forked from open-mmlab/mmsegmentation
-
Notifications
You must be signed in to change notification settings - Fork 0
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 hvu training configs * update README * add missing ckpt links * update changelog * make mean_average_percision robust (some category may missing in testing) * fix * fix bad configs * check if results is empty
- Loading branch information
1 parent
4e24ad7
commit 67151c1
Showing
9 changed files
with
781 additions
and
7 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
126 changes: 126 additions & 0 deletions
126
configs/recognition/tsn/hvu/tsn_r18_1x1x8_100e_hvu_action_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 +1,126 @@ | ||
| # model settings | ||
| category_nums = dict( | ||
| action=729, attribute=117, concept=291, event=69, object=1679, scene=248) | ||
| target_cate = 'action' | ||
|
|
||
| model = dict( | ||
| type='Recognizer2D', | ||
| backbone=dict( | ||
| type='ResNet', | ||
| pretrained='torchvision://resnet18', | ||
| depth=18, | ||
| norm_eval=False), | ||
| cls_head=dict( | ||
| type='TSNHead', | ||
| num_classes=category_nums[target_cate], | ||
| in_channels=512, | ||
| spatial_type='avg', | ||
| multi_class=True, | ||
| consensus=dict(type='AvgConsensus', dim=1), | ||
| loss_cls=dict(type='BCELossWithLogits', loss_weight=333.), | ||
| dropout_ratio=0.4, | ||
| init_std=0.01)) | ||
| # model training and testing settings | ||
| train_cfg = None | ||
| test_cfg = dict(average_clips=None) | ||
| # dataset settings | ||
| dataset_type = 'RawframeDataset' | ||
| data_root = 'data/hvu/rawframes_train' | ||
| data_root_val = 'data/hvu/rawframes_val' | ||
| ann_file_train = f'data/hvu/hvu_{target_cate}_train.json' | ||
| ann_file_val = f'data/hvu/hvu_{target_cate}_val.json' | ||
| ann_file_test = f'data/hvu/hvu_{target_cate}_val.json' | ||
| 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=1, frame_interval=1, num_clips=8), | ||
| 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='NCHW'), | ||
| dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]), | ||
| dict(type='ToTensor', keys=['imgs', 'label']) | ||
| ] | ||
| val_pipeline = [ | ||
| dict( | ||
| type='SampleFrames', | ||
| clip_len=1, | ||
| frame_interval=1, | ||
| num_clips=8, | ||
| test_mode=True), | ||
| dict(type='RawFrameDecode'), | ||
| dict(type='Resize', scale=(-1, 256)), | ||
| dict(type='CenterCrop', crop_size=256), | ||
| dict(type='Flip', flip_ratio=0), | ||
| dict(type='Normalize', **img_norm_cfg), | ||
| dict(type='FormatShape', input_format='NCHW'), | ||
| dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]), | ||
| dict(type='ToTensor', keys=['imgs']) | ||
| ] | ||
| test_pipeline = [ | ||
| dict( | ||
| type='SampleFrames', | ||
| clip_len=1, | ||
| frame_interval=1, | ||
| num_clips=25, | ||
| 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='NCHW'), | ||
| dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]), | ||
| dict(type='ToTensor', keys=['imgs']) | ||
| ] | ||
| data = dict( | ||
| videos_per_gpu=32, | ||
| workers_per_gpu=2, | ||
| train=dict( | ||
| type=dataset_type, | ||
| ann_file=ann_file_train, | ||
| data_prefix=data_root, | ||
| pipeline=train_pipeline, | ||
| multi_class=True, | ||
| num_classes=category_nums[target_cate], | ||
| filename_tmpl='img_{:05d}.jpg'), | ||
| val=dict( | ||
| type=dataset_type, | ||
| ann_file=ann_file_val, | ||
| data_prefix=data_root_val, | ||
| pipeline=val_pipeline, | ||
| multi_class=True, | ||
| num_classes=category_nums[target_cate], | ||
| filename_tmpl='img_{:05d}.jpg'), | ||
| test=dict( | ||
| type=dataset_type, | ||
| ann_file=ann_file_test, | ||
| data_prefix=data_root_val, | ||
| pipeline=test_pipeline, | ||
| multi_class=True, | ||
| num_classes=category_nums[target_cate], | ||
| filename_tmpl='img_{:05d}.jpg')) | ||
| # 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=[40, 80]) | ||
| total_epochs = 100 | ||
| checkpoint_config = dict(interval=1) | ||
| evaluation = dict(interval=2, metrics=['mean_average_precision']) | ||
| log_config = dict( | ||
| interval=20, hooks=[ | ||
| dict(type='TextLoggerHook'), | ||
| ]) | ||
| # runtime settings | ||
| dist_params = dict(backend='nccl') | ||
| log_level = 'INFO' | ||
| work_dir = f'./work_dirs/tsn_r18_1x1x8_100e_hvu_{target_cate}_rgb/' | ||
| load_from = None | ||
| resume_from = None | ||
| workflow = [('train', 1)] |
126 changes: 126 additions & 0 deletions
126
configs/recognition/tsn/hvu/tsn_r18_1x1x8_100e_hvu_attribute_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 +1,126 @@ | ||
| # model settings | ||
| category_nums = dict( | ||
| action=729, attribute=117, concept=291, event=69, object=1679, scene=248) | ||
| target_cate = 'attribute' | ||
|
|
||
| model = dict( | ||
| type='Recognizer2D', | ||
| backbone=dict( | ||
| type='ResNet', | ||
| pretrained='torchvision://resnet18', | ||
| depth=18, | ||
| norm_eval=False), | ||
| cls_head=dict( | ||
| type='TSNHead', | ||
| num_classes=category_nums[target_cate], | ||
| in_channels=512, | ||
| spatial_type='avg', | ||
| multi_class=True, | ||
| consensus=dict(type='AvgConsensus', dim=1), | ||
| loss_cls=dict(type='BCELossWithLogits', loss_weight=333.), | ||
| dropout_ratio=0.4, | ||
| init_std=0.01)) | ||
| # model training and testing settings | ||
| train_cfg = None | ||
| test_cfg = dict(average_clips=None) | ||
| # dataset settings | ||
| dataset_type = 'RawframeDataset' | ||
| data_root = 'data/hvu/rawframes_train' | ||
| data_root_val = 'data/hvu/rawframes_val' | ||
| ann_file_train = f'data/hvu/hvu_{target_cate}_train.json' | ||
| ann_file_val = f'data/hvu/hvu_{target_cate}_val.json' | ||
| ann_file_test = f'data/hvu/hvu_{target_cate}_val.json' | ||
| 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=1, frame_interval=1, num_clips=8), | ||
| 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='NCHW'), | ||
| dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]), | ||
| dict(type='ToTensor', keys=['imgs', 'label']) | ||
| ] | ||
| val_pipeline = [ | ||
| dict( | ||
| type='SampleFrames', | ||
| clip_len=1, | ||
| frame_interval=1, | ||
| num_clips=8, | ||
| test_mode=True), | ||
| dict(type='RawFrameDecode'), | ||
| dict(type='Resize', scale=(-1, 256)), | ||
| dict(type='CenterCrop', crop_size=256), | ||
| dict(type='Flip', flip_ratio=0), | ||
| dict(type='Normalize', **img_norm_cfg), | ||
| dict(type='FormatShape', input_format='NCHW'), | ||
| dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]), | ||
| dict(type='ToTensor', keys=['imgs']) | ||
| ] | ||
| test_pipeline = [ | ||
| dict( | ||
| type='SampleFrames', | ||
| clip_len=1, | ||
| frame_interval=1, | ||
| num_clips=25, | ||
| 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='NCHW'), | ||
| dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]), | ||
| dict(type='ToTensor', keys=['imgs']) | ||
| ] | ||
| data = dict( | ||
| videos_per_gpu=32, | ||
| workers_per_gpu=2, | ||
| train=dict( | ||
| type=dataset_type, | ||
| ann_file=ann_file_train, | ||
| data_prefix=data_root, | ||
| pipeline=train_pipeline, | ||
| multi_class=True, | ||
| num_classes=category_nums[target_cate], | ||
| filename_tmpl='img_{:05d}.jpg'), | ||
| val=dict( | ||
| type=dataset_type, | ||
| ann_file=ann_file_val, | ||
| data_prefix=data_root_val, | ||
| pipeline=val_pipeline, | ||
| multi_class=True, | ||
| num_classes=category_nums[target_cate], | ||
| filename_tmpl='img_{:05d}.jpg'), | ||
| test=dict( | ||
| type=dataset_type, | ||
| ann_file=ann_file_test, | ||
| data_prefix=data_root_val, | ||
| pipeline=test_pipeline, | ||
| multi_class=True, | ||
| num_classes=category_nums[target_cate], | ||
| filename_tmpl='img_{:05d}.jpg')) | ||
| # 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=[40, 80]) | ||
| total_epochs = 100 | ||
| checkpoint_config = dict(interval=1) | ||
| evaluation = dict(interval=2, metrics=['mean_average_precision']) | ||
| log_config = dict( | ||
| interval=20, hooks=[ | ||
| dict(type='TextLoggerHook'), | ||
| ]) | ||
| # runtime settings | ||
| dist_params = dict(backend='nccl') | ||
| log_level = 'INFO' | ||
| work_dir = f'./work_dirs/tsn_r18_1x1x8_100e_hvu_{target_cate}_rgb/' | ||
| load_from = None | ||
| resume_from = None | ||
| workflow = [('train', 1)] |
Oops, something went wrong.