2023/04/17 22:39:46 - mmengine - INFO - ------------------------------------------------------------ System environment: sys.platform: linux Python: 3.7.13 (default, Mar 29 2022, 02:18:16) [GCC 7.5.0] CUDA available: True numpy_random_seed: 1787676745 GPU 0,1,2,3,4,5,6,7: NVIDIA A100-SXM4-80GB CUDA_HOME: /mnt/cache/share/cuda-11.1 NVCC: Cuda compilation tools, release 11.1, V11.1.74 GCC: gcc (GCC) 5.4.0 PyTorch: 1.12.0 PyTorch compiling details: PyTorch built with: - GCC 9.3 - 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 v2.6.0 (Git Hash 52b5f107dd9cf10910aaa19cb47f3abf9b349815) - 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 8.3.2 (built against CUDA 11.5) - Magma 2.5.2 - Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.3, CUDNN_VERSION=8.3.2, CXX_COMPILER=/opt/rh/devtoolset-9/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-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 -Werror=cast-function-type -Wno-stringop-overflow, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, TORCH_VERSION=1.12.0, 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: 0.13.0 OpenCV: 4.7.0 MMEngine: 0.7.0 Runtime environment: cudnn_benchmark: False mp_cfg: {'mp_start_method': 'fork', 'opencv_num_threads': 0} dist_cfg: {'backend': 'nccl'} seed: None diff_rank_seed: False deterministic: False Distributed launcher: pytorch Distributed training: True GPU number: 8 ------------------------------------------------------------ 2023/04/17 22:39:46 - mmengine - INFO - Config: default_scope = 'mmaction' default_hooks = dict( runtime_info=dict(type='RuntimeInfoHook'), timer=dict(type='IterTimerHook'), logger=dict(type='LoggerHook', interval=100, ignore_last=False), param_scheduler=dict(type='ParamSchedulerHook'), checkpoint=dict(type='CheckpointHook', interval=1, save_best='auto'), sampler_seed=dict(type='DistSamplerSeedHook'), sync_buffers=dict(type='SyncBuffersHook')) env_cfg = dict( cudnn_benchmark=False, mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0), dist_cfg=dict(backend='nccl')) log_processor = dict(type='LogProcessor', window_size=20, by_epoch=True) vis_backends = [dict(type='LocalVisBackend')] visualizer = dict( type='ActionVisualizer', vis_backends=[dict(type='LocalVisBackend')]) log_level = 'INFO' load_from = None resume = False model = dict( type='RecognizerGCN', backbone=dict( type='STGCN', gcn_adaptive='init', gcn_with_res=True, tcn_type='mstcn', graph_cfg=dict(layout='hand', mode='spatial')), cls_head=dict(type='GCNHead', num_classes=27, in_channels=256)) dataset_type = 'PoseDataset' ann_file = 'jester.pkl' train_pipeline = [ dict(type='PreNormalize2D'), dict(type='GenSkeFeat', dataset='coco', feats=['j']), dict(type='UniformSampleFrames', clip_len=100), dict(type='PoseDecode'), dict(type='FormatGCNInput', num_person=1), dict(type='PackActionInputs') ] val_pipeline = [ dict(type='PreNormalize2D'), dict(type='GenSkeFeat', dataset='coco', feats=['j']), dict( type='UniformSampleFrames', clip_len=100, num_clips=1, test_mode=True), dict(type='PoseDecode'), dict(type='FormatGCNInput', num_person=1), dict(type='PackActionInputs') ] test_pipeline = [ dict(type='PreNormalize2D'), dict(type='GenSkeFeat', dataset='coco', feats=['j']), dict( type='UniformSampleFrames', clip_len=100, num_clips=10, test_mode=True), dict(type='PoseDecode'), dict(type='FormatGCNInput', num_person=1), 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='jester.pkl', pipeline=[ dict(type='PreNormalize2D'), dict(type='GenSkeFeat', dataset='coco', feats=['j']), dict(type='UniformSampleFrames', clip_len=100), dict(type='PoseDecode'), dict(type='FormatGCNInput', num_person=1), dict(type='PackActionInputs') ], split='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='jester.pkl', pipeline=[ dict(type='PreNormalize2D'), dict(type='GenSkeFeat', dataset='coco', feats=['j']), dict( type='UniformSampleFrames', clip_len=100, num_clips=1, test_mode=True), dict(type='PoseDecode'), dict(type='FormatGCNInput', num_person=1), dict(type='PackActionInputs') ], split='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='jester.pkl', pipeline=[ dict(type='PreNormalize2D'), dict(type='GenSkeFeat', dataset='coco', feats=['j']), dict( type='UniformSampleFrames', clip_len=100, num_clips=10, test_mode=True), dict(type='PoseDecode'), dict(type='FormatGCNInput', num_person=1), dict(type='PackActionInputs') ], split='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/stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d' randomness = dict(seed=None, diff_rank_seed=False, deterministic=False) 2023/04/17 22:39:54 - mmengine - INFO - Hooks will be executed in the following order: before_run: (VERY_HIGH ) RuntimeInfoHook (BELOW_NORMAL) LoggerHook -------------------- before_train: (VERY_HIGH ) RuntimeInfoHook (NORMAL ) IterTimerHook (VERY_LOW ) CheckpointHook -------------------- before_train_epoch: (VERY_HIGH ) RuntimeInfoHook (NORMAL ) IterTimerHook (NORMAL ) DistSamplerSeedHook -------------------- before_train_iter: (VERY_HIGH ) RuntimeInfoHook (NORMAL ) IterTimerHook -------------------- after_train_iter: (VERY_HIGH ) RuntimeInfoHook (NORMAL ) IterTimerHook (BELOW_NORMAL) LoggerHook (LOW ) ParamSchedulerHook (VERY_LOW ) CheckpointHook -------------------- after_train_epoch: (NORMAL ) IterTimerHook (NORMAL ) SyncBuffersHook (LOW ) ParamSchedulerHook (VERY_LOW ) CheckpointHook -------------------- before_val_epoch: (NORMAL ) IterTimerHook -------------------- before_val_iter: (NORMAL ) IterTimerHook -------------------- after_val_iter: (NORMAL ) IterTimerHook (BELOW_NORMAL) LoggerHook -------------------- after_val_epoch: (VERY_HIGH ) RuntimeInfoHook (NORMAL ) IterTimerHook (BELOW_NORMAL) LoggerHook (LOW ) ParamSchedulerHook (VERY_LOW ) CheckpointHook -------------------- before_test_epoch: (NORMAL ) IterTimerHook -------------------- before_test_iter: (NORMAL ) IterTimerHook -------------------- after_test_iter: (NORMAL ) IterTimerHook (BELOW_NORMAL) LoggerHook -------------------- after_test_epoch: (VERY_HIGH ) RuntimeInfoHook (NORMAL ) IterTimerHook (BELOW_NORMAL) LoggerHook -------------------- after_run: (BELOW_NORMAL) LoggerHook -------------------- Name of parameter - Initialization information backbone.data_bn.weight - torch.Size([63]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.data_bn.bias - torch.Size([63]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.gcn.A - torch.Size([3, 21, 21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.gcn.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.gcn.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.gcn.conv.weight - torch.Size([192, 3, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.gcn.conv.bias - torch.Size([192]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.gcn.down.0.weight - torch.Size([64, 3, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.gcn.down.0.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.gcn.down.1.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.gcn.down.1.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.tcn.branches.0.0.weight - torch.Size([14, 64, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.tcn.branches.0.0.bias - torch.Size([14]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.tcn.branches.0.1.weight - torch.Size([14]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.tcn.branches.0.1.bias - torch.Size([14]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.tcn.branches.0.3.conv.weight - torch.Size([14, 14, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.tcn.branches.0.3.conv.bias - torch.Size([14]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.tcn.branches.1.0.weight - torch.Size([10, 64, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.tcn.branches.1.0.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.tcn.branches.1.1.weight - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.tcn.branches.1.1.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.tcn.branches.1.3.conv.weight - torch.Size([10, 10, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.tcn.branches.1.3.conv.bias - torch.Size([10]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.tcn.branches.2.0.weight - torch.Size([10, 64, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.tcn.branches.2.0.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.tcn.branches.2.1.weight - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.tcn.branches.2.1.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.tcn.branches.2.3.conv.weight - torch.Size([10, 10, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.tcn.branches.2.3.conv.bias - torch.Size([10]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.tcn.branches.3.0.weight - torch.Size([10, 64, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.tcn.branches.3.0.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.tcn.branches.3.1.weight - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.tcn.branches.3.1.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.tcn.branches.3.3.conv.weight - torch.Size([10, 10, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.tcn.branches.3.3.conv.bias - torch.Size([10]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.0.tcn.branches.4.0.weight - torch.Size([10, 64, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.tcn.branches.4.0.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.tcn.branches.4.1.weight - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.tcn.branches.4.1.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.tcn.branches.5.weight - torch.Size([10, 64, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.tcn.branches.5.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.tcn.transform.0.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.tcn.transform.0.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.tcn.transform.2.weight - torch.Size([64, 64, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.tcn.transform.2.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.tcn.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.0.tcn.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.gcn.A - torch.Size([3, 21, 21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.gcn.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.gcn.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.gcn.conv.weight - torch.Size([192, 64, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.gcn.conv.bias - torch.Size([192]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.tcn.branches.0.0.weight - torch.Size([14, 64, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.tcn.branches.0.0.bias - torch.Size([14]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.tcn.branches.0.1.weight - torch.Size([14]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.tcn.branches.0.1.bias - torch.Size([14]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.tcn.branches.0.3.conv.weight - torch.Size([14, 14, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.1.tcn.branches.0.3.conv.bias - torch.Size([14]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.1.tcn.branches.1.0.weight - torch.Size([10, 64, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.tcn.branches.1.0.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.tcn.branches.1.1.weight - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.tcn.branches.1.1.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.tcn.branches.1.3.conv.weight - torch.Size([10, 10, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.1.tcn.branches.1.3.conv.bias - torch.Size([10]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.1.tcn.branches.2.0.weight - torch.Size([10, 64, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.tcn.branches.2.0.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.tcn.branches.2.1.weight - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.tcn.branches.2.1.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.tcn.branches.2.3.conv.weight - torch.Size([10, 10, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.1.tcn.branches.2.3.conv.bias - torch.Size([10]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.1.tcn.branches.3.0.weight - torch.Size([10, 64, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.tcn.branches.3.0.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.tcn.branches.3.1.weight - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.tcn.branches.3.1.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.tcn.branches.3.3.conv.weight - torch.Size([10, 10, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.1.tcn.branches.3.3.conv.bias - torch.Size([10]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.1.tcn.branches.4.0.weight - torch.Size([10, 64, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.tcn.branches.4.0.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.tcn.branches.4.1.weight - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.tcn.branches.4.1.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.tcn.branches.5.weight - torch.Size([10, 64, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.tcn.branches.5.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.tcn.transform.0.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.tcn.transform.0.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.tcn.transform.2.weight - torch.Size([64, 64, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.tcn.transform.2.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.tcn.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.1.tcn.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.gcn.A - torch.Size([3, 21, 21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.gcn.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.gcn.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.gcn.conv.weight - torch.Size([192, 64, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.gcn.conv.bias - torch.Size([192]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.tcn.branches.0.0.weight - torch.Size([14, 64, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.tcn.branches.0.0.bias - torch.Size([14]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.tcn.branches.0.1.weight - torch.Size([14]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.tcn.branches.0.1.bias - torch.Size([14]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.tcn.branches.0.3.conv.weight - torch.Size([14, 14, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.2.tcn.branches.0.3.conv.bias - torch.Size([14]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.2.tcn.branches.1.0.weight - torch.Size([10, 64, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.tcn.branches.1.0.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.tcn.branches.1.1.weight - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.tcn.branches.1.1.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.tcn.branches.1.3.conv.weight - torch.Size([10, 10, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.2.tcn.branches.1.3.conv.bias - torch.Size([10]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.2.tcn.branches.2.0.weight - torch.Size([10, 64, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.tcn.branches.2.0.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.tcn.branches.2.1.weight - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.tcn.branches.2.1.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.tcn.branches.2.3.conv.weight - torch.Size([10, 10, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.2.tcn.branches.2.3.conv.bias - torch.Size([10]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.2.tcn.branches.3.0.weight - torch.Size([10, 64, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.tcn.branches.3.0.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.tcn.branches.3.1.weight - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.tcn.branches.3.1.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.tcn.branches.3.3.conv.weight - torch.Size([10, 10, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.2.tcn.branches.3.3.conv.bias - torch.Size([10]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.2.tcn.branches.4.0.weight - torch.Size([10, 64, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.tcn.branches.4.0.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.tcn.branches.4.1.weight - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.tcn.branches.4.1.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.tcn.branches.5.weight - torch.Size([10, 64, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.tcn.branches.5.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.tcn.transform.0.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.tcn.transform.0.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.tcn.transform.2.weight - torch.Size([64, 64, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.tcn.transform.2.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.tcn.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.2.tcn.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.gcn.A - torch.Size([3, 21, 21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.gcn.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.gcn.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.gcn.conv.weight - torch.Size([192, 64, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.gcn.conv.bias - torch.Size([192]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.tcn.branches.0.0.weight - torch.Size([14, 64, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.tcn.branches.0.0.bias - torch.Size([14]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.tcn.branches.0.1.weight - torch.Size([14]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.tcn.branches.0.1.bias - torch.Size([14]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.tcn.branches.0.3.conv.weight - torch.Size([14, 14, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.3.tcn.branches.0.3.conv.bias - torch.Size([14]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.3.tcn.branches.1.0.weight - torch.Size([10, 64, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.tcn.branches.1.0.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.tcn.branches.1.1.weight - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.tcn.branches.1.1.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.tcn.branches.1.3.conv.weight - torch.Size([10, 10, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.3.tcn.branches.1.3.conv.bias - torch.Size([10]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.3.tcn.branches.2.0.weight - torch.Size([10, 64, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.tcn.branches.2.0.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.tcn.branches.2.1.weight - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.tcn.branches.2.1.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.tcn.branches.2.3.conv.weight - torch.Size([10, 10, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.3.tcn.branches.2.3.conv.bias - torch.Size([10]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.3.tcn.branches.3.0.weight - torch.Size([10, 64, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.tcn.branches.3.0.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.tcn.branches.3.1.weight - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.tcn.branches.3.1.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.tcn.branches.3.3.conv.weight - torch.Size([10, 10, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.3.tcn.branches.3.3.conv.bias - torch.Size([10]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.3.tcn.branches.4.0.weight - torch.Size([10, 64, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.tcn.branches.4.0.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.tcn.branches.4.1.weight - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.tcn.branches.4.1.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.tcn.branches.5.weight - torch.Size([10, 64, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.tcn.branches.5.bias - torch.Size([10]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.tcn.transform.0.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.tcn.transform.0.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.tcn.transform.2.weight - torch.Size([64, 64, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.tcn.transform.2.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.tcn.bn.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.3.tcn.bn.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.gcn.A - torch.Size([3, 21, 21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.gcn.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.gcn.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.gcn.conv.weight - torch.Size([384, 64, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.gcn.conv.bias - torch.Size([384]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.gcn.down.0.weight - torch.Size([128, 64, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.gcn.down.0.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.gcn.down.1.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.gcn.down.1.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.tcn.branches.0.0.weight - torch.Size([23, 128, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.tcn.branches.0.0.bias - torch.Size([23]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.tcn.branches.0.1.weight - torch.Size([23]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.tcn.branches.0.1.bias - torch.Size([23]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.tcn.branches.0.3.conv.weight - torch.Size([23, 23, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.tcn.branches.0.3.conv.bias - torch.Size([23]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.tcn.branches.1.0.weight - torch.Size([21, 128, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.tcn.branches.1.0.bias - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.tcn.branches.1.1.weight - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.tcn.branches.1.1.bias - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.tcn.branches.1.3.conv.weight - torch.Size([21, 21, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.tcn.branches.1.3.conv.bias - torch.Size([21]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.tcn.branches.2.0.weight - torch.Size([21, 128, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.tcn.branches.2.0.bias - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.tcn.branches.2.1.weight - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.tcn.branches.2.1.bias - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.tcn.branches.2.3.conv.weight - torch.Size([21, 21, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.tcn.branches.2.3.conv.bias - torch.Size([21]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.tcn.branches.3.0.weight - torch.Size([21, 128, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.tcn.branches.3.0.bias - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.tcn.branches.3.1.weight - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.tcn.branches.3.1.bias - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.tcn.branches.3.3.conv.weight - torch.Size([21, 21, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.tcn.branches.3.3.conv.bias - torch.Size([21]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.tcn.branches.4.0.weight - torch.Size([21, 128, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.tcn.branches.4.0.bias - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.tcn.branches.4.1.weight - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.tcn.branches.4.1.bias - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.tcn.branches.5.weight - torch.Size([21, 128, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.tcn.branches.5.bias - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.tcn.transform.0.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.tcn.transform.0.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.tcn.transform.2.weight - torch.Size([128, 128, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.tcn.transform.2.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.tcn.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.tcn.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.residual.conv.weight - torch.Size([128, 64, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.residual.conv.bias - torch.Size([128]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.4.residual.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.4.residual.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.gcn.A - torch.Size([3, 21, 21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.gcn.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.gcn.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.gcn.conv.weight - torch.Size([384, 128, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.gcn.conv.bias - torch.Size([384]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.tcn.branches.0.0.weight - torch.Size([23, 128, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.tcn.branches.0.0.bias - torch.Size([23]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.tcn.branches.0.1.weight - torch.Size([23]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.tcn.branches.0.1.bias - torch.Size([23]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.tcn.branches.0.3.conv.weight - torch.Size([23, 23, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.5.tcn.branches.0.3.conv.bias - torch.Size([23]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.5.tcn.branches.1.0.weight - torch.Size([21, 128, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.tcn.branches.1.0.bias - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.tcn.branches.1.1.weight - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.tcn.branches.1.1.bias - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.tcn.branches.1.3.conv.weight - torch.Size([21, 21, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.5.tcn.branches.1.3.conv.bias - torch.Size([21]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.5.tcn.branches.2.0.weight - torch.Size([21, 128, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.tcn.branches.2.0.bias - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.tcn.branches.2.1.weight - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.tcn.branches.2.1.bias - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.tcn.branches.2.3.conv.weight - torch.Size([21, 21, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.5.tcn.branches.2.3.conv.bias - torch.Size([21]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.5.tcn.branches.3.0.weight - torch.Size([21, 128, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.tcn.branches.3.0.bias - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.tcn.branches.3.1.weight - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.tcn.branches.3.1.bias - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.tcn.branches.3.3.conv.weight - torch.Size([21, 21, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.5.tcn.branches.3.3.conv.bias - torch.Size([21]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.5.tcn.branches.4.0.weight - torch.Size([21, 128, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.tcn.branches.4.0.bias - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.tcn.branches.4.1.weight - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.tcn.branches.4.1.bias - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.tcn.branches.5.weight - torch.Size([21, 128, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.tcn.branches.5.bias - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.tcn.transform.0.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.tcn.transform.0.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.tcn.transform.2.weight - torch.Size([128, 128, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.tcn.transform.2.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.tcn.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.5.tcn.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.gcn.A - torch.Size([3, 21, 21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.gcn.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.gcn.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.gcn.conv.weight - torch.Size([384, 128, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.gcn.conv.bias - torch.Size([384]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.tcn.branches.0.0.weight - torch.Size([23, 128, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.tcn.branches.0.0.bias - torch.Size([23]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.tcn.branches.0.1.weight - torch.Size([23]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.tcn.branches.0.1.bias - torch.Size([23]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.tcn.branches.0.3.conv.weight - torch.Size([23, 23, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.6.tcn.branches.0.3.conv.bias - torch.Size([23]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.6.tcn.branches.1.0.weight - torch.Size([21, 128, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.tcn.branches.1.0.bias - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.tcn.branches.1.1.weight - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.tcn.branches.1.1.bias - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.tcn.branches.1.3.conv.weight - torch.Size([21, 21, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.6.tcn.branches.1.3.conv.bias - torch.Size([21]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.6.tcn.branches.2.0.weight - torch.Size([21, 128, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.tcn.branches.2.0.bias - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.tcn.branches.2.1.weight - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.tcn.branches.2.1.bias - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.tcn.branches.2.3.conv.weight - torch.Size([21, 21, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.6.tcn.branches.2.3.conv.bias - torch.Size([21]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.6.tcn.branches.3.0.weight - torch.Size([21, 128, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.tcn.branches.3.0.bias - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.tcn.branches.3.1.weight - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.tcn.branches.3.1.bias - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.tcn.branches.3.3.conv.weight - torch.Size([21, 21, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.6.tcn.branches.3.3.conv.bias - torch.Size([21]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.6.tcn.branches.4.0.weight - torch.Size([21, 128, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.tcn.branches.4.0.bias - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.tcn.branches.4.1.weight - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.tcn.branches.4.1.bias - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.tcn.branches.5.weight - torch.Size([21, 128, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.tcn.branches.5.bias - torch.Size([21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.tcn.transform.0.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.tcn.transform.0.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.tcn.transform.2.weight - torch.Size([128, 128, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.tcn.transform.2.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.tcn.bn.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.6.tcn.bn.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.gcn.A - torch.Size([3, 21, 21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.gcn.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.gcn.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.gcn.conv.weight - torch.Size([768, 128, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.gcn.conv.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.gcn.down.0.weight - torch.Size([256, 128, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.gcn.down.0.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.gcn.down.1.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.gcn.down.1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.tcn.branches.0.0.weight - torch.Size([46, 256, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.tcn.branches.0.0.bias - torch.Size([46]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.tcn.branches.0.1.weight - torch.Size([46]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.tcn.branches.0.1.bias - torch.Size([46]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.tcn.branches.0.3.conv.weight - torch.Size([46, 46, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.tcn.branches.0.3.conv.bias - torch.Size([46]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.tcn.branches.1.0.weight - torch.Size([42, 256, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.tcn.branches.1.0.bias - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.tcn.branches.1.1.weight - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.tcn.branches.1.1.bias - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.tcn.branches.1.3.conv.weight - torch.Size([42, 42, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.tcn.branches.1.3.conv.bias - torch.Size([42]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.tcn.branches.2.0.weight - torch.Size([42, 256, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.tcn.branches.2.0.bias - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.tcn.branches.2.1.weight - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.tcn.branches.2.1.bias - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.tcn.branches.2.3.conv.weight - torch.Size([42, 42, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.tcn.branches.2.3.conv.bias - torch.Size([42]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.tcn.branches.3.0.weight - torch.Size([42, 256, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.tcn.branches.3.0.bias - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.tcn.branches.3.1.weight - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.tcn.branches.3.1.bias - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.tcn.branches.3.3.conv.weight - torch.Size([42, 42, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.tcn.branches.3.3.conv.bias - torch.Size([42]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.tcn.branches.4.0.weight - torch.Size([42, 256, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.tcn.branches.4.0.bias - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.tcn.branches.4.1.weight - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.tcn.branches.4.1.bias - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.tcn.branches.5.weight - torch.Size([42, 256, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.tcn.branches.5.bias - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.tcn.transform.0.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.tcn.transform.0.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.tcn.transform.2.weight - torch.Size([256, 256, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.tcn.transform.2.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.tcn.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.tcn.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.residual.conv.weight - torch.Size([256, 128, 1, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.residual.conv.bias - torch.Size([256]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.7.residual.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.7.residual.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.gcn.A - torch.Size([3, 21, 21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.gcn.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.gcn.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.gcn.conv.weight - torch.Size([768, 256, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.gcn.conv.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.tcn.branches.0.0.weight - torch.Size([46, 256, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.tcn.branches.0.0.bias - torch.Size([46]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.tcn.branches.0.1.weight - torch.Size([46]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.tcn.branches.0.1.bias - torch.Size([46]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.tcn.branches.0.3.conv.weight - torch.Size([46, 46, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.8.tcn.branches.0.3.conv.bias - torch.Size([46]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.8.tcn.branches.1.0.weight - torch.Size([42, 256, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.tcn.branches.1.0.bias - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.tcn.branches.1.1.weight - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.tcn.branches.1.1.bias - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.tcn.branches.1.3.conv.weight - torch.Size([42, 42, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.8.tcn.branches.1.3.conv.bias - torch.Size([42]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.8.tcn.branches.2.0.weight - torch.Size([42, 256, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.tcn.branches.2.0.bias - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.tcn.branches.2.1.weight - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.tcn.branches.2.1.bias - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.tcn.branches.2.3.conv.weight - torch.Size([42, 42, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.8.tcn.branches.2.3.conv.bias - torch.Size([42]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.8.tcn.branches.3.0.weight - torch.Size([42, 256, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.tcn.branches.3.0.bias - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.tcn.branches.3.1.weight - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.tcn.branches.3.1.bias - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.tcn.branches.3.3.conv.weight - torch.Size([42, 42, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.8.tcn.branches.3.3.conv.bias - torch.Size([42]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.8.tcn.branches.4.0.weight - torch.Size([42, 256, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.tcn.branches.4.0.bias - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.tcn.branches.4.1.weight - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.tcn.branches.4.1.bias - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.tcn.branches.5.weight - torch.Size([42, 256, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.tcn.branches.5.bias - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.tcn.transform.0.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.tcn.transform.0.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.tcn.transform.2.weight - torch.Size([256, 256, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.tcn.transform.2.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.tcn.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.8.tcn.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.gcn.A - torch.Size([3, 21, 21]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.gcn.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.gcn.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.gcn.conv.weight - torch.Size([768, 256, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.gcn.conv.bias - torch.Size([768]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.tcn.branches.0.0.weight - torch.Size([46, 256, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.tcn.branches.0.0.bias - torch.Size([46]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.tcn.branches.0.1.weight - torch.Size([46]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.tcn.branches.0.1.bias - torch.Size([46]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.tcn.branches.0.3.conv.weight - torch.Size([46, 46, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.9.tcn.branches.0.3.conv.bias - torch.Size([46]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.9.tcn.branches.1.0.weight - torch.Size([42, 256, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.tcn.branches.1.0.bias - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.tcn.branches.1.1.weight - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.tcn.branches.1.1.bias - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.tcn.branches.1.3.conv.weight - torch.Size([42, 42, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.9.tcn.branches.1.3.conv.bias - torch.Size([42]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.9.tcn.branches.2.0.weight - torch.Size([42, 256, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.tcn.branches.2.0.bias - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.tcn.branches.2.1.weight - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.tcn.branches.2.1.bias - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.tcn.branches.2.3.conv.weight - torch.Size([42, 42, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.9.tcn.branches.2.3.conv.bias - torch.Size([42]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.9.tcn.branches.3.0.weight - torch.Size([42, 256, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.tcn.branches.3.0.bias - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.tcn.branches.3.1.weight - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.tcn.branches.3.1.bias - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.tcn.branches.3.3.conv.weight - torch.Size([42, 42, 3, 1]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.9.tcn.branches.3.3.conv.bias - torch.Size([42]): KaimingInit: a=0, mode=fan_out, nonlinearity=relu, distribution =normal, bias=0 backbone.gcn.9.tcn.branches.4.0.weight - torch.Size([42, 256, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.tcn.branches.4.0.bias - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.tcn.branches.4.1.weight - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.tcn.branches.4.1.bias - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.tcn.branches.5.weight - torch.Size([42, 256, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.tcn.branches.5.bias - torch.Size([42]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.tcn.transform.0.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.tcn.transform.0.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.tcn.transform.2.weight - torch.Size([256, 256, 1, 1]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.tcn.transform.2.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.tcn.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN backbone.gcn.9.tcn.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of RecognizerGCN cls_head.fc.weight - torch.Size([27, 256]): NormalInit: mean=0, std=0.01, bias=0 cls_head.fc.bias - torch.Size([27]): NormalInit: mean=0, std=0.01, bias=0 2023/04/17 22:42:33 - mmengine - WARNING - "FileClient" will be deprecated in future. Please use io functions in https://mmengine.readthedocs.io/en/latest/api/fileio.html#file-io 2023/04/17 22:42:33 - mmengine - WARNING - "HardDiskBackend" is the alias of "LocalBackend" and the former will be deprecated in future. 2023/04/17 22:42:33 - mmengine - INFO - Checkpoints will be saved to /mnt/petrelfs/hukai/mmaction2/work_dirs/stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d. 2023/04/17 22:42:51 - mmengine - INFO - Epoch(train) [1][ 100/4632] lr: 1.0000e-01 eta: 3:34:18 time: 0.1004 data_time: 0.0071 memory: 1125 loss: 2.7751 top1_acc: 0.1250 top5_acc: 0.5625 loss_cls: 2.7751 2023/04/17 22:43:01 - mmengine - INFO - Epoch(train) [1][ 200/4632] lr: 9.9998e-02 eta: 2:49:01 time: 0.1025 data_time: 0.0073 memory: 1125 loss: 1.9531 top1_acc: 0.3750 top5_acc: 0.8125 loss_cls: 1.9531 2023/04/17 22:43:11 - mmengine - INFO - Epoch(train) [1][ 300/4632] lr: 9.9996e-02 eta: 2:33:58 time: 0.1009 data_time: 0.0072 memory: 1125 loss: 1.4537 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 1.4537 2023/04/17 22:43:21 - mmengine - INFO - Epoch(train) [1][ 400/4632] lr: 9.9993e-02 eta: 2:26:07 time: 0.0998 data_time: 0.0072 memory: 1125 loss: 1.1195 top1_acc: 0.4375 top5_acc: 0.9375 loss_cls: 1.1195 2023/04/17 22:43:31 - mmengine - INFO - Epoch(train) [1][ 500/4632] lr: 9.9989e-02 eta: 2:21:12 time: 0.0992 data_time: 0.0072 memory: 1125 loss: 1.1383 top1_acc: 0.5625 top5_acc: 0.9375 loss_cls: 1.1383 2023/04/17 22:43:41 - mmengine - INFO - Epoch(train) [1][ 600/4632] lr: 9.9984e-02 eta: 2:17:41 time: 0.0999 data_time: 0.0072 memory: 1125 loss: 0.9958 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.9958 2023/04/17 22:43:51 - mmengine - INFO - Epoch(train) [1][ 700/4632] lr: 9.9978e-02 eta: 2:15:07 time: 0.0989 data_time: 0.0071 memory: 1125 loss: 1.0606 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 1.0606 2023/04/17 22:44:00 - mmengine - INFO - Epoch(train) [1][ 800/4632] lr: 9.9971e-02 eta: 2:13:06 time: 0.0984 data_time: 0.0072 memory: 1125 loss: 0.9187 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 0.9187 2023/04/17 22:44:10 - mmengine - INFO - Epoch(train) [1][ 900/4632] lr: 9.9964e-02 eta: 2:11:16 time: 0.0972 data_time: 0.0071 memory: 1125 loss: 0.9087 top1_acc: 0.5625 top5_acc: 0.6250 loss_cls: 0.9087 2023/04/17 22:44:20 - mmengine - INFO - Exp name: stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230417_223936 2023/04/17 22:44:20 - mmengine - INFO - Epoch(train) [1][1000/4632] lr: 9.9955e-02 eta: 2:09:53 time: 0.0976 data_time: 0.0072 memory: 1125 loss: 0.7901 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 0.7901 2023/04/17 22:44:30 - mmengine - INFO - Epoch(train) [1][1100/4632] lr: 9.9946e-02 eta: 2:08:42 time: 0.0977 data_time: 0.0072 memory: 1125 loss: 0.7684 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.7684 2023/04/17 22:44:39 - mmengine - INFO - Epoch(train) [1][1200/4632] lr: 9.9935e-02 eta: 2:07:42 time: 0.0982 data_time: 0.0071 memory: 1125 loss: 0.8890 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.8890 2023/04/17 22:44:49 - mmengine - INFO - Epoch(train) [1][1300/4632] lr: 9.9924e-02 eta: 2:06:48 time: 0.0979 data_time: 0.0071 memory: 1125 loss: 0.7261 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.7261 2023/04/17 22:44:59 - mmengine - INFO - Epoch(train) [1][1400/4632] lr: 9.9912e-02 eta: 2:06:02 time: 0.0978 data_time: 0.0073 memory: 1125 loss: 0.7659 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 0.7659 2023/04/17 22:45:09 - mmengine - INFO - Epoch(train) [1][1500/4632] lr: 9.9899e-02 eta: 2:05:30 time: 0.0988 data_time: 0.0078 memory: 1125 loss: 0.6985 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.6985 2023/04/17 22:45:19 - mmengine - INFO - Epoch(train) [1][1600/4632] lr: 9.9885e-02 eta: 2:04:58 time: 0.0993 data_time: 0.0072 memory: 1125 loss: 0.6005 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.6005 2023/04/17 22:45:29 - mmengine - INFO - Epoch(train) [1][1700/4632] lr: 9.9870e-02 eta: 2:04:29 time: 0.0991 data_time: 0.0071 memory: 1125 loss: 0.8091 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.8091 2023/04/17 22:45:38 - mmengine - INFO - Epoch(train) [1][1800/4632] lr: 9.9855e-02 eta: 2:04:02 time: 0.0990 data_time: 0.0072 memory: 1125 loss: 0.7840 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.7840 2023/04/17 22:45:48 - mmengine - INFO - Epoch(train) [1][1900/4632] lr: 9.9838e-02 eta: 2:03:38 time: 0.0990 data_time: 0.0072 memory: 1125 loss: 0.6236 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.6236 2023/04/17 22:45:58 - mmengine - INFO - Exp name: stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230417_223936 2023/04/17 22:45:58 - mmengine - INFO - Epoch(train) [1][2000/4632] lr: 9.9821e-02 eta: 2:03:12 time: 0.0980 data_time: 0.0072 memory: 1125 loss: 0.5554 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 0.5554 2023/04/17 22:46:08 - mmengine - INFO - Epoch(train) [1][2100/4632] lr: 9.9802e-02 eta: 2:02:48 time: 0.0983 data_time: 0.0079 memory: 1125 loss: 0.7387 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.7387 2023/04/17 22:46:18 - mmengine - INFO - Epoch(train) [1][2200/4632] lr: 9.9783e-02 eta: 2:02:22 time: 0.0972 data_time: 0.0081 memory: 1125 loss: 0.6532 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.6532 2023/04/17 22:46:28 - mmengine - INFO - Epoch(train) [1][2300/4632] lr: 9.9763e-02 eta: 2:01:57 time: 0.0974 data_time: 0.0079 memory: 1125 loss: 0.6273 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.6273 2023/04/17 22:46:38 - mmengine - INFO - Epoch(train) [1][2400/4632] lr: 9.9742e-02 eta: 2:01:40 time: 0.0995 data_time: 0.0078 memory: 1125 loss: 0.5826 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.5826 2023/04/17 22:46:47 - mmengine - INFO - Epoch(train) [1][2500/4632] lr: 9.9720e-02 eta: 2:01:22 time: 0.0985 data_time: 0.0072 memory: 1125 loss: 0.7239 top1_acc: 0.6875 top5_acc: 0.8125 loss_cls: 0.7239 2023/04/17 22:46:57 - mmengine - INFO - Epoch(train) [1][2600/4632] lr: 9.9697e-02 eta: 2:01:04 time: 0.0977 data_time: 0.0072 memory: 1125 loss: 0.5917 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 0.5917 2023/04/17 22:47:07 - mmengine - INFO - Epoch(train) [1][2700/4632] lr: 9.9673e-02 eta: 2:00:44 time: 0.0989 data_time: 0.0073 memory: 1125 loss: 0.6173 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.6173 2023/04/17 22:47:17 - mmengine - INFO - Epoch(train) [1][2800/4632] lr: 9.9648e-02 eta: 2:00:24 time: 0.0974 data_time: 0.0071 memory: 1125 loss: 0.6313 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.6313 2023/04/17 22:47:27 - mmengine - INFO - Epoch(train) [1][2900/4632] lr: 9.9623e-02 eta: 2:00:05 time: 0.0972 data_time: 0.0073 memory: 1125 loss: 0.6688 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.6688 2023/04/17 22:47:36 - mmengine - INFO - Exp name: stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230417_223936 2023/04/17 22:47:36 - mmengine - INFO - Epoch(train) [1][3000/4632] lr: 9.9597e-02 eta: 1:59:46 time: 0.0970 data_time: 0.0072 memory: 1125 loss: 0.5980 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.5980 2023/04/17 22:47:46 - mmengine - INFO - Epoch(train) [1][3100/4632] lr: 9.9569e-02 eta: 1:59:28 time: 0.0976 data_time: 0.0072 memory: 1125 loss: 0.7142 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.7142 2023/04/17 22:47:56 - mmengine - INFO - Epoch(train) [1][3200/4632] lr: 9.9541e-02 eta: 1:59:12 time: 0.0985 data_time: 0.0075 memory: 1125 loss: 0.5713 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.5713 2023/04/17 22:48:06 - mmengine - INFO - Epoch(train) [1][3300/4632] lr: 9.9512e-02 eta: 1:58:55 time: 0.0975 data_time: 0.0076 memory: 1125 loss: 0.6381 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.6381 2023/04/17 22:48:15 - mmengine - INFO - Epoch(train) [1][3400/4632] lr: 9.9482e-02 eta: 1:58:35 time: 0.0961 data_time: 0.0078 memory: 1125 loss: 0.6107 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.6107 2023/04/17 22:48:25 - mmengine - INFO - Epoch(train) [1][3500/4632] lr: 9.9451e-02 eta: 1:58:16 time: 0.0967 data_time: 0.0073 memory: 1125 loss: 0.6916 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.6916 2023/04/17 22:48:35 - mmengine - INFO - Epoch(train) [1][3600/4632] lr: 9.9419e-02 eta: 1:57:58 time: 0.0960 data_time: 0.0071 memory: 1125 loss: 0.5862 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.5862 2023/04/17 22:48:44 - mmengine - INFO - Epoch(train) [1][3700/4632] lr: 9.9387e-02 eta: 1:57:40 time: 0.0957 data_time: 0.0072 memory: 1125 loss: 0.6008 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.6008 2023/04/17 22:48:54 - mmengine - INFO - Epoch(train) [1][3800/4632] lr: 9.9353e-02 eta: 1:57:22 time: 0.0964 data_time: 0.0073 memory: 1125 loss: 0.7421 top1_acc: 0.6250 top5_acc: 1.0000 loss_cls: 0.7421 2023/04/17 22:49:03 - mmengine - INFO - Epoch(train) [1][3900/4632] lr: 9.9319e-02 eta: 1:57:04 time: 0.0956 data_time: 0.0078 memory: 1125 loss: 0.5676 top1_acc: 0.8750 top5_acc: 0.8750 loss_cls: 0.5676 2023/04/17 22:49:13 - mmengine - INFO - Exp name: stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230417_223936 2023/04/17 22:49:13 - mmengine - INFO - Epoch(train) [1][4000/4632] lr: 9.9283e-02 eta: 1:56:48 time: 0.0959 data_time: 0.0076 memory: 1125 loss: 0.6168 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.6168 2023/04/17 22:49:23 - mmengine - INFO - Epoch(train) [1][4100/4632] lr: 9.9247e-02 eta: 1:56:31 time: 0.0956 data_time: 0.0076 memory: 1125 loss: 0.6098 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.6098 2023/04/17 22:49:32 - mmengine - INFO - Epoch(train) [1][4200/4632] lr: 9.9210e-02 eta: 1:56:14 time: 0.0972 data_time: 0.0076 memory: 1125 loss: 0.6428 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.6428 2023/04/17 22:49:42 - mmengine - INFO - Epoch(train) [1][4300/4632] lr: 9.9172e-02 eta: 1:56:02 time: 0.0983 data_time: 0.0082 memory: 1125 loss: 0.6049 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 0.6049 2023/04/17 22:49:52 - mmengine - INFO - Epoch(train) [1][4400/4632] lr: 9.9133e-02 eta: 1:55:49 time: 0.0974 data_time: 0.0078 memory: 1125 loss: 0.6550 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.6550 2023/04/17 22:50:02 - mmengine - INFO - Epoch(train) [1][4500/4632] lr: 9.9093e-02 eta: 1:55:36 time: 0.0986 data_time: 0.0076 memory: 1125 loss: 0.6388 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.6388 2023/04/17 22:50:12 - mmengine - INFO - Epoch(train) [1][4600/4632] lr: 9.9053e-02 eta: 1:55:25 time: 0.0986 data_time: 0.0073 memory: 1125 loss: 0.5484 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.5484 2023/04/17 22:50:15 - mmengine - INFO - Exp name: stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230417_223936 2023/04/17 22:50:15 - mmengine - INFO - Epoch(train) [1][4632/4632] lr: 9.9040e-02 eta: 1:55:22 time: 0.1028 data_time: 0.0073 memory: 1125 loss: 0.5934 top1_acc: 0.6667 top5_acc: 1.0000 loss_cls: 0.5934 2023/04/17 22:50:15 - mmengine - INFO - Saving checkpoint at 1 epochs 2023/04/17 22:50:18 - mmengine - INFO - Epoch(val) [1][100/116] eta: 0:00:00 time: 0.0272 data_time: 0.0065 memory: 171 2023/04/17 22:50:19 - mmengine - INFO - Epoch(val) [1][116/116] acc/top1: 0.8209 acc/top5: 0.9644 acc/mean1: 0.8241data_time: 0.0069 time: 0.0279 2023/04/17 22:50:19 - mmengine - INFO - The best checkpoint with 0.8209 acc/top1 at 1 epoch is saved to best_acc/top1_epoch_1.pth. 2023/04/17 22:50:29 - mmengine - INFO - Epoch(train) [2][ 100/4632] lr: 9.8998e-02 eta: 1:55:08 time: 0.0966 data_time: 0.0074 memory: 1125 loss: 0.5782 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.5782 2023/04/17 22:50:39 - mmengine - INFO - Epoch(train) [2][ 200/4632] lr: 9.8955e-02 eta: 1:54:54 time: 0.0959 data_time: 0.0074 memory: 1125 loss: 0.4746 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.4746 2023/04/17 22:50:49 - mmengine - INFO - Epoch(train) [2][ 300/4632] lr: 9.8912e-02 eta: 1:54:41 time: 0.0986 data_time: 0.0083 memory: 1125 loss: 0.6017 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.6017 2023/04/17 22:50:55 - mmengine - INFO - Exp name: stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230417_223936 2023/04/17 22:50:58 - mmengine - INFO - Epoch(train) [2][ 400/4632] lr: 9.8867e-02 eta: 1:54:28 time: 0.0964 data_time: 0.0071 memory: 1125 loss: 0.5764 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.5764 2023/04/17 22:51:08 - mmengine - INFO - Epoch(train) [2][ 500/4632] lr: 9.8822e-02 eta: 1:54:16 time: 0.0979 data_time: 0.0072 memory: 1125 loss: 0.5776 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 0.5776 2023/04/17 22:51:18 - mmengine - INFO - Epoch(train) [2][ 600/4632] lr: 9.8776e-02 eta: 1:54:04 time: 0.0975 data_time: 0.0072 memory: 1125 loss: 0.6836 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.6836 2023/04/17 22:51:27 - mmengine - INFO - Epoch(train) [2][ 700/4632] lr: 9.8729e-02 eta: 1:53:51 time: 0.0970 data_time: 0.0071 memory: 1125 loss: 0.6571 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.6571 2023/04/17 22:51:37 - mmengine - INFO - Epoch(train) [2][ 800/4632] lr: 9.8681e-02 eta: 1:53:37 time: 0.0966 data_time: 0.0074 memory: 1125 loss: 0.5702 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.5702 2023/04/17 22:51:47 - mmengine - INFO - Epoch(train) [2][ 900/4632] lr: 9.8632e-02 eta: 1:53:24 time: 0.0989 data_time: 0.0071 memory: 1125 loss: 0.5596 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.5596 2023/04/17 22:51:57 - mmengine - INFO - Epoch(train) [2][1000/4632] lr: 9.8582e-02 eta: 1:53:13 time: 0.0981 data_time: 0.0071 memory: 1125 loss: 0.6047 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.6047 2023/04/17 22:52:06 - mmengine - INFO - Epoch(train) [2][1100/4632] lr: 9.8532e-02 eta: 1:53:00 time: 0.0972 data_time: 0.0071 memory: 1125 loss: 0.5795 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 0.5795 2023/04/17 22:52:16 - mmengine - INFO - Epoch(train) [2][1200/4632] lr: 9.8480e-02 eta: 1:52:47 time: 0.0964 data_time: 0.0071 memory: 1125 loss: 0.6090 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.6090 2023/04/17 22:52:26 - mmengine - INFO - Epoch(train) [2][1300/4632] lr: 9.8428e-02 eta: 1:52:34 time: 0.0962 data_time: 0.0071 memory: 1125 loss: 0.5622 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.5622 2023/04/17 22:52:32 - mmengine - INFO - Exp name: stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230417_223936 2023/04/17 22:52:35 - mmengine - INFO - Epoch(train) [2][1400/4632] lr: 9.8375e-02 eta: 1:52:21 time: 0.0962 data_time: 0.0072 memory: 1125 loss: 0.6137 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 0.6137 2023/04/17 22:52:45 - mmengine - INFO - Epoch(train) [2][1500/4632] lr: 9.8321e-02 eta: 1:52:08 time: 0.0959 data_time: 0.0072 memory: 1125 loss: 0.5283 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 0.5283 2023/04/17 22:52:54 - mmengine - INFO - Epoch(train) [2][1600/4632] lr: 9.8266e-02 eta: 1:51:55 time: 0.0960 data_time: 0.0071 memory: 1125 loss: 0.6575 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 0.6575 2023/04/17 22:53:04 - mmengine - INFO - Epoch(train) [2][1700/4632] lr: 9.8210e-02 eta: 1:51:42 time: 0.0959 data_time: 0.0072 memory: 1125 loss: 0.5416 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.5416 2023/04/17 22:53:14 - mmengine - INFO - Epoch(train) [2][1800/4632] lr: 9.8154e-02 eta: 1:51:30 time: 0.0958 data_time: 0.0071 memory: 1125 loss: 0.6750 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.6750 2023/04/17 22:53:23 - mmengine - INFO - Epoch(train) [2][1900/4632] lr: 9.8096e-02 eta: 1:51:17 time: 0.0958 data_time: 0.0071 memory: 1125 loss: 0.6579 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.6579 2023/04/17 22:53:33 - mmengine - INFO - Epoch(train) [2][2000/4632] lr: 9.8038e-02 eta: 1:51:05 time: 0.0961 data_time: 0.0072 memory: 1125 loss: 0.6366 top1_acc: 0.6250 top5_acc: 0.8125 loss_cls: 0.6366 2023/04/17 22:53:43 - mmengine - INFO - Epoch(train) [2][2100/4632] lr: 9.7979e-02 eta: 1:50:53 time: 0.0966 data_time: 0.0072 memory: 1125 loss: 0.5272 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.5272 2023/04/17 22:53:52 - mmengine - INFO - Epoch(train) [2][2200/4632] lr: 9.7918e-02 eta: 1:50:41 time: 0.0970 data_time: 0.0071 memory: 1125 loss: 0.6712 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.6712 2023/04/17 22:54:02 - mmengine - INFO - Epoch(train) [2][2300/4632] lr: 9.7857e-02 eta: 1:50:29 time: 0.0970 data_time: 0.0073 memory: 1125 loss: 0.4945 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.4945 2023/04/17 22:54:09 - mmengine - INFO - Exp name: stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230417_223936 2023/04/17 22:54:12 - mmengine - INFO - Epoch(train) [2][2400/4632] lr: 9.7796e-02 eta: 1:50:18 time: 0.0969 data_time: 0.0072 memory: 1125 loss: 0.6513 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.6513 2023/04/17 22:54:22 - mmengine - INFO - Epoch(train) [2][2500/4632] lr: 9.7733e-02 eta: 1:50:07 time: 0.0982 data_time: 0.0073 memory: 1125 loss: 0.6900 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.6900 2023/04/17 22:54:31 - mmengine - INFO - Epoch(train) [2][2600/4632] lr: 9.7669e-02 eta: 1:49:56 time: 0.0991 data_time: 0.0072 memory: 1125 loss: 0.5829 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.5829 2023/04/17 22:54:41 - mmengine - INFO - Epoch(train) [2][2700/4632] lr: 9.7605e-02 eta: 1:49:45 time: 0.0988 data_time: 0.0074 memory: 1125 loss: 0.5998 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.5998 2023/04/17 22:54:51 - mmengine - INFO - Epoch(train) [2][2800/4632] lr: 9.7540e-02 eta: 1:49:35 time: 0.0995 data_time: 0.0072 memory: 1125 loss: 0.5014 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.5014 2023/04/17 22:55:01 - mmengine - INFO - Epoch(train) [2][2900/4632] lr: 9.7474e-02 eta: 1:49:24 time: 0.0980 data_time: 0.0074 memory: 1125 loss: 0.5678 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.5678 2023/04/17 22:55:10 - mmengine - INFO - Epoch(train) [2][3000/4632] lr: 9.7407e-02 eta: 1:49:13 time: 0.0973 data_time: 0.0071 memory: 1125 loss: 0.5539 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.5539 2023/04/17 22:55:20 - mmengine - INFO - Epoch(train) [2][3100/4632] lr: 9.7339e-02 eta: 1:49:02 time: 0.0977 data_time: 0.0071 memory: 1125 loss: 0.6370 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.6370 2023/04/17 22:55:30 - mmengine - INFO - Epoch(train) [2][3200/4632] lr: 9.7270e-02 eta: 1:48:50 time: 0.0955 data_time: 0.0072 memory: 1125 loss: 0.7214 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.7214 2023/04/17 22:55:39 - mmengine - INFO - Epoch(train) [2][3300/4632] lr: 9.7201e-02 eta: 1:48:38 time: 0.0971 data_time: 0.0072 memory: 1125 loss: 0.6937 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.6937 2023/04/17 22:55:46 - mmengine - INFO - Exp name: stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230417_223936 2023/04/17 22:55:49 - mmengine - INFO - Epoch(train) [2][3400/4632] lr: 9.7131e-02 eta: 1:48:27 time: 0.0955 data_time: 0.0071 memory: 1125 loss: 0.5679 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.5679 2023/04/17 22:55:59 - mmengine - INFO - Epoch(train) [2][3500/4632] lr: 9.7059e-02 eta: 1:48:15 time: 0.0957 data_time: 0.0072 memory: 1125 loss: 0.6798 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.6798 2023/04/17 22:56:08 - mmengine - INFO - Epoch(train) [2][3600/4632] lr: 9.6987e-02 eta: 1:48:05 time: 0.0989 data_time: 0.0072 memory: 1125 loss: 0.7197 top1_acc: 0.8125 top5_acc: 0.8125 loss_cls: 0.7197 2023/04/17 22:56:18 - mmengine - INFO - Epoch(train) [2][3700/4632] lr: 9.6914e-02 eta: 1:47:55 time: 0.0989 data_time: 0.0072 memory: 1125 loss: 0.5808 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.5808 2023/04/17 22:56:28 - mmengine - INFO - Epoch(train) [2][3800/4632] lr: 9.6841e-02 eta: 1:47:45 time: 0.0985 data_time: 0.0072 memory: 1125 loss: 0.5206 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.5206 2023/04/17 22:56:38 - mmengine - INFO - Epoch(train) [2][3900/4632] lr: 9.6766e-02 eta: 1:47:36 time: 0.0994 data_time: 0.0076 memory: 1125 loss: 0.6218 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.6218 2023/04/17 22:56:48 - mmengine - INFO - Epoch(train) [2][4000/4632] lr: 9.6691e-02 eta: 1:47:27 time: 0.0997 data_time: 0.0071 memory: 1125 loss: 0.4823 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4823 2023/04/17 22:56:58 - mmengine - INFO - Epoch(train) [2][4100/4632] lr: 9.6614e-02 eta: 1:47:18 time: 0.0996 data_time: 0.0072 memory: 1125 loss: 0.5295 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.5295 2023/04/17 22:57:08 - mmengine - INFO - Epoch(train) [2][4200/4632] lr: 9.6537e-02 eta: 1:47:09 time: 0.0997 data_time: 0.0076 memory: 1125 loss: 0.4707 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4707 2023/04/17 22:57:18 - mmengine - INFO - Epoch(train) [2][4300/4632] lr: 9.6459e-02 eta: 1:46:59 time: 0.0985 data_time: 0.0071 memory: 1125 loss: 0.6573 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.6573 2023/04/17 22:57:24 - mmengine - INFO - Exp name: stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230417_223936 2023/04/17 22:57:27 - mmengine - INFO - Epoch(train) [2][4400/4632] lr: 9.6381e-02 eta: 1:46:48 time: 0.0977 data_time: 0.0072 memory: 1125 loss: 0.5893 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.5893 2023/04/17 22:57:37 - mmengine - INFO - Epoch(train) [2][4500/4632] lr: 9.6301e-02 eta: 1:46:37 time: 0.0978 data_time: 0.0079 memory: 1125 loss: 0.6213 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.6213 2023/04/17 22:57:47 - mmengine - INFO - Epoch(train) [2][4600/4632] lr: 9.6221e-02 eta: 1:46:26 time: 0.0971 data_time: 0.0071 memory: 1125 loss: 0.5274 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.5274 2023/04/17 22:57:50 - mmengine - INFO - Exp name: stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230417_223936 2023/04/17 22:57:50 - mmengine - INFO - Epoch(train) [2][4632/4632] lr: 9.6195e-02 eta: 1:46:23 time: 0.0971 data_time: 0.0073 memory: 1125 loss: 0.5449 top1_acc: 0.8333 top5_acc: 0.8333 loss_cls: 0.5449 2023/04/17 22:57:50 - mmengine - INFO - Saving checkpoint at 2 epochs 2023/04/17 22:57:53 - mmengine - INFO - Epoch(val) [2][100/116] eta: 0:00:00 time: 0.0272 data_time: 0.0064 memory: 171 2023/04/17 22:57:54 - mmengine - INFO - Epoch(val) [2][116/116] acc/top1: 0.8342 acc/top5: 0.9635 acc/mean1: 0.8345data_time: 0.0063 time: 0.0270 2023/04/17 22:57:54 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/hukai/mmaction2/work_dirs/stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_1.pth is removed 2023/04/17 22:57:54 - mmengine - INFO - The best checkpoint with 0.8342 acc/top1 at 2 epoch is saved to best_acc/top1_epoch_2.pth. 2023/04/17 22:58:04 - mmengine - INFO - Epoch(train) [3][ 100/4632] lr: 9.6113e-02 eta: 1:46:15 time: 0.0997 data_time: 0.0076 memory: 1125 loss: 0.5243 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.5243 2023/04/17 22:58:14 - mmengine - INFO - Epoch(train) [3][ 200/4632] lr: 9.6031e-02 eta: 1:46:05 time: 0.0984 data_time: 0.0072 memory: 1125 loss: 0.4387 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4387 2023/04/17 22:58:24 - mmengine - INFO - Epoch(train) [3][ 300/4632] lr: 9.5948e-02 eta: 1:45:55 time: 0.0992 data_time: 0.0072 memory: 1125 loss: 0.5618 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.5618 2023/04/17 22:58:34 - mmengine - INFO - Epoch(train) [3][ 400/4632] lr: 9.5864e-02 eta: 1:45:46 time: 0.1000 data_time: 0.0076 memory: 1125 loss: 0.4931 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.4931 2023/04/17 22:58:44 - mmengine - INFO - Epoch(train) [3][ 500/4632] lr: 9.5779e-02 eta: 1:45:37 time: 0.0999 data_time: 0.0071 memory: 1125 loss: 0.6340 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.6340 2023/04/17 22:58:54 - mmengine - INFO - Epoch(train) [3][ 600/4632] lr: 9.5693e-02 eta: 1:45:28 time: 0.0990 data_time: 0.0073 memory: 1125 loss: 0.6295 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.6295 2023/04/17 22:59:04 - mmengine - INFO - Epoch(train) [3][ 700/4632] lr: 9.5607e-02 eta: 1:45:19 time: 0.0998 data_time: 0.0072 memory: 1125 loss: 0.5145 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.5145 2023/04/17 22:59:08 - mmengine - INFO - Exp name: stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230417_223936 2023/04/17 22:59:14 - mmengine - INFO - Epoch(train) [3][ 800/4632] lr: 9.5520e-02 eta: 1:45:10 time: 0.0996 data_time: 0.0072 memory: 1125 loss: 0.5472 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.5472 2023/04/17 22:59:24 - mmengine - INFO - Epoch(train) [3][ 900/4632] lr: 9.5431e-02 eta: 1:45:01 time: 0.1008 data_time: 0.0072 memory: 1125 loss: 0.4939 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4939 2023/04/17 22:59:34 - mmengine - INFO - Epoch(train) [3][1000/4632] lr: 9.5343e-02 eta: 1:44:52 time: 0.0998 data_time: 0.0072 memory: 1125 loss: 0.5236 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.5236 2023/04/17 22:59:44 - mmengine - INFO - Epoch(train) [3][1100/4632] lr: 9.5253e-02 eta: 1:44:43 time: 0.0994 data_time: 0.0073 memory: 1125 loss: 0.5210 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.5210 2023/04/17 22:59:54 - mmengine - INFO - Epoch(train) [3][1200/4632] lr: 9.5162e-02 eta: 1:44:34 time: 0.0999 data_time: 0.0073 memory: 1125 loss: 0.5120 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.5120 2023/04/17 23:00:04 - mmengine - INFO - Epoch(train) [3][1300/4632] lr: 9.5071e-02 eta: 1:44:25 time: 0.1003 data_time: 0.0072 memory: 1125 loss: 0.4362 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.4362 2023/04/17 23:00:14 - mmengine - INFO - Epoch(train) [3][1400/4632] lr: 9.4979e-02 eta: 1:44:16 time: 0.1011 data_time: 0.0072 memory: 1125 loss: 0.6068 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.6068 2023/04/17 23:00:24 - mmengine - INFO - Epoch(train) [3][1500/4632] lr: 9.4886e-02 eta: 1:44:08 time: 0.1014 data_time: 0.0072 memory: 1125 loss: 0.5177 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.5177 2023/04/17 23:00:34 - mmengine - INFO - Epoch(train) [3][1600/4632] lr: 9.4792e-02 eta: 1:43:58 time: 0.0971 data_time: 0.0072 memory: 1125 loss: 0.6137 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.6137 2023/04/17 23:00:44 - mmengine - INFO - Epoch(train) [3][1700/4632] lr: 9.4697e-02 eta: 1:43:48 time: 0.0969 data_time: 0.0073 memory: 1125 loss: 0.5196 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.5196 2023/04/17 23:00:47 - mmengine - INFO - Exp name: stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230417_223936 2023/04/17 23:00:54 - mmengine - INFO - Epoch(train) [3][1800/4632] lr: 9.4602e-02 eta: 1:43:37 time: 0.0999 data_time: 0.0073 memory: 1125 loss: 0.6334 top1_acc: 0.3750 top5_acc: 0.9375 loss_cls: 0.6334 2023/04/17 23:01:04 - mmengine - INFO - Epoch(train) [3][1900/4632] lr: 9.4506e-02 eta: 1:43:30 time: 0.1025 data_time: 0.0073 memory: 1125 loss: 0.5587 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.5587 2023/04/17 23:01:14 - mmengine - INFO - Epoch(train) [3][2000/4632] lr: 9.4409e-02 eta: 1:43:22 time: 0.1030 data_time: 0.0073 memory: 1125 loss: 0.5334 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.5334 2023/04/17 23:01:24 - mmengine - INFO - Epoch(train) [3][2100/4632] lr: 9.4311e-02 eta: 1:43:13 time: 0.0974 data_time: 0.0072 memory: 1125 loss: 0.5921 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.5921 2023/04/17 23:01:34 - mmengine - INFO - Epoch(train) [3][2200/4632] lr: 9.4212e-02 eta: 1:43:02 time: 0.0971 data_time: 0.0072 memory: 1125 loss: 0.4810 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.4810 2023/04/17 23:01:44 - mmengine - INFO - Epoch(train) [3][2300/4632] lr: 9.4113e-02 eta: 1:42:52 time: 0.0968 data_time: 0.0072 memory: 1125 loss: 0.6143 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.6143 2023/04/17 23:01:53 - mmengine - INFO - Epoch(train) [3][2400/4632] lr: 9.4013e-02 eta: 1:42:42 time: 0.0974 data_time: 0.0072 memory: 1125 loss: 0.4768 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.4768 2023/04/17 23:02:03 - mmengine - INFO - Epoch(train) [3][2500/4632] lr: 9.3912e-02 eta: 1:42:32 time: 0.1017 data_time: 0.0072 memory: 1125 loss: 0.4900 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4900 2023/04/17 23:02:13 - mmengine - INFO - Epoch(train) [3][2600/4632] lr: 9.3810e-02 eta: 1:42:23 time: 0.0997 data_time: 0.0071 memory: 1125 loss: 0.6450 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.6450 2023/04/17 23:02:23 - mmengine - INFO - Epoch(train) [3][2700/4632] lr: 9.3708e-02 eta: 1:42:14 time: 0.0992 data_time: 0.0073 memory: 1125 loss: 0.5370 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 0.5370 2023/04/17 23:02:27 - mmengine - INFO - Exp name: stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230417_223936 2023/04/17 23:02:33 - mmengine - INFO - Epoch(train) [3][2800/4632] lr: 9.3604e-02 eta: 1:42:04 time: 0.0997 data_time: 0.0072 memory: 1125 loss: 0.5201 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.5201 2023/04/17 23:02:43 - mmengine - INFO - Epoch(train) [3][2900/4632] lr: 9.3500e-02 eta: 1:41:54 time: 0.0979 data_time: 0.0072 memory: 1125 loss: 0.5047 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.5047 2023/04/17 23:02:53 - mmengine - INFO - Epoch(train) [3][3000/4632] lr: 9.3395e-02 eta: 1:41:44 time: 0.0986 data_time: 0.0075 memory: 1125 loss: 0.6731 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.6731 2023/04/17 23:03:03 - mmengine - INFO - Epoch(train) [3][3100/4632] lr: 9.3290e-02 eta: 1:41:34 time: 0.0986 data_time: 0.0073 memory: 1125 loss: 0.5392 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.5392 2023/04/17 23:03:13 - mmengine - INFO - Epoch(train) [3][3200/4632] lr: 9.3183e-02 eta: 1:41:24 time: 0.0986 data_time: 0.0072 memory: 1125 loss: 0.5583 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.5583 2023/04/17 23:03:22 - mmengine - INFO - Epoch(train) [3][3300/4632] lr: 9.3076e-02 eta: 1:41:14 time: 0.0976 data_time: 0.0073 memory: 1125 loss: 0.5781 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.5781 2023/04/17 23:03:32 - mmengine - INFO - Epoch(train) [3][3400/4632] lr: 9.2968e-02 eta: 1:41:04 time: 0.0984 data_time: 0.0074 memory: 1125 loss: 0.5689 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.5689 2023/04/17 23:03:42 - mmengine - INFO - Epoch(train) [3][3500/4632] lr: 9.2859e-02 eta: 1:40:54 time: 0.0977 data_time: 0.0072 memory: 1125 loss: 0.4338 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.4338 2023/04/17 23:03:52 - mmengine - INFO - Epoch(train) [3][3600/4632] lr: 9.2750e-02 eta: 1:40:43 time: 0.0978 data_time: 0.0072 memory: 1125 loss: 0.4777 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.4777 2023/04/17 23:04:02 - mmengine - INFO - Epoch(train) [3][3700/4632] lr: 9.2639e-02 eta: 1:40:33 time: 0.0988 data_time: 0.0073 memory: 1125 loss: 0.6045 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.6045 2023/04/17 23:04:05 - mmengine - INFO - Exp name: stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230417_223936 2023/04/17 23:04:11 - mmengine - INFO - Epoch(train) [3][3800/4632] lr: 9.2528e-02 eta: 1:40:23 time: 0.0977 data_time: 0.0072 memory: 1125 loss: 0.5034 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.5034 2023/04/17 23:04:21 - mmengine - INFO - Epoch(train) [3][3900/4632] lr: 9.2416e-02 eta: 1:40:13 time: 0.0978 data_time: 0.0073 memory: 1125 loss: 0.6874 top1_acc: 0.6250 top5_acc: 1.0000 loss_cls: 0.6874 2023/04/17 23:04:31 - mmengine - INFO - Epoch(train) [3][4000/4632] lr: 9.2304e-02 eta: 1:40:02 time: 0.0983 data_time: 0.0072 memory: 1125 loss: 0.6285 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.6285 2023/04/17 23:04:41 - mmengine - INFO - Epoch(train) [3][4100/4632] lr: 9.2190e-02 eta: 1:39:52 time: 0.0983 data_time: 0.0072 memory: 1125 loss: 0.5582 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 0.5582 2023/04/17 23:04:51 - mmengine - INFO - Epoch(train) [3][4200/4632] lr: 9.2076e-02 eta: 1:39:42 time: 0.0985 data_time: 0.0072 memory: 1125 loss: 0.5228 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.5228 2023/04/17 23:05:01 - mmengine - INFO - Epoch(train) [3][4300/4632] lr: 9.1961e-02 eta: 1:39:33 time: 0.0985 data_time: 0.0073 memory: 1125 loss: 0.5627 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.5627 2023/04/17 23:05:10 - mmengine - INFO - Epoch(train) [3][4400/4632] lr: 9.1846e-02 eta: 1:39:23 time: 0.0991 data_time: 0.0072 memory: 1125 loss: 0.4990 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.4990 2023/04/17 23:05:20 - mmengine - INFO - Epoch(train) [3][4500/4632] lr: 9.1729e-02 eta: 1:39:13 time: 0.0983 data_time: 0.0073 memory: 1125 loss: 0.5493 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.5493 2023/04/17 23:05:30 - mmengine - INFO - Epoch(train) [3][4600/4632] lr: 9.1612e-02 eta: 1:39:03 time: 0.0984 data_time: 0.0074 memory: 1125 loss: 0.5494 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.5494 2023/04/17 23:05:33 - mmengine - INFO - Exp name: stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230417_223936 2023/04/17 23:05:33 - mmengine - INFO - Epoch(train) [3][4632/4632] lr: 9.1575e-02 eta: 1:39:00 time: 0.0994 data_time: 0.0073 memory: 1125 loss: 0.5905 top1_acc: 0.5000 top5_acc: 0.6667 loss_cls: 0.5905 2023/04/17 23:05:33 - mmengine - INFO - Saving checkpoint at 3 epochs 2023/04/17 23:05:37 - mmengine - INFO - Epoch(val) [3][100/116] eta: 0:00:00 time: 0.0292 data_time: 0.0077 memory: 171 2023/04/17 23:05:37 - mmengine - INFO - Epoch(val) [3][116/116] acc/top1: 0.8441 acc/top5: 0.9688 acc/mean1: 0.8491data_time: 0.0069 time: 0.0289 2023/04/17 23:05:37 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/hukai/mmaction2/work_dirs/stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_2.pth is removed 2023/04/17 23:05:38 - mmengine - INFO - The best checkpoint with 0.8441 acc/top1 at 3 epoch is saved to best_acc/top1_epoch_3.pth. 2023/04/17 23:05:47 - mmengine - INFO - Epoch(train) [4][ 100/4632] lr: 9.1457e-02 eta: 1:38:49 time: 0.0968 data_time: 0.0074 memory: 1125 loss: 0.5530 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.5530 2023/04/17 23:05:48 - mmengine - INFO - Exp name: stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230417_223936 2023/04/17 23:05:57 - mmengine - INFO - Epoch(train) [4][ 200/4632] lr: 9.1338e-02 eta: 1:38:39 time: 0.0971 data_time: 0.0073 memory: 1125 loss: 0.5269 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.5269 2023/04/17 23:06:07 - mmengine - INFO - Epoch(train) [4][ 300/4632] lr: 9.1218e-02 eta: 1:38:29 time: 0.0998 data_time: 0.0073 memory: 1125 loss: 0.5548 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.5548 2023/04/17 23:06:17 - mmengine - INFO - Epoch(train) [4][ 400/4632] lr: 9.1098e-02 eta: 1:38:19 time: 0.0975 data_time: 0.0073 memory: 1125 loss: 0.4762 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.4762 2023/04/17 23:06:27 - mmengine - INFO - Epoch(train) [4][ 500/4632] lr: 9.0977e-02 eta: 1:38:08 time: 0.0975 data_time: 0.0073 memory: 1125 loss: 0.5339 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 0.5339 2023/04/17 23:06:36 - mmengine - INFO - Epoch(train) [4][ 600/4632] lr: 9.0855e-02 eta: 1:37:58 time: 0.0984 data_time: 0.0076 memory: 1125 loss: 0.4537 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.4537 2023/04/17 23:06:46 - mmengine - INFO - Epoch(train) [4][ 700/4632] lr: 9.0732e-02 eta: 1:37:49 time: 0.0986 data_time: 0.0072 memory: 1125 loss: 0.4867 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.4867 2023/04/17 23:06:56 - mmengine - INFO - Epoch(train) [4][ 800/4632] lr: 9.0609e-02 eta: 1:37:39 time: 0.0986 data_time: 0.0072 memory: 1125 loss: 0.5868 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.5868 2023/04/17 23:07:06 - mmengine - INFO - Epoch(train) [4][ 900/4632] lr: 9.0485e-02 eta: 1:37:29 time: 0.0994 data_time: 0.0073 memory: 1125 loss: 0.6544 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.6544 2023/04/17 23:07:16 - mmengine - INFO - Epoch(train) [4][1000/4632] lr: 9.0360e-02 eta: 1:37:20 time: 0.0990 data_time: 0.0072 memory: 1125 loss: 0.5074 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.5074 2023/04/17 23:07:26 - mmengine - INFO - Epoch(train) [4][1100/4632] lr: 9.0235e-02 eta: 1:37:10 time: 0.0991 data_time: 0.0072 memory: 1125 loss: 0.6055 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.6055 2023/04/17 23:07:26 - mmengine - INFO - Exp name: stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230417_223936 2023/04/17 23:07:36 - mmengine - INFO - Epoch(train) [4][1200/4632] lr: 9.0109e-02 eta: 1:37:01 time: 0.1018 data_time: 0.0073 memory: 1125 loss: 0.4690 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.4690 2023/04/17 23:07:46 - mmengine - INFO - Epoch(train) [4][1300/4632] lr: 8.9982e-02 eta: 1:36:53 time: 0.1046 data_time: 0.0073 memory: 1125 loss: 0.4819 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.4819 2023/04/17 23:07:57 - mmengine - INFO - Epoch(train) [4][1400/4632] lr: 8.9854e-02 eta: 1:36:45 time: 0.1046 data_time: 0.0073 memory: 1125 loss: 0.5944 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.5944 2023/04/17 23:08:07 - mmengine - INFO - Epoch(train) [4][1500/4632] lr: 8.9726e-02 eta: 1:36:36 time: 0.0990 data_time: 0.0074 memory: 1125 loss: 0.5893 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.5893 2023/04/17 23:08:17 - mmengine - INFO - Epoch(train) [4][1600/4632] lr: 8.9597e-02 eta: 1:36:26 time: 0.0985 data_time: 0.0073 memory: 1125 loss: 0.4826 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4826 2023/04/17 23:08:27 - mmengine - INFO - Epoch(train) [4][1700/4632] lr: 8.9467e-02 eta: 1:36:16 time: 0.0987 data_time: 0.0074 memory: 1125 loss: 0.4476 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4476 2023/04/17 23:08:37 - mmengine - INFO - Epoch(train) [4][1800/4632] lr: 8.9336e-02 eta: 1:36:07 time: 0.0995 data_time: 0.0074 memory: 1125 loss: 0.5649 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 0.5649 2023/04/17 23:08:46 - mmengine - INFO - Epoch(train) [4][1900/4632] lr: 8.9205e-02 eta: 1:35:57 time: 0.0991 data_time: 0.0077 memory: 1125 loss: 0.5055 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.5055 2023/04/17 23:08:56 - mmengine - INFO - Epoch(train) [4][2000/4632] lr: 8.9073e-02 eta: 1:35:47 time: 0.0986 data_time: 0.0074 memory: 1125 loss: 0.5408 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.5408 2023/04/17 23:09:06 - mmengine - INFO - Epoch(train) [4][2100/4632] lr: 8.8941e-02 eta: 1:35:37 time: 0.0988 data_time: 0.0075 memory: 1125 loss: 0.5658 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 0.5658 2023/04/17 23:09:07 - mmengine - INFO - Exp name: stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230417_223936 2023/04/17 23:09:17 - mmengine - INFO - Epoch(train) [4][2200/4632] lr: 8.8807e-02 eta: 1:35:30 time: 0.1053 data_time: 0.0073 memory: 1125 loss: 0.4774 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4774 2023/04/17 23:09:27 - mmengine - INFO - Epoch(train) [4][2300/4632] lr: 8.8673e-02 eta: 1:35:22 time: 0.1052 data_time: 0.0074 memory: 1125 loss: 0.5458 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.5458 2023/04/17 23:09:38 - mmengine - INFO - Epoch(train) [4][2400/4632] lr: 8.8539e-02 eta: 1:35:14 time: 0.0993 data_time: 0.0079 memory: 1125 loss: 0.4384 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.4384 2023/04/17 23:09:48 - mmengine - INFO - Epoch(train) [4][2500/4632] lr: 8.8403e-02 eta: 1:35:05 time: 0.1058 data_time: 0.0073 memory: 1125 loss: 0.4487 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.4487 2023/04/17 23:09:58 - mmengine - INFO - Epoch(train) [4][2600/4632] lr: 8.8267e-02 eta: 1:34:57 time: 0.0991 data_time: 0.0074 memory: 1125 loss: 0.6587 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.6587 2023/04/17 23:10:08 - mmengine - INFO - Epoch(train) [4][2700/4632] lr: 8.8130e-02 eta: 1:34:47 time: 0.0989 data_time: 0.0074 memory: 1125 loss: 0.5423 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.5423 2023/04/17 23:10:18 - mmengine - INFO - Epoch(train) [4][2800/4632] lr: 8.7993e-02 eta: 1:34:37 time: 0.0993 data_time: 0.0073 memory: 1125 loss: 0.6156 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 0.6156 2023/04/17 23:10:28 - mmengine - INFO - Epoch(train) [4][2900/4632] lr: 8.7855e-02 eta: 1:34:28 time: 0.0991 data_time: 0.0073 memory: 1125 loss: 0.5682 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 0.5682 2023/04/17 23:10:38 - mmengine - INFO - Epoch(train) [4][3000/4632] lr: 8.7716e-02 eta: 1:34:19 time: 0.1062 data_time: 0.0074 memory: 1125 loss: 0.5746 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.5746 2023/04/17 23:10:49 - mmengine - INFO - Epoch(train) [4][3100/4632] lr: 8.7577e-02 eta: 1:34:12 time: 0.1058 data_time: 0.0073 memory: 1125 loss: 0.5772 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.5772 2023/04/17 23:10:49 - mmengine - INFO - Exp name: stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230417_223936 2023/04/17 23:10:59 - mmengine - INFO - Epoch(train) [4][3200/4632] lr: 8.7436e-02 eta: 1:34:03 time: 0.0991 data_time: 0.0073 memory: 1125 loss: 0.4067 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4067 2023/04/17 23:11:09 - mmengine - INFO - Epoch(train) [4][3300/4632] lr: 8.7296e-02 eta: 1:33:54 time: 0.1006 data_time: 0.0073 memory: 1125 loss: 0.5614 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.5614 2023/04/17 23:11:19 - mmengine - INFO - Epoch(train) [4][3400/4632] lr: 8.7154e-02 eta: 1:33:44 time: 0.0989 data_time: 0.0074 memory: 1125 loss: 0.4757 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.4757 2023/04/17 23:11:29 - mmengine - INFO - Epoch(train) [4][3500/4632] lr: 8.7012e-02 eta: 1:33:35 time: 0.0993 data_time: 0.0073 memory: 1125 loss: 0.6087 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.6087 2023/04/17 23:11:39 - mmengine - INFO - Epoch(train) [4][3600/4632] lr: 8.6869e-02 eta: 1:33:25 time: 0.0990 data_time: 0.0075 memory: 1125 loss: 0.5132 top1_acc: 0.7500 top5_acc: 0.8125 loss_cls: 0.5132 2023/04/17 23:11:49 - mmengine - INFO - Epoch(train) [4][3700/4632] lr: 8.6726e-02 eta: 1:33:15 time: 0.0989 data_time: 0.0073 memory: 1125 loss: 0.4543 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4543 2023/04/17 23:11:59 - mmengine - INFO - Epoch(train) [4][3800/4632] lr: 8.6581e-02 eta: 1:33:05 time: 0.0990 data_time: 0.0080 memory: 1125 loss: 0.6937 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.6937 2023/04/17 23:12:09 - mmengine - INFO - Epoch(train) [4][3900/4632] lr: 8.6437e-02 eta: 1:32:55 time: 0.0993 data_time: 0.0075 memory: 1125 loss: 0.4933 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 0.4933 2023/04/17 23:12:19 - mmengine - INFO - Epoch(train) [4][4000/4632] lr: 8.6291e-02 eta: 1:32:45 time: 0.0995 data_time: 0.0073 memory: 1125 loss: 0.5072 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.5072 2023/04/17 23:12:29 - mmengine - INFO - Epoch(train) [4][4100/4632] lr: 8.6145e-02 eta: 1:32:36 time: 0.0991 data_time: 0.0074 memory: 1125 loss: 0.5354 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.5354 2023/04/17 23:12:29 - mmengine - INFO - Exp name: stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230417_223936 2023/04/17 23:12:39 - mmengine - INFO - Epoch(train) [4][4200/4632] lr: 8.5998e-02 eta: 1:32:26 time: 0.0987 data_time: 0.0073 memory: 1125 loss: 0.5904 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 0.5904 2023/04/17 23:12:49 - mmengine - INFO - Epoch(train) [4][4300/4632] lr: 8.5851e-02 eta: 1:32:16 time: 0.0990 data_time: 0.0073 memory: 1125 loss: 0.4508 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4508 2023/04/17 23:12:59 - mmengine - INFO - Epoch(train) [4][4400/4632] lr: 8.5703e-02 eta: 1:32:06 time: 0.0992 data_time: 0.0080 memory: 1125 loss: 0.4579 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4579 2023/04/17 23:13:09 - mmengine - INFO - Epoch(train) [4][4500/4632] lr: 8.5554e-02 eta: 1:31:56 time: 0.1025 data_time: 0.0074 memory: 1125 loss: 0.5504 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.5504 2023/04/17 23:13:18 - mmengine - INFO - Epoch(train) [4][4600/4632] lr: 8.5405e-02 eta: 1:31:46 time: 0.0991 data_time: 0.0073 memory: 1125 loss: 0.4826 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4826 2023/04/17 23:13:22 - mmengine - INFO - Exp name: stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230417_223936 2023/04/17 23:13:22 - mmengine - INFO - Epoch(train) [4][4632/4632] lr: 8.5357e-02 eta: 1:31:43 time: 0.0991 data_time: 0.0080 memory: 1125 loss: 0.5640 top1_acc: 0.5000 top5_acc: 0.8333 loss_cls: 0.5640 2023/04/17 23:13:22 - mmengine - INFO - Saving checkpoint at 4 epochs 2023/04/17 23:13:25 - mmengine - INFO - Epoch(val) [4][100/116] eta: 0:00:00 time: 0.0288 data_time: 0.0065 memory: 171 2023/04/17 23:13:26 - mmengine - INFO - Epoch(val) [4][116/116] acc/top1: 0.8497 acc/top5: 0.9691 acc/mean1: 0.8490data_time: 0.0063 time: 0.0275 2023/04/17 23:13:26 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/hukai/mmaction2/work_dirs/stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_3.pth is removed 2023/04/17 23:13:26 - mmengine - INFO - The best checkpoint with 0.8497 acc/top1 at 4 epoch is saved to best_acc/top1_epoch_4.pth. 2023/04/17 23:13:36 - mmengine - INFO - Epoch(train) [5][ 100/4632] lr: 8.5207e-02 eta: 1:31:34 time: 0.1005 data_time: 0.0080 memory: 1125 loss: 0.5235 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.5235 2023/04/17 23:13:46 - mmengine - INFO - Epoch(train) [5][ 200/4632] lr: 8.5056e-02 eta: 1:31:24 time: 0.1007 data_time: 0.0083 memory: 1125 loss: 0.5887 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.5887 2023/04/17 23:13:56 - mmengine - INFO - Epoch(train) [5][ 300/4632] lr: 8.4904e-02 eta: 1:31:15 time: 0.0997 data_time: 0.0074 memory: 1125 loss: 0.5907 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.5907 2023/04/17 23:14:06 - mmengine - INFO - Epoch(train) [5][ 400/4632] lr: 8.4752e-02 eta: 1:31:05 time: 0.0960 data_time: 0.0074 memory: 1125 loss: 0.4669 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.4669 2023/04/17 23:14:13 - mmengine - INFO - Exp name: stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230417_223936 2023/04/17 23:14:16 - mmengine - INFO - Epoch(train) [5][ 500/4632] lr: 8.4600e-02 eta: 1:30:54 time: 0.0959 data_time: 0.0072 memory: 1125 loss: 0.4794 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.4794 2023/04/17 23:14:25 - mmengine - INFO - Epoch(train) [5][ 600/4632] lr: 8.4446e-02 eta: 1:30:43 time: 0.0963 data_time: 0.0076 memory: 1125 loss: 0.4846 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.4846 2023/04/17 23:14:35 - mmengine - INFO - Epoch(train) [5][ 700/4632] lr: 8.4292e-02 eta: 1:30:32 time: 0.0959 data_time: 0.0073 memory: 1125 loss: 0.5161 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.5161 2023/04/17 23:14:45 - mmengine - INFO - Epoch(train) [5][ 800/4632] lr: 8.4138e-02 eta: 1:30:22 time: 0.0964 data_time: 0.0073 memory: 1125 loss: 0.6698 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.6698 2023/04/17 23:14:54 - mmengine - INFO - Epoch(train) [5][ 900/4632] lr: 8.3983e-02 eta: 1:30:11 time: 0.0963 data_time: 0.0073 memory: 1125 loss: 0.3848 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.3848 2023/04/17 23:15:04 - mmengine - INFO - Epoch(train) [5][1000/4632] lr: 8.3827e-02 eta: 1:30:01 time: 0.0978 data_time: 0.0073 memory: 1125 loss: 0.3589 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.3589 2023/04/17 23:15:14 - mmengine - INFO - Epoch(train) [5][1100/4632] lr: 8.3670e-02 eta: 1:29:51 time: 0.0979 data_time: 0.0073 memory: 1125 loss: 0.5078 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.5078 2023/04/17 23:15:24 - mmengine - INFO - Epoch(train) [5][1200/4632] lr: 8.3514e-02 eta: 1:29:41 time: 0.0980 data_time: 0.0073 memory: 1125 loss: 0.4378 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 0.4378 2023/04/17 23:15:33 - mmengine - INFO - Epoch(train) [5][1300/4632] lr: 8.3356e-02 eta: 1:29:31 time: 0.0970 data_time: 0.0073 memory: 1125 loss: 0.4925 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.4925 2023/04/17 23:15:43 - mmengine - INFO - Epoch(train) [5][1400/4632] lr: 8.3198e-02 eta: 1:29:20 time: 0.0972 data_time: 0.0073 memory: 1125 loss: 0.3772 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.3772 2023/04/17 23:15:50 - mmengine - INFO - Exp name: stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230417_223936 2023/04/17 23:15:53 - mmengine - INFO - Epoch(train) [5][1500/4632] lr: 8.3039e-02 eta: 1:29:10 time: 0.0970 data_time: 0.0073 memory: 1125 loss: 0.4274 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4274 2023/04/17 23:16:03 - mmengine - INFO - Epoch(train) [5][1600/4632] lr: 8.2880e-02 eta: 1:29:00 time: 0.0960 data_time: 0.0074 memory: 1125 loss: 0.4489 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.4489 2023/04/17 23:16:12 - mmengine - INFO - Epoch(train) [5][1700/4632] lr: 8.2720e-02 eta: 1:28:49 time: 0.0967 data_time: 0.0073 memory: 1125 loss: 0.4939 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.4939 2023/04/17 23:16:22 - mmengine - INFO - Epoch(train) [5][1800/4632] lr: 8.2559e-02 eta: 1:28:38 time: 0.0968 data_time: 0.0073 memory: 1125 loss: 0.4316 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.4316 2023/04/17 23:16:32 - mmengine - INFO - Epoch(train) [5][1900/4632] lr: 8.2398e-02 eta: 1:28:28 time: 0.0974 data_time: 0.0074 memory: 1125 loss: 0.4464 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.4464 2023/04/17 23:16:41 - mmengine - INFO - Epoch(train) [5][2000/4632] lr: 8.2236e-02 eta: 1:28:18 time: 0.0969 data_time: 0.0073 memory: 1125 loss: 0.5671 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.5671 2023/04/17 23:16:51 - mmengine - INFO - Epoch(train) [5][2100/4632] lr: 8.2074e-02 eta: 1:28:07 time: 0.0968 data_time: 0.0073 memory: 1125 loss: 0.5169 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.5169 2023/04/17 23:17:01 - mmengine - INFO - Epoch(train) [5][2200/4632] lr: 8.1911e-02 eta: 1:27:57 time: 0.0975 data_time: 0.0073 memory: 1125 loss: 0.5799 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.5799 2023/04/17 23:17:10 - mmengine - INFO - Epoch(train) [5][2300/4632] lr: 8.1748e-02 eta: 1:27:47 time: 0.0976 data_time: 0.0073 memory: 1125 loss: 0.4575 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.4575 2023/04/17 23:17:20 - mmengine - INFO - Epoch(train) [5][2400/4632] lr: 8.1583e-02 eta: 1:27:36 time: 0.0966 data_time: 0.0074 memory: 1125 loss: 0.4988 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.4988 2023/04/17 23:17:27 - mmengine - INFO - Exp name: stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230417_223936 2023/04/17 23:17:30 - mmengine - INFO - Epoch(train) [5][2500/4632] lr: 8.1419e-02 eta: 1:27:26 time: 0.0985 data_time: 0.0074 memory: 1125 loss: 0.4795 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4795 2023/04/17 23:17:40 - mmengine - INFO - Epoch(train) [5][2600/4632] lr: 8.1254e-02 eta: 1:27:16 time: 0.0964 data_time: 0.0073 memory: 1125 loss: 0.5106 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.5106 2023/04/17 23:17:49 - mmengine - INFO - Epoch(train) [5][2700/4632] lr: 8.1088e-02 eta: 1:27:05 time: 0.0965 data_time: 0.0073 memory: 1125 loss: 0.4172 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.4172 2023/04/17 23:17:59 - mmengine - INFO - Epoch(train) [5][2800/4632] lr: 8.0922e-02 eta: 1:26:55 time: 0.0962 data_time: 0.0074 memory: 1125 loss: 0.5003 top1_acc: 0.8750 top5_acc: 0.8750 loss_cls: 0.5003 2023/04/17 23:18:09 - mmengine - INFO - Epoch(train) [5][2900/4632] lr: 8.0755e-02 eta: 1:26:45 time: 0.1048 data_time: 0.0074 memory: 1125 loss: 0.3926 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3926 2023/04/17 23:18:19 - mmengine - INFO - Epoch(train) [5][3000/4632] lr: 8.0588e-02 eta: 1:26:35 time: 0.0984 data_time: 0.0081 memory: 1125 loss: 0.5518 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.5518 2023/04/17 23:18:29 - mmengine - INFO - Epoch(train) [5][3100/4632] lr: 8.0420e-02 eta: 1:26:25 time: 0.0987 data_time: 0.0074 memory: 1125 loss: 0.4469 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.4469 2023/04/17 23:18:38 - mmengine - INFO - Epoch(train) [5][3200/4632] lr: 8.0251e-02 eta: 1:26:15 time: 0.0997 data_time: 0.0083 memory: 1125 loss: 0.4812 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4812 2023/04/17 23:18:48 - mmengine - INFO - Epoch(train) [5][3300/4632] lr: 8.0082e-02 eta: 1:26:05 time: 0.0983 data_time: 0.0076 memory: 1125 loss: 0.5288 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.5288 2023/04/17 23:18:58 - mmengine - INFO - Epoch(train) [5][3400/4632] lr: 7.9912e-02 eta: 1:25:55 time: 0.0983 data_time: 0.0075 memory: 1125 loss: 0.4848 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 0.4848 2023/04/17 23:19:05 - mmengine - INFO - Exp name: stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230417_223936 2023/04/17 23:19:08 - mmengine - INFO - Epoch(train) [5][3500/4632] lr: 7.9742e-02 eta: 1:25:45 time: 0.0982 data_time: 0.0076 memory: 1125 loss: 0.6012 top1_acc: 0.6875 top5_acc: 0.8750 loss_cls: 0.6012 2023/04/17 23:19:18 - mmengine - INFO - Epoch(train) [5][3600/4632] lr: 7.9572e-02 eta: 1:25:35 time: 0.0982 data_time: 0.0074 memory: 1125 loss: 0.5613 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.5613 2023/04/17 23:19:28 - mmengine - INFO - Epoch(train) [5][3700/4632] lr: 7.9401e-02 eta: 1:25:25 time: 0.0983 data_time: 0.0074 memory: 1125 loss: 0.5246 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.5246 2023/04/17 23:19:37 - mmengine - INFO - Epoch(train) [5][3800/4632] lr: 7.9229e-02 eta: 1:25:15 time: 0.0987 data_time: 0.0079 memory: 1125 loss: 0.4272 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4272 2023/04/17 23:19:47 - mmengine - INFO - Epoch(train) [5][3900/4632] lr: 7.9057e-02 eta: 1:25:05 time: 0.0980 data_time: 0.0073 memory: 1125 loss: 0.4874 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4874 2023/04/17 23:19:57 - mmengine - INFO - Epoch(train) [5][4000/4632] lr: 7.8884e-02 eta: 1:24:55 time: 0.0982 data_time: 0.0074 memory: 1125 loss: 0.4990 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.4990 2023/04/17 23:20:07 - mmengine - INFO - Epoch(train) [5][4100/4632] lr: 7.8711e-02 eta: 1:24:45 time: 0.0982 data_time: 0.0073 memory: 1125 loss: 0.4729 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.4729 2023/04/17 23:20:17 - mmengine - INFO - Epoch(train) [5][4200/4632] lr: 7.8537e-02 eta: 1:24:35 time: 0.0979 data_time: 0.0073 memory: 1125 loss: 0.5160 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.5160 2023/04/17 23:20:26 - mmengine - INFO - Epoch(train) [5][4300/4632] lr: 7.8363e-02 eta: 1:24:25 time: 0.0979 data_time: 0.0074 memory: 1125 loss: 0.4807 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.4807 2023/04/17 23:20:36 - mmengine - INFO - Epoch(train) [5][4400/4632] lr: 7.8188e-02 eta: 1:24:15 time: 0.0977 data_time: 0.0075 memory: 1125 loss: 0.3935 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3935 2023/04/17 23:20:43 - mmengine - INFO - Exp name: stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230417_223936 2023/04/17 23:20:46 - mmengine - INFO - Epoch(train) [5][4500/4632] lr: 7.8012e-02 eta: 1:24:05 time: 0.0979 data_time: 0.0075 memory: 1125 loss: 0.5308 top1_acc: 0.7500 top5_acc: 0.8125 loss_cls: 0.5308 2023/04/17 23:20:56 - mmengine - INFO - Epoch(train) [5][4600/4632] lr: 7.7837e-02 eta: 1:23:55 time: 0.0977 data_time: 0.0073 memory: 1125 loss: 0.5817 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 0.5817 2023/04/17 23:20:59 - mmengine - INFO - Exp name: stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230417_223936 2023/04/17 23:20:59 - mmengine - INFO - Epoch(train) [5][4632/4632] lr: 7.7780e-02 eta: 1:23:52 time: 0.0990 data_time: 0.0075 memory: 1125 loss: 0.4207 top1_acc: 0.8333 top5_acc: 1.0000 loss_cls: 0.4207 2023/04/17 23:20:59 - mmengine - INFO - Saving checkpoint at 5 epochs 2023/04/17 23:21:03 - mmengine - INFO - Epoch(val) [5][100/116] eta: 0:00:00 time: 0.0290 data_time: 0.0076 memory: 171 2023/04/17 23:21:03 - mmengine - INFO - Epoch(val) [5][116/116] acc/top1: 0.8491 acc/top5: 0.9682 acc/mean1: 0.8570data_time: 0.0079 time: 0.0288 2023/04/17 23:21:13 - mmengine - INFO - Epoch(train) [6][ 100/4632] lr: 7.7604e-02 eta: 1:23:42 time: 0.1002 data_time: 0.0081 memory: 1125 loss: 0.5080 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.5080 2023/04/17 23:21:23 - mmengine - INFO - Epoch(train) [6][ 200/4632] lr: 7.7427e-02 eta: 1:23:33 time: 0.1013 data_time: 0.0074 memory: 1125 loss: 0.4495 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 0.4495 2023/04/17 23:21:33 - mmengine - INFO - Epoch(train) [6][ 300/4632] lr: 7.7249e-02 eta: 1:23:23 time: 0.1010 data_time: 0.0073 memory: 1125 loss: 0.5036 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.5036 2023/04/17 23:21:44 - mmengine - INFO - Epoch(train) [6][ 400/4632] lr: 7.7071e-02 eta: 1:23:14 time: 0.1009 data_time: 0.0074 memory: 1125 loss: 0.6716 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.6716 2023/04/17 23:21:54 - mmengine - INFO - Epoch(train) [6][ 500/4632] lr: 7.6893e-02 eta: 1:23:05 time: 0.0995 data_time: 0.0074 memory: 1125 loss: 0.4972 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.4972 2023/04/17 23:22:04 - mmengine - INFO - Epoch(train) [6][ 600/4632] lr: 7.6714e-02 eta: 1:22:55 time: 0.1003 data_time: 0.0073 memory: 1125 loss: 0.5144 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.5144 2023/04/17 23:22:14 - mmengine - INFO - Epoch(train) [6][ 700/4632] lr: 7.6535e-02 eta: 1:22:46 time: 0.1015 data_time: 0.0073 memory: 1125 loss: 0.4509 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.4509 2023/04/17 23:22:24 - mmengine - INFO - Epoch(train) [6][ 800/4632] lr: 7.6355e-02 eta: 1:22:36 time: 0.1005 data_time: 0.0074 memory: 1125 loss: 0.4404 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4404 2023/04/17 23:22:28 - mmengine - INFO - Exp name: stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230417_223936 2023/04/17 23:22:34 - mmengine - INFO - Epoch(train) [6][ 900/4632] lr: 7.6174e-02 eta: 1:22:27 time: 0.0993 data_time: 0.0073 memory: 1125 loss: 0.4926 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4926 2023/04/17 23:22:44 - mmengine - INFO - Epoch(train) [6][1000/4632] lr: 7.5994e-02 eta: 1:22:17 time: 0.0983 data_time: 0.0073 memory: 1125 loss: 0.5100 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.5100 2023/04/17 23:22:54 - mmengine - INFO - Epoch(train) [6][1100/4632] lr: 7.5812e-02 eta: 1:22:07 time: 0.0981 data_time: 0.0074 memory: 1125 loss: 0.4173 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4173 2023/04/17 23:23:04 - mmengine - INFO - Epoch(train) [6][1200/4632] lr: 7.5631e-02 eta: 1:21:57 time: 0.1025 data_time: 0.0074 memory: 1125 loss: 0.4070 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.4070 2023/04/17 23:23:14 - mmengine - INFO - Epoch(train) [6][1300/4632] lr: 7.5448e-02 eta: 1:21:48 time: 0.1013 data_time: 0.0073 memory: 1125 loss: 0.4225 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.4225 2023/04/17 23:23:24 - mmengine - INFO - Epoch(train) [6][1400/4632] lr: 7.5266e-02 eta: 1:21:38 time: 0.1004 data_time: 0.0073 memory: 1125 loss: 0.4136 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.4136 2023/04/17 23:23:34 - mmengine - INFO - Epoch(train) [6][1500/4632] lr: 7.5083e-02 eta: 1:21:29 time: 0.1009 data_time: 0.0074 memory: 1125 loss: 0.4168 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4168 2023/04/17 23:23:44 - mmengine - INFO - Epoch(train) [6][1600/4632] lr: 7.4899e-02 eta: 1:21:19 time: 0.0991 data_time: 0.0073 memory: 1125 loss: 0.5327 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.5327 2023/04/17 23:23:54 - mmengine - INFO - Epoch(train) [6][1700/4632] lr: 7.4715e-02 eta: 1:21:09 time: 0.1007 data_time: 0.0074 memory: 1125 loss: 0.6183 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.6183 2023/04/17 23:24:04 - mmengine - INFO - Epoch(train) [6][1800/4632] lr: 7.4530e-02 eta: 1:21:00 time: 0.1006 data_time: 0.0073 memory: 1125 loss: 0.5253 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.5253 2023/04/17 23:24:08 - mmengine - INFO - Exp name: stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230417_223936 2023/04/17 23:24:14 - mmengine - INFO - Epoch(train) [6][1900/4632] lr: 7.4346e-02 eta: 1:20:50 time: 0.1000 data_time: 0.0073 memory: 1125 loss: 0.5689 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 0.5689 2023/04/17 23:24:24 - mmengine - INFO - Epoch(train) [6][2000/4632] lr: 7.4160e-02 eta: 1:20:40 time: 0.1001 data_time: 0.0074 memory: 1125 loss: 0.5133 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.5133 2023/04/17 23:24:34 - mmengine - INFO - Epoch(train) [6][2100/4632] lr: 7.3974e-02 eta: 1:20:31 time: 0.0984 data_time: 0.0074 memory: 1125 loss: 0.5101 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.5101 2023/04/17 23:24:44 - mmengine - INFO - Epoch(train) [6][2200/4632] lr: 7.3788e-02 eta: 1:20:21 time: 0.0976 data_time: 0.0073 memory: 1125 loss: 0.6046 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.6046 2023/04/17 23:24:54 - mmengine - INFO - Epoch(train) [6][2300/4632] lr: 7.3602e-02 eta: 1:20:10 time: 0.0982 data_time: 0.0073 memory: 1125 loss: 0.4913 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.4913 2023/04/17 23:25:03 - mmengine - INFO - Epoch(train) [6][2400/4632] lr: 7.3415e-02 eta: 1:20:01 time: 0.0992 data_time: 0.0074 memory: 1125 loss: 0.4088 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.4088 2023/04/17 23:25:13 - mmengine - INFO - Epoch(train) [6][2500/4632] lr: 7.3227e-02 eta: 1:19:51 time: 0.0989 data_time: 0.0074 memory: 1125 loss: 0.4336 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.4336 2023/04/17 23:25:23 - mmengine - INFO - Epoch(train) [6][2600/4632] lr: 7.3039e-02 eta: 1:19:41 time: 0.0989 data_time: 0.0074 memory: 1125 loss: 0.4695 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.4695 2023/04/17 23:25:33 - mmengine - INFO - Epoch(train) [6][2700/4632] lr: 7.2851e-02 eta: 1:19:31 time: 0.0988 data_time: 0.0074 memory: 1125 loss: 0.4460 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.4460 2023/04/17 23:25:43 - mmengine - INFO - Epoch(train) [6][2800/4632] lr: 7.2662e-02 eta: 1:19:21 time: 0.0982 data_time: 0.0074 memory: 1125 loss: 0.3856 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3856 2023/04/17 23:25:47 - mmengine - INFO - Exp name: stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230417_223936 2023/04/17 23:25:53 - mmengine - INFO - Epoch(train) [6][2900/4632] lr: 7.2473e-02 eta: 1:19:11 time: 0.0982 data_time: 0.0074 memory: 1125 loss: 0.5385 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.5385 2023/04/17 23:26:03 - mmengine - INFO - Epoch(train) [6][3000/4632] lr: 7.2283e-02 eta: 1:19:01 time: 0.0979 data_time: 0.0075 memory: 1125 loss: 0.4643 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4643 2023/04/17 23:26:13 - mmengine - INFO - Epoch(train) [6][3100/4632] lr: 7.2094e-02 eta: 1:18:51 time: 0.0988 data_time: 0.0073 memory: 1125 loss: 0.5062 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.5062 2023/04/17 23:26:22 - mmengine - INFO - Epoch(train) [6][3200/4632] lr: 7.1903e-02 eta: 1:18:41 time: 0.0978 data_time: 0.0074 memory: 1125 loss: 0.3974 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3974 2023/04/17 23:26:32 - mmengine - INFO - Epoch(train) [6][3300/4632] lr: 7.1712e-02 eta: 1:18:31 time: 0.0976 data_time: 0.0074 memory: 1125 loss: 0.5541 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.5541 2023/04/17 23:26:42 - mmengine - INFO - Epoch(train) [6][3400/4632] lr: 7.1521e-02 eta: 1:18:21 time: 0.0969 data_time: 0.0076 memory: 1125 loss: 0.4576 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.4576 2023/04/17 23:26:52 - mmengine - INFO - Epoch(train) [6][3500/4632] lr: 7.1330e-02 eta: 1:18:11 time: 0.0977 data_time: 0.0075 memory: 1125 loss: 0.5370 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.5370 2023/04/17 23:27:02 - mmengine - INFO - Epoch(train) [6][3600/4632] lr: 7.1138e-02 eta: 1:18:01 time: 0.1011 data_time: 0.0079 memory: 1125 loss: 0.4749 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4749 2023/04/17 23:27:12 - mmengine - INFO - Epoch(train) [6][3700/4632] lr: 7.0946e-02 eta: 1:17:51 time: 0.1013 data_time: 0.0077 memory: 1125 loss: 0.5462 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.5462 2023/04/17 23:27:22 - mmengine - INFO - Epoch(train) [6][3800/4632] lr: 7.0753e-02 eta: 1:17:42 time: 0.0995 data_time: 0.0090 memory: 1125 loss: 0.5516 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.5516 2023/04/17 23:27:26 - mmengine - INFO - Exp name: stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230417_223936 2023/04/17 23:27:32 - mmengine - INFO - Epoch(train) [6][3900/4632] lr: 7.0560e-02 eta: 1:17:32 time: 0.1004 data_time: 0.0083 memory: 1125 loss: 0.4969 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 0.4969 2023/04/17 23:27:42 - mmengine - INFO - Epoch(train) [6][4000/4632] lr: 7.0367e-02 eta: 1:17:22 time: 0.1001 data_time: 0.0077 memory: 1125 loss: 0.5046 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.5046 2023/04/17 23:27:52 - mmengine - INFO - Epoch(train) [6][4100/4632] lr: 7.0173e-02 eta: 1:17:13 time: 0.0993 data_time: 0.0091 memory: 1125 loss: 0.4543 top1_acc: 0.8750 top5_acc: 0.8750 loss_cls: 0.4543 2023/04/17 23:28:02 - mmengine - INFO - Epoch(train) [6][4200/4632] lr: 6.9979e-02 eta: 1:17:03 time: 0.1000 data_time: 0.0091 memory: 1125 loss: 0.4724 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4724 2023/04/17 23:28:12 - mmengine - INFO - Epoch(train) [6][4300/4632] lr: 6.9784e-02 eta: 1:16:53 time: 0.1001 data_time: 0.0083 memory: 1125 loss: 0.5578 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.5578 2023/04/17 23:28:22 - mmengine - INFO - Epoch(train) [6][4400/4632] lr: 6.9589e-02 eta: 1:16:43 time: 0.0993 data_time: 0.0085 memory: 1125 loss: 0.5397 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.5397 2023/04/17 23:28:32 - mmengine - INFO - Epoch(train) [6][4500/4632] lr: 6.9394e-02 eta: 1:16:34 time: 0.1010 data_time: 0.0081 memory: 1125 loss: 0.5769 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.5769 2023/04/17 23:28:42 - mmengine - INFO - Epoch(train) [6][4600/4632] lr: 6.9199e-02 eta: 1:16:24 time: 0.1008 data_time: 0.0083 memory: 1125 loss: 0.4407 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4407 2023/04/17 23:28:45 - mmengine - INFO - Exp name: stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230417_223936 2023/04/17 23:28:45 - mmengine - INFO - Epoch(train) [6][4632/4632] lr: 6.9136e-02 eta: 1:16:21 time: 0.1011 data_time: 0.0083 memory: 1125 loss: 0.3816 top1_acc: 0.6667 top5_acc: 1.0000 loss_cls: 0.3816 2023/04/17 23:28:45 - mmengine - INFO - Saving checkpoint at 6 epochs 2023/04/17 23:28:48 - mmengine - INFO - Epoch(val) [6][100/116] eta: 0:00:00 time: 0.0279 data_time: 0.0067 memory: 171 2023/04/17 23:28:49 - mmengine - INFO - Epoch(val) [6][116/116] acc/top1: 0.8595 acc/top5: 0.9711 acc/mean1: 0.8666data_time: 0.0066 time: 0.0275 2023/04/17 23:28:49 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/hukai/mmaction2/work_dirs/stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_4.pth is removed 2023/04/17 23:28:49 - mmengine - INFO - The best checkpoint with 0.8595 acc/top1 at 6 epoch is saved to best_acc/top1_epoch_6.pth. 2023/04/17 23:28:59 - mmengine - INFO - Epoch(train) [7][ 100/4632] lr: 6.8940e-02 eta: 1:16:11 time: 0.0983 data_time: 0.0074 memory: 1125 loss: 0.4844 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.4844 2023/04/17 23:29:09 - mmengine - INFO - Epoch(train) [7][ 200/4632] lr: 6.8744e-02 eta: 1:16:01 time: 0.0980 data_time: 0.0076 memory: 1125 loss: 0.5323 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.5323 2023/04/17 23:29:10 - mmengine - INFO - Exp name: stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230417_223936 2023/04/17 23:29:19 - mmengine - INFO - Epoch(train) [7][ 300/4632] lr: 6.8547e-02 eta: 1:15:51 time: 0.0973 data_time: 0.0077 memory: 1125 loss: 0.5068 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.5068 2023/04/17 23:29:29 - mmengine - INFO - Epoch(train) [7][ 400/4632] lr: 6.8350e-02 eta: 1:15:41 time: 0.0971 data_time: 0.0074 memory: 1125 loss: 0.4232 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4232 2023/04/17 23:29:38 - mmengine - INFO - Epoch(train) [7][ 500/4632] lr: 6.8153e-02 eta: 1:15:31 time: 0.1007 data_time: 0.0074 memory: 1125 loss: 0.4904 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.4904 2023/04/17 23:29:48 - mmengine - INFO - Epoch(train) [7][ 600/4632] lr: 6.7955e-02 eta: 1:15:21 time: 0.1006 data_time: 0.0074 memory: 1125 loss: 0.4636 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4636 2023/04/17 23:29:58 - mmengine - INFO - Epoch(train) [7][ 700/4632] lr: 6.7757e-02 eta: 1:15:12 time: 0.1000 data_time: 0.0074 memory: 1125 loss: 0.5260 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.5260 2023/04/17 23:30:08 - mmengine - INFO - Epoch(train) [7][ 800/4632] lr: 6.7559e-02 eta: 1:15:02 time: 0.0975 data_time: 0.0078 memory: 1125 loss: 0.5220 top1_acc: 0.5625 top5_acc: 0.8125 loss_cls: 0.5220 2023/04/17 23:30:18 - mmengine - INFO - Epoch(train) [7][ 900/4632] lr: 6.7360e-02 eta: 1:14:51 time: 0.0974 data_time: 0.0074 memory: 1125 loss: 0.4924 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.4924 2023/04/17 23:30:28 - mmengine - INFO - Epoch(train) [7][1000/4632] lr: 6.7161e-02 eta: 1:14:41 time: 0.0967 data_time: 0.0074 memory: 1125 loss: 0.4262 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4262 2023/04/17 23:30:37 - mmengine - INFO - Epoch(train) [7][1100/4632] lr: 6.6962e-02 eta: 1:14:31 time: 0.0966 data_time: 0.0074 memory: 1125 loss: 0.4616 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 0.4616 2023/04/17 23:30:47 - mmengine - INFO - Epoch(train) [7][1200/4632] lr: 6.6763e-02 eta: 1:14:21 time: 0.0966 data_time: 0.0074 memory: 1125 loss: 0.4446 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4446 2023/04/17 23:30:48 - mmengine - INFO - Exp name: stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230417_223936 2023/04/17 23:30:57 - mmengine - INFO - Epoch(train) [7][1300/4632] lr: 6.6563e-02 eta: 1:14:11 time: 0.0967 data_time: 0.0074 memory: 1125 loss: 0.3911 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3911 2023/04/17 23:31:06 - mmengine - INFO - Epoch(train) [7][1400/4632] lr: 6.6363e-02 eta: 1:14:01 time: 0.0968 data_time: 0.0074 memory: 1125 loss: 0.5580 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.5580 2023/04/17 23:31:16 - mmengine - INFO - Epoch(train) [7][1500/4632] lr: 6.6162e-02 eta: 1:13:50 time: 0.0972 data_time: 0.0074 memory: 1125 loss: 0.5641 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.5641 2023/04/17 23:31:26 - mmengine - INFO - Epoch(train) [7][1600/4632] lr: 6.5962e-02 eta: 1:13:40 time: 0.0971 data_time: 0.0074 memory: 1125 loss: 0.4921 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 0.4921 2023/04/17 23:31:36 - mmengine - INFO - Epoch(train) [7][1700/4632] lr: 6.5761e-02 eta: 1:13:30 time: 0.0970 data_time: 0.0074 memory: 1125 loss: 0.5768 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 0.5768 2023/04/17 23:31:45 - mmengine - INFO - Epoch(train) [7][1800/4632] lr: 6.5559e-02 eta: 1:13:20 time: 0.0989 data_time: 0.0075 memory: 1125 loss: 0.5691 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.5691 2023/04/17 23:31:55 - mmengine - INFO - Epoch(train) [7][1900/4632] lr: 6.5358e-02 eta: 1:13:10 time: 0.0998 data_time: 0.0074 memory: 1125 loss: 0.4958 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.4958 2023/04/17 23:32:05 - mmengine - INFO - Epoch(train) [7][2000/4632] lr: 6.5156e-02 eta: 1:13:00 time: 0.0994 data_time: 0.0074 memory: 1125 loss: 0.4432 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.4432 2023/04/17 23:32:15 - mmengine - INFO - Epoch(train) [7][2100/4632] lr: 6.4954e-02 eta: 1:12:51 time: 0.0992 data_time: 0.0073 memory: 1125 loss: 0.4453 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 0.4453 2023/04/17 23:32:25 - mmengine - INFO - Epoch(train) [7][2200/4632] lr: 6.4751e-02 eta: 1:12:41 time: 0.0989 data_time: 0.0073 memory: 1125 loss: 0.5828 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.5828 2023/04/17 23:32:26 - mmengine - INFO - Exp name: stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230417_223936 2023/04/17 23:32:35 - mmengine - INFO - Epoch(train) [7][2300/4632] lr: 6.4549e-02 eta: 1:12:31 time: 0.0994 data_time: 0.0073 memory: 1125 loss: 0.4730 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4730 2023/04/17 23:32:45 - mmengine - INFO - Epoch(train) [7][2400/4632] lr: 6.4346e-02 eta: 1:12:21 time: 0.0998 data_time: 0.0074 memory: 1125 loss: 0.4768 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4768 2023/04/17 23:32:55 - mmengine - INFO - Epoch(train) [7][2500/4632] lr: 6.4143e-02 eta: 1:12:12 time: 0.1006 data_time: 0.0075 memory: 1125 loss: 0.3947 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3947 2023/04/17 23:33:05 - mmengine - INFO - Epoch(train) [7][2600/4632] lr: 6.3939e-02 eta: 1:12:02 time: 0.1010 data_time: 0.0081 memory: 1125 loss: 0.4905 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.4905 2023/04/17 23:33:15 - mmengine - INFO - Epoch(train) [7][2700/4632] lr: 6.3736e-02 eta: 1:11:53 time: 0.1029 data_time: 0.0074 memory: 1125 loss: 0.4170 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4170 2023/04/17 23:33:26 - mmengine - INFO - Epoch(train) [7][2800/4632] lr: 6.3532e-02 eta: 1:11:43 time: 0.1014 data_time: 0.0074 memory: 1125 loss: 0.4432 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4432 2023/04/17 23:33:36 - mmengine - INFO - Epoch(train) [7][2900/4632] lr: 6.3327e-02 eta: 1:11:34 time: 0.1012 data_time: 0.0074 memory: 1125 loss: 0.4658 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4658 2023/04/17 23:33:46 - mmengine - INFO - Epoch(train) [7][3000/4632] lr: 6.3123e-02 eta: 1:11:24 time: 0.1006 data_time: 0.0075 memory: 1125 loss: 0.5019 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.5019 2023/04/17 23:33:56 - mmengine - INFO - Epoch(train) [7][3100/4632] lr: 6.2918e-02 eta: 1:11:14 time: 0.1008 data_time: 0.0074 memory: 1125 loss: 0.3918 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3918 2023/04/17 23:34:06 - mmengine - INFO - Epoch(train) [7][3200/4632] lr: 6.2714e-02 eta: 1:11:04 time: 0.0984 data_time: 0.0074 memory: 1125 loss: 0.5015 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.5015 2023/04/17 23:34:07 - mmengine - INFO - Exp name: stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230417_223936 2023/04/17 23:34:16 - mmengine - INFO - Epoch(train) [7][3300/4632] lr: 6.2508e-02 eta: 1:10:54 time: 0.0993 data_time: 0.0074 memory: 1125 loss: 0.4379 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.4379 2023/04/17 23:34:25 - mmengine - INFO - Epoch(train) [7][3400/4632] lr: 6.2303e-02 eta: 1:10:44 time: 0.0979 data_time: 0.0074 memory: 1125 loss: 0.4429 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4429 2023/04/17 23:34:35 - mmengine - INFO - Epoch(train) [7][3500/4632] lr: 6.2098e-02 eta: 1:10:34 time: 0.0973 data_time: 0.0074 memory: 1125 loss: 0.4413 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.4413 2023/04/17 23:34:45 - mmengine - INFO - Epoch(train) [7][3600/4632] lr: 6.1892e-02 eta: 1:10:24 time: 0.0972 data_time: 0.0074 memory: 1125 loss: 0.3491 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.3491 2023/04/17 23:34:55 - mmengine - INFO - Epoch(train) [7][3700/4632] lr: 6.1686e-02 eta: 1:10:14 time: 0.0975 data_time: 0.0074 memory: 1125 loss: 0.4210 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.4210 2023/04/17 23:35:05 - mmengine - INFO - Epoch(train) [7][3800/4632] lr: 6.1480e-02 eta: 1:10:04 time: 0.0980 data_time: 0.0080 memory: 1125 loss: 0.4129 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.4129 2023/04/17 23:35:15 - mmengine - INFO - Epoch(train) [7][3900/4632] lr: 6.1273e-02 eta: 1:09:54 time: 0.0980 data_time: 0.0074 memory: 1125 loss: 0.4906 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.4906 2023/04/17 23:35:24 - mmengine - INFO - Epoch(train) [7][4000/4632] lr: 6.1067e-02 eta: 1:09:44 time: 0.1002 data_time: 0.0074 memory: 1125 loss: 0.5070 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.5070 2023/04/17 23:35:34 - mmengine - INFO - Epoch(train) [7][4100/4632] lr: 6.0860e-02 eta: 1:09:35 time: 0.0983 data_time: 0.0081 memory: 1125 loss: 0.5082 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.5082 2023/04/17 23:35:44 - mmengine - INFO - Epoch(train) [7][4200/4632] lr: 6.0653e-02 eta: 1:09:25 time: 0.0987 data_time: 0.0081 memory: 1125 loss: 0.4891 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.4891 2023/04/17 23:35:45 - mmengine - INFO - Exp name: stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230417_223936 2023/04/17 23:35:54 - mmengine - INFO - Epoch(train) [7][4300/4632] lr: 6.0446e-02 eta: 1:09:15 time: 0.0981 data_time: 0.0074 memory: 1125 loss: 0.4185 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 0.4185 2023/04/17 23:36:04 - mmengine - INFO - Epoch(train) [7][4400/4632] lr: 6.0238e-02 eta: 1:09:05 time: 0.0985 data_time: 0.0073 memory: 1125 loss: 0.5260 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.5260 2023/04/17 23:36:14 - mmengine - INFO - Epoch(train) [7][4500/4632] lr: 6.0031e-02 eta: 1:08:55 time: 0.0990 data_time: 0.0081 memory: 1125 loss: 0.5878 top1_acc: 0.6250 top5_acc: 0.9375 loss_cls: 0.5878 2023/04/17 23:36:24 - mmengine - INFO - Epoch(train) [7][4600/4632] lr: 5.9823e-02 eta: 1:08:45 time: 0.0974 data_time: 0.0082 memory: 1125 loss: 0.4212 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 0.4212 2023/04/17 23:36:27 - mmengine - INFO - Exp name: stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230417_223936 2023/04/17 23:36:27 - mmengine - INFO - Epoch(train) [7][4632/4632] lr: 5.9757e-02 eta: 1:08:42 time: 0.0976 data_time: 0.0081 memory: 1125 loss: 0.4772 top1_acc: 0.8333 top5_acc: 1.0000 loss_cls: 0.4772 2023/04/17 23:36:27 - mmengine - INFO - Saving checkpoint at 7 epochs 2023/04/17 23:36:30 - mmengine - INFO - Epoch(val) [7][100/116] eta: 0:00:00 time: 0.0279 data_time: 0.0067 memory: 171 2023/04/17 23:36:31 - mmengine - INFO - Epoch(val) [7][116/116] acc/top1: 0.8652 acc/top5: 0.9726 acc/mean1: 0.8663data_time: 0.0063 time: 0.0272 2023/04/17 23:36:31 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/hukai/mmaction2/work_dirs/stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_6.pth is removed 2023/04/17 23:36:31 - mmengine - INFO - The best checkpoint with 0.8652 acc/top1 at 7 epoch is saved to best_acc/top1_epoch_7.pth. 2023/04/17 23:36:41 - mmengine - INFO - Epoch(train) [8][ 100/4632] lr: 5.9549e-02 eta: 1:08:32 time: 0.0983 data_time: 0.0080 memory: 1125 loss: 0.3750 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3750 2023/04/17 23:36:51 - mmengine - INFO - Epoch(train) [8][ 200/4632] lr: 5.9340e-02 eta: 1:08:22 time: 0.0984 data_time: 0.0082 memory: 1125 loss: 0.3993 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 0.3993 2023/04/17 23:37:01 - mmengine - INFO - Epoch(train) [8][ 300/4632] lr: 5.9132e-02 eta: 1:08:12 time: 0.0993 data_time: 0.0078 memory: 1125 loss: 0.4866 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4866 2023/04/17 23:37:11 - mmengine - INFO - Epoch(train) [8][ 400/4632] lr: 5.8924e-02 eta: 1:08:02 time: 0.0986 data_time: 0.0081 memory: 1125 loss: 0.5655 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.5655 2023/04/17 23:37:21 - mmengine - INFO - Epoch(train) [8][ 500/4632] lr: 5.8715e-02 eta: 1:07:52 time: 0.0987 data_time: 0.0075 memory: 1125 loss: 0.4504 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4504 2023/04/17 23:37:28 - mmengine - INFO - Exp name: stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230417_223936 2023/04/17 23:37:31 - mmengine - INFO - Epoch(train) [8][ 600/4632] lr: 5.8506e-02 eta: 1:07:42 time: 0.0993 data_time: 0.0075 memory: 1125 loss: 0.4429 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4429 2023/04/17 23:37:40 - mmengine - INFO - Epoch(train) [8][ 700/4632] lr: 5.8297e-02 eta: 1:07:32 time: 0.0985 data_time: 0.0074 memory: 1125 loss: 0.4874 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.4874 2023/04/17 23:37:50 - mmengine - INFO - Epoch(train) [8][ 800/4632] lr: 5.8088e-02 eta: 1:07:22 time: 0.0984 data_time: 0.0075 memory: 1125 loss: 0.4552 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4552 2023/04/17 23:38:00 - mmengine - INFO - Epoch(train) [8][ 900/4632] lr: 5.7879e-02 eta: 1:07:13 time: 0.0992 data_time: 0.0074 memory: 1125 loss: 0.3778 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.3778 2023/04/17 23:38:10 - mmengine - INFO - Epoch(train) [8][1000/4632] lr: 5.7670e-02 eta: 1:07:03 time: 0.0996 data_time: 0.0074 memory: 1125 loss: 0.4287 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.4287 2023/04/17 23:38:20 - mmengine - INFO - Epoch(train) [8][1100/4632] lr: 5.7460e-02 eta: 1:06:53 time: 0.1004 data_time: 0.0081 memory: 1125 loss: 0.5305 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 0.5305 2023/04/17 23:38:30 - mmengine - INFO - Epoch(train) [8][1200/4632] lr: 5.7251e-02 eta: 1:06:43 time: 0.1004 data_time: 0.0082 memory: 1125 loss: 0.4540 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.4540 2023/04/17 23:38:40 - mmengine - INFO - Epoch(train) [8][1300/4632] lr: 5.7041e-02 eta: 1:06:33 time: 0.0985 data_time: 0.0074 memory: 1125 loss: 0.3576 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.3576 2023/04/17 23:38:50 - mmengine - INFO - Epoch(train) [8][1400/4632] lr: 5.6831e-02 eta: 1:06:23 time: 0.0976 data_time: 0.0074 memory: 1125 loss: 0.4723 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4723 2023/04/17 23:39:00 - mmengine - INFO - Epoch(train) [8][1500/4632] lr: 5.6621e-02 eta: 1:06:13 time: 0.0977 data_time: 0.0074 memory: 1125 loss: 0.5711 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 0.5711 2023/04/17 23:39:07 - mmengine - INFO - Exp name: stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230417_223936 2023/04/17 23:39:09 - mmengine - INFO - Epoch(train) [8][1600/4632] lr: 5.6411e-02 eta: 1:06:03 time: 0.0985 data_time: 0.0074 memory: 1125 loss: 0.4212 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4212 2023/04/17 23:39:19 - mmengine - INFO - Epoch(train) [8][1700/4632] lr: 5.6200e-02 eta: 1:05:53 time: 0.0981 data_time: 0.0075 memory: 1125 loss: 0.4214 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4214 2023/04/17 23:39:29 - mmengine - INFO - Epoch(train) [8][1800/4632] lr: 5.5990e-02 eta: 1:05:43 time: 0.0977 data_time: 0.0074 memory: 1125 loss: 0.4070 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.4070 2023/04/17 23:39:39 - mmengine - INFO - Epoch(train) [8][1900/4632] lr: 5.5780e-02 eta: 1:05:33 time: 0.0973 data_time: 0.0074 memory: 1125 loss: 0.4227 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.4227 2023/04/17 23:39:49 - mmengine - INFO - Epoch(train) [8][2000/4632] lr: 5.5569e-02 eta: 1:05:23 time: 0.0975 data_time: 0.0075 memory: 1125 loss: 0.4218 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4218 2023/04/17 23:39:59 - mmengine - INFO - Epoch(train) [8][2100/4632] lr: 5.5358e-02 eta: 1:05:14 time: 0.1006 data_time: 0.0075 memory: 1125 loss: 0.4085 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4085 2023/04/17 23:40:08 - mmengine - INFO - Epoch(train) [8][2200/4632] lr: 5.5148e-02 eta: 1:05:04 time: 0.0982 data_time: 0.0075 memory: 1125 loss: 0.4769 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4769 2023/04/17 23:40:18 - mmengine - INFO - Epoch(train) [8][2300/4632] lr: 5.4937e-02 eta: 1:04:54 time: 0.0974 data_time: 0.0075 memory: 1125 loss: 0.3320 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3320 2023/04/17 23:40:28 - mmengine - INFO - Epoch(train) [8][2400/4632] lr: 5.4726e-02 eta: 1:04:44 time: 0.0975 data_time: 0.0075 memory: 1125 loss: 0.4982 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4982 2023/04/17 23:40:38 - mmengine - INFO - Epoch(train) [8][2500/4632] lr: 5.4515e-02 eta: 1:04:34 time: 0.0986 data_time: 0.0074 memory: 1125 loss: 0.4385 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.4385 2023/04/17 23:40:45 - mmengine - INFO - Exp name: stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230417_223936 2023/04/17 23:40:48 - mmengine - INFO - Epoch(train) [8][2600/4632] lr: 5.4304e-02 eta: 1:04:24 time: 0.0987 data_time: 0.0075 memory: 1125 loss: 0.4631 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4631 2023/04/17 23:40:58 - mmengine - INFO - Epoch(train) [8][2700/4632] lr: 5.4092e-02 eta: 1:04:14 time: 0.0981 data_time: 0.0075 memory: 1125 loss: 0.4511 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4511 2023/04/17 23:41:07 - mmengine - INFO - Epoch(train) [8][2800/4632] lr: 5.3881e-02 eta: 1:04:04 time: 0.0983 data_time: 0.0077 memory: 1125 loss: 0.4423 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.4423 2023/04/17 23:41:17 - mmengine - INFO - Epoch(train) [8][2900/4632] lr: 5.3670e-02 eta: 1:03:54 time: 0.0982 data_time: 0.0074 memory: 1125 loss: 0.3661 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.3661 2023/04/17 23:41:27 - mmengine - INFO - Epoch(train) [8][3000/4632] lr: 5.3458e-02 eta: 1:03:44 time: 0.0984 data_time: 0.0074 memory: 1125 loss: 0.3441 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3441 2023/04/17 23:41:37 - mmengine - INFO - Epoch(train) [8][3100/4632] lr: 5.3247e-02 eta: 1:03:34 time: 0.0986 data_time: 0.0074 memory: 1125 loss: 0.4353 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4353 2023/04/17 23:41:47 - mmengine - INFO - Epoch(train) [8][3200/4632] lr: 5.3035e-02 eta: 1:03:24 time: 0.0991 data_time: 0.0074 memory: 1125 loss: 0.4489 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.4489 2023/04/17 23:41:57 - mmengine - INFO - Epoch(train) [8][3300/4632] lr: 5.2824e-02 eta: 1:03:14 time: 0.0981 data_time: 0.0074 memory: 1125 loss: 0.3968 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.3968 2023/04/17 23:42:07 - mmengine - INFO - Epoch(train) [8][3400/4632] lr: 5.2612e-02 eta: 1:03:04 time: 0.0986 data_time: 0.0074 memory: 1125 loss: 0.4582 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.4582 2023/04/17 23:42:16 - mmengine - INFO - Epoch(train) [8][3500/4632] lr: 5.2400e-02 eta: 1:02:54 time: 0.0981 data_time: 0.0074 memory: 1125 loss: 0.4225 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4225 2023/04/17 23:42:24 - mmengine - INFO - Exp name: stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230417_223936 2023/04/17 23:42:26 - mmengine - INFO - Epoch(train) [8][3600/4632] lr: 5.2189e-02 eta: 1:02:44 time: 0.0985 data_time: 0.0074 memory: 1125 loss: 0.5664 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.5664 2023/04/17 23:42:36 - mmengine - INFO - Epoch(train) [8][3700/4632] lr: 5.1977e-02 eta: 1:02:34 time: 0.0974 data_time: 0.0074 memory: 1125 loss: 0.3749 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3749 2023/04/17 23:42:46 - mmengine - INFO - Epoch(train) [8][3800/4632] lr: 5.1765e-02 eta: 1:02:25 time: 0.0982 data_time: 0.0075 memory: 1125 loss: 0.4090 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.4090 2023/04/17 23:42:56 - mmengine - INFO - Epoch(train) [8][3900/4632] lr: 5.1553e-02 eta: 1:02:15 time: 0.0976 data_time: 0.0074 memory: 1125 loss: 0.4127 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4127 2023/04/17 23:43:06 - mmengine - INFO - Epoch(train) [8][4000/4632] lr: 5.1341e-02 eta: 1:02:05 time: 0.0996 data_time: 0.0074 memory: 1125 loss: 0.4238 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4238 2023/04/17 23:43:15 - mmengine - INFO - Epoch(train) [8][4100/4632] lr: 5.1130e-02 eta: 1:01:55 time: 0.0978 data_time: 0.0074 memory: 1125 loss: 0.3987 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3987 2023/04/17 23:43:25 - mmengine - INFO - Epoch(train) [8][4200/4632] lr: 5.0918e-02 eta: 1:01:45 time: 0.0974 data_time: 0.0074 memory: 1125 loss: 0.5144 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.5144 2023/04/17 23:43:35 - mmengine - INFO - Epoch(train) [8][4300/4632] lr: 5.0706e-02 eta: 1:01:35 time: 0.0981 data_time: 0.0074 memory: 1125 loss: 0.4180 top1_acc: 0.8750 top5_acc: 0.8750 loss_cls: 0.4180 2023/04/17 23:43:45 - mmengine - INFO - Epoch(train) [8][4400/4632] lr: 5.0494e-02 eta: 1:01:25 time: 0.0986 data_time: 0.0075 memory: 1125 loss: 0.4643 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4643 2023/04/17 23:43:55 - mmengine - INFO - Epoch(train) [8][4500/4632] lr: 5.0282e-02 eta: 1:01:15 time: 0.0977 data_time: 0.0075 memory: 1125 loss: 0.4663 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.4663 2023/04/17 23:44:02 - mmengine - INFO - Exp name: stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230417_223936 2023/04/17 23:44:05 - mmengine - INFO - Epoch(train) [8][4600/4632] lr: 5.0070e-02 eta: 1:01:05 time: 0.0988 data_time: 0.0074 memory: 1125 loss: 0.4520 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.4520 2023/04/17 23:44:08 - mmengine - INFO - Exp name: stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230417_223936 2023/04/17 23:44:08 - mmengine - INFO - Epoch(train) [8][4632/4632] lr: 5.0002e-02 eta: 1:01:02 time: 0.0981 data_time: 0.0075 memory: 1125 loss: 0.5097 top1_acc: 0.6667 top5_acc: 0.6667 loss_cls: 0.5097 2023/04/17 23:44:08 - mmengine - INFO - Saving checkpoint at 8 epochs 2023/04/17 23:44:11 - mmengine - INFO - Epoch(val) [8][100/116] eta: 0:00:00 time: 0.0278 data_time: 0.0069 memory: 171 2023/04/17 23:44:12 - mmengine - INFO - Epoch(val) [8][116/116] acc/top1: 0.8599 acc/top5: 0.9715 acc/mean1: 0.8633data_time: 0.0063 time: 0.0270 2023/04/17 23:44:22 - mmengine - INFO - Epoch(train) [9][ 100/4632] lr: 4.9790e-02 eta: 1:00:52 time: 0.0982 data_time: 0.0075 memory: 1125 loss: 0.3772 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3772 2023/04/17 23:44:31 - mmengine - INFO - Epoch(train) [9][ 200/4632] lr: 4.9578e-02 eta: 1:00:42 time: 0.0995 data_time: 0.0074 memory: 1125 loss: 0.3644 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3644 2023/04/17 23:44:41 - mmengine - INFO - Epoch(train) [9][ 300/4632] lr: 4.9366e-02 eta: 1:00:32 time: 0.0988 data_time: 0.0083 memory: 1125 loss: 0.3359 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3359 2023/04/17 23:44:51 - mmengine - INFO - Epoch(train) [9][ 400/4632] lr: 4.9154e-02 eta: 1:00:22 time: 0.0989 data_time: 0.0076 memory: 1125 loss: 0.4126 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4126 2023/04/17 23:45:01 - mmengine - INFO - Epoch(train) [9][ 500/4632] lr: 4.8942e-02 eta: 1:00:13 time: 0.0989 data_time: 0.0075 memory: 1125 loss: 0.4794 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.4794 2023/04/17 23:45:11 - mmengine - INFO - Epoch(train) [9][ 600/4632] lr: 4.8731e-02 eta: 1:00:03 time: 0.0988 data_time: 0.0075 memory: 1125 loss: 0.4708 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.4708 2023/04/17 23:45:21 - mmengine - INFO - Epoch(train) [9][ 700/4632] lr: 4.8519e-02 eta: 0:59:53 time: 0.0981 data_time: 0.0083 memory: 1125 loss: 0.4597 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.4597 2023/04/17 23:45:31 - mmengine - INFO - Epoch(train) [9][ 800/4632] lr: 4.8307e-02 eta: 0:59:43 time: 0.0983 data_time: 0.0083 memory: 1125 loss: 0.5308 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 0.5308 2023/04/17 23:45:41 - mmengine - INFO - Epoch(train) [9][ 900/4632] lr: 4.8095e-02 eta: 0:59:33 time: 0.0978 data_time: 0.0074 memory: 1125 loss: 0.5155 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.5155 2023/04/17 23:45:45 - mmengine - INFO - Exp name: stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230417_223936 2023/04/17 23:45:50 - mmengine - INFO - Epoch(train) [9][1000/4632] lr: 4.7883e-02 eta: 0:59:23 time: 0.0992 data_time: 0.0081 memory: 1125 loss: 0.4839 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.4839 2023/04/17 23:46:00 - mmengine - INFO - Epoch(train) [9][1100/4632] lr: 4.7672e-02 eta: 0:59:13 time: 0.0982 data_time: 0.0081 memory: 1125 loss: 0.4301 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.4301 2023/04/17 23:46:10 - mmengine - INFO - Epoch(train) [9][1200/4632] lr: 4.7460e-02 eta: 0:59:03 time: 0.0992 data_time: 0.0077 memory: 1125 loss: 0.3781 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.3781 2023/04/17 23:46:20 - mmengine - INFO - Epoch(train) [9][1300/4632] lr: 4.7248e-02 eta: 0:58:53 time: 0.0989 data_time: 0.0075 memory: 1125 loss: 0.4645 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 0.4645 2023/04/17 23:46:30 - mmengine - INFO - Epoch(train) [9][1400/4632] lr: 4.7037e-02 eta: 0:58:43 time: 0.0988 data_time: 0.0082 memory: 1125 loss: 0.4810 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.4810 2023/04/17 23:46:40 - mmengine - INFO - Epoch(train) [9][1500/4632] lr: 4.6825e-02 eta: 0:58:34 time: 0.1038 data_time: 0.0075 memory: 1125 loss: 0.3647 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 0.3647 2023/04/17 23:46:50 - mmengine - INFO - Epoch(train) [9][1600/4632] lr: 4.6614e-02 eta: 0:58:24 time: 0.1036 data_time: 0.0075 memory: 1125 loss: 0.4332 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 0.4332 2023/04/17 23:47:01 - mmengine - INFO - Epoch(train) [9][1700/4632] lr: 4.6402e-02 eta: 0:58:15 time: 0.0975 data_time: 0.0074 memory: 1125 loss: 0.4580 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.4580 2023/04/17 23:47:10 - mmengine - INFO - Epoch(train) [9][1800/4632] lr: 4.6191e-02 eta: 0:58:05 time: 0.0979 data_time: 0.0074 memory: 1125 loss: 0.3887 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.3887 2023/04/17 23:47:20 - mmengine - INFO - Epoch(train) [9][1900/4632] lr: 4.5979e-02 eta: 0:57:55 time: 0.0977 data_time: 0.0074 memory: 1125 loss: 0.5035 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.5035 2023/04/17 23:47:25 - mmengine - INFO - Exp name: stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230417_223936 2023/04/17 23:47:30 - mmengine - INFO - Epoch(train) [9][2000/4632] lr: 4.5768e-02 eta: 0:57:45 time: 0.0984 data_time: 0.0074 memory: 1125 loss: 0.4364 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4364 2023/04/17 23:47:40 - mmengine - INFO - Epoch(train) [9][2100/4632] lr: 4.5557e-02 eta: 0:57:35 time: 0.0973 data_time: 0.0077 memory: 1125 loss: 0.3785 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3785 2023/04/17 23:47:50 - mmengine - INFO - Epoch(train) [9][2200/4632] lr: 4.5346e-02 eta: 0:57:25 time: 0.0989 data_time: 0.0075 memory: 1125 loss: 0.3985 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.3985 2023/04/17 23:48:00 - mmengine - INFO - Epoch(train) [9][2300/4632] lr: 4.5135e-02 eta: 0:57:15 time: 0.0978 data_time: 0.0074 memory: 1125 loss: 0.4290 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4290 2023/04/17 23:48:09 - mmengine - INFO - Epoch(train) [9][2400/4632] lr: 4.4924e-02 eta: 0:57:05 time: 0.0980 data_time: 0.0075 memory: 1125 loss: 0.4197 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4197 2023/04/17 23:48:19 - mmengine - INFO - Epoch(train) [9][2500/4632] lr: 4.4713e-02 eta: 0:56:55 time: 0.0999 data_time: 0.0075 memory: 1125 loss: 0.5025 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.5025 2023/04/17 23:48:29 - mmengine - INFO - Epoch(train) [9][2600/4632] lr: 4.4503e-02 eta: 0:56:45 time: 0.0994 data_time: 0.0074 memory: 1125 loss: 0.4175 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4175 2023/04/17 23:48:39 - mmengine - INFO - Epoch(train) [9][2700/4632] lr: 4.4292e-02 eta: 0:56:35 time: 0.1001 data_time: 0.0074 memory: 1125 loss: 0.4104 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4104 2023/04/17 23:48:49 - mmengine - INFO - Epoch(train) [9][2800/4632] lr: 4.4081e-02 eta: 0:56:26 time: 0.1003 data_time: 0.0074 memory: 1125 loss: 0.4115 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.4115 2023/04/17 23:48:59 - mmengine - INFO - Epoch(train) [9][2900/4632] lr: 4.3871e-02 eta: 0:56:16 time: 0.0995 data_time: 0.0074 memory: 1125 loss: 0.4894 top1_acc: 0.6875 top5_acc: 0.9375 loss_cls: 0.4894 2023/04/17 23:49:03 - mmengine - INFO - Exp name: stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230417_223936 2023/04/17 23:49:09 - mmengine - INFO - Epoch(train) [9][3000/4632] lr: 4.3661e-02 eta: 0:56:06 time: 0.0989 data_time: 0.0075 memory: 1125 loss: 0.3752 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 0.3752 2023/04/17 23:49:19 - mmengine - INFO - Epoch(train) [9][3100/4632] lr: 4.3451e-02 eta: 0:55:56 time: 0.0992 data_time: 0.0075 memory: 1125 loss: 0.3741 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.3741 2023/04/17 23:49:29 - mmengine - INFO - Epoch(train) [9][3200/4632] lr: 4.3241e-02 eta: 0:55:46 time: 0.1002 data_time: 0.0074 memory: 1125 loss: 0.4431 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4431 2023/04/17 23:49:39 - mmengine - INFO - Epoch(train) [9][3300/4632] lr: 4.3031e-02 eta: 0:55:36 time: 0.0993 data_time: 0.0074 memory: 1125 loss: 0.3947 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.3947 2023/04/17 23:49:49 - mmengine - INFO - Epoch(train) [9][3400/4632] lr: 4.2821e-02 eta: 0:55:27 time: 0.0989 data_time: 0.0074 memory: 1125 loss: 0.3333 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3333 2023/04/17 23:49:59 - mmengine - INFO - Epoch(train) [9][3500/4632] lr: 4.2611e-02 eta: 0:55:17 time: 0.0989 data_time: 0.0074 memory: 1125 loss: 0.3625 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3625 2023/04/17 23:50:09 - mmengine - INFO - Epoch(train) [9][3600/4632] lr: 4.2402e-02 eta: 0:55:07 time: 0.0994 data_time: 0.0076 memory: 1125 loss: 0.4196 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4196 2023/04/17 23:50:19 - mmengine - INFO - Epoch(train) [9][3700/4632] lr: 4.2192e-02 eta: 0:54:57 time: 0.0989 data_time: 0.0076 memory: 1125 loss: 0.4471 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 0.4471 2023/04/17 23:50:28 - mmengine - INFO - Epoch(train) [9][3800/4632] lr: 4.1983e-02 eta: 0:54:47 time: 0.0989 data_time: 0.0074 memory: 1125 loss: 0.4001 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4001 2023/04/17 23:50:38 - mmengine - INFO - Epoch(train) [9][3900/4632] lr: 4.1774e-02 eta: 0:54:37 time: 0.0997 data_time: 0.0074 memory: 1125 loss: 0.4061 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4061 2023/04/17 23:50:43 - mmengine - INFO - Exp name: stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230417_223936 2023/04/17 23:50:48 - mmengine - INFO - Epoch(train) [9][4000/4632] lr: 4.1565e-02 eta: 0:54:27 time: 0.0991 data_time: 0.0075 memory: 1125 loss: 0.4133 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.4133 2023/04/17 23:50:58 - mmengine - INFO - Epoch(train) [9][4100/4632] lr: 4.1356e-02 eta: 0:54:18 time: 0.0993 data_time: 0.0074 memory: 1125 loss: 0.3283 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3283 2023/04/17 23:51:08 - mmengine - INFO - Epoch(train) [9][4200/4632] lr: 4.1147e-02 eta: 0:54:08 time: 0.1000 data_time: 0.0082 memory: 1125 loss: 0.3804 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3804 2023/04/17 23:51:18 - mmengine - INFO - Epoch(train) [9][4300/4632] lr: 4.0939e-02 eta: 0:53:58 time: 0.1001 data_time: 0.0075 memory: 1125 loss: 0.3909 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3909 2023/04/17 23:51:28 - mmengine - INFO - Epoch(train) [9][4400/4632] lr: 4.0730e-02 eta: 0:53:48 time: 0.1002 data_time: 0.0075 memory: 1125 loss: 0.4555 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4555 2023/04/17 23:51:39 - mmengine - INFO - Epoch(train) [9][4500/4632] lr: 4.0522e-02 eta: 0:53:39 time: 0.1003 data_time: 0.0075 memory: 1125 loss: 0.4509 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4509 2023/04/17 23:51:49 - mmengine - INFO - Epoch(train) [9][4600/4632] lr: 4.0314e-02 eta: 0:53:29 time: 0.1001 data_time: 0.0074 memory: 1125 loss: 0.4966 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.4966 2023/04/17 23:51:52 - mmengine - INFO - Exp name: stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230417_223936 2023/04/17 23:51:52 - mmengine - INFO - Epoch(train) [9][4632/4632] lr: 4.0248e-02 eta: 0:53:26 time: 0.1001 data_time: 0.0076 memory: 1125 loss: 0.4217 top1_acc: 0.6667 top5_acc: 1.0000 loss_cls: 0.4217 2023/04/17 23:51:52 - mmengine - INFO - Saving checkpoint at 9 epochs 2023/04/17 23:51:55 - mmengine - INFO - Epoch(val) [9][100/116] eta: 0:00:00 time: 0.0277 data_time: 0.0065 memory: 171 2023/04/17 23:51:56 - mmengine - INFO - Epoch(val) [9][116/116] acc/top1: 0.8748 acc/top5: 0.9736 acc/mean1: 0.8713data_time: 0.0062 time: 0.0269 2023/04/17 23:51:56 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/hukai/mmaction2/work_dirs/stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_7.pth is removed 2023/04/17 23:51:56 - mmengine - INFO - The best checkpoint with 0.8748 acc/top1 at 9 epoch is saved to best_acc/top1_epoch_9.pth. 2023/04/17 23:52:06 - mmengine - INFO - Epoch(train) [10][ 100/4632] lr: 4.0040e-02 eta: 0:53:16 time: 0.0984 data_time: 0.0074 memory: 1125 loss: 0.4933 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4933 2023/04/17 23:52:16 - mmengine - INFO - Epoch(train) [10][ 200/4632] lr: 3.9832e-02 eta: 0:53:06 time: 0.0987 data_time: 0.0075 memory: 1125 loss: 0.3874 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 0.3874 2023/04/17 23:52:26 - mmengine - INFO - Epoch(train) [10][ 300/4632] lr: 3.9625e-02 eta: 0:52:56 time: 0.0987 data_time: 0.0074 memory: 1125 loss: 0.3881 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.3881 2023/04/17 23:52:27 - mmengine - INFO - Exp name: stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230417_223936 2023/04/17 23:52:36 - mmengine - INFO - Epoch(train) [10][ 400/4632] lr: 3.9417e-02 eta: 0:52:46 time: 0.0990 data_time: 0.0073 memory: 1125 loss: 0.3767 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3767 2023/04/17 23:52:46 - mmengine - INFO - Epoch(train) [10][ 500/4632] lr: 3.9210e-02 eta: 0:52:36 time: 0.0992 data_time: 0.0074 memory: 1125 loss: 0.3761 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3761 2023/04/17 23:52:56 - mmengine - INFO - Epoch(train) [10][ 600/4632] lr: 3.9004e-02 eta: 0:52:26 time: 0.0990 data_time: 0.0081 memory: 1125 loss: 0.3666 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3666 2023/04/17 23:53:06 - mmengine - INFO - Epoch(train) [10][ 700/4632] lr: 3.8797e-02 eta: 0:52:17 time: 0.0993 data_time: 0.0074 memory: 1125 loss: 0.4895 top1_acc: 0.6250 top5_acc: 0.8750 loss_cls: 0.4895 2023/04/17 23:53:16 - mmengine - INFO - Epoch(train) [10][ 800/4632] lr: 3.8590e-02 eta: 0:52:07 time: 0.0994 data_time: 0.0074 memory: 1125 loss: 0.3716 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3716 2023/04/17 23:53:26 - mmengine - INFO - Epoch(train) [10][ 900/4632] lr: 3.8384e-02 eta: 0:51:57 time: 0.0997 data_time: 0.0074 memory: 1125 loss: 0.4798 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 0.4798 2023/04/17 23:53:36 - mmengine - INFO - Epoch(train) [10][1000/4632] lr: 3.8178e-02 eta: 0:51:47 time: 0.0994 data_time: 0.0074 memory: 1125 loss: 0.3397 top1_acc: 0.8750 top5_acc: 0.8750 loss_cls: 0.3397 2023/04/17 23:53:46 - mmengine - INFO - Epoch(train) [10][1100/4632] lr: 3.7972e-02 eta: 0:51:37 time: 0.0990 data_time: 0.0074 memory: 1125 loss: 0.3929 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3929 2023/04/17 23:53:55 - mmengine - INFO - Epoch(train) [10][1200/4632] lr: 3.7767e-02 eta: 0:51:27 time: 0.0991 data_time: 0.0075 memory: 1125 loss: 0.3654 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3654 2023/04/17 23:54:05 - mmengine - INFO - Epoch(train) [10][1300/4632] lr: 3.7561e-02 eta: 0:51:18 time: 0.0993 data_time: 0.0074 memory: 1125 loss: 0.4409 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.4409 2023/04/17 23:54:07 - mmengine - INFO - Exp name: stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230417_223936 2023/04/17 23:54:15 - mmengine - INFO - Epoch(train) [10][1400/4632] lr: 3.7356e-02 eta: 0:51:08 time: 0.0985 data_time: 0.0082 memory: 1125 loss: 0.4135 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.4135 2023/04/17 23:54:25 - mmengine - INFO - Epoch(train) [10][1500/4632] lr: 3.7151e-02 eta: 0:50:58 time: 0.0984 data_time: 0.0074 memory: 1125 loss: 0.3660 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3660 2023/04/17 23:54:35 - mmengine - INFO - Epoch(train) [10][1600/4632] lr: 3.6946e-02 eta: 0:50:48 time: 0.0983 data_time: 0.0074 memory: 1125 loss: 0.4733 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4733 2023/04/17 23:54:45 - mmengine - INFO - Epoch(train) [10][1700/4632] lr: 3.6742e-02 eta: 0:50:38 time: 0.0995 data_time: 0.0075 memory: 1125 loss: 0.4469 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4469 2023/04/17 23:54:55 - mmengine - INFO - Epoch(train) [10][1800/4632] lr: 3.6538e-02 eta: 0:50:28 time: 0.1026 data_time: 0.0077 memory: 1125 loss: 0.4015 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.4015 2023/04/17 23:55:05 - mmengine - INFO - Epoch(train) [10][1900/4632] lr: 3.6334e-02 eta: 0:50:18 time: 0.0997 data_time: 0.0074 memory: 1125 loss: 0.2998 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.2998 2023/04/17 23:55:15 - mmengine - INFO - Epoch(train) [10][2000/4632] lr: 3.6130e-02 eta: 0:50:09 time: 0.1011 data_time: 0.0077 memory: 1125 loss: 0.4592 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 0.4592 2023/04/17 23:55:25 - mmengine - INFO - Epoch(train) [10][2100/4632] lr: 3.5926e-02 eta: 0:49:59 time: 0.1014 data_time: 0.0078 memory: 1125 loss: 0.3403 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3403 2023/04/17 23:55:35 - mmengine - INFO - Epoch(train) [10][2200/4632] lr: 3.5723e-02 eta: 0:49:49 time: 0.1001 data_time: 0.0077 memory: 1125 loss: 0.3597 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3597 2023/04/17 23:55:45 - mmengine - INFO - Epoch(train) [10][2300/4632] lr: 3.5520e-02 eta: 0:49:39 time: 0.0980 data_time: 0.0075 memory: 1125 loss: 0.3293 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 0.3293 2023/04/17 23:55:46 - mmengine - INFO - Exp name: stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230417_223936 2023/04/17 23:55:55 - mmengine - INFO - Epoch(train) [10][2400/4632] lr: 3.5318e-02 eta: 0:49:29 time: 0.0981 data_time: 0.0074 memory: 1125 loss: 0.2945 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2945 2023/04/17 23:56:05 - mmengine - INFO - Epoch(train) [10][2500/4632] lr: 3.5115e-02 eta: 0:49:19 time: 0.1004 data_time: 0.0074 memory: 1125 loss: 0.3646 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.3646 2023/04/17 23:56:15 - mmengine - INFO - Epoch(train) [10][2600/4632] lr: 3.4913e-02 eta: 0:49:09 time: 0.0979 data_time: 0.0074 memory: 1125 loss: 0.4035 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4035 2023/04/17 23:56:25 - mmengine - INFO - Epoch(train) [10][2700/4632] lr: 3.4711e-02 eta: 0:49:00 time: 0.0979 data_time: 0.0075 memory: 1125 loss: 0.3978 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3978 2023/04/17 23:56:34 - mmengine - INFO - Epoch(train) [10][2800/4632] lr: 3.4509e-02 eta: 0:48:50 time: 0.0977 data_time: 0.0081 memory: 1125 loss: 0.3050 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 0.3050 2023/04/17 23:56:44 - mmengine - INFO - Epoch(train) [10][2900/4632] lr: 3.4308e-02 eta: 0:48:40 time: 0.0976 data_time: 0.0074 memory: 1125 loss: 0.3228 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.3228 2023/04/17 23:56:54 - mmengine - INFO - Epoch(train) [10][3000/4632] lr: 3.4107e-02 eta: 0:48:30 time: 0.0977 data_time: 0.0075 memory: 1125 loss: 0.4193 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.4193 2023/04/17 23:57:04 - mmengine - INFO - Epoch(train) [10][3100/4632] lr: 3.3906e-02 eta: 0:48:20 time: 0.0981 data_time: 0.0074 memory: 1125 loss: 0.4050 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.4050 2023/04/17 23:57:14 - mmengine - INFO - Epoch(train) [10][3200/4632] lr: 3.3705e-02 eta: 0:48:10 time: 0.0981 data_time: 0.0075 memory: 1125 loss: 0.3834 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3834 2023/04/17 23:57:24 - mmengine - INFO - Epoch(train) [10][3300/4632] lr: 3.3505e-02 eta: 0:48:00 time: 0.0990 data_time: 0.0075 memory: 1125 loss: 0.3150 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3150 2023/04/17 23:57:25 - mmengine - INFO - Exp name: stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230417_223936 2023/04/17 23:57:33 - mmengine - INFO - Epoch(train) [10][3400/4632] lr: 3.3305e-02 eta: 0:47:50 time: 0.0981 data_time: 0.0078 memory: 1125 loss: 0.3907 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.3907 2023/04/17 23:57:43 - mmengine - INFO - Epoch(train) [10][3500/4632] lr: 3.3106e-02 eta: 0:47:40 time: 0.0980 data_time: 0.0082 memory: 1125 loss: 0.4045 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4045 2023/04/17 23:57:53 - mmengine - INFO - Epoch(train) [10][3600/4632] lr: 3.2906e-02 eta: 0:47:30 time: 0.0981 data_time: 0.0075 memory: 1125 loss: 0.3835 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3835 2023/04/17 23:58:03 - mmengine - INFO - Epoch(train) [10][3700/4632] lr: 3.2707e-02 eta: 0:47:20 time: 0.0985 data_time: 0.0082 memory: 1125 loss: 0.3243 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3243 2023/04/17 23:58:13 - mmengine - INFO - Epoch(train) [10][3800/4632] lr: 3.2509e-02 eta: 0:47:10 time: 0.0982 data_time: 0.0084 memory: 1125 loss: 0.3720 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3720 2023/04/17 23:58:23 - mmengine - INFO - Epoch(train) [10][3900/4632] lr: 3.2310e-02 eta: 0:47:00 time: 0.0984 data_time: 0.0075 memory: 1125 loss: 0.4061 top1_acc: 0.8125 top5_acc: 0.8750 loss_cls: 0.4061 2023/04/17 23:58:33 - mmengine - INFO - Epoch(train) [10][4000/4632] lr: 3.2112e-02 eta: 0:46:51 time: 0.0992 data_time: 0.0089 memory: 1125 loss: 0.4023 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.4023 2023/04/17 23:58:43 - mmengine - INFO - Epoch(train) [10][4100/4632] lr: 3.1914e-02 eta: 0:46:41 time: 0.1001 data_time: 0.0075 memory: 1125 loss: 0.4056 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4056 2023/04/17 23:58:53 - mmengine - INFO - Epoch(train) [10][4200/4632] lr: 3.1717e-02 eta: 0:46:31 time: 0.0989 data_time: 0.0074 memory: 1125 loss: 0.4377 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4377 2023/04/17 23:59:03 - mmengine - INFO - Epoch(train) [10][4300/4632] lr: 3.1520e-02 eta: 0:46:21 time: 0.0994 data_time: 0.0087 memory: 1125 loss: 0.3831 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.3831 2023/04/17 23:59:04 - mmengine - INFO - Exp name: stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230417_223936 2023/04/17 23:59:13 - mmengine - INFO - Epoch(train) [10][4400/4632] lr: 3.1323e-02 eta: 0:46:11 time: 0.1004 data_time: 0.0075 memory: 1125 loss: 0.3990 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.3990 2023/04/17 23:59:23 - mmengine - INFO - Epoch(train) [10][4500/4632] lr: 3.1127e-02 eta: 0:46:01 time: 0.1011 data_time: 0.0078 memory: 1125 loss: 0.4025 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.4025 2023/04/17 23:59:33 - mmengine - INFO - Epoch(train) [10][4600/4632] lr: 3.0930e-02 eta: 0:45:52 time: 0.1003 data_time: 0.0082 memory: 1125 loss: 0.3729 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3729 2023/04/17 23:59:36 - mmengine - INFO - Exp name: stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230417_223936 2023/04/17 23:59:36 - mmengine - INFO - Epoch(train) [10][4632/4632] lr: 3.0868e-02 eta: 0:45:49 time: 0.1007 data_time: 0.0081 memory: 1125 loss: 0.3851 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3851 2023/04/17 23:59:36 - mmengine - INFO - Saving checkpoint at 10 epochs 2023/04/17 23:59:39 - mmengine - INFO - Epoch(val) [10][100/116] eta: 0:00:00 time: 0.0277 data_time: 0.0066 memory: 171 2023/04/17 23:59:40 - mmengine - INFO - Epoch(val) [10][116/116] acc/top1: 0.8845 acc/top5: 0.9749 acc/mean1: 0.8840data_time: 0.0062 time: 0.0269 2023/04/17 23:59:40 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/hukai/mmaction2/work_dirs/stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_9.pth is removed 2023/04/17 23:59:40 - mmengine - INFO - The best checkpoint with 0.8845 acc/top1 at 10 epoch is saved to best_acc/top1_epoch_10.pth. 2023/04/17 23:59:51 - mmengine - INFO - Epoch(train) [11][ 100/4632] lr: 3.0672e-02 eta: 0:45:39 time: 0.1003 data_time: 0.0075 memory: 1125 loss: 0.3371 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.3371 2023/04/18 00:00:01 - mmengine - INFO - Epoch(train) [11][ 200/4632] lr: 3.0477e-02 eta: 0:45:29 time: 0.1005 data_time: 0.0078 memory: 1125 loss: 0.2836 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2836 2023/04/18 00:00:11 - mmengine - INFO - Epoch(train) [11][ 300/4632] lr: 3.0282e-02 eta: 0:45:19 time: 0.1002 data_time: 0.0075 memory: 1125 loss: 0.3538 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3538 2023/04/18 00:00:21 - mmengine - INFO - Epoch(train) [11][ 400/4632] lr: 3.0087e-02 eta: 0:45:09 time: 0.1004 data_time: 0.0075 memory: 1125 loss: 0.4374 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.4374 2023/04/18 00:00:31 - mmengine - INFO - Epoch(train) [11][ 500/4632] lr: 2.9893e-02 eta: 0:45:00 time: 0.1005 data_time: 0.0078 memory: 1125 loss: 0.3743 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3743 2023/04/18 00:00:41 - mmengine - INFO - Epoch(train) [11][ 600/4632] lr: 2.9699e-02 eta: 0:44:50 time: 0.1006 data_time: 0.0076 memory: 1125 loss: 0.3640 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.3640 2023/04/18 00:00:49 - mmengine - INFO - Exp name: stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230417_223936 2023/04/18 00:00:51 - mmengine - INFO - Epoch(train) [11][ 700/4632] lr: 2.9506e-02 eta: 0:44:40 time: 0.1004 data_time: 0.0075 memory: 1125 loss: 0.3990 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3990 2023/04/18 00:01:01 - mmengine - INFO - Epoch(train) [11][ 800/4632] lr: 2.9313e-02 eta: 0:44:30 time: 0.1001 data_time: 0.0077 memory: 1125 loss: 0.4199 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.4199 2023/04/18 00:01:11 - mmengine - INFO - Epoch(train) [11][ 900/4632] lr: 2.9120e-02 eta: 0:44:20 time: 0.1006 data_time: 0.0076 memory: 1125 loss: 0.3688 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3688 2023/04/18 00:01:21 - mmengine - INFO - Epoch(train) [11][1000/4632] lr: 2.8927e-02 eta: 0:44:11 time: 0.1007 data_time: 0.0075 memory: 1125 loss: 0.2976 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.2976 2023/04/18 00:01:31 - mmengine - INFO - Epoch(train) [11][1100/4632] lr: 2.8735e-02 eta: 0:44:01 time: 0.1007 data_time: 0.0089 memory: 1125 loss: 0.4369 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.4369 2023/04/18 00:01:41 - mmengine - INFO - Epoch(train) [11][1200/4632] lr: 2.8544e-02 eta: 0:43:51 time: 0.1011 data_time: 0.0087 memory: 1125 loss: 0.3450 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.3450 2023/04/18 00:01:51 - mmengine - INFO - Epoch(train) [11][1300/4632] lr: 2.8352e-02 eta: 0:43:41 time: 0.1008 data_time: 0.0087 memory: 1125 loss: 0.3109 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3109 2023/04/18 00:02:01 - mmengine - INFO - Epoch(train) [11][1400/4632] lr: 2.8162e-02 eta: 0:43:31 time: 0.1009 data_time: 0.0087 memory: 1125 loss: 0.2594 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.2594 2023/04/18 00:02:11 - mmengine - INFO - Epoch(train) [11][1500/4632] lr: 2.7971e-02 eta: 0:43:22 time: 0.1005 data_time: 0.0086 memory: 1125 loss: 0.4371 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4371 2023/04/18 00:02:21 - mmengine - INFO - Epoch(train) [11][1600/4632] lr: 2.7781e-02 eta: 0:43:12 time: 0.1010 data_time: 0.0091 memory: 1125 loss: 0.4154 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.4154 2023/04/18 00:02:30 - mmengine - INFO - Exp name: stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230417_223936 2023/04/18 00:02:32 - mmengine - INFO - Epoch(train) [11][1700/4632] lr: 2.7591e-02 eta: 0:43:02 time: 0.1005 data_time: 0.0086 memory: 1125 loss: 0.4380 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.4380 2023/04/18 00:02:42 - mmengine - INFO - Epoch(train) [11][1800/4632] lr: 2.7402e-02 eta: 0:42:52 time: 0.1010 data_time: 0.0086 memory: 1125 loss: 0.4073 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.4073 2023/04/18 00:02:52 - mmengine - INFO - Epoch(train) [11][1900/4632] lr: 2.7213e-02 eta: 0:42:42 time: 0.1005 data_time: 0.0082 memory: 1125 loss: 0.4328 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.4328 2023/04/18 00:03:02 - mmengine - INFO - Epoch(train) [11][2000/4632] lr: 2.7025e-02 eta: 0:42:33 time: 0.1001 data_time: 0.0075 memory: 1125 loss: 0.3323 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3323 2023/04/18 00:03:12 - mmengine - INFO - Epoch(train) [11][2100/4632] lr: 2.6837e-02 eta: 0:42:23 time: 0.0999 data_time: 0.0076 memory: 1125 loss: 0.3390 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3390 2023/04/18 00:03:22 - mmengine - INFO - Epoch(train) [11][2200/4632] lr: 2.6649e-02 eta: 0:42:13 time: 0.1005 data_time: 0.0076 memory: 1125 loss: 0.3852 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3852 2023/04/18 00:03:32 - mmengine - INFO - Epoch(train) [11][2300/4632] lr: 2.6462e-02 eta: 0:42:03 time: 0.1002 data_time: 0.0076 memory: 1125 loss: 0.3903 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.3903 2023/04/18 00:03:42 - mmengine - INFO - Epoch(train) [11][2400/4632] lr: 2.6275e-02 eta: 0:41:53 time: 0.0997 data_time: 0.0076 memory: 1125 loss: 0.3754 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.3754 2023/04/18 00:03:52 - mmengine - INFO - Epoch(train) [11][2500/4632] lr: 2.6089e-02 eta: 0:41:43 time: 0.0997 data_time: 0.0077 memory: 1125 loss: 0.3242 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.3242 2023/04/18 00:04:02 - mmengine - INFO - Epoch(train) [11][2600/4632] lr: 2.5903e-02 eta: 0:41:34 time: 0.1009 data_time: 0.0083 memory: 1125 loss: 0.3367 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.3367 2023/04/18 00:04:10 - mmengine - INFO - Exp name: stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230417_223936 2023/04/18 00:04:12 - mmengine - INFO - Epoch(train) [11][2700/4632] lr: 2.5717e-02 eta: 0:41:24 time: 0.1003 data_time: 0.0076 memory: 1125 loss: 0.4348 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4348 2023/04/18 00:04:22 - mmengine - INFO - Epoch(train) [11][2800/4632] lr: 2.5532e-02 eta: 0:41:14 time: 0.1009 data_time: 0.0075 memory: 1125 loss: 0.3413 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3413 2023/04/18 00:04:32 - mmengine - INFO - Epoch(train) [11][2900/4632] lr: 2.5348e-02 eta: 0:41:04 time: 0.1007 data_time: 0.0075 memory: 1125 loss: 0.3517 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3517 2023/04/18 00:04:42 - mmengine - INFO - Epoch(train) [11][3000/4632] lr: 2.5164e-02 eta: 0:40:54 time: 0.1004 data_time: 0.0081 memory: 1125 loss: 0.2703 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2703 2023/04/18 00:04:52 - mmengine - INFO - Epoch(train) [11][3100/4632] lr: 2.4980e-02 eta: 0:40:44 time: 0.0999 data_time: 0.0077 memory: 1125 loss: 0.2849 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2849 2023/04/18 00:05:02 - mmengine - INFO - Epoch(train) [11][3200/4632] lr: 2.4797e-02 eta: 0:40:35 time: 0.1003 data_time: 0.0075 memory: 1125 loss: 0.3143 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3143 2023/04/18 00:05:12 - mmengine - INFO - Epoch(train) [11][3300/4632] lr: 2.4614e-02 eta: 0:40:25 time: 0.1004 data_time: 0.0082 memory: 1125 loss: 0.2814 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2814 2023/04/18 00:05:22 - mmengine - INFO - Epoch(train) [11][3400/4632] lr: 2.4431e-02 eta: 0:40:15 time: 0.0997 data_time: 0.0076 memory: 1125 loss: 0.3378 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3378 2023/04/18 00:05:32 - mmengine - INFO - Epoch(train) [11][3500/4632] lr: 2.4249e-02 eta: 0:40:05 time: 0.1000 data_time: 0.0075 memory: 1125 loss: 0.3966 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3966 2023/04/18 00:05:42 - mmengine - INFO - Epoch(train) [11][3600/4632] lr: 2.4068e-02 eta: 0:39:55 time: 0.0997 data_time: 0.0076 memory: 1125 loss: 0.3732 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.3732 2023/04/18 00:05:50 - mmengine - INFO - Exp name: stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230417_223936 2023/04/18 00:05:52 - mmengine - INFO - Epoch(train) [11][3700/4632] lr: 2.3887e-02 eta: 0:39:45 time: 0.0997 data_time: 0.0077 memory: 1125 loss: 0.3334 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3334 2023/04/18 00:06:02 - mmengine - INFO - Epoch(train) [11][3800/4632] lr: 2.3706e-02 eta: 0:39:35 time: 0.0998 data_time: 0.0075 memory: 1125 loss: 0.4094 top1_acc: 0.7500 top5_acc: 0.8125 loss_cls: 0.4094 2023/04/18 00:06:12 - mmengine - INFO - Epoch(train) [11][3900/4632] lr: 2.3526e-02 eta: 0:39:26 time: 0.0995 data_time: 0.0075 memory: 1125 loss: 0.3307 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.3307 2023/04/18 00:06:22 - mmengine - INFO - Epoch(train) [11][4000/4632] lr: 2.3347e-02 eta: 0:39:16 time: 0.0994 data_time: 0.0075 memory: 1125 loss: 0.2770 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2770 2023/04/18 00:06:32 - mmengine - INFO - Epoch(train) [11][4100/4632] lr: 2.3168e-02 eta: 0:39:06 time: 0.0986 data_time: 0.0075 memory: 1125 loss: 0.3274 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3274 2023/04/18 00:06:42 - mmengine - INFO - Epoch(train) [11][4200/4632] lr: 2.2989e-02 eta: 0:38:56 time: 0.0990 data_time: 0.0075 memory: 1125 loss: 0.3276 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3276 2023/04/18 00:06:52 - mmengine - INFO - Epoch(train) [11][4300/4632] lr: 2.2811e-02 eta: 0:38:46 time: 0.0986 data_time: 0.0075 memory: 1125 loss: 0.4501 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4501 2023/04/18 00:07:02 - mmengine - INFO - Epoch(train) [11][4400/4632] lr: 2.2633e-02 eta: 0:38:36 time: 0.0986 data_time: 0.0075 memory: 1125 loss: 0.3383 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 0.3383 2023/04/18 00:07:12 - mmengine - INFO - Epoch(train) [11][4500/4632] lr: 2.2456e-02 eta: 0:38:26 time: 0.0986 data_time: 0.0075 memory: 1125 loss: 0.2860 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.2860 2023/04/18 00:07:21 - mmengine - INFO - Epoch(train) [11][4600/4632] lr: 2.2280e-02 eta: 0:38:16 time: 0.0985 data_time: 0.0075 memory: 1125 loss: 0.3475 top1_acc: 0.7500 top5_acc: 0.8750 loss_cls: 0.3475 2023/04/18 00:07:25 - mmengine - INFO - Exp name: stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230417_223936 2023/04/18 00:07:25 - mmengine - INFO - Epoch(train) [11][4632/4632] lr: 2.2223e-02 eta: 0:38:13 time: 0.0989 data_time: 0.0076 memory: 1125 loss: 0.2280 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2280 2023/04/18 00:07:25 - mmengine - INFO - Saving checkpoint at 11 epochs 2023/04/18 00:07:28 - mmengine - INFO - Epoch(val) [11][100/116] eta: 0:00:00 time: 0.0269 data_time: 0.0064 memory: 171 2023/04/18 00:07:28 - mmengine - INFO - Epoch(val) [11][116/116] acc/top1: 0.8825 acc/top5: 0.9771 acc/mean1: 0.8809data_time: 0.0062 time: 0.0267 2023/04/18 00:07:33 - mmengine - INFO - Exp name: stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230417_223936 2023/04/18 00:07:38 - mmengine - INFO - Epoch(train) [12][ 100/4632] lr: 2.2047e-02 eta: 0:38:03 time: 0.0996 data_time: 0.0080 memory: 1125 loss: 0.3545 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3545 2023/04/18 00:07:49 - mmengine - INFO - Epoch(train) [12][ 200/4632] lr: 2.1872e-02 eta: 0:37:53 time: 0.1062 data_time: 0.0078 memory: 1125 loss: 0.2746 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2746 2023/04/18 00:07:59 - mmengine - INFO - Epoch(train) [12][ 300/4632] lr: 2.1697e-02 eta: 0:37:44 time: 0.1003 data_time: 0.0077 memory: 1125 loss: 0.2311 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2311 2023/04/18 00:08:09 - mmengine - INFO - Epoch(train) [12][ 400/4632] lr: 2.1522e-02 eta: 0:37:34 time: 0.1003 data_time: 0.0075 memory: 1125 loss: 0.3244 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3244 2023/04/18 00:08:19 - mmengine - INFO - Epoch(train) [12][ 500/4632] lr: 2.1348e-02 eta: 0:37:24 time: 0.0998 data_time: 0.0075 memory: 1125 loss: 0.3562 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.3562 2023/04/18 00:08:29 - mmengine - INFO - Epoch(train) [12][ 600/4632] lr: 2.1175e-02 eta: 0:37:14 time: 0.1008 data_time: 0.0075 memory: 1125 loss: 0.2754 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2754 2023/04/18 00:08:39 - mmengine - INFO - Epoch(train) [12][ 700/4632] lr: 2.1002e-02 eta: 0:37:04 time: 0.0998 data_time: 0.0075 memory: 1125 loss: 0.2682 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2682 2023/04/18 00:08:49 - mmengine - INFO - Epoch(train) [12][ 800/4632] lr: 2.0830e-02 eta: 0:36:54 time: 0.0997 data_time: 0.0076 memory: 1125 loss: 0.3014 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 0.3014 2023/04/18 00:08:59 - mmengine - INFO - Epoch(train) [12][ 900/4632] lr: 2.0658e-02 eta: 0:36:45 time: 0.0999 data_time: 0.0082 memory: 1125 loss: 0.2897 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2897 2023/04/18 00:09:09 - mmengine - INFO - Epoch(train) [12][1000/4632] lr: 2.0486e-02 eta: 0:36:35 time: 0.0998 data_time: 0.0075 memory: 1125 loss: 0.4027 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.4027 2023/04/18 00:09:14 - mmengine - INFO - Exp name: stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230417_223936 2023/04/18 00:09:19 - mmengine - INFO - Epoch(train) [12][1100/4632] lr: 2.0316e-02 eta: 0:36:25 time: 0.0997 data_time: 0.0076 memory: 1125 loss: 0.3334 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3334 2023/04/18 00:09:29 - mmengine - INFO - Epoch(train) [12][1200/4632] lr: 2.0145e-02 eta: 0:36:15 time: 0.1003 data_time: 0.0075 memory: 1125 loss: 0.2984 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.2984 2023/04/18 00:09:39 - mmengine - INFO - Epoch(train) [12][1300/4632] lr: 1.9976e-02 eta: 0:36:05 time: 0.0987 data_time: 0.0076 memory: 1125 loss: 0.1940 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1940 2023/04/18 00:09:49 - mmengine - INFO - Epoch(train) [12][1400/4632] lr: 1.9806e-02 eta: 0:35:55 time: 0.0989 data_time: 0.0080 memory: 1125 loss: 0.2693 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2693 2023/04/18 00:09:59 - mmengine - INFO - Epoch(train) [12][1500/4632] lr: 1.9638e-02 eta: 0:35:45 time: 0.0994 data_time: 0.0082 memory: 1125 loss: 0.3607 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3607 2023/04/18 00:10:09 - mmengine - INFO - Epoch(train) [12][1600/4632] lr: 1.9470e-02 eta: 0:35:35 time: 0.1001 data_time: 0.0080 memory: 1125 loss: 0.2985 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2985 2023/04/18 00:10:19 - mmengine - INFO - Epoch(train) [12][1700/4632] lr: 1.9302e-02 eta: 0:35:26 time: 0.1000 data_time: 0.0081 memory: 1125 loss: 0.3026 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3026 2023/04/18 00:10:29 - mmengine - INFO - Epoch(train) [12][1800/4632] lr: 1.9135e-02 eta: 0:35:16 time: 0.1003 data_time: 0.0081 memory: 1125 loss: 0.3120 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3120 2023/04/18 00:10:39 - mmengine - INFO - Epoch(train) [12][1900/4632] lr: 1.8968e-02 eta: 0:35:06 time: 0.1009 data_time: 0.0083 memory: 1125 loss: 0.3708 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3708 2023/04/18 00:10:49 - mmengine - INFO - Epoch(train) [12][2000/4632] lr: 1.8803e-02 eta: 0:34:56 time: 0.1001 data_time: 0.0076 memory: 1125 loss: 0.2683 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 0.2683 2023/04/18 00:10:54 - mmengine - INFO - Exp name: stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230417_223936 2023/04/18 00:10:59 - mmengine - INFO - Epoch(train) [12][2100/4632] lr: 1.8637e-02 eta: 0:34:46 time: 0.1004 data_time: 0.0076 memory: 1125 loss: 0.2405 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2405 2023/04/18 00:11:09 - mmengine - INFO - Epoch(train) [12][2200/4632] lr: 1.8472e-02 eta: 0:34:36 time: 0.1000 data_time: 0.0075 memory: 1125 loss: 0.2686 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2686 2023/04/18 00:11:19 - mmengine - INFO - Epoch(train) [12][2300/4632] lr: 1.8308e-02 eta: 0:34:26 time: 0.1002 data_time: 0.0075 memory: 1125 loss: 0.3487 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.3487 2023/04/18 00:11:29 - mmengine - INFO - Epoch(train) [12][2400/4632] lr: 1.8145e-02 eta: 0:34:17 time: 0.0997 data_time: 0.0075 memory: 1125 loss: 0.3494 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.3494 2023/04/18 00:11:39 - mmengine - INFO - Epoch(train) [12][2500/4632] lr: 1.7981e-02 eta: 0:34:07 time: 0.1005 data_time: 0.0075 memory: 1125 loss: 0.3388 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.3388 2023/04/18 00:11:49 - mmengine - INFO - Epoch(train) [12][2600/4632] lr: 1.7819e-02 eta: 0:33:57 time: 0.0985 data_time: 0.0076 memory: 1125 loss: 0.3379 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.3379 2023/04/18 00:11:59 - mmengine - INFO - Epoch(train) [12][2700/4632] lr: 1.7657e-02 eta: 0:33:47 time: 0.1052 data_time: 0.0076 memory: 1125 loss: 0.3556 top1_acc: 0.8125 top5_acc: 0.9375 loss_cls: 0.3556 2023/04/18 00:12:09 - mmengine - INFO - Epoch(train) [12][2800/4632] lr: 1.7496e-02 eta: 0:33:37 time: 0.0986 data_time: 0.0081 memory: 1125 loss: 0.2973 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2973 2023/04/18 00:12:19 - mmengine - INFO - Epoch(train) [12][2900/4632] lr: 1.7335e-02 eta: 0:33:27 time: 0.0991 data_time: 0.0077 memory: 1125 loss: 0.2630 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2630 2023/04/18 00:12:29 - mmengine - INFO - Epoch(train) [12][3000/4632] lr: 1.7175e-02 eta: 0:33:17 time: 0.0992 data_time: 0.0077 memory: 1125 loss: 0.2880 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.2880 2023/04/18 00:12:34 - mmengine - INFO - Exp name: stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230417_223936 2023/04/18 00:12:39 - mmengine - INFO - Epoch(train) [12][3100/4632] lr: 1.7015e-02 eta: 0:33:07 time: 0.0990 data_time: 0.0076 memory: 1125 loss: 0.3381 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.3381 2023/04/18 00:12:49 - mmengine - INFO - Epoch(train) [12][3200/4632] lr: 1.6856e-02 eta: 0:32:57 time: 0.0993 data_time: 0.0075 memory: 1125 loss: 0.3515 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.3515 2023/04/18 00:12:59 - mmengine - INFO - Epoch(train) [12][3300/4632] lr: 1.6698e-02 eta: 0:32:47 time: 0.0990 data_time: 0.0076 memory: 1125 loss: 0.2814 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2814 2023/04/18 00:13:09 - mmengine - INFO - Epoch(train) [12][3400/4632] lr: 1.6540e-02 eta: 0:32:38 time: 0.0989 data_time: 0.0076 memory: 1125 loss: 0.2998 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2998 2023/04/18 00:13:19 - mmengine - INFO - Epoch(train) [12][3500/4632] lr: 1.6383e-02 eta: 0:32:28 time: 0.0990 data_time: 0.0076 memory: 1125 loss: 0.3110 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3110 2023/04/18 00:13:29 - mmengine - INFO - Epoch(train) [12][3600/4632] lr: 1.6226e-02 eta: 0:32:18 time: 0.1002 data_time: 0.0084 memory: 1125 loss: 0.2802 top1_acc: 0.7500 top5_acc: 0.9375 loss_cls: 0.2802 2023/04/18 00:13:39 - mmengine - INFO - Epoch(train) [12][3700/4632] lr: 1.6070e-02 eta: 0:32:08 time: 0.0999 data_time: 0.0083 memory: 1125 loss: 0.3471 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3471 2023/04/18 00:13:49 - mmengine - INFO - Epoch(train) [12][3800/4632] lr: 1.5915e-02 eta: 0:31:58 time: 0.0990 data_time: 0.0090 memory: 1125 loss: 0.3410 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3410 2023/04/18 00:13:58 - mmengine - INFO - Epoch(train) [12][3900/4632] lr: 1.5760e-02 eta: 0:31:48 time: 0.0991 data_time: 0.0083 memory: 1125 loss: 0.3097 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 0.3097 2023/04/18 00:14:08 - mmengine - INFO - Epoch(train) [12][4000/4632] lr: 1.5606e-02 eta: 0:31:38 time: 0.0991 data_time: 0.0076 memory: 1125 loss: 0.3193 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3193 2023/04/18 00:14:13 - mmengine - INFO - Exp name: stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230417_223936 2023/04/18 00:14:18 - mmengine - INFO - Epoch(train) [12][4100/4632] lr: 1.5452e-02 eta: 0:31:28 time: 0.0988 data_time: 0.0084 memory: 1125 loss: 0.2259 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 0.2259 2023/04/18 00:14:28 - mmengine - INFO - Epoch(train) [12][4200/4632] lr: 1.5300e-02 eta: 0:31:18 time: 0.1008 data_time: 0.0083 memory: 1125 loss: 0.2930 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.2930 2023/04/18 00:14:38 - mmengine - INFO - Epoch(train) [12][4300/4632] lr: 1.5147e-02 eta: 0:31:09 time: 0.1012 data_time: 0.0077 memory: 1125 loss: 0.2573 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2573 2023/04/18 00:14:49 - mmengine - INFO - Epoch(train) [12][4400/4632] lr: 1.4996e-02 eta: 0:30:59 time: 0.1016 data_time: 0.0078 memory: 1125 loss: 0.2891 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2891 2023/04/18 00:14:59 - mmengine - INFO - Epoch(train) [12][4500/4632] lr: 1.4845e-02 eta: 0:30:49 time: 0.1014 data_time: 0.0081 memory: 1125 loss: 0.4410 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.4410 2023/04/18 00:15:09 - mmengine - INFO - Epoch(train) [12][4600/4632] lr: 1.4694e-02 eta: 0:30:39 time: 0.1010 data_time: 0.0076 memory: 1125 loss: 0.3960 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3960 2023/04/18 00:15:12 - mmengine - INFO - Exp name: stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230417_223936 2023/04/18 00:15:12 - mmengine - INFO - Epoch(train) [12][4632/4632] lr: 1.4646e-02 eta: 0:30:36 time: 0.1011 data_time: 0.0085 memory: 1125 loss: 0.3086 top1_acc: 0.6667 top5_acc: 0.8333 loss_cls: 0.3086 2023/04/18 00:15:12 - mmengine - INFO - Saving checkpoint at 12 epochs 2023/04/18 00:15:15 - mmengine - INFO - Epoch(val) [12][100/116] eta: 0:00:00 time: 0.0281 data_time: 0.0066 memory: 171 2023/04/18 00:15:16 - mmengine - INFO - Epoch(val) [12][116/116] acc/top1: 0.8904 acc/top5: 0.9773 acc/mean1: 0.8916data_time: 0.0065 time: 0.0274 2023/04/18 00:15:16 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/hukai/mmaction2/work_dirs/stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_10.pth is removed 2023/04/18 00:15:17 - mmengine - INFO - The best checkpoint with 0.8904 acc/top1 at 12 epoch is saved to best_acc/top1_epoch_12.pth. 2023/04/18 00:15:27 - mmengine - INFO - Epoch(train) [13][ 100/4632] lr: 1.4497e-02 eta: 0:30:26 time: 0.1008 data_time: 0.0076 memory: 1125 loss: 0.2787 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2787 2023/04/18 00:15:37 - mmengine - INFO - Epoch(train) [13][ 200/4632] lr: 1.4348e-02 eta: 0:30:16 time: 0.1011 data_time: 0.0091 memory: 1125 loss: 0.2163 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2163 2023/04/18 00:15:47 - mmengine - INFO - Epoch(train) [13][ 300/4632] lr: 1.4199e-02 eta: 0:30:06 time: 0.1003 data_time: 0.0077 memory: 1125 loss: 0.1981 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1981 2023/04/18 00:15:57 - mmengine - INFO - Epoch(train) [13][ 400/4632] lr: 1.4052e-02 eta: 0:29:56 time: 0.1005 data_time: 0.0076 memory: 1125 loss: 0.3542 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.3542 2023/04/18 00:15:59 - mmengine - INFO - Exp name: stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230417_223936 2023/04/18 00:16:07 - mmengine - INFO - Epoch(train) [13][ 500/4632] lr: 1.3905e-02 eta: 0:29:47 time: 0.1026 data_time: 0.0078 memory: 1125 loss: 0.2482 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2482 2023/04/18 00:16:17 - mmengine - INFO - Epoch(train) [13][ 600/4632] lr: 1.3758e-02 eta: 0:29:37 time: 0.1003 data_time: 0.0084 memory: 1125 loss: 0.2804 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2804 2023/04/18 00:16:27 - mmengine - INFO - Epoch(train) [13][ 700/4632] lr: 1.3613e-02 eta: 0:29:27 time: 0.0991 data_time: 0.0084 memory: 1125 loss: 0.2501 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2501 2023/04/18 00:16:37 - mmengine - INFO - Epoch(train) [13][ 800/4632] lr: 1.3468e-02 eta: 0:29:17 time: 0.0989 data_time: 0.0084 memory: 1125 loss: 0.2213 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.2213 2023/04/18 00:16:47 - mmengine - INFO - Epoch(train) [13][ 900/4632] lr: 1.3323e-02 eta: 0:29:07 time: 0.0985 data_time: 0.0084 memory: 1125 loss: 0.2924 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2924 2023/04/18 00:16:57 - mmengine - INFO - Epoch(train) [13][1000/4632] lr: 1.3180e-02 eta: 0:28:57 time: 0.0985 data_time: 0.0076 memory: 1125 loss: 0.2306 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2306 2023/04/18 00:17:07 - mmengine - INFO - Epoch(train) [13][1100/4632] lr: 1.3037e-02 eta: 0:28:47 time: 0.0990 data_time: 0.0084 memory: 1125 loss: 0.2578 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2578 2023/04/18 00:17:17 - mmengine - INFO - Epoch(train) [13][1200/4632] lr: 1.2894e-02 eta: 0:28:37 time: 0.0990 data_time: 0.0084 memory: 1125 loss: 0.1894 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1894 2023/04/18 00:17:27 - mmengine - INFO - Epoch(train) [13][1300/4632] lr: 1.2752e-02 eta: 0:28:27 time: 0.0989 data_time: 0.0076 memory: 1125 loss: 0.2864 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.2864 2023/04/18 00:17:36 - mmengine - INFO - Epoch(train) [13][1400/4632] lr: 1.2611e-02 eta: 0:28:17 time: 0.0989 data_time: 0.0082 memory: 1125 loss: 0.3153 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.3153 2023/04/18 00:17:38 - mmengine - INFO - Exp name: stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230417_223936 2023/04/18 00:17:46 - mmengine - INFO - Epoch(train) [13][1500/4632] lr: 1.2471e-02 eta: 0:28:07 time: 0.0996 data_time: 0.0076 memory: 1125 loss: 0.2893 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.2893 2023/04/18 00:17:56 - mmengine - INFO - Epoch(train) [13][1600/4632] lr: 1.2331e-02 eta: 0:27:58 time: 0.0994 data_time: 0.0076 memory: 1125 loss: 0.2541 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2541 2023/04/18 00:18:06 - mmengine - INFO - Epoch(train) [13][1700/4632] lr: 1.2192e-02 eta: 0:27:48 time: 0.0991 data_time: 0.0075 memory: 1125 loss: 0.1983 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.1983 2023/04/18 00:18:16 - mmengine - INFO - Epoch(train) [13][1800/4632] lr: 1.2054e-02 eta: 0:27:38 time: 0.0991 data_time: 0.0076 memory: 1125 loss: 0.3305 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.3305 2023/04/18 00:18:26 - mmengine - INFO - Epoch(train) [13][1900/4632] lr: 1.1916e-02 eta: 0:27:28 time: 0.0994 data_time: 0.0085 memory: 1125 loss: 0.2314 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2314 2023/04/18 00:18:36 - mmengine - INFO - Epoch(train) [13][2000/4632] lr: 1.1779e-02 eta: 0:27:18 time: 0.0987 data_time: 0.0076 memory: 1125 loss: 0.2728 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2728 2023/04/18 00:18:46 - mmengine - INFO - Epoch(train) [13][2100/4632] lr: 1.1643e-02 eta: 0:27:08 time: 0.0990 data_time: 0.0077 memory: 1125 loss: 0.2409 top1_acc: 0.6875 top5_acc: 1.0000 loss_cls: 0.2409 2023/04/18 00:18:56 - mmengine - INFO - Epoch(train) [13][2200/4632] lr: 1.1507e-02 eta: 0:26:58 time: 0.0990 data_time: 0.0076 memory: 1125 loss: 0.3073 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3073 2023/04/18 00:19:06 - mmengine - INFO - Epoch(train) [13][2300/4632] lr: 1.1372e-02 eta: 0:26:48 time: 0.0991 data_time: 0.0076 memory: 1125 loss: 0.2135 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2135 2023/04/18 00:19:16 - mmengine - INFO - Epoch(train) [13][2400/4632] lr: 1.1238e-02 eta: 0:26:38 time: 0.0988 data_time: 0.0077 memory: 1125 loss: 0.2109 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2109 2023/04/18 00:19:17 - mmengine - INFO - Exp name: stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230417_223936 2023/04/18 00:19:26 - mmengine - INFO - Epoch(train) [13][2500/4632] lr: 1.1105e-02 eta: 0:26:28 time: 0.0989 data_time: 0.0077 memory: 1125 loss: 0.2358 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2358 2023/04/18 00:19:36 - mmengine - INFO - Epoch(train) [13][2600/4632] lr: 1.0972e-02 eta: 0:26:18 time: 0.0987 data_time: 0.0076 memory: 1125 loss: 0.2155 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2155 2023/04/18 00:19:45 - mmengine - INFO - Epoch(train) [13][2700/4632] lr: 1.0840e-02 eta: 0:26:09 time: 0.0990 data_time: 0.0076 memory: 1125 loss: 0.2918 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2918 2023/04/18 00:19:56 - mmengine - INFO - Epoch(train) [13][2800/4632] lr: 1.0708e-02 eta: 0:25:59 time: 0.1023 data_time: 0.0078 memory: 1125 loss: 0.2386 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2386 2023/04/18 00:20:05 - mmengine - INFO - Epoch(train) [13][2900/4632] lr: 1.0577e-02 eta: 0:25:49 time: 0.0990 data_time: 0.0077 memory: 1125 loss: 0.1930 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1930 2023/04/18 00:20:15 - mmengine - INFO - Epoch(train) [13][3000/4632] lr: 1.0447e-02 eta: 0:25:39 time: 0.0990 data_time: 0.0090 memory: 1125 loss: 0.2344 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2344 2023/04/18 00:20:25 - mmengine - INFO - Epoch(train) [13][3100/4632] lr: 1.0318e-02 eta: 0:25:29 time: 0.0987 data_time: 0.0077 memory: 1125 loss: 0.3352 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.3352 2023/04/18 00:20:35 - mmengine - INFO - Epoch(train) [13][3200/4632] lr: 1.0190e-02 eta: 0:25:19 time: 0.1035 data_time: 0.0092 memory: 1125 loss: 0.2409 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.2409 2023/04/18 00:20:46 - mmengine - INFO - Epoch(train) [13][3300/4632] lr: 1.0062e-02 eta: 0:25:09 time: 0.1010 data_time: 0.0090 memory: 1125 loss: 0.2475 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2475 2023/04/18 00:20:56 - mmengine - INFO - Epoch(train) [13][3400/4632] lr: 9.9345e-03 eta: 0:24:59 time: 0.1001 data_time: 0.0076 memory: 1125 loss: 0.1890 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1890 2023/04/18 00:20:57 - mmengine - INFO - Exp name: stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230417_223936 2023/04/18 00:21:06 - mmengine - INFO - Epoch(train) [13][3500/4632] lr: 9.8081e-03 eta: 0:24:49 time: 0.0991 data_time: 0.0076 memory: 1125 loss: 0.2690 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2690 2023/04/18 00:21:16 - mmengine - INFO - Epoch(train) [13][3600/4632] lr: 9.6824e-03 eta: 0:24:40 time: 0.1003 data_time: 0.0076 memory: 1125 loss: 0.2412 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2412 2023/04/18 00:21:26 - mmengine - INFO - Epoch(train) [13][3700/4632] lr: 9.5574e-03 eta: 0:24:30 time: 0.1006 data_time: 0.0084 memory: 1125 loss: 0.2703 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2703 2023/04/18 00:21:36 - mmengine - INFO - Epoch(train) [13][3800/4632] lr: 9.4331e-03 eta: 0:24:20 time: 0.1005 data_time: 0.0076 memory: 1125 loss: 0.2198 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2198 2023/04/18 00:21:46 - mmengine - INFO - Epoch(train) [13][3900/4632] lr: 9.3096e-03 eta: 0:24:10 time: 0.1032 data_time: 0.0076 memory: 1125 loss: 0.2222 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2222 2023/04/18 00:21:56 - mmengine - INFO - Epoch(train) [13][4000/4632] lr: 9.1868e-03 eta: 0:24:00 time: 0.1017 data_time: 0.0076 memory: 1125 loss: 0.2326 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2326 2023/04/18 00:22:06 - mmengine - INFO - Epoch(train) [13][4100/4632] lr: 9.0647e-03 eta: 0:23:50 time: 0.1016 data_time: 0.0076 memory: 1125 loss: 0.2276 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2276 2023/04/18 00:22:17 - mmengine - INFO - Epoch(train) [13][4200/4632] lr: 8.9434e-03 eta: 0:23:40 time: 0.1025 data_time: 0.0078 memory: 1125 loss: 0.2121 top1_acc: 0.7500 top5_acc: 1.0000 loss_cls: 0.2121 2023/04/18 00:22:27 - mmengine - INFO - Epoch(train) [13][4300/4632] lr: 8.8228e-03 eta: 0:23:31 time: 0.1012 data_time: 0.0077 memory: 1125 loss: 0.1971 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.1971 2023/04/18 00:22:37 - mmengine - INFO - Epoch(train) [13][4400/4632] lr: 8.7029e-03 eta: 0:23:21 time: 0.1027 data_time: 0.0076 memory: 1125 loss: 0.2272 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2272 2023/04/18 00:22:39 - mmengine - INFO - Exp name: stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230417_223936 2023/04/18 00:22:47 - mmengine - INFO - Epoch(train) [13][4500/4632] lr: 8.5838e-03 eta: 0:23:11 time: 0.1011 data_time: 0.0076 memory: 1125 loss: 0.2156 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2156 2023/04/18 00:22:57 - mmengine - INFO - Epoch(train) [13][4600/4632] lr: 8.4654e-03 eta: 0:23:01 time: 0.1023 data_time: 0.0076 memory: 1125 loss: 0.1362 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1362 2023/04/18 00:23:00 - mmengine - INFO - Exp name: stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230417_223936 2023/04/18 00:23:00 - mmengine - INFO - Epoch(train) [13][4632/4632] lr: 8.4277e-03 eta: 0:22:58 time: 0.1017 data_time: 0.0078 memory: 1125 loss: 0.3185 top1_acc: 0.5000 top5_acc: 1.0000 loss_cls: 0.3185 2023/04/18 00:23:00 - mmengine - INFO - Saving checkpoint at 13 epochs 2023/04/18 00:23:04 - mmengine - INFO - Epoch(val) [13][100/116] eta: 0:00:00 time: 0.0280 data_time: 0.0069 memory: 171 2023/04/18 00:23:05 - mmengine - INFO - Epoch(val) [13][116/116] acc/top1: 0.8904 acc/top5: 0.9795 acc/mean1: 0.8881data_time: 0.0061 time: 0.0268 2023/04/18 00:23:15 - mmengine - INFO - Epoch(train) [14][ 100/4632] lr: 8.3103e-03 eta: 0:22:48 time: 0.1009 data_time: 0.0078 memory: 1125 loss: 0.2184 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.2184 2023/04/18 00:23:25 - mmengine - INFO - Epoch(train) [14][ 200/4632] lr: 8.1937e-03 eta: 0:22:38 time: 0.0986 data_time: 0.0077 memory: 1125 loss: 0.1988 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1988 2023/04/18 00:23:34 - mmengine - INFO - Epoch(train) [14][ 300/4632] lr: 8.0778e-03 eta: 0:22:28 time: 0.0986 data_time: 0.0077 memory: 1125 loss: 0.2075 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2075 2023/04/18 00:23:44 - mmengine - INFO - Epoch(train) [14][ 400/4632] lr: 7.9627e-03 eta: 0:22:18 time: 0.0985 data_time: 0.0076 memory: 1125 loss: 0.2615 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2615 2023/04/18 00:23:54 - mmengine - INFO - Epoch(train) [14][ 500/4632] lr: 7.8483e-03 eta: 0:22:08 time: 0.0986 data_time: 0.0077 memory: 1125 loss: 0.2134 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2134 2023/04/18 00:24:04 - mmengine - INFO - Epoch(train) [14][ 600/4632] lr: 7.7347e-03 eta: 0:21:58 time: 0.0986 data_time: 0.0077 memory: 1125 loss: 0.2008 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2008 2023/04/18 00:24:14 - mmengine - INFO - Epoch(train) [14][ 700/4632] lr: 7.6218e-03 eta: 0:21:48 time: 0.0984 data_time: 0.0076 memory: 1125 loss: 0.1094 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1094 2023/04/18 00:24:22 - mmengine - INFO - Exp name: stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230417_223936 2023/04/18 00:24:24 - mmengine - INFO - Epoch(train) [14][ 800/4632] lr: 7.5097e-03 eta: 0:21:38 time: 0.0985 data_time: 0.0077 memory: 1125 loss: 0.2220 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2220 2023/04/18 00:24:34 - mmengine - INFO - Epoch(train) [14][ 900/4632] lr: 7.3984e-03 eta: 0:21:29 time: 0.0996 data_time: 0.0078 memory: 1125 loss: 0.2343 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2343 2023/04/18 00:24:44 - mmengine - INFO - Epoch(train) [14][1000/4632] lr: 7.2878e-03 eta: 0:21:19 time: 0.0993 data_time: 0.0076 memory: 1125 loss: 0.2088 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2088 2023/04/18 00:24:54 - mmengine - INFO - Epoch(train) [14][1100/4632] lr: 7.1780e-03 eta: 0:21:09 time: 0.1009 data_time: 0.0076 memory: 1125 loss: 0.2061 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2061 2023/04/18 00:25:04 - mmengine - INFO - Epoch(train) [14][1200/4632] lr: 7.0690e-03 eta: 0:20:59 time: 0.0992 data_time: 0.0076 memory: 1125 loss: 0.2227 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2227 2023/04/18 00:25:14 - mmengine - INFO - Epoch(train) [14][1300/4632] lr: 6.9607e-03 eta: 0:20:49 time: 0.0996 data_time: 0.0075 memory: 1125 loss: 0.1705 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1705 2023/04/18 00:25:24 - mmengine - INFO - Epoch(train) [14][1400/4632] lr: 6.8532e-03 eta: 0:20:39 time: 0.0996 data_time: 0.0076 memory: 1125 loss: 0.2791 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2791 2023/04/18 00:25:34 - mmengine - INFO - Epoch(train) [14][1500/4632] lr: 6.7465e-03 eta: 0:20:29 time: 0.0995 data_time: 0.0077 memory: 1125 loss: 0.1419 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.1419 2023/04/18 00:25:43 - mmengine - INFO - Epoch(train) [14][1600/4632] lr: 6.6406e-03 eta: 0:20:19 time: 0.0994 data_time: 0.0076 memory: 1125 loss: 0.2367 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2367 2023/04/18 00:25:53 - mmengine - INFO - Epoch(train) [14][1700/4632] lr: 6.5354e-03 eta: 0:20:09 time: 0.1000 data_time: 0.0077 memory: 1125 loss: 0.1112 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1112 2023/04/18 00:26:02 - mmengine - INFO - Exp name: stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230417_223936 2023/04/18 00:26:03 - mmengine - INFO - Epoch(train) [14][1800/4632] lr: 6.4310e-03 eta: 0:19:59 time: 0.0993 data_time: 0.0076 memory: 1125 loss: 0.1436 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1436 2023/04/18 00:26:13 - mmengine - INFO - Epoch(train) [14][1900/4632] lr: 6.3274e-03 eta: 0:19:49 time: 0.0998 data_time: 0.0075 memory: 1125 loss: 0.1976 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.1976 2023/04/18 00:26:23 - mmengine - INFO - Epoch(train) [14][2000/4632] lr: 6.2246e-03 eta: 0:19:39 time: 0.0996 data_time: 0.0076 memory: 1125 loss: 0.1586 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1586 2023/04/18 00:26:33 - mmengine - INFO - Epoch(train) [14][2100/4632] lr: 6.1226e-03 eta: 0:19:30 time: 0.0990 data_time: 0.0076 memory: 1125 loss: 0.1439 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1439 2023/04/18 00:26:43 - mmengine - INFO - Epoch(train) [14][2200/4632] lr: 6.0214e-03 eta: 0:19:20 time: 0.0991 data_time: 0.0075 memory: 1125 loss: 0.1336 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.1336 2023/04/18 00:26:53 - mmengine - INFO - Epoch(train) [14][2300/4632] lr: 5.9209e-03 eta: 0:19:10 time: 0.1001 data_time: 0.0076 memory: 1125 loss: 0.2633 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.2633 2023/04/18 00:27:03 - mmengine - INFO - Epoch(train) [14][2400/4632] lr: 5.8213e-03 eta: 0:19:00 time: 0.0987 data_time: 0.0083 memory: 1125 loss: 0.2130 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.2130 2023/04/18 00:27:13 - mmengine - INFO - Epoch(train) [14][2500/4632] lr: 5.7224e-03 eta: 0:18:50 time: 0.0985 data_time: 0.0075 memory: 1125 loss: 0.1559 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1559 2023/04/18 00:27:23 - mmengine - INFO - Epoch(train) [14][2600/4632] lr: 5.6244e-03 eta: 0:18:40 time: 0.0991 data_time: 0.0076 memory: 1125 loss: 0.1850 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1850 2023/04/18 00:27:33 - mmengine - INFO - Epoch(train) [14][2700/4632] lr: 5.5271e-03 eta: 0:18:30 time: 0.1015 data_time: 0.0077 memory: 1125 loss: 0.1649 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.1649 2023/04/18 00:27:41 - mmengine - INFO - Exp name: stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230417_223936 2023/04/18 00:27:43 - mmengine - INFO - Epoch(train) [14][2800/4632] lr: 5.4306e-03 eta: 0:18:20 time: 0.1010 data_time: 0.0075 memory: 1125 loss: 0.1101 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1101 2023/04/18 00:27:53 - mmengine - INFO - Epoch(train) [14][2900/4632] lr: 5.3350e-03 eta: 0:18:10 time: 0.0989 data_time: 0.0076 memory: 1125 loss: 0.1342 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1342 2023/04/18 00:28:03 - mmengine - INFO - Epoch(train) [14][3000/4632] lr: 5.2401e-03 eta: 0:18:00 time: 0.0990 data_time: 0.0076 memory: 1125 loss: 0.1088 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1088 2023/04/18 00:28:13 - mmengine - INFO - Epoch(train) [14][3100/4632] lr: 5.1461e-03 eta: 0:17:50 time: 0.0987 data_time: 0.0075 memory: 1125 loss: 0.1237 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1237 2023/04/18 00:28:23 - mmengine - INFO - Epoch(train) [14][3200/4632] lr: 5.0528e-03 eta: 0:17:40 time: 0.0987 data_time: 0.0075 memory: 1125 loss: 0.1275 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1275 2023/04/18 00:28:32 - mmengine - INFO - Epoch(train) [14][3300/4632] lr: 4.9604e-03 eta: 0:17:31 time: 0.0987 data_time: 0.0076 memory: 1125 loss: 0.2083 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.2083 2023/04/18 00:28:42 - mmengine - INFO - Epoch(train) [14][3400/4632] lr: 4.8687e-03 eta: 0:17:21 time: 0.0996 data_time: 0.0082 memory: 1125 loss: 0.1432 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.1432 2023/04/18 00:28:52 - mmengine - INFO - Epoch(train) [14][3500/4632] lr: 4.7779e-03 eta: 0:17:11 time: 0.0989 data_time: 0.0075 memory: 1125 loss: 0.2243 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.2243 2023/04/18 00:29:02 - mmengine - INFO - Epoch(train) [14][3600/4632] lr: 4.6879e-03 eta: 0:17:01 time: 0.0992 data_time: 0.0076 memory: 1125 loss: 0.1159 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1159 2023/04/18 00:29:12 - mmengine - INFO - Epoch(train) [14][3700/4632] lr: 4.5987e-03 eta: 0:16:51 time: 0.0987 data_time: 0.0075 memory: 1125 loss: 0.1798 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1798 2023/04/18 00:29:20 - mmengine - INFO - Exp name: stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230417_223936 2023/04/18 00:29:22 - mmengine - INFO - Epoch(train) [14][3800/4632] lr: 4.5103e-03 eta: 0:16:41 time: 0.0987 data_time: 0.0075 memory: 1125 loss: 0.0847 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0847 2023/04/18 00:29:32 - mmengine - INFO - Epoch(train) [14][3900/4632] lr: 4.4228e-03 eta: 0:16:31 time: 0.1002 data_time: 0.0076 memory: 1125 loss: 0.1918 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1918 2023/04/18 00:29:42 - mmengine - INFO - Epoch(train) [14][4000/4632] lr: 4.3360e-03 eta: 0:16:21 time: 0.1006 data_time: 0.0080 memory: 1125 loss: 0.1241 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1241 2023/04/18 00:29:52 - mmengine - INFO - Epoch(train) [14][4100/4632] lr: 4.2501e-03 eta: 0:16:11 time: 0.1001 data_time: 0.0076 memory: 1125 loss: 0.1645 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1645 2023/04/18 00:30:02 - mmengine - INFO - Epoch(train) [14][4200/4632] lr: 4.1650e-03 eta: 0:16:01 time: 0.1002 data_time: 0.0079 memory: 1125 loss: 0.0903 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0903 2023/04/18 00:30:12 - mmengine - INFO - Epoch(train) [14][4300/4632] lr: 4.0807e-03 eta: 0:15:51 time: 0.0998 data_time: 0.0075 memory: 1125 loss: 0.1366 top1_acc: 0.8750 top5_acc: 0.9375 loss_cls: 0.1366 2023/04/18 00:30:22 - mmengine - INFO - Epoch(train) [14][4400/4632] lr: 3.9973e-03 eta: 0:15:41 time: 0.1002 data_time: 0.0075 memory: 1125 loss: 0.0808 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0808 2023/04/18 00:30:32 - mmengine - INFO - Epoch(train) [14][4500/4632] lr: 3.9146e-03 eta: 0:15:32 time: 0.1007 data_time: 0.0076 memory: 1125 loss: 0.1498 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1498 2023/04/18 00:30:42 - mmengine - INFO - Epoch(train) [14][4600/4632] lr: 3.8328e-03 eta: 0:15:22 time: 0.1001 data_time: 0.0078 memory: 1125 loss: 0.1049 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1049 2023/04/18 00:30:45 - mmengine - INFO - Exp name: stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230417_223936 2023/04/18 00:30:45 - mmengine - INFO - Epoch(train) [14][4632/4632] lr: 3.8068e-03 eta: 0:15:18 time: 0.0998 data_time: 0.0079 memory: 1125 loss: 0.1529 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1529 2023/04/18 00:30:45 - mmengine - INFO - Saving checkpoint at 14 epochs 2023/04/18 00:30:49 - mmengine - INFO - Epoch(val) [14][100/116] eta: 0:00:00 time: 0.0283 data_time: 0.0072 memory: 171 2023/04/18 00:30:50 - mmengine - INFO - Epoch(val) [14][116/116] acc/top1: 0.8907 acc/top5: 0.9778 acc/mean1: 0.8882data_time: 0.0063 time: 0.0268 2023/04/18 00:30:50 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/hukai/mmaction2/work_dirs/stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_12.pth is removed 2023/04/18 00:30:50 - mmengine - INFO - The best checkpoint with 0.8907 acc/top1 at 14 epoch is saved to best_acc/top1_epoch_14.pth. 2023/04/18 00:31:00 - mmengine - INFO - Epoch(train) [15][ 100/4632] lr: 3.7261e-03 eta: 0:15:09 time: 0.1001 data_time: 0.0079 memory: 1125 loss: 0.1160 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1160 2023/04/18 00:31:05 - mmengine - INFO - Exp name: stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230417_223936 2023/04/18 00:31:10 - mmengine - INFO - Epoch(train) [15][ 200/4632] lr: 3.6463e-03 eta: 0:14:59 time: 0.1014 data_time: 0.0076 memory: 1125 loss: 0.1832 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1832 2023/04/18 00:31:20 - mmengine - INFO - Epoch(train) [15][ 300/4632] lr: 3.5672e-03 eta: 0:14:49 time: 0.1007 data_time: 0.0078 memory: 1125 loss: 0.1389 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1389 2023/04/18 00:31:30 - mmengine - INFO - Epoch(train) [15][ 400/4632] lr: 3.4890e-03 eta: 0:14:39 time: 0.1012 data_time: 0.0076 memory: 1125 loss: 0.1544 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1544 2023/04/18 00:31:40 - mmengine - INFO - Epoch(train) [15][ 500/4632] lr: 3.4117e-03 eta: 0:14:29 time: 0.0984 data_time: 0.0084 memory: 1125 loss: 0.1169 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1169 2023/04/18 00:31:51 - mmengine - INFO - Epoch(train) [15][ 600/4632] lr: 3.3351e-03 eta: 0:14:19 time: 0.1010 data_time: 0.0076 memory: 1125 loss: 0.1219 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1219 2023/04/18 00:32:00 - mmengine - INFO - Epoch(train) [15][ 700/4632] lr: 3.2594e-03 eta: 0:14:09 time: 0.0994 data_time: 0.0076 memory: 1125 loss: 0.1203 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1203 2023/04/18 00:32:11 - mmengine - INFO - Epoch(train) [15][ 800/4632] lr: 3.1846e-03 eta: 0:13:59 time: 0.1006 data_time: 0.0075 memory: 1125 loss: 0.1174 top1_acc: 0.8125 top5_acc: 1.0000 loss_cls: 0.1174 2023/04/18 00:32:21 - mmengine - INFO - Epoch(train) [15][ 900/4632] lr: 3.1106e-03 eta: 0:13:49 time: 0.1005 data_time: 0.0076 memory: 1125 loss: 0.1213 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1213 2023/04/18 00:32:31 - mmengine - INFO - Epoch(train) [15][1000/4632] lr: 3.0374e-03 eta: 0:13:39 time: 0.1008 data_time: 0.0081 memory: 1125 loss: 0.1185 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1185 2023/04/18 00:32:41 - mmengine - INFO - Epoch(train) [15][1100/4632] lr: 2.9651e-03 eta: 0:13:30 time: 0.1020 data_time: 0.0075 memory: 1125 loss: 0.1045 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.1045 2023/04/18 00:32:46 - mmengine - INFO - Exp name: stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230417_223936 2023/04/18 00:32:51 - mmengine - INFO - Epoch(train) [15][1200/4632] lr: 2.8936e-03 eta: 0:13:20 time: 0.1014 data_time: 0.0083 memory: 1125 loss: 0.0654 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0654 2023/04/18 00:33:01 - mmengine - INFO - Epoch(train) [15][1300/4632] lr: 2.8230e-03 eta: 0:13:10 time: 0.1016 data_time: 0.0076 memory: 1125 loss: 0.0858 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.0858 2023/04/18 00:33:11 - mmengine - INFO - Epoch(train) [15][1400/4632] lr: 2.7532e-03 eta: 0:13:00 time: 0.1008 data_time: 0.0079 memory: 1125 loss: 0.0678 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0678 2023/04/18 00:33:21 - mmengine - INFO - Epoch(train) [15][1500/4632] lr: 2.6842e-03 eta: 0:12:50 time: 0.1011 data_time: 0.0075 memory: 1125 loss: 0.0948 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.0948 2023/04/18 00:33:32 - mmengine - INFO - Epoch(train) [15][1600/4632] lr: 2.6162e-03 eta: 0:12:40 time: 0.1016 data_time: 0.0076 memory: 1125 loss: 0.0816 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0816 2023/04/18 00:33:42 - mmengine - INFO - Epoch(train) [15][1700/4632] lr: 2.5489e-03 eta: 0:12:30 time: 0.1023 data_time: 0.0076 memory: 1125 loss: 0.0925 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0925 2023/04/18 00:33:52 - mmengine - INFO - Epoch(train) [15][1800/4632] lr: 2.4825e-03 eta: 0:12:20 time: 0.1023 data_time: 0.0076 memory: 1125 loss: 0.0878 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0878 2023/04/18 00:34:02 - mmengine - INFO - Epoch(train) [15][1900/4632] lr: 2.4170e-03 eta: 0:12:10 time: 0.1002 data_time: 0.0077 memory: 1125 loss: 0.1140 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1140 2023/04/18 00:34:12 - mmengine - INFO - Epoch(train) [15][2000/4632] lr: 2.3523e-03 eta: 0:12:00 time: 0.0995 data_time: 0.0076 memory: 1125 loss: 0.0916 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0916 2023/04/18 00:34:22 - mmengine - INFO - Epoch(train) [15][2100/4632] lr: 2.2885e-03 eta: 0:11:51 time: 0.0996 data_time: 0.0076 memory: 1125 loss: 0.0988 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.0988 2023/04/18 00:34:27 - mmengine - INFO - Exp name: stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230417_223936 2023/04/18 00:34:32 - mmengine - INFO - Epoch(train) [15][2200/4632] lr: 2.2256e-03 eta: 0:11:41 time: 0.1007 data_time: 0.0077 memory: 1125 loss: 0.0872 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0872 2023/04/18 00:34:42 - mmengine - INFO - Epoch(train) [15][2300/4632] lr: 2.1635e-03 eta: 0:11:31 time: 0.1031 data_time: 0.0076 memory: 1125 loss: 0.0662 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0662 2023/04/18 00:34:52 - mmengine - INFO - Epoch(train) [15][2400/4632] lr: 2.1022e-03 eta: 0:11:21 time: 0.0997 data_time: 0.0077 memory: 1125 loss: 0.0974 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0974 2023/04/18 00:35:02 - mmengine - INFO - Epoch(train) [15][2500/4632] lr: 2.0418e-03 eta: 0:11:11 time: 0.1002 data_time: 0.0091 memory: 1125 loss: 0.0651 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0651 2023/04/18 00:35:12 - mmengine - INFO - Epoch(train) [15][2600/4632] lr: 1.9823e-03 eta: 0:11:01 time: 0.1009 data_time: 0.0077 memory: 1125 loss: 0.1098 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1098 2023/04/18 00:35:23 - mmengine - INFO - Epoch(train) [15][2700/4632] lr: 1.9237e-03 eta: 0:10:51 time: 0.1010 data_time: 0.0084 memory: 1125 loss: 0.0661 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0661 2023/04/18 00:35:33 - mmengine - INFO - Epoch(train) [15][2800/4632] lr: 1.8659e-03 eta: 0:10:41 time: 0.0997 data_time: 0.0084 memory: 1125 loss: 0.0702 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0702 2023/04/18 00:35:43 - mmengine - INFO - Epoch(train) [15][2900/4632] lr: 1.8089e-03 eta: 0:10:31 time: 0.1017 data_time: 0.0076 memory: 1125 loss: 0.0769 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0769 2023/04/18 00:35:53 - mmengine - INFO - Epoch(train) [15][3000/4632] lr: 1.7529e-03 eta: 0:10:21 time: 0.1020 data_time: 0.0076 memory: 1125 loss: 0.0489 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0489 2023/04/18 00:36:03 - mmengine - INFO - Epoch(train) [15][3100/4632] lr: 1.6977e-03 eta: 0:10:11 time: 0.1008 data_time: 0.0076 memory: 1125 loss: 0.0951 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0951 2023/04/18 00:36:08 - mmengine - INFO - Exp name: stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230417_223936 2023/04/18 00:36:13 - mmengine - INFO - Epoch(train) [15][3200/4632] lr: 1.6434e-03 eta: 0:10:02 time: 0.1016 data_time: 0.0076 memory: 1125 loss: 0.0663 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0663 2023/04/18 00:36:24 - mmengine - INFO - Epoch(train) [15][3300/4632] lr: 1.5899e-03 eta: 0:09:52 time: 0.1017 data_time: 0.0076 memory: 1125 loss: 0.0988 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0988 2023/04/18 00:36:34 - mmengine - INFO - Epoch(train) [15][3400/4632] lr: 1.5373e-03 eta: 0:09:42 time: 0.0995 data_time: 0.0076 memory: 1125 loss: 0.0926 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0926 2023/04/18 00:36:44 - mmengine - INFO - Epoch(train) [15][3500/4632] lr: 1.4856e-03 eta: 0:09:32 time: 0.0997 data_time: 0.0076 memory: 1125 loss: 0.0883 top1_acc: 0.9375 top5_acc: 0.9375 loss_cls: 0.0883 2023/04/18 00:36:54 - mmengine - INFO - Epoch(train) [15][3600/4632] lr: 1.4347e-03 eta: 0:09:22 time: 0.0996 data_time: 0.0077 memory: 1125 loss: 0.0786 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0786 2023/04/18 00:37:04 - mmengine - INFO - Epoch(train) [15][3700/4632] lr: 1.3848e-03 eta: 0:09:12 time: 0.0998 data_time: 0.0076 memory: 1125 loss: 0.0696 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0696 2023/04/18 00:37:14 - mmengine - INFO - Epoch(train) [15][3800/4632] lr: 1.3357e-03 eta: 0:09:02 time: 0.0997 data_time: 0.0076 memory: 1125 loss: 0.0675 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0675 2023/04/18 00:37:24 - mmengine - INFO - Epoch(train) [15][3900/4632] lr: 1.2874e-03 eta: 0:08:52 time: 0.0994 data_time: 0.0083 memory: 1125 loss: 0.1100 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.1100 2023/04/18 00:37:34 - mmengine - INFO - Epoch(train) [15][4000/4632] lr: 1.2401e-03 eta: 0:08:42 time: 0.1005 data_time: 0.0083 memory: 1125 loss: 0.0553 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0553 2023/04/18 00:37:44 - mmengine - INFO - Epoch(train) [15][4100/4632] lr: 1.1936e-03 eta: 0:08:32 time: 0.1018 data_time: 0.0077 memory: 1125 loss: 0.0789 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0789 2023/04/18 00:37:49 - mmengine - INFO - Exp name: stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230417_223936 2023/04/18 00:37:54 - mmengine - INFO - Epoch(train) [15][4200/4632] lr: 1.1480e-03 eta: 0:08:22 time: 0.0996 data_time: 0.0076 memory: 1125 loss: 0.0626 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0626 2023/04/18 00:38:04 - mmengine - INFO - Epoch(train) [15][4300/4632] lr: 1.1033e-03 eta: 0:08:12 time: 0.1012 data_time: 0.0082 memory: 1125 loss: 0.0516 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0516 2023/04/18 00:38:14 - mmengine - INFO - Epoch(train) [15][4400/4632] lr: 1.0595e-03 eta: 0:08:03 time: 0.1029 data_time: 0.0076 memory: 1125 loss: 0.0604 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0604 2023/04/18 00:38:24 - mmengine - INFO - Epoch(train) [15][4500/4632] lr: 1.0165e-03 eta: 0:07:53 time: 0.1015 data_time: 0.0076 memory: 1125 loss: 0.0577 top1_acc: 0.8750 top5_acc: 1.0000 loss_cls: 0.0577 2023/04/18 00:38:34 - mmengine - INFO - Epoch(train) [15][4600/4632] lr: 9.7443e-04 eta: 0:07:43 time: 0.0998 data_time: 0.0077 memory: 1125 loss: 0.0623 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0623 2023/04/18 00:38:38 - mmengine - INFO - Exp name: stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230417_223936 2023/04/18 00:38:38 - mmengine - INFO - Epoch(train) [15][4632/4632] lr: 9.6115e-04 eta: 0:07:40 time: 0.0997 data_time: 0.0078 memory: 1125 loss: 0.0999 top1_acc: 0.8333 top5_acc: 1.0000 loss_cls: 0.0999 2023/04/18 00:38:38 - mmengine - INFO - Saving checkpoint at 15 epochs 2023/04/18 00:38:41 - mmengine - INFO - Epoch(val) [15][100/116] eta: 0:00:00 time: 0.0272 data_time: 0.0065 memory: 171 2023/04/18 00:38:42 - mmengine - INFO - Epoch(val) [15][116/116] acc/top1: 0.8921 acc/top5: 0.9763 acc/mean1: 0.8936data_time: 0.0064 time: 0.0269 2023/04/18 00:38:42 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/hukai/mmaction2/work_dirs/stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_14.pth is removed 2023/04/18 00:38:42 - mmengine - INFO - The best checkpoint with 0.8921 acc/top1 at 15 epoch is saved to best_acc/top1_epoch_15.pth. 2023/04/18 00:38:52 - mmengine - INFO - Epoch(train) [16][ 100/4632] lr: 9.2023e-04 eta: 0:07:30 time: 0.0989 data_time: 0.0078 memory: 1125 loss: 0.0437 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0437 2023/04/18 00:39:02 - mmengine - INFO - Epoch(train) [16][ 200/4632] lr: 8.8020e-04 eta: 0:07:20 time: 0.1010 data_time: 0.0077 memory: 1125 loss: 0.0439 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0439 2023/04/18 00:39:12 - mmengine - INFO - Epoch(train) [16][ 300/4632] lr: 8.4104e-04 eta: 0:07:10 time: 0.0995 data_time: 0.0077 memory: 1125 loss: 0.0412 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0412 2023/04/18 00:39:22 - mmengine - INFO - Epoch(train) [16][ 400/4632] lr: 8.0277e-04 eta: 0:07:00 time: 0.0995 data_time: 0.0076 memory: 1125 loss: 0.0371 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0371 2023/04/18 00:39:32 - mmengine - INFO - Epoch(train) [16][ 500/4632] lr: 7.6539e-04 eta: 0:06:50 time: 0.0993 data_time: 0.0076 memory: 1125 loss: 0.0603 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0603 2023/04/18 00:39:34 - mmengine - INFO - Exp name: stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230417_223936 2023/04/18 00:39:42 - mmengine - INFO - Epoch(train) [16][ 600/4632] lr: 7.2889e-04 eta: 0:06:40 time: 0.0989 data_time: 0.0076 memory: 1125 loss: 0.0556 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0556 2023/04/18 00:39:52 - mmengine - INFO - Epoch(train) [16][ 700/4632] lr: 6.9327e-04 eta: 0:06:30 time: 0.0986 data_time: 0.0076 memory: 1125 loss: 0.0546 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0546 2023/04/18 00:40:02 - mmengine - INFO - Epoch(train) [16][ 800/4632] lr: 6.5854e-04 eta: 0:06:20 time: 0.0996 data_time: 0.0078 memory: 1125 loss: 0.0634 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0634 2023/04/18 00:40:11 - mmengine - INFO - Epoch(train) [16][ 900/4632] lr: 6.2470e-04 eta: 0:06:10 time: 0.0988 data_time: 0.0076 memory: 1125 loss: 0.0323 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0323 2023/04/18 00:40:21 - mmengine - INFO - Epoch(train) [16][1000/4632] lr: 5.9175e-04 eta: 0:06:00 time: 0.0990 data_time: 0.0076 memory: 1125 loss: 0.0864 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0864 2023/04/18 00:40:31 - mmengine - INFO - Epoch(train) [16][1100/4632] lr: 5.5968e-04 eta: 0:05:50 time: 0.0989 data_time: 0.0076 memory: 1125 loss: 0.0657 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0657 2023/04/18 00:40:41 - mmengine - INFO - Epoch(train) [16][1200/4632] lr: 5.2850e-04 eta: 0:05:40 time: 0.0995 data_time: 0.0077 memory: 1125 loss: 0.0503 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0503 2023/04/18 00:40:51 - mmengine - INFO - Epoch(train) [16][1300/4632] lr: 4.9821e-04 eta: 0:05:30 time: 0.0983 data_time: 0.0077 memory: 1125 loss: 0.0339 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0339 2023/04/18 00:41:01 - mmengine - INFO - Epoch(train) [16][1400/4632] lr: 4.6881e-04 eta: 0:05:20 time: 0.1004 data_time: 0.0076 memory: 1125 loss: 0.0600 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0600 2023/04/18 00:41:11 - mmengine - INFO - Epoch(train) [16][1500/4632] lr: 4.4030e-04 eta: 0:05:11 time: 0.1000 data_time: 0.0077 memory: 1125 loss: 0.0411 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0411 2023/04/18 00:41:13 - mmengine - INFO - Exp name: stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230417_223936 2023/04/18 00:41:21 - mmengine - INFO - Epoch(train) [16][1600/4632] lr: 4.1268e-04 eta: 0:05:01 time: 0.1001 data_time: 0.0076 memory: 1125 loss: 0.0459 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0459 2023/04/18 00:41:31 - mmengine - INFO - Epoch(train) [16][1700/4632] lr: 3.8595e-04 eta: 0:04:51 time: 0.0993 data_time: 0.0078 memory: 1125 loss: 0.0422 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0422 2023/04/18 00:41:41 - mmengine - INFO - Epoch(train) [16][1800/4632] lr: 3.6011e-04 eta: 0:04:41 time: 0.0988 data_time: 0.0078 memory: 1125 loss: 0.0827 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0827 2023/04/18 00:41:51 - mmengine - INFO - Epoch(train) [16][1900/4632] lr: 3.3516e-04 eta: 0:04:31 time: 0.0987 data_time: 0.0077 memory: 1125 loss: 0.0360 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0360 2023/04/18 00:42:01 - mmengine - INFO - Epoch(train) [16][2000/4632] lr: 3.1111e-04 eta: 0:04:21 time: 0.0991 data_time: 0.0082 memory: 1125 loss: 0.0291 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0291 2023/04/18 00:42:11 - mmengine - INFO - Epoch(train) [16][2100/4632] lr: 2.8795e-04 eta: 0:04:11 time: 0.0985 data_time: 0.0084 memory: 1125 loss: 0.0502 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0502 2023/04/18 00:42:21 - mmengine - INFO - Epoch(train) [16][2200/4632] lr: 2.6568e-04 eta: 0:04:01 time: 0.0985 data_time: 0.0076 memory: 1125 loss: 0.0298 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0298 2023/04/18 00:42:30 - mmengine - INFO - Epoch(train) [16][2300/4632] lr: 2.4431e-04 eta: 0:03:51 time: 0.0997 data_time: 0.0077 memory: 1125 loss: 0.0541 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0541 2023/04/18 00:42:41 - mmengine - INFO - Epoch(train) [16][2400/4632] lr: 2.2383e-04 eta: 0:03:41 time: 0.1027 data_time: 0.0077 memory: 1125 loss: 0.0606 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0606 2023/04/18 00:42:51 - mmengine - INFO - Epoch(train) [16][2500/4632] lr: 2.0424e-04 eta: 0:03:31 time: 0.0987 data_time: 0.0076 memory: 1125 loss: 0.0466 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0466 2023/04/18 00:42:53 - mmengine - INFO - Exp name: stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230417_223936 2023/04/18 00:43:01 - mmengine - INFO - Epoch(train) [16][2600/4632] lr: 1.8555e-04 eta: 0:03:21 time: 0.0988 data_time: 0.0077 memory: 1125 loss: 0.0430 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0430 2023/04/18 00:43:11 - mmengine - INFO - Epoch(train) [16][2700/4632] lr: 1.6776e-04 eta: 0:03:11 time: 0.1005 data_time: 0.0076 memory: 1125 loss: 0.0392 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0392 2023/04/18 00:43:21 - mmengine - INFO - Epoch(train) [16][2800/4632] lr: 1.5086e-04 eta: 0:03:01 time: 0.1000 data_time: 0.0078 memory: 1125 loss: 0.0379 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0379 2023/04/18 00:43:31 - mmengine - INFO - Epoch(train) [16][2900/4632] lr: 1.3485e-04 eta: 0:02:52 time: 0.0999 data_time: 0.0077 memory: 1125 loss: 0.0347 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0347 2023/04/18 00:43:41 - mmengine - INFO - Epoch(train) [16][3000/4632] lr: 1.1975e-04 eta: 0:02:42 time: 0.1003 data_time: 0.0076 memory: 1125 loss: 0.0720 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0720 2023/04/18 00:43:51 - mmengine - INFO - Epoch(train) [16][3100/4632] lr: 1.0553e-04 eta: 0:02:32 time: 0.1014 data_time: 0.0076 memory: 1125 loss: 0.0228 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0228 2023/04/18 00:44:01 - mmengine - INFO - Epoch(train) [16][3200/4632] lr: 9.2219e-05 eta: 0:02:22 time: 0.1008 data_time: 0.0078 memory: 1125 loss: 0.0337 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0337 2023/04/18 00:44:11 - mmengine - INFO - Epoch(train) [16][3300/4632] lr: 7.9801e-05 eta: 0:02:12 time: 0.1008 data_time: 0.0076 memory: 1125 loss: 0.0505 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0505 2023/04/18 00:44:21 - mmengine - INFO - Epoch(train) [16][3400/4632] lr: 6.8279e-05 eta: 0:02:02 time: 0.0995 data_time: 0.0076 memory: 1125 loss: 0.0526 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0526 2023/04/18 00:44:31 - mmengine - INFO - Epoch(train) [16][3500/4632] lr: 5.7655e-05 eta: 0:01:52 time: 0.1011 data_time: 0.0077 memory: 1125 loss: 0.0691 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0691 2023/04/18 00:44:33 - mmengine - INFO - Exp name: stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230417_223936 2023/04/18 00:44:41 - mmengine - INFO - Epoch(train) [16][3600/4632] lr: 4.7929e-05 eta: 0:01:42 time: 0.1014 data_time: 0.0078 memory: 1125 loss: 0.0281 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0281 2023/04/18 00:44:52 - mmengine - INFO - Epoch(train) [16][3700/4632] lr: 3.9099e-05 eta: 0:01:32 time: 0.1021 data_time: 0.0076 memory: 1125 loss: 0.0427 top1_acc: 0.9375 top5_acc: 1.0000 loss_cls: 0.0427 2023/04/18 00:45:02 - mmengine - INFO - Epoch(train) [16][3800/4632] lr: 3.1168e-05 eta: 0:01:22 time: 0.0995 data_time: 0.0076 memory: 1125 loss: 0.0366 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0366 2023/04/18 00:45:12 - mmengine - INFO - Epoch(train) [16][3900/4632] lr: 2.4134e-05 eta: 0:01:12 time: 0.1007 data_time: 0.0076 memory: 1125 loss: 0.0430 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0430 2023/04/18 00:45:22 - mmengine - INFO - Epoch(train) [16][4000/4632] lr: 1.7999e-05 eta: 0:01:02 time: 0.1020 data_time: 0.0076 memory: 1125 loss: 0.0503 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0503 2023/04/18 00:45:32 - mmengine - INFO - Epoch(train) [16][4100/4632] lr: 1.2761e-05 eta: 0:00:52 time: 0.1015 data_time: 0.0077 memory: 1125 loss: 0.0469 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0469 2023/04/18 00:45:42 - mmengine - INFO - Epoch(train) [16][4200/4632] lr: 8.4222e-06 eta: 0:00:42 time: 0.1008 data_time: 0.0077 memory: 1125 loss: 0.0400 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0400 2023/04/18 00:45:52 - mmengine - INFO - Epoch(train) [16][4300/4632] lr: 4.9813e-06 eta: 0:00:32 time: 0.1023 data_time: 0.0076 memory: 1125 loss: 0.0514 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0514 2023/04/18 00:46:03 - mmengine - INFO - Epoch(train) [16][4400/4632] lr: 2.4388e-06 eta: 0:00:23 time: 0.1016 data_time: 0.0091 memory: 1125 loss: 0.0425 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0425 2023/04/18 00:46:13 - mmengine - INFO - Epoch(train) [16][4500/4632] lr: 7.9463e-07 eta: 0:00:13 time: 0.1016 data_time: 0.0076 memory: 1125 loss: 0.0459 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0459 2023/04/18 00:46:15 - mmengine - INFO - Exp name: stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230417_223936 2023/04/18 00:46:23 - mmengine - INFO - Epoch(train) [16][4600/4632] lr: 4.8920e-08 eta: 0:00:03 time: 0.1017 data_time: 0.0076 memory: 1125 loss: 0.0339 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0339 2023/04/18 00:46:26 - mmengine - INFO - Exp name: stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d_20230417_223936 2023/04/18 00:46:26 - mmengine - INFO - Epoch(train) [16][4632/4632] lr: 4.4922e-11 eta: 0:00:00 time: 0.1012 data_time: 0.0077 memory: 1125 loss: 0.0450 top1_acc: 1.0000 top5_acc: 1.0000 loss_cls: 0.0450 2023/04/18 00:46:26 - mmengine - INFO - Saving checkpoint at 16 epochs 2023/04/18 00:46:30 - mmengine - INFO - Epoch(val) [16][100/116] eta: 0:00:00 time: 0.0284 data_time: 0.0067 memory: 171 2023/04/18 00:46:31 - mmengine - INFO - Epoch(val) [16][116/116] acc/top1: 0.8922 acc/top5: 0.9752 acc/mean1: 0.8933data_time: 0.0067 time: 0.0273 2023/04/18 00:46:31 - mmengine - INFO - The previous best checkpoint /mnt/petrelfs/hukai/mmaction2/work_dirs/stgcnpp_8xb16-joint-u100-80e_ntu60-xsub-keypoint-2d/best_acc/top1_epoch_15.pth is removed 2023/04/18 00:46:31 - mmengine - INFO - The best checkpoint with 0.8922 acc/top1 at 16 epoch is saved to best_acc/top1_epoch_16.pth.