-
Notifications
You must be signed in to change notification settings - Fork 1.2k
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Add slowonly finetune setting (#173)
- Loading branch information
1 parent
1f33cb8
commit 7f22912
Showing
3 changed files
with
242 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
120 changes: 120 additions & 0 deletions
120
configs/recognition/slowonly/slowonly_imagenet_pretrained_r50_4x16x1_150e_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 +1,120 @@ | ||
| 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=None) | ||
| 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=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=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=0.01, 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, 130], | ||
| warmup='linear', | ||
| warmup_by_epoch=True, | ||
| warmup_iters=10) | ||
| total_epochs = 150 | ||
| checkpoint_config = dict(interval=4) | ||
| workflow = [('train', 1)] | ||
| evaluation = dict( | ||
| interval=5, metrics=['top_k_accuracy', 'mean_class_accuracy'], topk=(1, 5)) | ||
| 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_150e' | ||
| '_kinetics400_rgb') | ||
| load_from = None | ||
| resume_from = None | ||
| find_unused_parameters = False |
120 changes: 120 additions & 0 deletions
120
configs/recognition/slowonly/slowonly_imagenet_pretrained_r50_8x8x1_150e_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 +1,120 @@ | ||
| 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=None) | ||
| 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=8, frame_interval=8, 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=8, | ||
| frame_interval=8, | ||
| 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=8, | ||
| frame_interval=8, | ||
| 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=0.01, 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, 130], | ||
| warmup='linear', | ||
| warmup_by_epoch=True, | ||
| warmup_iters=10) | ||
| total_epochs = 150 | ||
| checkpoint_config = dict(interval=4) | ||
| workflow = [('train', 1)] | ||
| evaluation = dict( | ||
| interval=5, metrics=['top_k_accuracy', 'mean_class_accuracy'], topk=(1, 5)) | ||
| 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_8x8x1_150e' | ||
| '_kinetics400_rgb') | ||
| load_from = None | ||
| resume_from = None | ||
| find_unused_parameters = False |