2021-06-06 01:01:56,041 - mmaction - INFO - Environment info: ------------------------------------------------------------ sys.platform: linux Python: 3.7.6 (default, Jan 8 2020, 19:59:22) [GCC 7.3.0] CUDA available: True GPU 0,1,2,3,4,5,6,7: GeForce GTX 1080 Ti CUDA_HOME: /mnt/lustrenvme/share/polaris/dep/cuda-9.0-cudnn7.6.5 NVCC: Cuda compilation tools, release 9.0, V9.0.176 GCC: gcc (GCC) 5.4.0 PyTorch: 1.5.0 PyTorch compiling details: PyTorch built with: - GCC 5.4 - C++ Version: 201402 - Intel(R) Math Kernel Library Version 2020.0.1 Product Build 20200208 for Intel(R) 64 architecture applications - Intel(R) MKL-DNN v0.21.1 (Git Hash 912ce228837d1ce28e1a61806118835de03f5751) - OpenMP 201307 (a.k.a. OpenMP 4.0) - NNPACK is enabled - CPU capability usage: AVX2 - CUDA Runtime 9.0 - NVCC architecture flags: -gencode;arch=compute_52,code=sm_52;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_61,code=sm_61;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_70,code=compute_70 - CuDNN 7.6.5 - Magma 2.5.0 - Build settings: BLAS=MKL, BUILD_TYPE=Release, CXX_FLAGS= -Wno-deprecated -fvisibility-inlines-hidden -fopenmp -DNDEBUG -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DUSE_INTERNAL_THREADPOOL_IMPL -O2 -fPIC -Wno-narrowing -Wall -Wextra -Werror=return-type -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wno-sign-compare -Wno-unused-parameter -Wno-unused-variable -Wno-unused-function -Wno-unused-result -Wno-strict-overflow -Wno-strict-aliasing -Wno-error=deprecated-declarations -Wno-error=pedantic -Wno-error=redundant-decls -Wno-error=old-style-cast -fdiagnostics-color=always -Wno-unused-but-set-variable -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Werror=format, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, USE_CUDA=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=ON, USE_NCCL=ON, USE_NNPACK=ON, USE_OPENMP=ON, USE_STATIC_DISPATCH=OFF, TorchVision: 0.6.0 OpenCV: 4.2.0 MMCV: 1.3.1 MMCV Compiler: GCC 5.4 MMCV CUDA Compiler: 9.0 MMAction2: 0.15.0+985d284 ------------------------------------------------------------ 2021-06-06 01:01:56,042 - mmaction - INFO - Distributed training: True 2021-06-06 01:01:57,057 - mmaction - INFO - Config: checkpoint_config = dict(interval=1, max_keep_ckpts=5) log_config = dict(interval=20, hooks=[dict(type='TextLoggerHook')]) dist_params = dict(backend='nccl') log_level = 'INFO' load_from = 'https://download.openmmlab.com/mmaction/recognition/slowonly/slowonly_r50_8x8x1_256e_kinetics400_rgb/slowonly_r50_8x8x1_256e_kinetics400_rgb_20200703-a79c555a.pth' resume_from = None workflow = [('train', 1)] model = dict( type='Recognizer3D', backbone=dict( type='ResNet3dSlowOnly', depth=50, pretrained='torchvision://resnet50', lateral=False, with_pool2=False, conv1_kernel=(1, 7, 7), conv1_stride_t=1, pool1_stride_t=1, inflate=(0, 0, 1, 1), norm_eval=False), cls_head=dict( type='I3DHead', in_channels=2048, num_classes=51, spatial_type='avg', dropout_ratio=0.5), train_cfg=None, test_cfg=dict(average_clips='prob')) split = 1 dataset_type = 'RawframeDataset' data_root = 'data/hmdb51/rawframes' data_root_val = 'data/hmdb51/rawframes' ann_file_train = 'data/hmdb51/hmdb51_rgb_train_split_1.txt' ann_file_val = 'data/hmdb51/hmdb51_rgb_val_split_1.txt' ann_file_test = 'data/hmdb51/hmdb51_rgb_val_split_1.txt' img_norm_cfg = dict( mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_bgr=False) mc_cfg = dict( server_list_cfg='/mnt/lustre/share/memcached_client/server_list.conf', client_cfg='/mnt/lustre/share/memcached_client/client.conf', sys_path='/mnt/lustre/share/pymc/py3') train_pipeline = [ dict(type='SampleFrames', clip_len=8, frame_interval=4, num_clips=1), dict( type='RawFrameDecode', io_backend='memcached', server_list_cfg='/mnt/lustre/share/memcached_client/server_list.conf', client_cfg='/mnt/lustre/share/memcached_client/client.conf', sys_path='/mnt/lustre/share/pymc/py3'), dict(type='RandomResizedCrop'), dict(type='Resize', scale=(224, 224), keep_ratio=False), dict(type='Flip', flip_ratio=0.5), dict( type='Normalize', mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_bgr=False), dict(type='FormatShape', input_format='NCTHW'), dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]), dict(type='ToTensor', keys=['imgs', 'label']) ] val_pipeline = [ dict( type='SampleFrames', clip_len=8, frame_interval=4, num_clips=1, test_mode=True), dict( type='RawFrameDecode', io_backend='memcached', server_list_cfg='/mnt/lustre/share/memcached_client/server_list.conf', client_cfg='/mnt/lustre/share/memcached_client/client.conf', sys_path='/mnt/lustre/share/pymc/py3'), dict(type='Resize', scale=(-1, 256)), dict(type='CenterCrop', crop_size=224), dict( type='Normalize', mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_bgr=False), dict(type='FormatShape', input_format='NCTHW'), dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]), dict(type='ToTensor', keys=['imgs']) ] test_pipeline = [ dict( type='SampleFrames', clip_len=8, frame_interval=4, num_clips=1, test_mode=True), dict( type='RawFrameDecode', io_backend='memcached', server_list_cfg='/mnt/lustre/share/memcached_client/server_list.conf', client_cfg='/mnt/lustre/share/memcached_client/client.conf', sys_path='/mnt/lustre/share/pymc/py3'), dict(type='Resize', scale=(-1, 256)), dict(type='CenterCrop', crop_size=224), dict( type='Normalize', mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_bgr=False), dict(type='FormatShape', input_format='NCTHW'), dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]), dict(type='ToTensor', keys=['imgs']) ] data = dict( videos_per_gpu=8, workers_per_gpu=4, train=dict( type='RawframeDataset', ann_file='data/hmdb51/hmdb51_rgb_train_split_1.txt', data_prefix='data/hmdb51/rawframes', pipeline=[ dict( type='SampleFrames', clip_len=8, frame_interval=4, num_clips=1), dict( type='RawFrameDecode', io_backend='memcached', server_list_cfg= '/mnt/lustre/share/memcached_client/server_list.conf', client_cfg='/mnt/lustre/share/memcached_client/client.conf', sys_path='/mnt/lustre/share/pymc/py3'), dict(type='RandomResizedCrop'), dict(type='Resize', scale=(224, 224), keep_ratio=False), dict(type='Flip', flip_ratio=0.5), dict( type='Normalize', mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_bgr=False), dict(type='FormatShape', input_format='NCTHW'), dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]), dict(type='ToTensor', keys=['imgs', 'label']) ]), val=dict( type='RawframeDataset', ann_file='data/hmdb51/hmdb51_rgb_val_split_1.txt', data_prefix='data/hmdb51/rawframes', pipeline=[ dict( type='SampleFrames', clip_len=8, frame_interval=4, num_clips=1, test_mode=True), dict( type='RawFrameDecode', io_backend='memcached', server_list_cfg= '/mnt/lustre/share/memcached_client/server_list.conf', client_cfg='/mnt/lustre/share/memcached_client/client.conf', sys_path='/mnt/lustre/share/pymc/py3'), dict(type='Resize', scale=(-1, 256)), dict(type='CenterCrop', crop_size=224), dict( type='Normalize', mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_bgr=False), dict(type='FormatShape', input_format='NCTHW'), dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]), dict(type='ToTensor', keys=['imgs']) ]), test=dict( type='RawframeDataset', ann_file='data/hmdb51/hmdb51_rgb_val_split_1.txt', data_prefix='data/hmdb51/rawframes', pipeline=[ dict( type='SampleFrames', clip_len=8, frame_interval=4, num_clips=1, test_mode=True), dict( type='RawFrameDecode', io_backend='memcached', server_list_cfg= '/mnt/lustre/share/memcached_client/server_list.conf', client_cfg='/mnt/lustre/share/memcached_client/client.conf', sys_path='/mnt/lustre/share/pymc/py3'), dict(type='Resize', scale=(-1, 256)), dict(type='CenterCrop', crop_size=224), dict( type='Normalize', mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_bgr=False), dict(type='FormatShape', input_format='NCTHW'), dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]), dict(type='ToTensor', keys=['imgs']) ])) evaluation = dict( interval=1, metrics=['top_k_accuracy', 'mean_class_accuracy'], start=30, gpu_collect=True) optimizer = dict(type='SGD', lr=0.001, momentum=0.9, weight_decay=0.0001) optimizer_config = dict(grad_clip=dict(max_norm=20, norm_type=2)) lr_config = dict(policy='step', step=[15, 30]) total_epochs = 40 work_dir = './work_dirs/slowonly_r50_k400_pretrained_8x4x1_40e_hmdb51_rgb' find_unused_parameters = False gpu_ids = range(0, 8) omnisource = False module_hooks = [] 2021-06-06 01:01:58,725 - mmaction - INFO - load model from: torchvision://resnet50 2021-06-06 01:02:17,046 - mmaction - INFO - These parameters in the 2d checkpoint are not loaded: {'fc.weight', 'fc.bias'} 2021-06-06 01:02:19,184 - mmaction - INFO - load checkpoint from https://download.openmmlab.com/mmaction/recognition/slowonly/slowonly_r50_8x8x1_256e_kinetics400_rgb/slowonly_r50_8x8x1_256e_kinetics400_rgb_20200703-a79c555a.pth 2021-06-06 01:02:19,184 - mmaction - INFO - Use load_from_http loader 2021-06-06 01:02:19,888 - mmaction - WARNING - The model and loaded state dict do not match exactly size mismatch for cls_head.fc_cls.weight: copying a param with shape torch.Size([400, 2048]) from checkpoint, the shape in current model is torch.Size([51, 2048]). size mismatch for cls_head.fc_cls.bias: copying a param with shape torch.Size([400]) from checkpoint, the shape in current model is torch.Size([51]). 2021-06-06 01:02:19,896 - mmaction - INFO - Start running, host: linjintao@SH-IDC1-10-5-30-54, work_dir: /mnt/lustre/linjintao/try/mmaction2_dev/work_dirs/slowonly_r50_k400_pretrained_8x4x1_40e_hmdb51_rgb 2021-06-06 01:02:19,896 - mmaction - INFO - workflow: [('train', 1)], max: 40 epochs 2021-06-06 01:10:02,264 - mmaction - INFO - Epoch [1][20/56] lr: 1.000e-03, eta: 14:15:15, time: 23.115, data_time: 22.157, memory: 5812, top1_acc: 0.0164, top5_acc: 0.0953, loss_cls: 3.9321, loss: 3.9321, grad_norm: 2.3531 2021-06-06 01:10:14,835 - mmaction - INFO - Epoch [1][40/56] lr: 1.000e-03, eta: 7:15:20, time: 0.631, data_time: 0.004, memory: 5812, top1_acc: 0.0328, top5_acc: 0.1562, loss_cls: 3.8977, loss: 3.8977, grad_norm: 2.3221 2021-06-06 01:10:29,890 - mmaction - INFO - Saving checkpoint at 1 epochs 2021-06-06 01:18:11,205 - mmaction - INFO - Epoch [2][20/56] lr: 1.000e-03, eta: 7:23:42, time: 23.003, data_time: 22.259, memory: 5812, top1_acc: 0.1164, top5_acc: 0.3180, loss_cls: 3.8067, loss: 3.8067, grad_norm: 2.3384 2021-06-06 01:18:23,785 - mmaction - INFO - Epoch [2][40/56] lr: 1.000e-03, eta: 5:52:42, time: 0.631, data_time: 0.003, memory: 5812, top1_acc: 0.1625, top5_acc: 0.3961, loss_cls: 3.7583, loss: 3.7583, grad_norm: 2.3390 2021-06-06 01:18:38,559 - mmaction - INFO - Saving checkpoint at 2 epochs 2021-06-06 01:26:22,639 - mmaction - INFO - Epoch [3][20/56] lr: 1.000e-03, eta: 6:15:23, time: 23.141, data_time: 22.390, memory: 5812, top1_acc: 0.2648, top5_acc: 0.5055, loss_cls: 3.6554, loss: 3.6554, grad_norm: 2.4084 2021-06-06 01:26:35,229 - mmaction - INFO - Epoch [3][40/56] lr: 1.000e-03, eta: 5:25:47, time: 0.631, data_time: 0.003, memory: 5812, top1_acc: 0.2781, top5_acc: 0.5484, loss_cls: 3.6129, loss: 3.6129, grad_norm: 2.4098 2021-06-06 01:26:50,027 - mmaction - INFO - Saving checkpoint at 3 epochs 2021-06-06 01:34:34,288 - mmaction - INFO - Epoch [4][20/56] lr: 1.000e-03, eta: 5:43:05, time: 23.150, data_time: 22.405, memory: 5812, top1_acc: 0.3508, top5_acc: 0.6266, loss_cls: 3.4721, loss: 3.4721, grad_norm: 2.4650 2021-06-06 01:34:46,899 - mmaction - INFO - Epoch [4][40/56] lr: 1.000e-03, eta: 5:09:08, time: 0.631, data_time: 0.002, memory: 5812, top1_acc: 0.3539, top5_acc: 0.6180, loss_cls: 3.4081, loss: 3.4081, grad_norm: 2.4700 2021-06-06 01:35:01,665 - mmaction - INFO - Saving checkpoint at 4 epochs 2021-06-06 01:42:14,731 - mmaction - INFO - Epoch [5][20/56] lr: 1.000e-03, eta: 5:17:43, time: 21.589, data_time: 20.843, memory: 5812, top1_acc: 0.3727, top5_acc: 0.6664, loss_cls: 3.2723, loss: 3.2723, grad_norm: 2.5227 2021-06-06 01:42:27,321 - mmaction - INFO - Epoch [5][40/56] lr: 1.000e-03, eta: 4:52:17, time: 0.631, data_time: 0.003, memory: 5812, top1_acc: 0.3781, top5_acc: 0.6719, loss_cls: 3.1959, loss: 3.1959, grad_norm: 2.5611 2021-06-06 01:42:41,213 - mmaction - INFO - Saving checkpoint at 5 epochs 2021-06-06 01:49:50,844 - mmaction - INFO - Epoch [6][20/56] lr: 1.000e-03, eta: 4:58:41, time: 21.418, data_time: 20.703, memory: 5812, top1_acc: 0.3922, top5_acc: 0.6773, loss_cls: 3.0613, loss: 3.0613, grad_norm: 2.5788 2021-06-06 01:50:03,451 - mmaction - INFO - Epoch [6][40/56] lr: 1.000e-03, eta: 4:38:24, time: 0.632, data_time: 0.004, memory: 5812, top1_acc: 0.3969, top5_acc: 0.6562, loss_cls: 3.0121, loss: 3.0121, grad_norm: 2.6010 2021-06-06 01:50:16,930 - mmaction - INFO - Saving checkpoint at 6 epochs 2021-06-06 01:57:40,637 - mmaction - INFO - Epoch [7][20/56] lr: 1.000e-03, eta: 4:44:34, time: 22.121, data_time: 21.361, memory: 5812, top1_acc: 0.4031, top5_acc: 0.6875, loss_cls: 2.8576, loss: 2.8576, grad_norm: 2.5974 2021-06-06 01:57:53,250 - mmaction - INFO - Epoch [7][40/56] lr: 1.000e-03, eta: 4:27:37, time: 0.634, data_time: 0.005, memory: 5812, top1_acc: 0.4164, top5_acc: 0.6922, loss_cls: 2.8071, loss: 2.8071, grad_norm: 2.6517 2021-06-06 01:58:07,993 - mmaction - INFO - Saving checkpoint at 7 epochs 2021-06-06 02:05:31,254 - mmaction - INFO - Epoch [8][20/56] lr: 1.000e-03, eta: 4:32:12, time: 22.091, data_time: 21.345, memory: 5812, top1_acc: 0.4461, top5_acc: 0.7367, loss_cls: 2.6508, loss: 2.6508, grad_norm: 2.6723 2021-06-06 02:05:43,842 - mmaction - INFO - Epoch [8][40/56] lr: 1.000e-03, eta: 4:17:38, time: 0.631, data_time: 0.002, memory: 5812, top1_acc: 0.4227, top5_acc: 0.7273, loss_cls: 2.6328, loss: 2.6328, grad_norm: 2.6881 2021-06-06 02:05:58,681 - mmaction - INFO - Saving checkpoint at 8 epochs 2021-06-06 02:13:43,342 - mmaction - INFO - Epoch [9][20/56] lr: 1.000e-03, eta: 4:22:19, time: 23.169, data_time: 22.430, memory: 5812, top1_acc: 0.4367, top5_acc: 0.7258, loss_cls: 2.5773, loss: 2.5773, grad_norm: 2.6959 2021-06-06 02:13:55,927 - mmaction - INFO - Epoch [9][40/56] lr: 1.000e-03, eta: 4:09:29, time: 0.631, data_time: 0.003, memory: 5812, top1_acc: 0.4422, top5_acc: 0.7438, loss_cls: 2.5057, loss: 2.5057, grad_norm: 2.7077 2021-06-06 02:14:10,739 - mmaction - INFO - Saving checkpoint at 9 epochs 2021-06-06 02:21:37,897 - mmaction - INFO - Epoch [10][20/56] lr: 1.000e-03, eta: 4:11:54, time: 22.295, data_time: 21.541, memory: 5812, top1_acc: 0.4734, top5_acc: 0.7672, loss_cls: 2.4115, loss: 2.4115, grad_norm: 2.7455 2021-06-06 02:21:50,501 - mmaction - INFO - Epoch [10][40/56] lr: 1.000e-03, eta: 4:00:28, time: 0.632, data_time: 0.003, memory: 5812, top1_acc: 0.4742, top5_acc: 0.7812, loss_cls: 2.3505, loss: 2.3505, grad_norm: 2.7094 2021-06-06 02:22:05,447 - mmaction - INFO - Saving checkpoint at 10 epochs 2021-06-06 02:29:45,536 - mmaction - INFO - Epoch [11][20/56] lr: 1.000e-03, eta: 4:02:39, time: 22.941, data_time: 22.190, memory: 5812, top1_acc: 0.4828, top5_acc: 0.7867, loss_cls: 2.2678, loss: 2.2678, grad_norm: 2.7051 2021-06-06 02:29:58,138 - mmaction - INFO - Epoch [11][40/56] lr: 1.000e-03, eta: 3:52:18, time: 0.631, data_time: 0.003, memory: 5812, top1_acc: 0.4961, top5_acc: 0.7844, loss_cls: 2.2350, loss: 2.2350, grad_norm: 2.8023 2021-06-06 02:30:15,345 - mmaction - INFO - Saving checkpoint at 11 epochs 2021-06-06 02:37:46,594 - mmaction - INFO - Epoch [12][20/56] lr: 1.000e-03, eta: 3:53:16, time: 22.499, data_time: 21.751, memory: 5812, top1_acc: 0.5227, top5_acc: 0.7898, loss_cls: 2.1876, loss: 2.1876, grad_norm: 2.8419 2021-06-06 02:37:59,193 - mmaction - INFO - Epoch [12][40/56] lr: 1.000e-03, eta: 3:43:50, time: 0.631, data_time: 0.003, memory: 5812, top1_acc: 0.4805, top5_acc: 0.7719, loss_cls: 2.2107, loss: 2.2107, grad_norm: 2.8719 2021-06-06 02:38:14,035 - mmaction - INFO - Saving checkpoint at 12 epochs 2021-06-06 02:45:28,364 - mmaction - INFO - Epoch [13][20/56] lr: 1.000e-03, eta: 3:43:31, time: 21.653, data_time: 20.907, memory: 5812, top1_acc: 0.5172, top5_acc: 0.7977, loss_cls: 2.0890, loss: 2.0890, grad_norm: 2.8779 2021-06-06 02:45:40,959 - mmaction - INFO - Epoch [13][40/56] lr: 1.000e-03, eta: 3:34:53, time: 0.632, data_time: 0.003, memory: 5812, top1_acc: 0.5008, top5_acc: 0.7969, loss_cls: 2.1287, loss: 2.1287, grad_norm: 2.9196 2021-06-06 02:45:55,588 - mmaction - INFO - Saving checkpoint at 13 epochs 2021-06-06 02:53:31,540 - mmaction - INFO - Epoch [14][20/56] lr: 1.000e-03, eta: 3:34:50, time: 22.734, data_time: 21.986, memory: 5812, top1_acc: 0.5391, top5_acc: 0.8234, loss_cls: 2.0044, loss: 2.0044, grad_norm: 2.8403 2021-06-06 02:53:44,142 - mmaction - INFO - Epoch [14][40/56] lr: 1.000e-03, eta: 3:26:50, time: 0.632, data_time: 0.003, memory: 5812, top1_acc: 0.5086, top5_acc: 0.8016, loss_cls: 2.0453, loss: 2.0453, grad_norm: 3.0035 2021-06-06 02:53:58,853 - mmaction - INFO - Saving checkpoint at 14 epochs 2021-06-06 03:01:12,958 - mmaction - INFO - Epoch [15][20/56] lr: 1.000e-03, eta: 3:25:38, time: 21.642, data_time: 20.901, memory: 5812, top1_acc: 0.5250, top5_acc: 0.8328, loss_cls: 1.9685, loss: 1.9685, grad_norm: 3.0148 2021-06-06 03:01:25,556 - mmaction - INFO - Epoch [15][40/56] lr: 1.000e-03, eta: 3:18:12, time: 0.631, data_time: 0.003, memory: 5812, top1_acc: 0.5211, top5_acc: 0.8180, loss_cls: 1.9829, loss: 1.9829, grad_norm: 3.0399 2021-06-06 03:01:40,325 - mmaction - INFO - Saving checkpoint at 15 epochs 2021-06-06 03:08:53,224 - mmaction - INFO - Epoch [16][20/56] lr: 1.000e-04, eta: 3:16:37, time: 21.581, data_time: 20.858, memory: 5812, top1_acc: 0.5734, top5_acc: 0.8469, loss_cls: 1.8689, loss: 1.8689, grad_norm: 3.0260 2021-06-06 03:09:05,834 - mmaction - INFO - Epoch [16][40/56] lr: 1.000e-04, eta: 3:09:42, time: 0.632, data_time: 0.003, memory: 5812, top1_acc: 0.5430, top5_acc: 0.8336, loss_cls: 1.9164, loss: 1.9164, grad_norm: 2.9851 2021-06-06 03:09:18,752 - mmaction - INFO - Saving checkpoint at 16 epochs 2021-06-06 03:16:54,256 - mmaction - INFO - Epoch [17][20/56] lr: 1.000e-04, eta: 3:08:21, time: 22.712, data_time: 21.968, memory: 5812, top1_acc: 0.5391, top5_acc: 0.8203, loss_cls: 1.9280, loss: 1.9280, grad_norm: 3.0407 2021-06-06 03:17:06,856 - mmaction - INFO - Epoch [17][40/56] lr: 1.000e-04, eta: 3:01:50, time: 0.631, data_time: 0.003, memory: 5812, top1_acc: 0.5359, top5_acc: 0.8148, loss_cls: 1.9573, loss: 1.9573, grad_norm: 3.0624 2021-06-06 03:17:21,491 - mmaction - INFO - Saving checkpoint at 17 epochs 2021-06-06 03:25:00,754 - mmaction - INFO - Epoch [18][20/56] lr: 1.000e-04, eta: 3:00:14, time: 22.900, data_time: 22.155, memory: 5812, top1_acc: 0.5406, top5_acc: 0.8148, loss_cls: 1.9509, loss: 1.9509, grad_norm: 3.0879 2021-06-06 03:25:13,382 - mmaction - INFO - Epoch [18][40/56] lr: 1.000e-04, eta: 2:54:04, time: 0.633, data_time: 0.003, memory: 5812, top1_acc: 0.5242, top5_acc: 0.8367, loss_cls: 1.9082, loss: 1.9082, grad_norm: 3.1027 2021-06-06 03:25:28,601 - mmaction - INFO - Saving checkpoint at 18 epochs 2021-06-06 03:32:53,148 - mmaction - INFO - Epoch [19][20/56] lr: 1.000e-04, eta: 2:51:50, time: 22.156, data_time: 21.396, memory: 5812, top1_acc: 0.5508, top5_acc: 0.8328, loss_cls: 1.8869, loss: 1.8869, grad_norm: 3.0336 2021-06-06 03:33:05,734 - mmaction - INFO - Epoch [19][40/56] lr: 1.000e-04, eta: 2:46:01, time: 0.632, data_time: 0.004, memory: 5812, top1_acc: 0.5516, top5_acc: 0.8336, loss_cls: 1.9097, loss: 1.9097, grad_norm: 3.0272 2021-06-06 03:33:20,474 - mmaction - INFO - Saving checkpoint at 19 epochs 2021-06-06 03:41:03,534 - mmaction - INFO - Epoch [20][20/56] lr: 1.000e-04, eta: 2:43:52, time: 23.088, data_time: 22.350, memory: 5812, top1_acc: 0.5508, top5_acc: 0.8289, loss_cls: 1.8820, loss: 1.8820, grad_norm: 3.0355 2021-06-06 03:41:16,129 - mmaction - INFO - Epoch [20][40/56] lr: 1.000e-04, eta: 2:38:20, time: 0.631, data_time: 0.003, memory: 5812, top1_acc: 0.5508, top5_acc: 0.8492, loss_cls: 1.8765, loss: 1.8765, grad_norm: 3.0140 2021-06-06 03:41:30,996 - mmaction - INFO - Saving checkpoint at 20 epochs 2021-06-06 03:49:03,917 - mmaction - INFO - Epoch [21][20/56] lr: 1.000e-04, eta: 2:35:44, time: 22.583, data_time: 21.836, memory: 5812, top1_acc: 0.5727, top5_acc: 0.8477, loss_cls: 1.8498, loss: 1.8498, grad_norm: 3.0592 2021-06-06 03:49:16,522 - mmaction - INFO - Epoch [21][40/56] lr: 1.000e-04, eta: 2:30:28, time: 0.631, data_time: 0.003, memory: 5812, top1_acc: 0.5328, top5_acc: 0.8242, loss_cls: 1.9131, loss: 1.9131, grad_norm: 3.0506 2021-06-06 03:49:31,386 - mmaction - INFO - Saving checkpoint at 21 epochs 2021-06-06 03:56:40,958 - mmaction - INFO - Epoch [22][20/56] lr: 1.000e-04, eta: 2:27:18, time: 21.415, data_time: 20.696, memory: 5812, top1_acc: 0.5609, top5_acc: 0.8242, loss_cls: 1.8901, loss: 1.8901, grad_norm: 3.1118 2021-06-06 03:56:53,548 - mmaction - INFO - Epoch [22][40/56] lr: 1.000e-04, eta: 2:22:17, time: 0.631, data_time: 0.003, memory: 5812, top1_acc: 0.5820, top5_acc: 0.8523, loss_cls: 1.8193, loss: 1.8193, grad_norm: 3.0324 2021-06-06 03:57:06,502 - mmaction - INFO - Saving checkpoint at 22 epochs 2021-06-06 04:04:32,662 - mmaction - INFO - Epoch [23][20/56] lr: 1.000e-04, eta: 2:19:11, time: 22.245, data_time: 21.503, memory: 5812, top1_acc: 0.5648, top5_acc: 0.8594, loss_cls: 1.8247, loss: 1.8247, grad_norm: 3.0584 2021-06-06 04:04:45,250 - mmaction - INFO - Epoch [23][40/56] lr: 1.000e-04, eta: 2:14:23, time: 0.630, data_time: 0.002, memory: 5812, top1_acc: 0.5500, top5_acc: 0.8313, loss_cls: 1.8644, loss: 1.8644, grad_norm: 2.9971 2021-06-06 04:05:00,126 - mmaction - INFO - Saving checkpoint at 23 epochs 2021-06-06 04:12:38,825 - mmaction - INFO - Epoch [24][20/56] lr: 1.000e-04, eta: 2:11:15, time: 22.870, data_time: 22.109, memory: 5812, top1_acc: 0.5500, top5_acc: 0.8344, loss_cls: 1.8556, loss: 1.8556, grad_norm: 3.0345 2021-06-06 04:12:51,409 - mmaction - INFO - Epoch [24][40/56] lr: 1.000e-04, eta: 2:06:39, time: 0.633, data_time: 0.005, memory: 5812, top1_acc: 0.5469, top5_acc: 0.8266, loss_cls: 1.8825, loss: 1.8825, grad_norm: 3.0422 2021-06-06 04:13:06,217 - mmaction - INFO - Saving checkpoint at 24 epochs 2021-06-06 04:20:13,458 - mmaction - INFO - Epoch [25][20/56] lr: 1.000e-04, eta: 2:03:00, time: 21.298, data_time: 20.585, memory: 5812, top1_acc: 0.5500, top5_acc: 0.8320, loss_cls: 1.8552, loss: 1.8552, grad_norm: 3.0193 2021-06-06 04:20:26,045 - mmaction - INFO - Epoch [25][40/56] lr: 1.000e-04, eta: 1:58:35, time: 0.631, data_time: 0.003, memory: 5812, top1_acc: 0.5719, top5_acc: 0.8555, loss_cls: 1.7931, loss: 1.7931, grad_norm: 3.0102 2021-06-06 04:20:39,209 - mmaction - INFO - Saving checkpoint at 25 epochs 2021-06-06 04:28:14,394 - mmaction - INFO - Epoch [26][20/56] lr: 1.000e-04, eta: 1:55:05, time: 22.696, data_time: 21.953, memory: 5812, top1_acc: 0.5773, top5_acc: 0.8391, loss_cls: 1.8144, loss: 1.8144, grad_norm: 3.0362 2021-06-06 04:28:26,985 - mmaction - INFO - Epoch [26][40/56] lr: 1.000e-04, eta: 1:50:50, time: 0.631, data_time: 0.003, memory: 5812, top1_acc: 0.5586, top5_acc: 0.8273, loss_cls: 1.8704, loss: 1.8704, grad_norm: 3.0310 2021-06-06 04:28:41,729 - mmaction - INFO - Saving checkpoint at 26 epochs 2021-06-06 04:36:23,840 - mmaction - INFO - Epoch [27][20/56] lr: 1.000e-04, eta: 1:47:14, time: 23.042, data_time: 22.294, memory: 5812, top1_acc: 0.5844, top5_acc: 0.8508, loss_cls: 1.7959, loss: 1.7959, grad_norm: 2.9902 2021-06-06 04:36:36,428 - mmaction - INFO - Epoch [27][40/56] lr: 1.000e-04, eta: 1:43:08, time: 0.631, data_time: 0.003, memory: 5812, top1_acc: 0.5742, top5_acc: 0.8430, loss_cls: 1.8483, loss: 1.8483, grad_norm: 3.0460 2021-06-06 04:36:51,220 - mmaction - INFO - Saving checkpoint at 27 epochs 2021-06-06 04:44:35,096 - mmaction - INFO - Epoch [28][20/56] lr: 1.000e-04, eta: 1:39:24, time: 23.130, data_time: 22.383, memory: 5812, top1_acc: 0.5656, top5_acc: 0.8398, loss_cls: 1.8283, loss: 1.8283, grad_norm: 3.0709 2021-06-06 04:44:47,712 - mmaction - INFO - Epoch [28][40/56] lr: 1.000e-04, eta: 1:35:27, time: 0.633, data_time: 0.004, memory: 5812, top1_acc: 0.5570, top5_acc: 0.8164, loss_cls: 1.8718, loss: 1.8718, grad_norm: 3.0860 2021-06-06 04:45:02,773 - mmaction - INFO - Saving checkpoint at 28 epochs 2021-06-06 04:52:09,089 - mmaction - INFO - Epoch [29][20/56] lr: 1.000e-04, eta: 1:31:18, time: 21.252, data_time: 20.524, memory: 5812, top1_acc: 0.5594, top5_acc: 0.8414, loss_cls: 1.8318, loss: 1.8318, grad_norm: 3.0582 2021-06-06 04:52:21,681 - mmaction - INFO - Epoch [29][40/56] lr: 1.000e-04, eta: 1:27:29, time: 0.631, data_time: 0.003, memory: 5812, top1_acc: 0.5687, top5_acc: 0.8484, loss_cls: 1.8286, loss: 1.8286, grad_norm: 3.0752 2021-06-06 04:52:34,799 - mmaction - INFO - Saving checkpoint at 29 epochs 2021-06-06 05:00:15,224 - mmaction - INFO - Epoch [30][20/56] lr: 1.000e-04, eta: 1:23:28, time: 22.956, data_time: 22.191, memory: 5812, top1_acc: 0.5531, top5_acc: 0.8500, loss_cls: 1.8088, loss: 1.8088, grad_norm: 3.0834 2021-06-06 05:00:27,832 - mmaction - INFO - Epoch [30][40/56] lr: 1.000e-04, eta: 1:19:46, time: 0.633, data_time: 0.005, memory: 5812, top1_acc: 0.5836, top5_acc: 0.8500, loss_cls: 1.7722, loss: 1.7722, grad_norm: 3.0243 2021-06-06 05:00:42,934 - mmaction - INFO - Saving checkpoint at 30 epochs 2021-06-06 05:07:41,899 - mmaction - INFO - Evaluating top_k_accuracy ... 2021-06-06 05:07:41,924 - mmaction - INFO - top1_acc 0.6183 top5_acc 0.8993 2021-06-06 05:07:41,924 - mmaction - INFO - Evaluating mean_class_accuracy ... 2021-06-06 05:07:41,950 - mmaction - INFO - mean_acc 0.6183 2021-06-06 05:07:43,139 - mmaction - INFO - Now best checkpoint is saved as best_top1_acc_epoch_30.pth. 2021-06-06 05:07:43,139 - mmaction - INFO - Best top1_acc is 0.6183 at 30 epoch. 2021-06-06 05:07:43,156 - mmaction - INFO - Epoch(val) [30][56] top1_acc: 0.6183, top5_acc: 0.8993, mean_class_accuracy: 0.6183 2021-06-06 05:15:22,583 - mmaction - INFO - Epoch [31][20/56] lr: 1.000e-05, eta: 1:15:38, time: 22.968, data_time: 22.210, memory: 5812, top1_acc: 0.5711, top5_acc: 0.8477, loss_cls: 1.8054, loss: 1.8054, grad_norm: 3.0325 2021-06-06 05:15:35,168 - mmaction - INFO - Epoch [31][40/56] lr: 1.000e-05, eta: 1:12:03, time: 0.632, data_time: 0.005, memory: 5812, top1_acc: 0.5797, top5_acc: 0.8477, loss_cls: 1.7740, loss: 1.7740, grad_norm: 3.0526 2021-06-06 05:15:49,856 - mmaction - INFO - Saving checkpoint at 31 epochs 2021-06-06 05:23:26,042 - mmaction - INFO - Evaluating top_k_accuracy ... 2021-06-06 05:23:26,085 - mmaction - INFO - top1_acc 0.6281 top5_acc 0.8922 2021-06-06 05:23:26,085 - mmaction - INFO - Evaluating mean_class_accuracy ... 2021-06-06 05:23:26,145 - mmaction - INFO - mean_acc 0.6281 2021-06-06 05:23:27,337 - mmaction - INFO - Now best checkpoint is saved as best_top1_acc_epoch_31.pth. 2021-06-06 05:23:27,337 - mmaction - INFO - Best top1_acc is 0.6281 at 31 epoch. 2021-06-06 05:23:27,354 - mmaction - INFO - Epoch(val) [31][56] top1_acc: 0.6281, top5_acc: 0.8922, mean_class_accuracy: 0.6281 2021-06-06 05:30:49,119 - mmaction - INFO - Epoch [32][20/56] lr: 1.000e-05, eta: 1:07:43, time: 22.087, data_time: 21.342, memory: 5812, top1_acc: 0.5492, top5_acc: 0.8516, loss_cls: 1.8372, loss: 1.8372, grad_norm: 3.1426 2021-06-06 05:31:01,708 - mmaction - INFO - Epoch [32][40/56] lr: 1.000e-05, eta: 1:04:14, time: 0.630, data_time: 0.002, memory: 5812, top1_acc: 0.5883, top5_acc: 0.8445, loss_cls: 1.7979, loss: 1.7979, grad_norm: 3.0492 2021-06-06 05:31:16,543 - mmaction - INFO - Saving checkpoint at 32 epochs 2021-06-06 05:38:04,877 - mmaction - INFO - Evaluating top_k_accuracy ... 2021-06-06 05:38:04,928 - mmaction - INFO - top1_acc 0.6137 top5_acc 0.8922 2021-06-06 05:38:04,928 - mmaction - INFO - Evaluating mean_class_accuracy ... 2021-06-06 05:38:04,973 - mmaction - INFO - mean_acc 0.6137 2021-06-06 05:38:04,974 - mmaction - INFO - Epoch(val) [32][56] top1_acc: 0.6137, top5_acc: 0.8922, mean_class_accuracy: 0.6137 2021-06-06 05:45:15,025 - mmaction - INFO - Epoch [33][20/56] lr: 1.000e-05, eta: 0:59:46, time: 21.500, data_time: 20.764, memory: 5812, top1_acc: 0.5609, top5_acc: 0.8242, loss_cls: 1.8344, loss: 1.8344, grad_norm: 3.0424 2021-06-06 05:45:27,643 - mmaction - INFO - Epoch [33][40/56] lr: 1.000e-05, eta: 0:56:24, time: 0.633, data_time: 0.004, memory: 5812, top1_acc: 0.5828, top5_acc: 0.8508, loss_cls: 1.7989, loss: 1.7989, grad_norm: 3.0174 2021-06-06 05:45:42,654 - mmaction - INFO - Saving checkpoint at 33 epochs 2021-06-06 05:53:22,003 - mmaction - INFO - Evaluating top_k_accuracy ... 2021-06-06 05:53:22,051 - mmaction - INFO - top1_acc 0.6222 top5_acc 0.8974 2021-06-06 05:53:22,051 - mmaction - INFO - Evaluating mean_class_accuracy ... 2021-06-06 05:53:22,117 - mmaction - INFO - mean_acc 0.6222 2021-06-06 05:53:22,117 - mmaction - INFO - Epoch(val) [33][56] top1_acc: 0.6222, top5_acc: 0.8974, mean_class_accuracy: 0.6222 2021-06-06 06:01:00,190 - mmaction - INFO - Epoch [34][20/56] lr: 1.000e-05, eta: 0:51:57, time: 22.898, data_time: 22.117, memory: 5812, top1_acc: 0.5445, top5_acc: 0.8383, loss_cls: 1.8498, loss: 1.8498, grad_norm: 3.0743 2021-06-06 06:01:12,804 - mmaction - INFO - Epoch [34][40/56] lr: 1.000e-05, eta: 0:48:41, time: 0.635, data_time: 0.006, memory: 5812, top1_acc: 0.5898, top5_acc: 0.8352, loss_cls: 1.7891, loss: 1.7891, grad_norm: 3.0440 2021-06-06 06:01:28,734 - mmaction - INFO - Saving checkpoint at 34 epochs 2021-06-06 06:09:15,357 - mmaction - INFO - Evaluating top_k_accuracy ... 2021-06-06 06:09:15,402 - mmaction - INFO - top1_acc 0.6268 top5_acc 0.8961 2021-06-06 06:09:15,402 - mmaction - INFO - Evaluating mean_class_accuracy ... 2021-06-06 06:09:15,462 - mmaction - INFO - mean_acc 0.6268 2021-06-06 06:09:15,463 - mmaction - INFO - Epoch(val) [34][56] top1_acc: 0.6268, top5_acc: 0.8961, mean_class_accuracy: 0.6268 2021-06-06 06:17:00,477 - mmaction - INFO - Epoch [35][20/56] lr: 1.000e-05, eta: 0:44:09, time: 23.246, data_time: 22.481, memory: 5812, top1_acc: 0.5820, top5_acc: 0.8523, loss_cls: 1.7662, loss: 1.7662, grad_norm: 3.0337 2021-06-06 06:17:13,095 - mmaction - INFO - Epoch [35][40/56] lr: 1.000e-05, eta: 0:40:58, time: 0.635, data_time: 0.005, memory: 5812, top1_acc: 0.5555, top5_acc: 0.8531, loss_cls: 1.8110, loss: 1.8110, grad_norm: 3.0485 2021-06-06 06:17:28,008 - mmaction - INFO - Saving checkpoint at 35 epochs 2021-06-06 06:24:59,007 - mmaction - INFO - Evaluating top_k_accuracy ... 2021-06-06 06:24:59,053 - mmaction - INFO - top1_acc 0.6327 top5_acc 0.8915 2021-06-06 06:24:59,053 - mmaction - INFO - Evaluating mean_class_accuracy ... 2021-06-06 06:24:59,113 - mmaction - INFO - mean_acc 0.6327 2021-06-06 06:25:00,323 - mmaction - INFO - Now best checkpoint is saved as best_top1_acc_epoch_35.pth. 2021-06-06 06:25:00,323 - mmaction - INFO - Best top1_acc is 0.6327 at 35 epoch. 2021-06-06 06:25:00,324 - mmaction - INFO - Epoch(val) [35][56] top1_acc: 0.6327, top5_acc: 0.8915, mean_class_accuracy: 0.6327 2021-06-06 06:32:06,108 - mmaction - INFO - Epoch [36][20/56] lr: 1.000e-05, eta: 0:36:16, time: 21.287, data_time: 20.574, memory: 5812, top1_acc: 0.5852, top5_acc: 0.8617, loss_cls: 1.7827, loss: 1.7827, grad_norm: 3.0532 2021-06-06 06:32:18,697 - mmaction - INFO - Epoch [36][40/56] lr: 1.000e-05, eta: 0:33:10, time: 0.631, data_time: 0.003, memory: 5812, top1_acc: 0.5625, top5_acc: 0.8414, loss_cls: 1.8362, loss: 1.8362, grad_norm: 3.1108 2021-06-06 06:32:31,836 - mmaction - INFO - Saving checkpoint at 36 epochs 2021-06-06 06:39:50,355 - mmaction - INFO - Evaluating top_k_accuracy ... 2021-06-06 06:39:50,404 - mmaction - INFO - top1_acc 0.6163 top5_acc 0.9007 2021-06-06 06:39:50,404 - mmaction - INFO - Evaluating mean_class_accuracy ... 2021-06-06 06:39:50,465 - mmaction - INFO - mean_acc 0.6163 2021-06-06 06:39:50,466 - mmaction - INFO - Epoch(val) [36][56] top1_acc: 0.6163, top5_acc: 0.9007, mean_class_accuracy: 0.6163 2021-06-06 06:47:32,867 - mmaction - INFO - Epoch [37][20/56] lr: 1.000e-05, eta: 0:28:28, time: 23.118, data_time: 22.380, memory: 5812, top1_acc: 0.5648, top5_acc: 0.8398, loss_cls: 1.8366, loss: 1.8366, grad_norm: 3.1361 2021-06-06 06:47:45,481 - mmaction - INFO - Epoch [37][40/56] lr: 1.000e-05, eta: 0:25:26, time: 0.632, data_time: 0.003, memory: 5812, top1_acc: 0.5687, top5_acc: 0.8477, loss_cls: 1.8125, loss: 1.8125, grad_norm: 3.1155 2021-06-06 06:48:00,146 - mmaction - INFO - Saving checkpoint at 37 epochs 2021-06-06 06:55:41,794 - mmaction - INFO - Evaluating top_k_accuracy ... 2021-06-06 06:55:41,838 - mmaction - INFO - top1_acc 0.6288 top5_acc 0.8941 2021-06-06 06:55:41,838 - mmaction - INFO - Evaluating mean_class_accuracy ... 2021-06-06 06:55:41,898 - mmaction - INFO - mean_acc 0.6288 2021-06-06 06:55:41,899 - mmaction - INFO - Epoch(val) [37][56] top1_acc: 0.6288, top5_acc: 0.8941, mean_class_accuracy: 0.6288 2021-06-06 07:03:21,910 - mmaction - INFO - Epoch [38][20/56] lr: 1.000e-05, eta: 0:20:39, time: 22.997, data_time: 22.249, memory: 5812, top1_acc: 0.5719, top5_acc: 0.8414, loss_cls: 1.8199, loss: 1.8199, grad_norm: 3.1039 2021-06-06 07:03:34,513 - mmaction - INFO - Epoch [38][40/56] lr: 1.000e-05, eta: 0:17:42, time: 0.633, data_time: 0.004, memory: 5812, top1_acc: 0.5680, top5_acc: 0.8391, loss_cls: 1.8191, loss: 1.8191, grad_norm: 3.0449 2021-06-06 07:03:49,327 - mmaction - INFO - Saving checkpoint at 38 epochs 2021-06-06 07:11:12,860 - mmaction - INFO - Evaluating top_k_accuracy ... 2021-06-06 07:11:12,911 - mmaction - INFO - top1_acc 0.6353 top5_acc 0.8967 2021-06-06 07:11:12,911 - mmaction - INFO - Evaluating mean_class_accuracy ... 2021-06-06 07:11:12,972 - mmaction - INFO - mean_acc 0.6353 2021-06-06 07:11:14,186 - mmaction - INFO - Now best checkpoint is saved as best_top1_acc_epoch_38.pth. 2021-06-06 07:11:14,186 - mmaction - INFO - Best top1_acc is 0.6353 at 38 epoch. 2021-06-06 07:11:14,187 - mmaction - INFO - Epoch(val) [38][56] top1_acc: 0.6353, top5_acc: 0.8967, mean_class_accuracy: 0.6353 2021-06-06 07:18:37,030 - mmaction - INFO - Epoch [39][20/56] lr: 1.000e-05, eta: 0:12:49, time: 22.136, data_time: 21.387, memory: 5812, top1_acc: 0.5883, top5_acc: 0.8602, loss_cls: 1.7585, loss: 1.7585, grad_norm: 3.0625 2021-06-06 07:18:49,663 - mmaction - INFO - Epoch [39][40/56] lr: 1.000e-05, eta: 0:09:57, time: 0.633, data_time: 0.003, memory: 5812, top1_acc: 0.5570, top5_acc: 0.8492, loss_cls: 1.8384, loss: 1.8384, grad_norm: 3.0814 2021-06-06 07:19:04,477 - mmaction - INFO - Saving checkpoint at 39 epochs 2021-06-06 07:26:43,444 - mmaction - INFO - Evaluating top_k_accuracy ... 2021-06-06 07:26:43,501 - mmaction - INFO - top1_acc 0.6261 top5_acc 0.8935 2021-06-06 07:26:43,501 - mmaction - INFO - Evaluating mean_class_accuracy ... 2021-06-06 07:26:43,567 - mmaction - INFO - mean_acc 0.6261 2021-06-06 07:26:43,567 - mmaction - INFO - Epoch(val) [39][56] top1_acc: 0.6261, top5_acc: 0.8935, mean_class_accuracy: 0.6261 2021-06-06 07:34:23,814 - mmaction - INFO - Epoch [40][20/56] lr: 1.000e-05, eta: 0:05:01, time: 23.010, data_time: 22.271, memory: 5812, top1_acc: 0.5930, top5_acc: 0.8508, loss_cls: 1.7695, loss: 1.7695, grad_norm: 3.0530 2021-06-06 07:34:36,397 - mmaction - INFO - Epoch [40][40/56] lr: 1.000e-05, eta: 0:02:12, time: 0.630, data_time: 0.003, memory: 5812, top1_acc: 0.5422, top5_acc: 0.8234, loss_cls: 1.8750, loss: 1.8750, grad_norm: 3.0647 2021-06-06 07:34:51,101 - mmaction - INFO - Saving checkpoint at 40 epochs 2021-06-06 07:42:01,810 - mmaction - INFO - Evaluating top_k_accuracy ... 2021-06-06 07:42:01,860 - mmaction - INFO - top1_acc 0.6261 top5_acc 0.8941 2021-06-06 07:42:01,860 - mmaction - INFO - Evaluating mean_class_accuracy ... 2021-06-06 07:42:01,925 - mmaction - INFO - mean_acc 0.6261 2021-06-06 07:42:01,926 - mmaction - INFO - Epoch(val) [40][56] top1_acc: 0.6261, top5_acc: 0.8941, mean_class_accuracy: 0.6261