162 data_time: 0.0068 memory: 1996 loss: 0.2050 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2050 2023/03/06 23:42:47 - mmengine - INFO - Epoch(train) [7][ 300/1567] lr: 6.7390e-02 eta: 0:29:43 time: 0.1130 data_time: 0.0065 memory: 1996 loss: 0.2926 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2926 2023/03/06 23:42:59 - mmengine - INFO - Epoch(train) [7][ 400/1567] lr: 6.6802e-02 eta: 0:29:31 time: 0.1135 data_time: 0.0070 memory: 1996 loss: 0.2506 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2506 2023/03/06 23:43:10 - mmengine - INFO - Epoch(train) [7][ 500/1567] lr: 6.6210e-02 eta: 0:29:19 time: 0.1141 data_time: 0.0067 memory: 1996 loss: 0.2458 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2458 2023/03/06 23:43:22 - mmengine - INFO - Exp name: ctrgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230306_232308 2023/03/06 23:43:22 - mmengine - INFO - Epoch(train) [7][ 600/1567] lr: 6.5616e-02 eta: 0:29:07 time: 0.1175 data_time: 0.0067 memory: 1996 loss: 0.2277 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2277 2023/03/06 23:43:33 - mmengine - INFO - Epoch(train) [7][ 700/1567] lr: 6.5020e-02 eta: 0:28:56 time: 0.1135 data_time: 0.0065 memory: 1996 loss: 0.2527 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2527 2023/03/06 23:43:45 - mmengine - INFO - Epoch(train) [7][ 800/1567] lr: 6.4421e-02 eta: 0:28:44 time: 0.1180 data_time: 0.0066 memory: 1996 loss: 0.2351 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2351 2023/03/06 23:43:57 - mmengine - INFO - Epoch(train) [7][ 900/1567] lr: 6.3820e-02 eta: 0:28:33 time: 0.1140 data_time: 0.0065 memory: 1996 loss: 0.2080 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2080 2023/03/06 23:44:08 - mmengine - INFO - Epoch(train) [7][1000/1567] lr: 6.3217e-02 eta: 0:28:21 time: 0.1168 data_time: 0.0072 memory: 1996 loss: 0.3366 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.3366 2023/03/06 23:44:20 - mmengine - INFO - Epoch(train) [7][1100/1567] lr: 6.2612e-02 eta: 0:28:10 time: 0.1165 data_time: 0.0067 memory: 1996 loss: 0.1903 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1903 2023/03/06 23:44:31 - mmengine - INFO - Epoch(train) [7][1200/1567] lr: 6.2005e-02 eta: 0:27:58 time: 0.1136 data_time: 0.0065 memory: 1996 loss: 0.2199 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2199 2023/03/06 23:44:43 - mmengine - INFO - Epoch(train) [7][1300/1567] lr: 6.1396e-02 eta: 0:27:46 time: 0.1152 data_time: 0.0080 memory: 1996 loss: 0.2526 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2526 2023/03/06 23:44:55 - mmengine - INFO - Epoch(train) [7][1400/1567] lr: 6.0785e-02 eta: 0:27:35 time: 0.1133 data_time: 0.0074 memory: 1996 loss: 0.2548 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2548 2023/03/06 23:45:07 - mmengine - INFO - Epoch(train) [7][1500/1567] lr: 6.0172e-02 eta: 0:27:24 time: 0.1183 data_time: 0.0067 memory: 1996 loss: 0.2041 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2041 2023/03/06 23:45:15 - mmengine - INFO - Exp name: ctrgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230306_232308 2023/03/06 23:45:15 - mmengine - INFO - Epoch(train) [7][1567/1567] lr: 5.9761e-02 eta: 0:27:16 time: 0.1128 data_time: 0.0068 memory: 1996 loss: 0.3098 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3098 2023/03/06 23:45:15 - mmengine - INFO - Saving checkpoint at 7 epochs 2023/03/06 23:45:19 - mmengine - INFO - Epoch(val) [7][100/129] eta: 0:00:01 time: 0.0371 data_time: 0.0064 memory: 156 2023/03/06 23:45:20 - mmengine - INFO - Epoch(val) [7][129/129] acc/top1: 0.8080 acc/top5: 0.9782 acc/mean1: 0.8080 2023/03/06 23:45:20 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/projects/ctrgcn/work_dirs/ctrgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_5.pth is removed 2023/03/06 23:45:21 - mmengine - INFO - The best checkpoint with 0.8080 acc/top1 at 7 epoch is saved to best_acc/top1_epoch_7.pth. 2023/03/06 23:45:24 - mmengine - INFO - Exp name: ctrgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230306_232308 2023/03/06 23:45:32 - mmengine - INFO - Epoch(train) [8][ 100/1567] lr: 5.9145e-02 eta: 0:27:04 time: 0.1147 data_time: 0.0074 memory: 1996 loss: 0.2247 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.2247 2023/03/06 23:45:44 - mmengine - INFO - Epoch(train) [8][ 200/1567] lr: 5.8529e-02 eta: 0:26:53 time: 0.1139 data_time: 0.0066 memory: 1996 loss: 0.1673 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1673 2023/03/06 23:45:56 - mmengine - INFO - Epoch(train) [8][ 300/1567] lr: 5.7911e-02 eta: 0:26:41 time: 0.1175 data_time: 0.0065 memory: 1996 loss: 0.1650 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1650 2023/03/06 23:46:07 - mmengine - INFO - Epoch(train) [8][ 400/1567] lr: 5.7292e-02 eta: 0:26:30 time: 0.1156 data_time: 0.0067 memory: 1996 loss: 0.1921 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1921 2023/03/06 23:46:19 - mmengine - INFO - Epoch(train) [8][ 500/1567] lr: 5.6671e-02 eta: 0:26:18 time: 0.1176 data_time: 0.0066 memory: 1996 loss: 0.1914 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1914 2023/03/06 23:46:31 - mmengine - INFO - Epoch(train) [8][ 600/1567] lr: 5.6050e-02 eta: 0:26:07 time: 0.1141 data_time: 0.0071 memory: 1996 loss: 0.1600 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.1600 2023/03/06 23:46:42 - mmengine - INFO - Epoch(train) [8][ 700/1567] lr: 5.5427e-02 eta: 0:25:55 time: 0.1153 data_time: 0.0070 memory: 1996 loss: 0.2108 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2108 2023/03/06 23:46:54 - mmengine - INFO - Epoch(train) [8][ 800/1567] lr: 5.4804e-02 eta: 0:25:44 time: 0.1142 data_time: 0.0065 memory: 1996 loss: 0.2103 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2103 2023/03/06 23:47:05 - mmengine - INFO - Epoch(train) [8][ 900/1567] lr: 5.4180e-02 eta: 0:25:32 time: 0.1173 data_time: 0.0070 memory: 1996 loss: 0.1953 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1953 2023/03/06 23:47:17 - mmengine - INFO - Epoch(train) [8][1000/1567] lr: 5.3556e-02 eta: 0:25:20 time: 0.1146 data_time: 0.0066 memory: 1996 loss: 0.2415 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2415 2023/03/06 23:47:21 - mmengine - INFO - Exp name: ctrgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230306_232308 2023/03/06 23:47:29 - mmengine - INFO - Epoch(train) [8][1100/1567] lr: 5.2930e-02 eta: 0:25:09 time: 0.1220 data_time: 0.0066 memory: 1996 loss: 0.1774 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1774 2023/03/06 23:47:41 - mmengine - INFO - Epoch(train) [8][1200/1567] lr: 5.2305e-02 eta: 0:24:58 time: 0.1181 data_time: 0.0074 memory: 1996 loss: 0.1607 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1607 2023/03/06 23:47:53 - mmengine - INFO - Epoch(train) [8][1300/1567] lr: 5.1679e-02 eta: 0:24:46 time: 0.1160 data_time: 0.0067 memory: 1996 loss: 0.2018 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2018 2023/03/06 23:48:04 - mmengine - INFO - Epoch(train) [8][1400/1567] lr: 5.1052e-02 eta: 0:24:35 time: 0.1198 data_time: 0.0068 memory: 1996 loss: 0.1386 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1386 2023/03/06 23:48:17 - mmengine - INFO - Epoch(train) [8][1500/1567] lr: 5.0426e-02 eta: 0:24:24 time: 0.1189 data_time: 0.0074 memory: 1996 loss: 0.1676 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.1676 2023/03/06 23:48:25 - mmengine - INFO - Exp name: ctrgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230306_232308 2023/03/06 23:48:25 - mmengine - INFO - Epoch(train) [8][1567/1567] lr: 5.0006e-02 eta: 0:24:16 time: 0.1187 data_time: 0.0073 memory: 1996 loss: 0.3444 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.3444 2023/03/06 23:48:25 - mmengine - INFO - Saving checkpoint at 8 epochs 2023/03/06 23:48:29 - mmengine - INFO - Epoch(val) [8][100/129] eta: 0:00:01 time: 0.0385 data_time: 0.0071 memory: 156 2023/03/06 23:48:30 - mmengine - INFO - Epoch(val) [8][129/129] acc/top1: 0.8306 acc/top5: 0.9770 acc/mean1: 0.8306 2023/03/06 23:48:30 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/projects/ctrgcn/work_dirs/ctrgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_7.pth is removed 2023/03/06 23:48:31 - mmengine - INFO - The best checkpoint with 0.8306 acc/top1 at 8 epoch is saved to best_acc/top1_epoch_8.pth. 2023/03/06 23:48:42 - mmengine - INFO - Epoch(train) [9][ 100/1567] lr: 4.9380e-02 eta: 0:24:04 time: 0.1139 data_time: 0.0073 memory: 1996 loss: 0.1857 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.1857 2023/03/06 23:48:54 - mmengine - INFO - Epoch(train) [9][ 200/1567] lr: 4.8753e-02 eta: 0:23:53 time: 0.1137 data_time: 0.0066 memory: 1996 loss: 0.1684 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1684 2023/03/06 23:49:05 - mmengine - INFO - Epoch(train) [9][ 300/1567] lr: 4.8127e-02 eta: 0:23:41 time: 0.1167 data_time: 0.0069 memory: 1996 loss: 0.1467 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1467 2023/03/06 23:49:17 - mmengine - INFO - Epoch(train) [9][ 400/1567] lr: 4.7501e-02 eta: 0:23:30 time: 0.1157 data_time: 0.0064 memory: 1996 loss: 0.1570 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.1570 2023/03/06 23:49:24 - mmengine - INFO - Exp name: ctrgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230306_232308 2023/03/06 23:49:29 - mmengine - INFO - Epoch(train) [9][ 500/1567] lr: 4.6876e-02 eta: 0:23:18 time: 0.1187 data_time: 0.0066 memory: 1996 loss: 0.1432 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1432 2023/03/06 23:49:40 - mmengine - INFO - Epoch(train) [9][ 600/1567] lr: 4.6251e-02 eta: 0:23:06 time: 0.1175 data_time: 0.0065 memory: 1996 loss: 0.1419 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.1419 2023/03/06 23:49:52 - mmengine - INFO - Epoch(train) [9][ 700/1567] lr: 4.5626e-02 eta: 0:22:55 time: 0.1167 data_time: 0.0069 memory: 1996 loss: 0.1947 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.1947 2023/03/06 23:50:03 - mmengine - INFO - Epoch(train) [9][ 800/1567] lr: 4.5003e-02 eta: 0:22:43 time: 0.1137 data_time: 0.0070 memory: 1996 loss: 0.1447 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1447 2023/03/06 23:50:15 - mmengine - INFO - Epoch(train) [9][ 900/1567] lr: 4.4380e-02 eta: 0:22:31 time: 0.1141 data_time: 0.0072 memory: 1996 loss: 0.1600 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1600 2023/03/06 23:50:27 - mmengine - INFO - Epoch(train) [9][1000/1567] lr: 4.3757e-02 eta: 0:22:20 time: 0.1161 data_time: 0.0065 memory: 1996 loss: 0.1534 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1534 2023/03/06 23:50:38 - mmengine - INFO - Epoch(train) [9][1100/1567] lr: 4.3136e-02 eta: 0:22:08 time: 0.1135 data_time: 0.0082 memory: 1996 loss: 0.1823 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1823 2023/03/06 23:50:50 - mmengine - INFO - Epoch(train) [9][1200/1567] lr: 4.2516e-02 eta: 0:21:57 time: 0.1177 data_time: 0.0071 memory: 1996 loss: 0.1096 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.1096 2023/03/06 23:51:01 - mmengine - INFO - Epoch(train) [9][1300/1567] lr: 4.1897e-02 eta: 0:21:45 time: 0.1191 data_time: 0.0068 memory: 1996 loss: 0.1912 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1912 2023/03/06 23:51:13 - mmengine - INFO - Epoch(train) [9][1400/1567] lr: 4.1280e-02 eta: 0:21:34 time: 0.1145 data_time: 0.0066 memory: 1996 loss: 0.1361 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1361 2023/03/06 23:51:21 - mmengine - INFO - Exp name: ctrgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230306_232308 2023/03/06 23:51:25 - mmengine - INFO - Epoch(train) [9][1500/1567] lr: 4.0664e-02 eta: 0:21:22 time: 0.1203 data_time: 0.0065 memory: 1996 loss: 0.1223 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1223 2023/03/06 23:51:33 - mmengine - INFO - Exp name: ctrgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230306_232308 2023/03/06 23:51:33 - mmengine - INFO - Epoch(train) [9][1567/1567] lr: 4.0252e-02 eta: 0:21:14 time: 0.1125 data_time: 0.0063 memory: 1996 loss: 0.3427 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.3427 2023/03/06 23:51:33 - mmengine - INFO - Saving checkpoint at 9 epochs 2023/03/06 23:51:38 - mmengine - INFO - Epoch(val) [9][100/129] eta: 0:00:01 time: 0.0416 data_time: 0.0068 memory: 156 2023/03/06 23:51:39 - mmengine - INFO - Epoch(val) [9][129/129] acc/top1: 0.8311 acc/top5: 0.9785 acc/mean1: 0.8310 2023/03/06 23:51:39 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/projects/ctrgcn/work_dirs/ctrgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_8.pth is removed 2023/03/06 23:51:39 - mmengine - INFO - The best checkpoint with 0.8311 acc/top1 at 9 epoch is saved to best_acc/top1_epoch_9.pth. 2023/03/06 23:51:51 - mmengine - INFO - Epoch(train) [10][ 100/1567] lr: 3.9638e-02 eta: 0:21:03 time: 0.1164 data_time: 0.0067 memory: 1996 loss: 0.1636 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1636 2023/03/06 23:52:02 - mmengine - INFO - Epoch(train) [10][ 200/1567] lr: 3.9026e-02 eta: 0:20:51 time: 0.1128 data_time: 0.0065 memory: 1996 loss: 0.0781 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0781 2023/03/06 23:52:14 - mmengine - INFO - Epoch(train) [10][ 300/1567] lr: 3.8415e-02 eta: 0:20:39 time: 0.1135 data_time: 0.0066 memory: 1996 loss: 0.1368 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1368 2023/03/06 23:52:26 - mmengine - INFO - Epoch(train) [10][ 400/1567] lr: 3.7807e-02 eta: 0:20:28 time: 0.1141 data_time: 0.0065 memory: 1996 loss: 0.1314 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1314 2023/03/06 23:52:37 - mmengine - INFO - Epoch(train) [10][ 500/1567] lr: 3.7200e-02 eta: 0:20:16 time: 0.1178 data_time: 0.0068 memory: 1996 loss: 0.0883 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0883 2023/03/06 23:52:49 - mmengine - INFO - Epoch(train) [10][ 600/1567] lr: 3.6596e-02 eta: 0:20:04 time: 0.1166 data_time: 0.0066 memory: 1996 loss: 0.1192 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.1192 2023/03/06 23:53:00 - mmengine - INFO - Epoch(train) [10][ 700/1567] lr: 3.5993e-02 eta: 0:19:53 time: 0.1151 data_time: 0.0066 memory: 1996 loss: 0.1164 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.1164 2023/03/06 23:53:12 - mmengine - INFO - Epoch(train) [10][ 800/1567] lr: 3.5393e-02 eta: 0:19:41 time: 0.1140 data_time: 0.0066 memory: 1996 loss: 0.1405 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1405 2023/03/06 23:53:23 - mmengine - INFO - Exp name: ctrgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230306_232308 2023/03/06 23:53:23 - mmengine - INFO - Epoch(train) [10][ 900/1567] lr: 3.4795e-02 eta: 0:19:29 time: 0.1142 data_time: 0.0066 memory: 1996 loss: 0.1267 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1267 2023/03/06 23:53:35 - mmengine - INFO - Epoch(train) [10][1000/1567] lr: 3.4199e-02 eta: 0:19:18 time: 0.1215 data_time: 0.0066 memory: 1996 loss: 0.0504 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0504 2023/03/06 23:53:47 - mmengine - INFO - Epoch(train) [10][1100/1567] lr: 3.3606e-02 eta: 0:19:06 time: 0.1142 data_time: 0.0067 memory: 1996 loss: 0.1272 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1272 2023/03/06 23:53:59 - mmengine - INFO - Epoch(train) [10][1200/1567] lr: 3.3015e-02 eta: 0:18:55 time: 0.1131 data_time: 0.0066 memory: 1996 loss: 0.0796 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0796 2023/03/06 23:54:10 - mmengine - INFO - Epoch(train) [10][1300/1567] lr: 3.2428e-02 eta: 0:18:43 time: 0.1152 data_time: 0.0065 memory: 1996 loss: 0.1038 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1038 2023/03/06 23:54:22 - mmengine - INFO - Epoch(train) [10][1400/1567] lr: 3.1842e-02 eta: 0:18:32 time: 0.1149 data_time: 0.0070 memory: 1996 loss: 0.1333 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1333 2023/03/06 23:54:33 - mmengine - INFO - Epoch(train) [10][1500/1567] lr: 3.1260e-02 eta: 0:18:20 time: 0.1149 data_time: 0.0067 memory: 1996 loss: 0.0819 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0819 2023/03/06 23:54:41 - mmengine - INFO - Exp name: ctrgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230306_232308 2023/03/06 23:54:41 - mmengine - INFO - Epoch(train) [10][1567/1567] lr: 3.0872e-02 eta: 0:18:12 time: 0.1136 data_time: 0.0062 memory: 1996 loss: 0.2431 top1_acc: 0.0000 top5_acc: 1.0000 loss_cls: 0.2431 2023/03/06 23:54:41 - mmengine - INFO - Saving checkpoint at 10 epochs 2023/03/06 23:54:45 - mmengine - INFO - Epoch(val) [10][100/129] eta: 0:00:01 time: 0.0377 data_time: 0.0069 memory: 156 2023/03/06 23:54:46 - mmengine - INFO - Epoch(val) [10][129/129] acc/top1: 0.8492 acc/top5: 0.9858 acc/mean1: 0.8492 2023/03/06 23:54:46 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/projects/ctrgcn/work_dirs/ctrgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_9.pth is removed 2023/03/06 23:54:47 - mmengine - INFO - The best checkpoint with 0.8492 acc/top1 at 10 epoch is saved to best_acc/top1_epoch_10.pth. 2023/03/06 23:54:58 - mmengine - INFO - Epoch(train) [11][ 100/1567] lr: 3.0294e-02 eta: 0:18:00 time: 0.1154 data_time: 0.0070 memory: 1996 loss: 0.0567 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0567 2023/03/06 23:55:10 - mmengine - INFO - Epoch(train) [11][ 200/1567] lr: 2.9720e-02 eta: 0:17:49 time: 0.1141 data_time: 0.0068 memory: 1996 loss: 0.0928 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0928 2023/03/06 23:55:22 - mmengine - INFO - Epoch(train) [11][ 300/1567] lr: 2.9149e-02 eta: 0:17:37 time: 0.1357 data_time: 0.0069 memory: 1996 loss: 0.0778 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0778 2023/03/06 23:55:25 - mmengine - INFO - Exp name: ctrgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230306_232308 2023/03/06 23:55:33 - mmengine - INFO - Epoch(train) [11][ 400/1567] lr: 2.8581e-02 eta: 0:17:25 time: 0.1135 data_time: 0.0071 memory: 1996 loss: 0.1084 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1084 2023/03/06 23:55:45 - mmengine - INFO - Epoch(train) [11][ 500/1567] lr: 2.8017e-02 eta: 0:17:14 time: 0.1145 data_time: 0.0068 memory: 1996 loss: 0.0873 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0873 2023/03/06 23:55:56 - mmengine - INFO - Epoch(train) [11][ 600/1567] lr: 2.7456e-02 eta: 0:17:02 time: 0.1135 data_time: 0.0067 memory: 1996 loss: 0.0777 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0777 2023/03/06 23:56:08 - mmengine - INFO - Epoch(train) [11][ 700/1567] lr: 2.6898e-02 eta: 0:16:50 time: 0.1133 data_time: 0.0066 memory: 1996 loss: 0.0891 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0891 2023/03/06 23:56:19 - mmengine - INFO - Epoch(train) [11][ 800/1567] lr: 2.6345e-02 eta: 0:16:39 time: 0.1159 data_time: 0.0066 memory: 1996 loss: 0.0743 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0743 2023/03/06 23:56:31 - mmengine - INFO - Epoch(train) [11][ 900/1567] lr: 2.5794e-02 eta: 0:16:27 time: 0.1134 data_time: 0.0065 memory: 1996 loss: 0.0679 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0679 2023/03/06 23:56:42 - mmengine - INFO - Epoch(train) [11][1000/1567] lr: 2.5248e-02 eta: 0:16:15 time: 0.1170 data_time: 0.0065 memory: 1996 loss: 0.1140 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1140 2023/03/06 23:56:54 - mmengine - INFO - Epoch(train) [11][1100/1567] lr: 2.4706e-02 eta: 0:16:04 time: 0.1141 data_time: 0.0065 memory: 1996 loss: 0.1066 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1066 2023/03/06 23:57:05 - mmengine - INFO - Epoch(train) [11][1200/1567] lr: 2.4167e-02 eta: 0:15:52 time: 0.1225 data_time: 0.0070 memory: 1996 loss: 0.1028 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1028 2023/03/06 23:57:17 - mmengine - INFO - Epoch(train) [11][1300/1567] lr: 2.3633e-02 eta: 0:15:41 time: 0.1155 data_time: 0.0065 memory: 1996 loss: 0.0546 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0546 2023/03/06 23:57:21 - mmengine - INFO - Exp name: ctrgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230306_232308 2023/03/06 23:57:29 - mmengine - INFO - Epoch(train) [11][1400/1567] lr: 2.3103e-02 eta: 0:15:29 time: 0.1146 data_time: 0.0066 memory: 1996 loss: 0.0704 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0704 2023/03/06 23:57:41 - mmengine - INFO - Epoch(train) [11][1500/1567] lr: 2.2577e-02 eta: 0:15:18 time: 0.1180 data_time: 0.0066 memory: 1996 loss: 0.0899 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0899 2023/03/06 23:57:49 - mmengine - INFO - Exp name: ctrgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230306_232308 2023/03/06 23:57:49 - mmengine - INFO - Epoch(train) [11][1567/1567] lr: 2.2227e-02 eta: 0:15:10 time: 0.1162 data_time: 0.0069 memory: 1996 loss: 0.2681 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.2681 2023/03/06 23:57:49 - mmengine - INFO - Saving checkpoint at 11 epochs 2023/03/06 23:57:53 - mmengine - INFO - Epoch(val) [11][100/129] eta: 0:00:01 time: 0.0373 data_time: 0.0061 memory: 156 2023/03/06 23:57:54 - mmengine - INFO - Epoch(val) [11][129/129] acc/top1: 0.8638 acc/top5: 0.9871 acc/mean1: 0.8637 2023/03/06 23:57:54 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/projects/ctrgcn/work_dirs/ctrgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_10.pth is removed 2023/03/06 23:57:55 - mmengine - INFO - The best checkpoint with 0.8638 acc/top1 at 11 epoch is saved to best_acc/top1_epoch_11.pth. 2023/03/06 23:58:07 - mmengine - INFO - Epoch(train) [12][ 100/1567] lr: 2.1708e-02 eta: 0:14:58 time: 0.1190 data_time: 0.0083 memory: 1996 loss: 0.0475 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0475 2023/03/06 23:58:18 - mmengine - INFO - Epoch(train) [12][ 200/1567] lr: 2.1194e-02 eta: 0:14:47 time: 0.1139 data_time: 0.0067 memory: 1996 loss: 0.0765 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0765 2023/03/06 23:58:30 - mmengine - INFO - Epoch(train) [12][ 300/1567] lr: 2.0684e-02 eta: 0:14:35 time: 0.1137 data_time: 0.0066 memory: 1996 loss: 0.0821 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.0821 2023/03/06 23:58:41 - mmengine - INFO - Epoch(train) [12][ 400/1567] lr: 2.0179e-02 eta: 0:14:23 time: 0.1134 data_time: 0.0066 memory: 1996 loss: 0.0683 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0683 2023/03/06 23:58:52 - mmengine - INFO - Epoch(train) [12][ 500/1567] lr: 1.9678e-02 eta: 0:14:12 time: 0.1134 data_time: 0.0067 memory: 1996 loss: 0.0526 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0526 2023/03/06 23:59:04 - mmengine - INFO - Epoch(train) [12][ 600/1567] lr: 1.9182e-02 eta: 0:14:00 time: 0.1138 data_time: 0.0066 memory: 1996 loss: 0.0492 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0492 2023/03/06 23:59:15 - mmengine - INFO - Epoch(train) [12][ 700/1567] lr: 1.8691e-02 eta: 0:13:48 time: 0.1146 data_time: 0.0067 memory: 1996 loss: 0.0518 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0518 2023/03/06 23:59:23 - mmengine - INFO - Exp name: ctrgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230306_232308 2023/03/06 23:59:27 - mmengine - INFO - Epoch(train) [12][ 800/1567] lr: 1.8205e-02 eta: 0:13:36 time: 0.1140 data_time: 0.0070 memory: 1996 loss: 0.0350 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0350 2023/03/06 23:59:38 - mmengine - INFO - Epoch(train) [12][ 900/1567] lr: 1.7724e-02 eta: 0:13:25 time: 0.1137 data_time: 0.0068 memory: 1996 loss: 0.0423 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0423 2023/03/06 23:59:50 - mmengine - INFO - Epoch(train) [12][1000/1567] lr: 1.7248e-02 eta: 0:13:13 time: 0.1181 data_time: 0.0066 memory: 1996 loss: 0.0499 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0499 2023/03/07 00:00:01 - mmengine - INFO - Epoch(train) [12][1100/1567] lr: 1.6778e-02 eta: 0:13:02 time: 0.1154 data_time: 0.0067 memory: 1996 loss: 0.0503 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0503 2023/03/07 00:00:13 - mmengine - INFO - Epoch(train) [12][1200/1567] lr: 1.6312e-02 eta: 0:12:50 time: 0.1151 data_time: 0.0069 memory: 1996 loss: 0.0794 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0794 2023/03/07 00:00:25 - mmengine - INFO - Epoch(train) [12][1300/1567] lr: 1.5852e-02 eta: 0:12:38 time: 0.1145 data_time: 0.0065 memory: 1996 loss: 0.0314 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0314 2023/03/07 00:00:36 - mmengine - INFO - Epoch(train) [12][1400/1567] lr: 1.5397e-02 eta: 0:12:27 time: 0.1196 data_time: 0.0067 memory: 1996 loss: 0.0670 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0670 2023/03/07 00:00:48 - mmengine - INFO - Epoch(train) [12][1500/1567] lr: 1.4947e-02 eta: 0:12:15 time: 0.1194 data_time: 0.0066 memory: 1996 loss: 0.0521 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0521 2023/03/07 00:00:56 - mmengine - INFO - Exp name: ctrgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230306_232308 2023/03/07 00:00:56 - mmengine - INFO - Epoch(train) [12][1567/1567] lr: 1.4649e-02 eta: 0:12:07 time: 0.1147 data_time: 0.0063 memory: 1996 loss: 0.2797 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.2797 2023/03/07 00:00:56 - mmengine - INFO - Saving checkpoint at 12 epochs 2023/03/07 00:01:00 - mmengine - INFO - Epoch(val) [12][100/129] eta: 0:00:01 time: 0.0375 data_time: 0.0065 memory: 156 2023/03/07 00:01:02 - mmengine - INFO - Epoch(val) [12][129/129] acc/top1: 0.8601 acc/top5: 0.9851 acc/mean1: 0.8599 2023/03/07 00:01:13 - mmengine - INFO - Epoch(train) [13][ 100/1567] lr: 1.4209e-02 eta: 0:11:56 time: 0.1147 data_time: 0.0074 memory: 1996 loss: 0.0370 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0370 2023/03/07 00:01:25 - mmengine - INFO - Exp name: ctrgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230306_232308 2023/03/07 00:01:25 - mmengine - INFO - Epoch(train) [13][ 200/1567] lr: 1.3774e-02 eta: 0:11:44 time: 0.1135 data_time: 0.0065 memory: 1996 loss: 0.0307 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0307 2023/03/07 00:01:37 - mmengine - INFO - Epoch(train) [13][ 300/1567] lr: 1.3345e-02 eta: 0:11:33 time: 0.1182 data_time: 0.0067 memory: 1996 loss: 0.0503 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0503 2023/03/07 00:01:48 - mmengine - INFO - Epoch(train) [13][ 400/1567] lr: 1.2922e-02 eta: 0:11:21 time: 0.1134 data_time: 0.0070 memory: 1996 loss: 0.0256 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0256 2023/03/07 00:02:00 - mmengine - INFO - Epoch(train) [13][ 500/1567] lr: 1.2505e-02 eta: 0:11:09 time: 0.1146 data_time: 0.0068 memory: 1996 loss: 0.0237 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0237 2023/03/07 00:02:11 - mmengine - INFO - Epoch(train) [13][ 600/1567] lr: 1.2093e-02 eta: 0:10:58 time: 0.1132 data_time: 0.0067 memory: 1996 loss: 0.0369 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0369 2023/03/07 00:02:23 - mmengine - INFO - Epoch(train) [13][ 700/1567] lr: 1.1687e-02 eta: 0:10:46 time: 0.1143 data_time: 0.0065 memory: 1996 loss: 0.0398 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0398 2023/03/07 00:02:35 - mmengine - INFO - Epoch(train) [13][ 800/1567] lr: 1.1288e-02 eta: 0:10:35 time: 0.1159 data_time: 0.0068 memory: 1996 loss: 0.0258 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0258 2023/03/07 00:02:46 - mmengine - INFO - Epoch(train) [13][ 900/1567] lr: 1.0894e-02 eta: 0:10:23 time: 0.1174 data_time: 0.0066 memory: 1996 loss: 0.0223 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0223 2023/03/07 00:02:59 - mmengine - INFO - Epoch(train) [13][1000/1567] lr: 1.0507e-02 eta: 0:10:12 time: 0.1174 data_time: 0.0066 memory: 1996 loss: 0.0201 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0201 2023/03/07 00:03:11 - mmengine - INFO - Epoch(train) [13][1100/1567] lr: 1.0126e-02 eta: 0:10:00 time: 0.1172 data_time: 0.0067 memory: 1996 loss: 0.0183 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0183 2023/03/07 00:03:22 - mmengine - INFO - Exp name: ctrgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230306_232308 2023/03/07 00:03:22 - mmengine - INFO - Epoch(train) [13][1200/1567] lr: 9.7512e-03 eta: 0:09:48 time: 0.1192 data_time: 0.0073 memory: 1996 loss: 0.0415 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0415 2023/03/07 00:03:34 - mmengine - INFO - Epoch(train) [13][1300/1567] lr: 9.3826e-03 eta: 0:09:37 time: 0.1141 data_time: 0.0066 memory: 1996 loss: 0.0227 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0227 2023/03/07 00:03:46 - mmengine - INFO - Epoch(train) [13][1400/1567] lr: 9.0204e-03 eta: 0:09:25 time: 0.1171 data_time: 0.0077 memory: 1996 loss: 0.0220 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0220 2023/03/07 00:03:58 - mmengine - INFO - Epoch(train) [13][1500/1567] lr: 8.6647e-03 eta: 0:09:14 time: 0.1160 data_time: 0.0070 memory: 1996 loss: 0.0170 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0170 2023/03/07 00:04:05 - mmengine - INFO - Exp name: ctrgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230306_232308 2023/03/07 00:04:05 - mmengine - INFO - Epoch(train) [13][1567/1567] lr: 8.4300e-03 eta: 0:09:06 time: 0.1194 data_time: 0.0065 memory: 1996 loss: 0.2406 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.2406 2023/03/07 00:04:05 - mmengine - INFO - Saving checkpoint at 13 epochs 2023/03/07 00:04:10 - mmengine - INFO - Epoch(val) [13][100/129] eta: 0:00:01 time: 0.0363 data_time: 0.0061 memory: 156 2023/03/07 00:04:11 - mmengine - INFO - Epoch(val) [13][129/129] acc/top1: 0.8774 acc/top5: 0.9870 acc/mean1: 0.8773 2023/03/07 00:04:11 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/projects/ctrgcn/work_dirs/ctrgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_11.pth is removed 2023/03/07 00:04:11 - mmengine - INFO - The best checkpoint with 0.8774 acc/top1 at 13 epoch is saved to best_acc/top1_epoch_13.pth. 2023/03/07 00:04:23 - mmengine - INFO - Epoch(train) [14][ 100/1567] lr: 8.0851e-03 eta: 0:08:54 time: 0.1166 data_time: 0.0078 memory: 1996 loss: 0.0147 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0147 2023/03/07 00:04:34 - mmengine - INFO - Epoch(train) [14][ 200/1567] lr: 7.7469e-03 eta: 0:08:43 time: 0.1138 data_time: 0.0067 memory: 1996 loss: 0.0176 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0176 2023/03/07 00:04:46 - mmengine - INFO - Epoch(train) [14][ 300/1567] lr: 7.4152e-03 eta: 0:08:31 time: 0.1182 data_time: 0.0066 memory: 1996 loss: 0.0124 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0124 2023/03/07 00:05:00 - mmengine - INFO - Epoch(train) [14][ 400/1567] lr: 7.0902e-03 eta: 0:08:20 time: 0.1440 data_time: 0.0066 memory: 1996 loss: 0.0106 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0106 2023/03/07 00:05:11 - mmengine - INFO - Epoch(train) [14][ 500/1567] lr: 6.7720e-03 eta: 0:08:08 time: 0.1142 data_time: 0.0068 memory: 1996 loss: 0.0187 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0187 2023/03/07 00:05:23 - mmengine - INFO - Epoch(train) [14][ 600/1567] lr: 6.4606e-03 eta: 0:07:56 time: 0.1138 data_time: 0.0069 memory: 1996 loss: 0.0250 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0250 2023/03/07 00:05:26 - mmengine - INFO - Exp name: ctrgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230306_232308 2023/03/07 00:05:35 - mmengine - INFO - Epoch(train) [14][ 700/1567] lr: 6.1560e-03 eta: 0:07:45 time: 0.1180 data_time: 0.0071 memory: 1996 loss: 0.0102 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0102 2023/03/07 00:05:46 - mmengine - INFO - Epoch(train) [14][ 800/1567] lr: 5.8582e-03 eta: 0:07:33 time: 0.1142 data_time: 0.0068 memory: 1996 loss: 0.0066 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0066 2023/03/07 00:05:58 - mmengine - INFO - Epoch(train) [14][ 900/1567] lr: 5.5675e-03 eta: 0:07:22 time: 0.1130 data_time: 0.0066 memory: 1996 loss: 0.0129 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0129 2023/03/07 00:06:10 - mmengine - INFO - Epoch(train) [14][1000/1567] lr: 5.2836e-03 eta: 0:07:10 time: 0.1166 data_time: 0.0067 memory: 1996 loss: 0.0132 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0132 2023/03/07 00:06:22 - mmengine - INFO - Epoch(train) [14][1100/1567] lr: 5.0068e-03 eta: 0:06:58 time: 0.1173 data_time: 0.0068 memory: 1996 loss: 0.0075 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0075 2023/03/07 00:06:33 - mmengine - INFO - Epoch(train) [14][1200/1567] lr: 4.7371e-03 eta: 0:06:47 time: 0.1143 data_time: 0.0066 memory: 1996 loss: 0.0073 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0073 2023/03/07 00:06:45 - mmengine - INFO - Epoch(train) [14][1300/1567] lr: 4.4745e-03 eta: 0:06:35 time: 0.1145 data_time: 0.0066 memory: 1996 loss: 0.0078 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0078 2023/03/07 00:06:57 - mmengine - INFO - Epoch(train) [14][1400/1567] lr: 4.2190e-03 eta: 0:06:24 time: 0.1153 data_time: 0.0066 memory: 1996 loss: 0.0175 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0175 2023/03/07 00:07:08 - mmengine - INFO - Epoch(train) [14][1500/1567] lr: 3.9707e-03 eta: 0:06:12 time: 0.1152 data_time: 0.0065 memory: 1996 loss: 0.0078 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0078 2023/03/07 00:07:16 - mmengine - INFO - Exp name: ctrgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230306_232308 2023/03/07 00:07:16 - mmengine - INFO - Epoch(train) [14][1567/1567] lr: 3.8084e-03 eta: 0:06:04 time: 0.1183 data_time: 0.0066 memory: 1996 loss: 0.2182 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.2182 2023/03/07 00:07:16 - mmengine - INFO - Saving checkpoint at 14 epochs 2023/03/07 00:07:20 - mmengine - INFO - Epoch(val) [14][100/129] eta: 0:00:01 time: 0.0388 data_time: 0.0068 memory: 156 2023/03/07 00:07:22 - mmengine - INFO - Epoch(val) [14][129/129] acc/top1: 0.8845 acc/top5: 0.9887 acc/mean1: 0.8844 2023/03/07 00:07:22 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/projects/ctrgcn/work_dirs/ctrgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_13.pth is removed 2023/03/07 00:07:22 - mmengine - INFO - The best checkpoint with 0.8845 acc/top1 at 14 epoch is saved to best_acc/top1_epoch_14.pth. 2023/03/07 00:07:29 - mmengine - INFO - Exp name: ctrgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230306_232308 2023/03/07 00:07:34 - mmengine - INFO - Epoch(train) [15][ 100/1567] lr: 3.5722e-03 eta: 0:05:52 time: 0.1152 data_time: 0.0074 memory: 1996 loss: 0.0098 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0098 2023/03/07 00:07:45 - mmengine - INFO - Epoch(train) [15][ 200/1567] lr: 3.3433e-03 eta: 0:05:41 time: 0.1161 data_time: 0.0077 memory: 1996 loss: 0.0079 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0079 2023/03/07 00:07:57 - mmengine - INFO - Epoch(train) [15][ 300/1567] lr: 3.1217e-03 eta: 0:05:29 time: 0.1150 data_time: 0.0068 memory: 1996 loss: 0.0102 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0102 2023/03/07 00:08:09 - mmengine - INFO - Epoch(train) [15][ 400/1567] lr: 2.9075e-03 eta: 0:05:18 time: 0.1160 data_time: 0.0072 memory: 1996 loss: 0.0075 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0075 2023/03/07 00:08:20 - mmengine - INFO - Epoch(train) [15][ 500/1567] lr: 2.7007e-03 eta: 0:05:06 time: 0.1225 data_time: 0.0067 memory: 1996 loss: 0.0094 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0094 2023/03/07 00:08:32 - mmengine - INFO - Epoch(train) [15][ 600/1567] lr: 2.5013e-03 eta: 0:04:54 time: 0.1155 data_time: 0.0066 memory: 1996 loss: 0.0080 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0080 2023/03/07 00:08:44 - mmengine - INFO - Epoch(train) [15][ 700/1567] lr: 2.3093e-03 eta: 0:04:43 time: 0.1172 data_time: 0.0071 memory: 1996 loss: 0.0062 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0062 2023/03/07 00:08:56 - mmengine - INFO - Epoch(train) [15][ 800/1567] lr: 2.1249e-03 eta: 0:04:31 time: 0.1197 data_time: 0.0067 memory: 1996 loss: 0.0123 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0123 2023/03/07 00:09:08 - mmengine - INFO - Epoch(train) [15][ 900/1567] lr: 1.9479e-03 eta: 0:04:19 time: 0.1217 data_time: 0.0077 memory: 1996 loss: 0.0071 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0071 2023/03/07 00:09:19 - mmengine - INFO - Epoch(train) [15][1000/1567] lr: 1.7785e-03 eta: 0:04:08 time: 0.1165 data_time: 0.0079 memory: 1996 loss: 0.0072 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0072 2023/03/07 00:09:27 - mmengine - INFO - Exp name: ctrgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230306_232308 2023/03/07 00:09:31 - mmengine - INFO - Epoch(train) [15][1100/1567] lr: 1.6167e-03 eta: 0:03:56 time: 0.1163 data_time: 0.0066 memory: 1996 loss: 0.0127 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0127 2023/03/07 00:09:43 - mmengine - INFO - Epoch(train) [15][1200/1567] lr: 1.4625e-03 eta: 0:03:45 time: 0.1146 data_time: 0.0074 memory: 1996 loss: 0.0063 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0063 2023/03/07 00:09:54 - mmengine - INFO - Epoch(train) [15][1300/1567] lr: 1.3159e-03 eta: 0:03:33 time: 0.1146 data_time: 0.0074 memory: 1996 loss: 0.0056 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0056 2023/03/07 00:10:06 - mmengine - INFO - Epoch(train) [15][1400/1567] lr: 1.1769e-03 eta: 0:03:21 time: 0.1205 data_time: 0.0081 memory: 1996 loss: 0.0085 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0085 2023/03/07 00:10:18 - mmengine - INFO - Epoch(train) [15][1500/1567] lr: 1.0456e-03 eta: 0:03:10 time: 0.1152 data_time: 0.0066 memory: 1996 loss: 0.0054 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0054 2023/03/07 00:10:26 - mmengine - INFO - Exp name: ctrgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230306_232308 2023/03/07 00:10:26 - mmengine - INFO - Epoch(train) [15][1567/1567] lr: 9.6196e-04 eta: 0:03:02 time: 0.1171 data_time: 0.0064 memory: 1996 loss: 0.2550 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.2550 2023/03/07 00:10:26 - mmengine - INFO - Saving checkpoint at 15 epochs 2023/03/07 00:10:30 - mmengine - INFO - Epoch(val) [15][100/129] eta: 0:00:01 time: 0.0387 data_time: 0.0064 memory: 156 2023/03/07 00:10:31 - mmengine - INFO - Epoch(val) [15][129/129] acc/top1: 0.8905 acc/top5: 0.9893 acc/mean1: 0.8905 2023/03/07 00:10:31 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/projects/ctrgcn/work_dirs/ctrgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_14.pth is removed 2023/03/07 00:10:32 - mmengine - INFO - The best checkpoint with 0.8905 acc/top1 at 15 epoch is saved to best_acc/top1_epoch_15.pth. 2023/03/07 00:10:43 - mmengine - INFO - Epoch(train) [16][ 100/1567] lr: 8.4351e-04 eta: 0:02:50 time: 0.1177 data_time: 0.0072 memory: 1996 loss: 0.0058 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0058 2023/03/07 00:10:55 - mmengine - INFO - Epoch(train) [16][ 200/1567] lr: 7.3277e-04 eta: 0:02:39 time: 0.1154 data_time: 0.0078 memory: 1996 loss: 0.0087 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0087 2023/03/07 00:11:07 - mmengine - INFO - Epoch(train) [16][ 300/1567] lr: 6.2978e-04 eta: 0:02:27 time: 0.1202 data_time: 0.0080 memory: 1996 loss: 0.0070 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0070 2023/03/07 00:11:19 - mmengine - INFO - Epoch(train) [16][ 400/1567] lr: 5.3453e-04 eta: 0:02:15 time: 0.1149 data_time: 0.0070 memory: 1996 loss: 0.0073 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0073 2023/03/07 00:11:30 - mmengine - INFO - Exp name: ctrgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230306_232308 2023/03/07 00:11:30 - mmengine - INFO - Epoch(train) [16][ 500/1567] lr: 4.4705e-04 eta: 0:02:04 time: 0.1154 data_time: 0.0067 memory: 1996 loss: 0.0073 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0073 2023/03/07 00:11:42 - mmengine - INFO - Epoch(train) [16][ 600/1567] lr: 3.6735e-04 eta: 0:01:52 time: 0.1189 data_time: 0.0065 memory: 1996 loss: 0.0055 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0055 2023/03/07 00:11:54 - mmengine - INFO - Epoch(train) [16][ 700/1567] lr: 2.9544e-04 eta: 0:01:40 time: 0.1171 data_time: 0.0076 memory: 1996 loss: 0.0070 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0070 2023/03/07 00:12:06 - mmengine - INFO - Epoch(train) [16][ 800/1567] lr: 2.3134e-04 eta: 0:01:29 time: 0.1197 data_time: 0.0081 memory: 1996 loss: 0.0066 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0066 2023/03/07 00:12:17 - mmengine - INFO - Epoch(train) [16][ 900/1567] lr: 1.7505e-04 eta: 0:01:17 time: 0.1162 data_time: 0.0068 memory: 1996 loss: 0.0081 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0081 2023/03/07 00:12:29 - mmengine - INFO - Epoch(train) [16][1000/1567] lr: 1.2658e-04 eta: 0:01:06 time: 0.1141 data_time: 0.0067 memory: 1996 loss: 0.0075 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0075 2023/03/07 00:12:41 - mmengine - INFO - Epoch(train) [16][1100/1567] lr: 8.5947e-05 eta: 0:00:54 time: 0.1200 data_time: 0.0067 memory: 1996 loss: 0.0091 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0091 2023/03/07 00:12:53 - mmengine - INFO - Epoch(train) [16][1200/1567] lr: 5.3147e-05 eta: 0:00:42 time: 0.1187 data_time: 0.0071 memory: 1996 loss: 0.0079 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0079 2023/03/07 00:13:05 - mmengine - INFO - Epoch(train) [16][1300/1567] lr: 2.8190e-05 eta: 0:00:31 time: 0.1212 data_time: 0.0073 memory: 1996 loss: 0.0120 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0120 2023/03/07 00:13:17 - mmengine - INFO - Epoch(train) [16][1400/1567] lr: 1.1078e-05 eta: 0:00:19 time: 0.1230 data_time: 0.0073 memory: 1996 loss: 0.0071 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0071 2023/03/07 00:13:28 - mmengine - INFO - Exp name: ctrgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230306_232308 2023/03/07 00:13:29 - mmengine - INFO - Epoch(train) [16][1500/1567] lr: 1.8150e-06 eta: 0:00:07 time: 0.1171 data_time: 0.0066 memory: 1996 loss: 0.0059 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0059 2023/03/07 00:13:36 - mmengine - INFO - Exp name: ctrgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230306_232308 2023/03/07 00:13:36 - mmengine - INFO - Epoch(train) [16][1567/1567] lr: 3.9252e-10 eta: 0:00:00 time: 0.1147 data_time: 0.0071 memory: 1996 loss: 0.2008 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.2008 2023/03/07 00:13:36 - mmengine - INFO - Saving checkpoint at 16 epochs 2023/03/07 00:13:41 - mmengine - INFO - Epoch(val) [16][100/129] eta: 0:00:01 time: 0.0367 data_time: 0.0064 memory: 156 2023/03/07 00:13:42 - mmengine - INFO - Epoch(val) [16][129/129] acc/top1: 0.8922 acc/top5: 0.9893 acc/mean1: 0.8922 2023/03/07 00:13:42 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/projects/ctrgcn/work_dirs/ctrgcn_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_15.pth is removed 2023/03/07 00:13:43 - mmengine - INFO - The best checkpoint with 0.8922 acc/top1 at 16 epoch is saved to best_acc/top1_epoch_16.pth.