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: 1087380457 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=['jm']), dict(type='UniformSampleFrames', clip_len=100), dict(type='PoseDecode'), dict(type='FormatGCNInput', num_person=2), dict(type='PackActionInputs') ] val_pipeline = [ dict(type='PreNormalize3D'), dict(type='GenSkeFeat', dataset='nturgb+d', feats=['jm']), dict( type='UniformSampleFrames', clip_len=100, num_clips=1, test_mode=True), dict(type='PoseDecode'), dict(type='FormatGCNInput', num_person=2), dict(type='PackActionInputs') ] test_pipeline = [ dict(type='PreNormalize3D'), dict(type='GenSkeFeat', dataset='nturgb+d', feats=['jm']), dict( type='UniformSampleFrames', clip_len=100, num_clips=10, test_mode=True), dict(type='PoseDecode'), dict(type='FormatGCNInput', num_person=2), dict(type='PackActionInputs') ] train_dataloader = dict( batch_size=16, num_workers=2, persistent_workers=True, sampler=dict(type='DefaultSampler', shuffle=True), dataset=dict( type='RepeatDataset', times=5, dataset=dict( type='PoseDataset', ann_file='data/skeleton/ntu60_3d.pkl', pipeline=[ dict(type='PreNormalize3D'), dict(type='GenSkeFeat', dataset='nturgb+d', feats=['jm']), dict(type='UniformSampleFrames', clip_len=100), dict(type='PoseDecode'), dict(type='FormatGCNInput', num_person=2), dict(type='PackActionInputs') ], split='xsub_train'))) val_dataloader = dict( batch_size=16, num_workers=2, persistent_workers=True, sampler=dict(type='DefaultSampler', shuffle=False), dataset=dict( type='PoseDataset', ann_file='data/skeleton/ntu60_3d.pkl', pipeline=[ dict(type='PreNormalize3D'), dict(type='GenSkeFeat', dataset='nturgb+d', feats=['jm']), dict( type='UniformSampleFrames', clip_len=100, num_clips=1, test_mode=True), dict(type='PoseDecode'), dict(type='FormatGCNInput', num_person=2), dict(type='PackActionInputs') ], split='xsub_val', test_mode=True)) test_dataloader = dict( batch_size=1, num_workers=2, persistent_workers=True, sampler=dict(type='DefaultSampler', shuffle=False), dataset=dict( type='PoseDataset', ann_file='data/skeleton/ntu60_3d.pkl', pipeline=[ dict(type='PreNormalize3D'), dict(type='GenSkeFeat', dataset='nturgb+d', feats=['jm']), dict( type='UniformSampleFrames', clip_len=100, num_clips=10, test_mode=True), dict(type='PoseDecode'), dict(type='FormatGCNInput', num_person=2), dict(type='PackActionInputs') ], split='xsub_val', test_mode=True)) val_evaluator = [dict(type='AccMetric')] test_evaluator = [dict(type='AccMetric')] train_cfg = dict( type='EpochBasedTrainLoop', max_epochs=16, val_begin=1, val_interval=1) val_cfg = dict(type='ValLoop') test_cfg = dict(type='TestLoop') param_scheduler = [ dict( type='CosineAnnealingLR', eta_min=0, T_max=16, by_epoch=True, convert_to_iter_based=True) ] optim_wrapper = dict( optimizer=dict( type='SGD', lr=0.1, momentum=0.9, weight_decay=0.0005, nesterov=True)) auto_scale_lr = dict(enable=False, base_batch_size=128) launcher = 'pytorch' work_dir = './work_dirs/2s-agcn_8xb16-joint-motion-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-joint-motion-u100-80e_ntu60-xsub-keypoint-3d/modules_statistic_results.json 2022/12/22 11:06:53 - 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-joint-motion-u100-80e_ntu60-xsub-keypoint-3d. 2022/12/22 11:09:12 - mmengine - INFO - Epoch(train) [1][ 100/1567] lr: 9.9996e-02 eta: 4:30:16 time: 0.5422 data_time: 0.0070 memory: 2111 loss: 2.8016 top1_acc: 0.1875 top5_acc: 0.5625 loss_cls: 2.8016 2022/12/22 11:10:06 - mmengine - INFO - Epoch(train) [1][ 200/1567] lr: 9.9984e-02 eta: 4:07:26 time: 0.5418 data_time: 0.0072 memory: 2111 loss: 2.0902 top1_acc: 0.4375 top5_acc: 0.8750 loss_cls: 2.0902 2022/12/22 11:11:01 - mmengine - INFO - Epoch(train) [1][ 300/1567] lr: 9.9965e-02 eta: 3:59:03 time: 0.5408 data_time: 0.0074 memory: 2111 loss: 1.7052 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 1.7052 2022/12/22 11:11:56 - mmengine - INFO - Epoch(train) [1][ 400/1567] lr: 9.9938e-02 eta: 3:54:55 time: 0.5463 data_time: 0.0070 memory: 2111 loss: 1.2278 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.2278 2022/12/22 11:12:50 - mmengine - INFO - Epoch(train) [1][ 500/1567] lr: 9.9902e-02 eta: 3:51:59 time: 0.5446 data_time: 0.0074 memory: 2111 loss: 1.2388 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 1.2388 2022/12/22 11:13:44 - mmengine - INFO - Epoch(train) [1][ 600/1567] lr: 9.9859e-02 eta: 3:49:24 time: 0.5425 data_time: 0.0069 memory: 2111 loss: 1.1590 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 1.1590 2022/12/22 11:14:39 - mmengine - INFO - Epoch(train) [1][ 700/1567] lr: 9.9808e-02 eta: 3:47:33 time: 0.5489 data_time: 0.0071 memory: 2111 loss: 1.0401 top1_acc: 0.8750 top5_acc: 0.8750 loss_cls: 1.0401 2022/12/22 11:15:34 - mmengine - INFO - Epoch(train) [1][ 800/1567] lr: 9.9750e-02 eta: 3:45:54 time: 0.5448 data_time: 0.0073 memory: 2111 loss: 0.9556 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.9556 2022/12/22 11:16:28 - mmengine - INFO - Epoch(train) [1][ 900/1567] lr: 9.9683e-02 eta: 3:44:18 time: 0.5418 data_time: 0.0071 memory: 2111 loss: 0.8908 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 0.8908 2022/12/22 11:17:23 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 11:17:23 - mmengine - INFO - Epoch(train) [1][1000/1567] lr: 9.9609e-02 eta: 3:42:53 time: 0.5410 data_time: 0.0069 memory: 2111 loss: 0.7665 top1_acc: 0.6250 top5_acc: 1.0000 loss_cls: 0.7665 2022/12/22 11:18:17 - mmengine - INFO - Epoch(train) [1][1100/1567] lr: 9.9527e-02 eta: 3:41:39 time: 0.5446 data_time: 0.0068 memory: 2111 loss: 0.9420 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.9420 2022/12/22 11:19:12 - mmengine - INFO - Epoch(train) [1][1200/1567] lr: 9.9437e-02 eta: 3:40:27 time: 0.5516 data_time: 0.0073 memory: 2111 loss: 0.7532 top1_acc: 0.5000 top5_acc: 0.9375 loss_cls: 0.7532 2022/12/22 11:20:06 - mmengine - INFO - Epoch(train) [1][1300/1567] lr: 9.9339e-02 eta: 3:39:16 time: 0.5466 data_time: 0.0069 memory: 2111 loss: 0.7595 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 0.7595 2022/12/22 11:21:01 - mmengine - INFO - Epoch(train) [1][1400/1567] lr: 9.9234e-02 eta: 3:38:03 time: 0.5383 data_time: 0.0075 memory: 2111 loss: 0.7287 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.7287 2022/12/22 11:21:55 - mmengine - INFO - Epoch(train) [1][1500/1567] lr: 9.9121e-02 eta: 3:36:47 time: 0.5248 data_time: 0.0091 memory: 2111 loss: 0.7344 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.7344 2022/12/22 11:22:29 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 11:22:29 - mmengine - INFO - Epoch(train) [1][1567/1567] lr: 9.9040e-02 eta: 3:35:32 time: 0.4449 data_time: 0.0082 memory: 2111 loss: 0.8820 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.8820 2022/12/22 11:22:29 - mmengine - INFO - Saving checkpoint at 1 epochs 2022/12/22 11:22:49 - mmengine - INFO - Epoch(val) [1][100/129] eta: 0:00:05 time: 0.2108 data_time: 0.0069 memory: 293 2022/12/22 11:22:57 - mmengine - INFO - Epoch(val) [1][129/129] acc/top1: 0.6477 acc/top5: 0.9159 acc/mean1: 0.6476 2022/12/22 11:22:58 - mmengine - INFO - The best checkpoint with 0.6477 acc/top1 at 1 epoch is saved to best_acc/top1_epoch_1.pth. 2022/12/22 11:23:52 - mmengine - INFO - Epoch(train) [2][ 100/1567] lr: 9.8914e-02 eta: 3:34:32 time: 0.5448 data_time: 0.0069 memory: 2111 loss: 0.6922 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.6922 2022/12/22 11:24:47 - mmengine - INFO - Epoch(train) [2][ 200/1567] lr: 9.8781e-02 eta: 3:33:31 time: 0.5409 data_time: 0.0073 memory: 2111 loss: 0.6030 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.6030 2022/12/22 11:25:41 - mmengine - INFO - Epoch(train) [2][ 300/1567] lr: 9.8639e-02 eta: 3:32:28 time: 0.5490 data_time: 0.0069 memory: 2111 loss: 0.7976 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.7976 2022/12/22 11:26:36 - mmengine - INFO - Epoch(train) [2][ 400/1567] lr: 9.8491e-02 eta: 3:31:26 time: 0.5441 data_time: 0.0070 memory: 2111 loss: 0.6187 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 0.6187 2022/12/22 11:26:54 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 11:27:30 - mmengine - INFO - Epoch(train) [2][ 500/1567] lr: 9.8334e-02 eta: 3:30:27 time: 0.5433 data_time: 0.0068 memory: 2111 loss: 0.5500 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.5500 2022/12/22 11:28:25 - mmengine - INFO - Epoch(train) [2][ 600/1567] lr: 9.8170e-02 eta: 3:29:29 time: 0.5461 data_time: 0.0076 memory: 2111 loss: 0.6012 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.6012 2022/12/22 11:29:19 - mmengine - INFO - Epoch(train) [2][ 700/1567] lr: 9.7998e-02 eta: 3:28:31 time: 0.5430 data_time: 0.0069 memory: 2111 loss: 0.5730 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.5730 2022/12/22 11:30:14 - mmengine - INFO - Epoch(train) [2][ 800/1567] lr: 9.7819e-02 eta: 3:27:32 time: 0.5426 data_time: 0.0072 memory: 2111 loss: 0.6304 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.6304 2022/12/22 11:31:08 - mmengine - INFO - Epoch(train) [2][ 900/1567] lr: 9.7632e-02 eta: 3:26:33 time: 0.5475 data_time: 0.0070 memory: 2111 loss: 0.5631 top1_acc: 0.5000 top5_acc: 1.0000 loss_cls: 0.5631 2022/12/22 11:32:03 - mmengine - INFO - Epoch(train) [2][1000/1567] lr: 9.7438e-02 eta: 3:25:37 time: 0.5469 data_time: 0.0073 memory: 2111 loss: 0.5519 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.5519 2022/12/22 11:32:57 - mmengine - INFO - Epoch(train) [2][1100/1567] lr: 9.7236e-02 eta: 3:24:39 time: 0.5480 data_time: 0.0070 memory: 2111 loss: 0.5422 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.5422 2022/12/22 11:33:52 - mmengine - INFO - Epoch(train) [2][1200/1567] lr: 9.7027e-02 eta: 3:23:43 time: 0.5503 data_time: 0.0072 memory: 2111 loss: 0.5683 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.5683 2022/12/22 11:34:46 - mmengine - INFO - Epoch(train) [2][1300/1567] lr: 9.6810e-02 eta: 3:22:45 time: 0.5458 data_time: 0.0073 memory: 2111 loss: 0.5852 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.5852 2022/12/22 11:35:41 - mmengine - INFO - Epoch(train) [2][1400/1567] lr: 9.6587e-02 eta: 3:21:48 time: 0.5470 data_time: 0.0071 memory: 2111 loss: 0.5523 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.5523 2022/12/22 11:35:59 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 11:36:35 - mmengine - INFO - Epoch(train) [2][1500/1567] lr: 9.6355e-02 eta: 3:20:51 time: 0.5443 data_time: 0.0072 memory: 2111 loss: 0.5353 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.5353 2022/12/22 11:37:09 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 11:37:09 - mmengine - INFO - Epoch(train) [2][1567/1567] lr: 9.6196e-02 eta: 3:19:56 time: 0.4237 data_time: 0.0072 memory: 2111 loss: 0.7578 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.7578 2022/12/22 11:37:09 - mmengine - INFO - Saving checkpoint at 2 epochs 2022/12/22 11:37:29 - mmengine - INFO - Epoch(val) [2][100/129] eta: 0:00:05 time: 0.1938 data_time: 0.0068 memory: 293 2022/12/22 11:37:37 - mmengine - INFO - Epoch(val) [2][129/129] acc/top1: 0.7203 acc/top5: 0.9307 acc/mean1: 0.7201 2022/12/22 11:37:37 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_1.pth is removed 2022/12/22 11:37:37 - mmengine - INFO - The best checkpoint with 0.7203 acc/top1 at 2 epoch is saved to best_acc/top1_epoch_2.pth. 2022/12/22 11:38:32 - mmengine - INFO - Epoch(train) [3][ 100/1567] lr: 9.5953e-02 eta: 3:19:00 time: 0.5479 data_time: 0.0071 memory: 2111 loss: 0.5462 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 0.5462 2022/12/22 11:39:27 - mmengine - INFO - Epoch(train) [3][ 200/1567] lr: 9.5703e-02 eta: 3:18:05 time: 0.5491 data_time: 0.0074 memory: 2111 loss: 0.5604 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.5604 2022/12/22 11:40:21 - mmengine - INFO - Epoch(train) [3][ 300/1567] lr: 9.5445e-02 eta: 3:17:08 time: 0.5449 data_time: 0.0073 memory: 2111 loss: 0.4794 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.4794 2022/12/22 11:41:15 - mmengine - INFO - Epoch(train) [3][ 400/1567] lr: 9.5180e-02 eta: 3:16:12 time: 0.5439 data_time: 0.0071 memory: 2111 loss: 0.4322 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.4322 2022/12/22 11:42:10 - mmengine - INFO - Epoch(train) [3][ 500/1567] lr: 9.4908e-02 eta: 3:15:15 time: 0.5377 data_time: 0.0074 memory: 2111 loss: 0.4605 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.4605 2022/12/22 11:43:04 - mmengine - INFO - Epoch(train) [3][ 600/1567] lr: 9.4629e-02 eta: 3:14:19 time: 0.5414 data_time: 0.0071 memory: 2111 loss: 0.4702 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.4702 2022/12/22 11:43:58 - mmengine - INFO - Epoch(train) [3][ 700/1567] lr: 9.4343e-02 eta: 3:13:21 time: 0.5436 data_time: 0.0071 memory: 2111 loss: 0.4667 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.4667 2022/12/22 11:44:53 - mmengine - INFO - Epoch(train) [3][ 800/1567] lr: 9.4050e-02 eta: 3:12:26 time: 0.5501 data_time: 0.0070 memory: 2111 loss: 0.5241 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.5241 2022/12/22 11:45:29 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 11:45:47 - mmengine - INFO - Epoch(train) [3][ 900/1567] lr: 9.3750e-02 eta: 3:11:29 time: 0.5367 data_time: 0.0069 memory: 2111 loss: 0.4779 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.4779 2022/12/22 11:46:41 - mmengine - INFO - Epoch(train) [3][1000/1567] lr: 9.3444e-02 eta: 3:10:34 time: 0.5458 data_time: 0.0069 memory: 2111 loss: 0.4694 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.4694 2022/12/22 11:47:36 - mmengine - INFO - Epoch(train) [3][1100/1567] lr: 9.3130e-02 eta: 3:09:38 time: 0.5417 data_time: 0.0070 memory: 2111 loss: 0.3862 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3862 2022/12/22 11:48:30 - mmengine - INFO - Epoch(train) [3][1200/1567] lr: 9.2810e-02 eta: 3:08:42 time: 0.5441 data_time: 0.0073 memory: 2111 loss: 0.4962 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4962 2022/12/22 11:49:25 - mmengine - INFO - Epoch(train) [3][1300/1567] lr: 9.2483e-02 eta: 3:07:48 time: 0.5457 data_time: 0.0069 memory: 2111 loss: 0.4277 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4277 2022/12/22 11:50:19 - mmengine - INFO - Epoch(train) [3][1400/1567] lr: 9.2149e-02 eta: 3:06:53 time: 0.5492 data_time: 0.0073 memory: 2111 loss: 0.4893 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4893 2022/12/22 11:51:14 - mmengine - INFO - Epoch(train) [3][1500/1567] lr: 9.1809e-02 eta: 3:05:59 time: 0.5481 data_time: 0.0077 memory: 2111 loss: 0.4001 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.4001 2022/12/22 11:51:48 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 11:51:48 - mmengine - INFO - Epoch(train) [3][1567/1567] lr: 9.1577e-02 eta: 3:05:10 time: 0.4120 data_time: 0.0068 memory: 2111 loss: 0.6917 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.6917 2022/12/22 11:51:48 - mmengine - INFO - Saving checkpoint at 3 epochs 2022/12/22 11:52:06 - mmengine - INFO - Epoch(val) [3][100/129] eta: 0:00:05 time: 0.1839 data_time: 0.0092 memory: 293 2022/12/22 11:52:14 - mmengine - INFO - Epoch(val) [3][129/129] acc/top1: 0.7196 acc/top5: 0.9367 acc/mean1: 0.7194 2022/12/22 11:53:09 - mmengine - INFO - Epoch(train) [4][ 100/1567] lr: 9.1226e-02 eta: 3:04:16 time: 0.5400 data_time: 0.0072 memory: 2111 loss: 0.3803 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3803 2022/12/22 11:54:03 - mmengine - INFO - Epoch(train) [4][ 200/1567] lr: 9.0868e-02 eta: 3:03:19 time: 0.5387 data_time: 0.0070 memory: 2111 loss: 0.3413 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 0.3413 2022/12/22 11:54:56 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 11:54:56 - mmengine - INFO - Epoch(train) [4][ 300/1567] lr: 9.0504e-02 eta: 3:02:20 time: 0.5398 data_time: 0.0070 memory: 2111 loss: 0.3994 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.3994 2022/12/22 11:55:50 - mmengine - INFO - Epoch(train) [4][ 400/1567] lr: 9.0133e-02 eta: 3:01:22 time: 0.5392 data_time: 0.0072 memory: 2111 loss: 0.3840 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.3840 2022/12/22 11:56:44 - mmengine - INFO - Epoch(train) [4][ 500/1567] lr: 8.9756e-02 eta: 3:00:25 time: 0.5377 data_time: 0.0070 memory: 2111 loss: 0.4127 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4127 2022/12/22 11:57:38 - mmengine - INFO - Epoch(train) [4][ 600/1567] lr: 8.9373e-02 eta: 2:59:29 time: 0.5359 data_time: 0.0069 memory: 2111 loss: 0.4998 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4998 2022/12/22 11:58:32 - mmengine - INFO - Epoch(train) [4][ 700/1567] lr: 8.8984e-02 eta: 2:58:32 time: 0.5423 data_time: 0.0069 memory: 2111 loss: 0.4160 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.4160 2022/12/22 11:59:25 - mmengine - INFO - Epoch(train) [4][ 800/1567] lr: 8.8589e-02 eta: 2:57:35 time: 0.5367 data_time: 0.0070 memory: 2111 loss: 0.3804 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3804 2022/12/22 12:00:19 - mmengine - INFO - Epoch(train) [4][ 900/1567] lr: 8.8187e-02 eta: 2:56:38 time: 0.5385 data_time: 0.0068 memory: 2111 loss: 0.4558 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4558 2022/12/22 12:01:13 - mmengine - INFO - Epoch(train) [4][1000/1567] lr: 8.7780e-02 eta: 2:55:41 time: 0.5384 data_time: 0.0068 memory: 2111 loss: 0.3634 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.3634 2022/12/22 12:02:06 - mmengine - INFO - Epoch(train) [4][1100/1567] lr: 8.7367e-02 eta: 2:54:43 time: 0.5230 data_time: 0.0069 memory: 2111 loss: 0.3868 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.3868 2022/12/22 12:03:00 - mmengine - INFO - Epoch(train) [4][1200/1567] lr: 8.6947e-02 eta: 2:53:47 time: 0.5437 data_time: 0.0068 memory: 2111 loss: 0.4175 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.4175 2022/12/22 12:03:54 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 12:03:54 - mmengine - INFO - Epoch(train) [4][1300/1567] lr: 8.6522e-02 eta: 2:52:52 time: 0.5411 data_time: 0.0069 memory: 2111 loss: 0.4079 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.4079 2022/12/22 12:04:48 - mmengine - INFO - Epoch(train) [4][1400/1567] lr: 8.6092e-02 eta: 2:51:56 time: 0.5322 data_time: 0.0070 memory: 2111 loss: 0.3860 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.3860 2022/12/22 12:05:42 - mmengine - INFO - Epoch(train) [4][1500/1567] lr: 8.5655e-02 eta: 2:51:01 time: 0.5400 data_time: 0.0070 memory: 2111 loss: 0.3235 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3235 2022/12/22 12:06:15 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 12:06:15 - mmengine - INFO - Epoch(train) [4][1567/1567] lr: 8.5360e-02 eta: 2:50:15 time: 0.4015 data_time: 0.0070 memory: 2111 loss: 0.6199 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.6199 2022/12/22 12:06:15 - mmengine - INFO - Saving checkpoint at 4 epochs 2022/12/22 12:06:35 - mmengine - INFO - Epoch(val) [4][100/129] eta: 0:00:05 time: 0.2010 data_time: 0.0067 memory: 293 2022/12/22 12:06:43 - mmengine - INFO - Epoch(val) [4][129/129] acc/top1: 0.7151 acc/top5: 0.9332 acc/mean1: 0.7151 2022/12/22 12:07:37 - mmengine - INFO - Epoch(train) [5][ 100/1567] lr: 8.4914e-02 eta: 2:49:19 time: 0.5360 data_time: 0.0068 memory: 2111 loss: 0.4616 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.4616 2022/12/22 12:08:31 - mmengine - INFO - Epoch(train) [5][ 200/1567] lr: 8.4463e-02 eta: 2:48:23 time: 0.5399 data_time: 0.0075 memory: 2111 loss: 0.4175 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 0.4175 2022/12/22 12:09:24 - mmengine - INFO - Epoch(train) [5][ 300/1567] lr: 8.4006e-02 eta: 2:47:26 time: 0.5320 data_time: 0.0068 memory: 2111 loss: 0.3891 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.3891 2022/12/22 12:10:18 - mmengine - INFO - Epoch(train) [5][ 400/1567] lr: 8.3544e-02 eta: 2:46:32 time: 0.5397 data_time: 0.0073 memory: 2111 loss: 0.4188 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.4188 2022/12/22 12:11:12 - mmengine - INFO - Epoch(train) [5][ 500/1567] lr: 8.3077e-02 eta: 2:45:37 time: 0.5437 data_time: 0.0072 memory: 2111 loss: 0.3944 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3944 2022/12/22 12:12:06 - mmengine - INFO - Epoch(train) [5][ 600/1567] lr: 8.2605e-02 eta: 2:44:40 time: 0.5236 data_time: 0.0072 memory: 2111 loss: 0.3824 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3824 2022/12/22 12:12:59 - mmengine - INFO - Epoch(train) [5][ 700/1567] lr: 8.2127e-02 eta: 2:43:44 time: 0.5336 data_time: 0.0070 memory: 2111 loss: 0.3430 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3430 2022/12/22 12:13:17 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 12:13:53 - mmengine - INFO - Epoch(train) [5][ 800/1567] lr: 8.1645e-02 eta: 2:42:48 time: 0.5383 data_time: 0.0069 memory: 2111 loss: 0.2528 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2528 2022/12/22 12:14:47 - mmengine - INFO - Epoch(train) [5][ 900/1567] lr: 8.1157e-02 eta: 2:41:53 time: 0.5325 data_time: 0.0072 memory: 2111 loss: 0.3920 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.3920 2022/12/22 12:15:40 - mmengine - INFO - Epoch(train) [5][1000/1567] lr: 8.0665e-02 eta: 2:40:56 time: 0.5256 data_time: 0.0070 memory: 2111 loss: 0.3625 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3625 2022/12/22 12:16:34 - mmengine - INFO - Epoch(train) [5][1100/1567] lr: 8.0167e-02 eta: 2:40:01 time: 0.5416 data_time: 0.0075 memory: 2111 loss: 0.4065 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 0.4065 2022/12/22 12:17:28 - mmengine - INFO - Epoch(train) [5][1200/1567] lr: 7.9665e-02 eta: 2:39:05 time: 0.5180 data_time: 0.0071 memory: 2111 loss: 0.2585 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2585 2022/12/22 12:18:21 - mmengine - INFO - Epoch(train) [5][1300/1567] lr: 7.9159e-02 eta: 2:38:09 time: 0.5380 data_time: 0.0067 memory: 2111 loss: 0.2617 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.2617 2022/12/22 12:19:15 - mmengine - INFO - Epoch(train) [5][1400/1567] lr: 7.8647e-02 eta: 2:37:15 time: 0.5414 data_time: 0.0071 memory: 2111 loss: 0.3791 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.3791 2022/12/22 12:20:09 - mmengine - INFO - Epoch(train) [5][1500/1567] lr: 7.8132e-02 eta: 2:36:19 time: 0.5308 data_time: 0.0072 memory: 2111 loss: 0.3229 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3229 2022/12/22 12:20:42 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 12:20:42 - mmengine - INFO - Epoch(train) [5][1567/1567] lr: 7.7784e-02 eta: 2:35:36 time: 0.4054 data_time: 0.0067 memory: 2111 loss: 0.4913 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.4913 2022/12/22 12:20:42 - mmengine - INFO - Saving checkpoint at 5 epochs 2022/12/22 12:21:02 - mmengine - INFO - Epoch(val) [5][100/129] eta: 0:00:05 time: 0.1919 data_time: 0.0066 memory: 293 2022/12/22 12:21:10 - mmengine - INFO - Epoch(val) [5][129/129] acc/top1: 0.7761 acc/top5: 0.9508 acc/mean1: 0.7761 2022/12/22 12:21:10 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_2.pth is removed 2022/12/22 12:21:10 - mmengine - INFO - The best checkpoint with 0.7761 acc/top1 at 5 epoch is saved to best_acc/top1_epoch_5.pth. 2022/12/22 12:22:04 - mmengine - INFO - Epoch(train) [6][ 100/1567] lr: 7.7261e-02 eta: 2:34:41 time: 0.5408 data_time: 0.0073 memory: 2111 loss: 0.3623 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3623 2022/12/22 12:22:38 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 12:22:57 - mmengine - INFO - Epoch(train) [6][ 200/1567] lr: 7.6733e-02 eta: 2:33:45 time: 0.5446 data_time: 0.0078 memory: 2111 loss: 0.3169 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3169 2022/12/22 12:23:51 - mmengine - INFO - Epoch(train) [6][ 300/1567] lr: 7.6202e-02 eta: 2:32:49 time: 0.5379 data_time: 0.0074 memory: 2111 loss: 0.3260 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3260 2022/12/22 12:24:45 - mmengine - INFO - Epoch(train) [6][ 400/1567] lr: 7.5666e-02 eta: 2:31:55 time: 0.5403 data_time: 0.0071 memory: 2111 loss: 0.3092 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3092 2022/12/22 12:25:38 - mmengine - INFO - Epoch(train) [6][ 500/1567] lr: 7.5126e-02 eta: 2:31:00 time: 0.5373 data_time: 0.0074 memory: 2111 loss: 0.2324 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2324 2022/12/22 12:26:32 - mmengine - INFO - Epoch(train) [6][ 600/1567] lr: 7.4583e-02 eta: 2:30:04 time: 0.5026 data_time: 0.0076 memory: 2111 loss: 0.3191 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.3191 2022/12/22 12:27:25 - mmengine - INFO - Epoch(train) [6][ 700/1567] lr: 7.4035e-02 eta: 2:29:09 time: 0.5399 data_time: 0.0080 memory: 2111 loss: 0.2926 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2926 2022/12/22 12:28:19 - mmengine - INFO - Epoch(train) [6][ 800/1567] lr: 7.3484e-02 eta: 2:28:15 time: 0.5381 data_time: 0.0072 memory: 2111 loss: 0.3104 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3104 2022/12/22 12:29:13 - mmengine - INFO - Epoch(train) [6][ 900/1567] lr: 7.2929e-02 eta: 2:27:20 time: 0.5413 data_time: 0.0073 memory: 2111 loss: 0.2747 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2747 2022/12/22 12:30:07 - mmengine - INFO - Epoch(train) [6][1000/1567] lr: 7.2371e-02 eta: 2:26:25 time: 0.5345 data_time: 0.0072 memory: 2111 loss: 0.3105 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3105 2022/12/22 12:31:01 - mmengine - INFO - Epoch(train) [6][1100/1567] lr: 7.1809e-02 eta: 2:25:31 time: 0.5385 data_time: 0.0071 memory: 2111 loss: 0.2744 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2744 2022/12/22 12:31:36 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 12:31:55 - mmengine - INFO - Epoch(train) [6][1200/1567] lr: 7.1243e-02 eta: 2:24:36 time: 0.5393 data_time: 0.0076 memory: 2111 loss: 0.3377 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3377 2022/12/22 12:32:49 - mmengine - INFO - Epoch(train) [6][1300/1567] lr: 7.0674e-02 eta: 2:23:42 time: 0.5357 data_time: 0.0072 memory: 2111 loss: 0.2910 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2910 2022/12/22 12:33:42 - mmengine - INFO - Epoch(train) [6][1400/1567] lr: 7.0102e-02 eta: 2:22:47 time: 0.5438 data_time: 0.0072 memory: 2111 loss: 0.3028 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3028 2022/12/22 12:34:36 - mmengine - INFO - Epoch(train) [6][1500/1567] lr: 6.9527e-02 eta: 2:21:52 time: 0.5301 data_time: 0.0074 memory: 2111 loss: 0.3001 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3001 2022/12/22 12:35:09 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 12:35:09 - mmengine - INFO - Epoch(train) [6][1567/1567] lr: 6.9140e-02 eta: 2:21:10 time: 0.4005 data_time: 0.0075 memory: 2111 loss: 0.3508 top1_acc: 0.0000 top5_acc: 1.0000 loss_cls: 0.3508 2022/12/22 12:35:09 - mmengine - INFO - Saving checkpoint at 6 epochs 2022/12/22 12:35:29 - mmengine - INFO - Epoch(val) [6][100/129] eta: 0:00:05 time: 0.2249 data_time: 0.0067 memory: 293 2022/12/22 12:35:37 - mmengine - INFO - Epoch(val) [6][129/129] acc/top1: 0.7900 acc/top5: 0.9540 acc/mean1: 0.7899 2022/12/22 12:35:37 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_5.pth is removed 2022/12/22 12:35:37 - mmengine - INFO - The best checkpoint with 0.7900 acc/top1 at 6 epoch is saved to best_acc/top1_epoch_6.pth. 2022/12/22 12:36:31 - mmengine - INFO - Epoch(train) [7][ 100/1567] lr: 6.8560e-02 eta: 2:20:15 time: 0.5246 data_time: 0.0079 memory: 2111 loss: 0.2236 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 0.2236 2022/12/22 12:37:25 - mmengine - INFO - Epoch(train) [7][ 200/1567] lr: 6.7976e-02 eta: 2:19:20 time: 0.5294 data_time: 0.0076 memory: 2111 loss: 0.2021 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2021 2022/12/22 12:38:18 - mmengine - INFO - Epoch(train) [7][ 300/1567] lr: 6.7390e-02 eta: 2:18:25 time: 0.5297 data_time: 0.0074 memory: 2111 loss: 0.2372 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2372 2022/12/22 12:39:12 - mmengine - INFO - Epoch(train) [7][ 400/1567] lr: 6.6802e-02 eta: 2:17:31 time: 0.5288 data_time: 0.0074 memory: 2111 loss: 0.3425 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.3425 2022/12/22 12:40:06 - mmengine - INFO - Epoch(train) [7][ 500/1567] lr: 6.6210e-02 eta: 2:16:37 time: 0.5427 data_time: 0.0073 memory: 2111 loss: 0.2593 top1_acc: 0.8750 top5_acc: 0.8750 loss_cls: 0.2593 2022/12/22 12:40:59 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 12:41:00 - mmengine - INFO - Epoch(train) [7][ 600/1567] lr: 6.5616e-02 eta: 2:15:43 time: 0.5465 data_time: 0.0071 memory: 2111 loss: 0.2294 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2294 2022/12/22 12:41:54 - mmengine - INFO - Epoch(train) [7][ 700/1567] lr: 6.5020e-02 eta: 2:14:49 time: 0.5427 data_time: 0.0082 memory: 2111 loss: 0.2335 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2335 2022/12/22 12:42:48 - mmengine - INFO - Epoch(train) [7][ 800/1567] lr: 6.4421e-02 eta: 2:13:55 time: 0.5419 data_time: 0.0074 memory: 2111 loss: 0.2142 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2142 2022/12/22 12:43:42 - mmengine - INFO - Epoch(train) [7][ 900/1567] lr: 6.3820e-02 eta: 2:13:00 time: 0.5279 data_time: 0.0075 memory: 2111 loss: 0.2490 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2490 2022/12/22 12:44:36 - mmengine - INFO - Epoch(train) [7][1000/1567] lr: 6.3217e-02 eta: 2:12:06 time: 0.5366 data_time: 0.0076 memory: 2111 loss: 0.3153 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3153 2022/12/22 12:45:30 - mmengine - INFO - Epoch(train) [7][1100/1567] lr: 6.2612e-02 eta: 2:11:12 time: 0.5419 data_time: 0.0071 memory: 2111 loss: 0.2979 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2979 2022/12/22 12:46:24 - mmengine - INFO - Epoch(train) [7][1200/1567] lr: 6.2005e-02 eta: 2:10:18 time: 0.5442 data_time: 0.0072 memory: 2111 loss: 0.2505 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2505 2022/12/22 12:47:17 - mmengine - INFO - Epoch(train) [7][1300/1567] lr: 6.1396e-02 eta: 2:09:23 time: 0.5285 data_time: 0.0078 memory: 2111 loss: 0.2308 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2308 2022/12/22 12:48:11 - mmengine - INFO - Epoch(train) [7][1400/1567] lr: 6.0785e-02 eta: 2:08:29 time: 0.5412 data_time: 0.0070 memory: 2111 loss: 0.1960 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1960 2022/12/22 12:49:05 - mmengine - INFO - Epoch(train) [7][1500/1567] lr: 6.0172e-02 eta: 2:07:35 time: 0.5459 data_time: 0.0072 memory: 2111 loss: 0.2449 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 0.2449 2022/12/22 12:49:37 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 12:49:37 - mmengine - INFO - Epoch(train) [7][1567/1567] lr: 5.9761e-02 eta: 2:06:54 time: 0.3824 data_time: 0.0075 memory: 2111 loss: 0.3987 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.3987 2022/12/22 12:49:37 - mmengine - INFO - Saving checkpoint at 7 epochs 2022/12/22 12:49:58 - mmengine - INFO - Epoch(val) [7][100/129] eta: 0:00:05 time: 0.2407 data_time: 0.0069 memory: 293 2022/12/22 12:50:06 - mmengine - INFO - Epoch(val) [7][129/129] acc/top1: 0.7949 acc/top5: 0.9544 acc/mean1: 0.7947 2022/12/22 12:50:06 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_6.pth is removed 2022/12/22 12:50:06 - mmengine - INFO - The best checkpoint with 0.7949 acc/top1 at 7 epoch is saved to best_acc/top1_epoch_7.pth. 2022/12/22 12:50:23 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 12:51:00 - mmengine - INFO - Epoch(train) [8][ 100/1567] lr: 5.9145e-02 eta: 2:05:59 time: 0.5371 data_time: 0.0072 memory: 2111 loss: 0.1599 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1599 2022/12/22 12:51:53 - mmengine - INFO - Epoch(train) [8][ 200/1567] lr: 5.8529e-02 eta: 2:05:05 time: 0.5374 data_time: 0.0071 memory: 2111 loss: 0.2098 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2098 2022/12/22 12:52:47 - mmengine - INFO - Epoch(train) [8][ 300/1567] lr: 5.7911e-02 eta: 2:04:10 time: 0.5059 data_time: 0.0089 memory: 2111 loss: 0.2174 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2174 2022/12/22 12:53:40 - mmengine - INFO - Epoch(train) [8][ 400/1567] lr: 5.7292e-02 eta: 2:03:15 time: 0.5335 data_time: 0.0073 memory: 2111 loss: 0.1323 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1323 2022/12/22 12:54:34 - mmengine - INFO - Epoch(train) [8][ 500/1567] lr: 5.6671e-02 eta: 2:02:21 time: 0.5431 data_time: 0.0078 memory: 2111 loss: 0.1487 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1487 2022/12/22 12:55:28 - mmengine - INFO - Epoch(train) [8][ 600/1567] lr: 5.6050e-02 eta: 2:01:27 time: 0.5447 data_time: 0.0080 memory: 2111 loss: 0.2075 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2075 2022/12/22 12:56:22 - mmengine - INFO - Epoch(train) [8][ 700/1567] lr: 5.5427e-02 eta: 2:00:33 time: 0.5396 data_time: 0.0071 memory: 2111 loss: 0.2106 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2106 2022/12/22 12:57:16 - mmengine - INFO - Epoch(train) [8][ 800/1567] lr: 5.4804e-02 eta: 1:59:39 time: 0.5416 data_time: 0.0072 memory: 2111 loss: 0.2196 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2196 2022/12/22 12:58:10 - mmengine - INFO - Epoch(train) [8][ 900/1567] lr: 5.4180e-02 eta: 1:58:45 time: 0.5372 data_time: 0.0077 memory: 2111 loss: 0.2261 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2261 2022/12/22 12:59:04 - mmengine - INFO - Epoch(train) [8][1000/1567] lr: 5.3556e-02 eta: 1:57:51 time: 0.5381 data_time: 0.0072 memory: 2111 loss: 0.1915 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1915 2022/12/22 12:59:20 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 12:59:57 - mmengine - INFO - Epoch(train) [8][1100/1567] lr: 5.2930e-02 eta: 1:56:57 time: 0.5380 data_time: 0.0082 memory: 2111 loss: 0.1355 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1355 2022/12/22 13:00:51 - mmengine - INFO - Epoch(train) [8][1200/1567] lr: 5.2305e-02 eta: 1:56:03 time: 0.5413 data_time: 0.0075 memory: 2111 loss: 0.2017 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2017 2022/12/22 13:01:45 - mmengine - INFO - Epoch(train) [8][1300/1567] lr: 5.1679e-02 eta: 1:55:08 time: 0.5386 data_time: 0.0080 memory: 2111 loss: 0.1905 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.1905 2022/12/22 13:02:39 - mmengine - INFO - Epoch(train) [8][1400/1567] lr: 5.1052e-02 eta: 1:54:14 time: 0.5395 data_time: 0.0075 memory: 2111 loss: 0.1400 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1400 2022/12/22 13:03:33 - mmengine - INFO - Epoch(train) [8][1500/1567] lr: 5.0426e-02 eta: 1:53:20 time: 0.5373 data_time: 0.0071 memory: 2111 loss: 0.2077 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2077 2022/12/22 13:04:04 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 13:04:04 - mmengine - INFO - Epoch(train) [8][1567/1567] lr: 5.0006e-02 eta: 1:52:39 time: 0.3982 data_time: 0.0073 memory: 2111 loss: 0.2805 top1_acc: 0.0000 top5_acc: 1.0000 loss_cls: 0.2805 2022/12/22 13:04:04 - mmengine - INFO - Saving checkpoint at 8 epochs 2022/12/22 13:04:25 - mmengine - INFO - Epoch(val) [8][100/129] eta: 0:00:05 time: 0.2396 data_time: 0.0070 memory: 293 2022/12/22 13:04:33 - mmengine - INFO - Epoch(val) [8][129/129] acc/top1: 0.7738 acc/top5: 0.9396 acc/mean1: 0.7737 2022/12/22 13:05:27 - mmengine - INFO - Epoch(train) [9][ 100/1567] lr: 4.9380e-02 eta: 1:51:45 time: 0.5347 data_time: 0.0073 memory: 2111 loss: 0.1526 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.1526 2022/12/22 13:06:21 - mmengine - INFO - Epoch(train) [9][ 200/1567] lr: 4.8753e-02 eta: 1:50:52 time: 0.5390 data_time: 0.0073 memory: 2111 loss: 0.1555 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1555 2022/12/22 13:07:15 - mmengine - INFO - Epoch(train) [9][ 300/1567] lr: 4.8127e-02 eta: 1:49:58 time: 0.5281 data_time: 0.0074 memory: 2111 loss: 0.2100 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2100 2022/12/22 13:08:09 - mmengine - INFO - Epoch(train) [9][ 400/1567] lr: 4.7501e-02 eta: 1:49:03 time: 0.5429 data_time: 0.0072 memory: 2111 loss: 0.1671 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1671 2022/12/22 13:08:44 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 13:09:03 - mmengine - INFO - Epoch(train) [9][ 500/1567] lr: 4.6876e-02 eta: 1:48:10 time: 0.5389 data_time: 0.0072 memory: 2111 loss: 0.1687 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.1687 2022/12/22 13:09:57 - mmengine - INFO - Epoch(train) [9][ 600/1567] lr: 4.6251e-02 eta: 1:47:16 time: 0.5445 data_time: 0.0073 memory: 2111 loss: 0.1509 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1509 2022/12/22 13:10:51 - mmengine - INFO - Epoch(train) [9][ 700/1567] lr: 4.5626e-02 eta: 1:46:22 time: 0.5413 data_time: 0.0073 memory: 2111 loss: 0.2145 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2145 2022/12/22 13:11:45 - mmengine - INFO - Epoch(train) [9][ 800/1567] lr: 4.5003e-02 eta: 1:45:28 time: 0.5476 data_time: 0.0073 memory: 2111 loss: 0.1816 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.1816 2022/12/22 13:12:39 - mmengine - INFO - Epoch(train) [9][ 900/1567] lr: 4.4380e-02 eta: 1:44:35 time: 0.5347 data_time: 0.0077 memory: 2111 loss: 0.1010 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1010 2022/12/22 13:13:33 - mmengine - INFO - Epoch(train) [9][1000/1567] lr: 4.3757e-02 eta: 1:43:41 time: 0.5408 data_time: 0.0072 memory: 2111 loss: 0.1327 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1327 2022/12/22 13:14:27 - mmengine - INFO - Epoch(train) [9][1100/1567] lr: 4.3136e-02 eta: 1:42:47 time: 0.5387 data_time: 0.0076 memory: 2111 loss: 0.1216 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1216 2022/12/22 13:15:22 - mmengine - INFO - Epoch(train) [9][1200/1567] lr: 4.2516e-02 eta: 1:41:53 time: 0.5427 data_time: 0.0080 memory: 2111 loss: 0.1729 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1729 2022/12/22 13:16:16 - mmengine - INFO - Epoch(train) [9][1300/1567] lr: 4.1897e-02 eta: 1:41:00 time: 0.5401 data_time: 0.0075 memory: 2111 loss: 0.1682 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1682 2022/12/22 13:17:10 - mmengine - INFO - Epoch(train) [9][1400/1567] lr: 4.1280e-02 eta: 1:40:06 time: 0.5392 data_time: 0.0073 memory: 2111 loss: 0.1587 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1587 2022/12/22 13:17:45 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 13:18:04 - mmengine - INFO - Epoch(train) [9][1500/1567] lr: 4.0664e-02 eta: 1:39:12 time: 0.5434 data_time: 0.0071 memory: 2111 loss: 0.1502 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1502 2022/12/22 13:18:36 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 13:18:36 - mmengine - INFO - Epoch(train) [9][1567/1567] lr: 4.0252e-02 eta: 1:38:33 time: 0.4084 data_time: 0.0076 memory: 2111 loss: 0.3101 top1_acc: 0.0000 top5_acc: 1.0000 loss_cls: 0.3101 2022/12/22 13:18:36 - mmengine - INFO - Saving checkpoint at 9 epochs 2022/12/22 13:18:58 - mmengine - INFO - Epoch(val) [9][100/129] eta: 0:00:06 time: 0.2473 data_time: 0.0072 memory: 293 2022/12/22 13:19:06 - mmengine - INFO - Epoch(val) [9][129/129] acc/top1: 0.8185 acc/top5: 0.9607 acc/mean1: 0.8184 2022/12/22 13:19:06 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_7.pth is removed 2022/12/22 13:19:06 - mmengine - INFO - The best checkpoint with 0.8185 acc/top1 at 9 epoch is saved to best_acc/top1_epoch_9.pth. 2022/12/22 13:20:01 - mmengine - INFO - Epoch(train) [10][ 100/1567] lr: 3.9638e-02 eta: 1:37:39 time: 0.5292 data_time: 0.0071 memory: 2111 loss: 0.1119 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1119 2022/12/22 13:20:55 - mmengine - INFO - Epoch(train) [10][ 200/1567] lr: 3.9026e-02 eta: 1:36:45 time: 0.5391 data_time: 0.0074 memory: 2111 loss: 0.0974 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0974 2022/12/22 13:21:49 - mmengine - INFO - Epoch(train) [10][ 300/1567] lr: 3.8415e-02 eta: 1:35:52 time: 0.5379 data_time: 0.0076 memory: 2111 loss: 0.1237 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1237 2022/12/22 13:22:43 - mmengine - INFO - Epoch(train) [10][ 400/1567] lr: 3.7807e-02 eta: 1:34:58 time: 0.5410 data_time: 0.0072 memory: 2111 loss: 0.1445 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1445 2022/12/22 13:23:36 - mmengine - INFO - Epoch(train) [10][ 500/1567] lr: 3.7200e-02 eta: 1:34:04 time: 0.5457 data_time: 0.0074 memory: 2111 loss: 0.1378 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1378 2022/12/22 13:24:31 - mmengine - INFO - Epoch(train) [10][ 600/1567] lr: 3.6596e-02 eta: 1:33:10 time: 0.5416 data_time: 0.0074 memory: 2111 loss: 0.0999 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0999 2022/12/22 13:25:25 - mmengine - INFO - Epoch(train) [10][ 700/1567] lr: 3.5993e-02 eta: 1:32:16 time: 0.5417 data_time: 0.0077 memory: 2111 loss: 0.1363 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1363 2022/12/22 13:26:19 - mmengine - INFO - Epoch(train) [10][ 800/1567] lr: 3.5393e-02 eta: 1:31:22 time: 0.5447 data_time: 0.0073 memory: 2111 loss: 0.1011 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1011 2022/12/22 13:27:12 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 13:27:13 - mmengine - INFO - Epoch(train) [10][ 900/1567] lr: 3.4795e-02 eta: 1:30:29 time: 0.5321 data_time: 0.0074 memory: 2111 loss: 0.1530 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.1530 2022/12/22 13:28:07 - mmengine - INFO - Epoch(train) [10][1000/1567] lr: 3.4199e-02 eta: 1:29:35 time: 0.5467 data_time: 0.0073 memory: 2111 loss: 0.1336 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1336 2022/12/22 13:29:01 - mmengine - INFO - Epoch(train) [10][1100/1567] lr: 3.3606e-02 eta: 1:28:41 time: 0.5320 data_time: 0.0073 memory: 2111 loss: 0.1075 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1075 2022/12/22 13:29:55 - mmengine - INFO - Epoch(train) [10][1200/1567] lr: 3.3015e-02 eta: 1:27:47 time: 0.5247 data_time: 0.0076 memory: 2111 loss: 0.0829 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0829 2022/12/22 13:30:49 - mmengine - INFO - Epoch(train) [10][1300/1567] lr: 3.2428e-02 eta: 1:26:53 time: 0.5463 data_time: 0.0078 memory: 2111 loss: 0.1524 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1524 2022/12/22 13:31:44 - mmengine - INFO - Epoch(train) [10][1400/1567] lr: 3.1842e-02 eta: 1:26:00 time: 0.5475 data_time: 0.0078 memory: 2111 loss: 0.0898 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0898 2022/12/22 13:32:38 - mmengine - INFO - Epoch(train) [10][1500/1567] lr: 3.1260e-02 eta: 1:25:06 time: 0.5378 data_time: 0.0072 memory: 2111 loss: 0.1136 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1136 2022/12/22 13:33:09 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 13:33:09 - mmengine - INFO - Epoch(train) [10][1567/1567] lr: 3.0872e-02 eta: 1:24:27 time: 0.4079 data_time: 0.0077 memory: 2111 loss: 0.2261 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2261 2022/12/22 13:33:09 - mmengine - INFO - Saving checkpoint at 10 epochs 2022/12/22 13:33:31 - mmengine - INFO - Epoch(val) [10][100/129] eta: 0:00:06 time: 0.2456 data_time: 0.0070 memory: 293 2022/12/22 13:33:39 - mmengine - INFO - Epoch(val) [10][129/129] acc/top1: 0.8268 acc/top5: 0.9598 acc/mean1: 0.8267 2022/12/22 13:33:39 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_9.pth is removed 2022/12/22 13:33:40 - mmengine - INFO - The best checkpoint with 0.8268 acc/top1 at 10 epoch is saved to best_acc/top1_epoch_10.pth. 2022/12/22 13:34:34 - mmengine - INFO - Epoch(train) [11][ 100/1567] lr: 3.0294e-02 eta: 1:23:33 time: 0.5424 data_time: 0.0070 memory: 2111 loss: 0.0747 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0747 2022/12/22 13:35:28 - mmengine - INFO - Epoch(train) [11][ 200/1567] lr: 2.9720e-02 eta: 1:22:40 time: 0.5460 data_time: 0.0074 memory: 2111 loss: 0.0779 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0779 2022/12/22 13:36:23 - mmengine - INFO - Epoch(train) [11][ 300/1567] lr: 2.9149e-02 eta: 1:21:46 time: 0.5445 data_time: 0.0070 memory: 2111 loss: 0.0923 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0923 2022/12/22 13:36:39 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 13:37:17 - mmengine - INFO - Epoch(train) [11][ 400/1567] lr: 2.8581e-02 eta: 1:20:52 time: 0.5404 data_time: 0.0075 memory: 2111 loss: 0.0795 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0795 2022/12/22 13:38:11 - mmengine - INFO - Epoch(train) [11][ 500/1567] lr: 2.8017e-02 eta: 1:19:58 time: 0.5408 data_time: 0.0071 memory: 2111 loss: 0.1134 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.1134 2022/12/22 13:39:05 - mmengine - INFO - Epoch(train) [11][ 600/1567] lr: 2.7456e-02 eta: 1:19:05 time: 0.5419 data_time: 0.0071 memory: 2111 loss: 0.0561 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0561 2022/12/22 13:39:59 - mmengine - INFO - Epoch(train) [11][ 700/1567] lr: 2.6898e-02 eta: 1:18:11 time: 0.5427 data_time: 0.0073 memory: 2111 loss: 0.0677 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0677 2022/12/22 13:40:54 - mmengine - INFO - Epoch(train) [11][ 800/1567] lr: 2.6345e-02 eta: 1:17:17 time: 0.5351 data_time: 0.0072 memory: 2111 loss: 0.0618 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0618 2022/12/22 13:41:48 - mmengine - INFO - Epoch(train) [11][ 900/1567] lr: 2.5794e-02 eta: 1:16:23 time: 0.5406 data_time: 0.0070 memory: 2111 loss: 0.0822 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0822 2022/12/22 13:42:42 - mmengine - INFO - Epoch(train) [11][1000/1567] lr: 2.5248e-02 eta: 1:15:30 time: 0.5430 data_time: 0.0070 memory: 2111 loss: 0.0560 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0560 2022/12/22 13:43:36 - mmengine - INFO - Epoch(train) [11][1100/1567] lr: 2.4706e-02 eta: 1:14:36 time: 0.5401 data_time: 0.0070 memory: 2111 loss: 0.0659 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0659 2022/12/22 13:44:31 - mmengine - INFO - Epoch(train) [11][1200/1567] lr: 2.4167e-02 eta: 1:13:42 time: 0.5423 data_time: 0.0069 memory: 2111 loss: 0.0528 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0528 2022/12/22 13:45:24 - mmengine - INFO - Epoch(train) [11][1300/1567] lr: 2.3633e-02 eta: 1:12:48 time: 0.5390 data_time: 0.0070 memory: 2111 loss: 0.0644 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0644 2022/12/22 13:45:41 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 13:46:18 - mmengine - INFO - Epoch(train) [11][1400/1567] lr: 2.3103e-02 eta: 1:11:54 time: 0.5479 data_time: 0.0074 memory: 2111 loss: 0.0504 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0504 2022/12/22 13:47:13 - mmengine - INFO - Epoch(train) [11][1500/1567] lr: 2.2577e-02 eta: 1:11:01 time: 0.5345 data_time: 0.0069 memory: 2111 loss: 0.0738 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0738 2022/12/22 13:47:44 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 13:47:44 - mmengine - INFO - Epoch(train) [11][1567/1567] lr: 2.2227e-02 eta: 1:10:22 time: 0.4117 data_time: 0.0068 memory: 2111 loss: 0.2685 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.2685 2022/12/22 13:47:44 - mmengine - INFO - Saving checkpoint at 11 epochs 2022/12/22 13:48:06 - mmengine - INFO - Epoch(val) [11][100/129] eta: 0:00:06 time: 0.2475 data_time: 0.0069 memory: 293 2022/12/22 13:48:14 - mmengine - INFO - Epoch(val) [11][129/129] acc/top1: 0.8406 acc/top5: 0.9650 acc/mean1: 0.8405 2022/12/22 13:48:14 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_10.pth is removed 2022/12/22 13:48:14 - mmengine - INFO - The best checkpoint with 0.8406 acc/top1 at 11 epoch is saved to best_acc/top1_epoch_11.pth. 2022/12/22 13:49:09 - mmengine - INFO - Epoch(train) [12][ 100/1567] lr: 2.1708e-02 eta: 1:09:28 time: 0.5343 data_time: 0.0068 memory: 2111 loss: 0.0803 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0803 2022/12/22 13:50:03 - mmengine - INFO - Epoch(train) [12][ 200/1567] lr: 2.1194e-02 eta: 1:08:35 time: 0.5366 data_time: 0.0071 memory: 2111 loss: 0.0448 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0448 2022/12/22 13:50:57 - mmengine - INFO - Epoch(train) [12][ 300/1567] lr: 2.0684e-02 eta: 1:07:41 time: 0.5465 data_time: 0.0072 memory: 2111 loss: 0.0334 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0334 2022/12/22 13:51:51 - mmengine - INFO - Epoch(train) [12][ 400/1567] lr: 2.0179e-02 eta: 1:06:47 time: 0.5430 data_time: 0.0070 memory: 2111 loss: 0.0856 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0856 2022/12/22 13:52:46 - mmengine - INFO - Epoch(train) [12][ 500/1567] lr: 1.9678e-02 eta: 1:05:53 time: 0.5453 data_time: 0.0069 memory: 2111 loss: 0.0493 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0493 2022/12/22 13:53:39 - mmengine - INFO - Epoch(train) [12][ 600/1567] lr: 1.9182e-02 eta: 1:04:59 time: 0.5387 data_time: 0.0071 memory: 2111 loss: 0.0343 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0343 2022/12/22 13:54:34 - mmengine - INFO - Epoch(train) [12][ 700/1567] lr: 1.8691e-02 eta: 1:04:06 time: 0.5435 data_time: 0.0069 memory: 2111 loss: 0.0376 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0376 2022/12/22 13:55:08 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 13:55:28 - mmengine - INFO - Epoch(train) [12][ 800/1567] lr: 1.8205e-02 eta: 1:03:12 time: 0.5371 data_time: 0.0069 memory: 2111 loss: 0.0573 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0573 2022/12/22 13:56:22 - mmengine - INFO - Epoch(train) [12][ 900/1567] lr: 1.7724e-02 eta: 1:02:18 time: 0.5396 data_time: 0.0069 memory: 2111 loss: 0.0484 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0484 2022/12/22 13:57:16 - mmengine - INFO - Epoch(train) [12][1000/1567] lr: 1.7248e-02 eta: 1:01:24 time: 0.5368 data_time: 0.0071 memory: 2111 loss: 0.0301 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0301 2022/12/22 13:58:10 - mmengine - INFO - Epoch(train) [12][1100/1567] lr: 1.6778e-02 eta: 1:00:30 time: 0.5400 data_time: 0.0072 memory: 2111 loss: 0.0348 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0348 2022/12/22 13:59:04 - mmengine - INFO - Epoch(train) [12][1200/1567] lr: 1.6312e-02 eta: 0:59:37 time: 0.5419 data_time: 0.0069 memory: 2111 loss: 0.0413 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0413 2022/12/22 13:59:58 - mmengine - INFO - Epoch(train) [12][1300/1567] lr: 1.5852e-02 eta: 0:58:43 time: 0.5411 data_time: 0.0072 memory: 2111 loss: 0.0419 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0419 2022/12/22 14:00:53 - mmengine - INFO - Epoch(train) [12][1400/1567] lr: 1.5397e-02 eta: 0:57:49 time: 0.5430 data_time: 0.0072 memory: 2111 loss: 0.0233 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0233 2022/12/22 14:01:47 - mmengine - INFO - Epoch(train) [12][1500/1567] lr: 1.4947e-02 eta: 0:56:55 time: 0.5440 data_time: 0.0071 memory: 2111 loss: 0.0202 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0202 2022/12/22 14:02:18 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 14:02:18 - mmengine - INFO - Epoch(train) [12][1567/1567] lr: 1.4649e-02 eta: 0:56:17 time: 0.4155 data_time: 0.0069 memory: 2111 loss: 0.2303 top1_acc: 0.0000 top5_acc: 0.0000 loss_cls: 0.2303 2022/12/22 14:02:18 - mmengine - INFO - Saving checkpoint at 12 epochs 2022/12/22 14:02:40 - mmengine - INFO - Epoch(val) [12][100/129] eta: 0:00:06 time: 0.2433 data_time: 0.0064 memory: 293 2022/12/22 14:02:48 - mmengine - INFO - Epoch(val) [12][129/129] acc/top1: 0.8462 acc/top5: 0.9637 acc/mean1: 0.8462 2022/12/22 14:02:48 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_11.pth is removed 2022/12/22 14:02:48 - mmengine - INFO - The best checkpoint with 0.8462 acc/top1 at 12 epoch is saved to best_acc/top1_epoch_12.pth. 2022/12/22 14:03:43 - mmengine - INFO - Epoch(train) [13][ 100/1567] lr: 1.4209e-02 eta: 0:55:23 time: 0.5409 data_time: 0.0067 memory: 2111 loss: 0.0256 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0256 2022/12/22 14:04:35 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 14:04:37 - mmengine - INFO - Epoch(train) [13][ 200/1567] lr: 1.3774e-02 eta: 0:54:30 time: 0.5465 data_time: 0.0070 memory: 2111 loss: 0.0284 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0284 2022/12/22 14:05:31 - mmengine - INFO - Epoch(train) [13][ 300/1567] lr: 1.3345e-02 eta: 0:53:36 time: 0.5439 data_time: 0.0069 memory: 2111 loss: 0.0459 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0459 2022/12/22 14:06:25 - mmengine - INFO - Epoch(train) [13][ 400/1567] lr: 1.2922e-02 eta: 0:52:42 time: 0.5367 data_time: 0.0069 memory: 2111 loss: 0.0238 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0238 2022/12/22 14:07:19 - mmengine - INFO - Epoch(train) [13][ 500/1567] lr: 1.2505e-02 eta: 0:51:48 time: 0.5443 data_time: 0.0071 memory: 2111 loss: 0.0294 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0294 2022/12/22 14:08:13 - mmengine - INFO - Epoch(train) [13][ 600/1567] lr: 1.2093e-02 eta: 0:50:54 time: 0.5465 data_time: 0.0068 memory: 2111 loss: 0.0116 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0116 2022/12/22 14:09:08 - mmengine - INFO - Epoch(train) [13][ 700/1567] lr: 1.1687e-02 eta: 0:50:01 time: 0.5441 data_time: 0.0072 memory: 2111 loss: 0.0249 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0249 2022/12/22 14:10:02 - mmengine - INFO - Epoch(train) [13][ 800/1567] lr: 1.1288e-02 eta: 0:49:07 time: 0.5461 data_time: 0.0069 memory: 2111 loss: 0.0166 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0166 2022/12/22 14:10:56 - mmengine - INFO - Epoch(train) [13][ 900/1567] lr: 1.0894e-02 eta: 0:48:13 time: 0.5469 data_time: 0.0071 memory: 2111 loss: 0.0161 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0161 2022/12/22 14:11:50 - mmengine - INFO - Epoch(train) [13][1000/1567] lr: 1.0507e-02 eta: 0:47:19 time: 0.5421 data_time: 0.0072 memory: 2111 loss: 0.0262 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0262 2022/12/22 14:12:45 - mmengine - INFO - Epoch(train) [13][1100/1567] lr: 1.0126e-02 eta: 0:46:25 time: 0.5424 data_time: 0.0073 memory: 2111 loss: 0.0262 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0262 2022/12/22 14:13:37 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 14:13:39 - mmengine - INFO - Epoch(train) [13][1200/1567] lr: 9.7512e-03 eta: 0:45:32 time: 0.5450 data_time: 0.0069 memory: 2111 loss: 0.0197 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0197 2022/12/22 14:14:33 - mmengine - INFO - Epoch(train) [13][1300/1567] lr: 9.3826e-03 eta: 0:44:38 time: 0.5435 data_time: 0.0070 memory: 2111 loss: 0.0242 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0242 2022/12/22 14:15:28 - mmengine - INFO - Epoch(train) [13][1400/1567] lr: 9.0204e-03 eta: 0:43:44 time: 0.5483 data_time: 0.0074 memory: 2111 loss: 0.0175 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0175 2022/12/22 14:16:22 - mmengine - INFO - Epoch(train) [13][1500/1567] lr: 8.6647e-03 eta: 0:42:50 time: 0.5433 data_time: 0.0077 memory: 2111 loss: 0.0171 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0171 2022/12/22 14:16:53 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 14:16:53 - mmengine - INFO - Epoch(train) [13][1567/1567] lr: 8.4300e-03 eta: 0:42:13 time: 0.4119 data_time: 0.0068 memory: 2111 loss: 0.2138 top1_acc: 0.0000 top5_acc: 1.0000 loss_cls: 0.2138 2022/12/22 14:16:53 - mmengine - INFO - Saving checkpoint at 13 epochs 2022/12/22 14:17:15 - mmengine - INFO - Epoch(val) [13][100/129] eta: 0:00:06 time: 0.2426 data_time: 0.0066 memory: 293 2022/12/22 14:17:23 - mmengine - INFO - Epoch(val) [13][129/129] acc/top1: 0.8524 acc/top5: 0.9647 acc/mean1: 0.8523 2022/12/22 14:17:23 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_12.pth is removed 2022/12/22 14:17:24 - mmengine - INFO - The best checkpoint with 0.8524 acc/top1 at 13 epoch is saved to best_acc/top1_epoch_13.pth. 2022/12/22 14:18:18 - mmengine - INFO - Epoch(train) [14][ 100/1567] lr: 8.0851e-03 eta: 0:41:19 time: 0.5467 data_time: 0.0070 memory: 2111 loss: 0.0182 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0182 2022/12/22 14:19:12 - mmengine - INFO - Epoch(train) [14][ 200/1567] lr: 7.7469e-03 eta: 0:40:25 time: 0.5457 data_time: 0.0069 memory: 2111 loss: 0.0091 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0091 2022/12/22 14:20:07 - mmengine - INFO - Epoch(train) [14][ 300/1567] lr: 7.4152e-03 eta: 0:39:31 time: 0.5478 data_time: 0.0071 memory: 2111 loss: 0.0124 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0124 2022/12/22 14:21:01 - mmengine - INFO - Epoch(train) [14][ 400/1567] lr: 7.0902e-03 eta: 0:38:38 time: 0.5387 data_time: 0.0069 memory: 2111 loss: 0.0136 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0136 2022/12/22 14:21:55 - mmengine - INFO - Epoch(train) [14][ 500/1567] lr: 6.7720e-03 eta: 0:37:44 time: 0.5422 data_time: 0.0069 memory: 2111 loss: 0.0125 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0125 2022/12/22 14:22:49 - mmengine - INFO - Epoch(train) [14][ 600/1567] lr: 6.4606e-03 eta: 0:36:50 time: 0.5426 data_time: 0.0069 memory: 2111 loss: 0.0101 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0101 2022/12/22 14:23:05 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 14:23:44 - mmengine - INFO - Epoch(train) [14][ 700/1567] lr: 6.1560e-03 eta: 0:35:56 time: 0.5433 data_time: 0.0071 memory: 2111 loss: 0.0144 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0144 2022/12/22 14:24:38 - mmengine - INFO - Epoch(train) [14][ 800/1567] lr: 5.8582e-03 eta: 0:35:02 time: 0.5423 data_time: 0.0071 memory: 2111 loss: 0.0121 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0121 2022/12/22 14:25:32 - mmengine - INFO - Epoch(train) [14][ 900/1567] lr: 5.5675e-03 eta: 0:34:08 time: 0.5407 data_time: 0.0068 memory: 2111 loss: 0.0198 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0198 2022/12/22 14:26:26 - mmengine - INFO - Epoch(train) [14][1000/1567] lr: 5.2836e-03 eta: 0:33:14 time: 0.5437 data_time: 0.0068 memory: 2111 loss: 0.0085 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0085 2022/12/22 14:27:20 - mmengine - INFO - Epoch(train) [14][1100/1567] lr: 5.0068e-03 eta: 0:32:21 time: 0.5341 data_time: 0.0071 memory: 2111 loss: 0.0085 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0085 2022/12/22 14:28:14 - mmengine - INFO - Epoch(train) [14][1200/1567] lr: 4.7371e-03 eta: 0:31:27 time: 0.5413 data_time: 0.0068 memory: 2111 loss: 0.0076 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0076 2022/12/22 14:29:08 - mmengine - INFO - Epoch(train) [14][1300/1567] lr: 4.4745e-03 eta: 0:30:33 time: 0.5323 data_time: 0.0069 memory: 2111 loss: 0.0072 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0072 2022/12/22 14:30:01 - mmengine - INFO - Epoch(train) [14][1400/1567] lr: 4.2190e-03 eta: 0:29:39 time: 0.5380 data_time: 0.0076 memory: 2111 loss: 0.0224 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0224 2022/12/22 14:30:55 - mmengine - INFO - Epoch(train) [14][1500/1567] lr: 3.9707e-03 eta: 0:28:45 time: 0.5341 data_time: 0.0070 memory: 2111 loss: 0.0142 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0142 2022/12/22 14:31:26 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 14:31:26 - mmengine - INFO - Epoch(train) [14][1567/1567] lr: 3.8084e-03 eta: 0:28:08 time: 0.4158 data_time: 0.0067 memory: 2111 loss: 0.1729 top1_acc: 0.0000 top5_acc: 1.0000 loss_cls: 0.1729 2022/12/22 14:31:26 - mmengine - INFO - Saving checkpoint at 14 epochs 2022/12/22 14:31:48 - mmengine - INFO - Epoch(val) [14][100/129] eta: 0:00:06 time: 0.2457 data_time: 0.0066 memory: 293 2022/12/22 14:31:56 - mmengine - INFO - Epoch(val) [14][129/129] acc/top1: 0.8574 acc/top5: 0.9684 acc/mean1: 0.8573 2022/12/22 14:31:56 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_13.pth is removed 2022/12/22 14:31:56 - mmengine - INFO - The best checkpoint with 0.8574 acc/top1 at 14 epoch is saved to best_acc/top1_epoch_14.pth. 2022/12/22 14:32:30 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 14:32:51 - mmengine - INFO - Epoch(train) [15][ 100/1567] lr: 3.5722e-03 eta: 0:27:14 time: 0.5387 data_time: 0.0111 memory: 2111 loss: 0.0115 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0115 2022/12/22 14:33:44 - mmengine - INFO - Epoch(train) [15][ 200/1567] lr: 3.3433e-03 eta: 0:26:20 time: 0.5447 data_time: 0.0088 memory: 2111 loss: 0.0064 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0064 2022/12/22 14:34:39 - mmengine - INFO - Epoch(train) [15][ 300/1567] lr: 3.1217e-03 eta: 0:25:26 time: 0.5428 data_time: 0.0097 memory: 2111 loss: 0.0071 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0071 2022/12/22 14:35:33 - mmengine - INFO - Epoch(train) [15][ 400/1567] lr: 2.9075e-03 eta: 0:24:33 time: 0.5455 data_time: 0.0099 memory: 2111 loss: 0.0097 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0097 2022/12/22 14:36:28 - mmengine - INFO - Epoch(train) [15][ 500/1567] lr: 2.7007e-03 eta: 0:23:39 time: 0.5454 data_time: 0.0089 memory: 2111 loss: 0.0079 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0079 2022/12/22 14:37:22 - mmengine - INFO - Epoch(train) [15][ 600/1567] lr: 2.5013e-03 eta: 0:22:45 time: 0.5320 data_time: 0.0111 memory: 2111 loss: 0.0092 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0092 2022/12/22 14:38:17 - mmengine - INFO - Epoch(train) [15][ 700/1567] lr: 2.3093e-03 eta: 0:21:51 time: 0.5426 data_time: 0.0093 memory: 2111 loss: 0.0079 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0079 2022/12/22 14:39:11 - mmengine - INFO - Epoch(train) [15][ 800/1567] lr: 2.1249e-03 eta: 0:20:57 time: 0.5367 data_time: 0.0107 memory: 2111 loss: 0.0075 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0075 2022/12/22 14:40:06 - mmengine - INFO - Epoch(train) [15][ 900/1567] lr: 1.9479e-03 eta: 0:20:04 time: 0.5518 data_time: 0.0084 memory: 2111 loss: 0.0073 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0073 2022/12/22 14:41:00 - mmengine - INFO - Epoch(train) [15][1000/1567] lr: 1.7785e-03 eta: 0:19:10 time: 0.5414 data_time: 0.0115 memory: 2111 loss: 0.0079 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0079 2022/12/22 14:41:34 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 14:41:54 - mmengine - INFO - Epoch(train) [15][1100/1567] lr: 1.6167e-03 eta: 0:18:16 time: 0.5434 data_time: 0.0093 memory: 2111 loss: 0.0105 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0105 2022/12/22 14:42:49 - mmengine - INFO - Epoch(train) [15][1200/1567] lr: 1.4625e-03 eta: 0:17:22 time: 0.5502 data_time: 0.0113 memory: 2111 loss: 0.0057 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0057 2022/12/22 14:43:43 - mmengine - INFO - Epoch(train) [15][1300/1567] lr: 1.3159e-03 eta: 0:16:28 time: 0.5376 data_time: 0.0093 memory: 2111 loss: 0.0086 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0086 2022/12/22 14:44:37 - mmengine - INFO - Epoch(train) [15][1400/1567] lr: 1.1769e-03 eta: 0:15:34 time: 0.5362 data_time: 0.0090 memory: 2111 loss: 0.0072 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0072 2022/12/22 14:45:32 - mmengine - INFO - Epoch(train) [15][1500/1567] lr: 1.0456e-03 eta: 0:14:40 time: 0.5481 data_time: 0.0100 memory: 2111 loss: 0.0112 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0112 2022/12/22 14:46:03 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 14:46:03 - mmengine - INFO - Epoch(train) [15][1567/1567] lr: 9.6196e-04 eta: 0:14:04 time: 0.4188 data_time: 0.0105 memory: 2111 loss: 0.1786 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1786 2022/12/22 14:46:03 - mmengine - INFO - Saving checkpoint at 15 epochs 2022/12/22 14:46:26 - mmengine - INFO - Epoch(val) [15][100/129] eta: 0:00:06 time: 0.2455 data_time: 0.0075 memory: 293 2022/12/22 14:46:34 - mmengine - INFO - Epoch(val) [15][129/129] acc/top1: 0.8612 acc/top5: 0.9688 acc/mean1: 0.8611 2022/12/22 14:46:34 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/daiwenxun/mmlab/mmaction2/work_dirs/2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d/best_acc/top1_epoch_14.pth is removed 2022/12/22 14:46:34 - mmengine - INFO - The best checkpoint with 0.8612 acc/top1 at 15 epoch is saved to best_acc/top1_epoch_15.pth. 2022/12/22 14:47:29 - mmengine - INFO - Epoch(train) [16][ 100/1567] lr: 8.4351e-04 eta: 0:13:10 time: 0.5406 data_time: 0.0116 memory: 2111 loss: 0.0100 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0100 2022/12/22 14:48:23 - mmengine - INFO - Epoch(train) [16][ 200/1567] lr: 7.3277e-04 eta: 0:12:16 time: 0.5340 data_time: 0.0086 memory: 2111 loss: 0.0141 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0141 2022/12/22 14:49:17 - mmengine - INFO - Epoch(train) [16][ 300/1567] lr: 6.2978e-04 eta: 0:11:22 time: 0.5419 data_time: 0.0112 memory: 2111 loss: 0.0066 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0066 2022/12/22 14:50:12 - mmengine - INFO - Epoch(train) [16][ 400/1567] lr: 5.3453e-04 eta: 0:10:28 time: 0.5445 data_time: 0.0092 memory: 2111 loss: 0.0062 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0062 2022/12/22 14:51:03 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 14:51:06 - mmengine - INFO - Epoch(train) [16][ 500/1567] lr: 4.4705e-04 eta: 0:09:35 time: 0.5494 data_time: 0.0107 memory: 2111 loss: 0.0095 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0095 2022/12/22 14:52:00 - mmengine - INFO - Epoch(train) [16][ 600/1567] lr: 3.6735e-04 eta: 0:08:41 time: 0.5331 data_time: 0.0097 memory: 2111 loss: 0.0062 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0062 2022/12/22 14:52:55 - mmengine - INFO - Epoch(train) [16][ 700/1567] lr: 2.9544e-04 eta: 0:07:47 time: 0.5462 data_time: 0.0105 memory: 2111 loss: 0.0079 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0079 2022/12/22 14:53:49 - mmengine - INFO - Epoch(train) [16][ 800/1567] lr: 2.3134e-04 eta: 0:06:53 time: 0.5306 data_time: 0.0100 memory: 2111 loss: 0.0096 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0096 2022/12/22 14:54:43 - mmengine - INFO - Epoch(train) [16][ 900/1567] lr: 1.7505e-04 eta: 0:05:59 time: 0.5507 data_time: 0.0096 memory: 2111 loss: 0.0067 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0067 2022/12/22 14:55:37 - mmengine - INFO - Epoch(train) [16][1000/1567] lr: 1.2658e-04 eta: 0:05:05 time: 0.5431 data_time: 0.0088 memory: 2111 loss: 0.0087 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0087 2022/12/22 14:56:32 - mmengine - INFO - Epoch(train) [16][1100/1567] lr: 8.5947e-05 eta: 0:04:11 time: 0.5494 data_time: 0.0091 memory: 2111 loss: 0.0057 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0057 2022/12/22 14:57:26 - mmengine - INFO - Epoch(train) [16][1200/1567] lr: 5.3147e-05 eta: 0:03:17 time: 0.5411 data_time: 0.0103 memory: 2111 loss: 0.0083 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0083 2022/12/22 14:58:20 - mmengine - INFO - Epoch(train) [16][1300/1567] lr: 2.8190e-05 eta: 0:02:23 time: 0.5505 data_time: 0.0084 memory: 2111 loss: 0.0068 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0068 2022/12/22 14:59:15 - mmengine - INFO - Epoch(train) [16][1400/1567] lr: 1.1078e-05 eta: 0:01:30 time: 0.5335 data_time: 0.0101 memory: 2111 loss: 0.0068 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0068 2022/12/22 15:00:07 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 15:00:09 - mmengine - INFO - Epoch(train) [16][1500/1567] lr: 1.8150e-06 eta: 0:00:36 time: 0.5516 data_time: 0.0086 memory: 2111 loss: 0.0063 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0063 2022/12/22 15:00:40 - mmengine - INFO - Exp name: 2s-agcn_8xb16-joint-motion-u100-80e_ntu60-xsub-keypoint-3d_20221222_110634 2022/12/22 15:00:40 - mmengine - INFO - Epoch(train) [16][1567/1567] lr: 3.9252e-10 eta: 0:00:00 time: 0.4198 data_time: 0.0092 memory: 2111 loss: 0.1862 top1_acc: 0.0000 top5_acc: 1.0000 loss_cls: 0.1862 2022/12/22 15:00:40 - mmengine - INFO - Saving checkpoint at 16 epochs 2022/12/22 15:00:55 - mmengine - INFO - Epoch(val) [16][100/129] eta: 0:00:04 time: 0.1274 data_time: 0.0102 memory: 293 2022/12/22 15:01:00 - mmengine - INFO - Epoch(val) [16][129/129] acc/top1: 0.8597 acc/top5: 0.9688 acc/mean1: 0.8596