-
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.
* add posetrack * update posetrack18 * add config * init posetrack dataset * update posetrack18 * fix dependencies * make pred dir * fix dependencies * fix docs * fix build error * rm dataclass * rm unnecessary cpu/cuda mapping * add @ * fix clone to copy * fix return values * add posetrack test * use url model path * add hrnet * use gt bbox * add pre-trained models * fix build * update modelzoo * add tests * add tests * add tests * compress the jpeg images
- Loading branch information
Showing
25 changed files
with
4,366 additions
and
21 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
174 changes: 174 additions & 0 deletions
174
configs/top_down/hrnet/posetrack18/hrnet_w32_posetrack18_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 +1,174 @@ | ||
| log_level = 'INFO' | ||
| load_from = 'https://download.openmmlab.com/mmpose/top_down/hrnet/hrnet_w32_coco_256x192-c78dce93_20200708.pth' # noqa: E501 | ||
| resume_from = None | ||
| dist_params = dict(backend='nccl') | ||
| workflow = [('train', 1)] | ||
| checkpoint_config = dict(interval=1) | ||
| evaluation = dict(interval=1, metric='mAP', key_indicator='Total 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=[10, 15]) | ||
| total_epochs = 20 | ||
| log_config = dict( | ||
| interval=50, | ||
| hooks=[ | ||
| dict(type='TextLoggerHook'), | ||
| # dict(type='TensorboardLoggerHook') | ||
| ]) | ||
|
|
||
| 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 | ||
| model = dict( | ||
| type='TopDown', | ||
| pretrained=None, | ||
| backbone=dict( | ||
| type='HRNet', | ||
| in_channels=3, | ||
| extra=dict( | ||
| stage1=dict( | ||
| num_modules=1, | ||
| num_branches=1, | ||
| block='BOTTLENECK', | ||
| num_blocks=(4, ), | ||
| num_channels=(64, )), | ||
| stage2=dict( | ||
| num_modules=1, | ||
| num_branches=2, | ||
| block='BASIC', | ||
| num_blocks=(4, 4), | ||
| num_channels=(32, 64)), | ||
| stage3=dict( | ||
| num_modules=4, | ||
| num_branches=3, | ||
| block='BASIC', | ||
| num_blocks=(4, 4, 4), | ||
| num_channels=(32, 64, 128)), | ||
| stage4=dict( | ||
| num_modules=3, | ||
| num_branches=4, | ||
| block='BASIC', | ||
| num_blocks=(4, 4, 4, 4), | ||
| num_channels=(32, 64, 128, 256))), | ||
| ), | ||
| keypoint_head=dict( | ||
| type='TopDownSimpleHead', | ||
| in_channels=32, | ||
| out_channels=channel_cfg['num_output_channels'], | ||
| num_deconv_layers=0, | ||
| extra=dict(final_conv_kernel=1, ), | ||
| ), | ||
| train_cfg=dict(), | ||
| test_cfg=dict( | ||
| flip_test=True, | ||
| post_process=True, | ||
| shift_heatmap=True, | ||
| unbiased_decoding=False, | ||
| modulate_kernel=11), | ||
| loss_pose=dict(type='JointsMSELoss', use_target_weight=True)) | ||
|
|
||
| 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, | ||
| bbox_thr=1.0, | ||
| use_gt_bbox=True, | ||
| image_thr=0.4, | ||
| bbox_file='data/posetrack18/annotations/' | ||
| 'posetrack18_val_human_detections.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_root = 'data/posetrack18' | ||
| data = dict( | ||
| samples_per_gpu=64, | ||
| workers_per_gpu=2, | ||
| train=dict( | ||
| type='TopDownPoseTrack18Dataset', | ||
| ann_file=f'{data_root}/annotations/posetrack18_train.json', | ||
| img_prefix=f'{data_root}/', | ||
| data_cfg=data_cfg, | ||
| pipeline=train_pipeline), | ||
| val=dict( | ||
| type='TopDownPoseTrack18Dataset', | ||
| ann_file=f'{data_root}/annotations/posetrack18_val.json', | ||
| img_prefix=f'{data_root}/', | ||
| data_cfg=data_cfg, | ||
| pipeline=val_pipeline), | ||
| test=dict( | ||
| type='TopDownPoseTrack18Dataset', | ||
| ann_file=f'{data_root}/annotations/posetrack18_val.json', | ||
| img_prefix=f'{data_root}/', | ||
| data_cfg=data_cfg, | ||
| pipeline=val_pipeline), | ||
| ) |
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
144 changes: 144 additions & 0 deletions
144
configs/top_down/resnet/posetrack18/res50_posetrack18_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 +1,144 @@ | ||
| log_level = 'INFO' | ||
| load_from = 'https://download.openmmlab.com/mmpose/top_down/resnet/res50_coco_256x192-ec54d7f3_20200709.pth' # noqa: E501 | ||
| resume_from = None | ||
| dist_params = dict(backend='nccl') | ||
| workflow = [('train', 1)] | ||
| checkpoint_config = dict(interval=1) | ||
| evaluation = dict(interval=1, metric='mAP', key_indicator='Total 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=[10, 15]) | ||
| total_epochs = 20 | ||
| log_config = dict( | ||
| interval=50, | ||
| hooks=[ | ||
| dict(type='TextLoggerHook'), | ||
| # dict(type='TensorboardLoggerHook') | ||
| ]) | ||
|
|
||
| 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 | ||
| model = dict( | ||
| type='TopDown', | ||
| pretrained=None, | ||
| backbone=dict(type='ResNet', depth=50), | ||
| keypoint_head=dict( | ||
| type='TopDownSimpleHead', | ||
| in_channels=2048, | ||
| out_channels=channel_cfg['num_output_channels'], | ||
| ), | ||
| train_cfg=dict(), | ||
| test_cfg=dict( | ||
| flip_test=True, | ||
| post_process=True, | ||
| shift_heatmap=True, | ||
| unbiased_decoding=False, | ||
| modulate_kernel=11), | ||
| loss_pose=dict(type='JointsMSELoss', use_target_weight=True)) | ||
|
|
||
| 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, | ||
| bbox_thr=1.0, | ||
| use_gt_bbox=True, | ||
| image_thr=0.4, | ||
| bbox_file='data/posetrack18/annotations/' | ||
| 'posetrack18_val_human_detections.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_root = 'data/posetrack18' | ||
| data = dict( | ||
| samples_per_gpu=64, | ||
| workers_per_gpu=2, | ||
| train=dict( | ||
| type='TopDownPoseTrack18Dataset', | ||
| ann_file=f'{data_root}/annotations/posetrack18_train.json', | ||
| img_prefix=f'{data_root}/', | ||
| data_cfg=data_cfg, | ||
| pipeline=train_pipeline), | ||
| val=dict( | ||
| type='TopDownPoseTrack18Dataset', | ||
| ann_file=f'{data_root}/annotations/posetrack18_val.json', | ||
| img_prefix=f'{data_root}/', | ||
| data_cfg=data_cfg, | ||
| pipeline=val_pipeline), | ||
| test=dict( | ||
| type='TopDownPoseTrack18Dataset', | ||
| ann_file=f'{data_root}/annotations/posetrack18_val.json', | ||
| img_prefix=f'{data_root}/', | ||
| data_cfg=data_cfg, | ||
| pipeline=val_pipeline), | ||
| ) |
Oops, something went wrong.