-
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.
[Feature] Add ViPNAS_Mbv3 wholebody model (#1055)
* add vipnas mbv3 coco_wholebody * add vipnas mbv3 coco_wholebody md&yml * fix lint Co-authored-by: ly015 <[email protected]>
- Loading branch information
Showing
6 changed files
with
342 additions
and
4 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
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
146 changes: 146 additions & 0 deletions
146
...2d_kpt_sview_rgb_img/topdown_heatmap/coco-wholebody/vipnas_mbv3_coco_wholebody_256x192.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 +1,146 @@ | ||
| _base_ = ['../../../../_base_/datasets/coco_wholebody.py'] | ||
| log_level = 'INFO' | ||
| load_from = None | ||
| resume_from = None | ||
| dist_params = dict(backend='nccl') | ||
| workflow = [('train', 1)] | ||
| checkpoint_config = dict(interval=10) | ||
| evaluation = dict(interval=10, metric='mAP', save_best='AP') | ||
|
|
||
| optimizer = dict( | ||
| type='Adam', | ||
| lr=5e-4, | ||
| ) | ||
| optimizer_config = dict(grad_clip=None) | ||
| # learning policy | ||
| lr_config = dict( | ||
| policy='step', | ||
| warmup='linear', | ||
| warmup_iters=500, | ||
| warmup_ratio=0.001, | ||
| step=[170, 200]) | ||
| total_epochs = 210 | ||
| log_config = dict( | ||
| interval=50, | ||
| hooks=[ | ||
| dict(type='TextLoggerHook'), | ||
| # dict(type='TensorboardLoggerHook') | ||
| ]) | ||
|
|
||
| channel_cfg = dict( | ||
| num_output_channels=133, | ||
| dataset_joints=133, | ||
| dataset_channel=[ | ||
| list(range(133)), | ||
| ], | ||
| inference_channel=list(range(133))) | ||
|
|
||
| # model settings | ||
| model = dict( | ||
| type='TopDown', | ||
| pretrained=None, | ||
| backbone=dict(type='ViPNAS_MobileNetV3'), | ||
| keypoint_head=dict( | ||
| type='ViPNASHeatmapSimpleHead', | ||
| in_channels=160, | ||
| out_channels=channel_cfg['num_output_channels'], | ||
| num_deconv_filters=(160, 160, 160), | ||
| num_deconv_groups=(160, 160, 160), | ||
| loss_keypoint=dict(type='JointsMSELoss', use_target_weight=True)), | ||
| train_cfg=dict(), | ||
| test_cfg=dict( | ||
| flip_test=True, | ||
| post_process='default', | ||
| shift_heatmap=True, | ||
| modulate_kernel=11)) | ||
|
|
||
| data_cfg = dict( | ||
| image_size=[192, 256], | ||
| heatmap_size=[48, 64], | ||
| num_output_channels=channel_cfg['num_output_channels'], | ||
| num_joints=channel_cfg['dataset_joints'], | ||
| dataset_channel=channel_cfg['dataset_channel'], | ||
| inference_channel=channel_cfg['inference_channel'], | ||
| soft_nms=False, | ||
| nms_thr=1.0, | ||
| oks_thr=0.9, | ||
| vis_thr=0.2, | ||
| use_gt_bbox=False, | ||
| det_bbox_thr=0.0, | ||
| bbox_file='data/coco/person_detection_results/' | ||
| 'COCO_val2017_detections_AP_H_56_person.json', | ||
| ) | ||
|
|
||
| train_pipeline = [ | ||
| dict(type='LoadImageFromFile'), | ||
| dict(type='TopDownRandomFlip', flip_prob=0.5), | ||
| dict( | ||
| type='TopDownHalfBodyTransform', | ||
| num_joints_half_body=8, | ||
| prob_half_body=0.3), | ||
| dict( | ||
| type='TopDownGetRandomScaleRotation', rot_factor=30, | ||
| scale_factor=0.25), | ||
| dict(type='TopDownAffine'), | ||
| dict(type='ToTensor'), | ||
| dict( | ||
| type='NormalizeTensor', | ||
| mean=[0.485, 0.456, 0.406], | ||
| std=[0.229, 0.224, 0.225]), | ||
| dict(type='TopDownGenerateTarget', sigma=2), | ||
| dict( | ||
| type='Collect', | ||
| keys=['img', 'target', 'target_weight'], | ||
| meta_keys=[ | ||
| 'image_file', 'joints_3d', 'joints_3d_visible', 'center', 'scale', | ||
| 'rotation', 'bbox_score', 'flip_pairs' | ||
| ]), | ||
| ] | ||
|
|
||
| val_pipeline = [ | ||
| dict(type='LoadImageFromFile'), | ||
| dict(type='TopDownAffine'), | ||
| dict(type='ToTensor'), | ||
| dict( | ||
| type='NormalizeTensor', | ||
| mean=[0.485, 0.456, 0.406], | ||
| std=[0.229, 0.224, 0.225]), | ||
| dict( | ||
| type='Collect', | ||
| keys=['img'], | ||
| meta_keys=[ | ||
| 'image_file', 'center', 'scale', 'rotation', 'bbox_score', | ||
| 'flip_pairs' | ||
| ]), | ||
| ] | ||
|
|
||
| test_pipeline = val_pipeline | ||
|
|
||
| data_root = 'data/coco' | ||
| data = dict( | ||
| samples_per_gpu=64, | ||
| workers_per_gpu=2, | ||
| val_dataloader=dict(samples_per_gpu=32), | ||
| test_dataloader=dict(samples_per_gpu=32), | ||
| train=dict( | ||
| type='TopDownCocoWholeBodyDataset', | ||
| ann_file=f'{data_root}/annotations/coco_wholebody_train_v1.0.json', | ||
| img_prefix=f'{data_root}/train2017/', | ||
| data_cfg=data_cfg, | ||
| pipeline=train_pipeline, | ||
| dataset_info={{_base_.dataset_info}}), | ||
| val=dict( | ||
| type='TopDownCocoWholeBodyDataset', | ||
| ann_file=f'{data_root}/annotations/coco_wholebody_val_v1.0.json', | ||
| img_prefix=f'{data_root}/val2017/', | ||
| data_cfg=data_cfg, | ||
| pipeline=val_pipeline, | ||
| dataset_info={{_base_.dataset_info}}), | ||
| test=dict( | ||
| type='TopDownCocoWholeBodyDataset', | ||
| ann_file=f'{data_root}/annotations/coco_wholebody_val_v1.0.json', | ||
| img_prefix=f'{data_root}/val2017/', | ||
| data_cfg=data_cfg, | ||
| pipeline=test_pipeline, | ||
| dataset_info={{_base_.dataset_info}}), | ||
| ) |
146 changes: 146 additions & 0 deletions
146
...t_sview_rgb_img/topdown_heatmap/coco-wholebody/vipnas_mbv3_coco_wholebody_256x192_dark.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 +1,146 @@ | ||
| _base_ = ['../../../../_base_/datasets/coco_wholebody.py'] | ||
| log_level = 'INFO' | ||
| load_from = None | ||
| resume_from = None | ||
| dist_params = dict(backend='nccl') | ||
| workflow = [('train', 1)] | ||
| checkpoint_config = dict(interval=10) | ||
| evaluation = dict(interval=10, metric='mAP', save_best='AP') | ||
|
|
||
| optimizer = dict( | ||
| type='Adam', | ||
| lr=5e-4, | ||
| ) | ||
| optimizer_config = dict(grad_clip=None) | ||
| # learning policy | ||
| lr_config = dict( | ||
| policy='step', | ||
| warmup='linear', | ||
| warmup_iters=500, | ||
| warmup_ratio=0.001, | ||
| step=[170, 200]) | ||
| total_epochs = 210 | ||
| log_config = dict( | ||
| interval=50, | ||
| hooks=[ | ||
| dict(type='TextLoggerHook'), | ||
| # dict(type='TensorboardLoggerHook') | ||
| ]) | ||
|
|
||
| channel_cfg = dict( | ||
| num_output_channels=133, | ||
| dataset_joints=133, | ||
| dataset_channel=[ | ||
| list(range(133)), | ||
| ], | ||
| inference_channel=list(range(133))) | ||
|
|
||
| # model settings | ||
| model = dict( | ||
| type='TopDown', | ||
| pretrained=None, | ||
| backbone=dict(type='ViPNAS_MobileNetV3'), | ||
| keypoint_head=dict( | ||
| type='ViPNASHeatmapSimpleHead', | ||
| in_channels=160, | ||
| out_channels=channel_cfg['num_output_channels'], | ||
| num_deconv_filters=(160, 160, 160), | ||
| num_deconv_groups=(160, 160, 160), | ||
| loss_keypoint=dict(type='JointsMSELoss', use_target_weight=True)), | ||
| train_cfg=dict(), | ||
| test_cfg=dict( | ||
| flip_test=True, | ||
| post_process='unbiased', | ||
| shift_heatmap=True, | ||
| modulate_kernel=11)) | ||
|
|
||
| data_cfg = dict( | ||
| image_size=[192, 256], | ||
| heatmap_size=[48, 64], | ||
| num_output_channels=channel_cfg['num_output_channels'], | ||
| num_joints=channel_cfg['dataset_joints'], | ||
| dataset_channel=channel_cfg['dataset_channel'], | ||
| inference_channel=channel_cfg['inference_channel'], | ||
| soft_nms=False, | ||
| nms_thr=1.0, | ||
| oks_thr=0.9, | ||
| vis_thr=0.2, | ||
| use_gt_bbox=False, | ||
| det_bbox_thr=0.0, | ||
| bbox_file='data/coco/person_detection_results/' | ||
| 'COCO_val2017_detections_AP_H_56_person.json', | ||
| ) | ||
|
|
||
| train_pipeline = [ | ||
| dict(type='LoadImageFromFile'), | ||
| dict(type='TopDownRandomFlip', flip_prob=0.5), | ||
| dict( | ||
| type='TopDownHalfBodyTransform', | ||
| num_joints_half_body=8, | ||
| prob_half_body=0.3), | ||
| dict( | ||
| type='TopDownGetRandomScaleRotation', rot_factor=30, | ||
| scale_factor=0.25), | ||
| dict(type='TopDownAffine'), | ||
| dict(type='ToTensor'), | ||
| dict( | ||
| type='NormalizeTensor', | ||
| mean=[0.485, 0.456, 0.406], | ||
| std=[0.229, 0.224, 0.225]), | ||
| dict(type='TopDownGenerateTarget', sigma=2, unbiased_encoding=True), | ||
| dict( | ||
| type='Collect', | ||
| keys=['img', 'target', 'target_weight'], | ||
| meta_keys=[ | ||
| 'image_file', 'joints_3d', 'joints_3d_visible', 'center', 'scale', | ||
| 'rotation', 'bbox_score', 'flip_pairs' | ||
| ]), | ||
| ] | ||
|
|
||
| val_pipeline = [ | ||
| dict(type='LoadImageFromFile'), | ||
| dict(type='TopDownAffine'), | ||
| dict(type='ToTensor'), | ||
| dict( | ||
| type='NormalizeTensor', | ||
| mean=[0.485, 0.456, 0.406], | ||
| std=[0.229, 0.224, 0.225]), | ||
| dict( | ||
| type='Collect', | ||
| keys=['img'], | ||
| meta_keys=[ | ||
| 'image_file', 'center', 'scale', 'rotation', 'bbox_score', | ||
| 'flip_pairs' | ||
| ]), | ||
| ] | ||
|
|
||
| test_pipeline = val_pipeline | ||
|
|
||
| data_root = 'data/coco' | ||
| data = dict( | ||
| samples_per_gpu=64, | ||
| workers_per_gpu=2, | ||
| val_dataloader=dict(samples_per_gpu=32), | ||
| test_dataloader=dict(samples_per_gpu=32), | ||
| train=dict( | ||
| type='TopDownCocoWholeBodyDataset', | ||
| ann_file=f'{data_root}/annotations/coco_wholebody_train_v1.0.json', | ||
| img_prefix=f'{data_root}/train2017/', | ||
| data_cfg=data_cfg, | ||
| pipeline=train_pipeline, | ||
| dataset_info={{_base_.dataset_info}}), | ||
| val=dict( | ||
| type='TopDownCocoWholeBodyDataset', | ||
| ann_file=f'{data_root}/annotations/coco_wholebody_val_v1.0.json', | ||
| img_prefix=f'{data_root}/val2017/', | ||
| data_cfg=data_cfg, | ||
| pipeline=val_pipeline, | ||
| dataset_info={{_base_.dataset_info}}), | ||
| test=dict( | ||
| type='TopDownCocoWholeBodyDataset', | ||
| ann_file=f'{data_root}/annotations/coco_wholebody_val_v1.0.json', | ||
| img_prefix=f'{data_root}/val2017/', | ||
| data_cfg=data_cfg, | ||
| pipeline=test_pipeline, | ||
| dataset_info={{_base_.dataset_info}}), | ||
| ) |