-
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.
* resolve comments * update changelog * add config * add table * update url * update url * remove comment
- Loading branch information
1 parent
4dfae3a
commit e4b8bfc
Showing
3 changed files
with
256 additions
and
12 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
114 changes: 114 additions & 0 deletions
114
configs/recognition/slowonly/slowonly_imagenet_pretrained_r50_4x16x1_120e_gym99_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 +1,114 @@ | ||
| model = dict( | ||
| type='Recognizer3D', | ||
| backbone=dict( | ||
| type='ResNet3dSlowOnly', | ||
| depth=50, | ||
| pretrained='torchvision://resnet50', | ||
| lateral=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=400, | ||
| spatial_type='avg', | ||
| dropout_ratio=0.5)) | ||
| train_cfg = None | ||
| test_cfg = dict(average_clips='prob') | ||
| dataset_type = 'RawframeDataset' | ||
| data_root = 'data/gym/subaction_frames' | ||
| data_root_val = 'data/gym/subaction_frames' | ||
| ann_file_train = 'data/gym/annotations/gym99_train_frame.txt' | ||
| ann_file_val = 'data/gym/annotations/gym99_val_frame.txt' | ||
| ann_file_test = 'data/gym/annotations/gym99_val_frame.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=4, frame_interval=16, 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=4, | ||
| frame_interval=16, | ||
| 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=4, | ||
| frame_interval=16, | ||
| 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=24, | ||
| 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=0.03, 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='step', step=[90, 110]) | ||
| total_epochs = 120 | ||
| checkpoint_config = dict(interval=1) | ||
| 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/slowonly_imagenet_pretrained_r50_4x16x1_120e_gym99_rgb' | ||
| load_from = None | ||
| resume_from = None | ||
| find_unused_parameters = False |
Oops, something went wrong.