-
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.
[Feature] Add hrformer backbone (#1203)
* hrformer * modify cfg * update url and readme for hrformer. * add readme for hrformer papar * modify reaadme * fix publish year Co-authored-by: ly015 <[email protected]>
- Loading branch information
1 parent
546a1e4
commit b168781
Showing
13 changed files
with
1,842 additions
and
1 deletion.
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
191 changes: 191 additions & 0 deletions
191
configs/body/2d_kpt_sview_rgb_img/topdown_heatmap/coco/hrformer_base_coco_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 +1,191 @@ | ||
| log_level = 'INFO' | ||
| load_from = None | ||
| resume_from = None | ||
| dist_params = dict(backend='nccl') | ||
| workflow = [('train', 1)] | ||
| checkpoint_config = dict(interval=5, create_symlink=False) | ||
| evaluation = dict(interval=10, metric='mAP', key_indicator='AP') | ||
|
|
||
| optimizer = dict( | ||
| type='AdamW', | ||
| lr=5e-4, | ||
| betas=(0.9, 0.999), | ||
| weight_decay=0.01, | ||
| paramwise_cfg=dict( | ||
| custom_keys={'relative_position_bias_table': dict(decay_mult=0.)})) | ||
|
|
||
| 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'), | ||
| ]) | ||
|
|
||
| channel_cfg = dict( | ||
| num_output_channels=17, | ||
| dataset_joints=17, | ||
| dataset_channel=[ | ||
| [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16], | ||
| ], | ||
| inference_channel=[ | ||
| 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16 | ||
| ]) | ||
|
|
||
| # model settings | ||
| norm_cfg = dict(type='SyncBN', requires_grad=True) | ||
| model = dict( | ||
| type='TopDown', | ||
| pretrained='https://download.openmmlab.com/mmpose/' | ||
| 'pretrain_models/hrformer_base-32815020_20220226.pth', | ||
| backbone=dict( | ||
| type='HRFormer', | ||
| in_channels=3, | ||
| norm_cfg=norm_cfg, | ||
| extra=dict( | ||
| drop_path_rate=0.2, | ||
| with_rpe=False, | ||
| stage1=dict( | ||
| num_modules=1, | ||
| num_branches=1, | ||
| block='BOTTLENECK', | ||
| num_blocks=(2, ), | ||
| num_channels=(64, ), | ||
| num_heads=[2], | ||
| mlp_ratios=[4]), | ||
| stage2=dict( | ||
| num_modules=1, | ||
| num_branches=2, | ||
| block='HRFORMERBLOCK', | ||
| num_blocks=(2, 2), | ||
| num_channels=(78, 156), | ||
| num_heads=[2, 4], | ||
| mlp_ratios=[4, 4], | ||
| window_sizes=[7, 7]), | ||
| stage3=dict( | ||
| num_modules=4, | ||
| num_branches=3, | ||
| block='HRFORMERBLOCK', | ||
| num_blocks=(2, 2, 2), | ||
| num_channels=(78, 156, 312), | ||
| num_heads=[2, 4, 8], | ||
| mlp_ratios=[4, 4, 4], | ||
| window_sizes=[7, 7, 7]), | ||
| stage4=dict( | ||
| num_modules=2, | ||
| num_branches=4, | ||
| block='HRFORMERBLOCK', | ||
| num_blocks=(2, 2, 2, 2), | ||
| num_channels=(78, 156, 312, 624), | ||
| num_heads=[2, 4, 8, 16], | ||
| mlp_ratios=[4, 4, 4, 4], | ||
| window_sizes=[7, 7, 7, 7]))), | ||
| keypoint_head=dict( | ||
| type='TopdownHeatmapSimpleHead', | ||
| in_channels=78, | ||
| out_channels=channel_cfg['num_output_channels'], | ||
| num_deconv_layers=0, | ||
| extra=dict(final_conv_kernel=1, ), | ||
| 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_root = 'data/coco' | ||
| 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=f'{data_root}/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=40, scale_factor=0.5), | ||
| 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 = dict( | ||
| samples_per_gpu=32, | ||
| workers_per_gpu=2, | ||
| val_dataloader=dict(samples_per_gpu=32), | ||
| test_dataloader=dict(samples_per_gpu=32), | ||
| train=dict( | ||
| type='TopDownCocoDataset', | ||
| ann_file=f'{data_root}/annotations/person_keypoints_train2017.json', | ||
| img_prefix=f'{data_root}/train2017/', | ||
| data_cfg=data_cfg, | ||
| pipeline=train_pipeline), | ||
| val=dict( | ||
| type='TopDownCocoDataset', | ||
| ann_file=f'{data_root}/annotations/person_keypoints_val2017.json', | ||
| img_prefix=f'{data_root}/val2017/', | ||
| data_cfg=data_cfg, | ||
| pipeline=val_pipeline), | ||
| test=dict( | ||
| type='TopDownCocoDataset', | ||
| ann_file=f'{data_root}/annotations/person_keypoints_val2017.json', | ||
| img_prefix=f'{data_root}/val2017/', | ||
| data_cfg=data_cfg, | ||
| pipeline=val_pipeline), | ||
| ) | ||
|
|
||
| # fp16 settings | ||
| fp16 = dict(loss_scale='dynamic') |
Oops, something went wrong.