-
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 with_global option * f bug * + contiguous * update * add config w. context * test with_global * update README * update changelog
- Loading branch information
1 parent
cb02092
commit dc0c82b
Showing
5 changed files
with
210 additions
and
3 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
175 changes: 175 additions & 0 deletions
175
configs/detection/ava/slowfast_context_kinetics_pretrained_r50_4x16x1_20e_ava_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 +1,175 @@ | ||
| # model setting | ||
| model = dict( | ||
| type='FastRCNN', | ||
| backbone=dict( | ||
| type='ResNet3dSlowFast', | ||
| pretrained=None, | ||
| resample_rate=8, | ||
| speed_ratio=8, | ||
| channel_ratio=8, | ||
| slow_pathway=dict( | ||
| type='resnet3d', | ||
| depth=50, | ||
| 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), | ||
| spatial_strides=(1, 2, 2, 1)), | ||
| 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, | ||
| spatial_strides=(1, 2, 2, 1))), | ||
| roi_head=dict( | ||
| type='AVARoIHead', | ||
| bbox_roi_extractor=dict( | ||
| type='SingleRoIExtractor3D', | ||
| roi_layer_type='RoIAlign', | ||
| output_size=8, | ||
| with_temporal_pool=True, | ||
| with_global=True), | ||
| bbox_head=dict( | ||
| type='BBoxHeadAVA', | ||
| in_channels=4608, | ||
| num_classes=81, | ||
| multilabel=True, | ||
| dropout_ratio=0.5))) | ||
|
|
||
| train_cfg = dict( | ||
| rcnn=dict( | ||
| assigner=dict( | ||
| type='MaxIoUAssignerAVA', | ||
| pos_iou_thr=0.9, | ||
| neg_iou_thr=0.9, | ||
| min_pos_iou=0.9), | ||
| sampler=dict( | ||
| type='RandomSampler', | ||
| num=32, | ||
| pos_fraction=1, | ||
| neg_pos_ub=-1, | ||
| add_gt_as_proposals=True), | ||
| pos_weight=1.0, | ||
| debug=False)) | ||
| test_cfg = dict(rcnn=dict(action_thr=0.00)) | ||
|
|
||
| dataset_type = 'AVADataset' | ||
| data_root = 'data/ava/rawframes' | ||
| anno_root = 'data/ava/annotations' | ||
|
|
||
| ann_file_train = f'{anno_root}/ava_train_v2.1.csv' | ||
| ann_file_val = f'{anno_root}/ava_val_v2.1.csv' | ||
|
|
||
| exclude_file_train = f'{anno_root}/ava_train_excluded_timestamps_v2.1.csv' | ||
| exclude_file_val = f'{anno_root}/ava_val_excluded_timestamps_v2.1.csv' | ||
|
|
||
| label_file = f'{anno_root}/ava_action_list_v2.1_for_activitynet_2018.pbtxt' | ||
|
|
||
| proposal_file_train = (f'{anno_root}/ava_dense_proposals_train.FAIR.' | ||
| 'recall_93.9.pkl') | ||
| proposal_file_val = f'{anno_root}/ava_dense_proposals_val.FAIR.recall_93.9.pkl' | ||
|
|
||
| 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='SampleAVAFrames', clip_len=32, frame_interval=2), | ||
| dict(type='RawFrameDecode'), | ||
| dict(type='RandomRescale', scale_range=(256, 320)), | ||
| dict(type='RandomCrop', size=256), | ||
| dict(type='Flip', flip_ratio=0.5), | ||
| dict(type='Normalize', **img_norm_cfg), | ||
| dict(type='FormatShape', input_format='NCTHW', collapse=True), | ||
| # Rename is needed to use mmdet detectors | ||
| dict(type='Rename', mapping=dict(imgs='img')), | ||
| dict(type='ToTensor', keys=['img', 'proposals', 'gt_bboxes', 'gt_labels']), | ||
| dict( | ||
| type='ToDataContainer', | ||
| fields=[ | ||
| dict(key=['proposals', 'gt_bboxes', 'gt_labels'], stack=False) | ||
| ]), | ||
| dict( | ||
| type='Collect', | ||
| keys=['img', 'proposals', 'gt_bboxes', 'gt_labels'], | ||
| meta_keys=['scores', 'entity_ids']) | ||
| ] | ||
| # The testing is w/o. any cropping / flipping | ||
| val_pipeline = [ | ||
| dict(type='SampleAVAFrames', clip_len=32, frame_interval=2), | ||
| dict(type='RawFrameDecode'), | ||
| dict(type='Resize', scale=(-1, 256)), | ||
| dict(type='Normalize', **img_norm_cfg), | ||
| dict(type='FormatShape', input_format='NCTHW', collapse=True), | ||
| # Rename is needed to use mmdet detectors | ||
| dict(type='Rename', mapping=dict(imgs='img')), | ||
| dict(type='ToTensor', keys=['img', 'proposals']), | ||
| dict(type='ToDataContainer', fields=[dict(key='proposals', stack=False)]), | ||
| dict( | ||
| type='Collect', | ||
| keys=['img', 'proposals'], | ||
| meta_keys=['scores', 'img_shape'], | ||
| nested=True) | ||
| ] | ||
|
|
||
| data = dict( | ||
| videos_per_gpu=9, | ||
| workers_per_gpu=4, | ||
| val_dataloader=dict(videos_per_gpu=1), | ||
| test_dataloader=dict(videos_per_gpu=1), | ||
| train=dict( | ||
| type=dataset_type, | ||
| ann_file=ann_file_train, | ||
| exclude_file=exclude_file_train, | ||
| pipeline=train_pipeline, | ||
| label_file=label_file, | ||
| proposal_file=proposal_file_train, | ||
| person_det_score_thr=0.9, | ||
| data_prefix=data_root), | ||
| val=dict( | ||
| type=dataset_type, | ||
| ann_file=ann_file_val, | ||
| exclude_file=exclude_file_val, | ||
| pipeline=val_pipeline, | ||
| label_file=label_file, | ||
| proposal_file=proposal_file_val, | ||
| person_det_score_thr=0.9, | ||
| data_prefix=data_root)) | ||
| data['test'] = data['val'] | ||
|
|
||
| optimizer = dict(type='SGD', lr=0.1125, momentum=0.9, weight_decay=0.00001) | ||
| # 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=[10, 15], | ||
| warmup='linear', | ||
| warmup_by_epoch=True, | ||
| warmup_iters=5, | ||
| warmup_ratio=0.1) | ||
| total_epochs = 20 | ||
| checkpoint_config = dict(interval=1) | ||
| workflow = [('train', 1)] | ||
| evaluation = dict(interval=1) | ||
| log_config = dict( | ||
| interval=20, hooks=[ | ||
| dict(type='TextLoggerHook'), | ||
| ]) | ||
| dist_params = dict(backend='nccl') | ||
| log_level = 'INFO' | ||
| work_dir = ('./work_dirs/ava/' | ||
| 'slowfast_context_kinetics_pretrained_r50_4x16x1_20e_ava_rgb') | ||
| load_from = ('https://download.openmmlab.com/mmaction/recognition/slowfast/' | ||
| 'slowfast_r50_4x16x1_256e_kinetics400_rgb/' | ||
| 'slowfast_r50_4x16x1_256e_kinetics400_rgb_20200704-bcde7ed7.pth') | ||
| resume_from = None | ||
| find_unused_parameters = False |
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
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
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