-
Notifications
You must be signed in to change notification settings - Fork 1.3k
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
* Add configs and some stats. * Update. * Update r101 8x8. * Minor. * Update url. * Update changelog. * Fix typos and workdir.
- Loading branch information
su
authored
Feb 26, 2021
1 parent
f3a26aa
commit b7b40a1
Showing
5 changed files
with
413 additions
and
0 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
137 changes: 137 additions & 0 deletions
137
configs/recognition/slowfast/slowfast_r101_8x8x1_256e_kinetics400_rgb.py
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,137 @@ | ||
| model = dict( | ||
| type='Recognizer3D', | ||
| backbone=dict( | ||
| type='ResNet3dSlowFast', | ||
| pretrained=None, | ||
| resample_rate=4, # tau | ||
| speed_ratio=4, # alpha | ||
| channel_ratio=8, # beta_inv | ||
| slow_pathway=dict( | ||
| type='resnet3d', | ||
| depth=101, | ||
| pretrained=None, | ||
| lateral=True, | ||
| fusion_kernel=7, | ||
| conv1_kernel=(1, 7, 7), | ||
| dilations=(1, 1, 1, 1), | ||
| conv1_stride_t=1, | ||
| pool1_stride_t=1, | ||
| inflate=(0, 0, 1, 1), | ||
| norm_eval=False), | ||
| fast_pathway=dict( | ||
| type='resnet3d', | ||
| depth=101, | ||
| pretrained=None, | ||
| lateral=False, | ||
| base_channels=8, | ||
| conv1_kernel=(5, 7, 7), | ||
| conv1_stride_t=1, | ||
| pool1_stride_t=1, | ||
| norm_eval=False)), | ||
| cls_head=dict( | ||
| type='SlowFastHead', | ||
| in_channels=2304, # 2048+256 | ||
| num_classes=400, | ||
| spatial_type='avg', | ||
| dropout_ratio=0.5)) | ||
| train_cfg = None | ||
| test_cfg = dict(average_clips='prob') | ||
| dataset_type = 'RawframeDataset' | ||
| data_root = 'data/kinetics400/rawframes_train' | ||
| data_root_val = 'data/kinetics400/rawframes_val' | ||
| ann_file_train = 'data/kinetics400/kinetics400_train_list_rawframes.txt' | ||
| ann_file_val = 'data/kinetics400/kinetics400_val_list_rawframes.txt' | ||
| ann_file_test = 'data/kinetics400/kinetics400_val_list_rawframes.txt' | ||
| img_norm_cfg = dict( | ||
| mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_bgr=False) | ||
| train_pipeline = [ | ||
| dict(type='SampleFrames', clip_len=32, frame_interval=2, num_clips=1), | ||
| dict(type='RawFrameDecode'), | ||
| dict(type='Resize', scale=(-1, 256)), | ||
| dict(type='RandomResizedCrop'), | ||
| dict(type='Resize', scale=(224, 224), keep_ratio=False), | ||
| dict(type='Flip', flip_ratio=0.5), | ||
| dict(type='Normalize', **img_norm_cfg), | ||
| 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=32, | ||
| frame_interval=2, | ||
| num_clips=1, | ||
| test_mode=True), | ||
| dict(type='RawFrameDecode'), | ||
| dict(type='Resize', scale=(-1, 256)), | ||
| dict(type='CenterCrop', crop_size=224), | ||
| dict(type='Flip', flip_ratio=0), | ||
| dict(type='Normalize', **img_norm_cfg), | ||
| 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=32, | ||
| frame_interval=2, | ||
| num_clips=10, | ||
| test_mode=True), | ||
| dict(type='RawFrameDecode'), | ||
| dict(type='Resize', scale=(-1, 256)), | ||
| dict(type='ThreeCrop', crop_size=256), | ||
| dict(type='Flip', flip_ratio=0), | ||
| dict(type='Normalize', **img_norm_cfg), | ||
| 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=dataset_type, | ||
| ann_file=ann_file_train, | ||
| data_prefix=data_root, | ||
| pipeline=train_pipeline), | ||
| val=dict( | ||
| type=dataset_type, | ||
| ann_file=ann_file_val, | ||
| data_prefix=data_root_val, | ||
| pipeline=val_pipeline), | ||
| test=dict( | ||
| type=dataset_type, | ||
| ann_file=ann_file_test, | ||
| data_prefix=data_root_val, | ||
| pipeline=test_pipeline)) | ||
| # optimizer | ||
| optimizer = dict( | ||
| type='SGD', lr=0.1, momentum=0.9, | ||
| weight_decay=0.0001) # this lr is used for 8 gpus | ||
| optimizer_config = dict(grad_clip=dict(max_norm=40, norm_type=2)) | ||
| # learning policy | ||
| lr_config = dict( | ||
| policy='CosineAnnealing', | ||
| min_lr=0, | ||
| warmup='linear', | ||
| warmup_by_epoch=True, | ||
| warmup_iters=34) | ||
| total_epochs = 256 | ||
| checkpoint_config = dict(interval=4) | ||
| workflow = [('train', 1)] | ||
| evaluation = dict( | ||
| interval=5, metrics=['top_k_accuracy', 'mean_class_accuracy']) | ||
| log_config = dict( | ||
| interval=20, | ||
| hooks=[ | ||
| dict(type='TextLoggerHook'), | ||
| # dict(type='TensorboardLoggerHook'), | ||
| ]) | ||
| dist_params = dict(backend='nccl') | ||
| log_level = 'INFO' | ||
| work_dir = './work_dirs/slowfast_r101_8x8x1_256e_kinetics400_rgb' | ||
| load_from = None | ||
| resume_from = None | ||
| find_unused_parameters = False |
136 changes: 136 additions & 0 deletions
136
configs/recognition/slowfast/slowfast_r101_r50_4x16x1_256e_kinetics400_rgb.py
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,136 @@ | ||
| model = dict( | ||
| type='Recognizer3D', | ||
| backbone=dict( | ||
| type='ResNet3dSlowFast', | ||
| pretrained=None, | ||
| resample_rate=8, # tau | ||
| speed_ratio=8, # alpha | ||
| channel_ratio=8, # beta_inv | ||
| slow_pathway=dict( | ||
| type='resnet3d', | ||
| depth=101, | ||
| pretrained=None, | ||
| lateral=True, | ||
| conv1_kernel=(1, 7, 7), | ||
| dilations=(1, 1, 1, 1), | ||
| conv1_stride_t=1, | ||
| pool1_stride_t=1, | ||
| inflate=(0, 0, 1, 1), | ||
| norm_eval=False), | ||
| fast_pathway=dict( | ||
| type='resnet3d', | ||
| depth=50, | ||
| pretrained=None, | ||
| lateral=False, | ||
| base_channels=8, | ||
| conv1_kernel=(5, 7, 7), | ||
| conv1_stride_t=1, | ||
| pool1_stride_t=1, | ||
| norm_eval=False)), | ||
| cls_head=dict( | ||
| type='SlowFastHead', | ||
| in_channels=2304, # 2048+256 | ||
| num_classes=400, | ||
| spatial_type='avg', | ||
| dropout_ratio=0.5)) | ||
| train_cfg = None | ||
| test_cfg = dict(average_clips='prob') | ||
| dataset_type = 'RawframeDataset' | ||
| data_root = 'data/kinetics400/rawframes_train' | ||
| data_root_val = 'data/kinetics400/rawframes_val' | ||
| ann_file_train = 'data/kinetics400/kinetics400_train_list_rawframes.txt' | ||
| ann_file_val = 'data/kinetics400/kinetics400_val_list_rawframes.txt' | ||
| ann_file_test = 'data/kinetics400/kinetics400_val_list_rawframes.txt' | ||
| img_norm_cfg = dict( | ||
| mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_bgr=False) | ||
| train_pipeline = [ | ||
| dict(type='SampleFrames', clip_len=32, frame_interval=2, num_clips=1), | ||
| dict(type='RawFrameDecode'), | ||
| dict(type='Resize', scale=(-1, 256)), | ||
| dict(type='RandomResizedCrop'), | ||
| dict(type='Resize', scale=(224, 224), keep_ratio=False), | ||
| dict(type='Flip', flip_ratio=0.5), | ||
| dict(type='Normalize', **img_norm_cfg), | ||
| 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=32, | ||
| frame_interval=2, | ||
| num_clips=1, | ||
| test_mode=True), | ||
| dict(type='RawFrameDecode'), | ||
| dict(type='Resize', scale=(-1, 256)), | ||
| dict(type='CenterCrop', crop_size=224), | ||
| dict(type='Flip', flip_ratio=0), | ||
| dict(type='Normalize', **img_norm_cfg), | ||
| 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=32, | ||
| frame_interval=2, | ||
| num_clips=10, | ||
| test_mode=True), | ||
| dict(type='RawFrameDecode'), | ||
| dict(type='Resize', scale=(-1, 256)), | ||
| dict(type='ThreeCrop', crop_size=256), | ||
| dict(type='Flip', flip_ratio=0), | ||
| dict(type='Normalize', **img_norm_cfg), | ||
| 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=dataset_type, | ||
| ann_file=ann_file_train, | ||
| data_prefix=data_root, | ||
| pipeline=train_pipeline), | ||
| val=dict( | ||
| type=dataset_type, | ||
| ann_file=ann_file_val, | ||
| data_prefix=data_root_val, | ||
| pipeline=val_pipeline), | ||
| test=dict( | ||
| type=dataset_type, | ||
| ann_file=ann_file_test, | ||
| data_prefix=data_root_val, | ||
| pipeline=test_pipeline)) | ||
| # optimizer | ||
| optimizer = dict( | ||
| type='SGD', lr=0.1, momentum=0.9, | ||
| weight_decay=0.0001) # this lr is used for 8 gpus | ||
| optimizer_config = dict(grad_clip=dict(max_norm=40, norm_type=2)) | ||
| # learning policy | ||
| lr_config = dict( | ||
| policy='CosineAnnealing', | ||
| min_lr=0, | ||
| warmup='linear', | ||
| warmup_by_epoch=True, | ||
| warmup_iters=34) | ||
| total_epochs = 256 | ||
| checkpoint_config = dict(interval=4) | ||
| workflow = [('train', 1)] | ||
| evaluation = dict( | ||
| interval=5, metrics=['top_k_accuracy', 'mean_class_accuracy']) | ||
| log_config = dict( | ||
| interval=20, | ||
| hooks=[ | ||
| dict(type='TextLoggerHook'), | ||
| # dict(type='TensorboardLoggerHook'), | ||
| ]) | ||
| dist_params = dict(backend='nccl') | ||
| log_level = 'INFO' | ||
| work_dir = './work_dirs/slowfast_r101_r50_4x16x1_256e_kinetics400_rgb' | ||
| load_from = None | ||
| resume_from = None | ||
| find_unused_parameters = False |
Oops, something went wrong.