2022/12/22 11:06:53 - 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: 1351858896 GPU 0,1,2,3,4,5,6,7: NVIDIA A100-SXM4-80GB CUDA_HOME: /mnt/petrelfs/share/cuda-11.1 NVCC: Cuda compilation tools, release 11.1, V11.1.74 GCC: gcc (GCC) 5.4.0 PyTorch: 1.11.0 PyTorch compiling details: PyTorch built with: - GCC 7.3 - C++ Version: 201402 - Intel(R) oneAPI Math Kernel Library Version 2021.4-Product Build 20210904 for Intel(R) 64 architecture applications - Intel(R) MKL-DNN v2.5.2 (Git Hash a9302535553c73243c632ad3c4c80beec3d19a1e) - OpenMP 201511 (a.k.a. OpenMP 4.5) - LAPACK is enabled (usually provided by MKL) - NNPACK is enabled - CPU capability usage: AVX2 - CUDA Runtime 11.3 - NVCC architecture flags: -gencode;arch=compute_37,code=sm_37;-gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_61,code=sm_61;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-gencode;arch=compute_80,code=sm_80;-gencode;arch=compute_86,code=sm_86;-gencode;arch=compute_37,code=compute_37 - CuDNN 8.2 - Magma 2.5.2 - Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.3, CUDNN_VERSION=8.2.0, CXX_COMPILER=/opt/rh/devtoolset-7/root/usr/bin/c++, CXX_FLAGS= -Wno-deprecated -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -fopenmp -DNDEBUG -DUSE_KINETO -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DSYMBOLICATE_MOBILE_DEBUG_HANDLE -DEDGE_PROFILER_USE_KINETO -O2 -fPIC -Wno-narrowing -Wall -Wextra -Werror=return-type -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wno-sign-compare -Wno-unused-parameter -Wno-unused-function -Wno-unused-result -Wno-unused-local-typedefs -Wno-strict-overflow -Wno-strict-aliasing -Wno-error=deprecated-declarations -Wno-stringop-overflow -Wno-psabi -Wno-error=pedantic -Wno-error=redundant-decls -Wno-error=old-style-cast -fdiagnostics-color=always -faligned-new -Wno-unused-but-set-variable -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Werror=format -Wno-stringop-overflow, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, TORCH_VERSION=1.11.0, USE_CUDA=ON, USE_CUDNN=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=OFF, USE_MPI=OFF, USE_NCCL=ON, USE_NNPACK=ON, USE_OPENMP=ON, USE_ROCM=OFF, TorchVision: 0.12.0 OpenCV: 4.6.0 MMEngine: 0.3.2 Runtime environment: cudnn_benchmark: False mp_cfg: {'mp_start_method': 'fork', 'opencv_num_threads': 0} dist_cfg: {'backend': 'nccl'} seed: None diff_rank_seed: False deterministic: False Distributed launcher: pytorch Distributed training: True GPU number: 8 ------------------------------------------------------------ 2022/12/22 11:06:53 - mmengine - INFO - Config: default_scope = 'mmaction' default_hooks = dict( runtime_info=dict(type='RuntimeInfoHook'), timer=dict(type='IterTimerHook'), logger=dict(type='LoggerHook', interval=100, ignore_last=False), param_scheduler=dict(type='ParamSchedulerHook'), checkpoint=dict(type='CheckpointHook', interval=1, save_best='auto'), sampler_seed=dict(type='DistSamplerSeedHook'), sync_buffers=dict(type='SyncBuffersHook')) env_cfg = dict( cudnn_benchmark=False, mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0), dist_cfg=dict(backend='nccl')) log_processor = dict(type='LogProcessor', window_size=20, by_epoch=True) vis_backends = [dict(type='LocalVisBackend')] visualizer = dict( type='ActionVisualizer', vis_backends=[dict(type='LocalVisBackend')]) log_level = 'INFO' load_from = None resume = False model = dict( type='RecognizerGCN', backbone=dict( type='AAGCN', graph_cfg=dict(layout='nturgb+d', mode='spatial'), stage_cfgs=dict(gcn_attention=False)), cls_head=dict(type='GCNHead', num_classes=60, in_channels=256)) dataset_type = 'PoseDataset' ann_file = 'data/skeleton/ntu60_3d.pkl' train_pipeline = [ dict(type='PreNormalize3D'), dict(type='GenSkeFeat', dataset='nturgb+d', feats=['b']), dict(type='UniformSampleFrames', clip_len=100), dict(type='PoseDecode'), dict(type='FormatGCNInput', num_person=2), dict(type='PackActionInputs') ] val_pipeline = [ dict(type='PreNormalize3D'), dict(type='GenSkeFeat', dataset='nturgb+d', feats=['b']), dict( type='UniformSampleFrames', clip_len=100, num_clips=1, test_mode=True), dict(type='PoseDecode'), dict(type='FormatGCNInput', num_person=2), dict(type='PackActionInputs') ] test_pipeline = [ dict(type='PreNormalize3D'), dict(type='GenSkeFeat', dataset='nturgb+d', feats=['b']), dict( type='UniformSampleFrames', clip_len=100, num_clips=10, test_mode=True), dict(type='PoseDecode'), dict(type='FormatGCNInput', num_person=2), dict(type='PackActionInputs') ] train_dataloader = dict( batch_size=16, num_workers=2, persistent_workers=True, sampler=dict(type='DefaultSampler', shuffle=True), dataset=dict( type='RepeatDataset', times=5, dataset=dict( type='PoseDataset', ann_file='data/skeleton/ntu60_3d.pkl', pipeline=[ dict(type='PreNormalize3D'), dict(type='GenSkeFeat', dataset='nturgb+d', feats=['b']), dict(type='UniformSampleFrames', clip_len=100), dict(type='PoseDecode'), dict(type='FormatGCNInput', num_person=2), dict(type='PackActionInputs') ], split='xsub_train'))) val_dataloader = dict( batch_size=16, num_workers=2, persistent_workers=True, sampler=dict(type='DefaultSampler', shuffle=False), dataset=dict( type='PoseDataset', ann_file='data/skeleton/ntu60_3d.pkl', pipeline=[ dict(type='PreNormalize3D'), dict(type='GenSkeFeat', dataset='nturgb+d', feats=['b']), dict( type='UniformSampleFrames', clip_len=100, num_clips=1, test_mode=True), dict(type='PoseDecode'), dict(type='FormatGCNInput', num_person=2), dict(type='PackActionInputs') ], split='xsub_val', test_mode=True)) test_dataloader = dict( batch_size=1, num_workers=2, persistent_workers=True, sampler=dict(type='DefaultSampler', shuffle=False), dataset=dict( type='PoseDataset', ann_file='data/skeleton/ntu60_3d.pkl', pipeline=[ dict(type='PreNormalize3D'), dict(type='GenSkeFeat', dataset='nturgb+d', feats=['b']), dict( type='UniformSampleFrames', clip_len=100, num_clips=10, test_mode=True), dict(type='PoseDecode'), dict(type='FormatGCNInput', num_person=2), dict(type='PackActionInputs') ], split='xsub_val', test_mode=True)) val_evaluator = [dict(type='AccMetric')] test_evaluator = [dict(type='AccMetric')] train_cfg = dict( type='EpochBasedTrainLoop', max_epochs=16, val_begin=1, val_interval=1) val_cfg = dict(type='ValLoop') test_cfg = dict(type='TestLoop') param_scheduler = [ dict( type='CosineAnnealingLR', eta_min=0, T_max=16, by_epoch=True, convert_to_iter_based=True) ] optim_wrapper = dict( optimizer=dict( type='SGD', lr=0.1, momentum=0.9, weight_decay=0.0005, nesterov=True)) auto_scale_lr = dict(enable=False, base_batch_size=128) launcher = 'pytorch' work_dir = './work_dirs/2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d' randomness = dict(seed=None, diff_rank_seed=False, deterministic=False) 2022/12/22 11:06:53 - mmengine - INFO - Result has been saved to /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d/modules_statistic_results.json 2022/12/22 11:06:54 - mmengine - INFO - Hooks will be executed in the following order: before_run: (VERY_HIGH ) RuntimeInfoHook (BELOW_NORMAL) LoggerHook -------------------- before_train: (VERY_HIGH ) RuntimeInfoHook (NORMAL ) IterTimerHook (VERY_LOW ) CheckpointHook -------------------- before_train_epoch: (VERY_HIGH ) RuntimeInfoHook (NORMAL ) IterTimerHook (NORMAL ) DistSamplerSeedHook -------------------- before_train_iter: (VERY_HIGH ) RuntimeInfoHook (NORMAL ) IterTimerHook -------------------- after_train_iter: (VERY_HIGH ) RuntimeInfoHook (NORMAL ) IterTimerHook (BELOW_NORMAL) LoggerHook (LOW ) ParamSchedulerHook (VERY_LOW ) CheckpointHook -------------------- after_train_epoch: (NORMAL ) IterTimerHook (NORMAL ) SyncBuffersHook (LOW ) ParamSchedulerHook (VERY_LOW ) CheckpointHook -------------------- before_val_epoch: (NORMAL ) IterTimerHook -------------------- before_val_iter: (NORMAL ) IterTimerHook -------------------- after_val_iter: (NORMAL ) IterTimerHook (BELOW_NORMAL) LoggerHook -------------------- after_val_epoch: (VERY_HIGH ) RuntimeInfoHook (NORMAL ) IterTimerHook (BELOW_NORMAL) LoggerHook (VERY_LOW ) CheckpointHook -------------------- before_test_epoch: (NORMAL ) IterTimerHook -------------------- before_test_iter: (NORMAL ) IterTimerHook -------------------- after_test_iter: (NORMAL ) IterTimerHook (BELOW_NORMAL) LoggerHook -------------------- after_test_epoch: (VERY_HIGH ) RuntimeInfoHook (NORMAL ) IterTimerHook (BELOW_NORMAL) LoggerHook -------------------- after_run: (BELOW_NORMAL) LoggerHook -------------------- Name of parameter - Initialization information backbone.data_bn.weight - torch.Size([150]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.data_bn.bias - torch.Size([150]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.gcn.A - torch.Size([3, 25, 25]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.gcn.alpha - torch.Size([1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.gcn.conv_d.0.weight - torch.Size([64, 3, 1, 1]): ConvBranchInit backbone.gcn.0.gcn.conv_d.0.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.gcn.conv_d.1.weight - torch.Size([64, 3, 1, 1]): ConvBranchInit backbone.gcn.0.gcn.conv_d.1.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.gcn.conv_d.2.weight - torch.Size([64, 3, 1, 1]): ConvBranchInit backbone.gcn.0.gcn.conv_d.2.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.gcn.conv_a.0.weight - torch.Size([16, 3, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.gcn.conv_a.0.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.gcn.conv_a.1.weight - torch.Size([16, 3, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.gcn.conv_a.1.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.gcn.conv_a.2.weight - torch.Size([16, 3, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.gcn.conv_a.2.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.gcn.conv_b.0.weight - torch.Size([16, 3, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.gcn.conv_b.0.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.gcn.conv_b.1.weight - torch.Size([16, 3, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.gcn.conv_b.1.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.gcn.conv_b.2.weight - torch.Size([16, 3, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.gcn.conv_b.2.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.gcn.down.0.weight - torch.Size([64, 3, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.gcn.down.0.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.gcn.down.1.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.gcn.down.1.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.gcn.bn.weight - torch.Size([64]): ConstantInit: val=1e-06, bias=0 backbone.gcn.0.gcn.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.tcn.conv.weight - torch.Size([64, 64, 9, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.tcn.conv.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.tcn.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.tcn.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.gcn.A - torch.Size([3, 25, 25]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.gcn.alpha - torch.Size([1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.gcn.conv_d.0.weight - torch.Size([64, 64, 1, 1]): ConvBranchInit backbone.gcn.1.gcn.conv_d.0.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.1.gcn.conv_d.1.weight - torch.Size([64, 64, 1, 1]): ConvBranchInit backbone.gcn.1.gcn.conv_d.1.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.1.gcn.conv_d.2.weight - torch.Size([64, 64, 1, 1]): ConvBranchInit backbone.gcn.1.gcn.conv_d.2.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.1.gcn.conv_a.0.weight - torch.Size([16, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.1.gcn.conv_a.0.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.1.gcn.conv_a.1.weight - torch.Size([16, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.1.gcn.conv_a.1.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.1.gcn.conv_a.2.weight - torch.Size([16, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.1.gcn.conv_a.2.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.1.gcn.conv_b.0.weight - torch.Size([16, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.1.gcn.conv_b.0.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.1.gcn.conv_b.1.weight - torch.Size([16, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.1.gcn.conv_b.1.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.1.gcn.conv_b.2.weight - torch.Size([16, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.1.gcn.conv_b.2.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.1.gcn.bn.weight - torch.Size([64]): ConstantInit: val=1e-06, bias=0 backbone.gcn.1.gcn.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.tcn.conv.weight - torch.Size([64, 64, 9, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.1.tcn.conv.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.1.tcn.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.tcn.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.gcn.A - torch.Size([3, 25, 25]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.gcn.alpha - torch.Size([1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.gcn.conv_d.0.weight - torch.Size([64, 64, 1, 1]): ConvBranchInit backbone.gcn.2.gcn.conv_d.0.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.2.gcn.conv_d.1.weight - torch.Size([64, 64, 1, 1]): ConvBranchInit backbone.gcn.2.gcn.conv_d.1.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.2.gcn.conv_d.2.weight - torch.Size([64, 64, 1, 1]): ConvBranchInit backbone.gcn.2.gcn.conv_d.2.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.2.gcn.conv_a.0.weight - torch.Size([16, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.2.gcn.conv_a.0.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.2.gcn.conv_a.1.weight - torch.Size([16, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.2.gcn.conv_a.1.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.2.gcn.conv_a.2.weight - torch.Size([16, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.2.gcn.conv_a.2.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.2.gcn.conv_b.0.weight - torch.Size([16, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.2.gcn.conv_b.0.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.2.gcn.conv_b.1.weight - torch.Size([16, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.2.gcn.conv_b.1.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.2.gcn.conv_b.2.weight - torch.Size([16, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.2.gcn.conv_b.2.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.2.gcn.bn.weight - torch.Size([64]): ConstantInit: val=1e-06, bias=0 backbone.gcn.2.gcn.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.tcn.conv.weight - torch.Size([64, 64, 9, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.2.tcn.conv.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.2.tcn.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.tcn.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.gcn.A - torch.Size([3, 25, 25]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.gcn.alpha - torch.Size([1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.gcn.conv_d.0.weight - torch.Size([64, 64, 1, 1]): ConvBranchInit backbone.gcn.3.gcn.conv_d.0.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.3.gcn.conv_d.1.weight - torch.Size([64, 64, 1, 1]): ConvBranchInit backbone.gcn.3.gcn.conv_d.1.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.3.gcn.conv_d.2.weight - torch.Size([64, 64, 1, 1]): ConvBranchInit backbone.gcn.3.gcn.conv_d.2.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.3.gcn.conv_a.0.weight - torch.Size([16, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.3.gcn.conv_a.0.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.3.gcn.conv_a.1.weight - torch.Size([16, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.3.gcn.conv_a.1.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.3.gcn.conv_a.2.weight - torch.Size([16, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.3.gcn.conv_a.2.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.3.gcn.conv_b.0.weight - torch.Size([16, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.3.gcn.conv_b.0.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.3.gcn.conv_b.1.weight - torch.Size([16, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.3.gcn.conv_b.1.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.3.gcn.conv_b.2.weight - torch.Size([16, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.3.gcn.conv_b.2.bias - torch.Size([16]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.3.gcn.bn.weight - torch.Size([64]): ConstantInit: val=1e-06, bias=0 backbone.gcn.3.gcn.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.tcn.conv.weight - torch.Size([64, 64, 9, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.3.tcn.conv.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.3.tcn.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.tcn.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.gcn.A - torch.Size([3, 25, 25]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.gcn.alpha - torch.Size([1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.gcn.conv_d.0.weight - torch.Size([128, 64, 1, 1]): ConvBranchInit backbone.gcn.4.gcn.conv_d.0.bias - torch.Size([128]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.gcn.conv_d.1.weight - torch.Size([128, 64, 1, 1]): ConvBranchInit backbone.gcn.4.gcn.conv_d.1.bias - torch.Size([128]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.gcn.conv_d.2.weight - torch.Size([128, 64, 1, 1]): ConvBranchInit backbone.gcn.4.gcn.conv_d.2.bias - torch.Size([128]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.gcn.conv_a.0.weight - torch.Size([32, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.gcn.conv_a.0.bias - torch.Size([32]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.gcn.conv_a.1.weight - torch.Size([32, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.gcn.conv_a.1.bias - torch.Size([32]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.gcn.conv_a.2.weight - torch.Size([32, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.gcn.conv_a.2.bias - torch.Size([32]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.gcn.conv_b.0.weight - torch.Size([32, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.gcn.conv_b.0.bias - torch.Size([32]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.gcn.conv_b.1.weight - torch.Size([32, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.gcn.conv_b.1.bias - torch.Size([32]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.gcn.conv_b.2.weight - torch.Size([32, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.gcn.conv_b.2.bias - torch.Size([32]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.gcn.down.0.weight - torch.Size([128, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.gcn.down.0.bias - torch.Size([128]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.gcn.down.1.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.gcn.down.1.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.gcn.bn.weight - torch.Size([128]): ConstantInit: val=1e-06, bias=0 backbone.gcn.4.gcn.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.tcn.conv.weight - torch.Size([128, 128, 9, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.tcn.conv.bias - torch.Size([128]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.tcn.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.tcn.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.residual.conv.weight - torch.Size([128, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.residual.conv.bias - torch.Size([128]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.residual.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.residual.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.gcn.A - torch.Size([3, 25, 25]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.gcn.alpha - torch.Size([1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.gcn.conv_d.0.weight - torch.Size([128, 128, 1, 1]): ConvBranchInit backbone.gcn.5.gcn.conv_d.0.bias - torch.Size([128]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.5.gcn.conv_d.1.weight - torch.Size([128, 128, 1, 1]): ConvBranchInit backbone.gcn.5.gcn.conv_d.1.bias - torch.Size([128]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.5.gcn.conv_d.2.weight - torch.Size([128, 128, 1, 1]): ConvBranchInit backbone.gcn.5.gcn.conv_d.2.bias - torch.Size([128]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.5.gcn.conv_a.0.weight - torch.Size([32, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.5.gcn.conv_a.0.bias - torch.Size([32]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.5.gcn.conv_a.1.weight - torch.Size([32, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.5.gcn.conv_a.1.bias - torch.Size([32]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.5.gcn.conv_a.2.weight - torch.Size([32, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.5.gcn.conv_a.2.bias - torch.Size([32]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.5.gcn.conv_b.0.weight - torch.Size([32, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.5.gcn.conv_b.0.bias - torch.Size([32]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.5.gcn.conv_b.1.weight - torch.Size([32, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.5.gcn.conv_b.1.bias - torch.Size([32]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.5.gcn.conv_b.2.weight - torch.Size([32, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.5.gcn.conv_b.2.bias - torch.Size([32]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.5.gcn.bn.weight - torch.Size([128]): ConstantInit: val=1e-06, bias=0 backbone.gcn.5.gcn.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.tcn.conv.weight - torch.Size([128, 128, 9, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.5.tcn.conv.bias - torch.Size([128]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.5.tcn.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.tcn.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.gcn.A - torch.Size([3, 25, 25]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.gcn.alpha - torch.Size([1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.gcn.conv_d.0.weight - torch.Size([128, 128, 1, 1]): ConvBranchInit backbone.gcn.6.gcn.conv_d.0.bias - torch.Size([128]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.6.gcn.conv_d.1.weight - torch.Size([128, 128, 1, 1]): ConvBranchInit backbone.gcn.6.gcn.conv_d.1.bias - torch.Size([128]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.6.gcn.conv_d.2.weight - torch.Size([128, 128, 1, 1]): ConvBranchInit backbone.gcn.6.gcn.conv_d.2.bias - torch.Size([128]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.6.gcn.conv_a.0.weight - torch.Size([32, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.6.gcn.conv_a.0.bias - torch.Size([32]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.6.gcn.conv_a.1.weight - torch.Size([32, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.6.gcn.conv_a.1.bias - torch.Size([32]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.6.gcn.conv_a.2.weight - torch.Size([32, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.6.gcn.conv_a.2.bias - torch.Size([32]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.6.gcn.conv_b.0.weight - torch.Size([32, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.6.gcn.conv_b.0.bias - torch.Size([32]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.6.gcn.conv_b.1.weight - torch.Size([32, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.6.gcn.conv_b.1.bias - torch.Size([32]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.6.gcn.conv_b.2.weight - torch.Size([32, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.6.gcn.conv_b.2.bias - torch.Size([32]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.6.gcn.bn.weight - torch.Size([128]): ConstantInit: val=1e-06, bias=0 backbone.gcn.6.gcn.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.tcn.conv.weight - torch.Size([128, 128, 9, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.6.tcn.conv.bias - torch.Size([128]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.6.tcn.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.tcn.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.gcn.A - torch.Size([3, 25, 25]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.gcn.alpha - torch.Size([1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.gcn.conv_d.0.weight - torch.Size([256, 128, 1, 1]): ConvBranchInit backbone.gcn.7.gcn.conv_d.0.bias - torch.Size([256]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.gcn.conv_d.1.weight - torch.Size([256, 128, 1, 1]): ConvBranchInit backbone.gcn.7.gcn.conv_d.1.bias - torch.Size([256]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.gcn.conv_d.2.weight - torch.Size([256, 128, 1, 1]): ConvBranchInit backbone.gcn.7.gcn.conv_d.2.bias - torch.Size([256]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.gcn.conv_a.0.weight - torch.Size([64, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.gcn.conv_a.0.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.gcn.conv_a.1.weight - torch.Size([64, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.gcn.conv_a.1.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.gcn.conv_a.2.weight - torch.Size([64, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.gcn.conv_a.2.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.gcn.conv_b.0.weight - torch.Size([64, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.gcn.conv_b.0.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.gcn.conv_b.1.weight - torch.Size([64, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.gcn.conv_b.1.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.gcn.conv_b.2.weight - torch.Size([64, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.gcn.conv_b.2.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.gcn.down.0.weight - torch.Size([256, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.gcn.down.0.bias - torch.Size([256]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.gcn.down.1.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.gcn.down.1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.gcn.bn.weight - torch.Size([256]): ConstantInit: val=1e-06, bias=0 backbone.gcn.7.gcn.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.tcn.conv.weight - torch.Size([256, 256, 9, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.tcn.conv.bias - torch.Size([256]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.tcn.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.tcn.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.residual.conv.weight - torch.Size([256, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.residual.conv.bias - torch.Size([256]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.residual.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.residual.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.gcn.A - torch.Size([3, 25, 25]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.gcn.alpha - torch.Size([1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.gcn.conv_d.0.weight - torch.Size([256, 256, 1, 1]): ConvBranchInit backbone.gcn.8.gcn.conv_d.0.bias - torch.Size([256]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.8.gcn.conv_d.1.weight - torch.Size([256, 256, 1, 1]): ConvBranchInit backbone.gcn.8.gcn.conv_d.1.bias - torch.Size([256]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.8.gcn.conv_d.2.weight - torch.Size([256, 256, 1, 1]): ConvBranchInit backbone.gcn.8.gcn.conv_d.2.bias - torch.Size([256]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.8.gcn.conv_a.0.weight - torch.Size([64, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.8.gcn.conv_a.0.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.8.gcn.conv_a.1.weight - torch.Size([64, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.8.gcn.conv_a.1.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.8.gcn.conv_a.2.weight - torch.Size([64, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.8.gcn.conv_a.2.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.8.gcn.conv_b.0.weight - torch.Size([64, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.8.gcn.conv_b.0.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.8.gcn.conv_b.1.weight - torch.Size([64, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.8.gcn.conv_b.1.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.8.gcn.conv_b.2.weight - torch.Size([64, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.8.gcn.conv_b.2.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.8.gcn.bn.weight - torch.Size([256]): ConstantInit: val=1e-06, bias=0 backbone.gcn.8.gcn.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.tcn.conv.weight - torch.Size([256, 256, 9, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.8.tcn.conv.bias - torch.Size([256]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.8.tcn.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.tcn.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.gcn.A - torch.Size([3, 25, 25]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.gcn.alpha - torch.Size([1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.gcn.conv_d.0.weight - torch.Size([256, 256, 1, 1]): ConvBranchInit backbone.gcn.9.gcn.conv_d.0.bias - torch.Size([256]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.9.gcn.conv_d.1.weight - torch.Size([256, 256, 1, 1]): ConvBranchInit backbone.gcn.9.gcn.conv_d.1.bias - torch.Size([256]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.9.gcn.conv_d.2.weight - torch.Size([256, 256, 1, 1]): ConvBranchInit backbone.gcn.9.gcn.conv_d.2.bias - torch.Size([256]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.9.gcn.conv_a.0.weight - torch.Size([64, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.9.gcn.conv_a.0.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.9.gcn.conv_a.1.weight - torch.Size([64, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.9.gcn.conv_a.1.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.9.gcn.conv_a.2.weight - torch.Size([64, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.9.gcn.conv_a.2.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.9.gcn.conv_b.0.weight - torch.Size([64, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.9.gcn.conv_b.0.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.9.gcn.conv_b.1.weight - torch.Size([64, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.9.gcn.conv_b.1.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.9.gcn.conv_b.2.weight - torch.Size([64, 256, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.9.gcn.conv_b.2.bias - torch.Size([64]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.9.gcn.bn.weight - torch.Size([256]): ConstantInit: val=1e-06, bias=0 backbone.gcn.9.gcn.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.tcn.conv.weight - torch.Size([256, 256, 9, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.9.tcn.conv.bias - torch.Size([256]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.9.tcn.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.tcn.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN cls_head.fc.weight - torch.Size([60, 256]): NormalInit: mean=0, std=0.01, bias=0 cls_head.fc.bias - torch.Size([60]): NormalInit: mean=0, std=0.01, bias=0 2022/12/22 11:08:07 - mmengine - INFO - Checkpoints will be saved to /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d. 2022/12/22 11:09:11 - mmengine - INFO - Epoch(train) [1][ 100/1567] lr: 9.9996e-02 eta: 4:25:32 time: 0.5436 data_time: 0.0073 memory: 2111 loss: 3.2052 top1_acc: 0.0625 top5_acc: 0.7500 loss_cls: 3.2052 2022/12/22 11:10:05 - mmengine - INFO - Epoch(train) [1][ 200/1567] lr: 9.9984e-02 eta: 4:05:08 time: 0.5445 data_time: 0.0075 memory: 2111 loss: 2.5654 top1_acc: 0.1875 top5_acc: 0.5625 loss_cls: 2.5654 2022/12/22 11:10:59 - mmengine - INFO - Epoch(train) [1][ 300/1567] lr: 9.9965e-02 eta: 3:57:22 time: 0.5447 data_time: 0.0071 memory: 2111 loss: 2.0822 top1_acc: 0.3750 top5_acc: 0.8125 loss_cls: 2.0822 2022/12/22 11:11:54 - mmengine - INFO - Epoch(train) [1][ 400/1567] lr: 9.9938e-02 eta: 3:53:16 time: 0.5443 data_time: 0.0070 memory: 2111 loss: 1.7836 top1_acc: 0.1250 top5_acc: 0.8125 loss_cls: 1.7836 2022/12/22 11:12:48 - mmengine - INFO - Epoch(train) [1][ 500/1567] lr: 9.9902e-02 eta: 3:50:32 time: 0.5446 data_time: 0.0072 memory: 2111 loss: 1.5991 top1_acc: 0.2500 top5_acc: 0.7500 loss_cls: 1.5991 2022/12/22 11:13:43 - mmengine - INFO - Epoch(train) [1][ 600/1567] lr: 9.9859e-02 eta: 3:48:12 time: 0.5366 data_time: 0.0072 memory: 2111 loss: 1.2259 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 1.2259 2022/12/22 11:14:37 - mmengine - INFO - Epoch(train) [1][ 700/1567] lr: 9.9808e-02 eta: 3:46:24 time: 0.5501 data_time: 0.0072 memory: 2111 loss: 1.2637 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.2637 2022/12/22 11:15:31 - mmengine - INFO - Epoch(train) [1][ 800/1567] lr: 9.9750e-02 eta: 3:44:48 time: 0.5399 data_time: 0.0073 memory: 2111 loss: 1.0587 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.0587 2022/12/22 11:16:26 - mmengine - INFO - Epoch(train) [1][ 900/1567] lr: 9.9683e-02 eta: 3:43:20 time: 0.5442 data_time: 0.0072 memory: 2111 loss: 1.1473 top1_acc: 0.5625 top5_acc: 0.8750 loss_cls: 1.1473 2022/12/22 11:17:20 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 11:17:20 - mmengine - INFO - Epoch(train) [1][1000/1567] lr: 9.9609e-02 eta: 3:42:01 time: 0.5427 data_time: 0.0070 memory: 2111 loss: 0.9595 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.9595 2022/12/22 11:18:15 - mmengine - INFO - Epoch(train) [1][1100/1567] lr: 9.9527e-02 eta: 3:40:51 time: 0.5448 data_time: 0.0075 memory: 2111 loss: 0.8973 top1_acc: 0.4375 top5_acc: 0.8125 loss_cls: 0.8973 2022/12/22 11:19:09 - mmengine - INFO - Epoch(train) [1][1200/1567] lr: 9.9437e-02 eta: 3:39:37 time: 0.5448 data_time: 0.0071 memory: 2111 loss: 0.8953 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.8953 2022/12/22 11:20:04 - mmengine - INFO - Epoch(train) [1][1300/1567] lr: 9.9339e-02 eta: 3:38:26 time: 0.5477 data_time: 0.0076 memory: 2111 loss: 0.7966 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.7966 2022/12/22 11:20:58 - mmengine - INFO - Epoch(train) [1][1400/1567] lr: 9.9234e-02 eta: 3:37:16 time: 0.5380 data_time: 0.0075 memory: 2111 loss: 0.8088 top1_acc: 0.5625 top5_acc: 1.0000 loss_cls: 0.8088 2022/12/22 11:21:52 - mmengine - INFO - Epoch(train) [1][1500/1567] lr: 9.9121e-02 eta: 3:35:59 time: 0.5242 data_time: 0.0081 memory: 2111 loss: 0.7887 top1_acc: 0.5625 top5_acc: 1.0000 loss_cls: 0.7887 2022/12/22 11:22:27 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 11:22:27 - mmengine - INFO - Epoch(train) [1][1567/1567] lr: 9.9040e-02 eta: 3:34:58 time: 0.4801 data_time: 0.0071 memory: 2111 loss: 0.8325 top1_acc: 0.0000 top5_acc: 1.0000 loss_cls: 0.8325 2022/12/22 11:22:27 - mmengine - INFO - Saving checkpoint at 1 epochs 2022/12/22 11:22:47 - mmengine - INFO - Epoch(val) [1][100/129] eta: 0:00:05 time: 0.1910 data_time: 0.0063 memory: 293 2022/12/22 11:22:54 - mmengine - INFO - Epoch(val) [1][129/129] acc/top1: 0.6377 acc/top5: 0.9315 acc/mean1: 0.6376 2022/12/22 11:22:54 - mmengine - INFO - The best checkpoint with 0.6377 acc/top1 at 1 epoch is saved to best_acc/top1_epoch_1.pth. 2022/12/22 11:23:49 - mmengine - INFO - Epoch(train) [2][ 100/1567] lr: 9.8914e-02 eta: 3:33:59 time: 0.5426 data_time: 0.0069 memory: 2111 loss: 0.7507 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 0.7507 2022/12/22 11:24:43 - mmengine - INFO - Epoch(train) [2][ 200/1567] lr: 9.8781e-02 eta: 3:32:58 time: 0.5417 data_time: 0.0073 memory: 2111 loss: 0.5901 top1_acc: 0.6250 top5_acc: 1.0000 loss_cls: 0.5901 2022/12/22 11:25:38 - mmengine - INFO - Epoch(train) [2][ 300/1567] lr: 9.8639e-02 eta: 3:31:57 time: 0.5427 data_time: 0.0074 memory: 2111 loss: 0.7388 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.7388 2022/12/22 11:26:32 - mmengine - INFO - Epoch(train) [2][ 400/1567] lr: 9.8491e-02 eta: 3:30:58 time: 0.5408 data_time: 0.0077 memory: 2111 loss: 0.7015 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.7015 2022/12/22 11:26:50 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 11:27:27 - mmengine - INFO - Epoch(train) [2][ 500/1567] lr: 9.8334e-02 eta: 3:30:00 time: 0.5472 data_time: 0.0077 memory: 2111 loss: 0.6454 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.6454 2022/12/22 11:28:21 - mmengine - INFO - Epoch(train) [2][ 600/1567] lr: 9.8170e-02 eta: 3:28:59 time: 0.5444 data_time: 0.0074 memory: 2111 loss: 0.6853 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.6853 2022/12/22 11:29:15 - mmengine - INFO - Epoch(train) [2][ 700/1567] lr: 9.7998e-02 eta: 3:28:01 time: 0.5468 data_time: 0.0080 memory: 2111 loss: 0.6160 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.6160 2022/12/22 11:30:10 - mmengine - INFO - Epoch(train) [2][ 800/1567] lr: 9.7819e-02 eta: 3:27:03 time: 0.5418 data_time: 0.0072 memory: 2111 loss: 0.6188 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.6188 2022/12/22 11:31:04 - mmengine - INFO - Epoch(train) [2][ 900/1567] lr: 9.7632e-02 eta: 3:26:04 time: 0.5410 data_time: 0.0074 memory: 2111 loss: 0.6176 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.6176 2022/12/22 11:31:58 - mmengine - INFO - Epoch(train) [2][1000/1567] lr: 9.7438e-02 eta: 3:25:08 time: 0.5491 data_time: 0.0072 memory: 2111 loss: 0.5632 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.5632 2022/12/22 11:32:53 - mmengine - INFO - Epoch(train) [2][1100/1567] lr: 9.7236e-02 eta: 3:24:10 time: 0.5452 data_time: 0.0069 memory: 2111 loss: 0.6145 top1_acc: 0.6250 top5_acc: 1.0000 loss_cls: 0.6145 2022/12/22 11:33:47 - mmengine - INFO - Epoch(train) [2][1200/1567] lr: 9.7027e-02 eta: 3:23:13 time: 0.5415 data_time: 0.0072 memory: 2111 loss: 0.5928 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.5928 2022/12/22 11:34:42 - mmengine - INFO - Epoch(train) [2][1300/1567] lr: 9.6810e-02 eta: 3:22:18 time: 0.5408 data_time: 0.0070 memory: 2111 loss: 0.6312 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.6312 2022/12/22 11:35:36 - mmengine - INFO - Epoch(train) [2][1400/1567] lr: 9.6587e-02 eta: 3:21:20 time: 0.5415 data_time: 0.0069 memory: 2111 loss: 0.5589 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.5589 2022/12/22 11:35:54 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 11:36:30 - mmengine - INFO - Epoch(train) [2][1500/1567] lr: 9.6355e-02 eta: 3:20:23 time: 0.5462 data_time: 0.0070 memory: 2111 loss: 0.5542 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.5542 2022/12/22 11:37:06 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 11:37:06 - mmengine - INFO - Epoch(train) [2][1567/1567] lr: 9.6196e-02 eta: 3:19:38 time: 0.4909 data_time: 0.0072 memory: 2111 loss: 0.6562 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.6562 2022/12/22 11:37:06 - mmengine - INFO - Saving checkpoint at 2 epochs 2022/12/22 11:37:25 - mmengine - INFO - Epoch(val) [2][100/129] eta: 0:00:05 time: 0.1888 data_time: 0.0067 memory: 293 2022/12/22 11:37:32 - mmengine - INFO - Epoch(val) [2][129/129] acc/top1: 0.7184 acc/top5: 0.9449 acc/mean1: 0.7183 2022/12/22 11:37:32 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_1.pth is removed 2022/12/22 11:37:33 - mmengine - INFO - The best checkpoint with 0.7184 acc/top1 at 2 epoch is saved to best_acc/top1_epoch_2.pth. 2022/12/22 11:38:27 - mmengine - INFO - Epoch(train) [3][ 100/1567] lr: 9.5953e-02 eta: 3:18:40 time: 0.5471 data_time: 0.0074 memory: 2111 loss: 0.5260 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.5260 2022/12/22 11:39:21 - mmengine - INFO - Epoch(train) [3][ 200/1567] lr: 9.5703e-02 eta: 3:17:45 time: 0.5467 data_time: 0.0071 memory: 2111 loss: 0.5398 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.5398 2022/12/22 11:40:16 - mmengine - INFO - Epoch(train) [3][ 300/1567] lr: 9.5445e-02 eta: 3:16:50 time: 0.5408 data_time: 0.0074 memory: 2111 loss: 0.4810 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.4810 2022/12/22 11:41:10 - mmengine - INFO - Epoch(train) [3][ 400/1567] lr: 9.5180e-02 eta: 3:15:54 time: 0.5468 data_time: 0.0074 memory: 2111 loss: 0.5180 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.5180 2022/12/22 11:42:05 - mmengine - INFO - Epoch(train) [3][ 500/1567] lr: 9.4908e-02 eta: 3:14:58 time: 0.5445 data_time: 0.0073 memory: 2111 loss: 0.4269 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4269 2022/12/22 11:42:59 - mmengine - INFO - Epoch(train) [3][ 600/1567] lr: 9.4629e-02 eta: 3:14:02 time: 0.5454 data_time: 0.0077 memory: 2111 loss: 0.5008 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.5008 2022/12/22 11:43:53 - mmengine - INFO - Epoch(train) [3][ 700/1567] lr: 9.4343e-02 eta: 3:13:05 time: 0.5360 data_time: 0.0072 memory: 2111 loss: 0.4274 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.4274 2022/12/22 11:44:47 - mmengine - INFO - Epoch(train) [3][ 800/1567] lr: 9.4050e-02 eta: 3:12:10 time: 0.5437 data_time: 0.0072 memory: 2111 loss: 0.4649 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4649 2022/12/22 11:45:23 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 11:45:42 - mmengine - INFO - Epoch(train) [3][ 900/1567] lr: 9.3750e-02 eta: 3:11:14 time: 0.5407 data_time: 0.0072 memory: 2111 loss: 0.5387 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.5387 2022/12/22 11:46:36 - mmengine - INFO - Epoch(train) [3][1000/1567] lr: 9.3444e-02 eta: 3:10:18 time: 0.5438 data_time: 0.0070 memory: 2111 loss: 0.5088 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.5088 2022/12/22 11:47:30 - mmengine - INFO - Epoch(train) [3][1100/1567] lr: 9.3130e-02 eta: 3:09:22 time: 0.5371 data_time: 0.0076 memory: 2111 loss: 0.4756 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.4756 2022/12/22 11:48:24 - mmengine - INFO - Epoch(train) [3][1200/1567] lr: 9.2810e-02 eta: 3:08:26 time: 0.5355 data_time: 0.0075 memory: 2111 loss: 0.4261 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4261 2022/12/22 11:49:19 - mmengine - INFO - Epoch(train) [3][1300/1567] lr: 9.2483e-02 eta: 3:07:31 time: 0.5460 data_time: 0.0073 memory: 2111 loss: 0.3671 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.3671 2022/12/22 11:50:13 - mmengine - INFO - Epoch(train) [3][1400/1567] lr: 9.2149e-02 eta: 3:06:36 time: 0.5461 data_time: 0.0070 memory: 2111 loss: 0.4888 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 0.4888 2022/12/22 11:51:08 - mmengine - INFO - Epoch(train) [3][1500/1567] lr: 9.1809e-02 eta: 3:05:41 time: 0.5452 data_time: 0.0071 memory: 2111 loss: 0.4246 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.4246 2022/12/22 11:51:43 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 11:51:43 - mmengine - INFO - Epoch(train) [3][1567/1567] lr: 9.1577e-02 eta: 3:05:00 time: 0.4961 data_time: 0.0071 memory: 2111 loss: 0.5672 top1_acc: 0.0000 top5_acc: 1.0000 loss_cls: 0.5672 2022/12/22 11:51:43 - mmengine - INFO - Saving checkpoint at 3 epochs 2022/12/22 11:52:02 - mmengine - INFO - Epoch(val) [3][100/129] eta: 0:00:05 time: 0.1242 data_time: 0.0134 memory: 293 2022/12/22 11:52:09 - mmengine - INFO - Epoch(val) [3][129/129] acc/top1: 0.7764 acc/top5: 0.9546 acc/mean1: 0.7763 2022/12/22 11:52:09 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_2.pth is removed 2022/12/22 11:52:09 - mmengine - INFO - The best checkpoint with 0.7764 acc/top1 at 3 epoch is saved to best_acc/top1_epoch_3.pth. 2022/12/22 11:53:03 - mmengine - INFO - Epoch(train) [4][ 100/1567] lr: 9.1226e-02 eta: 3:04:06 time: 0.5441 data_time: 0.0070 memory: 2111 loss: 0.5219 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.5219 2022/12/22 11:53:57 - mmengine - INFO - Epoch(train) [4][ 200/1567] lr: 9.0868e-02 eta: 3:03:08 time: 0.5365 data_time: 0.0074 memory: 2111 loss: 0.4170 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4170 2022/12/22 11:54:50 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 11:54:50 - mmengine - INFO - Epoch(train) [4][ 300/1567] lr: 9.0504e-02 eta: 3:02:09 time: 0.5381 data_time: 0.0071 memory: 2111 loss: 0.2949 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2949 2022/12/22 11:55:44 - mmengine - INFO - Epoch(train) [4][ 400/1567] lr: 9.0133e-02 eta: 3:01:12 time: 0.5386 data_time: 0.0069 memory: 2111 loss: 0.3994 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.3994 2022/12/22 11:56:38 - mmengine - INFO - Epoch(train) [4][ 500/1567] lr: 8.9756e-02 eta: 3:00:16 time: 0.5390 data_time: 0.0072 memory: 2111 loss: 0.3873 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.3873 2022/12/22 11:57:32 - mmengine - INFO - Epoch(train) [4][ 600/1567] lr: 8.9373e-02 eta: 2:59:19 time: 0.5335 data_time: 0.0072 memory: 2111 loss: 0.4437 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4437 2022/12/22 11:58:26 - mmengine - INFO - Epoch(train) [4][ 700/1567] lr: 8.8984e-02 eta: 2:58:21 time: 0.5332 data_time: 0.0071 memory: 2111 loss: 0.4590 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4590 2022/12/22 11:59:19 - mmengine - INFO - Epoch(train) [4][ 800/1567] lr: 8.8589e-02 eta: 2:57:25 time: 0.5325 data_time: 0.0070 memory: 2111 loss: 0.4202 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.4202 2022/12/22 12:00:13 - mmengine - INFO - Epoch(train) [4][ 900/1567] lr: 8.8187e-02 eta: 2:56:28 time: 0.5355 data_time: 0.0072 memory: 2111 loss: 0.3805 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3805 2022/12/22 12:01:06 - mmengine - INFO - Epoch(train) [4][1000/1567] lr: 8.7780e-02 eta: 2:55:30 time: 0.5285 data_time: 0.0070 memory: 2111 loss: 0.3488 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3488 2022/12/22 12:02:00 - mmengine - INFO - Epoch(train) [4][1100/1567] lr: 8.7367e-02 eta: 2:54:32 time: 0.5198 data_time: 0.0070 memory: 2111 loss: 0.4555 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4555 2022/12/22 12:02:53 - mmengine - INFO - Epoch(train) [4][1200/1567] lr: 8.6947e-02 eta: 2:53:36 time: 0.5416 data_time: 0.0071 memory: 2111 loss: 0.3300 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.3300 2022/12/22 12:03:47 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 12:03:47 - mmengine - INFO - Epoch(train) [4][1300/1567] lr: 8.6522e-02 eta: 2:52:40 time: 0.5421 data_time: 0.0078 memory: 2111 loss: 0.3950 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.3950 2022/12/22 12:04:41 - mmengine - INFO - Epoch(train) [4][1400/1567] lr: 8.6092e-02 eta: 2:51:43 time: 0.5268 data_time: 0.0068 memory: 2111 loss: 0.4514 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.4514 2022/12/22 12:05:35 - mmengine - INFO - Epoch(train) [4][1500/1567] lr: 8.5655e-02 eta: 2:50:48 time: 0.5396 data_time: 0.0071 memory: 2111 loss: 0.4004 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4004 2022/12/22 12:06:10 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 12:06:10 - mmengine - INFO - Epoch(train) [4][1567/1567] lr: 8.5360e-02 eta: 2:50:09 time: 0.5030 data_time: 0.0067 memory: 2111 loss: 0.5444 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.5444 2022/12/22 12:06:10 - mmengine - INFO - Saving checkpoint at 4 epochs 2022/12/22 12:06:30 - mmengine - INFO - Epoch(val) [4][100/129] eta: 0:00:05 time: 0.1889 data_time: 0.0069 memory: 293 2022/12/22 12:06:37 - mmengine - INFO - Epoch(val) [4][129/129] acc/top1: 0.7579 acc/top5: 0.9546 acc/mean1: 0.7577 2022/12/22 12:07:30 - mmengine - INFO - Epoch(train) [5][ 100/1567] lr: 8.4914e-02 eta: 2:49:12 time: 0.5397 data_time: 0.0067 memory: 2111 loss: 0.3422 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3422 2022/12/22 12:08:24 - mmengine - INFO - Epoch(train) [5][ 200/1567] lr: 8.4463e-02 eta: 2:48:16 time: 0.5345 data_time: 0.0070 memory: 2111 loss: 0.3288 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3288 2022/12/22 12:09:18 - mmengine - INFO - Epoch(train) [5][ 300/1567] lr: 8.4006e-02 eta: 2:47:20 time: 0.5403 data_time: 0.0070 memory: 2111 loss: 0.3540 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3540 2022/12/22 12:10:11 - mmengine - INFO - Epoch(train) [5][ 400/1567] lr: 8.3544e-02 eta: 2:46:24 time: 0.5365 data_time: 0.0072 memory: 2111 loss: 0.3128 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3128 2022/12/22 12:11:05 - mmengine - INFO - Epoch(train) [5][ 500/1567] lr: 8.3077e-02 eta: 2:45:28 time: 0.5344 data_time: 0.0068 memory: 2111 loss: 0.3570 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.3570 2022/12/22 12:11:58 - mmengine - INFO - Epoch(train) [5][ 600/1567] lr: 8.2605e-02 eta: 2:44:32 time: 0.5387 data_time: 0.0069 memory: 2111 loss: 0.2518 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2518 2022/12/22 12:12:52 - mmengine - INFO - Epoch(train) [5][ 700/1567] lr: 8.2127e-02 eta: 2:43:35 time: 0.5409 data_time: 0.0070 memory: 2111 loss: 0.3819 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.3819 2022/12/22 12:13:09 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 12:13:45 - mmengine - INFO - Epoch(train) [5][ 800/1567] lr: 8.1645e-02 eta: 2:42:40 time: 0.5372 data_time: 0.0070 memory: 2111 loss: 0.3553 top1_acc: 0.5000 top5_acc: 0.9375 loss_cls: 0.3553 2022/12/22 12:14:39 - mmengine - INFO - Epoch(train) [5][ 900/1567] lr: 8.1157e-02 eta: 2:41:44 time: 0.5311 data_time: 0.0069 memory: 2111 loss: 0.3179 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3179 2022/12/22 12:15:33 - mmengine - INFO - Epoch(train) [5][1000/1567] lr: 8.0665e-02 eta: 2:40:49 time: 0.5415 data_time: 0.0070 memory: 2111 loss: 0.2341 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2341 2022/12/22 12:16:26 - mmengine - INFO - Epoch(train) [5][1100/1567] lr: 8.0167e-02 eta: 2:39:53 time: 0.5400 data_time: 0.0069 memory: 2111 loss: 0.2932 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2932 2022/12/22 12:17:20 - mmengine - INFO - Epoch(train) [5][1200/1567] lr: 7.9665e-02 eta: 2:38:57 time: 0.5198 data_time: 0.0076 memory: 2111 loss: 0.2665 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2665 2022/12/22 12:18:13 - mmengine - INFO - Epoch(train) [5][1300/1567] lr: 7.9159e-02 eta: 2:38:01 time: 0.5315 data_time: 0.0070 memory: 2111 loss: 0.2749 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2749 2022/12/22 12:19:07 - mmengine - INFO - Epoch(train) [5][1400/1567] lr: 7.8647e-02 eta: 2:37:07 time: 0.5373 data_time: 0.0068 memory: 2111 loss: 0.3193 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3193 2022/12/22 12:20:01 - mmengine - INFO - Epoch(train) [5][1500/1567] lr: 7.8132e-02 eta: 2:36:11 time: 0.5272 data_time: 0.0070 memory: 2111 loss: 0.3946 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.3946 2022/12/22 12:20:36 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 12:20:36 - mmengine - INFO - Epoch(train) [5][1567/1567] lr: 7.7784e-02 eta: 2:35:32 time: 0.5004 data_time: 0.0068 memory: 2111 loss: 0.4002 top1_acc: 0.0000 top5_acc: 1.0000 loss_cls: 0.4002 2022/12/22 12:20:36 - mmengine - INFO - Saving checkpoint at 5 epochs 2022/12/22 12:20:56 - mmengine - INFO - Epoch(val) [5][100/129] eta: 0:00:05 time: 0.1900 data_time: 0.0064 memory: 293 2022/12/22 12:21:03 - mmengine - INFO - Epoch(val) [5][129/129] acc/top1: 0.8029 acc/top5: 0.9626 acc/mean1: 0.8029 2022/12/22 12:21:03 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_3.pth is removed 2022/12/22 12:21:03 - mmengine - INFO - The best checkpoint with 0.8029 acc/top1 at 5 epoch is saved to best_acc/top1_epoch_5.pth. 2022/12/22 12:21:56 - mmengine - INFO - Epoch(train) [6][ 100/1567] lr: 7.7261e-02 eta: 2:34:36 time: 0.5336 data_time: 0.0069 memory: 2111 loss: 0.2620 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2620 2022/12/22 12:22:30 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 12:22:49 - mmengine - INFO - Epoch(train) [6][ 200/1567] lr: 7.6733e-02 eta: 2:33:39 time: 0.5312 data_time: 0.0069 memory: 2111 loss: 0.2645 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2645 2022/12/22 12:23:42 - mmengine - INFO - Epoch(train) [6][ 300/1567] lr: 7.6202e-02 eta: 2:32:44 time: 0.5303 data_time: 0.0075 memory: 2111 loss: 0.3303 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.3303 2022/12/22 12:24:36 - mmengine - INFO - Epoch(train) [6][ 400/1567] lr: 7.5666e-02 eta: 2:31:48 time: 0.5299 data_time: 0.0070 memory: 2111 loss: 0.3314 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.3314 2022/12/22 12:25:30 - mmengine - INFO - Epoch(train) [6][ 500/1567] lr: 7.5126e-02 eta: 2:30:53 time: 0.5323 data_time: 0.0070 memory: 2111 loss: 0.2584 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2584 2022/12/22 12:26:23 - mmengine - INFO - Epoch(train) [6][ 600/1567] lr: 7.4583e-02 eta: 2:29:58 time: 0.5359 data_time: 0.0073 memory: 2111 loss: 0.3145 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.3145 2022/12/22 12:27:16 - mmengine - INFO - Epoch(train) [6][ 700/1567] lr: 7.4035e-02 eta: 2:29:01 time: 0.5419 data_time: 0.0068 memory: 2111 loss: 0.1661 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1661 2022/12/22 12:28:10 - mmengine - INFO - Epoch(train) [6][ 800/1567] lr: 7.3484e-02 eta: 2:28:07 time: 0.5380 data_time: 0.0069 memory: 2111 loss: 0.3098 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3098 2022/12/22 12:29:03 - mmengine - INFO - Epoch(train) [6][ 900/1567] lr: 7.2929e-02 eta: 2:27:12 time: 0.5420 data_time: 0.0069 memory: 2111 loss: 0.2979 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.2979 2022/12/22 12:29:57 - mmengine - INFO - Epoch(train) [6][1000/1567] lr: 7.2371e-02 eta: 2:26:17 time: 0.5353 data_time: 0.0068 memory: 2111 loss: 0.2739 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2739 2022/12/22 12:30:50 - mmengine - INFO - Epoch(train) [6][1100/1567] lr: 7.1809e-02 eta: 2:25:22 time: 0.5346 data_time: 0.0068 memory: 2111 loss: 0.3010 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3010 2022/12/22 12:31:25 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 12:31:44 - mmengine - INFO - Epoch(train) [6][1200/1567] lr: 7.1243e-02 eta: 2:24:27 time: 0.5382 data_time: 0.0071 memory: 2111 loss: 0.2120 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2120 2022/12/22 12:32:38 - mmengine - INFO - Epoch(train) [6][1300/1567] lr: 7.0674e-02 eta: 2:23:32 time: 0.5368 data_time: 0.0072 memory: 2111 loss: 0.2947 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2947 2022/12/22 12:33:31 - mmengine - INFO - Epoch(train) [6][1400/1567] lr: 7.0102e-02 eta: 2:22:38 time: 0.5364 data_time: 0.0069 memory: 2111 loss: 0.2965 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2965 2022/12/22 12:34:25 - mmengine - INFO - Epoch(train) [6][1500/1567] lr: 6.9527e-02 eta: 2:21:43 time: 0.5332 data_time: 0.0070 memory: 2111 loss: 0.2426 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.2426 2022/12/22 12:35:00 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 12:35:00 - mmengine - INFO - Epoch(train) [6][1567/1567] lr: 6.9140e-02 eta: 2:21:05 time: 0.5000 data_time: 0.0067 memory: 2111 loss: 0.4268 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.4268 2022/12/22 12:35:00 - mmengine - INFO - Saving checkpoint at 6 epochs 2022/12/22 12:35:21 - mmengine - INFO - Epoch(val) [6][100/129] eta: 0:00:05 time: 0.1903 data_time: 0.0063 memory: 293 2022/12/22 12:35:27 - mmengine - INFO - Epoch(val) [6][129/129] acc/top1: 0.8098 acc/top5: 0.9612 acc/mean1: 0.8098 2022/12/22 12:35:27 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_5.pth is removed 2022/12/22 12:35:28 - mmengine - INFO - The best checkpoint with 0.8098 acc/top1 at 6 epoch is saved to best_acc/top1_epoch_6.pth. 2022/12/22 12:36:20 - mmengine - INFO - Epoch(train) [7][ 100/1567] lr: 6.8560e-02 eta: 2:20:09 time: 0.5363 data_time: 0.0072 memory: 2111 loss: 0.2500 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2500 2022/12/22 12:37:14 - mmengine - INFO - Epoch(train) [7][ 200/1567] lr: 6.7976e-02 eta: 2:19:14 time: 0.5387 data_time: 0.0071 memory: 2111 loss: 0.1970 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1970 2022/12/22 12:38:07 - mmengine - INFO - Epoch(train) [7][ 300/1567] lr: 6.7390e-02 eta: 2:18:19 time: 0.5365 data_time: 0.0069 memory: 2111 loss: 0.2057 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2057 2022/12/22 12:39:01 - mmengine - INFO - Epoch(train) [7][ 400/1567] lr: 6.6802e-02 eta: 2:17:24 time: 0.5410 data_time: 0.0071 memory: 2111 loss: 0.2359 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2359 2022/12/22 12:39:54 - mmengine - INFO - Epoch(train) [7][ 500/1567] lr: 6.6210e-02 eta: 2:16:30 time: 0.5393 data_time: 0.0076 memory: 2111 loss: 0.2549 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2549 2022/12/22 12:40:47 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 12:40:48 - mmengine - INFO - Epoch(train) [7][ 600/1567] lr: 6.5616e-02 eta: 2:15:35 time: 0.5407 data_time: 0.0070 memory: 2111 loss: 0.2478 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2478 2022/12/22 12:41:42 - mmengine - INFO - Epoch(train) [7][ 700/1567] lr: 6.5020e-02 eta: 2:14:41 time: 0.5350 data_time: 0.0068 memory: 2111 loss: 0.1803 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1803 2022/12/22 12:42:36 - mmengine - INFO - Epoch(train) [7][ 800/1567] lr: 6.4421e-02 eta: 2:13:47 time: 0.5400 data_time: 0.0068 memory: 2111 loss: 0.2332 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2332 2022/12/22 12:43:30 - mmengine - INFO - Epoch(train) [7][ 900/1567] lr: 6.3820e-02 eta: 2:12:53 time: 0.5377 data_time: 0.0071 memory: 2111 loss: 0.2175 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2175 2022/12/22 12:44:23 - mmengine - INFO - Epoch(train) [7][1000/1567] lr: 6.3217e-02 eta: 2:11:58 time: 0.5373 data_time: 0.0068 memory: 2111 loss: 0.2636 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.2636 2022/12/22 12:45:17 - mmengine - INFO - Epoch(train) [7][1100/1567] lr: 6.2612e-02 eta: 2:11:04 time: 0.5395 data_time: 0.0076 memory: 2111 loss: 0.2259 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2259 2022/12/22 12:46:11 - mmengine - INFO - Epoch(train) [7][1200/1567] lr: 6.2005e-02 eta: 2:10:10 time: 0.5363 data_time: 0.0071 memory: 2111 loss: 0.2767 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2767 2022/12/22 12:47:04 - mmengine - INFO - Epoch(train) [7][1300/1567] lr: 6.1396e-02 eta: 2:09:15 time: 0.5413 data_time: 0.0069 memory: 2111 loss: 0.2486 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2486 2022/12/22 12:47:58 - mmengine - INFO - Epoch(train) [7][1400/1567] lr: 6.0785e-02 eta: 2:08:21 time: 0.5338 data_time: 0.0070 memory: 2111 loss: 0.1623 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1623 2022/12/22 12:48:52 - mmengine - INFO - Epoch(train) [7][1500/1567] lr: 6.0172e-02 eta: 2:07:26 time: 0.5380 data_time: 0.0067 memory: 2111 loss: 0.2393 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2393 2022/12/22 12:49:27 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 12:49:27 - mmengine - INFO - Epoch(train) [7][1567/1567] lr: 5.9761e-02 eta: 2:06:49 time: 0.5054 data_time: 0.0065 memory: 2111 loss: 0.4099 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.4099 2022/12/22 12:49:27 - mmengine - INFO - Saving checkpoint at 7 epochs 2022/12/22 12:49:48 - mmengine - INFO - Epoch(val) [7][100/129] eta: 0:00:05 time: 0.1896 data_time: 0.0064 memory: 293 2022/12/22 12:49:54 - mmengine - INFO - Epoch(val) [7][129/129] acc/top1: 0.8303 acc/top5: 0.9699 acc/mean1: 0.8301 2022/12/22 12:49:54 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_6.pth is removed 2022/12/22 12:49:54 - mmengine - INFO - The best checkpoint with 0.8303 acc/top1 at 7 epoch is saved to best_acc/top1_epoch_7.pth. 2022/12/22 12:50:09 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 12:50:46 - mmengine - INFO - Epoch(train) [8][ 100/1567] lr: 5.9145e-02 eta: 2:05:52 time: 0.5406 data_time: 0.0070 memory: 2111 loss: 0.2357 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2357 2022/12/22 12:51:40 - mmengine - INFO - Epoch(train) [8][ 200/1567] lr: 5.8529e-02 eta: 2:04:58 time: 0.5364 data_time: 0.0069 memory: 2111 loss: 0.2056 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2056 2022/12/22 12:52:33 - mmengine - INFO - Epoch(train) [8][ 300/1567] lr: 5.7911e-02 eta: 2:04:04 time: 0.5367 data_time: 0.0069 memory: 2111 loss: 0.2327 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.2327 2022/12/22 12:53:27 - mmengine - INFO - Epoch(train) [8][ 400/1567] lr: 5.7292e-02 eta: 2:03:09 time: 0.5396 data_time: 0.0068 memory: 2111 loss: 0.2286 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2286 2022/12/22 12:54:20 - mmengine - INFO - Epoch(train) [8][ 500/1567] lr: 5.6671e-02 eta: 2:02:15 time: 0.5419 data_time: 0.0069 memory: 2111 loss: 0.2182 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2182 2022/12/22 12:55:14 - mmengine - INFO - Epoch(train) [8][ 600/1567] lr: 5.6050e-02 eta: 2:01:20 time: 0.5387 data_time: 0.0068 memory: 2111 loss: 0.2214 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2214 2022/12/22 12:56:08 - mmengine - INFO - Epoch(train) [8][ 700/1567] lr: 5.5427e-02 eta: 2:00:27 time: 0.5383 data_time: 0.0068 memory: 2111 loss: 0.1611 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1611 2022/12/22 12:57:02 - mmengine - INFO - Epoch(train) [8][ 800/1567] lr: 5.4804e-02 eta: 1:59:33 time: 0.5347 data_time: 0.0069 memory: 2111 loss: 0.2109 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2109 2022/12/22 12:57:55 - mmengine - INFO - Epoch(train) [8][ 900/1567] lr: 5.4180e-02 eta: 1:58:38 time: 0.5383 data_time: 0.0079 memory: 2111 loss: 0.1624 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1624 2022/12/22 12:58:49 - mmengine - INFO - Epoch(train) [8][1000/1567] lr: 5.3556e-02 eta: 1:57:44 time: 0.5330 data_time: 0.0070 memory: 2111 loss: 0.1768 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1768 2022/12/22 12:59:06 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 12:59:43 - mmengine - INFO - Epoch(train) [8][1100/1567] lr: 5.2930e-02 eta: 1:56:50 time: 0.5308 data_time: 0.0068 memory: 2111 loss: 0.1980 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1980 2022/12/22 13:00:36 - mmengine - INFO - Epoch(train) [8][1200/1567] lr: 5.2305e-02 eta: 1:55:56 time: 0.5379 data_time: 0.0068 memory: 2111 loss: 0.1577 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1577 2022/12/22 13:01:30 - mmengine - INFO - Epoch(train) [8][1300/1567] lr: 5.1679e-02 eta: 1:55:01 time: 0.5301 data_time: 0.0068 memory: 2111 loss: 0.1844 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1844 2022/12/22 13:02:24 - mmengine - INFO - Epoch(train) [8][1400/1567] lr: 5.1052e-02 eta: 1:54:07 time: 0.5371 data_time: 0.0069 memory: 2111 loss: 0.1905 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1905 2022/12/22 13:03:17 - mmengine - INFO - Epoch(train) [8][1500/1567] lr: 5.0426e-02 eta: 1:53:13 time: 0.5391 data_time: 0.0073 memory: 2111 loss: 0.1661 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1661 2022/12/22 13:03:53 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 13:03:53 - mmengine - INFO - Epoch(train) [8][1567/1567] lr: 5.0006e-02 eta: 1:52:36 time: 0.5079 data_time: 0.0068 memory: 2111 loss: 0.2988 top1_acc: 0.0000 top5_acc: 1.0000 loss_cls: 0.2988 2022/12/22 13:03:53 - mmengine - INFO - Saving checkpoint at 8 epochs 2022/12/22 13:04:14 - mmengine - INFO - Epoch(val) [8][100/129] eta: 0:00:05 time: 0.1807 data_time: 0.0062 memory: 293 2022/12/22 13:04:20 - mmengine - INFO - Epoch(val) [8][129/129] acc/top1: 0.8341 acc/top5: 0.9654 acc/mean1: 0.8341 2022/12/22 13:04:20 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_7.pth is removed 2022/12/22 13:04:20 - mmengine - INFO - The best checkpoint with 0.8341 acc/top1 at 8 epoch is saved to best_acc/top1_epoch_8.pth. 2022/12/22 13:05:13 - mmengine - INFO - Epoch(train) [9][ 100/1567] lr: 4.9380e-02 eta: 1:51:41 time: 0.5341 data_time: 0.0068 memory: 2111 loss: 0.1183 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1183 2022/12/22 13:06:07 - mmengine - INFO - Epoch(train) [9][ 200/1567] lr: 4.8753e-02 eta: 1:50:47 time: 0.5360 data_time: 0.0068 memory: 2111 loss: 0.1979 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1979 2022/12/22 13:07:00 - mmengine - INFO - Epoch(train) [9][ 300/1567] lr: 4.8127e-02 eta: 1:49:53 time: 0.5327 data_time: 0.0068 memory: 2111 loss: 0.1630 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.1630 2022/12/22 13:07:54 - mmengine - INFO - Epoch(train) [9][ 400/1567] lr: 4.7501e-02 eta: 1:48:59 time: 0.5340 data_time: 0.0068 memory: 2111 loss: 0.1244 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1244 2022/12/22 13:08:28 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 13:08:48 - mmengine - INFO - Epoch(train) [9][ 500/1567] lr: 4.6876e-02 eta: 1:48:04 time: 0.5287 data_time: 0.0070 memory: 2111 loss: 0.1107 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1107 2022/12/22 13:09:41 - mmengine - INFO - Epoch(train) [9][ 600/1567] lr: 4.6251e-02 eta: 1:47:10 time: 0.5414 data_time: 0.0078 memory: 2111 loss: 0.0924 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0924 2022/12/22 13:10:36 - mmengine - INFO - Epoch(train) [9][ 700/1567] lr: 4.5626e-02 eta: 1:46:17 time: 0.5442 data_time: 0.0069 memory: 2111 loss: 0.1599 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.1599 2022/12/22 13:11:29 - mmengine - INFO - Epoch(train) [9][ 800/1567] lr: 4.5003e-02 eta: 1:45:23 time: 0.5312 data_time: 0.0071 memory: 2111 loss: 0.1719 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1719 2022/12/22 13:12:23 - mmengine - INFO - Epoch(train) [9][ 900/1567] lr: 4.4380e-02 eta: 1:44:29 time: 0.5398 data_time: 0.0070 memory: 2111 loss: 0.1597 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1597 2022/12/22 13:13:17 - mmengine - INFO - Epoch(train) [9][1000/1567] lr: 4.3757e-02 eta: 1:43:35 time: 0.5432 data_time: 0.0068 memory: 2111 loss: 0.1463 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.1463 2022/12/22 13:14:11 - mmengine - INFO - Epoch(train) [9][1100/1567] lr: 4.3136e-02 eta: 1:42:41 time: 0.5431 data_time: 0.0070 memory: 2111 loss: 0.1054 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.1054 2022/12/22 13:15:05 - mmengine - INFO - Epoch(train) [9][1200/1567] lr: 4.2516e-02 eta: 1:41:47 time: 0.5333 data_time: 0.0068 memory: 2111 loss: 0.1514 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1514 2022/12/22 13:15:59 - mmengine - INFO - Epoch(train) [9][1300/1567] lr: 4.1897e-02 eta: 1:40:54 time: 0.5343 data_time: 0.0069 memory: 2111 loss: 0.1378 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1378 2022/12/22 13:16:53 - mmengine - INFO - Epoch(train) [9][1400/1567] lr: 4.1280e-02 eta: 1:40:00 time: 0.5388 data_time: 0.0072 memory: 2111 loss: 0.0922 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0922 2022/12/22 13:17:28 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 13:17:47 - mmengine - INFO - Epoch(train) [9][1500/1567] lr: 4.0664e-02 eta: 1:39:06 time: 0.5384 data_time: 0.0070 memory: 2111 loss: 0.1332 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1332 2022/12/22 13:18:23 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 13:18:23 - mmengine - INFO - Epoch(train) [9][1567/1567] lr: 4.0252e-02 eta: 1:38:30 time: 0.5058 data_time: 0.0070 memory: 2111 loss: 0.3004 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.3004 2022/12/22 13:18:23 - mmengine - INFO - Saving checkpoint at 9 epochs 2022/12/22 13:18:45 - mmengine - INFO - Epoch(val) [9][100/129] eta: 0:00:06 time: 0.1881 data_time: 0.0063 memory: 293 2022/12/22 13:18:51 - mmengine - INFO - Epoch(val) [9][129/129] acc/top1: 0.8471 acc/top5: 0.9702 acc/mean1: 0.8470 2022/12/22 13:18:51 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_8.pth is removed 2022/12/22 13:18:51 - mmengine - INFO - The best checkpoint with 0.8471 acc/top1 at 9 epoch is saved to best_acc/top1_epoch_9.pth. 2022/12/22 13:19:43 - mmengine - INFO - Epoch(train) [10][ 100/1567] lr: 3.9638e-02 eta: 1:37:34 time: 0.5372 data_time: 0.0069 memory: 2111 loss: 0.0865 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0865 2022/12/22 13:20:37 - mmengine - INFO - Epoch(train) [10][ 200/1567] lr: 3.9026e-02 eta: 1:36:40 time: 0.5430 data_time: 0.0069 memory: 2111 loss: 0.1159 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1159 2022/12/22 13:21:31 - mmengine - INFO - Epoch(train) [10][ 300/1567] lr: 3.8415e-02 eta: 1:35:47 time: 0.5426 data_time: 0.0076 memory: 2111 loss: 0.1226 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1226 2022/12/22 13:22:25 - mmengine - INFO - Epoch(train) [10][ 400/1567] lr: 3.7807e-02 eta: 1:34:53 time: 0.5316 data_time: 0.0068 memory: 2111 loss: 0.0848 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0848 2022/12/22 13:23:18 - mmengine - INFO - Epoch(train) [10][ 500/1567] lr: 3.7200e-02 eta: 1:33:59 time: 0.5481 data_time: 0.0072 memory: 2111 loss: 0.1009 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1009 2022/12/22 13:24:12 - mmengine - INFO - Epoch(train) [10][ 600/1567] lr: 3.6596e-02 eta: 1:33:05 time: 0.5461 data_time: 0.0069 memory: 2111 loss: 0.0791 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0791 2022/12/22 13:25:06 - mmengine - INFO - Epoch(train) [10][ 700/1567] lr: 3.5993e-02 eta: 1:32:11 time: 0.5394 data_time: 0.0070 memory: 2111 loss: 0.1375 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1375 2022/12/22 13:26:01 - mmengine - INFO - Epoch(train) [10][ 800/1567] lr: 3.5393e-02 eta: 1:31:17 time: 0.5410 data_time: 0.0070 memory: 2111 loss: 0.0799 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0799 2022/12/22 13:26:53 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 13:26:55 - mmengine - INFO - Epoch(train) [10][ 900/1567] lr: 3.4795e-02 eta: 1:30:24 time: 0.5433 data_time: 0.0069 memory: 2111 loss: 0.1210 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.1210 2022/12/22 13:27:49 - mmengine - INFO - Epoch(train) [10][1000/1567] lr: 3.4199e-02 eta: 1:29:30 time: 0.5409 data_time: 0.0068 memory: 2111 loss: 0.0803 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0803 2022/12/22 13:28:42 - mmengine - INFO - Epoch(train) [10][1100/1567] lr: 3.3606e-02 eta: 1:28:36 time: 0.5453 data_time: 0.0076 memory: 2111 loss: 0.0920 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0920 2022/12/22 13:29:36 - mmengine - INFO - Epoch(train) [10][1200/1567] lr: 3.3015e-02 eta: 1:27:42 time: 0.5394 data_time: 0.0070 memory: 2111 loss: 0.0710 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0710 2022/12/22 13:30:30 - mmengine - INFO - Epoch(train) [10][1300/1567] lr: 3.2428e-02 eta: 1:26:48 time: 0.5394 data_time: 0.0070 memory: 2111 loss: 0.0960 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0960 2022/12/22 13:31:24 - mmengine - INFO - Epoch(train) [10][1400/1567] lr: 3.1842e-02 eta: 1:25:54 time: 0.5455 data_time: 0.0073 memory: 2111 loss: 0.0692 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0692 2022/12/22 13:32:18 - mmengine - INFO - Epoch(train) [10][1500/1567] lr: 3.1260e-02 eta: 1:25:01 time: 0.5445 data_time: 0.0071 memory: 2111 loss: 0.0931 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0931 2022/12/22 13:32:54 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 13:32:54 - mmengine - INFO - Epoch(train) [10][1567/1567] lr: 3.0872e-02 eta: 1:24:24 time: 0.4932 data_time: 0.0070 memory: 2111 loss: 0.2443 top1_acc: 0.0000 top5_acc: 1.0000 loss_cls: 0.2443 2022/12/22 13:32:54 - mmengine - INFO - Saving checkpoint at 10 epochs 2022/12/22 13:33:16 - mmengine - INFO - Epoch(val) [10][100/129] eta: 0:00:06 time: 0.1829 data_time: 0.0064 memory: 293 2022/12/22 13:33:23 - mmengine - INFO - Epoch(val) [10][129/129] acc/top1: 0.8457 acc/top5: 0.9654 acc/mean1: 0.8457 2022/12/22 13:34:15 - mmengine - INFO - Epoch(train) [11][ 100/1567] lr: 3.0294e-02 eta: 1:23:29 time: 0.5434 data_time: 0.0071 memory: 2111 loss: 0.0726 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0726 2022/12/22 13:35:09 - mmengine - INFO - Epoch(train) [11][ 200/1567] lr: 2.9720e-02 eta: 1:22:36 time: 0.5427 data_time: 0.0070 memory: 2111 loss: 0.0579 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0579 2022/12/22 13:36:03 - mmengine - INFO - Epoch(train) [11][ 300/1567] lr: 2.9149e-02 eta: 1:21:42 time: 0.5419 data_time: 0.0068 memory: 2111 loss: 0.0806 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0806 2022/12/22 13:36:19 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 13:36:57 - mmengine - INFO - Epoch(train) [11][ 400/1567] lr: 2.8581e-02 eta: 1:20:48 time: 0.5402 data_time: 0.0072 memory: 2111 loss: 0.0597 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0597 2022/12/22 13:37:52 - mmengine - INFO - Epoch(train) [11][ 500/1567] lr: 2.8017e-02 eta: 1:19:55 time: 0.5430 data_time: 0.0073 memory: 2111 loss: 0.0448 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0448 2022/12/22 13:38:46 - mmengine - INFO - Epoch(train) [11][ 600/1567] lr: 2.7456e-02 eta: 1:19:01 time: 0.5358 data_time: 0.0074 memory: 2111 loss: 0.0712 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0712 2022/12/22 13:39:40 - mmengine - INFO - Epoch(train) [11][ 700/1567] lr: 2.6898e-02 eta: 1:18:07 time: 0.5411 data_time: 0.0070 memory: 2111 loss: 0.0561 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0561 2022/12/22 13:40:34 - mmengine - INFO - Epoch(train) [11][ 800/1567] lr: 2.6345e-02 eta: 1:17:13 time: 0.5445 data_time: 0.0071 memory: 2111 loss: 0.0680 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0680 2022/12/22 13:41:28 - mmengine - INFO - Epoch(train) [11][ 900/1567] lr: 2.5794e-02 eta: 1:16:19 time: 0.5329 data_time: 0.0071 memory: 2111 loss: 0.0434 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0434 2022/12/22 13:42:22 - mmengine - INFO - Epoch(train) [11][1000/1567] lr: 2.5248e-02 eta: 1:15:26 time: 0.5399 data_time: 0.0070 memory: 2111 loss: 0.0421 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0421 2022/12/22 13:43:16 - mmengine - INFO - Epoch(train) [11][1100/1567] lr: 2.4706e-02 eta: 1:14:32 time: 0.5405 data_time: 0.0070 memory: 2111 loss: 0.0511 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0511 2022/12/22 13:44:10 - mmengine - INFO - Epoch(train) [11][1200/1567] lr: 2.4167e-02 eta: 1:13:38 time: 0.5389 data_time: 0.0071 memory: 2111 loss: 0.0394 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0394 2022/12/22 13:45:04 - mmengine - INFO - Epoch(train) [11][1300/1567] lr: 2.3633e-02 eta: 1:12:45 time: 0.5329 data_time: 0.0070 memory: 2111 loss: 0.0548 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0548 2022/12/22 13:45:20 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 13:45:58 - mmengine - INFO - Epoch(train) [11][1400/1567] lr: 2.3103e-02 eta: 1:11:51 time: 0.5396 data_time: 0.0071 memory: 2111 loss: 0.0229 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0229 2022/12/22 13:46:52 - mmengine - INFO - Epoch(train) [11][1500/1567] lr: 2.2577e-02 eta: 1:10:57 time: 0.5386 data_time: 0.0070 memory: 2111 loss: 0.0356 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0356 2022/12/22 13:47:28 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 13:47:28 - mmengine - INFO - Epoch(train) [11][1567/1567] lr: 2.2227e-02 eta: 1:10:20 time: 0.4928 data_time: 0.0068 memory: 2111 loss: 0.1963 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1963 2022/12/22 13:47:28 - mmengine - INFO - Saving checkpoint at 11 epochs 2022/12/22 13:47:50 - mmengine - INFO - Epoch(val) [11][100/129] eta: 0:00:06 time: 0.1865 data_time: 0.0064 memory: 293 2022/12/22 13:47:57 - mmengine - INFO - Epoch(val) [11][129/129] acc/top1: 0.8615 acc/top5: 0.9716 acc/mean1: 0.8615 2022/12/22 13:47:57 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_9.pth is removed 2022/12/22 13:47:57 - mmengine - INFO - The best checkpoint with 0.8615 acc/top1 at 11 epoch is saved to best_acc/top1_epoch_11.pth. 2022/12/22 13:48:49 - mmengine - INFO - Epoch(train) [12][ 100/1567] lr: 2.1708e-02 eta: 1:09:25 time: 0.5297 data_time: 0.0071 memory: 2111 loss: 0.0327 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0327 2022/12/22 13:49:43 - mmengine - INFO - Epoch(train) [12][ 200/1567] lr: 2.1194e-02 eta: 1:08:32 time: 0.5428 data_time: 0.0068 memory: 2111 loss: 0.0267 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0267 2022/12/22 13:50:37 - mmengine - INFO - Epoch(train) [12][ 300/1567] lr: 2.0684e-02 eta: 1:07:38 time: 0.5448 data_time: 0.0072 memory: 2111 loss: 0.0581 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0581 2022/12/22 13:51:31 - mmengine - INFO - Epoch(train) [12][ 400/1567] lr: 2.0179e-02 eta: 1:06:44 time: 0.5449 data_time: 0.0068 memory: 2111 loss: 0.0201 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0201 2022/12/22 13:52:25 - mmengine - INFO - Epoch(train) [12][ 500/1567] lr: 1.9678e-02 eta: 1:05:51 time: 0.5424 data_time: 0.0072 memory: 2111 loss: 0.0201 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0201 2022/12/22 13:53:20 - mmengine - INFO - Epoch(train) [12][ 600/1567] lr: 1.9182e-02 eta: 1:04:57 time: 0.5438 data_time: 0.0069 memory: 2111 loss: 0.0257 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0257 2022/12/22 13:54:13 - mmengine - INFO - Epoch(train) [12][ 700/1567] lr: 1.8691e-02 eta: 1:04:03 time: 0.5462 data_time: 0.0068 memory: 2111 loss: 0.0217 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0217 2022/12/22 13:54:47 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 13:55:07 - mmengine - INFO - Epoch(train) [12][ 800/1567] lr: 1.8205e-02 eta: 1:03:09 time: 0.5471 data_time: 0.0076 memory: 2111 loss: 0.0263 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0263 2022/12/22 13:56:01 - mmengine - INFO - Epoch(train) [12][ 900/1567] lr: 1.7724e-02 eta: 1:02:15 time: 0.5353 data_time: 0.0072 memory: 2111 loss: 0.0140 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0140 2022/12/22 13:56:55 - mmengine - INFO - Epoch(train) [12][1000/1567] lr: 1.7248e-02 eta: 1:01:21 time: 0.5418 data_time: 0.0073 memory: 2111 loss: 0.0110 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0110 2022/12/22 13:57:49 - mmengine - INFO - Epoch(train) [12][1100/1567] lr: 1.6778e-02 eta: 1:00:28 time: 0.5371 data_time: 0.0074 memory: 2111 loss: 0.0222 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0222 2022/12/22 13:58:43 - mmengine - INFO - Epoch(train) [12][1200/1567] lr: 1.6312e-02 eta: 0:59:34 time: 0.5419 data_time: 0.0071 memory: 2111 loss: 0.0192 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0192 2022/12/22 13:59:37 - mmengine - INFO - Epoch(train) [12][1300/1567] lr: 1.5852e-02 eta: 0:58:40 time: 0.5426 data_time: 0.0068 memory: 2111 loss: 0.0219 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0219 2022/12/22 14:00:32 - mmengine - INFO - Epoch(train) [12][1400/1567] lr: 1.5397e-02 eta: 0:57:46 time: 0.5412 data_time: 0.0070 memory: 2111 loss: 0.0184 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0184 2022/12/22 14:01:26 - mmengine - INFO - Epoch(train) [12][1500/1567] lr: 1.4947e-02 eta: 0:56:52 time: 0.5451 data_time: 0.0074 memory: 2111 loss: 0.0182 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0182 2022/12/22 14:02:01 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 14:02:01 - mmengine - INFO - Epoch(train) [12][1567/1567] lr: 1.4649e-02 eta: 0:56:16 time: 0.4993 data_time: 0.0068 memory: 2111 loss: 0.2205 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.2205 2022/12/22 14:02:01 - mmengine - INFO - Saving checkpoint at 12 epochs 2022/12/22 14:02:24 - mmengine - INFO - Epoch(val) [12][100/129] eta: 0:00:06 time: 0.1906 data_time: 0.0064 memory: 293 2022/12/22 14:02:30 - mmengine - INFO - Epoch(val) [12][129/129] acc/top1: 0.8807 acc/top5: 0.9742 acc/mean1: 0.8806 2022/12/22 14:02:30 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_11.pth is removed 2022/12/22 14:02:30 - mmengine - INFO - The best checkpoint with 0.8807 acc/top1 at 12 epoch is saved to best_acc/top1_epoch_12.pth. 2022/12/22 14:03:22 - mmengine - INFO - Epoch(train) [13][ 100/1567] lr: 1.4209e-02 eta: 0:55:22 time: 0.5441 data_time: 0.0074 memory: 2111 loss: 0.0147 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0147 2022/12/22 14:04:14 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 14:04:17 - mmengine - INFO - Epoch(train) [13][ 200/1567] lr: 1.3774e-02 eta: 0:54:28 time: 0.5426 data_time: 0.0071 memory: 2111 loss: 0.0167 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0167 2022/12/22 14:05:11 - mmengine - INFO - Epoch(train) [13][ 300/1567] lr: 1.3345e-02 eta: 0:53:34 time: 0.5395 data_time: 0.0070 memory: 2111 loss: 0.0084 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0084 2022/12/22 14:06:05 - mmengine - INFO - Epoch(train) [13][ 400/1567] lr: 1.2922e-02 eta: 0:52:40 time: 0.5424 data_time: 0.0068 memory: 2111 loss: 0.0139 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0139 2022/12/22 14:06:59 - mmengine - INFO - Epoch(train) [13][ 500/1567] lr: 1.2505e-02 eta: 0:51:46 time: 0.5461 data_time: 0.0070 memory: 2111 loss: 0.0099 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0099 2022/12/22 14:07:53 - mmengine - INFO - Epoch(train) [13][ 600/1567] lr: 1.2093e-02 eta: 0:50:53 time: 0.5385 data_time: 0.0071 memory: 2111 loss: 0.0103 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0103 2022/12/22 14:08:47 - mmengine - INFO - Epoch(train) [13][ 700/1567] lr: 1.1687e-02 eta: 0:49:59 time: 0.5425 data_time: 0.0067 memory: 2111 loss: 0.0074 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0074 2022/12/22 14:09:41 - mmengine - INFO - Epoch(train) [13][ 800/1567] lr: 1.1288e-02 eta: 0:49:05 time: 0.5396 data_time: 0.0071 memory: 2111 loss: 0.0088 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0088 2022/12/22 14:10:35 - mmengine - INFO - Epoch(train) [13][ 900/1567] lr: 1.0894e-02 eta: 0:48:11 time: 0.5458 data_time: 0.0073 memory: 2111 loss: 0.0101 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0101 2022/12/22 14:11:29 - mmengine - INFO - Epoch(train) [13][1000/1567] lr: 1.0507e-02 eta: 0:47:17 time: 0.5432 data_time: 0.0070 memory: 2111 loss: 0.0124 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0124 2022/12/22 14:12:23 - mmengine - INFO - Epoch(train) [13][1100/1567] lr: 1.0126e-02 eta: 0:46:24 time: 0.5408 data_time: 0.0070 memory: 2111 loss: 0.0102 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0102 2022/12/22 14:13:15 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 14:13:17 - mmengine - INFO - Epoch(train) [13][1200/1567] lr: 9.7512e-03 eta: 0:45:30 time: 0.5402 data_time: 0.0070 memory: 2111 loss: 0.0074 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0074 2022/12/22 14:14:11 - mmengine - INFO - Epoch(train) [13][1300/1567] lr: 9.3826e-03 eta: 0:44:36 time: 0.5450 data_time: 0.0071 memory: 2111 loss: 0.0103 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0103 2022/12/22 14:15:06 - mmengine - INFO - Epoch(train) [13][1400/1567] lr: 9.0204e-03 eta: 0:43:42 time: 0.5396 data_time: 0.0076 memory: 2111 loss: 0.0090 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0090 2022/12/22 14:16:00 - mmengine - INFO - Epoch(train) [13][1500/1567] lr: 8.6647e-03 eta: 0:42:48 time: 0.5414 data_time: 0.0069 memory: 2111 loss: 0.0077 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0077 2022/12/22 14:16:35 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 14:16:35 - mmengine - INFO - Epoch(train) [13][1567/1567] lr: 8.4300e-03 eta: 0:42:12 time: 0.4922 data_time: 0.0068 memory: 2111 loss: 0.2367 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.2367 2022/12/22 14:16:35 - mmengine - INFO - Saving checkpoint at 13 epochs 2022/12/22 14:16:58 - mmengine - INFO - Epoch(val) [13][100/129] eta: 0:00:06 time: 0.1892 data_time: 0.0065 memory: 293 2022/12/22 14:17:04 - mmengine - INFO - Epoch(val) [13][129/129] acc/top1: 0.8820 acc/top5: 0.9760 acc/mean1: 0.8820 2022/12/22 14:17:04 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_12.pth is removed 2022/12/22 14:17:05 - mmengine - INFO - The best checkpoint with 0.8820 acc/top1 at 13 epoch is saved to best_acc/top1_epoch_13.pth. 2022/12/22 14:17:57 - mmengine - INFO - Epoch(train) [14][ 100/1567] lr: 8.0851e-03 eta: 0:41:18 time: 0.5464 data_time: 0.0070 memory: 2111 loss: 0.0078 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0078 2022/12/22 14:18:51 - mmengine - INFO - Epoch(train) [14][ 200/1567] lr: 7.7469e-03 eta: 0:40:24 time: 0.5463 data_time: 0.0069 memory: 2111 loss: 0.0087 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0087 2022/12/22 14:19:45 - mmengine - INFO - Epoch(train) [14][ 300/1567] lr: 7.4152e-03 eta: 0:39:30 time: 0.5422 data_time: 0.0070 memory: 2111 loss: 0.0069 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0069 2022/12/22 14:20:39 - mmengine - INFO - Epoch(train) [14][ 400/1567] lr: 7.0902e-03 eta: 0:38:36 time: 0.5414 data_time: 0.0072 memory: 2111 loss: 0.0084 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0084 2022/12/22 14:21:33 - mmengine - INFO - Epoch(train) [14][ 500/1567] lr: 6.7720e-03 eta: 0:37:42 time: 0.5406 data_time: 0.0069 memory: 2111 loss: 0.0072 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0072 2022/12/22 14:22:27 - mmengine - INFO - Epoch(train) [14][ 600/1567] lr: 6.4606e-03 eta: 0:36:49 time: 0.5381 data_time: 0.0070 memory: 2111 loss: 0.0104 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0104 2022/12/22 14:22:43 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 14:23:22 - mmengine - INFO - Epoch(train) [14][ 700/1567] lr: 6.1560e-03 eta: 0:35:55 time: 0.5440 data_time: 0.0070 memory: 2111 loss: 0.0075 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0075 2022/12/22 14:24:15 - mmengine - INFO - Epoch(train) [14][ 800/1567] lr: 5.8582e-03 eta: 0:35:01 time: 0.5439 data_time: 0.0069 memory: 2111 loss: 0.0063 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0063 2022/12/22 14:25:09 - mmengine - INFO - Epoch(train) [14][ 900/1567] lr: 5.5675e-03 eta: 0:34:07 time: 0.5329 data_time: 0.0074 memory: 2111 loss: 0.0062 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0062 2022/12/22 14:26:03 - mmengine - INFO - Epoch(train) [14][1000/1567] lr: 5.2836e-03 eta: 0:33:13 time: 0.5404 data_time: 0.0073 memory: 2111 loss: 0.0057 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0057 2022/12/22 14:26:57 - mmengine - INFO - Epoch(train) [14][1100/1567] lr: 5.0068e-03 eta: 0:32:19 time: 0.5429 data_time: 0.0069 memory: 2111 loss: 0.0078 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0078 2022/12/22 14:27:51 - mmengine - INFO - Epoch(train) [14][1200/1567] lr: 4.7371e-03 eta: 0:31:25 time: 0.5442 data_time: 0.0074 memory: 2111 loss: 0.0091 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0091 2022/12/22 14:28:44 - mmengine - INFO - Epoch(train) [14][1300/1567] lr: 4.4745e-03 eta: 0:30:32 time: 0.5365 data_time: 0.0068 memory: 2111 loss: 0.0079 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0079 2022/12/22 14:29:38 - mmengine - INFO - Epoch(train) [14][1400/1567] lr: 4.2190e-03 eta: 0:29:38 time: 0.5380 data_time: 0.0068 memory: 2111 loss: 0.0067 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0067 2022/12/22 14:30:32 - mmengine - INFO - Epoch(train) [14][1500/1567] lr: 3.9707e-03 eta: 0:28:44 time: 0.5330 data_time: 0.0073 memory: 2111 loss: 0.0081 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0081 2022/12/22 14:31:07 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 14:31:07 - mmengine - INFO - Epoch(train) [14][1567/1567] lr: 3.8084e-03 eta: 0:28:07 time: 0.4947 data_time: 0.0069 memory: 2111 loss: 0.1561 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1561 2022/12/22 14:31:07 - mmengine - INFO - Saving checkpoint at 14 epochs 2022/12/22 14:31:30 - mmengine - INFO - Epoch(val) [14][100/129] eta: 0:00:06 time: 0.1897 data_time: 0.0067 memory: 293 2022/12/22 14:31:36 - mmengine - INFO - Epoch(val) [14][129/129] acc/top1: 0.8872 acc/top5: 0.9777 acc/mean1: 0.8871 2022/12/22 14:31:36 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_13.pth is removed 2022/12/22 14:31:37 - mmengine - INFO - The best checkpoint with 0.8872 acc/top1 at 14 epoch is saved to best_acc/top1_epoch_14.pth. 2022/12/22 14:32:07 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 14:32:28 - mmengine - INFO - Epoch(train) [15][ 100/1567] lr: 3.5722e-03 eta: 0:27:13 time: 0.5343 data_time: 0.0090 memory: 2111 loss: 0.0091 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0091 2022/12/22 14:33:21 - mmengine - INFO - Epoch(train) [15][ 200/1567] lr: 3.3433e-03 eta: 0:26:19 time: 0.5342 data_time: 0.0088 memory: 2111 loss: 0.0144 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0144 2022/12/22 14:34:15 - mmengine - INFO - Epoch(train) [15][ 300/1567] lr: 3.1217e-03 eta: 0:25:25 time: 0.5467 data_time: 0.0096 memory: 2111 loss: 0.0082 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0082 2022/12/22 14:35:10 - mmengine - INFO - Epoch(train) [15][ 400/1567] lr: 2.9075e-03 eta: 0:24:32 time: 0.5429 data_time: 0.0090 memory: 2111 loss: 0.0074 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0074 2022/12/22 14:36:04 - mmengine - INFO - Epoch(train) [15][ 500/1567] lr: 2.7007e-03 eta: 0:23:38 time: 0.5456 data_time: 0.0106 memory: 2111 loss: 0.0077 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0077 2022/12/22 14:36:58 - mmengine - INFO - Epoch(train) [15][ 600/1567] lr: 2.5013e-03 eta: 0:22:44 time: 0.5304 data_time: 0.0104 memory: 2111 loss: 0.0093 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0093 2022/12/22 14:37:53 - mmengine - INFO - Epoch(train) [15][ 700/1567] lr: 2.3093e-03 eta: 0:21:50 time: 0.5442 data_time: 0.0101 memory: 2111 loss: 0.0073 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0073 2022/12/22 14:38:47 - mmengine - INFO - Epoch(train) [15][ 800/1567] lr: 2.1249e-03 eta: 0:20:56 time: 0.5376 data_time: 0.0106 memory: 2111 loss: 0.0071 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0071 2022/12/22 14:39:41 - mmengine - INFO - Epoch(train) [15][ 900/1567] lr: 1.9479e-03 eta: 0:20:03 time: 0.5457 data_time: 0.0084 memory: 2111 loss: 0.0083 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0083 2022/12/22 14:40:35 - mmengine - INFO - Epoch(train) [15][1000/1567] lr: 1.7785e-03 eta: 0:19:09 time: 0.5394 data_time: 0.0092 memory: 2111 loss: 0.0073 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0073 2022/12/22 14:41:09 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 14:41:30 - mmengine - INFO - Epoch(train) [15][1100/1567] lr: 1.6167e-03 eta: 0:18:15 time: 0.5481 data_time: 0.0101 memory: 2111 loss: 0.0101 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0101 2022/12/22 14:42:24 - mmengine - INFO - Epoch(train) [15][1200/1567] lr: 1.4625e-03 eta: 0:17:21 time: 0.5347 data_time: 0.0113 memory: 2111 loss: 0.0061 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0061 2022/12/22 14:43:19 - mmengine - INFO - Epoch(train) [15][1300/1567] lr: 1.3159e-03 eta: 0:16:27 time: 0.5468 data_time: 0.0093 memory: 2111 loss: 0.0080 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0080 2022/12/22 14:44:13 - mmengine - INFO - Epoch(train) [15][1400/1567] lr: 1.1769e-03 eta: 0:15:34 time: 0.5393 data_time: 0.0114 memory: 2111 loss: 0.0069 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0069 2022/12/22 14:45:07 - mmengine - INFO - Epoch(train) [15][1500/1567] lr: 1.0456e-03 eta: 0:14:40 time: 0.5474 data_time: 0.0093 memory: 2111 loss: 0.0077 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0077 2022/12/22 14:45:42 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 14:45:42 - mmengine - INFO - Epoch(train) [15][1567/1567] lr: 9.6196e-04 eta: 0:14:04 time: 0.4968 data_time: 0.0088 memory: 2111 loss: 0.2060 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.2060 2022/12/22 14:45:42 - mmengine - INFO - Saving checkpoint at 15 epochs 2022/12/22 14:46:06 - mmengine - INFO - Epoch(val) [15][100/129] eta: 0:00:06 time: 0.1763 data_time: 0.0088 memory: 293 2022/12/22 14:46:13 - mmengine - INFO - Epoch(val) [15][129/129] acc/top1: 0.8871 acc/top5: 0.9768 acc/mean1: 0.8870 2022/12/22 14:47:03 - mmengine - INFO - Epoch(train) [16][ 100/1567] lr: 8.4351e-04 eta: 0:13:10 time: 0.5435 data_time: 0.0097 memory: 2111 loss: 0.0069 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0069 2022/12/22 14:47:58 - mmengine - INFO - Epoch(train) [16][ 200/1567] lr: 7.3277e-04 eta: 0:12:16 time: 0.5389 data_time: 0.0090 memory: 2111 loss: 0.0061 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0061 2022/12/22 14:48:52 - mmengine - INFO - Epoch(train) [16][ 300/1567] lr: 6.2978e-04 eta: 0:11:22 time: 0.5429 data_time: 0.0093 memory: 2111 loss: 0.0089 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0089 2022/12/22 14:49:46 - mmengine - INFO - Epoch(train) [16][ 400/1567] lr: 5.3453e-04 eta: 0:10:28 time: 0.5385 data_time: 0.0083 memory: 2111 loss: 0.0074 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0074 2022/12/22 14:50:38 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 14:50:40 - mmengine - INFO - Epoch(train) [16][ 500/1567] lr: 4.4705e-04 eta: 0:09:34 time: 0.5388 data_time: 0.0103 memory: 2111 loss: 0.0080 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0080 2022/12/22 14:51:35 - mmengine - INFO - Epoch(train) [16][ 600/1567] lr: 3.6735e-04 eta: 0:08:40 time: 0.5440 data_time: 0.0095 memory: 2111 loss: 0.0081 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0081 2022/12/22 14:52:29 - mmengine - INFO - Epoch(train) [16][ 700/1567] lr: 2.9544e-04 eta: 0:07:46 time: 0.5399 data_time: 0.0110 memory: 2111 loss: 0.0082 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0082 2022/12/22 14:53:23 - mmengine - INFO - Epoch(train) [16][ 800/1567] lr: 2.3134e-04 eta: 0:06:53 time: 0.5468 data_time: 0.0090 memory: 2111 loss: 0.0082 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0082 2022/12/22 14:54:17 - mmengine - INFO - Epoch(train) [16][ 900/1567] lr: 1.7505e-04 eta: 0:05:59 time: 0.5125 data_time: 0.0120 memory: 2111 loss: 0.0068 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0068 2022/12/22 14:55:11 - mmengine - INFO - Epoch(train) [16][1000/1567] lr: 1.2658e-04 eta: 0:05:05 time: 0.5493 data_time: 0.0088 memory: 2111 loss: 0.0095 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0095 2022/12/22 14:56:05 - mmengine - INFO - Epoch(train) [16][1100/1567] lr: 8.5947e-05 eta: 0:04:11 time: 0.5442 data_time: 0.0108 memory: 2111 loss: 0.0091 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0091 2022/12/22 14:57:00 - mmengine - INFO - Epoch(train) [16][1200/1567] lr: 5.3147e-05 eta: 0:03:17 time: 0.5359 data_time: 0.0094 memory: 2111 loss: 0.0078 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0078 2022/12/22 14:57:54 - mmengine - INFO - Epoch(train) [16][1300/1567] lr: 2.8190e-05 eta: 0:02:23 time: 0.5472 data_time: 0.0110 memory: 2111 loss: 0.0080 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0080 2022/12/22 14:58:49 - mmengine - INFO - Epoch(train) [16][1400/1567] lr: 1.1078e-05 eta: 0:01:29 time: 0.5398 data_time: 0.0100 memory: 2111 loss: 0.0083 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0083 2022/12/22 14:59:40 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 14:59:43 - mmengine - INFO - Epoch(train) [16][1500/1567] lr: 1.8150e-06 eta: 0:00:36 time: 0.5474 data_time: 0.0096 memory: 2111 loss: 0.0091 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0091 2022/12/22 15:00:19 - mmengine - INFO - Exp name: 2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 15:00:19 - mmengine - INFO - Epoch(train) [16][1567/1567] lr: 3.9252e-10 eta: 0:00:00 time: 0.5006 data_time: 0.0091 memory: 2111 loss: 0.2295 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.2295 2022/12/22 15:00:19 - mmengine - INFO - Saving checkpoint at 16 epochs 2022/12/22 15:00:43 - mmengine - INFO - Epoch(val) [16][100/129] eta: 0:00:06 time: 0.1900 data_time: 0.0099 memory: 293 2022/12/22 15:00:48 - mmengine - INFO - Epoch(val) [16][129/129] acc/top1: 0.8878 acc/top5: 0.9770 acc/mean1: 0.8877 2022/12/22 15:00:48 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-bone-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_14.pth is removed 2022/12/22 15:00:48 - mmengine - INFO - The best checkpoint with 0.8878 acc/top1 at 16 epoch is saved to best_acc/top1_epoch_16.pth.